diff options
| author | Ingo Molnar <mingo@elte.hu> | 2009-04-06 07:02:57 (GMT) |
|---|---|---|
| committer | Ingo Molnar <mingo@elte.hu> | 2009-04-06 07:02:57 (GMT) |
| commit | f541ae326fa120fa5c57433e4d9a133df212ce41 (patch) | |
| tree | bdbd94ec72cfc601118051cb35e8617d55510177 /arch/x86 | |
| parent | e255357764f92afcafafbd4879b222b8c752065a (diff) | |
| parent | 0221c81b1b8eb0cbb6b30a0ced52ead32d2b4e4c (diff) | |
| download | linux-f541ae326fa120fa5c57433e4d9a133df212ce41.tar.xz | |
Merge branch 'linus' into perfcounters/core-v2
Merge reason: we have gathered quite a few conflicts, need to merge upstream
Conflicts:
arch/powerpc/kernel/Makefile
arch/x86/ia32/ia32entry.S
arch/x86/include/asm/hardirq.h
arch/x86/include/asm/unistd_32.h
arch/x86/include/asm/unistd_64.h
arch/x86/kernel/cpu/common.c
arch/x86/kernel/irq.c
arch/x86/kernel/syscall_table_32.S
arch/x86/mm/iomap_32.c
include/linux/sched.h
kernel/Makefile
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch/x86')
284 files changed, 13105 insertions, 7546 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e18dfd3..bcf4cae 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -34,12 +34,18 @@ config X86 select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST + select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE + select HAVE_FTRACE_SYSCALLS select HAVE_KVM select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK select HAVE_GENERIC_DMA_COHERENT if X86_32 select HAVE_EFFICIENT_UNALIGNED_ACCESS select USER_STACKTRACE_SUPPORT + select HAVE_DMA_API_DEBUG + select HAVE_KERNEL_GZIP + select HAVE_KERNEL_BZIP2 + select HAVE_KERNEL_LZMA config ARCH_DEFCONFIG string @@ -135,6 +141,9 @@ config ARCH_HAS_CACHE_LINE_SIZE config HAVE_SETUP_PER_CPU_AREA def_bool y +config HAVE_DYNAMIC_PER_CPU_AREA + def_bool y + config HAVE_CPUMASK_OF_CPU_MAP def_bool X86_64_SMP @@ -158,11 +167,17 @@ config AUDIT_ARCH config ARCH_SUPPORTS_OPTIMIZED_INLINING def_bool y +config ARCH_SUPPORTS_DEBUG_PAGEALLOC + def_bool y + # Use the generic interrupt handling code in kernel/irq/: config GENERIC_HARDIRQS bool default y +config GENERIC_HARDIRQS_NO__DO_IRQ + def_bool y + config GENERIC_IRQ_PROBE bool default y @@ -778,6 +793,11 @@ config X86_MCE_AMD Additional support for AMD specific MCE features such as the DRAM Error Threshold. +config X86_MCE_THRESHOLD + depends on X86_MCE_AMD || X86_MCE_INTEL + bool + default y + config X86_MCE_NONFATAL tristate "Check for non-fatal errors on AMD Athlon/Duron / Intel Pentium 4" depends on X86_32 && X86_MCE @@ -921,6 +941,12 @@ config X86_CPUID with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to /dev/cpu/31/cpuid. +config X86_CPU_DEBUG + tristate "/sys/kernel/debug/x86/cpu/* - CPU Debug support" + ---help--- + If you select this option, this will provide various x86 CPUs + information through debugfs. + choice prompt "High Memory Support" default HIGHMEM4G if !X86_NUMAQ @@ -1113,7 +1139,7 @@ config NUMA_EMU config NODES_SHIFT int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP - range 1 9 if X86_64 + range 1 9 default "9" if MAXSMP default "6" if X86_64 default "4" if X86_NUMAQ @@ -1121,9 +1147,9 @@ config NODES_SHIFT depends on NEED_MULTIPLE_NODES ---help--- Specify the maximum number of NUMA Nodes available on the target - system. Increases memory reserved to accomodate various tables. + system. Increases memory reserved to accommodate various tables. -config HAVE_ARCH_BOOTMEM_NODE +config HAVE_ARCH_BOOTMEM def_bool y depends on X86_32 && NUMA @@ -1299,7 +1325,7 @@ config MTRR_SANITIZER add writeback entries. Can be disabled with disable_mtrr_cleanup on the kernel command line. - The largest mtrr entry size for a continous block can be set with + The largest mtrr entry size for a continuous block can be set with mtrr_chunk_size. If unsure, say Y. @@ -1421,7 +1447,7 @@ config CRASH_DUMP config KEXEC_JUMP bool "kexec jump (EXPERIMENTAL)" depends on EXPERIMENTAL - depends on KEXEC && HIBERNATION && X86_32 + depends on KEXEC && HIBERNATION ---help--- Jump between original kernel and kexeced kernel and invoke code in physical address mode via KEXEC @@ -1814,8 +1840,8 @@ config PCI_MMCONFIG config DMAR bool "Support for DMA Remapping Devices (EXPERIMENTAL)" - depends on X86_64 && PCI_MSI && ACPI && EXPERIMENTAL - ---help--- + depends on PCI_MSI && ACPI && EXPERIMENTAL + help DMA remapping (DMAR) devices support enables independent address translations for Direct Memory Access (DMA) from devices. These DMA remapping devices are reported via ACPI tables diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index a95eaf0..924e156 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -456,24 +456,9 @@ config CPU_SUP_AMD If unsure, say N. -config CPU_SUP_CENTAUR_32 +config CPU_SUP_CENTAUR default y bool "Support Centaur processors" if PROCESSOR_SELECT - depends on !64BIT - ---help--- - This enables detection, tunings and quirks for Centaur processors - - You need this enabled if you want your kernel to run on a - Centaur CPU. Disabling this option on other types of CPUs - makes the kernel a tiny bit smaller. Disabling it on a Centaur - CPU might render the kernel unbootable. - - If unsure, say N. - -config CPU_SUP_CENTAUR_64 - default y - bool "Support Centaur processors" if PROCESSOR_SELECT - depends on 64BIT ---help--- This enables detection, tunings and quirks for Centaur processors diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index fdb45df..d8359e7 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -72,14 +72,6 @@ config DEBUG_STACK_USAGE This option will slow down process creation somewhat. -config DEBUG_PAGEALLOC - bool "Debug page memory allocations" - depends on DEBUG_KERNEL - ---help--- - Unmap pages from the kernel linear mapping after free_pages(). - This results in a large slowdown, but helps to find certain types - of memory corruptions. - config DEBUG_PER_CPU_MAPS bool "Debug access to per_cpu maps" depends on DEBUG_KERNEL diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 1836191..f05d8c9 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -153,34 +153,23 @@ endif boot := arch/x86/boot -PHONY += zImage bzImage compressed zlilo bzlilo \ - zdisk bzdisk fdimage fdimage144 fdimage288 isoimage install +BOOT_TARGETS = bzlilo bzdisk fdimage fdimage144 fdimage288 isoimage install + +PHONY += bzImage $(BOOT_TARGETS) # Default kernel to build all: bzImage # KBUILD_IMAGE specify target image being built - KBUILD_IMAGE := $(boot)/bzImage -zImage zlilo zdisk: KBUILD_IMAGE := $(boot)/zImage +KBUILD_IMAGE := $(boot)/bzImage -zImage bzImage: vmlinux +bzImage: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(KBUILD_IMAGE) $(Q)mkdir -p $(objtree)/arch/$(UTS_MACHINE)/boot $(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/$(UTS_MACHINE)/boot/$@ -compressed: zImage - -zlilo bzlilo: vmlinux - $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) zlilo - -zdisk bzdisk: vmlinux - $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) zdisk - -fdimage fdimage144 fdimage288 isoimage: vmlinux - $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) $@ - -install: - $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) install +$(BOOT_TARGETS): vmlinux + $(Q)$(MAKE) $(build)=$(boot) $@ PHONY += vdso_install vdso_install: @@ -205,7 +194,3 @@ define archhelp echo ' FDARGS="..." arguments for the booted kernel' echo ' FDINITRD=file initrd for the booted kernel' endef - -CLEAN_FILES += arch/x86/boot/fdimage \ - arch/x86/boot/image.iso \ - arch/x86/boot/mtools.conf diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index c70eff6..6633b6e 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -6,26 +6,24 @@ # for more details. # # Copyright (C) 1994 by Linus Torvalds +# Changed by many, many contributors over the years. # # ROOT_DEV specifies the default root-device when making the image. # This can be either FLOPPY, CURRENT, /dev/xxxx or empty, in which case # the default of FLOPPY is used by 'build'. -ROOT_DEV := CURRENT +ROOT_DEV := CURRENT # If you want to preset the SVGA mode, uncomment the next line and # set SVGA_MODE to whatever number you want. # Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode. # The number is the same as you would ordinarily press at bootup. -SVGA_MODE := -DSVGA_MODE=NORMAL_VGA +SVGA_MODE := -DSVGA_MODE=NORMAL_VGA -# If you want the RAM disk device, define this to be the size in blocks. - -#RAMDISK := -DRAMDISK=512 - -targets := vmlinux.bin setup.bin setup.elf zImage bzImage +targets := vmlinux.bin setup.bin setup.elf bzImage +targets += fdimage fdimage144 fdimage288 image.iso mtools.conf subdir- := compressed setup-y += a20.o cmdline.o copy.o cpu.o cpucheck.o edd.o @@ -59,6 +57,7 @@ $(obj)/cpustr.h: $(obj)/mkcpustr FORCE # How to compile the 16-bit code. Note we always compile for -march=i386, # that way we can complain to the user if the CPU is insufficient. KBUILD_CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \ + -DDISABLE_BRANCH_PROFILING \ -Wall -Wstrict-prototypes \ -march=i386 -mregparm=3 \ -include $(srctree)/$(src)/code16gcc.h \ @@ -68,20 +67,16 @@ KBUILD_CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \ $(call cc-option, -fno-unit-at-a-time)) \ $(call cc-option, -fno-stack-protector) \ $(call cc-option, -mpreferred-stack-boundary=2) -KBUILD_CFLAGS += $(call cc-option,-m32) +KBUILD_CFLAGS += $(call cc-option, -m32) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ -$(obj)/zImage: asflags-y := $(SVGA_MODE) $(RAMDISK) -$(obj)/bzImage: ccflags-y := -D__BIG_KERNEL__ -$(obj)/bzImage: asflags-y := $(SVGA_MODE) $(RAMDISK) -D__BIG_KERNEL__ -$(obj)/bzImage: BUILDFLAGS := -b +$(obj)/bzImage: asflags-y := $(SVGA_MODE) quiet_cmd_image = BUILD $@ -cmd_image = $(obj)/tools/build $(BUILDFLAGS) $(obj)/setup.bin \ - $(obj)/vmlinux.bin $(ROOT_DEV) > $@ +cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \ + $(ROOT_DEV) > $@ -$(obj)/zImage $(obj)/bzImage: $(obj)/setup.bin \ - $(obj)/vmlinux.bin $(obj)/tools/build FORCE +$(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE $(call if_changed,image) @echo 'Kernel: $@ is ready' ' (#'`cat .version`')' @@ -116,9 +111,11 @@ $(obj)/setup.bin: $(obj)/setup.elf FORCE $(obj)/compressed/vmlinux: FORCE $(Q)$(MAKE) $(build)=$(obj)/compressed $@ -# Set this if you want to pass append arguments to the zdisk/fdimage/isoimage kernel +# Set this if you want to pass append arguments to the +# bzdisk/fdimage/isoimage kernel FDARGS = -# Set this if you want an initrd included with the zdisk/fdimage/isoimage kernel +# Set this if you want an initrd included with the +# bzdisk/fdimage/isoimage kernel FDINITRD = image_cmdline = default linux $(FDARGS) $(if $(FDINITRD),initrd=initrd.img,) @@ -127,7 +124,7 @@ $(obj)/mtools.conf: $(src)/mtools.conf.in sed -e 's|@OBJ@|$(obj)|g' < $< > $@ # This requires write access to /dev/fd0 -zdisk: $(BOOTIMAGE) $(obj)/mtools.conf +bzdisk: $(obj)/bzImage $(obj)/mtools.conf MTOOLSRC=$(obj)/mtools.conf mformat a: ; sync syslinux /dev/fd0 ; sync echo '$(image_cmdline)' | \ @@ -135,10 +132,10 @@ zdisk: $(BOOTIMAGE) $(obj)/mtools.conf if [ -f '$(FDINITRD)' ] ; then \ MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' a:initrd.img ; \ fi - MTOOLSRC=$(obj)/mtools.conf mcopy $(BOOTIMAGE) a:linux ; sync + MTOOLSRC=$(obj)/mtools.conf mcopy $(obj)/bzImage a:linux ; sync # These require being root or having syslinux 2.02 or higher installed -fdimage fdimage144: $(BOOTIMAGE) $(obj)/mtools.conf +fdimage fdimage144: $(obj)/bzImage $(obj)/mtools.conf dd if=/dev/zero of=$(obj)/fdimage bs=1024 count=1440 MTOOLSRC=$(obj)/mtools.conf mformat v: ; sync syslinux $(obj)/fdimage ; sync @@ -147,9 +144,9 @@ fdimage fdimage144: $(BOOTIMAGE) $(obj)/mtools.conf if [ -f '$(FDINITRD)' ] ; then \ MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' v:initrd.img ; \ fi - MTOOLSRC=$(obj)/mtools.conf mcopy $(BOOTIMAGE) v:linux ; sync + MTOOLSRC=$(obj)/mtools.conf mcopy $(obj)/bzImage v:linux ; sync -fdimage288: $(BOOTIMAGE) $(obj)/mtools.conf +fdimage288: $(obj)/bzImage $(obj)/mtools.conf dd if=/dev/zero of=$(obj)/fdimage bs=1024 count=2880 MTOOLSRC=$(obj)/mtools.conf mformat w: ; sync syslinux $(obj)/fdimage ; sync @@ -158,9 +155,9 @@ fdimage288: $(BOOTIMAGE) $(obj)/mtools.conf if [ -f '$(FDINITRD)' ] ; then \ MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' w:initrd.img ; \ fi - MTOOLSRC=$(obj)/mtools.conf mcopy $(BOOTIMAGE) w:linux ; sync + MTOOLSRC=$(obj)/mtools.conf mcopy $(obj)/bzImage w:linux ; sync -isoimage: $(BOOTIMAGE) +isoimage: $(obj)/bzImage -rm -rf $(obj)/isoimage mkdir $(obj)/isoimage for i in lib lib64 share end ; do \ @@ -170,7 +167,7 @@ isoimage: $(BOOTIMAGE) fi ; \ if [ $$i = end ] ; then exit 1 ; fi ; \ done - cp $(BOOTIMAGE) $(obj)/isoimage/linux + cp $(obj)/bzImage $(obj)/isoimage/linux echo '$(image_cmdline)' > $(obj)/isoimage/isolinux.cfg if [ -f '$(FDINITRD)' ] ; then \ cp '$(FDINITRD)' $(obj)/isoimage/initrd.img ; \ @@ -181,12 +178,13 @@ isoimage: $(BOOTIMAGE) isohybrid $(obj)/image.iso 2>/dev/null || true rm -rf $(obj)/isoimage -zlilo: $(BOOTIMAGE) +bzlilo: $(obj)/bzImage if [ -f $(INSTALL_PATH)/vmlinuz ]; then mv $(INSTALL_PATH)/vmlinuz $(INSTALL_PATH)/vmlinuz.old; fi if [ -f $(INSTALL_PATH)/System.map ]; then mv $(INSTALL_PATH)/System.map $(INSTALL_PATH)/System.old; fi - cat $(BOOTIMAGE) > $(INSTALL_PATH)/vmlinuz + cat $(obj)/bzImage > $(INSTALL_PATH)/vmlinuz cp System.map $(INSTALL_PATH)/ if [ -x /sbin/lilo ]; then /sbin/lilo; else /etc/lilo/install; fi install: - sh $(srctree)/$(src)/install.sh $(KERNELRELEASE) $(BOOTIMAGE) System.map "$(INSTALL_PATH)" + sh $(srctree)/$(src)/install.sh $(KERNELRELEASE) $(obj)/bzImage \ + System.map "$(INSTALL_PATH)" diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 1771c80..65551c9 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -4,10 +4,11 @@ # create a compressed vmlinux image from the original vmlinux # -targets := vmlinux vmlinux.bin vmlinux.bin.gz head_$(BITS).o misc.o piggy.o +targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma head_$(BITS).o misc.o piggy.o KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC +KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING cflags-$(CONFIG_X86_64) := -mcmodel=small KBUILD_CFLAGS += $(cflags-y) KBUILD_CFLAGS += $(call cc-option,-ffreestanding) @@ -47,18 +48,35 @@ ifeq ($(CONFIG_X86_32),y) ifdef CONFIG_RELOCATABLE $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin.all FORCE $(call if_changed,gzip) +$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin.all FORCE + $(call if_changed,bzip2) +$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin.all FORCE + $(call if_changed,lzma) else $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE $(call if_changed,gzip) +$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE + $(call if_changed,bzip2) +$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE + $(call if_changed,lzma) endif LDFLAGS_piggy.o := -r --format binary --oformat elf32-i386 -T else + $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE $(call if_changed,gzip) +$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE + $(call if_changed,bzip2) +$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE + $(call if_changed,lzma) LDFLAGS_piggy.o := -r --format binary --oformat elf64-x86-64 -T endif -$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.gz FORCE +suffix_$(CONFIG_KERNEL_GZIP) = gz +suffix_$(CONFIG_KERNEL_BZIP2) = bz2 +suffix_$(CONFIG_KERNEL_LZMA) = lzma + +$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix_y) FORCE $(call if_changed,ld) diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index da06221..e45be73 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -116,71 +116,13 @@ /* * gzip declarations */ - -#define OF(args) args #define STATIC static #undef memset #undef memcpy #define memzero(s, n) memset((s), 0, (n)) -typedef unsigned char uch; -typedef unsigned short ush; -typedef unsigned long ulg; - -/* - * Window size must be at least 32k, and a power of two. - * We don't actually have a window just a huge output buffer, - * so we report a 2G window size, as that should always be - * larger than our output buffer: - */ -#define WSIZE 0x80000000 - -/* Input buffer: */ -static unsigned char *inbuf; - -/* Sliding window buffer (and final output buffer): */ -static unsigned char *window; - -/* Valid bytes in inbuf: */ -static unsigned insize; - -/* Index of next byte to be processed in inbuf: */ -static unsigned inptr; - -/* Bytes in output buffer: */ -static unsigned outcnt; - -/* gzip flag byte */ -#define ASCII_FLAG 0x01 /* bit 0 set: file probably ASCII text */ -#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gz file */ -#define EXTRA_FIELD 0x04 /* bit 2 set: extra field present */ -#define ORIG_NAM 0x08 /* bit 3 set: original file name present */ -#define COMMENT 0x10 /* bit 4 set: file comment present */ -#define ENCRYPTED 0x20 /* bit 5 set: file is encrypted */ -#define RESERVED 0xC0 /* bit 6, 7: reserved */ - -#define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf()) - -/* Diagnostic functions */ -#ifdef DEBUG -# define Assert(cond, msg) do { if (!(cond)) error(msg); } while (0) -# define Trace(x) do { fprintf x; } while (0) -# define Tracev(x) do { if (verbose) fprintf x ; } while (0) -# define Tracevv(x) do { if (verbose > 1) fprintf x ; } while (0) -# define Tracec(c, x) do { if (verbose && (c)) fprintf x ; } while (0) -# define Tracecv(c, x) do { if (verbose > 1 && (c)) fprintf x ; } while (0) -#else -# define Assert(cond, msg) -# define Trace(x) -# define Tracev(x) -# define Tracevv(x) -# define Tracec(c, x) -# define Tracecv(c, x) -#endif -static int fill_inbuf(void); -static void flush_window(void); static void error(char *m); /* @@ -189,13 +131,8 @@ static void error(char *m); static struct boot_params *real_mode; /* Pointer to real-mode data */ static int quiet; -extern unsigned char input_data[]; -extern int input_len; - -static long bytes_out; - static void *memset(void *s, int c, unsigned n); -static void *memcpy(void *dest, const void *src, unsigned n); +void *memcpy(void *dest, const void *src, unsigned n); static void __putstr(int, const char *); #define putstr(__x) __putstr(0, __x) @@ -213,7 +150,17 @@ static char *vidmem; static int vidport; static int lines, cols; -#include "../../../../lib/inflate.c" +#ifdef CONFIG_KERNEL_GZIP +#include "../../../../lib/decompress_inflate.c" +#endif + +#ifdef CONFIG_KERNEL_BZIP2 +#include "../../../../lib/decompress_bunzip2.c" +#endif + +#ifdef CONFIG_KERNEL_LZMA +#include "../../../../lib/decompress_unlzma.c" +#endif static void scroll(void) { @@ -282,7 +229,7 @@ static void *memset(void *s, int c, unsigned n) return s; } -static void *memcpy(void *dest, const void *src, unsigned n) +void *memcpy(void *dest, const void *src, unsigned n) { int i; const char *s = src; @@ -293,38 +240,6 @@ static void *memcpy(void *dest, const void *src, unsigned n) return dest; } -/* =========================================================================== - * Fill the input buffer. This is called only when the buffer is empty - * and at least one byte is really needed. - */ -static int fill_inbuf(void) -{ - error("ran out of input data"); - return 0; -} - -/* =========================================================================== - * Write the output window window[0..outcnt-1] and update crc and bytes_out. - * (Used for the decompressed data only.) - */ -static void flush_window(void) -{ - /* With my window equal to my output buffer - * I only need to compute the crc here. - */ - unsigned long c = crc; /* temporary variable */ - unsigned n; - unsigned char *in, ch; - - in = window; - for (n = 0; n < outcnt; n++) { - ch = *in++; - c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8); - } - crc = c; - bytes_out += (unsigned long)outcnt; - outcnt = 0; -} static void error(char *x) { @@ -407,12 +322,8 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, lines = real_mode->screen_info.orig_video_lines; cols = real_mode->screen_info.orig_video_cols; - window = output; /* Output buffer (Normally at 1M) */ free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; - inbuf = input_data; /* Input buffer */ - insize = input_len; - inptr = 0; #ifdef CONFIG_X86_64 if ((unsigned long)output & (__KERNEL_ALIGN - 1)) @@ -430,10 +341,9 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, #endif #endif - makecrc(); if (!quiet) putstr("\nDecompressing Linux... "); - gunzip(); + decompress(input_data, input_len, NULL, NULL, output, NULL, error); parse_elf(output); if (!quiet) putstr("done.\nBooting the kernel.\n"); diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 7ccff48..5d84d1c 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -24,12 +24,8 @@ #include "boot.h" #include "offsets.h" -SETUPSECTS = 4 /* default nr of setup-sectors */ BOOTSEG = 0x07C0 /* original address of boot-sector */ -SYSSEG = DEF_SYSSEG /* system loaded at 0x10000 (65536) */ -SYSSIZE = DEF_SYSSIZE /* system size: # of 16-byte clicks */ - /* to be loaded */ -ROOT_DEV = 0 /* ROOT_DEV is now written by "build" */ +SYSSEG = 0x1000 /* historical load address >> 4 */ #ifndef SVGA_MODE #define SVGA_MODE ASK_VGA @@ -97,12 +93,12 @@ bugger_off_msg: .section ".header", "a" .globl hdr hdr: -setup_sects: .byte SETUPSECTS +setup_sects: .byte 0 /* Filled in by build.c */ root_flags: .word ROOT_RDONLY -syssize: .long SYSSIZE -ram_size: .word RAMDISK +syssize: .long 0 /* Filled in by build.c */ +ram_size: .word 0 /* Obsolete */ vid_mode: .word SVGA_MODE -root_dev: .word ROOT_DEV +root_dev: .word 0 /* Filled in by build.c */ boot_flag: .word 0xAA55 # offset 512, entry point @@ -123,14 +119,15 @@ _start: # or else old loadlin-1.5 will fail) .globl realmode_swtch realmode_swtch: .word 0, 0 # default_switch, SETUPSEG -start_sys_seg: .word SYSSEG +start_sys_seg: .word SYSSEG # obsolete and meaningless, but just + # in case something decided to "use" it .word kernel_version-512 # pointing to kernel version string # above section of header is compatible # with loadlin-1.5 (header v1.5). Don't # change it. -type_of_loader: .byte 0 # = 0, old one (LILO, Loadlin, - # Bootlin, SYSLX, bootsect...) +type_of_loader: .byte 0 # 0 means ancient bootloader, newer + # bootloaders know to change this. # See Documentation/i386/boot.txt for # assigned ids @@ -142,11 +139,7 @@ CAN_USE_HEAP = 0x80 # If set, the loader also has set # space behind setup.S can be used for # heap purposes. # Only the loader knows what is free -#ifndef __BIG_KERNEL__ - .byte 0 -#else .byte LOADED_HIGH -#endif setup_move_size: .word 0x8000 # size to move, when setup is not # loaded at 0x90000. We will move setup @@ -157,11 +150,7 @@ setup_move_size: .word 0x8000 # size to move, when setup is not code32_start: # here loaders can put a different # start address for 32-bit code. -#ifndef __BIG_KERNEL__ - .long 0x1000 # 0x1000 = default for zImage -#else .long 0x100000 # 0x100000 = default for big kernel -#endif ramdisk_image: .long 0 # address of loaded ramdisk image # Here the loader puts the 32-bit diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c index 8c3c25f..5054c2d 100644 --- a/arch/x86/boot/memory.c +++ b/arch/x86/boot/memory.c @@ -2,6 +2,7 @@ * * Copyright (C) 1991, 1992 Linus Torvalds * Copyright 2007 rPath, Inc. - All Rights Reserved + * Copyright 2009 Intel Corporation; author H. Peter Anvin * * This file is part of the Linux kernel, and is made available under * the terms of the GNU General Public License version 2. @@ -16,24 +17,38 @@ #define SMAP 0x534d4150 /* ASCII "SMAP" */ +struct e820_ext_entry { + struct e820entry std; + u32 ext_flags; +} __attribute__((packed)); + static int detect_memory_e820(void) { int count = 0; u32 next = 0; - u32 size, id; + u32 size, id, edi; u8 err; struct e820entry *desc = boot_params.e820_map; + static struct e820_ext_entry buf; /* static so it is zeroed */ + + /* + * Set this here so that if the BIOS doesn't change this field + * but still doesn't change %ecx, we're still okay... + */ + buf.ext_flags = 1; do { - size = sizeof(struct e820entry); + size = sizeof buf; - /* Important: %edx is clobbered by some BIOSes, - so it must be either used for the error output - or explicitly marked clobbered. */ - asm("int $0x15; setc %0" + /* Important: %edx and %esi are clobbered by some BIOSes, + so they must be either used for the error output + or explicitly marked clobbered. Given that, assume there + is something out there clobbering %ebp and %edi, too. */ + asm("pushl %%ebp; int $0x15; popl %%ebp; setc %0" : "=d" (err), "+b" (next), "=a" (id), "+c" (size), - "=m" (*desc) - : "D" (desc), "d" (SMAP), "a" (0xe820)); + "=D" (edi), "+m" (buf) + : "D" (&buf), "d" (SMAP), "a" (0xe820) + : "esi"); /* BIOSes which terminate the chain with CF = 1 as opposed to %ebx = 0 don't always report the SMAP signature on @@ -51,8 +66,14 @@ static int detect_memory_e820(void) break; } + /* ACPI 3.0 added the extended flags support. If bit 0 + in the extended flags is zero, we're supposed to simply + ignore the entry -- a backwards incompatible change! */ + if (size > 20 && !(buf.ext_flags & 1)) + continue; + + *desc++ = buf.std; count++; - desc++; } while (next && count < ARRAY_SIZE(boot_params.e820_map)); return boot_params.e820_entries = count; diff --git a/arch/x86/boot/pm.c b/arch/x86/boot/pm.c index 85a1cd8..8062f89 100644 --- a/arch/x86/boot/pm.c +++ b/arch/x86/boot/pm.c @@ -33,47 +33,6 @@ static void realmode_switch_hook(void) } /* - * A zImage kernel is loaded at 0x10000 but wants to run at 0x1000. - * A bzImage kernel is loaded and runs at 0x100000. - */ -static void move_kernel_around(void) -{ - /* Note: rely on the compile-time option here rather than - the LOADED_HIGH flag. The Qemu kernel loader unconditionally - sets the loadflags to zero. */ -#ifndef __BIG_KERNEL__ - u16 dst_seg, src_seg; - u32 syssize; - - dst_seg = 0x1000 >> 4; - src_seg = 0x10000 >> 4; - syssize = boot_params.hdr.syssize; /* Size in 16-byte paragraphs */ - - while (syssize) { - int paras = (syssize >= 0x1000) ? 0x1000 : syssize; - int dwords = paras << 2; - - asm volatile("pushw %%es ; " - "pushw %%ds ; " - "movw %1,%%es ; " - "movw %2,%%ds ; " - "xorw %%di,%%di ; " - "xorw %%si,%%si ; " - "rep;movsl ; " - "popw %%ds ; " - "popw %%es" - : "+c" (dwords) - : "r" (dst_seg), "r" (src_seg) - : "esi", "edi"); - - syssize -= paras; - dst_seg += paras; - src_seg += paras; - } -#endif -} - -/* * Disable all interrupts at the legacy PIC. */ static void mask_all_interrupts(void) @@ -147,9 +106,6 @@ void go_to_protected_mode(void) /* Hook before leaving real mode, also disables interrupts */ realmode_switch_hook(); - /* Move the kernel/setup to their final resting places */ - move_kernel_around(); - /* Enable the A20 gate */ if (enable_a20()) { puts("A20 gate not responding, unable to boot...\n"); diff --git a/arch/x86/boot/pmjump.S b/arch/x86/boot/pmjump.S index 019c17a..3e0edc6 100644 --- a/arch/x86/boot/pmjump.S +++ b/arch/x86/boot/pmjump.S @@ -47,6 +47,7 @@ GLOBAL(protected_mode_jump) ENDPROC(protected_mode_jump) .code32 + .section ".text32","ax" GLOBAL(in_pm32) # Set up data segments for flat 32-bit mode movl %ecx, %ds diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index df9234b..bb8dc2d 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -17,7 +17,8 @@ SECTIONS .header : { *(.header) } .inittext : { *(.inittext) } .initdata : { *(.initdata) } - .text : { *(.text*) } + .text : { *(.text) } + .text32 : { *(.text32) } . = ALIGN(16); .rodata : { *(.rodata*) } diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 44dc192..ee3a4ea 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -130,7 +130,7 @@ static void die(const char * str, ...) static void usage(void) { - die("Usage: build [-b] setup system [rootdev] [> image]"); + die("Usage: build setup system [rootdev] [> image]"); } int main(int argc, char ** argv) @@ -145,11 +145,6 @@ int main(int argc, char ** argv) void *kernel; u32 crc = 0xffffffffUL; - if (argc > 2 && !strcmp(argv[1], "-b")) - { - is_big_kernel = 1; - argc--, argv++; - } if ((argc < 3) || (argc > 4)) usage(); if (argc > 3) { @@ -216,8 +211,6 @@ int main(int argc, char ** argv) die("Unable to mmap '%s': %m", argv[2]); /* Number of 16-byte paragraphs, including space for a 4-byte CRC */ sys_size = (sz + 15 + 4) / 16; - if (!is_big_kernel && sys_size > DEF_SYSSIZE) - die("System is too big. Try using bzImage or modules."); /* Patch the setup code with the appropriate size parameters */ buf[0x1f1] = setup_sectors-1; diff --git a/arch/x86/boot/video-vga.c b/arch/x86/boot/video-vga.c index 5d4742e..95d86ce 100644 --- a/arch/x86/boot/video-vga.c +++ b/arch/x86/boot/video-vga.c @@ -129,41 +129,45 @@ u16 vga_crtc(void) return (inb(0x3cc) & 1) ? 0x3d4 : 0x3b4; } -static void vga_set_480_scanlines(int end) +static void vga_set_480_scanlines(int lines) { - u16 crtc; - u8 csel; + u16 crtc; /* CRTC base address */ + u8 csel; /* CRTC miscellaneous output register */ + u8 ovfw; /* CRTC overflow register */ + int end = lines-1; crtc = vga_crtc(); + ovfw = 0x3c | ((end >> (8-1)) & 0x02) | ((end >> (9-6)) & 0x40); + out_idx(0x0c, crtc, 0x11); /* Vertical sync end, unlock CR0-7 */ out_idx(0x0b, crtc, 0x06); /* Vertical total */ - out_idx(0x3e, crtc, 0x07); /* Vertical overflow */ + out_idx(ovfw, crtc, 0x07); /* Vertical overflow */ out_idx(0xea, crtc, 0x10); /* Vertical sync start */ - out_idx(end, crtc, 0x12); /* Vertical display end */ + out_idx(end, crtc, 0x12); /* Vertical display end */ out_idx(0xe7, crtc, 0x15); /* Vertical blank start */ out_idx(0x04, crtc, 0x16); /* Vertical blank end */ csel = inb(0x3cc); csel &= 0x0d; csel |= 0xe2; - outb(csel, 0x3cc); + outb(csel, 0x3c2); } static void vga_set_80x30(void) { - vga_set_480_scanlines(0xdf); + vga_set_480_scanlines(30*16); } static void vga_set_80x34(void) { vga_set_14font(); - vga_set_480_scanlines(0xdb); + vga_set_480_scanlines(34*14); } static void vga_set_80x60(void) { vga_set_8font(); - vga_set_480_scanlines(0xdf); + vga_set_480_scanlines(60*8); } static int vga_set_mode(struct mode_info *mode) diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 903de4a..ebe7dee 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -9,6 +9,7 @@ obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o +obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o @@ -19,3 +20,5 @@ salsa20-i586-y := salsa20-i586-asm_32.o salsa20_glue.o aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o + +aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o diff --git a/arch/x86/crypto/aes-i586-asm_32.S b/arch/x86/crypto/aes-i586-asm_32.S index e41b147..b949ec2 100644 --- a/arch/x86/crypto/aes-i586-asm_32.S +++ b/arch/x86/crypto/aes-i586-asm_32.S @@ -41,14 +41,14 @@ #define tlen 1024 // length of each of 4 'xor' arrays (256 32-bit words) /* offsets to parameters with one register pushed onto stack */ -#define tfm 8 +#define ctx 8 #define out_blk 12 #define in_blk 16 -/* offsets in crypto_tfm structure */ -#define klen (crypto_tfm_ctx_offset + 0) -#define ekey (crypto_tfm_ctx_offset + 4) -#define dkey (crypto_tfm_ctx_offset + 244) +/* offsets in crypto_aes_ctx structure */ +#define klen (480) +#define ekey (0) +#define dkey (240) // register mapping for encrypt and decrypt subroutines @@ -217,7 +217,7 @@ do_col (table, r5,r0,r1,r4, r2,r3); /* idx=r5 */ // AES (Rijndael) Encryption Subroutine -/* void aes_enc_blk(struct crypto_tfm *tfm, u8 *out_blk, const u8 *in_blk) */ +/* void aes_enc_blk(struct crypto_aes_ctx *ctx, u8 *out_blk, const u8 *in_blk) */ .global aes_enc_blk @@ -228,7 +228,7 @@ aes_enc_blk: push %ebp - mov tfm(%esp),%ebp + mov ctx(%esp),%ebp // CAUTION: the order and the values used in these assigns // rely on the register mappings @@ -292,7 +292,7 @@ aes_enc_blk: ret // AES (Rijndael) Decryption Subroutine -/* void aes_dec_blk(struct crypto_tfm *tfm, u8 *out_blk, const u8 *in_blk) */ +/* void aes_dec_blk(struct crypto_aes_ctx *ctx, u8 *out_blk, const u8 *in_blk) */ .global aes_dec_blk @@ -303,7 +303,7 @@ aes_enc_blk: aes_dec_blk: push %ebp - mov tfm(%esp),%ebp + mov ctx(%esp),%ebp // CAUTION: the order and the values used in these assigns // rely on the register mappings diff --git a/arch/x86/crypto/aes-x86_64-asm_64.S b/arch/x86/crypto/aes-x86_64-asm_64.S index a120f52..5b577d5 100644 --- a/arch/x86/crypto/aes-x86_64-asm_64.S +++ b/arch/x86/crypto/aes-x86_64-asm_64.S @@ -17,8 +17,6 @@ #include <asm/asm-offsets.h> -#define BASE crypto_tfm_ctx_offset - #define R1 %rax #define R1E %eax #define R1X %ax @@ -56,13 +54,13 @@ .align 8; \ FUNC: movq r1,r2; \ movq r3,r4; \ - leaq BASE+KEY+48+4(r8),r9; \ + leaq KEY+48(r8),r9; \ movq r10,r11; \ movl (r7),r5 ## E; \ movl 4(r7),r1 ## E; \ movl 8(r7),r6 ## E; \ movl 12(r7),r7 ## E; \ - movl BASE+0(r8),r10 ## E; \ + movl 480(r8),r10 ## E; \ xorl -48(r9),r5 ## E; \ xorl -44(r9),r1 ## E; \ xorl -40(r9),r6 ## E; \ diff --git a/arch/x86/crypto/aes_glue.c b/arch/x86/crypto/aes_glue.c index 71f4578..49ae9fe 100644 --- a/arch/x86/crypto/aes_glue.c +++ b/arch/x86/crypto/aes_glue.c @@ -5,17 +5,29 @@ #include <crypto/aes.h> -asmlinkage void aes_enc_blk(struct crypto_tfm *tfm, u8 *out, const u8 *in); -asmlinkage void aes_dec_blk(struct crypto_tfm *tfm, u8 *out, const u8 *in); +asmlinkage void aes_enc_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in); +asmlinkage void aes_dec_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in); + +void crypto_aes_encrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) +{ + aes_enc_blk(ctx, dst, src); +} +EXPORT_SYMBOL_GPL(crypto_aes_encrypt_x86); + +void crypto_aes_decrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) +{ + aes_dec_blk(ctx, dst, src); +} +EXPORT_SYMBOL_GPL(crypto_aes_decrypt_x86); static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { - aes_enc_blk(tfm, dst, src); + aes_enc_blk(crypto_tfm_ctx(tfm), dst, src); } static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { - aes_dec_blk(tfm, dst, src); + aes_dec_blk(crypto_tfm_ctx(tfm), dst, src); } static struct crypto_alg aes_alg = { diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S new file mode 100644 index 0000000..caba996 --- /dev/null +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -0,0 +1,896 @@ +/* + * Implement AES algorithm in Intel AES-NI instructions. + * + * The white paper of AES-NI instructions can be downloaded from: + * http://softwarecommunity.intel.com/isn/downloads/intelavx/AES-Instructions-Set_WP.pdf + * + * Copyright (C) 2008, Intel Corp. + * Author: Huang Ying <ying.huang@intel.com> + * Vinodh Gopal <vinodh.gopal@intel.com> + * Kahraman Akdemir + * + * 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/linkage.h> + +.text + +#define STATE1 %xmm0 +#define STATE2 %xmm4 +#define STATE3 %xmm5 +#define STATE4 %xmm6 +#define STATE STATE1 +#define IN1 %xmm1 +#define IN2 %xmm7 +#define IN3 %xmm8 +#define IN4 %xmm9 +#define IN IN1 +#define KEY %xmm2 +#define IV %xmm3 + +#define KEYP %rdi +#define OUTP %rsi +#define INP %rdx +#define LEN %rcx +#define IVP %r8 +#define KLEN %r9d +#define T1 %r10 +#define TKEYP T1 +#define T2 %r11 + +_key_expansion_128: +_key_expansion_256a: + pshufd $0b11111111, %xmm1, %xmm1 + shufps $0b00010000, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + shufps $0b10001100, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + pxor %xmm1, %xmm0 + movaps %xmm0, (%rcx) + add $0x10, %rcx + ret + +_key_expansion_192a: + pshufd $0b01010101, %xmm1, %xmm1 + shufps $0b00010000, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + shufps $0b10001100, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + pxor %xmm1, %xmm0 + + movaps %xmm2, %xmm5 + movaps %xmm2, %xmm6 + pslldq $4, %xmm5 + pshufd $0b11111111, %xmm0, %xmm3 + pxor %xmm3, %xmm2 + pxor %xmm5, %xmm2 + + movaps %xmm0, %xmm1 + shufps $0b01000100, %xmm0, %xmm6 + movaps %xmm6, (%rcx) + shufps $0b01001110, %xmm2, %xmm1 + movaps %xmm1, 16(%rcx) + add $0x20, %rcx + ret + +_key_expansion_192b: + pshufd $0b01010101, %xmm1, %xmm1 + shufps $0b00010000, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + shufps $0b10001100, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + pxor %xmm1, %xmm0 + + movaps %xmm2, %xmm5 + pslldq $4, %xmm5 + pshufd $0b11111111, %xmm0, %xmm3 + pxor %xmm3, %xmm2 + pxor %xmm5, %xmm2 + + movaps %xmm0, (%rcx) + add $0x10, %rcx + ret + +_key_expansion_256b: + pshufd $0b10101010, %xmm1, %xmm1 + shufps $0b00010000, %xmm2, %xmm4 + pxor %xmm4, %xmm2 + shufps $0b10001100, %xmm2, %xmm4 + pxor %xmm4, %xmm2 + pxor %xmm1, %xmm2 + movaps %xmm2, (%rcx) + add $0x10, %rcx + ret + +/* + * int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key, + * unsigned int key_len) + */ +ENTRY(aesni_set_key) + movups (%rsi), %xmm0 # user key (first 16 bytes) + movaps %xmm0, (%rdi) + lea 0x10(%rdi), %rcx # key addr + movl %edx, 480(%rdi) + pxor %xmm4, %xmm4 # xmm4 is assumed 0 in _key_expansion_x + cmp $24, %dl + jb .Lenc_key128 + je .Lenc_key192 + movups 0x10(%rsi), %xmm2 # other user key + movaps %xmm2, (%rcx) + add $0x10, %rcx + # aeskeygenassist $0x1, %xmm2, %xmm1 # round 1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x01 + call _key_expansion_256a + # aeskeygenassist $0x1, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x01 + call _key_expansion_256b + # aeskeygenassist $0x2, %xmm2, %xmm1 # round 2 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x02 + call _key_expansion_256a + # aeskeygenassist $0x2, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x02 + call _key_expansion_256b + # aeskeygenassist $0x4, %xmm2, %xmm1 # round 3 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x04 + call _key_expansion_256a + # aeskeygenassist $0x4, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x04 + call _key_expansion_256b + # aeskeygenassist $0x8, %xmm2, %xmm1 # round 4 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x08 + call _key_expansion_256a + # aeskeygenassist $0x8, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x08 + call _key_expansion_256b + # aeskeygenassist $0x10, %xmm2, %xmm1 # round 5 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x10 + call _key_expansion_256a + # aeskeygenassist $0x10, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x10 + call _key_expansion_256b + # aeskeygenassist $0x20, %xmm2, %xmm1 # round 6 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x20 + call _key_expansion_256a + # aeskeygenassist $0x20, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x20 + call _key_expansion_256b + # aeskeygenassist $0x40, %xmm2, %xmm1 # round 7 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x40 + call _key_expansion_256a + jmp .Ldec_key +.Lenc_key192: + movq 0x10(%rsi), %xmm2 # other user key + # aeskeygenassist $0x1, %xmm2, %xmm1 # round 1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x01 + call _key_expansion_192a + # aeskeygenassist $0x2, %xmm2, %xmm1 # round 2 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x02 + call _key_expansion_192b + # aeskeygenassist $0x4, %xmm2, %xmm1 # round 3 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x04 + call _key_expansion_192a + # aeskeygenassist $0x8, %xmm2, %xmm1 # round 4 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x08 + call _key_expansion_192b + # aeskeygenassist $0x10, %xmm2, %xmm1 # round 5 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x10 + call _key_expansion_192a + # aeskeygenassist $0x20, %xmm2, %xmm1 # round 6 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x20 + call _key_expansion_192b + # aeskeygenassist $0x40, %xmm2, %xmm1 # round 7 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x40 + call _key_expansion_192a + # aeskeygenassist $0x80, %xmm2, %xmm1 # round 8 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x80 + call _key_expansion_192b + jmp .Ldec_key +.Lenc_key128: + # aeskeygenassist $0x1, %xmm0, %xmm1 # round 1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x01 + call _key_expansion_128 + # aeskeygenassist $0x2, %xmm0, %xmm1 # round 2 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x02 + call _key_expansion_128 + # aeskeygenassist $0x4, %xmm0, %xmm1 # round 3 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x04 + call _key_expansion_128 + # aeskeygenassist $0x8, %xmm0, %xmm1 # round 4 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x08 + call _key_expansion_128 + # aeskeygenassist $0x10, %xmm0, %xmm1 # round 5 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x10 + call _key_expansion_128 + # aeskeygenassist $0x20, %xmm0, %xmm1 # round 6 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x20 + call _key_expansion_128 + # aeskeygenassist $0x40, %xmm0, %xmm1 # round 7 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x40 + call _key_expansion_128 + # aeskeygenassist $0x80, %xmm0, %xmm1 # round 8 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x80 + call _key_expansion_128 + # aeskeygenassist $0x1b, %xmm0, %xmm1 # round 9 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x1b + call _key_expansion_128 + # aeskeygenassist $0x36, %xmm0, %xmm1 # round 10 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x36 + call _key_expansion_128 +.Ldec_key: + sub $0x10, %rcx + movaps (%rdi), %xmm0 + movaps (%rcx), %xmm1 + movaps %xmm0, 240(%rcx) + movaps %xmm1, 240(%rdi) + add $0x10, %rdi + lea 240-16(%rcx), %rsi +.align 4 +.Ldec_key_loop: + movaps (%rdi), %xmm0 + # aesimc %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x38, 0xdb, 0xc8 + movaps %xmm1, (%rsi) + add $0x10, %rdi + sub $0x10, %rsi + cmp %rcx, %rdi + jb .Ldec_key_loop + xor %rax, %rax + ret + +/* + * void aesni_enc(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) + */ +ENTRY(aesni_enc) + movl 480(KEYP), KLEN # key length + movups (INP), STATE # input + call _aesni_enc1 + movups STATE, (OUTP) # output + ret + +/* + * _aesni_enc1: internal ABI + * input: + * KEYP: key struct pointer + * KLEN: round count + * STATE: initial state (input) + * output: + * STATE: finial state (output) + * changed: + * KEY + * TKEYP (T1) + */ +_aesni_enc1: + movaps (KEYP), KEY # key + mov KEYP, TKEYP + pxor KEY, STATE # round 0 + add $0x30, TKEYP + cmp $24, KLEN + jb .Lenc128 + lea 0x20(TKEYP), TKEYP + je .Lenc192 + add $0x20, TKEYP + movaps -0x60(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps -0x50(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 +.align 4 +.Lenc192: + movaps -0x40(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps -0x30(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 +.align 4 +.Lenc128: + movaps -0x20(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps -0x10(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps (TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x10(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x20(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x30(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x40(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x50(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x60(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x70(TKEYP), KEY + # aesenclast KEY, STATE # last round + .byte 0x66, 0x0f, 0x38, 0xdd, 0xc2 + ret + +/* + * _aesni_enc4: internal ABI + * input: + * KEYP: key struct pointer + * KLEN: round count + * STATE1: initial state (input) + * STATE2 + * STATE3 + * STATE4 + * output: + * STATE1: finial state (output) + * STATE2 + * STATE3 + * STATE4 + * changed: + * KEY + * TKEYP (T1) + */ +_aesni_enc4: + movaps (KEYP), KEY # key + mov KEYP, TKEYP + pxor KEY, STATE1 # round 0 + pxor KEY, STATE2 + pxor KEY, STATE3 + pxor KEY, STATE4 + add $0x30, TKEYP + cmp $24, KLEN + jb .L4enc128 + lea 0x20(TKEYP), TKEYP + je .L4enc192 + add $0x20, TKEYP + movaps -0x60(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps -0x50(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 +#.align 4 +.L4enc192: + movaps -0x40(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps -0x30(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 +#.align 4 +.L4enc128: + movaps -0x20(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps -0x10(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps (TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps 0x10(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps 0x20(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps 0x30(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps 0x40(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps 0x50(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps 0x60(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps 0x70(TKEYP), KEY + # aesenclast KEY, STATE1 # last round + .byte 0x66, 0x0f, 0x38, 0xdd, 0xc2 + # aesenclast KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdd, 0xe2 + # aesenclast KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdd, 0xea + # aesenclast KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdd, 0xf2 + ret + +/* + * void aesni_dec (struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) + */ +ENTRY(aesni_dec) + mov 480(KEYP), KLEN # key length + add $240, KEYP + movups (INP), STATE # input + call _aesni_dec1 + movups STATE, (OUTP) #output + ret + +/* + * _aesni_dec1: internal ABI + * input: + * KEYP: key struct pointer + * KLEN: key length + * STATE: initial state (input) + * output: + * STATE: finial state (output) + * changed: + * KEY + * TKEYP (T1) + */ +_aesni_dec1: + movaps (KEYP), KEY # key + mov KEYP, TKEYP + pxor KEY, STATE # round 0 + add $0x30, TKEYP + cmp $24, KLEN + jb .Ldec128 + lea 0x20(TKEYP), TKEYP + je .Ldec192 + add $0x20, TKEYP + movaps -0x60(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps -0x50(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 +.align 4 +.Ldec192: + movaps -0x40(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps -0x30(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 +.align 4 +.Ldec128: + movaps -0x20(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps -0x10(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps (TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x10(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x20(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x30(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x40(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x50(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x60(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x70(TKEYP), KEY + # aesdeclast KEY, STATE # last round + .byte 0x66, 0x0f, 0x38, 0xdf, 0xc2 + ret + +/* + * _aesni_dec4: internal ABI + * input: + * KEYP: key struct pointer + * KLEN: key length + * STATE1: initial state (input) + * STATE2 + * STATE3 + * STATE4 + * output: + * STATE1: finial state (output) + * STATE2 + * STATE3 + * STATE4 + * changed: + * KEY + * TKEYP (T1) + */ +_aesni_dec4: + movaps (KEYP), KEY # key + mov KEYP, TKEYP + pxor KEY, STATE1 # round 0 + pxor KEY, STATE2 + pxor KEY, STATE3 + pxor KEY, STATE4 + add $0x30, TKEYP + cmp $24, KLEN + jb .L4dec128 + lea 0x20(TKEYP), TKEYP + je .L4dec192 + add $0x20, TKEYP + movaps -0x60(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps -0x50(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 +.align 4 +.L4dec192: + movaps -0x40(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps -0x30(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 +.align 4 +.L4dec128: + movaps -0x20(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps -0x10(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps (TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps 0x10(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps 0x20(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps 0x30(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps 0x40(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps 0x50(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps 0x60(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps 0x70(TKEYP), KEY + # aesdeclast KEY, STATE1 # last round + .byte 0x66, 0x0f, 0x38, 0xdf, 0xc2 + # aesdeclast KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdf, 0xe2 + # aesdeclast KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdf, 0xea + # aesdeclast KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdf, 0xf2 + ret + +/* + * void aesni_ecb_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, + * size_t len) + */ +ENTRY(aesni_ecb_enc) + test LEN, LEN # check length + jz .Lecb_enc_ret + mov 480(KEYP), KLEN + cmp $16, LEN + jb .Lecb_enc_ret + cmp $64, LEN + jb .Lecb_enc_loop1 +.align 4 +.Lecb_enc_loop4: + movups (INP), STATE1 + movups 0x10(INP), STATE2 + movups 0x20(INP), STATE3 + movups 0x30(INP), STATE4 + call _aesni_enc4 + movups STATE1, (OUTP) + movups STATE2, 0x10(OUTP) + movups STATE3, 0x20(OUTP) + movups STATE4, 0x30(OUTP) + sub $64, LEN + add $64, INP + add $64, OUTP + cmp $64, LEN + jge .Lecb_enc_loop4 + cmp $16, LEN + jb .Lecb_enc_ret +.align 4 +.Lecb_enc_loop1: + movups (INP), STATE1 + call _aesni_enc1 + movups STATE1, (OUTP) + sub $16, LEN + add $16, INP + add $16, OUTP + cmp $16, LEN + jge .Lecb_enc_loop1 +.Lecb_enc_ret: + ret + +/* + * void aesni_ecb_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, + * size_t len); + */ +ENTRY(aesni_ecb_dec) + test LEN, LEN + jz .Lecb_dec_ret + mov 480(KEYP), KLEN + add $240, KEYP + cmp $16, LEN + jb .Lecb_dec_ret + cmp $64, LEN + jb .Lecb_dec_loop1 +.align 4 +.Lecb_dec_loop4: + movups (INP), STATE1 + movups 0x10(INP), STATE2 + movups 0x20(INP), STATE3 + movups 0x30(INP), STATE4 + call _aesni_dec4 + movups STATE1, (OUTP) + movups STATE2, 0x10(OUTP) + movups STATE3, 0x20(OUTP) + movups STATE4, 0x30(OUTP) + sub $64, LEN + add $64, INP + add $64, OUTP + cmp $64, LEN + jge .Lecb_dec_loop4 + cmp $16, LEN + jb .Lecb_dec_ret +.align 4 +.Lecb_dec_loop1: + movups (INP), STATE1 + call _aesni_dec1 + movups STATE1, (OUTP) + sub $16, LEN + add $16, INP + add $16, OUTP + cmp $16, LEN + jge .Lecb_dec_loop1 +.Lecb_dec_ret: + ret + +/* + * void aesni_cbc_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, + * size_t len, u8 *iv) + */ +ENTRY(aesni_cbc_enc) + cmp $16, LEN + jb .Lcbc_enc_ret + mov 480(KEYP), KLEN + movups (IVP), STATE # load iv as initial state +.align 4 +.Lcbc_enc_loop: + movups (INP), IN # load input + pxor IN, STATE + call _aesni_enc1 + movups STATE, (OUTP) # store output + sub $16, LEN + add $16, INP + add $16, OUTP + cmp $16, LEN + jge .Lcbc_enc_loop + movups STATE, (IVP) +.Lcbc_enc_ret: + ret + +/* + * void aesni_cbc_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, + * size_t len, u8 *iv) + */ +ENTRY(aesni_cbc_dec) + cmp $16, LEN + jb .Lcbc_dec_ret + mov 480(KEYP), KLEN + add $240, KEYP + movups (IVP), IV + cmp $64, LEN + jb .Lcbc_dec_loop1 +.align 4 +.Lcbc_dec_loop4: + movups (INP), IN1 + movaps IN1, STATE1 + movups 0x10(INP), IN2 + movaps IN2, STATE2 + movups 0x20(INP), IN3 + movaps IN3, STATE3 + movups 0x30(INP), IN4 + movaps IN4, STATE4 + call _aesni_dec4 + pxor IV, STATE1 + pxor IN1, STATE2 + pxor IN2, STATE3 + pxor IN3, STATE4 + movaps IN4, IV + movups STATE1, (OUTP) + movups STATE2, 0x10(OUTP) + movups STATE3, 0x20(OUTP) + movups STATE4, 0x30(OUTP) + sub $64, LEN + add $64, INP + add $64, OUTP + cmp $64, LEN + jge .Lcbc_dec_loop4 + cmp $16, LEN + jb .Lcbc_dec_ret +.align 4 +.Lcbc_dec_loop1: + movups (INP), IN + movaps IN, STATE + call _aesni_dec1 + pxor IV, STATE + movups STATE, (OUTP) + movaps IN, IV + sub $16, LEN + add $16, INP + add $16, OUTP + cmp $16, LEN + jge .Lcbc_dec_loop1 + movups IV, (IVP) +.Lcbc_dec_ret: + ret diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c new file mode 100644 index 0000000..02af0af --- /dev/null +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -0,0 +1,461 @@ +/* + * Support for Intel AES-NI instructions. This file contains glue + * code, the real AES implementation is in intel-aes_asm.S. + * + * Copyright (C) 2008, Intel Corp. + * Author: Huang Ying <ying.huang@intel.com> + * + * 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/hardirq.h> +#include <linux/types.h> +#include <linux/crypto.h> +#include <linux/err.h> +#include <crypto/algapi.h> +#include <crypto/aes.h> +#include <crypto/cryptd.h> +#include <asm/i387.h> +#include <asm/aes.h> + +struct async_aes_ctx { + struct cryptd_ablkcipher *cryptd_tfm; +}; + +#define AESNI_ALIGN 16 +#define AES_BLOCK_MASK (~(AES_BLOCK_SIZE-1)) + +asmlinkage int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key, + unsigned int key_len); +asmlinkage void aesni_enc(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in); +asmlinkage void aesni_dec(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in); +asmlinkage void aesni_ecb_enc(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len); +asmlinkage void aesni_ecb_dec(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len); +asmlinkage void aesni_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len, u8 *iv); +asmlinkage void aesni_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len, u8 *iv); + +static inline int kernel_fpu_using(void) +{ + if (in_interrupt() && !(read_cr0() & X86_CR0_TS)) + return 1; + return 0; +} + +static inline struct crypto_aes_ctx *aes_ctx(void *raw_ctx) +{ + unsigned long addr = (unsigned long)raw_ctx; + unsigned long align = AESNI_ALIGN; + + if (align <= crypto_tfm_ctx_alignment()) + align = 1; + return (struct crypto_aes_ctx *)ALIGN(addr, align); +} + +static int aes_set_key_common(struct crypto_tfm *tfm, void *raw_ctx, + const u8 *in_key, unsigned int key_len) +{ + struct crypto_aes_ctx *ctx = aes_ctx(raw_ctx); + u32 *flags = &tfm->crt_flags; + int err; + + if (key_len != AES_KEYSIZE_128 && key_len != AES_KEYSIZE_192 && + key_len != AES_KEYSIZE_256) { + *flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + return -EINVAL; + } + + if (kernel_fpu_using()) + err = crypto_aes_expand_key(ctx, in_key, key_len); + else { + kernel_fpu_begin(); + err = aesni_set_key(ctx, in_key, key_len); + kernel_fpu_end(); + } + + return err; +} + +static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, + unsigned int key_len) +{ + return aes_set_key_common(tfm, crypto_tfm_ctx(tfm), in_key, key_len); +} + +static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm)); + + if (kernel_fpu_using()) + crypto_aes_encrypt_x86(ctx, dst, src); + else { + kernel_fpu_begin(); + aesni_enc(ctx, dst, src); + kernel_fpu_end(); + } +} + +static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm)); + + if (kernel_fpu_using()) + crypto_aes_decrypt_x86(ctx, dst, src); + else { + kernel_fpu_begin(); + aesni_dec(ctx, dst, src); + kernel_fpu_end(); + } +} + +static struct crypto_alg aesni_alg = { + .cra_name = "aes", + .cra_driver_name = "aes-aesni", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_CIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx)+AESNI_ALIGN-1, + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(aesni_alg.cra_list), + .cra_u = { + .cipher = { + .cia_min_keysize = AES_MIN_KEY_SIZE, + .cia_max_keysize = AES_MAX_KEY_SIZE, + .cia_setkey = aes_set_key, + .cia_encrypt = aes_encrypt, + .cia_decrypt = aes_decrypt + } + } +}; + +static int ecb_encrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_blkcipher_ctx(desc->tfm)); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { + aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + kernel_fpu_end(); + + return err; +} + +static int ecb_decrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_blkcipher_ctx(desc->tfm)); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { + aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + kernel_fpu_end(); + + return err; +} + +static struct crypto_alg blk_ecb_alg = { + .cra_name = "__ecb-aes-aesni", + .cra_driver_name = "__driver-ecb-aes-aesni", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx)+AESNI_ALIGN-1, + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(blk_ecb_alg.cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = aes_set_key, + .encrypt = ecb_encrypt, + .decrypt = ecb_decrypt, + }, + }, +}; + +static int cbc_encrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_blkcipher_ctx(desc->tfm)); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { + aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + kernel_fpu_end(); + + return err; +} + +static int cbc_decrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_blkcipher_ctx(desc->tfm)); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { + aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + kernel_fpu_end(); + + return err; +} + +static struct crypto_alg blk_cbc_alg = { + .cra_name = "__cbc-aes-aesni", + .cra_driver_name = "__driver-cbc-aes-aesni", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx)+AESNI_ALIGN-1, + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(blk_cbc_alg.cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = aes_set_key, + .encrypt = cbc_encrypt, + .decrypt = cbc_decrypt, + }, + }, +}; + +static int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key, + unsigned int key_len) +{ + struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm); + + return crypto_ablkcipher_setkey(&ctx->cryptd_tfm->base, key, key_len); +} + +static int ablk_encrypt(struct ablkcipher_request *req) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm); + + if (kernel_fpu_using()) { + struct ablkcipher_request *cryptd_req = + ablkcipher_request_ctx(req); + memcpy(cryptd_req, req, sizeof(*req)); + ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); + return crypto_ablkcipher_encrypt(cryptd_req); + } else { + struct blkcipher_desc desc; + desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm); + desc.info = req->info; + desc.flags = 0; + return crypto_blkcipher_crt(desc.tfm)->encrypt( + &desc, req->dst, req->src, req->nbytes); + } +} + +static int ablk_decrypt(struct ablkcipher_request *req) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm); + + if (kernel_fpu_using()) { + struct ablkcipher_request *cryptd_req = + ablkcipher_request_ctx(req); + memcpy(cryptd_req, req, sizeof(*req)); + ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); + return crypto_ablkcipher_decrypt(cryptd_req); + } else { + struct blkcipher_desc desc; + desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm); + desc.info = req->info; + desc.flags = 0; + return crypto_blkcipher_crt(desc.tfm)->decrypt( + &desc, req->dst, req->src, req->nbytes); + } +} + +static void ablk_exit(struct crypto_tfm *tfm) +{ + struct async_aes_ctx *ctx = crypto_tfm_ctx(tfm); + + cryptd_free_ablkcipher(ctx->cryptd_tfm); +} + +static void ablk_init_common(struct crypto_tfm *tfm, + struct cryptd_ablkcipher *cryptd_tfm) +{ + struct async_aes_ctx *ctx = crypto_tfm_ctx(tfm); + + ctx->cryptd_tfm = cryptd_tfm; + tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) + + crypto_ablkcipher_reqsize(&cryptd_tfm->base); +} + +static int ablk_ecb_init(struct crypto_tfm *tfm) +{ + struct cryptd_ablkcipher *cryptd_tfm; + + cryptd_tfm = cryptd_alloc_ablkcipher("__driver-ecb-aes-aesni", 0, 0); + if (IS_ERR(cryptd_tfm)) + return PTR_ERR(cryptd_tfm); + ablk_init_common(tfm, cryptd_tfm); + return 0; +} + +static struct crypto_alg ablk_ecb_alg = { + .cra_name = "ecb(aes)", + .cra_driver_name = "ecb-aes-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct async_aes_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(ablk_ecb_alg.cra_list), + .cra_init = ablk_ecb_init, + .cra_exit = ablk_exit, + .cra_u = { + .ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + }, + }, +}; + +static int ablk_cbc_init(struct crypto_tfm *tfm) +{ + struct cryptd_ablkcipher *cryptd_tfm; + + cryptd_tfm = cryptd_alloc_ablkcipher("__driver-cbc-aes-aesni", 0, 0); + if (IS_ERR(cryptd_tfm)) + return PTR_ERR(cryptd_tfm); + ablk_init_common(tfm, cryptd_tfm); + return 0; +} + +static struct crypto_alg ablk_cbc_alg = { + .cra_name = "cbc(aes)", + .cra_driver_name = "cbc-aes-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct async_aes_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(ablk_cbc_alg.cra_list), + .cra_init = ablk_cbc_init, + .cra_exit = ablk_exit, + .cra_u = { + .ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + }, + }, +}; + +static int __init aesni_init(void) +{ + int err; + + if (!cpu_has_aes) { + printk(KERN_ERR "Intel AES-NI instructions are not detected.\n"); + return -ENODEV; + } + if ((err = crypto_register_alg(&aesni_alg))) + goto aes_err; + if ((err = crypto_register_alg(&blk_ecb_alg))) + goto blk_ecb_err; + if ((err = crypto_register_alg(&blk_cbc_alg))) + goto blk_cbc_err; + if ((err = crypto_register_alg(&ablk_ecb_alg))) + goto ablk_ecb_err; + if ((err = crypto_register_alg(&ablk_cbc_alg))) + goto ablk_cbc_err; + + return err; + +ablk_cbc_err: + crypto_unregister_alg(&ablk_ecb_alg); +ablk_ecb_err: + crypto_unregister_alg(&blk_cbc_alg); +blk_cbc_err: + crypto_unregister_alg(&blk_ecb_alg); +blk_ecb_err: + crypto_unregister_alg(&aesni_alg); +aes_err: + return err; +} + +static void __exit aesni_exit(void) +{ + crypto_unregister_alg(&ablk_cbc_alg); + crypto_unregister_alg(&ablk_ecb_alg); + crypto_unregister_alg(&blk_cbc_alg); + crypto_unregister_alg(&blk_ecb_alg); + crypto_unregister_alg(&aesni_alg); +} + +module_init(aesni_init); +module_exit(aesni_exit); + +MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("aes"); diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index e4baa06..19c61ef 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -557,7 +557,7 @@ ia32_sys_call_table: .quad sys32_olduname .quad sys_umask /* 60 */ .quad sys_chroot - .quad sys32_ustat + .quad compat_sys_ustat .quad sys_dup2 .quad sys_getppid .quad sys_getpgrp /* 65 */ @@ -828,5 +828,7 @@ ia32_sys_call_table: .quad sys_dup3 /* 330 */ .quad sys_pipe2 .quad sys_inotify_init1 + .quad compat_sys_preadv + .quad compat_sys_pwritev .quad sys_perf_counter_open ia32_syscall_end: diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 6c0d7f6..efac92f 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -638,28 +638,6 @@ long sys32_uname(struct old_utsname __user *name) return err ? -EFAULT : 0; } -long sys32_ustat(unsigned dev, struct ustat32 __user *u32p) -{ - struct ustat u; - mm_segment_t seg; - int ret; - - seg = get_fs(); - set_fs(KERNEL_DS); - ret = sys_ustat(dev, (struct ustat __user *)&u); - set_fs(seg); - if (ret < 0) - return ret; - - if (!access_ok(VERIFY_WRITE, u32p, sizeof(struct ustat32)) || - __put_user((__u32) u.f_tfree, &u32p->f_tfree) || - __put_user((__u32) u.f_tinode, &u32p->f_tfree) || - __copy_to_user(&u32p->f_fname, u.f_fname, sizeof(u.f_fname)) || - __copy_to_user(&u32p->f_fpack, u.f_fpack, sizeof(u.f_fpack))) - ret = -EFAULT; - return ret; -} - asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv, compat_uptr_t __user *envp, struct pt_regs *regs) { diff --git a/arch/x86/include/asm/aes.h b/arch/x86/include/asm/aes.h new file mode 100644 index 0000000..80545a1 --- /dev/null +++ b/arch/x86/include/asm/aes.h @@ -0,0 +1,11 @@ +#ifndef ASM_X86_AES_H +#define ASM_X86_AES_H + +#include <linux/crypto.h> +#include <crypto/aes.h> + +void crypto_aes_encrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, + const u8 *src); +void crypto_aes_decrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, + const u8 *src); +#endif diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index a6208dc..df8a300 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -75,7 +75,14 @@ static inline void default_inquire_remote_apic(int apicid) #define setup_secondary_clock setup_secondary_APIC_clock #endif +#ifdef CONFIG_X86_64 extern int is_vsmp_box(void); +#else +static inline int is_vsmp_box(void) +{ + return 0; +} +#endif extern void xapic_wait_icr_idle(void); extern u32 safe_xapic_wait_icr_idle(void); extern void xapic_icr_write(u32, u32); @@ -101,6 +108,16 @@ extern void native_apic_icr_write(u32 low, u32 id); extern u64 native_apic_icr_read(void); #ifdef CONFIG_X86_X2APIC +/* + * Make previous memory operations globally visible before + * sending the IPI through x2apic wrmsr. We need a serializing instruction or + * mfence for this. + */ +static inline void x2apic_wrmsr_fence(void) +{ + asm volatile("mfence" : : : "memory"); +} + static inline void native_apic_msr_write(u32 reg, u32 v) { if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR || @@ -177,6 +194,9 @@ static inline int x2apic_enabled(void) { return 0; } + +#define x2apic 0 + #endif extern int get_physical_broadcast(void); @@ -306,7 +326,7 @@ struct apic { void (*send_IPI_self)(int vector); /* wakeup_secondary_cpu */ - int (*wakeup_cpu)(int apicid, unsigned long start_eip); + int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip); int trampoline_phys_low; int trampoline_phys_high; @@ -324,8 +344,21 @@ struct apic { u32 (*safe_wait_icr_idle)(void); }; +/* + * Pointer to the local APIC driver in use on this system (there's + * always just one such driver in use - the kernel decides via an + * early probing process which one it picks - and then sticks to it): + */ extern struct apic *apic; +/* + * APIC functionality to boot other CPUs - only used on SMP: + */ +#ifdef CONFIG_SMP +extern atomic_t init_deasserted; +extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip); +#endif + static inline u32 apic_read(u32 reg) { return apic->read(reg); @@ -359,6 +392,7 @@ static inline u32 safe_apic_wait_icr_idle(void) static inline void ack_APIC_irq(void) { +#ifdef CONFIG_X86_LOCAL_APIC /* * ack_APIC_irq() actually gets compiled as a single instruction * ... yummie. @@ -366,6 +400,7 @@ static inline void ack_APIC_irq(void) /* Docs say use 0 for future compatibility */ apic_write(APIC_EOI, 0); +#endif } static inline unsigned default_get_apic_id(unsigned long x) @@ -384,9 +419,7 @@ static inline unsigned default_get_apic_id(unsigned long x) #define DEFAULT_TRAMPOLINE_PHYS_LOW 0x467 #define DEFAULT_TRAMPOLINE_PHYS_HIGH 0x469 -#ifdef CONFIG_X86_32 -extern void es7000_update_apic_to_cluster(void); -#else +#ifdef CONFIG_X86_64 extern struct apic apic_flat; extern struct apic apic_physflat; extern struct apic apic_x2apic_cluster; @@ -456,10 +489,19 @@ static inline int default_apic_id_registered(void) return physid_isset(read_apic_id(), phys_cpu_present_map); } +static inline int default_phys_pkg_id(int cpuid_apic, int index_msb) +{ + return cpuid_apic >> index_msb; +} + +extern int default_apicid_to_node(int logical_apicid); + +#endif + static inline unsigned int default_cpu_mask_to_apicid(const struct cpumask *cpumask) { - return cpumask_bits(cpumask)[0]; + return cpumask_bits(cpumask)[0] & APIC_ALL_CPUS; } static inline unsigned int @@ -473,15 +515,6 @@ default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, return (unsigned int)(mask1 & mask2 & mask3); } -static inline int default_phys_pkg_id(int cpuid_apic, int index_msb) -{ - return cpuid_apic >> index_msb; -} - -extern int default_apicid_to_node(int logical_apicid); - -#endif - static inline unsigned long default_check_apicid_used(physid_mask_t bitmap, int apicid) { return physid_isset(apicid, bitmap); diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index 63134e3..bc9514f 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -53,6 +53,7 @@ #define APIC_ESR_SENDILL 0x00020 #define APIC_ESR_RECVILL 0x00040 #define APIC_ESR_ILLREGA 0x00080 +#define APIC_LVTCMCI 0x2f0 #define APIC_ICR 0x300 #define APIC_DEST_SELF 0x40000 #define APIC_DEST_ALLINC 0x80000 diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index dd61616..6ba23dd 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -1,26 +1,36 @@ #ifndef _ASM_X86_BOOT_H #define _ASM_X86_BOOT_H -/* Don't touch these, unless you really know what you're doing. */ -#define DEF_SYSSEG 0x1000 -#define DEF_SYSSIZE 0x7F00 - /* Internal svga startup constants */ #define NORMAL_VGA 0xffff /* 80x25 mode */ #define EXTENDED_VGA 0xfffe /* 80x50 mode */ #define ASK_VGA 0xfffd /* ask for it at bootup */ +#ifdef __KERNEL__ + /* Physical address where kernel should be loaded. */ #define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \ + (CONFIG_PHYSICAL_ALIGN - 1)) \ & ~(CONFIG_PHYSICAL_ALIGN - 1)) +#ifdef CONFIG_KERNEL_BZIP2 +#define BOOT_HEAP_SIZE 0x400000 +#else /* !CONFIG_KERNEL_BZIP2 */ + #ifdef CONFIG_X86_64 #define BOOT_HEAP_SIZE 0x7000 -#define BOOT_STACK_SIZE 0x4000 #else #define BOOT_HEAP_SIZE 0x4000 +#endif + +#endif /* !CONFIG_KERNEL_BZIP2 */ + +#ifdef CONFIG_X86_64 +#define BOOT_STACK_SIZE 0x4000 +#else #define BOOT_STACK_SIZE 0x1000 #endif +#endif /* __KERNEL__ */ + #endif /* _ASM_X86_BOOT_H */ diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index 2f84665..e55dfc1 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -5,24 +5,43 @@ #include <linux/mm.h> /* Caches aren't brain-dead on the intel. */ -#define flush_cache_all() do { } while (0) -#define flush_cache_mm(mm) do { } while (0) -#define flush_cache_dup_mm(mm) do { } while (0) -#define flush_cache_range(vma, start, end) do { } while (0) -#define flush_cache_page(vma, vmaddr, pfn) do { } while (0) -#define flush_dcache_page(page) do { } while (0) -#define flush_dcache_mmap_lock(mapping) do { } while (0) -#define flush_dcache_mmap_unlock(mapping) do { } while (0) -#define flush_icache_range(start, end) do { } while (0) -#define flush_icache_page(vma, pg) do { } while (0) -#define flush_icache_user_range(vma, pg, adr, len) do { } while (0) -#define flush_cache_vmap(start, end) do { } while (0) -#define flush_cache_vunmap(start, end) do { } while (0) - -#define copy_to_user_page(vma, page, vaddr, dst, src, len) \ - memcpy((dst), (src), (len)) -#define copy_from_user_page(vma, page, vaddr, dst, src, len) \ - memcpy((dst), (src), (len)) +static inline void flush_cache_all(void) { } +static inline void flush_cache_mm(struct mm_struct *mm) { } +static inline void flush_cache_dup_mm(struct mm_struct *mm) { } +static inline void flush_cache_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) { } +static inline void flush_cache_page(struct vm_area_struct *vma, + unsigned long vmaddr, unsigned long pfn) { } +static inline void flush_dcache_page(struct page *page) { } +static inline void flush_dcache_mmap_lock(struct address_space *mapping) { } +static inline void flush_dcache_mmap_unlock(struct address_space *mapping) { } +static inline void flush_icache_range(unsigned long start, + unsigned long end) { } +static inline void flush_icache_page(struct vm_area_struct *vma, + struct page *page) { } +static inline void flush_icache_user_range(struct vm_area_struct *vma, + struct page *page, + unsigned long addr, + unsigned long len) { } +static inline void flush_cache_vmap(unsigned long start, unsigned long end) { } +static inline void flush_cache_vunmap(unsigned long start, + unsigned long end) { } + +static inline void copy_to_user_page(struct vm_area_struct *vma, + struct page *page, unsigned long vaddr, + void *dst, const void *src, + unsigned long len) +{ + memcpy(dst, src, len); +} + +static inline void copy_from_user_page(struct vm_area_struct *vma, + struct page *page, unsigned long vaddr, + void *dst, const void *src, + unsigned long len) +{ + memcpy(dst, src, len); +} #define PG_non_WB PG_arch_1 PAGEFLAG(NonWB, non_WB) @@ -71,6 +90,9 @@ int set_memory_4k(unsigned long addr, int numpages); int set_memory_array_uc(unsigned long *addr, int addrinarray); int set_memory_array_wb(unsigned long *addr, int addrinarray); +int set_pages_array_uc(struct page **pages, int addrinarray); +int set_pages_array_wb(struct page **pages, int addrinarray); + /* * For legacy compatibility with the old APIs, a few functions * are provided that work on a "struct page". @@ -104,6 +126,11 @@ void clflush_cache_range(void *addr, unsigned int size); #ifdef CONFIG_DEBUG_RODATA void mark_rodata_ro(void); extern const int rodata_test_data; +void set_kernel_text_rw(void); +void set_kernel_text_ro(void); +#else +static inline void set_kernel_text_rw(void) { } +static inline void set_kernel_text_ro(void) { } #endif #ifdef CONFIG_DEBUG_RODATA_TEST diff --git a/arch/x86/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h new file mode 100755 index 0000000..2228020 --- /dev/null +++ b/arch/x86/include/asm/cpu_debug.h @@ -0,0 +1,226 @@ +#ifndef _ASM_X86_CPU_DEBUG_H +#define _ASM_X86_CPU_DEBUG_H + +/* + * CPU x86 architecture debug + * + * Copyright(C) 2009 Jaswinder Singh Rajput + */ + +/* Register flags */ +enum cpu_debug_bit { +/* Model Specific Registers (MSRs) */ + CPU_MC_BIT, /* Machine Check */ + CPU_MONITOR_BIT, /* Monitor */ + CPU_TIME_BIT, /* Time */ + CPU_PMC_BIT, /* Performance Monitor */ + CPU_PLATFORM_BIT, /* Platform */ + CPU_APIC_BIT, /* APIC */ + CPU_POWERON_BIT, /* Power-on */ + CPU_CONTROL_BIT, /* Control */ + CPU_FEATURES_BIT, /* Features control */ + CPU_LBRANCH_BIT, /* Last Branch */ + CPU_BIOS_BIT, /* BIOS */ + CPU_FREQ_BIT, /* Frequency */ + CPU_MTTR_BIT, /* MTRR */ + CPU_PERF_BIT, /* Performance */ + CPU_CACHE_BIT, /* Cache */ + CPU_SYSENTER_BIT, /* Sysenter */ + CPU_THERM_BIT, /* Thermal */ + CPU_MISC_BIT, /* Miscellaneous */ + CPU_DEBUG_BIT, /* Debug */ + CPU_PAT_BIT, /* PAT */ + CPU_VMX_BIT, /* VMX */ + CPU_CALL_BIT, /* System Call */ + CPU_BASE_BIT, /* BASE Address */ + CPU_VER_BIT, /* Version ID */ + CPU_CONF_BIT, /* Configuration */ + CPU_SMM_BIT, /* System mgmt mode */ + CPU_SVM_BIT, /*Secure Virtual Machine*/ + CPU_OSVM_BIT, /* OS-Visible Workaround*/ +/* Standard Registers */ + CPU_TSS_BIT, /* Task Stack Segment */ + CPU_CR_BIT, /* Control Registers */ + CPU_DT_BIT, /* Descriptor Table */ +/* End of Registers flags */ + CPU_REG_ALL_BIT, /* Select all Registers */ +}; + +#define CPU_REG_ALL (~0) /* Select all Registers */ + +#define CPU_MC (1 << CPU_MC_BIT) +#define CPU_MONITOR (1 << CPU_MONITOR_BIT) +#define CPU_TIME (1 << CPU_TIME_BIT) +#define CPU_PMC (1 << CPU_PMC_BIT) +#define CPU_PLATFORM (1 << CPU_PLATFORM_BIT) +#define CPU_APIC (1 << CPU_APIC_BIT) +#define CPU_POWERON (1 << CPU_POWERON_BIT) +#define CPU_CONTROL (1 << CPU_CONTROL_BIT) +#define CPU_FEATURES (1 << CPU_FEATURES_BIT) +#define CPU_LBRANCH (1 << CPU_LBRANCH_BIT) +#define CPU_BIOS (1 << CPU_BIOS_BIT) +#define CPU_FREQ (1 << CPU_FREQ_BIT) +#define CPU_MTRR (1 << CPU_MTTR_BIT) +#define CPU_PERF (1 << CPU_PERF_BIT) +#define CPU_CACHE (1 << CPU_CACHE_BIT) +#define CPU_SYSENTER (1 << CPU_SYSENTER_BIT) +#define CPU_THERM (1 << CPU_THERM_BIT) +#define CPU_MISC (1 << CPU_MISC_BIT) +#define CPU_DEBUG (1 << CPU_DEBUG_BIT) +#define CPU_PAT (1 << CPU_PAT_BIT) +#define CPU_VMX (1 << CPU_VMX_BIT) +#define CPU_CALL (1 << CPU_CALL_BIT) +#define CPU_BASE (1 << CPU_BASE_BIT) +#define CPU_VER (1 << CPU_VER_BIT) +#define CPU_CONF (1 << CPU_CONF_BIT) +#define CPU_SMM (1 << CPU_SMM_BIT) +#define CPU_SVM (1 << CPU_SVM_BIT) +#define CPU_OSVM (1 << CPU_OSVM_BIT) +#define CPU_TSS (1 << CPU_TSS_BIT) +#define CPU_CR (1 << CPU_CR_BIT) +#define CPU_DT (1 << CPU_DT_BIT) + +/* Register file flags */ +enum cpu_file_bit { + CPU_INDEX_BIT, /* index */ + CPU_VALUE_BIT, /* value */ +}; + +#define CPU_FILE_VALUE (1 << CPU_VALUE_BIT) + +/* + * DisplayFamily_DisplayModel Processor Families/Processor Number Series + * -------------------------- ------------------------------------------ + * 05_01, 05_02, 05_04 Pentium, Pentium with MMX + * + * 06_01 Pentium Pro + * 06_03, 06_05 Pentium II Xeon, Pentium II + * 06_07, 06_08, 06_0A, 06_0B Pentium III Xeon, Pentum III + * + * 06_09, 060D Pentium M + * + * 06_0E Core Duo, Core Solo + * + * 06_0F Xeon 3000, 3200, 5100, 5300, 7300 series, + * Core 2 Quad, Core 2 Extreme, Core 2 Duo, + * Pentium dual-core + * 06_17 Xeon 5200, 5400 series, Core 2 Quad Q9650 + * + * 06_1C Atom + * + * 0F_00, 0F_01, 0F_02 Xeon, Xeon MP, Pentium 4 + * 0F_03, 0F_04 Xeon, Xeon MP, Pentium 4, Pentium D + * + * 0F_06 Xeon 7100, 5000 Series, Xeon MP, + * Pentium 4, Pentium D + */ + +/* Register processors bits */ +enum cpu_processor_bit { + CPU_NONE, +/* Intel */ + CPU_INTEL_PENTIUM_BIT, + CPU_INTEL_P6_BIT, + CPU_INTEL_PENTIUM_M_BIT, + CPU_INTEL_CORE_BIT, + CPU_INTEL_CORE2_BIT, + CPU_INTEL_ATOM_BIT, + CPU_INTEL_XEON_P4_BIT, + CPU_INTEL_XEON_MP_BIT, +/* AMD */ + CPU_AMD_K6_BIT, + CPU_AMD_K7_BIT, + CPU_AMD_K8_BIT, + CPU_AMD_0F_BIT, + CPU_AMD_10_BIT, + CPU_AMD_11_BIT, +}; + +#define CPU_INTEL_PENTIUM (1 << CPU_INTEL_PENTIUM_BIT) +#define CPU_INTEL_P6 (1 << CPU_INTEL_P6_BIT) +#define CPU_INTEL_PENTIUM_M (1 << CPU_INTEL_PENTIUM_M_BIT) +#define CPU_INTEL_CORE (1 << CPU_INTEL_CORE_BIT) +#define CPU_INTEL_CORE2 (1 << CPU_INTEL_CORE2_BIT) +#define CPU_INTEL_ATOM (1 << CPU_INTEL_ATOM_BIT) +#define CPU_INTEL_XEON_P4 (1 << CPU_INTEL_XEON_P4_BIT) +#define CPU_INTEL_XEON_MP (1 << CPU_INTEL_XEON_MP_BIT) + +#define CPU_INTEL_PX (CPU_INTEL_P6 | CPU_INTEL_PENTIUM_M) +#define CPU_INTEL_COREX (CPU_INTEL_CORE | CPU_INTEL_CORE2) +#define CPU_INTEL_XEON (CPU_INTEL_XEON_P4 | CPU_INTEL_XEON_MP) +#define CPU_CO_AT (CPU_INTEL_CORE | CPU_INTEL_ATOM) +#define CPU_C2_AT (CPU_INTEL_CORE2 | CPU_INTEL_ATOM) +#define CPU_CX_AT (CPU_INTEL_COREX | CPU_INTEL_ATOM) +#define CPU_CX_XE (CPU_INTEL_COREX | CPU_INTEL_XEON) +#define CPU_P6_XE (CPU_INTEL_P6 | CPU_INTEL_XEON) +#define CPU_PM_CO_AT (CPU_INTEL_PENTIUM_M | CPU_CO_AT) +#define CPU_C2_AT_XE (CPU_C2_AT | CPU_INTEL_XEON) +#define CPU_CX_AT_XE (CPU_CX_AT | CPU_INTEL_XEON) +#define CPU_P6_CX_AT (CPU_INTEL_P6 | CPU_CX_AT) +#define CPU_P6_CX_XE (CPU_P6_XE | CPU_INTEL_COREX) +#define CPU_P6_CX_AT_XE (CPU_INTEL_P6 | CPU_CX_AT_XE) +#define CPU_PM_CX_AT_XE (CPU_INTEL_PENTIUM_M | CPU_CX_AT_XE) +#define CPU_PM_CX_AT (CPU_INTEL_PENTIUM_M | CPU_CX_AT) +#define CPU_PM_CX_XE (CPU_INTEL_PENTIUM_M | CPU_CX_XE) +#define CPU_PX_CX_AT (CPU_INTEL_PX | CPU_CX_AT) +#define CPU_PX_CX_AT_XE (CPU_INTEL_PX | CPU_CX_AT_XE) + +/* Select all supported Intel CPUs */ +#define CPU_INTEL_ALL (CPU_INTEL_PENTIUM | CPU_PX_CX_AT_XE) + +#define CPU_AMD_K6 (1 << CPU_AMD_K6_BIT) +#define CPU_AMD_K7 (1 << CPU_AMD_K7_BIT) +#define CPU_AMD_K8 (1 << CPU_AMD_K8_BIT) +#define CPU_AMD_0F (1 << CPU_AMD_0F_BIT) +#define CPU_AMD_10 (1 << CPU_AMD_10_BIT) +#define CPU_AMD_11 (1 << CPU_AMD_11_BIT) + +#define CPU_K10_PLUS (CPU_AMD_10 | CPU_AMD_11) +#define CPU_K0F_PLUS (CPU_AMD_0F | CPU_K10_PLUS) +#define CPU_K8_PLUS (CPU_AMD_K8 | CPU_K0F_PLUS) +#define CPU_K7_PLUS (CPU_AMD_K7 | CPU_K8_PLUS) + +/* Select all supported AMD CPUs */ +#define CPU_AMD_ALL (CPU_AMD_K6 | CPU_K7_PLUS) + +/* Select all supported CPUs */ +#define CPU_ALL (CPU_INTEL_ALL | CPU_AMD_ALL) + +#define MAX_CPU_FILES 512 + +struct cpu_private { + unsigned cpu; + unsigned type; + unsigned reg; + unsigned file; +}; + +struct cpu_debug_base { + char *name; /* Register name */ + unsigned flag; /* Register flag */ + unsigned write; /* Register write flag */ +}; + +/* + * Currently it looks similar to cpu_debug_base but once we add more files + * cpu_file_base will go in different direction + */ +struct cpu_file_base { + char *name; /* Register file name */ + unsigned flag; /* Register file flag */ + unsigned write; /* Register write flag */ +}; + +struct cpu_cpuX_base { + struct dentry *dentry; /* Register dentry */ + int init; /* Register index file */ +}; + +struct cpu_debug_range { + unsigned min; /* Register range min */ + unsigned max; /* Register range max */ + unsigned flag; /* Supported flags */ + unsigned model; /* Supported models */ +}; + +#endif /* _ASM_X86_CPU_DEBUG_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 7301e60..0beba0d 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -213,6 +213,7 @@ extern const char * const x86_power_flags[32]; #define cpu_has_xmm boot_cpu_has(X86_FEATURE_XMM) #define cpu_has_xmm2 boot_cpu_has(X86_FEATURE_XMM2) #define cpu_has_xmm3 boot_cpu_has(X86_FEATURE_XMM3) +#define cpu_has_aes boot_cpu_has(X86_FEATURE_AES) #define cpu_has_ht boot_cpu_has(X86_FEATURE_HT) #define cpu_has_mp boot_cpu_has(X86_FEATURE_MP) #define cpu_has_nx boot_cpu_has(X86_FEATURE_NX) diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h index a7f3c75..61c852f 100644 --- a/arch/x86/include/asm/cpumask.h +++ b/arch/x86/include/asm/cpumask.h @@ -3,8 +3,6 @@ #ifndef __ASSEMBLY__ #include <linux/cpumask.h> -#ifdef CONFIG_X86_64 - extern cpumask_var_t cpu_callin_mask; extern cpumask_var_t cpu_callout_mask; extern cpumask_var_t cpu_initialized_mask; @@ -12,21 +10,5 @@ extern cpumask_var_t cpu_sibling_setup_mask; extern void setup_cpu_local_masks(void); -#else /* CONFIG_X86_32 */ - -extern cpumask_t cpu_callin_map; -extern cpumask_t cpu_callout_map; -extern cpumask_t cpu_initialized; -extern cpumask_t cpu_sibling_setup_map; - -#define cpu_callin_mask ((struct cpumask *)&cpu_callin_map) -#define cpu_callout_mask ((struct cpumask *)&cpu_callout_map) -#define cpu_initialized_mask ((struct cpumask *)&cpu_initialized) -#define cpu_sibling_setup_mask ((struct cpumask *)&cpu_sibling_setup_map) - -static inline void setup_cpu_local_masks(void) { } - -#endif /* CONFIG_X86_32 */ - #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_CPUMASK_H */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index dc27705..5623c50 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -91,7 +91,6 @@ static inline int desc_empty(const void *ptr) #define store_gdt(dtr) native_store_gdt(dtr) #define store_idt(dtr) native_store_idt(dtr) #define store_tr(tr) (tr = native_store_tr()) -#define store_ldt(ldt) asm("sldt %0":"=m" (ldt)) #define load_TLS(t, cpu) native_load_tls(t, cpu) #define set_ldt native_set_ldt @@ -112,6 +111,8 @@ static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries) } #endif /* CONFIG_PARAVIRT */ +#define store_ldt(ldt) asm("sldt %0" : "=m"(ldt)) + static inline void native_write_idt_entry(gate_desc *idt, int entry, const gate_desc *gate) { diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h index 3c034f4..4994a20 100644 --- a/arch/x86/include/asm/device.h +++ b/arch/x86/include/asm/device.h @@ -6,7 +6,7 @@ struct dev_archdata { void *acpi_handle; #endif #ifdef CONFIG_X86_64 -struct dma_mapping_ops *dma_ops; +struct dma_map_ops *dma_ops; #endif #ifdef CONFIG_DMAR void *iommu; /* hook for IOMMU specific extension */ diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 132a134..cea7b74 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -7,6 +7,8 @@ */ #include <linux/scatterlist.h> +#include <linux/dma-debug.h> +#include <linux/dma-attrs.h> #include <asm/io.h> #include <asm/swiotlb.h> #include <asm-generic/dma-coherent.h> @@ -16,47 +18,9 @@ extern int iommu_merge; extern struct device x86_dma_fallback_dev; extern int panic_on_overflow; -struct dma_mapping_ops { - int (*mapping_error)(struct device *dev, - dma_addr_t dma_addr); - void* (*alloc_coherent)(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp); - void (*free_coherent)(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle); - dma_addr_t (*map_single)(struct device *hwdev, phys_addr_t ptr, - size_t size, int direction); - void (*unmap_single)(struct device *dev, dma_addr_t addr, - size_t size, int direction); - void (*sync_single_for_cpu)(struct device *hwdev, - dma_addr_t dma_handle, size_t size, - int direction); - void (*sync_single_for_device)(struct device *hwdev, - dma_addr_t dma_handle, size_t size, - int direction); - void (*sync_single_range_for_cpu)(struct device *hwdev, - dma_addr_t dma_handle, unsigned long offset, - size_t size, int direction); - void (*sync_single_range_for_device)(struct device *hwdev, - dma_addr_t dma_handle, unsigned long offset, - size_t size, int direction); - void (*sync_sg_for_cpu)(struct device *hwdev, - struct scatterlist *sg, int nelems, - int direction); - void (*sync_sg_for_device)(struct device *hwdev, - struct scatterlist *sg, int nelems, - int direction); - int (*map_sg)(struct device *hwdev, struct scatterlist *sg, - int nents, int direction); - void (*unmap_sg)(struct device *hwdev, - struct scatterlist *sg, int nents, - int direction); - int (*dma_supported)(struct device *hwdev, u64 mask); - int is_phys; -}; - -extern struct dma_mapping_ops *dma_ops; - -static inline struct dma_mapping_ops *get_dma_ops(struct device *dev) +extern struct dma_map_ops *dma_ops; + +static inline struct dma_map_ops *get_dma_ops(struct device *dev) { #ifdef CONFIG_X86_32 return dma_ops; @@ -71,7 +35,7 @@ static inline struct dma_mapping_ops *get_dma_ops(struct device *dev) /* Make sure we keep the same behaviour */ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); if (ops->mapping_error) return ops->mapping_error(dev, dma_addr); @@ -90,137 +54,167 @@ extern void *dma_generic_alloc_coherent(struct device *dev, size_t size, static inline dma_addr_t dma_map_single(struct device *hwdev, void *ptr, size_t size, - int direction) + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); - - BUG_ON(!valid_dma_direction(direction)); - return ops->map_single(hwdev, virt_to_phys(ptr), size, direction); + struct dma_map_ops *ops = get_dma_ops(hwdev); + dma_addr_t addr; + + BUG_ON(!valid_dma_direction(dir)); + addr = ops->map_page(hwdev, virt_to_page(ptr), + (unsigned long)ptr & ~PAGE_MASK, size, + dir, NULL); + debug_dma_map_page(hwdev, virt_to_page(ptr), + (unsigned long)ptr & ~PAGE_MASK, size, + dir, addr, true); + return addr; } static inline void dma_unmap_single(struct device *dev, dma_addr_t addr, size_t size, - int direction) + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); - BUG_ON(!valid_dma_direction(direction)); - if (ops->unmap_single) - ops->unmap_single(dev, addr, size, direction); + BUG_ON(!valid_dma_direction(dir)); + if (ops->unmap_page) + ops->unmap_page(dev, addr, size, dir, NULL); + debug_dma_unmap_page(dev, addr, size, dir, true); } static inline int dma_map_sg(struct device *hwdev, struct scatterlist *sg, - int nents, int direction) + int nents, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); + int ents; + + BUG_ON(!valid_dma_direction(dir)); + ents = ops->map_sg(hwdev, sg, nents, dir, NULL); + debug_dma_map_sg(hwdev, sg, nents, ents, dir); - BUG_ON(!valid_dma_direction(direction)); - return ops->map_sg(hwdev, sg, nents, direction); + return ents; } static inline void dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents, - int direction) + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); + debug_dma_unmap_sg(hwdev, sg, nents, dir); if (ops->unmap_sg) - ops->unmap_sg(hwdev, sg, nents, direction); + ops->unmap_sg(hwdev, sg, nents, dir, NULL); } static inline void dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle, - size_t size, int direction) + size_t size, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_for_cpu) - ops->sync_single_for_cpu(hwdev, dma_handle, size, direction); + ops->sync_single_for_cpu(hwdev, dma_handle, size, dir); + debug_dma_sync_single_for_cpu(hwdev, dma_handle, size, dir); flush_write_buffers(); } static inline void dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle, - size_t size, int direction) + size_t size, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_for_device) - ops->sync_single_for_device(hwdev, dma_handle, size, direction); + ops->sync_single_for_device(hwdev, dma_handle, size, dir); + debug_dma_sync_single_for_device(hwdev, dma_handle, size, dir); flush_write_buffers(); } static inline void dma_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dma_handle, - unsigned long offset, size_t size, int direction) + unsigned long offset, size_t size, + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_range_for_cpu) ops->sync_single_range_for_cpu(hwdev, dma_handle, offset, - size, direction); + size, dir); + debug_dma_sync_single_range_for_cpu(hwdev, dma_handle, + offset, size, dir); flush_write_buffers(); } static inline void dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle, unsigned long offset, size_t size, - int direction) + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_range_for_device) ops->sync_single_range_for_device(hwdev, dma_handle, - offset, size, direction); + offset, size, dir); + debug_dma_sync_single_range_for_device(hwdev, dma_handle, + offset, size, dir); flush_write_buffers(); } static inline void dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, - int nelems, int direction) + int nelems, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_sg_for_cpu) - ops->sync_sg_for_cpu(hwdev, sg, nelems, direction); + ops->sync_sg_for_cpu(hwdev, sg, nelems, dir); + debug_dma_sync_sg_for_cpu(hwdev, sg, nelems, dir); flush_write_buffers(); } static inline void dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, - int nelems, int direction) + int nelems, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_sg_for_device) - ops->sync_sg_for_device(hwdev, sg, nelems, direction); + ops->sync_sg_for_device(hwdev, sg, nelems, dir); + debug_dma_sync_sg_for_device(hwdev, sg, nelems, dir); flush_write_buffers(); } static inline dma_addr_t dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, - int direction) + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); + dma_addr_t addr; - BUG_ON(!valid_dma_direction(direction)); - return ops->map_single(dev, page_to_phys(page) + offset, - size, direction); + BUG_ON(!valid_dma_direction(dir)); + addr = ops->map_page(dev, page, offset, size, dir, NULL); + debug_dma_map_page(dev, page, offset, size, dir, addr, false); + + return addr; } static inline void dma_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, int direction) + size_t size, enum dma_data_direction dir) { - dma_unmap_single(dev, addr, size, direction); + struct dma_map_ops *ops = get_dma_ops(dev); + + BUG_ON(!valid_dma_direction(dir)); + if (ops->unmap_page) + ops->unmap_page(dev, addr, size, dir, NULL); + debug_dma_unmap_page(dev, addr, size, dir, false); } static inline void @@ -266,7 +260,7 @@ static inline void * dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); void *memory; gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); @@ -285,20 +279,24 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, if (!ops->alloc_coherent) return NULL; - return ops->alloc_coherent(dev, size, dma_handle, - dma_alloc_coherent_gfp_flags(dev, gfp)); + memory = ops->alloc_coherent(dev, size, dma_handle, + dma_alloc_coherent_gfp_flags(dev, gfp)); + debug_dma_alloc_coherent(dev, size, *dma_handle, memory); + + return memory; } static inline void dma_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t bus) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); WARN_ON(irqs_disabled()); /* for portability */ if (dma_release_from_coherent(dev, get_order(size), vaddr)) return; + debug_dma_free_coherent(dev, size, vaddr, bus); if (ops->free_coherent) ops->free_coherent(dev, size, vaddr, bus); } diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h index bc68212..fd8f9e2 100644 --- a/arch/x86/include/asm/dmi.h +++ b/arch/x86/include/asm/dmi.h @@ -1,22 +1,15 @@ #ifndef _ASM_X86_DMI_H #define _ASM_X86_DMI_H -#include <asm/io.h> - -#define DMI_MAX_DATA 2048 +#include <linux/compiler.h> +#include <linux/init.h> -extern int dmi_alloc_index; -extern char dmi_alloc_data[DMI_MAX_DATA]; +#include <asm/io.h> +#include <asm/setup.h> -/* This is so early that there is no good way to allocate dynamic memory. - Allocate data in an BSS array. */ -static inline void *dmi_alloc(unsigned len) +static __always_inline __init void *dmi_alloc(unsigned len) { - int idx = dmi_alloc_index; - if ((dmi_alloc_index + len) > DMI_MAX_DATA) - return NULL; - dmi_alloc_index += len; - return dmi_alloc_data + idx; + return extend_brk(len, sizeof(int)); } /* Use early IO mappings for DMI because it's initialized early */ diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 00d41ce..7ecba4d 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -72,7 +72,7 @@ extern int e820_all_mapped(u64 start, u64 end, unsigned type); extern void e820_add_region(u64 start, u64 size, int type); extern void e820_print_map(char *who); extern int -sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, int *pnr_map); +sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map); extern u64 e820_update_range(u64 start, u64 size, unsigned old_type, unsigned new_type); extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type, diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index ca5ffb2..edc90f2 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -37,8 +37,6 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); #else /* !CONFIG_X86_32 */ -#define MAX_EFI_IO_PAGES 100 - extern u64 efi_call0(void *fp); extern u64 efi_call1(void *fp, u64 arg1); extern u64 efi_call2(void *fp, u64 arg1, u64 arg2); diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h index 854d538..c2e6bed 100644 --- a/arch/x86/include/asm/entry_arch.h +++ b/arch/x86/include/asm/entry_arch.h @@ -33,6 +33,8 @@ BUILD_INTERRUPT3(invalidate_interrupt7,INVALIDATE_TLB_VECTOR_START+7, smp_invalidate_interrupt) #endif +BUILD_INTERRUPT(generic_interrupt, GENERIC_INTERRUPT_VECTOR) + /* * every pentium local APIC has two 'local interrupts', with a * soft-definable vector attached to both interrupts, one of diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 23696d4..81937a5 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -1,11 +1,147 @@ +/* + * fixmap.h: compile-time virtual memory allocation + * + * 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. + * + * Copyright (C) 1998 Ingo Molnar + * + * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 + * x86_32 and x86_64 integration by Gustavo F. Padovan, February 2009 + */ + #ifndef _ASM_X86_FIXMAP_H #define _ASM_X86_FIXMAP_H +#ifndef __ASSEMBLY__ +#include <linux/kernel.h> +#include <asm/acpi.h> +#include <asm/apicdef.h> +#include <asm/page.h> +#ifdef CONFIG_X86_32 +#include <linux/threads.h> +#include <asm/kmap_types.h> +#else +#include <asm/vsyscall.h> +#endif + +/* + * We can't declare FIXADDR_TOP as variable for x86_64 because vsyscall + * uses fixmaps that relies on FIXADDR_TOP for proper address calculation. + * Because of this, FIXADDR_TOP x86 integration was left as later work. + */ +#ifdef CONFIG_X86_32 +/* used by vmalloc.c, vsyscall.lds.S. + * + * Leave one empty page between vmalloc'ed areas and + * the start of the fixmap. + */ +extern unsigned long __FIXADDR_TOP; +#define FIXADDR_TOP ((unsigned long)__FIXADDR_TOP) + +#define FIXADDR_USER_START __fix_to_virt(FIX_VDSO) +#define FIXADDR_USER_END __fix_to_virt(FIX_VDSO - 1) +#else +#define FIXADDR_TOP (VSYSCALL_END-PAGE_SIZE) + +/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */ +#define FIXADDR_USER_START ((unsigned long)VSYSCALL32_VSYSCALL) +#define FIXADDR_USER_END (FIXADDR_USER_START + PAGE_SIZE) +#endif + + +/* + * Here we define all the compile-time 'special' virtual + * addresses. The point is to have a constant address at + * compile time, but to set the physical address only + * in the boot process. + * for x86_32: We allocate these special addresses + * from the end of virtual memory (0xfffff000) backwards. + * Also this lets us do fail-safe vmalloc(), we + * can guarantee that these special addresses and + * vmalloc()-ed addresses never overlap. + * + * These 'compile-time allocated' memory buffers are + * fixed-size 4k pages (or larger if used with an increment + * higher than 1). Use set_fixmap(idx,phys) to associate + * physical memory with fixmap indices. + * + * TLB entries of such buffers will not be flushed across + * task switches. + */ +enum fixed_addresses { #ifdef CONFIG_X86_32 -# include "fixmap_32.h" + FIX_HOLE, + FIX_VDSO, #else -# include "fixmap_64.h" + VSYSCALL_LAST_PAGE, + VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE + + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1, + VSYSCALL_HPET, #endif + FIX_DBGP_BASE, + FIX_EARLYCON_MEM_BASE, +#ifdef CONFIG_X86_LOCAL_APIC + FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */ +#endif +#ifdef CONFIG_X86_IO_APIC + FIX_IO_APIC_BASE_0, + FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1, +#endif +#ifdef CONFIG_X86_VISWS_APIC + FIX_CO_CPU, /* Cobalt timer */ + FIX_CO_APIC, /* Cobalt APIC Redirection Table */ + FIX_LI_PCIA, /* Lithium PCI Bridge A */ + FIX_LI_PCIB, /* Lithium PCI Bridge B */ +#endif +#ifdef CONFIG_X86_F00F_BUG + FIX_F00F_IDT, /* Virtual mapping for IDT */ +#endif +#ifdef CONFIG_X86_CYCLONE_TIMER + FIX_CYCLONE_TIMER, /*cyclone timer register*/ +#endif +#ifdef CONFIG_X86_32 + FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ + FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, +#ifdef CONFIG_PCI_MMCONFIG + FIX_PCIE_MCFG, +#endif +#endif +#ifdef CONFIG_PARAVIRT + FIX_PARAVIRT_BOOTMAP, +#endif + FIX_TEXT_POKE0, /* reserve 2 pages for text_poke() */ + FIX_TEXT_POKE1, + __end_of_permanent_fixed_addresses, +#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT + FIX_OHCI1394_BASE, +#endif + /* + * 256 temporary boot-time mappings, used by early_ioremap(), + * before ioremap() is functional. + * + * We round it up to the next 256 pages boundary so that we + * can have a single pgd entry and a single pte table: + */ +#define NR_FIX_BTMAPS 64 +#define FIX_BTMAPS_SLOTS 4 + FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 - + (__end_of_permanent_fixed_addresses & 255), + FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1, +#ifdef CONFIG_X86_32 + FIX_WP_TEST, +#endif + __end_of_fixed_addresses +}; + + +extern void reserve_top_address(unsigned long reserve); + +#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_BOOT_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) +#define FIXADDR_BOOT_START (FIXADDR_TOP - FIXADDR_BOOT_SIZE) extern int fixmaps_set; @@ -69,4 +205,5 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr) BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START); return __virt_to_fix(vaddr); } +#endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_FIXMAP_H */ diff --git a/arch/x86/include/asm/fixmap_32.h b/arch/x86/include/asm/fixmap_32.h deleted file mode 100644 index 047d9ba..0000000 --- a/arch/x86/include/asm/fixmap_32.h +++ /dev/null @@ -1,115 +0,0 @@ -/* - * fixmap.h: compile-time virtual memory allocation - * - * 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. - * - * Copyright (C) 1998 Ingo Molnar - * - * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 - */ - -#ifndef _ASM_X86_FIXMAP_32_H -#define _ASM_X86_FIXMAP_32_H - - -/* used by vmalloc.c, vsyscall.lds.S. - * - * Leave one empty page between vmalloc'ed areas and - * the start of the fixmap. - */ -extern unsigned long __FIXADDR_TOP; -#define FIXADDR_USER_START __fix_to_virt(FIX_VDSO) -#define FIXADDR_USER_END __fix_to_virt(FIX_VDSO - 1) - -#ifndef __ASSEMBLY__ -#include <linux/kernel.h> -#include <asm/acpi.h> -#include <asm/apicdef.h> -#include <asm/page.h> -#include <linux/threads.h> -#include <asm/kmap_types.h> - -/* - * Here we define all the compile-time 'special' virtual - * addresses. The point is to have a constant address at - * compile time, but to set the physical address only - * in the boot process. We allocate these special addresses - * from the end of virtual memory (0xfffff000) backwards. - * Also this lets us do fail-safe vmalloc(), we - * can guarantee that these special addresses and - * vmalloc()-ed addresses never overlap. - * - * these 'compile-time allocated' memory buffers are - * fixed-size 4k pages. (or larger if used with an increment - * highger than 1) use fixmap_set(idx,phys) to associate - * physical memory with fixmap indices. - * - * TLB entries of such buffers will not be flushed across - * task switches. - */ -enum fixed_addresses { - FIX_HOLE, - FIX_VDSO, - FIX_DBGP_BASE, - FIX_EARLYCON_MEM_BASE, -#ifdef CONFIG_X86_LOCAL_APIC - FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */ -#endif -#ifdef CONFIG_X86_IO_APIC - FIX_IO_APIC_BASE_0, - FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS-1, -#endif -#ifdef CONFIG_X86_VISWS_APIC - FIX_CO_CPU, /* Cobalt timer */ - FIX_CO_APIC, /* Cobalt APIC Redirection Table */ - FIX_LI_PCIA, /* Lithium PCI Bridge A */ - FIX_LI_PCIB, /* Lithium PCI Bridge B */ -#endif -#ifdef CONFIG_X86_F00F_BUG - FIX_F00F_IDT, /* Virtual mapping for IDT */ -#endif -#ifdef CONFIG_X86_CYCLONE_TIMER - FIX_CYCLONE_TIMER, /*cyclone timer register*/ -#endif - FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ - FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, -#ifdef CONFIG_PCI_MMCONFIG - FIX_PCIE_MCFG, -#endif -#ifdef CONFIG_PARAVIRT - FIX_PARAVIRT_BOOTMAP, -#endif - __end_of_permanent_fixed_addresses, - /* - * 256 temporary boot-time mappings, used by early_ioremap(), - * before ioremap() is functional. - * - * We round it up to the next 256 pages boundary so that we - * can have a single pgd entry and a single pte table: - */ -#define NR_FIX_BTMAPS 64 -#define FIX_BTMAPS_SLOTS 4 - FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 - - (__end_of_permanent_fixed_addresses & 255), - FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1, - FIX_WP_TEST, -#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT - FIX_OHCI1394_BASE, -#endif - __end_of_fixed_addresses -}; - -extern void reserve_top_address(unsigned long reserve); - - -#define FIXADDR_TOP ((unsigned long)__FIXADDR_TOP) - -#define __FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) -#define __FIXADDR_BOOT_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_START (FIXADDR_TOP - __FIXADDR_SIZE) -#define FIXADDR_BOOT_START (FIXADDR_TOP - __FIXADDR_BOOT_SIZE) - -#endif /* !__ASSEMBLY__ */ -#endif /* _ASM_X86_FIXMAP_32_H */ diff --git a/arch/x86/include/asm/fixmap_64.h b/arch/x86/include/asm/fixmap_64.h deleted file mode 100644 index 298d9ba..0000000 --- a/arch/x86/include/asm/fixmap_64.h +++ /dev/null @@ -1,79 +0,0 @@ -/* - * fixmap.h: compile-time virtual memory allocation - * - * 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. - * - * Copyright (C) 1998 Ingo Molnar - */ - -#ifndef _ASM_X86_FIXMAP_64_H -#define _ASM_X86_FIXMAP_64_H - -#include <linux/kernel.h> -#include <asm/acpi.h> -#include <asm/apicdef.h> -#include <asm/page.h> -#include <asm/vsyscall.h> -#include <asm/efi.h> - -/* - * Here we define all the compile-time 'special' virtual - * addresses. The point is to have a constant address at - * compile time, but to set the physical address only - * in the boot process. - * - * These 'compile-time allocated' memory buffers are - * fixed-size 4k pages (or larger if used with an increment - * higher than 1). Use set_fixmap(idx,phys) to associate - * physical memory with fixmap indices. - * - * TLB entries of such buffers will not be flushed across - * task switches. - */ - -enum fixed_addresses { - VSYSCALL_LAST_PAGE, - VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE - + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1, - VSYSCALL_HPET, - FIX_DBGP_BASE, - FIX_EARLYCON_MEM_BASE, - FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */ - FIX_IO_APIC_BASE_0, - FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1, - FIX_EFI_IO_MAP_LAST_PAGE, - FIX_EFI_IO_MAP_FIRST_PAGE = FIX_EFI_IO_MAP_LAST_PAGE - + MAX_EFI_IO_PAGES - 1, -#ifdef CONFIG_PARAVIRT - FIX_PARAVIRT_BOOTMAP, -#endif - __end_of_permanent_fixed_addresses, -#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT - FIX_OHCI1394_BASE, -#endif - /* - * 256 temporary boot-time mappings, used by early_ioremap(), - * before ioremap() is functional. - * - * We round it up to the next 256 pages boundary so that we - * can have a single pgd entry and a single pte table: - */ -#define NR_FIX_BTMAPS 64 -#define FIX_BTMAPS_SLOTS 4 - FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 - - (__end_of_permanent_fixed_addresses & 255), - FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1, - __end_of_fixed_addresses -}; - -#define FIXADDR_TOP (VSYSCALL_END-PAGE_SIZE) -#define FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) - -/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */ -#define FIXADDR_USER_START ((unsigned long)VSYSCALL32_VSYSCALL) -#define FIXADDR_USER_END (FIXADDR_USER_START + PAGE_SIZE) - -#endif /* _ASM_X86_FIXMAP_64_H */ diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index b55b4a7..bd2c651 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -28,6 +28,13 @@ #endif +/* FIXME: I don't want to stay hardcoded */ +#ifdef CONFIG_X86_64 +# define FTRACE_SYSCALL_MAX 296 +#else +# define FTRACE_SYSCALL_MAX 333 +#endif + #ifdef CONFIG_FUNCTION_TRACER #define MCOUNT_ADDR ((long)(mcount)) #define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ @@ -55,29 +62,4 @@ struct dyn_arch_ftrace { #endif /* __ASSEMBLY__ */ #endif /* CONFIG_FUNCTION_TRACER */ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - -#ifndef __ASSEMBLY__ - -/* - * Stack of return addresses for functions - * of a thread. - * Used in struct thread_info - */ -struct ftrace_ret_stack { - unsigned long ret; - unsigned long func; - unsigned long long calltime; -}; - -/* - * Primary handler of a function return. - * It relays on ftrace_return_to_handler. - * Defined in entry_32/64.S - */ -extern void return_to_handler(void); - -#endif /* __ASSEMBLY__ */ -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ - #endif /* _ASM_X86_FTRACE_H */ diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 46ebed7..2545442 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -12,6 +12,7 @@ typedef struct { unsigned int apic_timer_irqs; /* arch dependent */ unsigned int irq_spurious_count; #endif + unsigned int generic_irqs; /* arch dependent */ unsigned int apic_perf_irqs; #ifdef CONFIG_SMP unsigned int irq_resched_count; diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h index bf9276b..014c2b85 100644 --- a/arch/x86/include/asm/highmem.h +++ b/arch/x86/include/asm/highmem.h @@ -63,6 +63,7 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot); void *kmap_atomic(struct page *page, enum km_type type); void kunmap_atomic(void *kvaddr, enum km_type type); void *kmap_atomic_pfn(unsigned long pfn, enum km_type type); +void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot); struct page *kmap_atomic_to_page(void *ptr); #ifndef CONFIG_PARAVIRT diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index f39881b..ae80f64 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -27,6 +27,7 @@ /* Interrupt handlers registered during init_IRQ */ extern void apic_timer_interrupt(void); +extern void generic_interrupt(void); extern void error_interrupt(void); extern void perf_counter_interrupt(void); diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 48f0004..71c9e51 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -172,7 +172,13 @@ static inline void __save_init_fpu(struct task_struct *tsk) #else /* CONFIG_X86_32 */ -extern void finit(void); +#ifdef CONFIG_MATH_EMULATION +extern void finit_task(struct task_struct *tsk); +#else +static inline void finit_task(struct task_struct *tsk) +{ +} +#endif static inline void tolerant_fwait(void) { diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index 50ca486..1f7e625 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -129,13 +129,6 @@ typedef struct compat_siginfo { } _sifields; } compat_siginfo_t; -struct ustat32 { - __u32 f_tfree; - compat_ino_t f_tinode; - char f_fname[6]; - char f_fpack[6]; -}; - #define IA32_STACK_TOP IA32_PAGE_OFFSET #ifdef __KERNEL__ diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h new file mode 100644 index 0000000..36fb1a6a --- /dev/null +++ b/arch/x86/include/asm/init.h @@ -0,0 +1,18 @@ +#ifndef _ASM_X86_INIT_32_H +#define _ASM_X86_INIT_32_H + +#ifdef CONFIG_X86_32 +extern void __init early_ioremap_page_table_range_init(void); +#endif + +extern unsigned long __init +kernel_physical_mapping_init(unsigned long start, + unsigned long end, + unsigned long page_size_mask); + + +extern unsigned long __initdata e820_table_start; +extern unsigned long __meminitdata e820_table_end; +extern unsigned long __meminitdata e820_table_top; + +#endif /* _ASM_X86_INIT_32_H */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 683d0b4..e5383e3 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -172,8 +172,6 @@ static inline void __iomem *ioremap(resource_size_t offset, unsigned long size) extern void iounmap(volatile void __iomem *addr); -extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys); - #ifdef CONFIG_X86_32 # include "io_32.h" @@ -198,7 +196,6 @@ extern void early_ioremap_reset(void); extern void __iomem *early_ioremap(unsigned long offset, unsigned long size); extern void __iomem *early_memremap(unsigned long offset, unsigned long size); extern void early_iounmap(void __iomem *addr, unsigned long size); -extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys); #define IO_SPACE_LIMIT 0xffff diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 59cb4a1..373cc2b 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -162,7 +162,8 @@ extern int (*ioapic_renumber_irq)(int ioapic, int irq); extern void ioapic_init_mappings(void); #ifdef CONFIG_X86_64 -extern int save_mask_IO_APIC_setup(void); +extern int save_IO_APIC_setup(void); +extern void mask_IO_APIC_setup(void); extern void restore_IO_APIC_setup(void); extern void reinit_intr_remapped_IO_APIC(int); #endif @@ -172,7 +173,7 @@ extern void probe_nr_irqs_gsi(void); extern int setup_ioapic_entry(int apic, int irq, struct IO_APIC_route_entry *entry, unsigned int destination, int trigger, - int polarity, int vector); + int polarity, int vector, int pin); extern void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e); #else /* !CONFIG_X86_IO_APIC */ diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h index bd46495..86af260 100644 --- a/arch/x86/include/asm/iomap.h +++ b/arch/x86/include/asm/iomap.h @@ -24,10 +24,7 @@ #include <asm/tlbflush.h> int -reserve_io_memtype_wc(u64 base, unsigned long size, pgprot_t *prot); - -void -free_io_memtype(u64 base, unsigned long size); +is_io_mapping_possible(resource_size_t base, unsigned long size); void * iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot); diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index a6ee9e6..af326a2 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -3,7 +3,7 @@ extern void pci_iommu_shutdown(void); extern void no_iommu_init(void); -extern struct dma_mapping_ops nommu_dma_ops; +extern struct dma_map_ops nommu_dma_ops; extern int force_iommu, no_iommu; extern int iommu_detected; diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 107eb21..f38481b 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -36,6 +36,7 @@ static inline int irq_canonicalize(int irq) extern void fixup_irqs(void); #endif +extern void (*generic_interrupt_extension)(void); extern void init_IRQ(void); extern void native_init_IRQ(void); extern bool handle_irq(unsigned irq, struct pt_regs *regs); diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index 20e1fd5..0396760 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -1,8 +1,6 @@ #ifndef _ASM_X86_IRQ_REMAPPING_H #define _ASM_X86_IRQ_REMAPPING_H -extern int x2apic; - #define IRTE_DEST(dest) ((x2apic) ? dest : dest << 8) #endif /* _ASM_X86_IRQ_REMAPPING_H */ diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 8a285f3..3cbd79b 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -112,6 +112,11 @@ #define LOCAL_PERF_VECTOR 0xee /* + * Generic system vector for platform specific use + */ +#define GENERIC_INTERRUPT_VECTOR 0xed + +/* * First APIC vector available to drivers: (vectors 0x30-0xee) we * start at 0x31(0x41) to spread out vectors evenly between priority * levels. (0x80 is the syscall vector) diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 0ceb6d1..317ff17 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -9,13 +9,13 @@ # define PAGES_NR 4 #else # define PA_CONTROL_PAGE 0 -# define PA_TABLE_PAGE 1 -# define PAGES_NR 2 +# define VA_CONTROL_PAGE 1 +# define PA_TABLE_PAGE 2 +# define PA_SWAP_PAGE 3 +# define PAGES_NR 4 #endif -#ifdef CONFIG_X86_32 # define KEXEC_CONTROL_CODE_MAX_SIZE 2048 -#endif #ifndef __ASSEMBLY__ @@ -136,10 +136,11 @@ relocate_kernel(unsigned long indirection_page, unsigned int has_pae, unsigned int preserve_context); #else -NORET_TYPE void +unsigned long relocate_kernel(unsigned long indirection_page, unsigned long page_list, - unsigned long start_address) ATTRIB_NORET; + unsigned long start_address, + unsigned int preserve_context); #endif #define ARCH_HAS_KIMAGE_ARCH diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index 886c940..dc3f6cf 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -15,6 +15,7 @@ #define __KVM_HAVE_DEVICE_ASSIGNMENT #define __KVM_HAVE_MSI #define __KVM_HAVE_USER_NMI +#define __KVM_HAVE_GUEST_DEBUG /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 @@ -212,7 +213,30 @@ struct kvm_pit_channel_state { __s64 count_load_time; }; +struct kvm_debug_exit_arch { + __u32 exception; + __u32 pad; + __u64 pc; + __u64 dr6; + __u64 dr7; +}; + +#define KVM_GUESTDBG_USE_SW_BP 0x00010000 +#define KVM_GUESTDBG_USE_HW_BP 0x00020000 +#define KVM_GUESTDBG_INJECT_DB 0x00040000 +#define KVM_GUESTDBG_INJECT_BP 0x00080000 + +/* for KVM_SET_GUEST_DEBUG */ +struct kvm_guest_debug_arch { + __u64 debugreg[8]; +}; + struct kvm_pit_state { struct kvm_pit_channel_state channels[3]; }; + +struct kvm_reinject_control { + __u8 pit_reinject; + __u8 reserved[31]; +}; #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 730843d..f0faf58 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -22,6 +22,7 @@ #include <asm/pvclock-abi.h> #include <asm/desc.h> #include <asm/mtrr.h> +#include <asm/msr-index.h> #define KVM_MAX_VCPUS 16 #define KVM_MEMORY_SLOTS 32 @@ -134,11 +135,18 @@ enum { #define KVM_NR_MEM_OBJS 40 -struct kvm_guest_debug { - int enabled; - unsigned long bp[4]; - int singlestep; -}; +#define KVM_NR_DB_REGS 4 + +#define DR6_BD (1 << 13) +#define DR6_BS (1 << 14) +#define DR6_FIXED_1 0xffff0ff0 +#define DR6_VOLATILE 0x0000e00f + +#define DR7_BP_EN_MASK 0x000000ff +#define DR7_GE (1 << 9) +#define DR7_GD (1 << 13) +#define DR7_FIXED_1 0x00000400 +#define DR7_VOLATILE 0xffff23ff /* * We don't want allocation failures within the mmu code, so we preallocate @@ -162,7 +170,8 @@ struct kvm_pte_chain { * bits 0:3 - total guest paging levels (2-4, or zero for real mode) * bits 4:7 - page table level for this shadow (1-4) * bits 8:9 - page table quadrant for 2-level guests - * bit 16 - "metaphysical" - gfn is not a real page (huge page/real mode) + * bit 16 - direct mapping of virtual to physical mapping at gfn + * used for real mode and two-dimensional paging * bits 17:19 - common access permissions for all ptes in this shadow page */ union kvm_mmu_page_role { @@ -172,9 +181,10 @@ union kvm_mmu_page_role { unsigned level:4; unsigned quadrant:2; unsigned pad_for_nice_hex_output:6; - unsigned metaphysical:1; + unsigned direct:1; unsigned access:3; unsigned invalid:1; + unsigned cr4_pge:1; }; }; @@ -218,6 +228,18 @@ struct kvm_pv_mmu_op_buffer { char buf[512] __aligned(sizeof(long)); }; +struct kvm_pio_request { + unsigned long count; + int cur_count; + gva_t guest_gva; + int in; + int port; + int size; + int string; + int down; + int rep; +}; + /* * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level * 32-bit). The kvm_mmu structure abstracts the details of the current mmu @@ -236,6 +258,7 @@ struct kvm_mmu { hpa_t root_hpa; int root_level; int shadow_root_level; + union kvm_mmu_page_role base_role; u64 *pae_root; }; @@ -258,6 +281,7 @@ struct kvm_vcpu_arch { unsigned long cr3; unsigned long cr4; unsigned long cr8; + u32 hflags; u64 pdptrs[4]; /* pae */ u64 shadow_efer; u64 apic_base; @@ -338,6 +362,15 @@ struct kvm_vcpu_arch { struct mtrr_state_type mtrr_state; u32 pat; + + int switch_db_regs; + unsigned long host_db[KVM_NR_DB_REGS]; + unsigned long host_dr6; + unsigned long host_dr7; + unsigned long db[KVM_NR_DB_REGS]; + unsigned long dr6; + unsigned long dr7; + unsigned long eff_db[KVM_NR_DB_REGS]; }; struct kvm_mem_alias { @@ -378,6 +411,7 @@ struct kvm_arch{ unsigned long irq_sources_bitmap; unsigned long irq_states[KVM_IOAPIC_NUM_PINS]; + u64 vm_init_tsc; }; struct kvm_vm_stat { @@ -446,8 +480,7 @@ struct kvm_x86_ops { void (*vcpu_put)(struct kvm_vcpu *vcpu); int (*set_guest_debug)(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg); - void (*guest_debug_pre)(struct kvm_vcpu *vcpu); + struct kvm_guest_debug *dbg); int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); @@ -583,16 +616,12 @@ void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2, u32 error_code); -void kvm_pic_set_irq(void *opaque, int irq, int level); +int kvm_pic_set_irq(void *opaque, int irq, int level); void kvm_inject_nmi(struct kvm_vcpu *vcpu); void fx_init(struct kvm_vcpu *vcpu); -int emulator_read_std(unsigned long addr, - void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu); int emulator_write_emulated(unsigned long addr, const void *val, unsigned int bytes, @@ -737,6 +766,10 @@ enum { TASK_SWITCH_GATE = 3, }; +#define HF_GIF_MASK (1 << 0) +#define HF_HIF_MASK (1 << 1) +#define HF_VINTR_MASK (1 << 2) + /* * Hardware virtualization extension instructions may fault if a * reboot turns off virtualization while processes are running. diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h index 4389442..0f4ee71 100644 --- a/arch/x86/include/asm/lguest_hcall.h +++ b/arch/x86/include/asm/lguest_hcall.h @@ -26,36 +26,20 @@ #ifndef __ASSEMBLY__ #include <asm/hw_irq.h> +#include <asm/kvm_para.h> /*G:031 But first, how does our Guest contact the Host to ask for privileged * operations? There are two ways: the direct way is to make a "hypercall", * to make requests of the Host Itself. * - * Our hypercall mechanism uses the highest unused trap code (traps 32 and - * above are used by real hardware interrupts). Fifteen hypercalls are + * We use the KVM hypercall mechanism. Eighteen hypercalls are * available: the hypercall number is put in the %eax register, and the - * arguments (when required) are placed in %edx, %ebx and %ecx. If a return + * arguments (when required) are placed in %ebx, %ecx and %edx. If a return * value makes sense, it's returned in %eax. * * Grossly invalid calls result in Sudden Death at the hands of the vengeful * Host, rather than returning failure. This reflects Winston Churchill's * definition of a gentleman: "someone who is only rude intentionally". */ -static inline unsigned long -hcall(unsigned long call, - unsigned long arg1, unsigned long arg2, unsigned long arg3) -{ - /* "int" is the Intel instruction to trigger a trap. */ - asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY) - /* The call in %eax (aka "a") might be overwritten */ - : "=a"(call) - /* The arguments are in %eax, %edx, %ebx & %ecx */ - : "a"(call), "d"(arg1), "b"(arg2), "c"(arg3) - /* "memory" means this might write somewhere in memory. - * This isn't true for all calls, but it's safe to tell - * gcc that it might happen so it doesn't get clever. */ - : "memory"); - return call; -} /*:*/ /* Can't use our min() macro here: needs to be a constant */ @@ -64,7 +48,7 @@ hcall(unsigned long call, #define LHCALL_RING_SIZE 64 struct hcall_args { /* These map directly onto eax, ebx, ecx, edx in struct lguest_regs */ - unsigned long arg0, arg2, arg3, arg1; + unsigned long arg0, arg1, arg2, arg3; }; #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 9320e2a..12d55e7 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -1,14 +1,11 @@ #ifndef _ASM_X86_LINKAGE_H #define _ASM_X86_LINKAGE_H +#include <linux/stringify.h> + #undef notrace #define notrace __attribute__((no_instrument_function)) -#ifdef CONFIG_X86_64 -#define __ALIGN .p2align 4,,15 -#define __ALIGN_STR ".p2align 4,,15" -#endif - #ifdef CONFIG_X86_32 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0))) /* @@ -50,16 +47,20 @@ __asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \ "g" (arg4), "g" (arg5), "g" (arg6)) -#endif +#endif /* CONFIG_X86_32 */ + +#ifdef __ASSEMBLY__ #define GLOBAL(name) \ .globl name; \ name: -#ifdef CONFIG_X86_ALIGNMENT_16 -#define __ALIGN .align 16,0x90 -#define __ALIGN_STR ".align 16,0x90" +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_ALIGNMENT_16) +#define __ALIGN .p2align 4, 0x90 +#define __ALIGN_STR __stringify(__ALIGN) #endif +#endif /* __ASSEMBLY__ */ + #endif /* _ASM_X86_LINKAGE_H */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 32c6e17..563933e 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -11,6 +11,8 @@ */ #define MCG_CTL_P (1UL<<8) /* MCG_CAP register available */ +#define MCG_EXT_P (1ULL<<9) /* Extended registers available */ +#define MCG_CMCI_P (1ULL<<10) /* CMCI supported */ #define MCG_STATUS_RIPV (1UL<<0) /* restart ip valid */ #define MCG_STATUS_EIPV (1UL<<1) /* ip points to correct instruction */ @@ -90,14 +92,29 @@ extern int mce_disabled; #include <asm/atomic.h> +void mce_setup(struct mce *m); void mce_log(struct mce *m); DECLARE_PER_CPU(struct sys_device, device_mce); extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu); +/* + * To support more than 128 would need to escape the predefined + * Linux defined extended banks first. + */ +#define MAX_NR_BANKS (MCE_EXTENDED_BANK - 1) + #ifdef CONFIG_X86_MCE_INTEL void mce_intel_feature_init(struct cpuinfo_x86 *c); +void cmci_clear(void); +void cmci_reenable(void); +void cmci_rediscover(int dying); +void cmci_recheck(void); #else static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { } +static inline void cmci_clear(void) {} +static inline void cmci_reenable(void) {} +static inline void cmci_rediscover(int dying) {} +static inline void cmci_recheck(void) {} #endif #ifdef CONFIG_X86_MCE_AMD @@ -106,11 +123,23 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c); static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { } #endif -void mce_log_therm_throt_event(unsigned int cpu, __u64 status); +extern int mce_available(struct cpuinfo_x86 *c); + +void mce_log_therm_throt_event(__u64 status); extern atomic_t mce_entry; extern void do_machine_check(struct pt_regs *, long); + +typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS); +DECLARE_PER_CPU(mce_banks_t, mce_poll_banks); + +enum mcp_flags { + MCP_TIMESTAMP = (1 << 0), /* log time stamp */ + MCP_UC = (1 << 1), /* log uncorrected errors */ +}; +extern void machine_check_poll(enum mcp_flags flags, mce_banks_t *b); + extern int mce_notify_user(void); #endif /* !CONFIG_X86_32 */ @@ -120,8 +149,8 @@ extern void mcheck_init(struct cpuinfo_x86 *c); #else #define mcheck_init(c) do { } while (0) #endif -extern void stop_mce(void); -extern void restart_mce(void); + +extern void (*mce_threshold_vector)(void); #endif /* __KERNEL__ */ #endif /* _ASM_X86_MCE_H */ diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h index 105fb90..ede6998 100644 --- a/arch/x86/include/asm/mmzone_32.h +++ b/arch/x86/include/asm/mmzone_32.h @@ -91,46 +91,9 @@ static inline int pfn_valid(int pfn) #endif /* CONFIG_DISCONTIGMEM */ #ifdef CONFIG_NEED_MULTIPLE_NODES - -/* - * Following are macros that are specific to this numa platform. - */ -#define reserve_bootmem(addr, size, flags) \ - reserve_bootmem_node(NODE_DATA(0), (addr), (size), (flags)) -#define alloc_bootmem(x) \ - __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_nopanic(x) \ - __alloc_bootmem_node_nopanic(NODE_DATA(0), (x), SMP_CACHE_BYTES, \ - __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_low(x) \ - __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, 0) -#define alloc_bootmem_pages(x) \ - __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_pages_nopanic(x) \ - __alloc_bootmem_node_nopanic(NODE_DATA(0), (x), PAGE_SIZE, \ - __pa(MAX_DMA_ADDRESS)) -#define alloc_bootmem_low_pages(x) \ - __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0) -#define alloc_bootmem_node(pgdat, x) \ -({ \ - struct pglist_data __maybe_unused \ - *__alloc_bootmem_node__pgdat = (pgdat); \ - __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, \ - __pa(MAX_DMA_ADDRESS)); \ -}) -#define alloc_bootmem_pages_node(pgdat, x) \ -({ \ - struct pglist_data __maybe_unused \ - *__alloc_bootmem_node__pgdat = (pgdat); \ - __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, \ - __pa(MAX_DMA_ADDRESS)); \ -}) -#define alloc_bootmem_low_pages_node(pgdat, x) \ -({ \ - struct pglist_data __maybe_unused \ - *__alloc_bootmem_node__pgdat = (pgdat); \ - __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0); \ -}) +/* always use node 0 for bootmem on this numa platform */ +#define bootmem_arch_preferred_node(__bdata, size, align, goal, limit) \ + (NODE_DATA(0)->bdata) #endif /* CONFIG_NEED_MULTIPLE_NODES */ #endif /* _ASM_X86_MMZONE_32_H */ diff --git a/arch/x86/include/asm/msidef.h b/arch/x86/include/asm/msidef.h index 6706b30..4cc48af 100644 --- a/arch/x86/include/asm/msidef.h +++ b/arch/x86/include/asm/msidef.h @@ -47,6 +47,7 @@ #define MSI_ADDR_DEST_ID_MASK 0x00ffff0 #define MSI_ADDR_DEST_ID(dest) (((dest) << MSI_ADDR_DEST_ID_SHIFT) & \ MSI_ADDR_DEST_ID_MASK) +#define MSI_ADDR_EXT_DEST_ID(dest) ((dest) & 0xffffff00) #define MSI_ADDR_IR_EXT_INT (1 << 4) #define MSI_ADDR_IR_SHV (1 << 3) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 358acc5..ec41fc1 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -18,11 +18,15 @@ #define _EFER_LME 8 /* Long mode enable */ #define _EFER_LMA 10 /* Long mode active (read-only) */ #define _EFER_NX 11 /* No execute enable */ +#define _EFER_SVME 12 /* Enable virtualization */ +#define _EFER_FFXSR 14 /* Enable Fast FXSAVE/FXRSTOR */ #define EFER_SCE (1<<_EFER_SCE) #define EFER_LME (1<<_EFER_LME) #define EFER_LMA (1<<_EFER_LMA) #define EFER_NX (1<<_EFER_NX) +#define EFER_SVME (1<<_EFER_SVME) +#define EFER_FFXSR (1<<_EFER_FFXSR) /* Intel MSRs. Some also available on other CPUs */ #define MSR_IA32_PERFCTR0 0x000000c1 @@ -77,6 +81,11 @@ #define MSR_IA32_MC0_ADDR 0x00000402 #define MSR_IA32_MC0_MISC 0x00000403 +/* These are consecutive and not in the normal 4er MCE bank block */ +#define MSR_IA32_MC0_CTL2 0x00000280 +#define CMCI_EN (1ULL << 30) +#define CMCI_THRESHOLD_MASK 0xffffULL + #define MSR_P6_PERFCTR0 0x000000c1 #define MSR_P6_PERFCTR1 0x000000c2 #define MSR_P6_EVNTSEL0 0x00000186 @@ -360,4 +369,9 @@ #define MSR_IA32_VMX_PROCBASED_CTLS2 0x0000048b #define MSR_IA32_VMX_EPT_VPID_CAP 0x0000048c +/* AMD-V MSRs */ + +#define MSR_VM_CR 0xc0010114 +#define MSR_VM_HSAVE_PA 0xc0010117 + #endif /* _ASM_X86_MSR_INDEX_H */ diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h index e9f5db7..a372290 100644 --- a/arch/x86/include/asm/numa_32.h +++ b/arch/x86/include/asm/numa_32.h @@ -4,8 +4,12 @@ extern int pxm_to_nid(int pxm); extern void numa_remove_cpu(int cpu); -#ifdef CONFIG_NUMA +#ifdef CONFIG_HIGHMEM extern void set_highmem_pages_init(void); +#else +static inline void set_highmem_pages_init(void) +{ +} #endif #endif /* _ASM_X86_NUMA_32_H */ diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h index f1e4a79..0f915ae 100644 --- a/arch/x86/include/asm/page_32_types.h +++ b/arch/x86/include/asm/page_32_types.h @@ -39,6 +39,11 @@ #define __VIRTUAL_MASK_SHIFT 32 #endif /* CONFIG_X86_PAE */ +/* + * Kernel image size is limited to 512 MB (see in arch/x86/kernel/head_32.S) + */ +#define KERNEL_IMAGE_SIZE (512 * 1024 * 1024) + #ifndef __ASSEMBLY__ /* diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index 2d625da..826ad37 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -40,14 +40,8 @@ #ifndef __ASSEMBLY__ -struct pgprot; - extern int page_is_ram(unsigned long pagenr); extern int devmem_is_allowed(unsigned long pagenr); -extern void map_devmem(unsigned long pfn, unsigned long size, - struct pgprot vma_prot); -extern void unmap_devmem(unsigned long pfn, unsigned long size, - struct pgprot vma_prot); extern unsigned long max_low_pfn_mapped; extern unsigned long max_pfn_mapped; diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 0617d5c..7727aa8 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -317,8 +317,6 @@ struct pv_mmu_ops { #if PAGETABLE_LEVELS >= 3 #ifdef CONFIG_X86_PAE void (*set_pte_atomic)(pte_t *ptep, pte_t pteval); - void (*set_pte_present)(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte); void (*pte_clear)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); void (*pmd_clear)(pmd_t *pmdp); @@ -389,7 +387,7 @@ extern struct pv_lock_ops pv_lock_ops; #define paravirt_type(op) \ [paravirt_typenum] "i" (PARAVIRT_PATCH(op)), \ - [paravirt_opptr] "m" (op) + [paravirt_opptr] "i" (&(op)) #define paravirt_clobber(clobber) \ [paravirt_clobber] "i" (clobber) @@ -443,7 +441,7 @@ int paravirt_disable_iospace(void); * offset into the paravirt_patch_template structure, and can therefore be * freely converted back into a structure offset. */ -#define PARAVIRT_CALL "call *%[paravirt_opptr];" +#define PARAVIRT_CALL "call *%c[paravirt_opptr];" /* * These macros are intended to wrap calls through one of the paravirt @@ -1365,13 +1363,6 @@ static inline void set_pte_atomic(pte_t *ptep, pte_t pte) pte.pte, pte.pte >> 32); } -static inline void set_pte_present(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) -{ - /* 5 arg words */ - pv_mmu_ops.set_pte_present(mm, addr, ptep, pte); -} - static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -1388,12 +1379,6 @@ static inline void set_pte_atomic(pte_t *ptep, pte_t pte) set_pte(ptep, pte); } -static inline void set_pte_present(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) -{ - set_pte(ptep, pte); -} - static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index b0e7005..2cd07b9 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -2,6 +2,7 @@ #define _ASM_X86_PAT_H #include <linux/types.h> +#include <asm/pgtable_types.h> #ifdef CONFIG_X86_PAT extern int pat_enabled; @@ -17,5 +18,9 @@ extern int free_memtype(u64 start, u64 end); extern int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flag); +extern void map_devmem(unsigned long pfn, unsigned long size, + struct pgprot vma_prot); +extern void unmap_devmem(unsigned long pfn, unsigned long size, + struct pgprot vma_prot); #endif /* _ASM_X86_PAT_H */ diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index a977de2..b51a1e8 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -86,12 +86,43 @@ static inline void early_quirks(void) { } extern void pci_iommu_alloc(void); -#endif /* __KERNEL__ */ +/* MSI arch hook */ +#define arch_setup_msi_irqs arch_setup_msi_irqs + +#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys) + +#if defined(CONFIG_X86_64) || defined(CONFIG_DMA_API_DEBUG) + +#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ + dma_addr_t ADDR_NAME; +#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ + __u32 LEN_NAME; +#define pci_unmap_addr(PTR, ADDR_NAME) \ + ((PTR)->ADDR_NAME) +#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ + (((PTR)->ADDR_NAME) = (VAL)) +#define pci_unmap_len(PTR, LEN_NAME) \ + ((PTR)->LEN_NAME) +#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ + (((PTR)->LEN_NAME) = (VAL)) -#ifdef CONFIG_X86_32 -# include "pci_32.h" #else -# include "pci_64.h" + +#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME[0]; +#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) unsigned LEN_NAME[0]; +#define pci_unmap_addr(PTR, ADDR_NAME) sizeof((PTR)->ADDR_NAME) +#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ + do { break; } while (pci_unmap_addr(PTR, ADDR_NAME)) +#define pci_unmap_len(PTR, LEN_NAME) sizeof((PTR)->LEN_NAME) +#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ + do { break; } while (pci_unmap_len(PTR, LEN_NAME)) + +#endif + +#endif /* __KERNEL__ */ + +#ifdef CONFIG_X86_64 +#include "pci_64.h" #endif /* implement the pci_ DMA API in terms of the generic device dma_ one */ @@ -109,11 +140,6 @@ static inline int __pcibus_to_node(const struct pci_bus *bus) return sd->node; } -static inline cpumask_t __pcibus_to_cpumask(struct pci_bus *bus) -{ - return node_to_cpumask(__pcibus_to_node(bus)); -} - static inline const struct cpumask * cpumask_of_pcibus(const struct pci_bus *bus) { diff --git a/arch/x86/include/asm/pci_32.h b/arch/x86/include/asm/pci_32.h deleted file mode 100644 index 6f1213a..0000000 --- a/arch/x86/include/asm/pci_32.h +++ /dev/null @@ -1,34 +0,0 @@ -#ifndef _ASM_X86_PCI_32_H -#define _ASM_X86_PCI_32_H - - -#ifdef __KERNEL__ - - -/* Dynamic DMA mapping stuff. - * i386 has everything mapped statically. - */ - -struct pci_dev; - -/* The PCI address space does equal the physical memory - * address space. The networking and block device layers use - * this boolean for bounce buffer decisions. - */ -#define PCI_DMA_BUS_IS_PHYS (1) - -/* pci_unmap_{page,single} is a nop so... */ -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME[0]; -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) unsigned LEN_NAME[0]; -#define pci_unmap_addr(PTR, ADDR_NAME) sizeof((PTR)->ADDR_NAME) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ - do { break; } while (pci_unmap_addr(PTR, ADDR_NAME)) -#define pci_unmap_len(PTR, LEN_NAME) sizeof((PTR)->LEN_NAME) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ - do { break; } while (pci_unmap_len(PTR, LEN_NAME)) - - -#endif /* __KERNEL__ */ - - -#endif /* _ASM_X86_PCI_32_H */ diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h index 4da2079..ae5e40f 100644 --- a/arch/x86/include/asm/pci_64.h +++ b/arch/x86/include/asm/pci_64.h @@ -24,28 +24,6 @@ extern int (*pci_config_write)(int seg, int bus, int dev, int fn, extern void dma32_reserve_bootmem(void); -/* The PCI address space does equal the physical memory - * address space. The networking and block device layers use - * this boolean for bounce buffer decisions - * - * On AMD64 it mostly equals, but we set it to zero if a hardware - * IOMMU (gart) of sotware IOMMU (swiotlb) is available. - */ -#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys) - -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ - dma_addr_t ADDR_NAME; -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ - __u32 LEN_NAME; -#define pci_unmap_addr(PTR, ADDR_NAME) \ - ((PTR)->ADDR_NAME) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ - (((PTR)->ADDR_NAME) = (VAL)) -#define pci_unmap_len(PTR, LEN_NAME) \ - ((PTR)->LEN_NAME) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ - (((PTR)->LEN_NAME) = (VAL)) - #endif /* __KERNEL__ */ #endif /* _ASM_X86_PCI_64_H */ diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index c1774ac..2334982 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -26,13 +26,6 @@ static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) native_set_pte(ptep, pte); } -static inline void native_set_pte_present(struct mm_struct *mm, - unsigned long addr, - pte_t *ptep, pte_t pte) -{ - native_set_pte(ptep, pte); -} - static inline void native_pmd_clear(pmd_t *pmdp) { native_set_pmd(pmdp, __pmd(0)); diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index 3f13cdf..177b016 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -31,23 +31,6 @@ static inline void native_set_pte(pte_t *ptep, pte_t pte) ptep->pte_low = pte.pte_low; } -/* - * Since this is only called on user PTEs, and the page fault handler - * must handle the already racy situation of simultaneous page faults, - * we are justified in merely clearing the PTE present bit, followed - * by a set. The ordering here is important. - */ -static inline void native_set_pte_present(struct mm_struct *mm, - unsigned long addr, - pte_t *ptep, pte_t pte) -{ - ptep->pte_low = 0; - smp_wmb(); - ptep->pte_high = pte.pte_high; - smp_wmb(); - ptep->pte_low = pte.pte_low; -} - static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) { set_64bit((unsigned long long *)(ptep), native_pte_val(pte)); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 1c097a3..29d96d1 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -31,8 +31,6 @@ extern struct list_head pgd_list; #define set_pte(ptep, pte) native_set_pte(ptep, pte) #define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte) -#define set_pte_present(mm, addr, ptep, pte) \ - native_set_pte_present(mm, addr, ptep, pte) #define set_pte_atomic(ptep, pte) \ native_set_pte_atomic(ptep, pte) @@ -288,6 +286,8 @@ static inline int is_new_memtype_allowed(unsigned long flags, return 1; } +pmd_t *populate_extra_pmd(unsigned long vaddr); +pte_t *populate_extra_pte(unsigned long vaddr); #endif /* __ASSEMBLY__ */ #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index 97612fc..31bd120 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -42,9 +42,6 @@ extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t); */ #undef TEST_ACCESS_OK -/* The boot page tables (all created as a single array) */ -extern unsigned long pg0[]; - #ifdef CONFIG_X86_PAE # include <asm/pgtable-3level.h> #else diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index bd8df3b..2733fad 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -25,6 +25,11 @@ * area for the same reason. ;) */ #define VMALLOC_OFFSET (8 * 1024 * 1024) + +#ifndef __ASSEMBLER__ +extern bool __vmalloc_start_set; /* set once high_memory is set */ +#endif + #define VMALLOC_START ((unsigned long)high_memory + VMALLOC_OFFSET) #ifdef CONFIG_X86_PAE #define LAST_PKMAP 512 diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 4d258ad..b8238dc 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -273,6 +273,7 @@ typedef struct page *pgtable_t; extern pteval_t __supported_pte_mask; extern int nx_enabled; +extern void set_nx(void); #define pgprot_writecombine pgprot_writecombine extern pgprot_t pgprot_writecombine(pgprot_t prot); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index c7a98f7..34c5237 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -75,9 +75,9 @@ struct cpuinfo_x86 { #else /* Number of 4K pages in DTLB/ITLB combined(in pages): */ int x86_tlbsize; +#endif __u8 x86_virt_bits; __u8 x86_phys_bits; -#endif /* CPUID returned core id bits: */ __u8 x86_coreid_bits; /* Max extended CPUID function supported: */ @@ -94,7 +94,7 @@ struct cpuinfo_x86 { unsigned long loops_per_jiffy; #ifdef CONFIG_SMP /* cpus sharing the last level cache: */ - cpumask_t llc_shared_map; + cpumask_var_t llc_shared_map; #endif /* cpuid returned max cores value: */ u16 x86_max_cores; @@ -248,7 +248,6 @@ struct x86_hw_tss { #define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long)) #define IO_BITMAP_OFFSET offsetof(struct tss_struct, io_bitmap) #define INVALID_IO_BITMAP_OFFSET 0x8000 -#define INVALID_IO_BITMAP_OFFSET_LAZY 0x9000 struct tss_struct { /* @@ -263,11 +262,6 @@ struct tss_struct { * be within the limit. */ unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; - /* - * Cache the current maximum and the last task that used the bitmap: - */ - unsigned long io_bitmap_max; - struct thread_struct *io_bitmap_owner; /* * .. and then another 0x100 bytes for the emergency kernel stack: @@ -397,6 +391,9 @@ DECLARE_PER_CPU(union irq_stack_union, irq_stack_union); DECLARE_INIT_PER_CPU(irq_stack_union); DECLARE_PER_CPU(char *, irq_stack_ptr); +DECLARE_PER_CPU(unsigned int, irq_count); +extern unsigned long kernel_eflags; +extern asmlinkage void ignore_sysret(void); #else /* X86_64 */ #ifdef CONFIG_CC_STACKPROTECTOR DECLARE_PER_CPU(unsigned long, stack_canary); @@ -739,6 +736,7 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx) extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx); extern void select_idle_routine(const struct cpuinfo_x86 *c); +extern void init_c1e_mask(void); extern unsigned long boot_option_idle_override; extern unsigned long idle_halt; diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h index 8e0f8d1..8672303 100644 --- a/arch/x86/include/asm/ptrace-abi.h +++ b/arch/x86/include/asm/ptrace-abi.h @@ -80,8 +80,6 @@ #define PTRACE_SINGLEBLOCK 33 /* resume execution until next branch */ -#ifdef CONFIG_X86_PTRACE_BTS - #ifndef __ASSEMBLY__ #include <linux/types.h> @@ -140,6 +138,5 @@ struct ptrace_bts_config { BTS records are read from oldest to newest. Returns number of BTS records drained. */ -#endif /* CONFIG_X86_PTRACE_BTS */ #endif /* _ASM_X86_PTRACE_ABI_H */ diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index 2b8c516..1b7ee5d 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -1 +1,8 @@ +#ifndef _ASM_X86_SECTIONS_H +#define _ASM_X86_SECTIONS_H + #include <asm-generic/sections.h> + +extern char __brk_base[], __brk_limit[]; + +#endif /* _ASM_X86_SECTIONS_H */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 66801cb..bdc2ada 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -31,7 +31,6 @@ struct x86_quirks { void (*smp_read_mpc_oem)(struct mpc_oemtable *oemtable, unsigned short oemsize); int (*setup_ioapic_ids)(void); - int (*update_apic)(void); }; extern void x86_quirk_pre_intr_init(void); @@ -65,7 +64,11 @@ extern void x86_quirk_time_init(void); #include <asm/bootparam.h> /* Interrupt control for vSMPowered x86_64 systems */ +#ifdef CONFIG_X86_64 void vsmp_init(void); +#else +static inline void vsmp_init(void) { } +#endif void setup_bios_corruption_check(void); @@ -77,8 +80,6 @@ static inline void visws_early_detect(void) { } static inline int is_visws_box(void) { return 0; } #endif -extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip); -extern int wakeup_secondary_cpu_via_init(int apicid, unsigned long start_eip); extern struct x86_quirks *x86_quirks; extern unsigned long saved_video_mode; @@ -99,20 +100,51 @@ extern struct boot_params boot_params; */ #define LOWMEMSIZE() (0x9f000) +/* exceedingly early brk-like allocator */ +extern unsigned long _brk_end; +void *extend_brk(size_t size, size_t align); + +/* + * Reserve space in the brk section. The name must be unique within + * the file, and somewhat descriptive. The size is in bytes. Must be + * used at file scope. + * + * (This uses a temp function to wrap the asm so we can pass it the + * size parameter; otherwise we wouldn't be able to. We can't use a + * "section" attribute on a normal variable because it always ends up + * being @progbits, which ends up allocating space in the vmlinux + * executable.) + */ +#define RESERVE_BRK(name,sz) \ + static void __section(.discard) __used \ + __brk_reservation_fn_##name##__(void) { \ + asm volatile ( \ + ".pushsection .brk_reservation,\"aw\",@nobits;" \ + ".brk." #name ":" \ + " 1:.skip %c0;" \ + " .size .brk." #name ", . - 1b;" \ + " .popsection" \ + : : "i" (sz)); \ + } + #ifdef __i386__ void __init i386_start_kernel(void); extern void probe_roms(void); -extern unsigned long init_pg_tables_start; -extern unsigned long init_pg_tables_end; - #else void __init x86_64_start_kernel(char *real_mode); void __init x86_64_start_reservations(char *real_mode_data); #endif /* __i386__ */ #endif /* _SETUP */ +#else +#define RESERVE_BRK(name,sz) \ + .pushsection .brk_reservation,"aw",@nobits; \ +.brk.name: \ +1: .skip sz; \ + .size .brk.name,.-1b; \ + .popsection #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 47d0e21..19e0d88 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -21,19 +21,19 @@ extern int smp_num_siblings; extern unsigned int num_processors; -DECLARE_PER_CPU(cpumask_t, cpu_sibling_map); -DECLARE_PER_CPU(cpumask_t, cpu_core_map); +DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map); +DECLARE_PER_CPU(cpumask_var_t, cpu_core_map); DECLARE_PER_CPU(u16, cpu_llc_id); DECLARE_PER_CPU(int, cpu_number); static inline struct cpumask *cpu_sibling_mask(int cpu) { - return &per_cpu(cpu_sibling_map, cpu); + return per_cpu(cpu_sibling_map, cpu); } static inline struct cpumask *cpu_core_mask(int cpu) { - return &per_cpu(cpu_core_map, cpu); + return per_cpu(cpu_core_map, cpu); } DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid); @@ -121,9 +121,10 @@ static inline void arch_send_call_function_single_ipi(int cpu) smp_ops.send_call_func_single_ipi(cpu); } -static inline void arch_send_call_function_ipi(cpumask_t mask) +#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask +static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) { - smp_ops.send_call_func_ipi(&mask); + smp_ops.send_call_func_ipi(mask); } void cpu_disable_common(void); diff --git a/arch/x86/include/asm/socket.h b/arch/x86/include/asm/socket.h index 8ab9cc8..ca8bf2c 100644 --- a/arch/x86/include/asm/socket.h +++ b/arch/x86/include/asm/socket.h @@ -54,4 +54,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _ASM_X86_SOCKET_H */ diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 3a56966..e5e6caf 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -295,6 +295,9 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw) : "+m" (rw->lock) : "i" (RW_LOCK_BIAS) : "memory"); } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index a5074bd..48dcfa6 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -24,28 +24,4 @@ struct saved_context { unsigned long return_address; } __attribute__((packed)); -#ifdef CONFIG_ACPI -extern unsigned long saved_eip; -extern unsigned long saved_esp; -extern unsigned long saved_ebp; -extern unsigned long saved_ebx; -extern unsigned long saved_esi; -extern unsigned long saved_edi; - -static inline void acpi_save_register_state(unsigned long return_point) -{ - saved_eip = return_point; - asm volatile("movl %%esp,%0" : "=m" (saved_esp)); - asm volatile("movl %%ebp,%0" : "=m" (saved_ebp)); - asm volatile("movl %%ebx,%0" : "=m" (saved_ebx)); - asm volatile("movl %%edi,%0" : "=m" (saved_edi)); - asm volatile("movl %%esi,%0" : "=m" (saved_esi)); -} - -#define acpi_restore_register_state() do {} while (0) - -/* routines for saving/restoring kernel state */ -extern int acpi_save_state_mem(void); -#endif - #endif /* _ASM_X86_SUSPEND_32_H */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 1b8afa7..82ada75 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -174,10 +174,6 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_CPUID_FEATURE_SHIFT 2 #define SVM_CPUID_FUNC 0x8000000a -#define MSR_EFER_SVME_MASK (1ULL << 12) -#define MSR_VM_CR 0xc0010114 -#define MSR_VM_HSAVE_PA 0xc0010117ULL - #define SVM_VM_CR_SVM_DISABLE 4 #define SVM_SELECTOR_S_SHIFT 4 diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index ffb08be..72a6dcd 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -70,8 +70,6 @@ struct old_utsname; asmlinkage long sys32_olduname(struct oldold_utsname __user *); long sys32_uname(struct old_utsname __user *); -long sys32_ustat(unsigned, struct ustat32 __user *); - asmlinkage long sys32_execve(char __user *, compat_uptr_t __user *, compat_uptr_t __user *, struct pt_regs *); asmlinkage long sys32_clone(unsigned int, unsigned int, struct pt_regs *); diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index c00bfdb..643c59b 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -20,6 +20,9 @@ struct task_struct; /* one of the stranger aspects of C forward declarations */ struct task_struct *__switch_to(struct task_struct *prev, struct task_struct *next); +struct tss_struct; +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, + struct tss_struct *tss); #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index ca7310e..3ffd5d2 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -95,6 +95,7 @@ struct thread_info { #define TIF_FORCED_TF 24 /* true if TF in eflags artificially */ #define TIF_DEBUGCTLMSR 25 /* uses thread_struct.debugctlmsr */ #define TIF_DS_AREA_MSR 26 /* uses thread_struct.ds_area_msr */ +#define TIF_SYSCALL_FTRACE 27 /* for ftrace syscall instrumentation */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) @@ -117,15 +118,17 @@ struct thread_info { #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) #define _TIF_DEBUGCTLMSR (1 << TIF_DEBUGCTLMSR) #define _TIF_DS_AREA_MSR (1 << TIF_DS_AREA_MSR) +#define _TIF_SYSCALL_FTRACE (1 << TIF_SYSCALL_FTRACE) /* work to do in syscall_trace_enter() */ #define _TIF_WORK_SYSCALL_ENTRY \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | \ + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_FTRACE | \ _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | _TIF_SINGLESTEP) /* work to do in syscall_trace_leave() */ #define _TIF_WORK_SYSCALL_EXIT \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP) + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP | \ + _TIF_SYSCALL_FTRACE) /* work to do on interrupt/exception return */ #define _TIF_WORK_MASK \ @@ -134,7 +137,7 @@ struct thread_info { _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU)) /* work to do on any return to user space */ -#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP) +#define _TIF_ALLWORK_MASK ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_FTRACE) /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index a81195e..bd37ed4 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -12,9 +12,9 @@ unsigned long native_calibrate_tsc(void); #ifdef CONFIG_X86_32 extern int timer_ack; -extern int recalibrate_cpu_khz(void); extern irqreturn_t timer_interrupt(int irq, void *dev_id); #endif /* CONFIG_X86_32 */ +extern int recalibrate_cpu_khz(void); extern int no_timer_check; diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 77cfb2c..892b119 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -44,9 +44,6 @@ #ifdef CONFIG_X86_32 -/* Mappings between node number and cpus on that node. */ -extern cpumask_t node_to_cpumask_map[]; - /* Mappings between logical cpu number and node number */ extern int cpu_to_node_map[]; @@ -57,30 +54,8 @@ static inline int cpu_to_node(int cpu) } #define early_cpu_to_node(cpu) cpu_to_node(cpu) -/* Returns a bitmask of CPUs on Node 'node'. - * - * Side note: this function creates the returned cpumask on the stack - * so with a high NR_CPUS count, excessive stack space is used. The - * cpumask_of_node function should be used whenever possible. - */ -static inline cpumask_t node_to_cpumask(int node) -{ - return node_to_cpumask_map[node]; -} - -/* Returns a bitmask of CPUs on Node 'node'. */ -static inline const struct cpumask *cpumask_of_node(int node) -{ - return &node_to_cpumask_map[node]; -} - -static inline void setup_node_to_cpumask_map(void) { } - #else /* CONFIG_X86_64 */ -/* Mappings between node number and cpus on that node. */ -extern cpumask_t *node_to_cpumask_map; - /* Mappings between logical cpu number and node number */ DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map); @@ -91,8 +66,6 @@ DECLARE_PER_CPU(int, node_number); #ifdef CONFIG_DEBUG_PER_CPU_MAPS extern int cpu_to_node(int cpu); extern int early_cpu_to_node(int cpu); -extern const cpumask_t *cpumask_of_node(int node); -extern cpumask_t node_to_cpumask(int node); #else /* !CONFIG_DEBUG_PER_CPU_MAPS */ @@ -108,42 +81,32 @@ static inline int early_cpu_to_node(int cpu) return early_per_cpu(x86_cpu_to_node_map, cpu); } -/* Returns a pointer to the cpumask of CPUs on Node 'node'. */ -static inline const cpumask_t *cpumask_of_node(int node) -{ - return &node_to_cpumask_map[node]; -} +#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ + +#endif /* CONFIG_X86_64 */ -/* Returns a bitmask of CPUs on Node 'node'. */ -static inline cpumask_t node_to_cpumask(int node) +/* Mappings between node number and cpus on that node. */ +extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +extern const struct cpumask *cpumask_of_node(int node); +#else +/* Returns a pointer to the cpumask of CPUs on Node 'node'. */ +static inline const struct cpumask *cpumask_of_node(int node) { return node_to_cpumask_map[node]; } - -#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ +#endif extern void setup_node_to_cpumask_map(void); /* - * Replace default node_to_cpumask_ptr with optimized version - * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)" - */ -#define node_to_cpumask_ptr(v, node) \ - const cpumask_t *v = cpumask_of_node(node) - -#define node_to_cpumask_ptr_next(v, node) \ - v = cpumask_of_node(node) - -#endif /* CONFIG_X86_64 */ - -/* * Returns the number of the node containing Node 'node'. This * architecture is flat, so it is a pretty simple function! */ #define parent_node(node) (node) #define pcibus_to_node(bus) __pcibus_to_node(bus) -#define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus) #ifdef CONFIG_X86_32 extern unsigned long node_start_pfn[]; @@ -209,52 +172,24 @@ static inline int early_cpu_to_node(int cpu) return 0; } -static inline const cpumask_t *cpumask_of_node(int node) -{ - return &cpu_online_map; -} -static inline cpumask_t node_to_cpumask(int node) -{ - return cpu_online_map; -} -static inline int node_to_first_cpu(int node) +static inline const struct cpumask *cpumask_of_node(int node) { - return first_cpu(cpu_online_map); + return cpu_online_mask; } static inline void setup_node_to_cpumask_map(void) { } -/* - * Replace default node_to_cpumask_ptr with optimized version - * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)" - */ -#define node_to_cpumask_ptr(v, node) \ - const cpumask_t *v = cpumask_of_node(node) - -#define node_to_cpumask_ptr_next(v, node) \ - v = cpumask_of_node(node) #endif #include <asm-generic/topology.h> -#ifdef CONFIG_NUMA -/* Returns the number of the first CPU on Node 'node'. */ -static inline int node_to_first_cpu(int node) -{ - return cpumask_first(cpumask_of_node(node)); -} -#endif - -extern cpumask_t cpu_coregroup_map(int cpu); extern const struct cpumask *cpu_coregroup_mask(int cpu); #ifdef ENABLE_TOPO_DEFINES #define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id) #define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) -#define topology_core_siblings(cpu) (per_cpu(cpu_core_map, cpu)) -#define topology_thread_siblings(cpu) (per_cpu(cpu_sibling_map, cpu)) -#define topology_core_cpumask(cpu) (&per_cpu(cpu_core_map, cpu)) -#define topology_thread_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu)) +#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) +#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) /* indicates that pointers to the topology cpumask_t maps are valid */ #define arch_provides_topology_pointers yes @@ -268,7 +203,7 @@ struct pci_bus; void set_pci_bus_resources_arch_default(struct pci_bus *b); #ifdef CONFIG_SMP -#define mc_capable() (cpus_weight(per_cpu(cpu_core_map, 0)) != nr_cpu_ids) +#define mc_capable() (cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids) #define smt_capable() (smp_num_siblings > 1) #endif diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index a0ba613..5e06259 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -157,7 +157,7 @@ __copy_from_user(void *to, const void __user *from, unsigned long n) } static __always_inline unsigned long __copy_from_user_nocache(void *to, - const void __user *from, unsigned long n, unsigned long total) + const void __user *from, unsigned long n) { might_fault(); if (__builtin_constant_p(n)) { @@ -180,7 +180,7 @@ static __always_inline unsigned long __copy_from_user_nocache(void *to, static __always_inline unsigned long __copy_from_user_inatomic_nocache(void *to, const void __user *from, - unsigned long n, unsigned long total) + unsigned long n) { return __copy_from_user_ll_nocache_nozero(to, from, n); } diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index dcaa0404..8cc6873 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -188,29 +188,18 @@ __copy_to_user_inatomic(void __user *dst, const void *src, unsigned size) extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size, int zerorest); -static inline int __copy_from_user_nocache(void *dst, const void __user *src, - unsigned size, unsigned long total) +static inline int +__copy_from_user_nocache(void *dst, const void __user *src, unsigned size) { might_sleep(); - /* - * In practice this limit means that large file write()s - * which get chunked to 4K copies get handled via - * non-temporal stores here. Smaller writes get handled - * via regular __copy_from_user(): - */ - if (likely(total >= PAGE_SIZE)) - return __copy_user_nocache(dst, src, size, 1); - else - return __copy_from_user(dst, src, size); + return __copy_user_nocache(dst, src, size, 1); } -static inline int __copy_from_user_inatomic_nocache(void *dst, - const void __user *src, unsigned size, unsigned total) +static inline int +__copy_from_user_inatomic_nocache(void *dst, const void __user *src, + unsigned size) { - if (likely(total >= PAGE_SIZE)) - return __copy_user_nocache(dst, src, size, 0); - else - return __copy_from_user_inatomic(dst, src, size); + return __copy_user_nocache(dst, src, size, 0); } unsigned long diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index 7e47658..0b4d8c2 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -338,6 +338,8 @@ #define __NR_dup3 330 #define __NR_pipe2 331 #define __NR_inotify_init1 332 +#define __NR_preadv 333 +#define __NR_pwritev 334 #define __NR_perf_counter_open 333 #ifdef __KERNEL__ diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 53025fe..d9aad87 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -653,6 +653,10 @@ __SYSCALL(__NR_dup3, sys_dup3) __SYSCALL(__NR_pipe2, sys_pipe2) #define __NR_inotify_init1 294 __SYSCALL(__NR_inotify_init1, sys_inotify_init1) +#define __NR_preadv 295 +__SYSCALL(__NR_preadv, sys_preadv) +#define __NR_pwritev 296 +__SYSCALL(__NR_pwritev, sys_pwritev) #define __NR_perf_counter_open 295 __SYSCALL(__NR_perf_counter_open, sys_perf_counter_open) diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index 8242bf9..c0a01b5 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -12,7 +12,6 @@ extern enum uv_system_type get_uv_system_type(void); extern int is_uv_system(void); extern void uv_cpu_init(void); extern void uv_system_init(void); -extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip); extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long va, @@ -24,8 +23,6 @@ static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; } static inline int is_uv_system(void) { return 0; } static inline void uv_cpu_init(void) { } static inline void uv_system_init(void) { } -static inline int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip) -{ return 1; } static inline const struct cpumask * uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long va, unsigned int cpu) diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 777327e..d3a98ea 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -11,11 +11,13 @@ #ifndef _ASM_X86_UV_UV_HUB_H #define _ASM_X86_UV_UV_HUB_H +#ifdef CONFIG_X86_64 #include <linux/numa.h> #include <linux/percpu.h> #include <linux/timer.h> #include <asm/types.h> #include <asm/percpu.h> +#include <asm/uv/uv_mmrs.h> /* @@ -199,6 +201,10 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info); #define SCIR_CPU_ACTIVITY 0x02 /* not idle */ #define SCIR_CPU_HB_INTERVAL (HZ) /* once per second */ +/* Loop through all installed blades */ +#define for_each_possible_blade(bid) \ + for ((bid) = 0; (bid) < uv_num_possible_blades(); (bid)++) + /* * Macros for converting between kernel virtual addresses, socket local physical * addresses, and UV global physical addresses. @@ -393,6 +399,7 @@ static inline void uv_set_scir_bits(unsigned char value) uv_write_local_mmr8(uv_hub_info->scir.offset, value); } } + static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value) { if (uv_cpu_hub_info(cpu)->scir.state != value) { @@ -401,4 +408,15 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value) } } +static inline void uv_hub_send_ipi(int pnode, int apicid, int vector) +{ + unsigned long val; + + val = (1UL << UVH_IPI_INT_SEND_SHFT) | + ((apicid & 0x3f) << UVH_IPI_INT_APIC_ID_SHFT) | + (vector << UVH_IPI_INT_VECTOR_SHFT); + uv_write_global_mmr64(pnode, UVH_IPI_INT, val); +} + +#endif /* CONFIG_X86_64 */ #endif /* _ASM_X86_UV_UV_HUB_H */ diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h index dd62779..db68ac8 100644 --- a/arch/x86/include/asm/uv/uv_mmrs.h +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -1,3 +1,4 @@ + /* * 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 @@ -243,6 +244,158 @@ union uvh_event_occurred0_u { #define UVH_EVENT_OCCURRED0_ALIAS_32 0x005f0 /* ========================================================================= */ +/* UVH_GR0_TLB_INT0_CONFIG */ +/* ========================================================================= */ +#define UVH_GR0_TLB_INT0_CONFIG 0x61b00UL + +#define UVH_GR0_TLB_INT0_CONFIG_VECTOR_SHFT 0 +#define UVH_GR0_TLB_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVH_GR0_TLB_INT0_CONFIG_DM_SHFT 8 +#define UVH_GR0_TLB_INT0_CONFIG_DM_MASK 0x0000000000000700UL +#define UVH_GR0_TLB_INT0_CONFIG_DESTMODE_SHFT 11 +#define UVH_GR0_TLB_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVH_GR0_TLB_INT0_CONFIG_STATUS_SHFT 12 +#define UVH_GR0_TLB_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVH_GR0_TLB_INT0_CONFIG_P_SHFT 13 +#define UVH_GR0_TLB_INT0_CONFIG_P_MASK 0x0000000000002000UL +#define UVH_GR0_TLB_INT0_CONFIG_T_SHFT 15 +#define UVH_GR0_TLB_INT0_CONFIG_T_MASK 0x0000000000008000UL +#define UVH_GR0_TLB_INT0_CONFIG_M_SHFT 16 +#define UVH_GR0_TLB_INT0_CONFIG_M_MASK 0x0000000000010000UL +#define UVH_GR0_TLB_INT0_CONFIG_APIC_ID_SHFT 32 +#define UVH_GR0_TLB_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + +union uvh_gr0_tlb_int0_config_u { + unsigned long v; + struct uvh_gr0_tlb_int0_config_s { + unsigned long vector_ : 8; /* RW */ + unsigned long dm : 3; /* RW */ + unsigned long destmode : 1; /* RW */ + unsigned long status : 1; /* RO */ + unsigned long p : 1; /* RO */ + unsigned long rsvd_14 : 1; /* */ + unsigned long t : 1; /* RO */ + unsigned long m : 1; /* RW */ + unsigned long rsvd_17_31: 15; /* */ + unsigned long apic_id : 32; /* RW */ + } s; +}; + +/* ========================================================================= */ +/* UVH_GR0_TLB_INT1_CONFIG */ +/* ========================================================================= */ +#define UVH_GR0_TLB_INT1_CONFIG 0x61b40UL + +#define UVH_GR0_TLB_INT1_CONFIG_VECTOR_SHFT 0 +#define UVH_GR0_TLB_INT1_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVH_GR0_TLB_INT1_CONFIG_DM_SHFT 8 +#define UVH_GR0_TLB_INT1_CONFIG_DM_MASK 0x0000000000000700UL +#define UVH_GR0_TLB_INT1_CONFIG_DESTMODE_SHFT 11 +#define UVH_GR0_TLB_INT1_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVH_GR0_TLB_INT1_CONFIG_STATUS_SHFT 12 +#define UVH_GR0_TLB_INT1_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVH_GR0_TLB_INT1_CONFIG_P_SHFT 13 +#define UVH_GR0_TLB_INT1_CONFIG_P_MASK 0x0000000000002000UL +#define UVH_GR0_TLB_INT1_CONFIG_T_SHFT 15 +#define UVH_GR0_TLB_INT1_CONFIG_T_MASK 0x0000000000008000UL +#define UVH_GR0_TLB_INT1_CONFIG_M_SHFT 16 +#define UVH_GR0_TLB_INT1_CONFIG_M_MASK 0x0000000000010000UL +#define UVH_GR0_TLB_INT1_CONFIG_APIC_ID_SHFT 32 +#define UVH_GR0_TLB_INT1_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + +union uvh_gr0_tlb_int1_config_u { + unsigned long v; + struct uvh_gr0_tlb_int1_config_s { + unsigned long vector_ : 8; /* RW */ + unsigned long dm : 3; /* RW */ + unsigned long destmode : 1; /* RW */ + unsigned long status : 1; /* RO */ + unsigned long p : 1; /* RO */ + unsigned long rsvd_14 : 1; /* */ + unsigned long t : 1; /* RO */ + unsigned long m : 1; /* RW */ + unsigned long rsvd_17_31: 15; /* */ + unsigned long apic_id : 32; /* RW */ + } s; +}; + +/* ========================================================================= */ +/* UVH_GR1_TLB_INT0_CONFIG */ +/* ========================================================================= */ +#define UVH_GR1_TLB_INT0_CONFIG 0x61f00UL + +#define UVH_GR1_TLB_INT0_CONFIG_VECTOR_SHFT 0 +#define UVH_GR1_TLB_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVH_GR1_TLB_INT0_CONFIG_DM_SHFT 8 +#define UVH_GR1_TLB_INT0_CONFIG_DM_MASK 0x0000000000000700UL +#define UVH_GR1_TLB_INT0_CONFIG_DESTMODE_SHFT 11 +#define UVH_GR1_TLB_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVH_GR1_TLB_INT0_CONFIG_STATUS_SHFT 12 +#define UVH_GR1_TLB_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVH_GR1_TLB_INT0_CONFIG_P_SHFT 13 +#define UVH_GR1_TLB_INT0_CONFIG_P_MASK 0x0000000000002000UL +#define UVH_GR1_TLB_INT0_CONFIG_T_SHFT 15 +#define UVH_GR1_TLB_INT0_CONFIG_T_MASK 0x0000000000008000UL +#define UVH_GR1_TLB_INT0_CONFIG_M_SHFT 16 +#define UVH_GR1_TLB_INT0_CONFIG_M_MASK 0x0000000000010000UL +#define UVH_GR1_TLB_INT0_CONFIG_APIC_ID_SHFT 32 +#define UVH_GR1_TLB_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + +union uvh_gr1_tlb_int0_config_u { + unsigned long v; + struct uvh_gr1_tlb_int0_config_s { + unsigned long vector_ : 8; /* RW */ + unsigned long dm : 3; /* RW */ + unsigned long destmode : 1; /* RW */ + unsigned long status : 1; /* RO */ + unsigned long p : 1; /* RO */ + unsigned long rsvd_14 : 1; /* */ + unsigned long t : 1; /* RO */ + unsigned long m : 1; /* RW */ + unsigned long rsvd_17_31: 15; /* */ + unsigned long apic_id : 32; /* RW */ + } s; +}; + +/* ========================================================================= */ +/* UVH_GR1_TLB_INT1_CONFIG */ +/* ========================================================================= */ +#define UVH_GR1_TLB_INT1_CONFIG 0x61f40UL + +#define UVH_GR1_TLB_INT1_CONFIG_VECTOR_SHFT 0 +#define UVH_GR1_TLB_INT1_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVH_GR1_TLB_INT1_CONFIG_DM_SHFT 8 +#define UVH_GR1_TLB_INT1_CONFIG_DM_MASK 0x0000000000000700UL +#define UVH_GR1_TLB_INT1_CONFIG_DESTMODE_SHFT 11 +#define UVH_GR1_TLB_INT1_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVH_GR1_TLB_INT1_CONFIG_STATUS_SHFT 12 +#define UVH_GR1_TLB_INT1_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVH_GR1_TLB_INT1_CONFIG_P_SHFT 13 +#define UVH_GR1_TLB_INT1_CONFIG_P_MASK 0x0000000000002000UL +#define UVH_GR1_TLB_INT1_CONFIG_T_SHFT 15 +#define UVH_GR1_TLB_INT1_CONFIG_T_MASK 0x0000000000008000UL +#define UVH_GR1_TLB_INT1_CONFIG_M_SHFT 16 +#define UVH_GR1_TLB_INT1_CONFIG_M_MASK 0x0000000000010000UL +#define UVH_GR1_TLB_INT1_CONFIG_APIC_ID_SHFT 32 +#define UVH_GR1_TLB_INT1_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + +union uvh_gr1_tlb_int1_config_u { + unsigned long v; + struct uvh_gr1_tlb_int1_config_s { + unsigned long vector_ : 8; /* RW */ + unsigned long dm : 3; /* RW */ + unsigned long destmode : 1; /* RW */ + unsigned long status : 1; /* RO */ + unsigned long p : 1; /* RO */ + unsigned long rsvd_14 : 1; /* */ + unsigned long t : 1; /* RO */ + unsigned long m : 1; /* RW */ + unsigned long rsvd_17_31: 15; /* */ + unsigned long apic_id : 32; /* RW */ + } s; +}; + +/* ========================================================================= */ /* UVH_INT_CMPB */ /* ========================================================================= */ #define UVH_INT_CMPB 0x22080UL diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index 5936362..e0f9aa1 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -118,7 +118,7 @@ static inline void cpu_svm_disable(void) wrmsrl(MSR_VM_HSAVE_PA, 0); rdmsrl(MSR_EFER, efer); - wrmsrl(MSR_EFER, efer & ~MSR_EFER_SVME_MASK); + wrmsrl(MSR_EFER, efer & ~EFER_SVME); } /** Makes sure SVM is disabled, if it is supported on the CPU diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index d0238e6..498f944 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -270,8 +270,9 @@ enum vmcs_field { #define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */ #define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */ -#define INTR_TYPE_EXCEPTION (3 << 8) /* processor exception */ +#define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */ #define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */ +#define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */ /* GUEST_INTERRUPTIBILITY_INFO flags. */ #define GUEST_INTR_STATE_STI 0x00000001 @@ -311,7 +312,7 @@ enum vmcs_field { #define DEBUG_REG_ACCESS_TYPE 0x10 /* 4, direction of access */ #define TYPE_MOV_TO_DR (0 << 4) #define TYPE_MOV_FROM_DR (1 << 4) -#define DEBUG_REG_ACCESS_REG 0xf00 /* 11:8, general purpose reg. */ +#define DEBUG_REG_ACCESS_REG(eq) (((eq) >> 8) & 0xf) /* 11:8, general purpose reg. */ /* segment AR */ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 5e79ca6..9c371e4 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -296,6 +296,8 @@ HYPERVISOR_get_debugreg(int reg) static inline int HYPERVISOR_update_descriptor(u64 ma, u64 desc) { + if (sizeof(u64) == sizeof(long)) + return _hypercall2(int, update_descriptor, ma, desc); return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32); } diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 4bd990e..1a918dd 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -164,6 +164,7 @@ static inline pte_t __pte_ma(pteval_t x) xmaddr_t arbitrary_virt_to_machine(void *address); +unsigned long arbitrary_virt_to_mfn(void *vaddr); void make_lowmem_page_readonly(void *vaddr); void make_lowmem_page_readwrite(void *vaddr); diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index de5657c..145cce7 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -66,11 +66,11 @@ obj-$(CONFIG_X86_MPPARSE) += mpparse.o obj-y += apic/ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o -obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o +obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o +obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o -obj-y += vsmp_64.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_MODULES) += module_$(BITS).o obj-$(CONFIG_EFI) += efi.o efi_$(BITS).o efi_stub_$(BITS).o @@ -106,12 +106,12 @@ obj-$(CONFIG_MICROCODE) += microcode.o obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o -obj-$(CONFIG_SWIOTLB) += pci-swiotlb_64.o # NB rename without _64 +obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) - obj-$(CONFIG_X86_UV) += tlb_uv.o bios_uv.o uv_irq.o uv_sysfs.o + obj-$(CONFIG_X86_UV) += tlb_uv.o bios_uv.o uv_irq.o uv_sysfs.o uv_time.o obj-$(CONFIG_X86_PM_TIMER) += pmtimer_64.o obj-$(CONFIG_AUDIT) += audit_64.o @@ -120,4 +120,5 @@ ifeq ($(CONFIG_X86_64),y) obj-$(CONFIG_AMD_IOMMU) += amd_iommu_init.o amd_iommu.o obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o + obj-y += vsmp_64.o endif diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index a18eb7c..723989d 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -230,6 +230,35 @@ static void __cpuinit acpi_register_lapic(int id, u8 enabled) } static int __init +acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) +{ + struct acpi_madt_local_x2apic *processor = NULL; + + processor = (struct acpi_madt_local_x2apic *)header; + + if (BAD_MADT_ENTRY(processor, end)) + return -EINVAL; + + acpi_table_print_madt_entry(header); + +#ifdef CONFIG_X86_X2APIC + /* + * We need to register disabled CPU as well to permit + * counting disabled CPUs. This allows us to size + * cpus_possible_map more accurately, to permit + * to not preallocating memory for all NR_CPUS + * when we use CPU hotplug. + */ + acpi_register_lapic(processor->local_apic_id, /* APIC ID */ + processor->lapic_flags & ACPI_MADT_ENABLED); +#else + printk(KERN_WARNING PREFIX "x2apic entry ignored\n"); +#endif + + return 0; +} + +static int __init acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end) { struct acpi_madt_local_apic *processor = NULL; @@ -289,6 +318,25 @@ acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header, } static int __init +acpi_parse_x2apic_nmi(struct acpi_subtable_header *header, + const unsigned long end) +{ + struct acpi_madt_local_x2apic_nmi *x2apic_nmi = NULL; + + x2apic_nmi = (struct acpi_madt_local_x2apic_nmi *)header; + + if (BAD_MADT_ENTRY(x2apic_nmi, end)) + return -EINVAL; + + acpi_table_print_madt_entry(header); + + if (x2apic_nmi->lint != 1) + printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n"); + + return 0; +} + +static int __init acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long end) { struct acpi_madt_local_apic_nmi *lapic_nmi = NULL; @@ -793,6 +841,7 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void) static int __init acpi_parse_madt_lapic_entries(void) { int count; + int x2count = 0; if (!cpu_has_apic) return -ENODEV; @@ -816,22 +865,28 @@ static int __init acpi_parse_madt_lapic_entries(void) count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC, acpi_parse_sapic, MAX_APICS); - if (!count) + if (!count) { + x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC, + acpi_parse_x2apic, MAX_APICS); count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, acpi_parse_lapic, MAX_APICS); - if (!count) { + } + if (!count && !x2count) { printk(KERN_ERR PREFIX "No LAPIC entries present\n"); /* TBD: Cleanup to allow fallback to MPS */ return -ENODEV; - } else if (count < 0) { + } else if (count < 0 || x2count < 0) { printk(KERN_ERR PREFIX "Error parsing LAPIC entry\n"); /* TBD: Cleanup to allow fallback to MPS */ return count; } + x2count = + acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC_NMI, + acpi_parse_x2apic_nmi, 0); count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_NMI, acpi_parse_lapic_nmi, 0); - if (count < 0) { + if (count < 0 || x2count < 0) { printk(KERN_ERR PREFIX "Error parsing LAPIC NMI entry\n"); /* TBD: Cleanup to allow fallback to MPS */ return count; @@ -1470,7 +1525,7 @@ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d) /* * If your system is blacklisted here, but you find that acpi=force - * works for you, please contact acpi-devel@sourceforge.net + * works for you, please contact linux-acpi@vger.kernel.org */ static struct dmi_system_id __initdata acpi_dmi_table[] = { /* diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 6907b8e..f576587 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -5,6 +5,7 @@ #include <linux/kprobes.h> #include <linux/mm.h> #include <linux/vmalloc.h> +#include <linux/memory.h> #include <asm/alternative.h> #include <asm/sections.h> #include <asm/pgtable.h> @@ -12,7 +13,9 @@ #include <asm/nmi.h> #include <asm/vsyscall.h> #include <asm/cacheflush.h> +#include <asm/tlbflush.h> #include <asm/io.h> +#include <asm/fixmap.h> #define MAX_PATCH_LEN (255-1) @@ -226,6 +229,7 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end) { u8 **ptr; + mutex_lock(&text_mutex); for (ptr = start; ptr < end; ptr++) { if (*ptr < text) continue; @@ -234,6 +238,7 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end) /* turn DS segment override prefix into lock prefix */ text_poke(*ptr, ((unsigned char []){0xf0}), 1); }; + mutex_unlock(&text_mutex); } static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end) @@ -243,6 +248,7 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end if (noreplace_smp) return; + mutex_lock(&text_mutex); for (ptr = start; ptr < end; ptr++) { if (*ptr < text) continue; @@ -251,6 +257,7 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end /* turn lock prefix into DS segment override prefix */ text_poke(*ptr, ((unsigned char []){0x3E}), 1); }; + mutex_unlock(&text_mutex); } struct smp_alt_module { @@ -414,9 +421,17 @@ void __init alternative_instructions(void) that might execute the to be patched code. Other CPUs are not running. */ stop_nmi(); -#ifdef CONFIG_X86_MCE - stop_mce(); -#endif + + /* + * Don't stop machine check exceptions while patching. + * MCEs only happen when something got corrupted and in this + * case we must do something about the corruption. + * Ignoring it is worse than a unlikely patching race. + * Also machine checks tend to be broadcast and if one CPU + * goes into machine check the others follow quickly, so we don't + * expect a machine check to cause undue problems during to code + * patching. + */ apply_alternatives(__alt_instructions, __alt_instructions_end); @@ -456,9 +471,6 @@ void __init alternative_instructions(void) (unsigned long)__smp_locks_end); restart_nmi(); -#ifdef CONFIG_X86_MCE - restart_mce(); -#endif } /** @@ -495,15 +507,16 @@ void *text_poke_early(void *addr, const void *opcode, size_t len) * It means the size must be writable atomically and the address must be aligned * in a way that permits an atomic write. It also makes sure we fit on a single * page. + * + * Note: Must be called under text_mutex. */ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) { + unsigned long flags; char *vaddr; - int nr_pages = 2; struct page *pages[2]; int i; - might_sleep(); if (!core_kernel_text((unsigned long)addr)) { pages[0] = vmalloc_to_page(addr); pages[1] = vmalloc_to_page(addr + PAGE_SIZE); @@ -513,18 +526,21 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) pages[1] = virt_to_page(addr + PAGE_SIZE); } BUG_ON(!pages[0]); - if (!pages[1]) - nr_pages = 1; - vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); - BUG_ON(!vaddr); - local_irq_disable(); + local_irq_save(flags); + set_fixmap(FIX_TEXT_POKE0, page_to_phys(pages[0])); + if (pages[1]) + set_fixmap(FIX_TEXT_POKE1, page_to_phys(pages[1])); + vaddr = (char *)fix_to_virt(FIX_TEXT_POKE0); memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len); - local_irq_enable(); - vunmap(vaddr); + clear_fixmap(FIX_TEXT_POKE0); + if (pages[1]) + clear_fixmap(FIX_TEXT_POKE1); + local_flush_tlb(); sync_core(); /* Could also do a CLFLUSH here to speed up CPU recovery; but that causes hangs on some VIA CPUs. */ for (i = 0; i < len; i++) BUG_ON(((char *)addr)[i] != ((char *)opcode)[i]); + local_irq_restore(flags); return addr; } diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 5113c08..a97db99 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -22,10 +22,9 @@ #include <linux/bitops.h> #include <linux/debugfs.h> #include <linux/scatterlist.h> +#include <linux/dma-mapping.h> #include <linux/iommu-helper.h> -#ifdef CONFIG_IOMMU_API #include <linux/iommu.h> -#endif #include <asm/proto.h> #include <asm/iommu.h> #include <asm/gart.h> @@ -1297,8 +1296,10 @@ static void __unmap_single(struct amd_iommu *iommu, /* * The exported map_single function for dma_ops. */ -static dma_addr_t map_single(struct device *dev, phys_addr_t paddr, - size_t size, int dir) +static dma_addr_t map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) { unsigned long flags; struct amd_iommu *iommu; @@ -1306,6 +1307,7 @@ static dma_addr_t map_single(struct device *dev, phys_addr_t paddr, u16 devid; dma_addr_t addr; u64 dma_mask; + phys_addr_t paddr = page_to_phys(page) + offset; INC_STATS_COUNTER(cnt_map_single); @@ -1340,8 +1342,8 @@ out: /* * The exported unmap_single function for dma_ops. */ -static void unmap_single(struct device *dev, dma_addr_t dma_addr, - size_t size, int dir) +static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, + enum dma_data_direction dir, struct dma_attrs *attrs) { unsigned long flags; struct amd_iommu *iommu; @@ -1390,7 +1392,8 @@ static int map_sg_no_iommu(struct device *dev, struct scatterlist *sglist, * lists). */ static int map_sg(struct device *dev, struct scatterlist *sglist, - int nelems, int dir) + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs) { unsigned long flags; struct amd_iommu *iommu; @@ -1457,7 +1460,8 @@ unmap: * lists). */ static void unmap_sg(struct device *dev, struct scatterlist *sglist, - int nelems, int dir) + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs) { unsigned long flags; struct amd_iommu *iommu; @@ -1644,11 +1648,11 @@ static void prealloc_protection_domains(void) } } -static struct dma_mapping_ops amd_iommu_dma_ops = { +static struct dma_map_ops amd_iommu_dma_ops = { .alloc_coherent = alloc_coherent, .free_coherent = free_coherent, - .map_single = map_single, - .unmap_single = unmap_single, + .map_page = map_page, + .unmap_page = unmap_page, .map_sg = map_sg, .unmap_sg = unmap_sg, .dma_supported = amd_iommu_dma_supported, @@ -1924,6 +1928,12 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, return paddr; } +static int amd_iommu_domain_has_cap(struct iommu_domain *domain, + unsigned long cap) +{ + return 0; +} + static struct iommu_ops amd_iommu_ops = { .domain_init = amd_iommu_domain_init, .domain_destroy = amd_iommu_domain_destroy, @@ -1932,5 +1942,6 @@ static struct iommu_ops amd_iommu_ops = { .map = amd_iommu_map_range, .unmap = amd_iommu_unmap_range, .iova_to_phys = amd_iommu_iova_to_phys, + .domain_has_cap = amd_iommu_domain_has_cap, }; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 4732768..b0e5e712 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -47,6 +47,7 @@ #include <asm/idle.h> #include <asm/mtrr.h> #include <asm/smp.h> +#include <asm/mce.h> unsigned int num_processors; @@ -811,7 +812,7 @@ void clear_local_APIC(void) u32 v; /* APIC hasn't been mapped yet */ - if (!apic_phys) + if (!x2apic && !apic_phys) return; maxlvt = lapic_get_maxlvt(); @@ -845,6 +846,14 @@ void clear_local_APIC(void) apic_write(APIC_LVTTHMR, v | APIC_LVT_MASKED); } #endif +#ifdef CONFIG_X86_MCE_INTEL + if (maxlvt >= 6) { + v = apic_read(APIC_LVTCMCI); + if (!(v & APIC_LVT_MASKED)) + apic_write(APIC_LVTCMCI, v | APIC_LVT_MASKED); + } +#endif + /* * Clean APIC state for other OSs: */ @@ -1245,6 +1254,12 @@ void __cpuinit setup_local_APIC(void) apic_write(APIC_LVT1, value); preempt_enable(); + +#ifdef CONFIG_X86_MCE_INTEL + /* Recheck CMCI information after local APIC is up on CPU #0 */ + if (smp_processor_id() == 0) + cmci_recheck(); +#endif } void __cpuinit end_local_APIC_setup(void) @@ -1323,15 +1338,16 @@ void __init enable_IR_x2apic(void) return; } - local_irq_save(flags); - mask_8259A(); - - ret = save_mask_IO_APIC_setup(); + ret = save_IO_APIC_setup(); if (ret) { pr_info("Saving IO-APIC state failed: %d\n", ret); goto end; } + local_irq_save(flags); + mask_IO_APIC_setup(); + mask_8259A(); + ret = enable_intr_remapping(1); if (ret && x2apic_preenabled) { @@ -1356,10 +1372,10 @@ end_restore: else reinit_intr_remapped_IO_APIC(x2apic_preenabled); -end: unmask_8259A(); local_irq_restore(flags); +end: if (!ret) { if (!x2apic_preenabled) pr_info("Enabled x2apic and interrupt-remapping\n"); @@ -1512,12 +1528,10 @@ void __init early_init_lapic_mapping(void) */ void __init init_apic_mappings(void) { -#ifdef CONFIG_X86_X2APIC if (x2apic) { boot_cpu_physical_apicid = read_apic_id(); return; } -#endif /* * If no local APIC can be found then set up a fake all @@ -1961,12 +1975,9 @@ static int lapic_resume(struct sys_device *dev) local_irq_save(flags); -#ifdef CONFIG_X86_X2APIC if (x2apic) enable_x2apic(); - else -#endif - { + else { /* * Make sure the APICBASE points to the right address * diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 3b00299..0014714 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -159,20 +159,6 @@ static int flat_apic_id_registered(void) return physid_isset(read_xapic_id(), phys_cpu_present_map); } -static unsigned int flat_cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - return cpumask_bits(cpumask)[0] & APIC_ALL_CPUS; -} - -static unsigned int flat_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - unsigned long mask1 = cpumask_bits(cpumask)[0] & APIC_ALL_CPUS; - unsigned long mask2 = cpumask_bits(andmask)[0] & APIC_ALL_CPUS; - - return mask1 & mask2; -} - static int flat_phys_pkg_id(int initial_apic_id, int index_msb) { return hard_smp_processor_id() >> index_msb; @@ -213,8 +199,8 @@ struct apic apic_flat = { .set_apic_id = set_apic_id, .apic_id_mask = 0xFFu << 24, - .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = default_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, .send_IPI_mask = flat_send_IPI_mask, .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself, @@ -222,7 +208,6 @@ struct apic apic_flat = { .send_IPI_all = flat_send_IPI_all, .send_IPI_self = apic_send_IPI_self, - .wakeup_cpu = NULL, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = NULL, @@ -373,7 +358,6 @@ struct apic apic_physflat = { .send_IPI_all = physflat_send_IPI_all, .send_IPI_self = apic_send_IPI_self, - .wakeup_cpu = NULL, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = NULL, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 0b10933..676cdac 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -16,32 +16,31 @@ #include <asm/apic.h> #include <asm/ipi.h> -static inline unsigned bigsmp_get_apic_id(unsigned long x) +static unsigned bigsmp_get_apic_id(unsigned long x) { return (x >> 24) & 0xFF; } -static inline int bigsmp_apic_id_registered(void) +static int bigsmp_apic_id_registered(void) { return 1; } -static inline const cpumask_t *bigsmp_target_cpus(void) +static const struct cpumask *bigsmp_target_cpus(void) { #ifdef CONFIG_SMP - return &cpu_online_map; + return cpu_online_mask; #else - return &cpumask_of_cpu(0); + return cpumask_of(0); #endif } -static inline unsigned long -bigsmp_check_apicid_used(physid_mask_t bitmap, int apicid) +static unsigned long bigsmp_check_apicid_used(physid_mask_t bitmap, int apicid) { return 0; } -static inline unsigned long bigsmp_check_apicid_present(int bit) +static unsigned long bigsmp_check_apicid_present(int bit) { return 1; } @@ -64,7 +63,7 @@ static inline unsigned long calculate_ldr(int cpu) * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel * document number 292116). So here it goes... */ -static inline void bigsmp_init_apic_ldr(void) +static void bigsmp_init_apic_ldr(void) { unsigned long val; int cpu = smp_processor_id(); @@ -74,19 +73,19 @@ static inline void bigsmp_init_apic_ldr(void) apic_write(APIC_LDR, val); } -static inline void bigsmp_setup_apic_routing(void) +static void bigsmp_setup_apic_routing(void) { printk(KERN_INFO "Enabling APIC mode: Physflat. Using %d I/O APICs\n", nr_ioapics); } -static inline int bigsmp_apicid_to_node(int logical_apicid) +static int bigsmp_apicid_to_node(int logical_apicid) { return apicid_2_node[hard_smp_processor_id()]; } -static inline int bigsmp_cpu_present_to_apicid(int mps_cpu) +static int bigsmp_cpu_present_to_apicid(int mps_cpu) { if (mps_cpu < nr_cpu_ids) return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu); @@ -94,7 +93,7 @@ static inline int bigsmp_cpu_present_to_apicid(int mps_cpu) return BAD_APICID; } -static inline physid_mask_t bigsmp_apicid_to_cpu_present(int phys_apicid) +static physid_mask_t bigsmp_apicid_to_cpu_present(int phys_apicid) { return physid_mask_of_physid(phys_apicid); } @@ -107,29 +106,24 @@ static inline int bigsmp_cpu_to_logical_apicid(int cpu) return cpu_physical_id(cpu); } -static inline physid_mask_t bigsmp_ioapic_phys_id_map(physid_mask_t phys_map) +static physid_mask_t bigsmp_ioapic_phys_id_map(physid_mask_t phys_map) { /* For clustered we don't have a good way to do this yet - hack */ return physids_promote(0xFFL); } -static inline void bigsmp_setup_portio_remap(void) -{ -} - -static inline int bigsmp_check_phys_apicid_present(int boot_cpu_physical_apicid) +static int bigsmp_check_phys_apicid_present(int boot_cpu_physical_apicid) { return 1; } /* As we are using single CPU as destination, pick only one CPU here */ -static inline unsigned int bigsmp_cpu_mask_to_apicid(const cpumask_t *cpumask) +static unsigned int bigsmp_cpu_mask_to_apicid(const struct cpumask *cpumask) { - return bigsmp_cpu_to_logical_apicid(first_cpu(*cpumask)); + return bigsmp_cpu_to_logical_apicid(cpumask_first(cpumask)); } -static inline unsigned int -bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask, +static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask, const struct cpumask *andmask) { int cpu; @@ -148,7 +142,7 @@ bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask, return BAD_APICID; } -static inline int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) +static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) { return cpuid_apic >> index_msb; } @@ -158,12 +152,12 @@ static inline void bigsmp_send_IPI_mask(const struct cpumask *mask, int vector) default_send_IPI_mask_sequence_phys(mask, vector); } -static inline void bigsmp_send_IPI_allbutself(int vector) +static void bigsmp_send_IPI_allbutself(int vector) { default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); } -static inline void bigsmp_send_IPI_all(int vector) +static void bigsmp_send_IPI_all(int vector) { bigsmp_send_IPI_mask(cpu_online_mask, vector); } @@ -194,10 +188,10 @@ static const struct dmi_system_id bigsmp_dmi_table[] = { { } /* NULL entry stops DMI scanning */ }; -static void bigsmp_vector_allocation_domain(int cpu, cpumask_t *retmask) +static void bigsmp_vector_allocation_domain(int cpu, struct cpumask *retmask) { - cpus_clear(*retmask); - cpu_set(cpu, *retmask); + cpumask_clear(retmask); + cpumask_set_cpu(cpu, retmask); } static int probe_bigsmp(void) @@ -256,7 +250,6 @@ struct apic apic_bigsmp = { .send_IPI_all = bigsmp_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .wakeup_cpu = NULL, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 320f2d2..1c11b81 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -163,22 +163,17 @@ static int wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip) return 0; } -static int __init es7000_update_apic(void) +static int es7000_apic_is_cluster(void) { - apic->wakeup_cpu = wakeup_secondary_cpu_via_mip; - /* MPENTIUMIII */ if (boot_cpu_data.x86 == 6 && - (boot_cpu_data.x86_model >= 7 || boot_cpu_data.x86_model <= 11)) { - es7000_update_apic_to_cluster(); - apic->wait_for_init_deassert = NULL; - apic->wakeup_cpu = wakeup_secondary_cpu_via_mip; - } + (boot_cpu_data.x86_model >= 7 || boot_cpu_data.x86_model <= 11)) + return 1; return 0; } -static void __init setup_unisys(void) +static void setup_unisys(void) { /* * Determine the generation of the ES7000 currently running. @@ -192,14 +187,12 @@ static void __init setup_unisys(void) else es7000_plat = ES7000_CLASSIC; ioapic_renumber_irq = es7000_rename_gsi; - - x86_quirks->update_apic = es7000_update_apic; } /* * Parse the OEM Table: */ -static int __init parse_unisys_oem(char *oemptr) +static int parse_unisys_oem(char *oemptr) { int i; int success = 0; @@ -261,7 +254,7 @@ static int __init parse_unisys_oem(char *oemptr) } #ifdef CONFIG_ACPI -static int __init find_unisys_acpi_oem_table(unsigned long *oem_addr) +static int find_unisys_acpi_oem_table(unsigned long *oem_addr) { struct acpi_table_header *header = NULL; struct es7000_oem_table *table; @@ -292,7 +285,7 @@ static int __init find_unisys_acpi_oem_table(unsigned long *oem_addr) return 0; } -static void __init unmap_unisys_acpi_oem_table(unsigned long oem_addr) +static void unmap_unisys_acpi_oem_table(unsigned long oem_addr) { if (!oem_addr) return; @@ -310,8 +303,10 @@ static int es7000_check_dsdt(void) return 0; } +static int es7000_acpi_ret; + /* Hook from generic ACPI tables.c */ -static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +static int es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { unsigned long oem_addr = 0; int check_dsdt; @@ -332,10 +327,26 @@ static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) */ unmap_unisys_acpi_oem_table(oem_addr); } - return ret; + + es7000_acpi_ret = ret; + + return ret && !es7000_apic_is_cluster(); } + +static int es7000_acpi_madt_oem_check_cluster(char *oem_id, char *oem_table_id) +{ + int ret = es7000_acpi_ret; + + return ret && es7000_apic_is_cluster(); +} + #else /* !CONFIG_ACPI: */ -static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +static int es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +{ + return 0; +} + +static int es7000_acpi_madt_oem_check_cluster(char *oem_id, char *oem_table_id) { return 0; } @@ -349,8 +360,7 @@ static void es7000_spin(int n) rep_nop(); } -static int __init -es7000_mip_write(struct mip_reg *mip_reg) +static int es7000_mip_write(struct mip_reg *mip_reg) { int status = 0; int spin; @@ -383,7 +393,7 @@ es7000_mip_write(struct mip_reg *mip_reg) return status; } -static void __init es7000_enable_apic_mode(void) +static void es7000_enable_apic_mode(void) { struct mip_reg es7000_mip_reg; int mip_status; @@ -400,7 +410,7 @@ static void __init es7000_enable_apic_mode(void) WARN(1, "Command failed, status = %x\n", mip_status); } -static void es7000_vector_allocation_domain(int cpu, cpumask_t *retmask) +static void es7000_vector_allocation_domain(int cpu, struct cpumask *retmask) { /* Careful. Some cpus do not strictly honor the set of cpus * specified in the interrupt destination when using lowest @@ -410,17 +420,15 @@ static void es7000_vector_allocation_domain(int cpu, cpumask_t *retmask) * deliver interrupts to the wrong hyperthread when only one * hyperthread was specified in the interrupt desitination. */ - *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } }; + cpumask_clear(retmask); + cpumask_bits(retmask)[0] = APIC_ALL_CPUS; } static void es7000_wait_for_init_deassert(atomic_t *deassert) { -#ifndef CONFIG_ES7000_CLUSTERED_APIC while (!atomic_read(deassert)) cpu_relax(); -#endif - return; } static unsigned int es7000_get_apic_id(unsigned long x) @@ -448,14 +456,14 @@ static int es7000_apic_id_registered(void) return 1; } -static const cpumask_t *target_cpus_cluster(void) +static const struct cpumask *target_cpus_cluster(void) { - return &CPU_MASK_ALL; + return cpu_all_mask; } -static const cpumask_t *es7000_target_cpus(void) +static const struct cpumask *es7000_target_cpus(void) { - return &cpumask_of_cpu(smp_processor_id()); + return cpumask_of(smp_processor_id()); } static unsigned long @@ -510,7 +518,7 @@ static void es7000_setup_apic_routing(void) "Enabling APIC mode: %s. Using %d I/O APICs, target cpus %lx\n", (apic_version[apic] == 0x14) ? "Physical Cluster" : "Logical Cluster", - nr_ioapics, cpus_addr(*es7000_target_cpus())[0]); + nr_ioapics, cpumask_bits(es7000_target_cpus())[0]); } static int es7000_apicid_to_node(int logical_apicid) @@ -565,72 +573,24 @@ static int es7000_check_phys_apicid_present(int cpu_physical_apicid) return 1; } -static unsigned int -es7000_cpu_mask_to_apicid_cluster(const struct cpumask *cpumask) -{ - int cpus_found = 0; - int num_bits_set; - int apicid; - int cpu; - - num_bits_set = cpumask_weight(cpumask); - /* Return id to all */ - if (num_bits_set == nr_cpu_ids) - return 0xFF; - /* - * The cpus in the mask must all be on the apic cluster. If are not - * on the same apicid cluster return default value of target_cpus(): - */ - cpu = cpumask_first(cpumask); - apicid = es7000_cpu_to_logical_apicid(cpu); - - while (cpus_found < num_bits_set) { - if (cpumask_test_cpu(cpu, cpumask)) { - int new_apicid = es7000_cpu_to_logical_apicid(cpu); - - if (APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { - WARN(1, "Not a valid mask!"); - - return 0xFF; - } - apicid = new_apicid; - cpus_found++; - } - cpu++; - } - return apicid; -} - -static unsigned int es7000_cpu_mask_to_apicid(const cpumask_t *cpumask) +static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask) { - int cpus_found = 0; - int num_bits_set; - int apicid; - int cpu; + unsigned int round = 0; + int cpu, uninitialized_var(apicid); - num_bits_set = cpus_weight(*cpumask); - /* Return id to all */ - if (num_bits_set == nr_cpu_ids) - return es7000_cpu_to_logical_apicid(0); /* - * The cpus in the mask must all be on the apic cluster. If are not - * on the same apicid cluster return default value of target_cpus(): + * The cpus in the mask must all be on the apic cluster. */ - cpu = first_cpu(*cpumask); - apicid = es7000_cpu_to_logical_apicid(cpu); - while (cpus_found < num_bits_set) { - if (cpu_isset(cpu, *cpumask)) { - int new_apicid = es7000_cpu_to_logical_apicid(cpu); + for_each_cpu(cpu, cpumask) { + int new_apicid = es7000_cpu_to_logical_apicid(cpu); - if (APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { - printk("%s: Not a valid mask!\n", __func__); + if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { + WARN(1, "Not a valid mask!"); - return es7000_cpu_to_logical_apicid(0); - } - apicid = new_apicid; - cpus_found++; + return BAD_APICID; } - cpu++; + apicid = new_apicid; + round++; } return apicid; } @@ -659,37 +619,103 @@ static int es7000_phys_pkg_id(int cpuid_apic, int index_msb) return cpuid_apic >> index_msb; } -void __init es7000_update_apic_to_cluster(void) -{ - apic->target_cpus = target_cpus_cluster; - apic->irq_delivery_mode = dest_LowestPrio; - /* logical delivery broadcast to all procs: */ - apic->irq_dest_mode = 1; - - apic->init_apic_ldr = es7000_init_apic_ldr_cluster; - - apic->cpu_mask_to_apicid = es7000_cpu_mask_to_apicid_cluster; -} - static int probe_es7000(void) { /* probed later in mptable/ACPI hooks */ return 0; } -static __init int -es7000_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid) +static int es7000_mps_ret; +static int es7000_mps_oem_check(struct mpc_table *mpc, char *oem, + char *productid) { + int ret = 0; + if (mpc->oemptr) { struct mpc_oemtable *oem_table = (struct mpc_oemtable *)mpc->oemptr; if (!strncmp(oem, "UNISYS", 6)) - return parse_unisys_oem((char *)oem_table); + ret = parse_unisys_oem((char *)oem_table); } - return 0; + + es7000_mps_ret = ret; + + return ret && !es7000_apic_is_cluster(); } +static int es7000_mps_oem_check_cluster(struct mpc_table *mpc, char *oem, + char *productid) +{ + int ret = es7000_mps_ret; + + return ret && es7000_apic_is_cluster(); +} + +struct apic apic_es7000_cluster = { + + .name = "es7000", + .probe = probe_es7000, + .acpi_madt_oem_check = es7000_acpi_madt_oem_check_cluster, + .apic_id_registered = es7000_apic_id_registered, + + .irq_delivery_mode = dest_LowestPrio, + /* logical delivery broadcast to all procs: */ + .irq_dest_mode = 1, + + .target_cpus = target_cpus_cluster, + .disable_esr = 1, + .dest_logical = 0, + .check_apicid_used = es7000_check_apicid_used, + .check_apicid_present = es7000_check_apicid_present, + + .vector_allocation_domain = es7000_vector_allocation_domain, + .init_apic_ldr = es7000_init_apic_ldr_cluster, + + .ioapic_phys_id_map = es7000_ioapic_phys_id_map, + .setup_apic_routing = es7000_setup_apic_routing, + .multi_timer_check = NULL, + .apicid_to_node = es7000_apicid_to_node, + .cpu_to_logical_apicid = es7000_cpu_to_logical_apicid, + .cpu_present_to_apicid = es7000_cpu_present_to_apicid, + .apicid_to_cpu_present = es7000_apicid_to_cpu_present, + .setup_portio_remap = NULL, + .check_phys_apicid_present = es7000_check_phys_apicid_present, + .enable_apic_mode = es7000_enable_apic_mode, + .phys_pkg_id = es7000_phys_pkg_id, + .mps_oem_check = es7000_mps_oem_check_cluster, + + .get_apic_id = es7000_get_apic_id, + .set_apic_id = NULL, + .apic_id_mask = 0xFF << 24, + + .cpu_mask_to_apicid = es7000_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = es7000_cpu_mask_to_apicid_and, + + .send_IPI_mask = es7000_send_IPI_mask, + .send_IPI_mask_allbutself = NULL, + .send_IPI_allbutself = es7000_send_IPI_allbutself, + .send_IPI_all = es7000_send_IPI_all, + .send_IPI_self = default_send_IPI_self, + + .wakeup_secondary_cpu = wakeup_secondary_cpu_via_mip, + + .trampoline_phys_low = 0x467, + .trampoline_phys_high = 0x469, + + .wait_for_init_deassert = NULL, + + /* Nothing to do for most platforms, since cleared by the INIT cycle: */ + .smp_callin_clear_local_apic = NULL, + .inquire_remote_apic = default_inquire_remote_apic, + + .read = native_apic_mem_read, + .write = native_apic_mem_write, + .icr_read = native_apic_icr_read, + .icr_write = native_apic_icr_write, + .wait_icr_idle = native_apic_wait_icr_idle, + .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, +}; struct apic apic_es7000 = { @@ -737,8 +763,6 @@ struct apic apic_es7000 = { .send_IPI_all = es7000_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .wakeup_cpu = NULL, - .trampoline_phys_low = 0x467, .trampoline_phys_high = 0x469, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 00e6071..1bb5c6c 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -389,6 +389,8 @@ struct io_apic { unsigned int index; unsigned int unused[3]; unsigned int data; + unsigned int unused2[11]; + unsigned int eoi; }; static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx) @@ -397,6 +399,12 @@ static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx) + (mp_ioapics[idx].apicaddr & ~PAGE_MASK); } +static inline void io_apic_eoi(unsigned int apic, unsigned int vector) +{ + struct io_apic __iomem *io_apic = io_apic_base(apic); + writel(vector, &io_apic->eoi); +} + static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg) { struct io_apic __iomem *io_apic = io_apic_base(apic); @@ -546,16 +554,12 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq apic = entry->apic; pin = entry->pin; -#ifdef CONFIG_INTR_REMAP /* * With interrupt-remapping, destination information comes * from interrupt-remapping table entry. */ if (!irq_remapped(irq)) io_apic_write(apic, 0x11 + pin*2, dest); -#else - io_apic_write(apic, 0x11 + pin*2, dest); -#endif reg = io_apic_read(apic, 0x10 + pin*2); reg &= ~IO_APIC_REDIR_VECTOR_MASK; reg |= vector; @@ -588,10 +592,12 @@ set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask) if (assign_irq_vector(irq, cfg, mask)) return BAD_APICID; - cpumask_and(desc->affinity, cfg->domain, mask); + /* check that before desc->addinity get updated */ set_extra_move_desc(desc, mask); - return apic->cpu_mask_to_apicid_and(desc->affinity, cpu_online_mask); + cpumask_copy(desc->affinity, mask); + + return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain); } static void @@ -849,9 +855,9 @@ __setup("pirq=", ioapic_pirq_setup); static struct IO_APIC_route_entry *early_ioapic_entries[MAX_IO_APICS]; /* - * Saves and masks all the unmasked IO-APIC RTE's + * Saves all the IO-APIC RTE's */ -int save_mask_IO_APIC_setup(void) +int save_IO_APIC_setup(void) { union IO_APIC_reg_01 reg_01; unsigned long flags; @@ -876,16 +882,9 @@ int save_mask_IO_APIC_setup(void) } for (apic = 0; apic < nr_ioapics; apic++) - for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { - struct IO_APIC_route_entry entry; - - entry = early_ioapic_entries[apic][pin] = + for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) + early_ioapic_entries[apic][pin] = ioapic_read_entry(apic, pin); - if (!entry.mask) { - entry.mask = 1; - ioapic_write_entry(apic, pin, entry); - } - } return 0; @@ -898,6 +897,25 @@ nomem: return -ENOMEM; } +void mask_IO_APIC_setup(void) +{ + int apic, pin; + + for (apic = 0; apic < nr_ioapics; apic++) { + if (!early_ioapic_entries[apic]) + break; + for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { + struct IO_APIC_route_entry entry; + + entry = early_ioapic_entries[apic][pin]; + if (!entry.mask) { + entry.mask = 1; + ioapic_write_entry(apic, pin, entry); + } + } + } +} + void restore_IO_APIC_setup(void) { int apic, pin; @@ -1411,9 +1429,7 @@ void __setup_vector_irq(int cpu) } static struct irq_chip ioapic_chip; -#ifdef CONFIG_INTR_REMAP static struct irq_chip ir_ioapic_chip; -#endif #define IOAPIC_AUTO -1 #define IOAPIC_EDGE 0 @@ -1452,7 +1468,6 @@ static void ioapic_register_intr(int irq, struct irq_desc *desc, unsigned long t else desc->status &= ~IRQ_LEVEL; -#ifdef CONFIG_INTR_REMAP if (irq_remapped(irq)) { desc->status |= IRQ_MOVE_PCNTXT; if (trigger) @@ -1464,7 +1479,7 @@ static void ioapic_register_intr(int irq, struct irq_desc *desc, unsigned long t handle_edge_irq, "edge"); return; } -#endif + if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || trigger == IOAPIC_LEVEL) set_irq_chip_and_handler_name(irq, &ioapic_chip, @@ -1478,14 +1493,13 @@ static void ioapic_register_intr(int irq, struct irq_desc *desc, unsigned long t int setup_ioapic_entry(int apic_id, int irq, struct IO_APIC_route_entry *entry, unsigned int destination, int trigger, - int polarity, int vector) + int polarity, int vector, int pin) { /* * add it to the IO-APIC irq-routing table: */ memset(entry,0,sizeof(*entry)); -#ifdef CONFIG_INTR_REMAP if (intr_remapping_enabled) { struct intel_iommu *iommu = map_ioapic_to_ir(apic_id); struct irte irte; @@ -1504,7 +1518,14 @@ int setup_ioapic_entry(int apic_id, int irq, irte.present = 1; irte.dst_mode = apic->irq_dest_mode; - irte.trigger_mode = trigger; + /* + * Trigger mode in the IRTE will always be edge, and the + * actual level or edge trigger will be setup in the IO-APIC + * RTE. This will help simplify level triggered irq migration. + * For more details, see the comments above explainig IO-APIC + * irq migration in the presence of interrupt-remapping. + */ + irte.trigger_mode = 0; irte.dlvry_mode = apic->irq_delivery_mode; irte.vector = vector; irte.dest_id = IRTE_DEST(destination); @@ -1515,18 +1536,21 @@ int setup_ioapic_entry(int apic_id, int irq, ir_entry->zero = 0; ir_entry->format = 1; ir_entry->index = (index & 0x7fff); - } else -#endif - { + /* + * IO-APIC RTE will be configured with virtual vector. + * irq handler will do the explicit EOI to the io-apic. + */ + ir_entry->vector = pin; + } else { entry->delivery_mode = apic->irq_delivery_mode; entry->dest_mode = apic->irq_dest_mode; entry->dest = destination; + entry->vector = vector; } entry->mask = 0; /* enable IRQ */ entry->trigger = trigger; entry->polarity = polarity; - entry->vector = vector; /* Mask level triggered irqs. * Use IRQ_DELAYED_DISABLE for edge triggered irqs. @@ -1561,7 +1585,7 @@ static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq if (setup_ioapic_entry(mp_ioapics[apic_id].apicid, irq, &entry, - dest, trigger, polarity, cfg->vector)) { + dest, trigger, polarity, cfg->vector, pin)) { printk("Failed to setup ioapic entry for ioapic %d, pin %d\n", mp_ioapics[apic_id].apicid, pin); __clear_irq_vector(irq, cfg); @@ -1642,10 +1666,8 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic_id, unsigned int pin, { struct IO_APIC_route_entry entry; -#ifdef CONFIG_INTR_REMAP if (intr_remapping_enabled) return; -#endif memset(&entry, 0, sizeof(entry)); @@ -2040,8 +2062,13 @@ void disable_IO_APIC(void) * If the i8259 is routed through an IOAPIC * Put that IOAPIC in virtual wire mode * so legacy interrupts can be delivered. + * + * With interrupt-remapping, for now we will use virtual wire A mode, + * as virtual wire B is little complex (need to configure both + * IOAPIC RTE aswell as interrupt-remapping table entry). + * As this gets called during crash dump, keep this simple for now. */ - if (ioapic_i8259.pin != -1) { + if (ioapic_i8259.pin != -1 && !intr_remapping_enabled) { struct IO_APIC_route_entry entry; memset(&entry, 0, sizeof(entry)); @@ -2061,7 +2088,10 @@ void disable_IO_APIC(void) ioapic_write_entry(ioapic_i8259.apic, ioapic_i8259.pin, entry); } - disconnect_bsp_APIC(ioapic_i8259.pin != -1); + /* + * Use virtual wire A mode when interrupt remapping is enabled. + */ + disconnect_bsp_APIC(!intr_remapping_enabled && ioapic_i8259.pin != -1); } #ifdef CONFIG_X86_32 @@ -2303,37 +2333,24 @@ static int ioapic_retrigger_irq(unsigned int irq) #ifdef CONFIG_SMP #ifdef CONFIG_INTR_REMAP -static void ir_irq_migration(struct work_struct *work); - -static DECLARE_DELAYED_WORK(ir_migration_work, ir_irq_migration); /* * Migrate the IO-APIC irq in the presence of intr-remapping. * - * For edge triggered, irq migration is a simple atomic update(of vector - * and cpu destination) of IRTE and flush the hardware cache. - * - * For level triggered, we need to modify the io-apic RTE aswell with the update - * vector information, along with modifying IRTE with vector and destination. - * So irq migration for level triggered is little bit more complex compared to - * edge triggered migration. But the good news is, we use the same algorithm - * for level triggered migration as we have today, only difference being, - * we now initiate the irq migration from process context instead of the - * interrupt context. + * For both level and edge triggered, irq migration is a simple atomic + * update(of vector and cpu destination) of IRTE and flush the hardware cache. * - * In future, when we do a directed EOI (combined with cpu EOI broadcast - * suppression) to the IO-APIC, level triggered irq migration will also be - * as simple as edge triggered migration and we can do the irq migration - * with a simple atomic update to IO-APIC RTE. + * For level triggered, we eliminate the io-apic RTE modification (with the + * updated vector information), by using a virtual vector (io-apic pin number). + * Real vector that is used for interrupting cpu will be coming from + * the interrupt-remapping table entry. */ static void migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask) { struct irq_cfg *cfg; struct irte irte; - int modify_ioapic_rte; unsigned int dest; - unsigned long flags; unsigned int irq; if (!cpumask_intersects(mask, cpu_online_mask)) @@ -2351,13 +2368,6 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask) dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask); - modify_ioapic_rte = desc->status & IRQ_LEVEL; - if (modify_ioapic_rte) { - spin_lock_irqsave(&ioapic_lock, flags); - __target_IO_APIC_irq(irq, dest, cfg); - spin_unlock_irqrestore(&ioapic_lock, flags); - } - irte.vector = cfg->vector; irte.dest_id = IRTE_DEST(dest); @@ -2372,73 +2382,12 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask) cpumask_copy(desc->affinity, mask); } -static int migrate_irq_remapped_level_desc(struct irq_desc *desc) -{ - int ret = -1; - struct irq_cfg *cfg = desc->chip_data; - - mask_IO_APIC_irq_desc(desc); - - if (io_apic_level_ack_pending(cfg)) { - /* - * Interrupt in progress. Migrating irq now will change the - * vector information in the IO-APIC RTE and that will confuse - * the EOI broadcast performed by cpu. - * So, delay the irq migration to the next instance. - */ - schedule_delayed_work(&ir_migration_work, 1); - goto unmask; - } - - /* everthing is clear. we have right of way */ - migrate_ioapic_irq_desc(desc, desc->pending_mask); - - ret = 0; - desc->status &= ~IRQ_MOVE_PENDING; - cpumask_clear(desc->pending_mask); - -unmask: - unmask_IO_APIC_irq_desc(desc); - - return ret; -} - -static void ir_irq_migration(struct work_struct *work) -{ - unsigned int irq; - struct irq_desc *desc; - - for_each_irq_desc(irq, desc) { - if (desc->status & IRQ_MOVE_PENDING) { - unsigned long flags; - - spin_lock_irqsave(&desc->lock, flags); - if (!desc->chip->set_affinity || - !(desc->status & IRQ_MOVE_PENDING)) { - desc->status &= ~IRQ_MOVE_PENDING; - spin_unlock_irqrestore(&desc->lock, flags); - continue; - } - - desc->chip->set_affinity(irq, desc->pending_mask); - spin_unlock_irqrestore(&desc->lock, flags); - } - } -} - /* * Migrates the IRQ destination in the process context. */ static void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask) { - if (desc->status & IRQ_LEVEL) { - desc->status |= IRQ_MOVE_PENDING; - cpumask_copy(desc->pending_mask, mask); - migrate_irq_remapped_level_desc(desc); - return; - } - migrate_ioapic_irq_desc(desc, mask); } static void set_ir_ioapic_affinity_irq(unsigned int irq, @@ -2448,6 +2397,11 @@ static void set_ir_ioapic_affinity_irq(unsigned int irq, set_ir_ioapic_affinity_irq_desc(desc, mask); } +#else +static inline void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc, + const struct cpumask *mask) +{ +} #endif asmlinkage void smp_irq_move_cleanup_interrupt(void) @@ -2461,6 +2415,7 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) me = smp_processor_id(); for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { unsigned int irq; + unsigned int irr; struct irq_desc *desc; struct irq_cfg *cfg; irq = __get_cpu_var(vector_irq)[vector]; @@ -2480,6 +2435,18 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) goto unlock; + irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); + /* + * Check if the vector that needs to be cleanedup is + * registered at the cpu's IRR. If so, then this is not + * the best time to clean it up. Lets clean it up in the + * next attempt by sending another IRQ_MOVE_CLEANUP_VECTOR + * to myself. + */ + if (irr & (1 << (vector % 32))) { + apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR); + goto unlock; + } __get_cpu_var(vector_irq)[vector] = -1; cfg->move_cleanup_count--; unlock: @@ -2529,9 +2496,44 @@ static inline void irq_complete_move(struct irq_desc **descp) {} #endif #ifdef CONFIG_INTR_REMAP +static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) +{ + int apic, pin; + struct irq_pin_list *entry; + + entry = cfg->irq_2_pin; + for (;;) { + + if (!entry) + break; + + apic = entry->apic; + pin = entry->pin; + io_apic_eoi(apic, pin); + entry = entry->next; + } +} + +static void +eoi_ioapic_irq(struct irq_desc *desc) +{ + struct irq_cfg *cfg; + unsigned long flags; + unsigned int irq; + + irq = desc->irq; + cfg = desc->chip_data; + + spin_lock_irqsave(&ioapic_lock, flags); + __eoi_ioapic_irq(irq, cfg); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + static void ack_x2apic_level(unsigned int irq) { + struct irq_desc *desc = irq_to_desc(irq); ack_x2APIC_irq(); + eoi_ioapic_irq(desc); } static void ack_x2apic_edge(unsigned int irq) @@ -2662,20 +2664,20 @@ static struct irq_chip ioapic_chip __read_mostly = { .retrigger = ioapic_retrigger_irq, }; -#ifdef CONFIG_INTR_REMAP static struct irq_chip ir_ioapic_chip __read_mostly = { .name = "IR-IO-APIC", .startup = startup_ioapic_irq, .mask = mask_IO_APIC_irq, .unmask = unmask_IO_APIC_irq, +#ifdef CONFIG_INTR_REMAP .ack = ack_x2apic_edge, .eoi = ack_x2apic_level, #ifdef CONFIG_SMP .set_affinity = set_ir_ioapic_affinity_irq, #endif +#endif .retrigger = ioapic_retrigger_irq, }; -#endif static inline void init_IO_APIC_traps(void) { @@ -2901,10 +2903,8 @@ static inline void __init check_timer(void) * 8259A. */ if (pin1 == -1) { -#ifdef CONFIG_INTR_REMAP if (intr_remapping_enabled) panic("BIOS bug: timer not connected to IO-APIC"); -#endif pin1 = pin2; apic1 = apic2; no_pin1 = 1; @@ -2940,10 +2940,8 @@ static inline void __init check_timer(void) clear_IO_APIC_pin(0, pin1); goto out; } -#ifdef CONFIG_INTR_REMAP if (intr_remapping_enabled) panic("timer doesn't work through Interrupt-remapped IO-APIC"); -#endif local_irq_disable(); clear_IO_APIC_pin(apic1, pin1); if (!no_pin1) @@ -3237,9 +3235,7 @@ void destroy_irq(unsigned int irq) if (desc) desc->chip_data = cfg; -#ifdef CONFIG_INTR_REMAP free_irte(irq); -#endif spin_lock_irqsave(&vector_lock, flags); __clear_irq_vector(irq, cfg); spin_unlock_irqrestore(&vector_lock, flags); @@ -3265,7 +3261,6 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus()); -#ifdef CONFIG_INTR_REMAP if (irq_remapped(irq)) { struct irte irte; int ir_index; @@ -3291,10 +3286,13 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms MSI_ADDR_IR_SHV | MSI_ADDR_IR_INDEX1(ir_index) | MSI_ADDR_IR_INDEX2(ir_index); - } else -#endif - { - msg->address_hi = MSI_ADDR_BASE_HI; + } else { + if (x2apic_enabled()) + msg->address_hi = MSI_ADDR_BASE_HI | + MSI_ADDR_EXT_DEST_ID(dest); + else + msg->address_hi = MSI_ADDR_BASE_HI; + msg->address_lo = MSI_ADDR_BASE_LO | ((apic->irq_dest_mode == 0) ? @@ -3394,15 +3392,16 @@ static struct irq_chip msi_chip = { .retrigger = ioapic_retrigger_irq, }; -#ifdef CONFIG_INTR_REMAP static struct irq_chip msi_ir_chip = { .name = "IR-PCI-MSI", .unmask = unmask_msi_irq, .mask = mask_msi_irq, +#ifdef CONFIG_INTR_REMAP .ack = ack_x2apic_edge, #ifdef CONFIG_SMP .set_affinity = ir_set_msi_irq_affinity, #endif +#endif .retrigger = ioapic_retrigger_irq, }; @@ -3432,7 +3431,6 @@ static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec) } return index; } -#endif static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq) { @@ -3446,7 +3444,6 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq) set_irq_msi(irq, msidesc); write_msi_msg(irq, &msg); -#ifdef CONFIG_INTR_REMAP if (irq_remapped(irq)) { struct irq_desc *desc = irq_to_desc(irq); /* @@ -3455,7 +3452,6 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq) desc->status |= IRQ_MOVE_PCNTXT; set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge"); } else -#endif set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge"); dev_printk(KERN_DEBUG, &dev->dev, "irq %d for MSI/MSI-X\n", irq); @@ -3469,11 +3465,12 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) int ret, sub_handle; struct msi_desc *msidesc; unsigned int irq_want; - -#ifdef CONFIG_INTR_REMAP - struct intel_iommu *iommu = 0; + struct intel_iommu *iommu = NULL; int index = 0; -#endif + + /* x86 doesn't support multiple MSI yet */ + if (type == PCI_CAP_ID_MSI && nvec > 1) + return 1; irq_want = nr_irqs_gsi; sub_handle = 0; @@ -3482,7 +3479,6 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) if (irq == 0) return -1; irq_want = irq + 1; -#ifdef CONFIG_INTR_REMAP if (!intr_remapping_enabled) goto no_ir; @@ -3510,7 +3506,6 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) set_irte_irq(irq, iommu, index, sub_handle); } no_ir: -#endif ret = setup_msi_irq(dev, msidesc, irq); if (ret < 0) goto error; @@ -3528,7 +3523,7 @@ void arch_teardown_msi_irq(unsigned int irq) destroy_irq(irq); } -#ifdef CONFIG_DMAR +#if defined (CONFIG_DMAR) || defined (CONFIG_INTR_REMAP) #ifdef CONFIG_SMP static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask) { @@ -3609,7 +3604,7 @@ static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask) #endif /* CONFIG_SMP */ -struct irq_chip hpet_msi_type = { +static struct irq_chip hpet_msi_type = { .name = "HPET_MSI", .unmask = hpet_msi_unmask, .mask = hpet_msi_mask, @@ -4045,11 +4040,9 @@ void __init setup_ioapic_dest(void) else mask = apic->target_cpus(); -#ifdef CONFIG_INTR_REMAP if (intr_remapping_enabled) set_ir_ioapic_affinity_irq_desc(desc, mask); else -#endif set_ioapic_affinity_irq_desc(desc, mask); } @@ -4142,9 +4135,12 @@ static int __init ioapic_insert_resources(void) struct resource *r = ioapic_resources; if (!r) { - printk(KERN_ERR - "IO APIC resources could be not be allocated.\n"); - return -1; + if (nr_ioapics > 0) { + printk(KERN_ERR + "IO APIC resources couldn't be allocated.\n"); + return -1; + } + return 0; } for (i = 0; i < nr_ioapics; i++) { diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index bdfad80..d6bd624 100644 --- a/arch/x86/kernel/apic/nmi.c +++ b/arch/x86/kernel/apic/nmi.c @@ -39,7 +39,7 @@ int unknown_nmi_panic; int nmi_watchdog_enabled; -static cpumask_t backtrace_mask = CPU_MASK_NONE; +static cpumask_var_t backtrace_mask; /* nmi_active: * >0: the lapic NMI watchdog is active, but can be disabled @@ -138,6 +138,7 @@ int __init check_nmi_watchdog(void) if (!prev_nmi_count) goto error; + alloc_cpumask_var(&backtrace_mask, GFP_KERNEL); printk(KERN_INFO "Testing NMI watchdog ... "); #ifdef CONFIG_SMP @@ -413,14 +414,14 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) touched = 1; } - if (cpu_isset(cpu, backtrace_mask)) { + if (cpumask_test_cpu(cpu, backtrace_mask)) { static DEFINE_SPINLOCK(lock); /* Serialise the printks */ spin_lock(&lock); printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu); dump_stack(); spin_unlock(&lock); - cpu_clear(cpu, backtrace_mask); + cpumask_clear_cpu(cpu, backtrace_mask); } /* Could check oops_in_progress here too, but it's safer not to */ @@ -554,10 +555,10 @@ void __trigger_all_cpu_backtrace(void) { int i; - backtrace_mask = cpu_online_map; + cpumask_copy(backtrace_mask, cpu_online_mask); /* Wait for up to 10 seconds for all CPUs to do the backtrace */ for (i = 0; i < 10 * 1000; i++) { - if (cpus_empty(backtrace_mask)) + if (cpumask_empty(backtrace_mask)) break; mdelay(1); } diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index d9d6d61..533e59c 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -69,7 +69,7 @@ struct mpc_trans { /* x86_quirks member */ static int mpc_record; -static __cpuinitdata struct mpc_trans *translation_table[MAX_MPC_ENTRY]; +static struct mpc_trans *translation_table[MAX_MPC_ENTRY]; int mp_bus_id_to_node[MAX_MP_BUSSES]; int mp_bus_id_to_local[MAX_MP_BUSSES]; @@ -256,13 +256,6 @@ static int __init numaq_setup_ioapic_ids(void) return 1; } -static int __init numaq_update_apic(void) -{ - apic->wakeup_cpu = wakeup_secondary_cpu_via_nmi; - - return 0; -} - static struct x86_quirks numaq_x86_quirks __initdata = { .arch_pre_time_init = numaq_pre_time_init, .arch_time_init = NULL, @@ -278,7 +271,6 @@ static struct x86_quirks numaq_x86_quirks __initdata = { .mpc_oem_pci_bus = mpc_oem_pci_bus, .smp_read_mpc_oem = smp_read_mpc_oem, .setup_ioapic_ids = numaq_setup_ioapic_ids, - .update_apic = numaq_update_apic, }; static __init void early_check_numaq(void) @@ -342,9 +334,9 @@ static inline void numaq_smp_callin_clear_local_apic(void) clear_local_APIC(); } -static inline const cpumask_t *numaq_target_cpus(void) +static inline const struct cpumask *numaq_target_cpus(void) { - return &CPU_MASK_ALL; + return cpu_all_mask; } static inline unsigned long @@ -435,7 +427,7 @@ static inline int numaq_check_phys_apicid_present(int boot_cpu_physical_apicid) * We use physical apicids here, not logical, so just return the default * physical broadcast to stop people from breaking us */ -static inline unsigned int numaq_cpu_mask_to_apicid(const cpumask_t *cpumask) +static unsigned int numaq_cpu_mask_to_apicid(const struct cpumask *cpumask) { return 0x0F; } @@ -470,7 +462,7 @@ static int probe_numaq(void) return found_numaq; } -static void numaq_vector_allocation_domain(int cpu, cpumask_t *retmask) +static void numaq_vector_allocation_domain(int cpu, struct cpumask *retmask) { /* Careful. Some cpus do not strictly honor the set of cpus * specified in the interrupt destination when using lowest @@ -480,7 +472,8 @@ static void numaq_vector_allocation_domain(int cpu, cpumask_t *retmask) * deliver interrupts to the wrong hyperthread when only one * hyperthread was specified in the interrupt desitination. */ - *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } }; + cpumask_clear(retmask); + cpumask_bits(retmask)[0] = APIC_ALL_CPUS; } static void numaq_setup_portio_remap(void) @@ -546,7 +539,7 @@ struct apic apic_numaq = { .send_IPI_all = numaq_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .wakeup_cpu = NULL, + .wakeup_secondary_cpu = wakeup_secondary_cpu_via_nmi, .trampoline_phys_low = NUMAQ_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = NUMAQ_TRAMPOLINE_PHYS_HIGH, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 3a730fa..01eda2a 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -83,7 +83,8 @@ static void default_vector_allocation_domain(int cpu, struct cpumask *retmask) * deliver interrupts to the wrong hyperthread when only one * hyperthread was specified in the interrupt desitination. */ - *retmask = (cpumask_t) { { [0] = APIC_ALL_CPUS } }; + cpumask_clear(retmask); + cpumask_bits(retmask)[0] = APIC_ALL_CPUS; } /* should be called last. */ @@ -138,7 +139,6 @@ struct apic apic_default = { .send_IPI_all = default_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .wakeup_cpu = NULL, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, @@ -159,6 +159,7 @@ extern struct apic apic_numaq; extern struct apic apic_summit; extern struct apic apic_bigsmp; extern struct apic apic_es7000; +extern struct apic apic_es7000_cluster; extern struct apic apic_default; struct apic *apic = &apic_default; @@ -176,6 +177,7 @@ static struct apic *apic_probe[] __initdata = { #endif #ifdef CONFIG_X86_ES7000 &apic_es7000, + &apic_es7000_cluster, #endif &apic_default, /* must be last */ NULL, @@ -197,9 +199,6 @@ static int __init parse_apic(char *arg) } } - if (x86_quirks->update_apic) - x86_quirks->update_apic(); - /* Parsed again by __setup for debug/verbose */ return 0; } @@ -218,8 +217,6 @@ void __init generic_bigsmp_probe(void) if (!cmdline_apic && apic == &apic_default) { if (apic_bigsmp.probe()) { apic = &apic_bigsmp; - if (x86_quirks->update_apic) - x86_quirks->update_apic(); printk(KERN_INFO "Overriding APIC driver with %s\n", apic->name); } @@ -240,9 +237,6 @@ void __init generic_apic_probe(void) /* Not visible without early console */ if (!apic_probe[i]) panic("Didn't find an APIC driver"); - - if (x86_quirks->update_apic) - x86_quirks->update_apic(); } printk(KERN_INFO "Using APIC driver %s\n", apic->name); } @@ -262,8 +256,6 @@ generic_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid) if (!cmdline_apic) { apic = apic_probe[i]; - if (x86_quirks->update_apic) - x86_quirks->update_apic(); printk(KERN_INFO "Switched to APIC driver `%s'.\n", apic->name); } @@ -284,8 +276,6 @@ int __init default_acpi_madt_oem_check(char *oem_id, char *oem_table_id) if (!cmdline_apic) { apic = apic_probe[i]; - if (x86_quirks->update_apic) - x86_quirks->update_apic(); printk(KERN_INFO "Switched to APIC driver `%s'.\n", apic->name); } diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index e7c1636..1783652 100644 --- a/arch/x86/kernel/apic/probe_64.c +++ b/arch/x86/kernel/apic/probe_64.c @@ -69,8 +69,12 @@ void __init default_setup_apic_routing(void) printk(KERN_INFO "Setting APIC routing to %s\n", apic->name); } - if (x86_quirks->update_apic) - x86_quirks->update_apic(); + /* + * Now that apic routing model is selected, configure the + * fault handling for intr remapping. + */ + if (intr_remapping_enabled) + enable_drhd_fault_handling(); } /* Same for both flat and physical. */ diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index 32838b5..9cfe1f4 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -53,23 +53,19 @@ static unsigned summit_get_apic_id(unsigned long x) return (x >> 24) & 0xFF; } -static inline void summit_send_IPI_mask(const cpumask_t *mask, int vector) +static inline void summit_send_IPI_mask(const struct cpumask *mask, int vector) { default_send_IPI_mask_sequence_logical(mask, vector); } static void summit_send_IPI_allbutself(int vector) { - cpumask_t mask = cpu_online_map; - cpu_clear(smp_processor_id(), mask); - - if (!cpus_empty(mask)) - summit_send_IPI_mask(&mask, vector); + default_send_IPI_mask_allbutself_logical(cpu_online_mask, vector); } static void summit_send_IPI_all(int vector) { - summit_send_IPI_mask(&cpu_online_map, vector); + summit_send_IPI_mask(cpu_online_mask, vector); } #include <asm/tsc.h> @@ -77,9 +73,9 @@ static void summit_send_IPI_all(int vector) extern int use_cyclone; #ifdef CONFIG_X86_SUMMIT_NUMA -extern void setup_summit(void); +static void setup_summit(void); #else -#define setup_summit() {} +static inline void setup_summit(void) {} #endif static int summit_mps_oem_check(struct mpc_table *mpc, char *oem, @@ -186,13 +182,13 @@ static inline int is_WPEG(struct rio_detail *rio){ #define SUMMIT_APIC_DFR_VALUE (APIC_DFR_CLUSTER) -static const cpumask_t *summit_target_cpus(void) +static const struct cpumask *summit_target_cpus(void) { /* CPU_MASK_ALL (0xff) has undefined behaviour with * dest_LowestPrio mode logical clustered apic interrupt routing * Just start on cpu 0. IRQ balancing will spread load */ - return &cpumask_of_cpu(0); + return cpumask_of(0); } static unsigned long summit_check_apicid_used(physid_mask_t bitmap, int apicid) @@ -289,35 +285,23 @@ static int summit_check_phys_apicid_present(int boot_cpu_physical_apicid) return 1; } -static unsigned int summit_cpu_mask_to_apicid(const cpumask_t *cpumask) +static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask) { - int cpus_found = 0; - int num_bits_set; - int apicid; - int cpu; + unsigned int round = 0; + int cpu, apicid = 0; - num_bits_set = cpus_weight(*cpumask); - if (num_bits_set >= nr_cpu_ids) - return BAD_APICID; /* * The cpus in the mask must all be on the apic cluster. */ - cpu = first_cpu(*cpumask); - apicid = summit_cpu_to_logical_apicid(cpu); - - while (cpus_found < num_bits_set) { - if (cpu_isset(cpu, *cpumask)) { - int new_apicid = summit_cpu_to_logical_apicid(cpu); + for_each_cpu(cpu, cpumask) { + int new_apicid = summit_cpu_to_logical_apicid(cpu); - if (APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { - printk("%s: Not a valid mask!\n", __func__); - - return BAD_APICID; - } - apicid = apicid | new_apicid; - cpus_found++; + if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { + printk("%s: Not a valid mask!\n", __func__); + return BAD_APICID; } - cpu++; + apicid |= new_apicid; + round++; } return apicid; } @@ -358,7 +342,7 @@ static int probe_summit(void) return 0; } -static void summit_vector_allocation_domain(int cpu, cpumask_t *retmask) +static void summit_vector_allocation_domain(int cpu, struct cpumask *retmask) { /* Careful. Some cpus do not strictly honor the set of cpus * specified in the interrupt destination when using lowest @@ -368,19 +352,20 @@ static void summit_vector_allocation_domain(int cpu, cpumask_t *retmask) * deliver interrupts to the wrong hyperthread when only one * hyperthread was specified in the interrupt desitination. */ - *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } }; + cpumask_clear(retmask); + cpumask_bits(retmask)[0] = APIC_ALL_CPUS; } #ifdef CONFIG_X86_SUMMIT_NUMA -static struct rio_table_hdr *rio_table_hdr __initdata; -static struct scal_detail *scal_devs[MAX_NUMNODES] __initdata; -static struct rio_detail *rio_devs[MAX_NUMNODES*4] __initdata; +static struct rio_table_hdr *rio_table_hdr; +static struct scal_detail *scal_devs[MAX_NUMNODES]; +static struct rio_detail *rio_devs[MAX_NUMNODES*4]; #ifndef CONFIG_X86_NUMAQ -static int mp_bus_id_to_node[MAX_MP_BUSSES] __initdata; +static int mp_bus_id_to_node[MAX_MP_BUSSES]; #endif -static int __init setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) +static int setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) { int twister = 0, node = 0; int i, bus, num_buses; @@ -442,7 +427,7 @@ static int __init setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) return bus; } -static int __init build_detail_arrays(void) +static int build_detail_arrays(void) { unsigned long ptr; int i, scal_detail_size, rio_detail_size; @@ -476,7 +461,7 @@ static int __init build_detail_arrays(void) return 1; } -void __init setup_summit(void) +void setup_summit(void) { unsigned long ptr; unsigned short offset; @@ -574,7 +559,6 @@ struct apic apic_summit = { .send_IPI_all = summit_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .wakeup_cpu = NULL, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 354b9c4..4a903e2 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -57,6 +57,8 @@ static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector) unsigned long query_cpu; unsigned long flags; + x2apic_wrmsr_fence(); + local_irq_save(flags); for_each_cpu(query_cpu, mask) { __x2apic_send_IPI_dest( @@ -73,6 +75,8 @@ static void unsigned long query_cpu; unsigned long flags; + x2apic_wrmsr_fence(); + local_irq_save(flags); for_each_cpu(query_cpu, mask) { if (query_cpu == this_cpu) @@ -90,6 +94,8 @@ static void x2apic_send_IPI_allbutself(int vector) unsigned long query_cpu; unsigned long flags; + x2apic_wrmsr_fence(); + local_irq_save(flags); for_each_online_cpu(query_cpu) { if (query_cpu == this_cpu) @@ -224,7 +230,6 @@ struct apic apic_x2apic_cluster = { .send_IPI_all = x2apic_send_IPI_all, .send_IPI_self = x2apic_send_IPI_self, - .wakeup_cpu = NULL, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = NULL, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 5bcb174..a284359 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -58,6 +58,8 @@ static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector) unsigned long query_cpu; unsigned long flags; + x2apic_wrmsr_fence(); + local_irq_save(flags); for_each_cpu(query_cpu, mask) { __x2apic_send_IPI_dest(per_cpu(x86_cpu_to_apicid, query_cpu), @@ -73,6 +75,8 @@ static void unsigned long query_cpu; unsigned long flags; + x2apic_wrmsr_fence(); + local_irq_save(flags); for_each_cpu(query_cpu, mask) { if (query_cpu != this_cpu) @@ -89,6 +93,8 @@ static void x2apic_send_IPI_allbutself(int vector) unsigned long query_cpu; unsigned long flags; + x2apic_wrmsr_fence(); + local_irq_save(flags); for_each_online_cpu(query_cpu) { if (query_cpu == this_cpu) @@ -213,7 +219,6 @@ struct apic apic_x2apic_phys = { .send_IPI_all = x2apic_send_IPI_all, .send_IPI_self = x2apic_send_IPI_self, - .wakeup_cpu = NULL, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = NULL, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 20b4ad0..1248318 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -7,28 +7,28 @@ * * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved. */ - -#include <linux/kernel.h> -#include <linux/threads.h> -#include <linux/cpu.h> #include <linux/cpumask.h> +#include <linux/hardirq.h> +#include <linux/proc_fs.h> +#include <linux/threads.h> +#include <linux/kernel.h> +#include <linux/module.h> #include <linux/string.h> #include <linux/ctype.h> -#include <linux/init.h> #include <linux/sched.h> -#include <linux/module.h> -#include <linux/hardirq.h> #include <linux/timer.h> -#include <linux/proc_fs.h> -#include <asm/current.h> -#include <asm/smp.h> -#include <asm/apic.h> -#include <asm/ipi.h> -#include <asm/pgtable.h> -#include <asm/uv/uv.h> +#include <linux/cpu.h> +#include <linux/init.h> + #include <asm/uv/uv_mmrs.h> #include <asm/uv/uv_hub.h> +#include <asm/current.h> +#include <asm/pgtable.h> #include <asm/uv/bios.h> +#include <asm/uv/uv.h> +#include <asm/apic.h> +#include <asm/ipi.h> +#include <asm/smp.h> DEFINE_PER_CPU(int, x2apic_extra_bits); @@ -91,40 +91,39 @@ static void uv_vector_allocation_domain(int cpu, struct cpumask *retmask) cpumask_set_cpu(cpu, retmask); } -int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip) +static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) { +#ifdef CONFIG_SMP unsigned long val; int pnode; pnode = uv_apicid_to_pnode(phys_apicid); val = (1UL << UVH_IPI_INT_SEND_SHFT) | (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) | - (((long)start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | + ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | APIC_DM_INIT; uv_write_global_mmr64(pnode, UVH_IPI_INT, val); mdelay(10); val = (1UL << UVH_IPI_INT_SEND_SHFT) | (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) | - (((long)start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | + ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | APIC_DM_STARTUP; uv_write_global_mmr64(pnode, UVH_IPI_INT, val); + + atomic_set(&init_deasserted, 1); +#endif return 0; } static void uv_send_IPI_one(int cpu, int vector) { - unsigned long val, apicid; + unsigned long apicid; int pnode; apicid = per_cpu(x86_cpu_to_apicid, cpu); pnode = uv_apicid_to_pnode(apicid); - - val = (1UL << UVH_IPI_INT_SEND_SHFT) | - (apicid << UVH_IPI_INT_APIC_ID_SHFT) | - (vector << UVH_IPI_INT_VECTOR_SHFT); - - uv_write_global_mmr64(pnode, UVH_IPI_INT, val); + uv_hub_send_ipi(pnode, apicid, vector); } static void uv_send_IPI_mask(const struct cpumask *mask, int vector) @@ -285,7 +284,7 @@ struct apic apic_x2apic_uv_x = { .send_IPI_all = uv_send_IPI_all, .send_IPI_self = uv_send_IPI_self, - .wakeup_cpu = NULL, + .wakeup_secondary_cpu = uv_wakeup_secondary, .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = NULL, @@ -365,7 +364,7 @@ static __init void map_high(char *id, unsigned long base, int shift, paddr = base << shift; bytes = (1UL << shift) * (max_pnode + 1); printk(KERN_INFO "UV: Map %s_HI 0x%lx - 0x%lx\n", id, paddr, - paddr + bytes); + paddr + bytes); if (map_type == map_uc) init_extra_mapping_uc(paddr, bytes); else @@ -528,7 +527,7 @@ late_initcall(uv_init_heartbeat); /* * Called on each cpu to initialize the per_cpu UV data area. - * ZZZ hotplug not supported yet + * FIXME: hotplug not supported yet */ void __cpuinit uv_cpu_init(void) { diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 10033fe..49e0939 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -466,7 +466,7 @@ static const lookup_t error_table[] = { * @err: APM BIOS return code * * Write a meaningful log entry to the kernel log in the event of - * an APM error. + * an APM error. Note that this also handles (negative) kernel errors. */ static void apm_error(char *str, int err) @@ -478,43 +478,14 @@ static void apm_error(char *str, int err) break; if (i < ERROR_COUNT) printk(KERN_NOTICE "apm: %s: %s\n", str, error_table[i].msg); + else if (err < 0) + printk(KERN_NOTICE "apm: %s: linux error code %i\n", str, err); else printk(KERN_NOTICE "apm: %s: unknown error code %#2.2x\n", str, err); } /* - * Lock APM functionality to physical CPU 0 - */ - -#ifdef CONFIG_SMP - -static cpumask_t apm_save_cpus(void) -{ - cpumask_t x = current->cpus_allowed; - /* Some bioses don't like being called from CPU != 0 */ - set_cpus_allowed(current, cpumask_of_cpu(0)); - BUG_ON(smp_processor_id() != 0); - return x; -} - -static inline void apm_restore_cpus(cpumask_t mask) -{ - set_cpus_allowed(current, mask); -} - -#else - -/* - * No CPU lockdown needed on a uniprocessor - */ - -#define apm_save_cpus() (current->cpus_allowed) -#define apm_restore_cpus(x) (void)(x) - -#endif - -/* * These are the actual BIOS calls. Depending on APM_ZERO_SEGS and * apm_info.allow_ints, we are being really paranoid here! Not only * are interrupts disabled, but all the segment registers (except SS) @@ -568,16 +539,23 @@ static inline void apm_irq_restore(unsigned long flags) # define APM_DO_RESTORE_SEGS #endif +struct apm_bios_call { + u32 func; + /* In and out */ + u32 ebx; + u32 ecx; + /* Out only */ + u32 eax; + u32 edx; + u32 esi; + + /* Error: -ENOMEM, or bits 8-15 of eax */ + int err; +}; + /** - * apm_bios_call - Make an APM BIOS 32bit call - * @func: APM function to execute - * @ebx_in: EBX register for call entry - * @ecx_in: ECX register for call entry - * @eax: EAX register return - * @ebx: EBX register return - * @ecx: ECX register return - * @edx: EDX register return - * @esi: ESI register return + * __apm_bios_call - Make an APM BIOS 32bit call + * @_call: pointer to struct apm_bios_call. * * Make an APM call using the 32bit protected mode interface. The * caller is responsible for knowing if APM BIOS is configured and @@ -586,80 +564,142 @@ static inline void apm_irq_restore(unsigned long flags) * flag is loaded into AL. If there is an error, then the error * code is returned in AH (bits 8-15 of eax) and this function * returns non-zero. + * + * Note: this makes the call on the current CPU. */ - -static u8 apm_bios_call(u32 func, u32 ebx_in, u32 ecx_in, - u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, u32 *esi) +static long __apm_bios_call(void *_call) { APM_DECL_SEGS unsigned long flags; - cpumask_t cpus; int cpu; struct desc_struct save_desc_40; struct desc_struct *gdt; - - cpus = apm_save_cpus(); + struct apm_bios_call *call = _call; cpu = get_cpu(); + BUG_ON(cpu != 0); gdt = get_cpu_gdt_table(cpu); save_desc_40 = gdt[0x40 / 8]; gdt[0x40 / 8] = bad_bios_desc; apm_irq_save(flags); APM_DO_SAVE_SEGS; - apm_bios_call_asm(func, ebx_in, ecx_in, eax, ebx, ecx, edx, esi); + apm_bios_call_asm(call->func, call->ebx, call->ecx, + &call->eax, &call->ebx, &call->ecx, &call->edx, + &call->esi); APM_DO_RESTORE_SEGS; apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); - apm_restore_cpus(cpus); - return *eax & 0xff; + return call->eax & 0xff; +} + +/* Run __apm_bios_call or __apm_bios_call_simple on CPU 0 */ +static int on_cpu0(long (*fn)(void *), struct apm_bios_call *call) +{ + int ret; + + /* Don't bother with work_on_cpu in the common case, so we don't + * have to worry about OOM or overhead. */ + if (get_cpu() == 0) { + ret = fn(call); + put_cpu(); + } else { + put_cpu(); + ret = work_on_cpu(0, fn, call); + } + + /* work_on_cpu can fail with -ENOMEM */ + if (ret < 0) + call->err = ret; + else + call->err = (call->eax >> 8) & 0xff; + + return ret; } /** - * apm_bios_call_simple - make a simple APM BIOS 32bit call - * @func: APM function to invoke - * @ebx_in: EBX register value for BIOS call - * @ecx_in: ECX register value for BIOS call - * @eax: EAX register on return from the BIOS call + * apm_bios_call - Make an APM BIOS 32bit call (on CPU 0) + * @call: the apm_bios_call registers. + * + * If there is an error, it is returned in @call.err. + */ +static int apm_bios_call(struct apm_bios_call *call) +{ + return on_cpu0(__apm_bios_call, call); +} + +/** + * __apm_bios_call_simple - Make an APM BIOS 32bit call (on CPU 0) + * @_call: pointer to struct apm_bios_call. * * Make a BIOS call that returns one value only, or just status. * If there is an error, then the error code is returned in AH - * (bits 8-15 of eax) and this function returns non-zero. This is - * used for simpler BIOS operations. This call may hold interrupts - * off for a long time on some laptops. + * (bits 8-15 of eax) and this function returns non-zero (it can + * also return -ENOMEM). This is used for simpler BIOS operations. + * This call may hold interrupts off for a long time on some laptops. + * + * Note: this makes the call on the current CPU. */ - -static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax) +static long __apm_bios_call_simple(void *_call) { u8 error; APM_DECL_SEGS unsigned long flags; - cpumask_t cpus; int cpu; struct desc_struct save_desc_40; struct desc_struct *gdt; - - cpus = apm_save_cpus(); + struct apm_bios_call *call = _call; cpu = get_cpu(); + BUG_ON(cpu != 0); gdt = get_cpu_gdt_table(cpu); save_desc_40 = gdt[0x40 / 8]; gdt[0x40 / 8] = bad_bios_desc; apm_irq_save(flags); APM_DO_SAVE_SEGS; - error = apm_bios_call_simple_asm(func, ebx_in, ecx_in, eax); + error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx, + &call->eax); APM_DO_RESTORE_SEGS; apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); - apm_restore_cpus(cpus); return error; } /** + * apm_bios_call_simple - make a simple APM BIOS 32bit call + * @func: APM function to invoke + * @ebx_in: EBX register value for BIOS call + * @ecx_in: ECX register value for BIOS call + * @eax: EAX register on return from the BIOS call + * @err: bits + * + * Make a BIOS call that returns one value only, or just status. + * If there is an error, then the error code is returned in @err + * and this function returns non-zero. This is used for simpler + * BIOS operations. This call may hold interrupts off for a long + * time on some laptops. + */ +static int apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax, + int *err) +{ + struct apm_bios_call call; + int ret; + + call.func = func; + call.ebx = ebx_in; + call.ecx = ecx_in; + + ret = on_cpu0(__apm_bios_call_simple, &call); + *eax = call.eax; + *err = call.err; + return ret; +} + +/** * apm_driver_version - APM driver version * @val: loaded with the APM version on return * @@ -678,9 +718,10 @@ static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax) static int apm_driver_version(u_short *val) { u32 eax; + int err; - if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax)) - return (eax >> 8) & 0xff; + if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax, &err)) + return err; *val = eax; return APM_SUCCESS; } @@ -701,22 +742,21 @@ static int apm_driver_version(u_short *val) * that APM 1.2 is in use. If no messges are pending the value 0x80 * is returned (No power management events pending). */ - static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info) { - u32 eax; - u32 ebx; - u32 ecx; - u32 dummy; + struct apm_bios_call call; - if (apm_bios_call(APM_FUNC_GET_EVENT, 0, 0, &eax, &ebx, &ecx, - &dummy, &dummy)) - return (eax >> 8) & 0xff; - *event = ebx; + call.func = APM_FUNC_GET_EVENT; + call.ebx = call.ecx = 0; + + if (apm_bios_call(&call)) + return call.err; + + *event = call.ebx; if (apm_info.connection_version < 0x0102) *info = ~0; /* indicate info not valid */ else - *info = ecx; + *info = call.ecx; return APM_SUCCESS; } @@ -737,9 +777,10 @@ static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info) static int set_power_state(u_short what, u_short state) { u32 eax; + int err; - if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax)) - return (eax >> 8) & 0xff; + if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax, &err)) + return err; return APM_SUCCESS; } @@ -770,6 +811,7 @@ static int apm_do_idle(void) u8 ret = 0; int idled = 0; int polling; + int err; polling = !!(current_thread_info()->status & TS_POLLING); if (polling) { @@ -782,7 +824,7 @@ static int apm_do_idle(void) } if (!need_resched()) { idled = 1; - ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax); + ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax, &err); } if (polling) current_thread_info()->status |= TS_POLLING; @@ -797,8 +839,7 @@ static int apm_do_idle(void) * Only report the failure the first 5 times. */ if (++t < 5) { - printk(KERN_DEBUG "apm_do_idle failed (%d)\n", - (eax >> 8) & 0xff); + printk(KERN_DEBUG "apm_do_idle failed (%d)\n", err); t = jiffies; } return -1; @@ -816,9 +857,10 @@ static int apm_do_idle(void) static void apm_do_busy(void) { u32 dummy; + int err; if (clock_slowed || ALWAYS_CALL_BUSY) { - (void)apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy); + (void)apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy, &err); clock_slowed = 0; } } @@ -937,7 +979,7 @@ static void apm_power_off(void) /* Some bioses don't like being called from CPU != 0 */ if (apm_info.realmode_power_off) { - (void)apm_save_cpus(); + set_cpus_allowed_ptr(current, cpumask_of(0)); machine_real_restart(po_bios_call, sizeof(po_bios_call)); } else { (void)set_system_power_state(APM_STATE_OFF); @@ -956,12 +998,13 @@ static void apm_power_off(void) static int apm_enable_power_management(int enable) { u32 eax; + int err; if ((enable == 0) && (apm_info.bios.flags & APM_BIOS_DISENGAGED)) return APM_NOT_ENGAGED; if (apm_bios_call_simple(APM_FUNC_ENABLE_PM, APM_DEVICE_BALL, - enable, &eax)) - return (eax >> 8) & 0xff; + enable, &eax, &err)) + return err; if (enable) apm_info.bios.flags &= ~APM_BIOS_DISABLED; else @@ -986,24 +1029,23 @@ static int apm_enable_power_management(int enable) static int apm_get_power_status(u_short *status, u_short *bat, u_short *life) { - u32 eax; - u32 ebx; - u32 ecx; - u32 edx; - u32 dummy; + struct apm_bios_call call; + + call.func = APM_FUNC_GET_STATUS; + call.ebx = APM_DEVICE_ALL; + call.ecx = 0; if (apm_info.get_power_status_broken) return APM_32_UNSUPPORTED; - if (apm_bios_call(APM_FUNC_GET_STATUS, APM_DEVICE_ALL, 0, - &eax, &ebx, &ecx, &edx, &dummy)) - return (eax >> 8) & 0xff; - *status = ebx; - *bat = ecx; + if (apm_bios_call(&call)) + return call.err; + *status = call.ebx; + *bat = call.ecx; if (apm_info.get_power_status_swabinminutes) { - *life = swab16((u16)edx); + *life = swab16((u16)call.edx); *life |= 0x8000; } else - *life = edx; + *life = call.edx; return APM_SUCCESS; } @@ -1048,12 +1090,14 @@ static int apm_get_battery_status(u_short which, u_short *status, static int apm_engage_power_management(u_short device, int enable) { u32 eax; + int err; if ((enable == 0) && (device == APM_DEVICE_ALL) && (apm_info.bios.flags & APM_BIOS_DISABLED)) return APM_DISABLED; - if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable, &eax)) - return (eax >> 8) & 0xff; + if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable, + &eax, &err)) + return err; if (device == APM_DEVICE_ALL) { if (enable) apm_info.bios.flags &= ~APM_BIOS_DISENGAGED; @@ -1190,8 +1234,10 @@ static int suspend(int vetoable) struct apm_user *as; device_suspend(PMSG_SUSPEND); - local_irq_disable(); + device_power_down(PMSG_SUSPEND); + + local_irq_disable(); sysdev_suspend(PMSG_SUSPEND); local_irq_enable(); @@ -1209,9 +1255,12 @@ static int suspend(int vetoable) if (err != APM_SUCCESS) apm_error("suspend", err); err = (err == APM_SUCCESS) ? 0 : -EIO; + sysdev_resume(); - device_power_up(PMSG_RESUME); local_irq_enable(); + + device_power_up(PMSG_RESUME); + device_resume(PMSG_RESUME); queue_event(APM_NORMAL_RESUME, NULL); spin_lock(&user_list_lock); @@ -1228,8 +1277,9 @@ static void standby(void) { int err; - local_irq_disable(); device_power_down(PMSG_SUSPEND); + + local_irq_disable(); sysdev_suspend(PMSG_SUSPEND); local_irq_enable(); @@ -1239,8 +1289,9 @@ static void standby(void) local_irq_disable(); sysdev_resume(); - device_power_up(PMSG_RESUME); local_irq_enable(); + + device_power_up(PMSG_RESUME); } static apm_event_t get_event(void) @@ -1682,16 +1733,14 @@ static int apm(void *unused) char *power_stat; char *bat_stat; -#ifdef CONFIG_SMP /* 2002/08/01 - WT * This is to avoid random crashes at boot time during initialization * on SMP systems in case of "apm=power-off" mode. Seen on ASUS A7M266D. * Some bioses don't like being called from CPU != 0. * Method suggested by Ingo Molnar. */ - set_cpus_allowed(current, cpumask_of_cpu(0)); + set_cpus_allowed_ptr(current, cpumask_of(0)); BUG_ON(smp_processor_id() != 0); -#endif if (apm_info.connection_version == 0) { apm_info.connection_version = apm_info.bios.version; diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index fbf2f33..5a6aa1c 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -18,6 +18,7 @@ #include <asm/thread_info.h> #include <asm/bootparam.h> #include <asm/elf.h> +#include <asm/suspend.h> #include <xen/interface/xen.h> diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 8793ab3..e72f062 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -16,6 +16,7 @@ #include <asm/thread_info.h> #include <asm/ia32.h> #include <asm/bootparam.h> +#include <asm/suspend.h> #include <xen/interface/xen.h> diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index 2ac0ab7..fc999e6 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -83,15 +83,15 @@ void __init setup_bios_corruption_check(void) u64 size; addr = find_e820_area_size(addr, &size, PAGE_SIZE); - if (addr == 0) + if (!(addr + 1)) + break; + + if (addr >= corruption_check_size) break; if ((addr + size) > corruption_check_size) size = corruption_check_size - addr; - if (size == 0) - break; - e820_update_range(addr, size, E820_RAM, E820_RESERVED); scan_areas[num_scan_areas].addr = addr; scan_areas[num_scan_areas].size = size; diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index c381330..3efcb2b 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -14,11 +14,12 @@ obj-y += vmware.o hypervisor.o obj-$(CONFIG_X86_32) += bugs.o cmpxchg.o obj-$(CONFIG_X86_64) += bugs_64.o +obj-$(CONFIG_X86_CPU_DEBUG) += cpu_debug.o + obj-$(CONFIG_CPU_SUP_INTEL) += intel.o obj-$(CONFIG_CPU_SUP_AMD) += amd.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o -obj-$(CONFIG_CPU_SUP_CENTAUR_32) += centaur.o -obj-$(CONFIG_CPU_SUP_CENTAUR_64) += centaur_64.o +obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c index 6882a73..8220ae6 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/addon_cpuid_features.c @@ -29,7 +29,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) u32 regs[4]; const struct cpuid_bit *cb; - static const struct cpuid_bit cpuid_bits[] = { + static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006 }, { 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index edcde52..fd69c51 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -5,6 +5,7 @@ #include <asm/io.h> #include <asm/processor.h> #include <asm/apic.h> +#include <asm/cpu.h> #ifdef CONFIG_X86_64 # include <asm/numa_64.h> @@ -141,6 +142,55 @@ static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c) } } +static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + /* calling is from identify_secondary_cpu() ? */ + if (c->cpu_index == boot_cpu_id) + return; + + /* + * Certain Athlons might work (for various values of 'work') in SMP + * but they are not certified as MP capable. + */ + /* Athlon 660/661 is valid. */ + if ((c->x86_model == 6) && ((c->x86_mask == 0) || + (c->x86_mask == 1))) + goto valid_k7; + + /* Duron 670 is valid */ + if ((c->x86_model == 7) && (c->x86_mask == 0)) + goto valid_k7; + + /* + * Athlon 662, Duron 671, and Athlon >model 7 have capability + * bit. It's worth noting that the A5 stepping (662) of some + * Athlon XP's have the MP bit set. + * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for + * more. + */ + if (((c->x86_model == 6) && (c->x86_mask >= 2)) || + ((c->x86_model == 7) && (c->x86_mask >= 1)) || + (c->x86_model > 7)) + if (cpu_has_mp) + goto valid_k7; + + /* If we get here, not a certified SMP capable AMD system. */ + + /* + * Don't taint if we are running SMP kernel on a single non-MP + * approved Athlon + */ + WARN_ONCE(1, "WARNING: This combination of AMD" + "processors is not suitable for SMP.\n"); + if (!test_taint(TAINT_UNSAFE_SMP)) + add_taint(TAINT_UNSAFE_SMP); + +valid_k7: + ; +#endif +} + static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c) { u32 l, h; @@ -175,6 +225,8 @@ static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c) } set_cpu_cap(c, X86_FEATURE_K7); + + amd_k7_smp_check(c); } #endif @@ -454,7 +506,7 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, unsigned int } #endif -static struct cpu_dev amd_cpu_dev __cpuinitdata = { +static const struct cpu_dev __cpuinitconst amd_cpu_dev = { .c_vendor = "AMD", .c_ident = { "AuthenticAMD" }, #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 89bfdd9..c95e831 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -1,11 +1,11 @@ +#include <linux/bitops.h> #include <linux/kernel.h> #include <linux/init.h> -#include <linux/bitops.h> #include <asm/processor.h> -#include <asm/msr.h> #include <asm/e820.h> #include <asm/mtrr.h> +#include <asm/msr.h> #include "cpu.h" @@ -276,7 +276,7 @@ static void __cpuinit init_c3(struct cpuinfo_x86 *c) */ c->x86_capability[5] = cpuid_edx(0xC0000001); } - +#ifdef CONFIG_X86_32 /* Cyrix III family needs CX8 & PGE explicitly enabled. */ if (c->x86_model >= 6 && c->x86_model <= 9) { rdmsr(MSR_VIA_FCR, lo, hi); @@ -288,6 +288,11 @@ static void __cpuinit init_c3(struct cpuinfo_x86 *c) /* Before Nehemiah, the C3's had 3dNOW! */ if (c->x86_model >= 6 && c->x86_model < 9) set_cpu_cap(c, X86_FEATURE_3DNOW); +#endif + if (c->x86 == 0x6 && c->x86_model >= 0xf) { + c->x86_cache_alignment = c->x86_clflush_size * 2; + set_cpu_cap(c, X86_FEATURE_REP_GOOD); + } display_cacheinfo(c); } @@ -316,16 +321,25 @@ enum { static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c) { switch (c->x86) { +#ifdef CONFIG_X86_32 case 5: /* Emulate MTRRs using Centaur's MCR. */ set_cpu_cap(c, X86_FEATURE_CENTAUR_MCR); break; +#endif + case 6: + if (c->x86_model >= 0xf) + set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); + break; } +#ifdef CONFIG_X86_64 + set_cpu_cap(c, X86_FEATURE_SYSENTER32); +#endif } static void __cpuinit init_centaur(struct cpuinfo_x86 *c) { - +#ifdef CONFIG_X86_32 char *name; u32 fcr_set = 0; u32 fcr_clr = 0; @@ -337,8 +351,10 @@ static void __cpuinit init_centaur(struct cpuinfo_x86 *c) * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */ clear_cpu_cap(c, 0*32+31); - +#endif + early_init_centaur(c); switch (c->x86) { +#ifdef CONFIG_X86_32 case 5: switch (c->x86_model) { case 4: @@ -442,16 +458,20 @@ static void __cpuinit init_centaur(struct cpuinfo_x86 *c) } sprintf(c->x86_model_id, "WinChip %s", name); break; - +#endif case 6: init_c3(c); break; } +#ifdef CONFIG_X86_64 + set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); +#endif } static unsigned int __cpuinit centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size) { +#ifdef CONFIG_X86_32 /* VIA C3 CPUs (670-68F) need further shifting. */ if ((c->x86 == 6) && ((c->x86_model == 7) || (c->x86_model == 8))) size >>= 8; @@ -464,11 +484,11 @@ centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size) if ((c->x86 == 6) && (c->x86_model == 9) && (c->x86_mask == 1) && (size == 65)) size -= 1; - +#endif return size; } -static struct cpu_dev centaur_cpu_dev __cpuinitdata = { +static const struct cpu_dev __cpuinitconst centaur_cpu_dev = { .c_vendor = "Centaur", .c_ident = { "CentaurHauls" }, .c_early_init = early_init_centaur, diff --git a/arch/x86/kernel/cpu/centaur_64.c b/arch/x86/kernel/cpu/centaur_64.c deleted file mode 100644 index a1625f5..0000000 --- a/arch/x86/kernel/cpu/centaur_64.c +++ /dev/null @@ -1,37 +0,0 @@ -#include <linux/init.h> -#include <linux/smp.h> - -#include <asm/cpufeature.h> -#include <asm/processor.h> - -#include "cpu.h" - -static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c) -{ - if (c->x86 == 0x6 && c->x86_model >= 0xf) - set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); - - set_cpu_cap(c, X86_FEATURE_SYSENTER32); -} - -static void __cpuinit init_centaur(struct cpuinfo_x86 *c) -{ - early_init_centaur(c); - - if (c->x86 == 0x6 && c->x86_model >= 0xf) { - c->x86_cache_alignment = c->x86_clflush_size * 2; - set_cpu_cap(c, X86_FEATURE_REP_GOOD); - } - set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); -} - -static struct cpu_dev centaur_cpu_dev __cpuinitdata = { - .c_vendor = "Centaur", - .c_ident = { "CentaurHauls" }, - .c_early_init = early_init_centaur, - .c_init = init_centaur, - .c_x86_vendor = X86_VENDOR_CENTAUR, -}; - -cpu_dev_register(centaur_cpu_dev); - diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b66af09..a86769e 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1,53 +1,51 @@ -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/string.h> #include <linux/bootmem.h> +#include <linux/linkage.h> #include <linux/bitops.h> +#include <linux/kernel.h> #include <linux/module.h> -#include <linux/kgdb.h> -#include <linux/topology.h> +#include <linux/percpu.h> +#include <linux/string.h> #include <linux/delay.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/kgdb.h> #include <linux/smp.h> -#include <linux/percpu.h> -#include <asm/i387.h> -#include <asm/msr.h> -#include <asm/io.h> -#include <asm/linkage.h> +#include <linux/io.h> + +#include <asm/stackprotector.h> +#include <asm/perf_counter.h> #include <asm/mmu_context.h> +#include <asm/hypervisor.h> +#include <asm/processor.h> +#include <asm/sections.h> +#include <asm/topology.h> +#include <asm/cpumask.h> +#include <asm/pgtable.h> +#include <asm/atomic.h> +#include <asm/proto.h> +#include <asm/setup.h> +#include <asm/apic.h> +#include <asm/desc.h> +#include <asm/i387.h> #include <asm/mtrr.h> +#include <asm/numa.h> +#include <asm/asm.h> +#include <asm/cpu.h> #include <asm/mce.h> -#include <asm/perf_counter.h> +#include <asm/msr.h> #include <asm/pat.h> -#include <asm/asm.h> -#include <asm/numa.h> #include <asm/smp.h> -#include <asm/cpu.h> -#include <asm/cpumask.h> -#include <asm/apic.h> #ifdef CONFIG_X86_LOCAL_APIC #include <asm/uv/uv.h> #endif -#include <asm/pgtable.h> -#include <asm/processor.h> -#include <asm/desc.h> -#include <asm/atomic.h> -#include <asm/proto.h> -#include <asm/sections.h> -#include <asm/setup.h> -#include <asm/hypervisor.h> -#include <asm/stackprotector.h> - #include "cpu.h" -#ifdef CONFIG_X86_64 - /* all of these masks are initialized in setup_cpu_local_masks() */ -cpumask_var_t cpu_callin_mask; -cpumask_var_t cpu_callout_mask; cpumask_var_t cpu_initialized_mask; +cpumask_var_t cpu_callout_mask; +cpumask_var_t cpu_callin_mask; /* representing cpus for which sibling maps can be computed */ cpumask_var_t cpu_sibling_setup_mask; @@ -61,17 +59,7 @@ void __init setup_cpu_local_masks(void) alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask); } -#else /* CONFIG_X86_32 */ - -cpumask_t cpu_callin_map; -cpumask_t cpu_callout_map; -cpumask_t cpu_initialized; -cpumask_t cpu_sibling_setup_map; - -#endif /* CONFIG_X86_32 */ - - -static struct cpu_dev *this_cpu __cpuinitdata; +static const struct cpu_dev *this_cpu __cpuinitdata; DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { #ifdef CONFIG_X86_64 @@ -80,48 +68,48 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { * IRET will check the segment types kkeil 2000/10/28 * Also sysret mandates a special GDT layout * - * The TLS descriptors are currently at a different place compared to i386. + * TLS descriptors are currently at a different place compared to i386. * Hopefully nobody expects them at a fixed place (Wine?) */ - [GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } }, - [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00af9b00 } } }, - [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9300 } } }, - [GDT_ENTRY_DEFAULT_USER32_CS] = { { { 0x0000ffff, 0x00cffb00 } } }, - [GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff300 } } }, - [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00affb00 } } }, + [GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } }, + [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00af9b00 } } }, + [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9300 } } }, + [GDT_ENTRY_DEFAULT_USER32_CS] = { { { 0x0000ffff, 0x00cffb00 } } }, + [GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff300 } } }, + [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00affb00 } } }, #else - [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00cf9a00 } } }, - [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9200 } } }, - [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00cffa00 } } }, - [GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff200 } } }, + [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00cf9a00 } } }, + [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9200 } } }, + [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00cffa00 } } }, + [GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff200 } } }, /* * Segments used for calling PnP BIOS have byte granularity. * They code segments and data segments have fixed 64k limits, * the transfer segment sizes are set at run time. */ /* 32-bit code */ - [GDT_ENTRY_PNPBIOS_CS32] = { { { 0x0000ffff, 0x00409a00 } } }, + [GDT_ENTRY_PNPBIOS_CS32] = { { { 0x0000ffff, 0x00409a00 } } }, /* 16-bit code */ - [GDT_ENTRY_PNPBIOS_CS16] = { { { 0x0000ffff, 0x00009a00 } } }, + [GDT_ENTRY_PNPBIOS_CS16] = { { { 0x0000ffff, 0x00009a00 } } }, /* 16-bit data */ - [GDT_ENTRY_PNPBIOS_DS] = { { { 0x0000ffff, 0x00009200 } } }, + [GDT_ENTRY_PNPBIOS_DS] = { { { 0x0000ffff, 0x00009200 } } }, /* 16-bit data */ - [GDT_ENTRY_PNPBIOS_TS1] = { { { 0x00000000, 0x00009200 } } }, + [GDT_ENTRY_PNPBIOS_TS1] = { { { 0x00000000, 0x00009200 } } }, /* 16-bit data */ - [GDT_ENTRY_PNPBIOS_TS2] = { { { 0x00000000, 0x00009200 } } }, + [GDT_ENTRY_PNPBIOS_TS2] = { { { 0x00000000, 0x00009200 } } }, /* * The APM segments have byte granularity and their bases * are set at run time. All have 64k limits. */ /* 32-bit code */ - [GDT_ENTRY_APMBIOS_BASE] = { { { 0x0000ffff, 0x00409a00 } } }, + [GDT_ENTRY_APMBIOS_BASE] = { { { 0x0000ffff, 0x00409a00 } } }, /* 16-bit code */ - [GDT_ENTRY_APMBIOS_BASE+1] = { { { 0x0000ffff, 0x00009a00 } } }, + [GDT_ENTRY_APMBIOS_BASE+1] = { { { 0x0000ffff, 0x00009a00 } } }, /* data */ - [GDT_ENTRY_APMBIOS_BASE+2] = { { { 0x0000ffff, 0x00409200 } } }, + [GDT_ENTRY_APMBIOS_BASE+2] = { { { 0x0000ffff, 0x00409200 } } }, - [GDT_ENTRY_ESPFIX_SS] = { { { 0x00000000, 0x00c09200 } } }, - [GDT_ENTRY_PERCPU] = { { { 0x0000ffff, 0x00cf9200 } } }, + [GDT_ENTRY_ESPFIX_SS] = { { { 0x00000000, 0x00c09200 } } }, + [GDT_ENTRY_PERCPU] = { { { 0x0000ffff, 0x00cf9200 } } }, GDT_STACK_CANARY_INIT #endif } }; @@ -165,16 +153,17 @@ static inline int flag_is_changeable_p(u32 flag) * the CPUID. Add "volatile" to not allow gcc to * optimize the subsequent calls to this function. */ - asm volatile ("pushfl\n\t" - "pushfl\n\t" - "popl %0\n\t" - "movl %0,%1\n\t" - "xorl %2,%0\n\t" - "pushl %0\n\t" - "popfl\n\t" - "pushfl\n\t" - "popl %0\n\t" - "popfl\n\t" + asm volatile ("pushfl \n\t" + "pushfl \n\t" + "popl %0 \n\t" + "movl %0, %1 \n\t" + "xorl %2, %0 \n\t" + "pushl %0 \n\t" + "popfl \n\t" + "pushfl \n\t" + "popl %0 \n\t" + "popfl \n\t" + : "=&r" (f1), "=&r" (f2) : "ir" (flag)); @@ -189,18 +178,22 @@ static int __cpuinit have_cpuid_p(void) static void __cpuinit squash_the_stupid_serial_number(struct cpuinfo_x86 *c) { - if (cpu_has(c, X86_FEATURE_PN) && disable_x86_serial_nr) { - /* Disable processor serial number */ - unsigned long lo, hi; - rdmsr(MSR_IA32_BBL_CR_CTL, lo, hi); - lo |= 0x200000; - wrmsr(MSR_IA32_BBL_CR_CTL, lo, hi); - printk(KERN_NOTICE "CPU serial number disabled.\n"); - clear_cpu_cap(c, X86_FEATURE_PN); - - /* Disabling the serial number may affect the cpuid level */ - c->cpuid_level = cpuid_eax(0); - } + unsigned long lo, hi; + + if (!cpu_has(c, X86_FEATURE_PN) || !disable_x86_serial_nr) + return; + + /* Disable processor serial number: */ + + rdmsr(MSR_IA32_BBL_CR_CTL, lo, hi); + lo |= 0x200000; + wrmsr(MSR_IA32_BBL_CR_CTL, lo, hi); + + printk(KERN_NOTICE "CPU serial number disabled.\n"); + clear_cpu_cap(c, X86_FEATURE_PN); + + /* Disabling the serial number may affect the cpuid level */ + c->cpuid_level = cpuid_eax(0); } static int __init x86_serial_nr_setup(char *s) @@ -233,6 +226,7 @@ struct cpuid_dependent_feature { u32 feature; u32 level; }; + static const struct cpuid_dependent_feature __cpuinitconst cpuid_dependent_features[] = { { X86_FEATURE_MWAIT, 0x00000005 }, @@ -244,7 +238,11 @@ cpuid_dependent_features[] = { static void __cpuinit filter_cpuid_features(struct cpuinfo_x86 *c, bool warn) { const struct cpuid_dependent_feature *df; + for (df = cpuid_dependent_features; df->feature; df++) { + + if (!cpu_has(c, df->feature)) + continue; /* * Note: cpuid_level is set to -1 if unavailable, but * extended_extended_level is set to 0 if unavailable @@ -252,32 +250,32 @@ static void __cpuinit filter_cpuid_features(struct cpuinfo_x86 *c, bool warn) * when signed; hence the weird messing around with * signs here... */ - if (cpu_has(c, df->feature) && - ((s32)df->level < 0 ? + if (!((s32)df->level < 0 ? (u32)df->level > (u32)c->extended_cpuid_level : - (s32)df->level > (s32)c->cpuid_level)) { - clear_cpu_cap(c, df->feature); - if (warn) - printk(KERN_WARNING - "CPU: CPU feature %s disabled " - "due to lack of CPUID level 0x%x\n", - x86_cap_flags[df->feature], - df->level); - } + (s32)df->level > (s32)c->cpuid_level)) + continue; + + clear_cpu_cap(c, df->feature); + if (!warn) + continue; + + printk(KERN_WARNING + "CPU: CPU feature %s disabled, no CPUID level 0x%x\n", + x86_cap_flags[df->feature], df->level); } } /* * Naming convention should be: <Name> [(<Codename>)] * This table only is used unless init_<vendor>() below doesn't set it; - * in particular, if CPUID levels 0x80000002..4 are supported, this isn't used - * + * in particular, if CPUID levels 0x80000002..4 are supported, this + * isn't used */ /* Look up CPU names by table lookup. */ -static char __cpuinit *table_lookup_model(struct cpuinfo_x86 *c) +static const char *__cpuinit table_lookup_model(struct cpuinfo_x86 *c) { - struct cpu_model_info *info; + const struct cpu_model_info *info; if (c->x86_model >= 16) return NULL; /* Range check */ @@ -308,8 +306,10 @@ void load_percpu_segment(int cpu) load_stack_canary_segment(); } -/* Current gdt points %fs at the "master" per-cpu area: after this, - * it's on the real one. */ +/* + * Current gdt points %fs at the "master" per-cpu area: after this, + * it's on the real one. + */ void switch_to_new_gdt(int cpu) { struct desc_ptr gdt_descr; @@ -322,7 +322,7 @@ void switch_to_new_gdt(int cpu) load_percpu_segment(cpu); } -static struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {}; +static const struct cpu_dev *__cpuinitdata cpu_devs[X86_VENDOR_NUM] = {}; static void __cpuinit default_init(struct cpuinfo_x86 *c) { @@ -341,7 +341,7 @@ static void __cpuinit default_init(struct cpuinfo_x86 *c) #endif } -static struct cpu_dev __cpuinitdata default_cpu = { +static const struct cpu_dev __cpuinitconst default_cpu = { .c_init = default_init, .c_vendor = "Unknown", .c_x86_vendor = X86_VENDOR_UNKNOWN, @@ -355,22 +355,24 @@ static void __cpuinit get_model_name(struct cpuinfo_x86 *c) if (c->extended_cpuid_level < 0x80000004) return; - v = (unsigned int *) c->x86_model_id; + v = (unsigned int *)c->x86_model_id; cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]); cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]); cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]); c->x86_model_id[48] = 0; - /* Intel chips right-justify this string for some dumb reason; - undo that brain damage */ + /* + * Intel chips right-justify this string for some dumb reason; + * undo that brain damage: + */ p = q = &c->x86_model_id[0]; while (*p == ' ') - p++; + p++; if (p != q) { - while (*p) - *q++ = *p++; - while (q <= &c->x86_model_id[48]) - *q++ = '\0'; /* Zero-pad the rest */ + while (*p) + *q++ = *p++; + while (q <= &c->x86_model_id[48]) + *q++ = '\0'; /* Zero-pad the rest */ } } @@ -439,27 +441,30 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) if (smp_num_siblings == 1) { printk(KERN_INFO "CPU: Hyper-Threading is disabled\n"); - } else if (smp_num_siblings > 1) { + goto out; + } - if (smp_num_siblings > nr_cpu_ids) { - printk(KERN_WARNING "CPU: Unsupported number of siblings %d", - smp_num_siblings); - smp_num_siblings = 1; - return; - } + if (smp_num_siblings <= 1) + goto out; - index_msb = get_count_order(smp_num_siblings); - c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb); + if (smp_num_siblings > nr_cpu_ids) { + pr_warning("CPU: Unsupported number of siblings %d", + smp_num_siblings); + smp_num_siblings = 1; + return; + } - smp_num_siblings = smp_num_siblings / c->x86_max_cores; + index_msb = get_count_order(smp_num_siblings); + c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb); - index_msb = get_count_order(smp_num_siblings); + smp_num_siblings = smp_num_siblings / c->x86_max_cores; - core_bits = get_count_order(c->x86_max_cores); + index_msb = get_count_order(smp_num_siblings); - c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) & - ((1 << core_bits) - 1); - } + core_bits = get_count_order(c->x86_max_cores); + + c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) & + ((1 << core_bits) - 1); out: if ((c->x86_max_cores * smp_num_siblings) > 1) { @@ -474,8 +479,8 @@ out: static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c) { char *v = c->x86_vendor_id; - int i; static int printed; + int i; for (i = 0; i < X86_VENDOR_NUM; i++) { if (!cpu_devs[i]) @@ -484,6 +489,7 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c) if (!strcmp(v, cpu_devs[i]->c_ident[0]) || (cpu_devs[i]->c_ident[1] && !strcmp(v, cpu_devs[i]->c_ident[1]))) { + this_cpu = cpu_devs[i]; c->x86_vendor = this_cpu->c_x86_vendor; return; @@ -492,7 +498,9 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c) if (!printed) { printed++; - printk(KERN_ERR "CPU: vendor_id '%s' unknown, using generic init.\n", v); + printk(KERN_ERR + "CPU: vendor_id '%s' unknown, using generic init.\n", v); + printk(KERN_ERR "CPU: Your system may be unstable.\n"); } @@ -512,14 +520,17 @@ void __cpuinit cpu_detect(struct cpuinfo_x86 *c) /* Intel-defined flags: level 0x00000001 */ if (c->cpuid_level >= 0x00000001) { u32 junk, tfms, cap0, misc; + cpuid(0x00000001, &tfms, &misc, &junk, &cap0); c->x86 = (tfms >> 8) & 0xf; c->x86_model = (tfms >> 4) & 0xf; c->x86_mask = tfms & 0xf; + if (c->x86 == 0xf) c->x86 += (tfms >> 20) & 0xff; if (c->x86 >= 0x6) c->x86_model += ((tfms >> 16) & 0xf) << 4; + if (cap0 & (1<<19)) { c->x86_clflush_size = ((misc >> 8) & 0xff) * 8; c->x86_cache_alignment = c->x86_clflush_size; @@ -535,6 +546,7 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) /* Intel-defined flags: level 0x00000001 */ if (c->cpuid_level >= 0x00000001) { u32 capability, excap; + cpuid(0x00000001, &tfms, &ebx, &excap, &capability); c->x86_capability[0] = capability; c->x86_capability[4] = excap; @@ -543,6 +555,7 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) /* AMD-defined flags: level 0x80000001 */ xlvl = cpuid_eax(0x80000000); c->extended_cpuid_level = xlvl; + if ((xlvl & 0xffff0000) == 0x80000000) { if (xlvl >= 0x80000001) { c->x86_capability[1] = cpuid_edx(0x80000001); @@ -550,13 +563,15 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) } } -#ifdef CONFIG_X86_64 if (c->extended_cpuid_level >= 0x80000008) { u32 eax = cpuid_eax(0x80000008); c->x86_virt_bits = (eax >> 8) & 0xff; c->x86_phys_bits = eax & 0xff; } +#ifdef CONFIG_X86_32 + else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) + c->x86_phys_bits = 36; #endif if (c->extended_cpuid_level >= 0x80000007) @@ -603,8 +618,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_64 c->x86_clflush_size = 64; + c->x86_phys_bits = 36; + c->x86_virt_bits = 48; #else c->x86_clflush_size = 32; + c->x86_phys_bits = 32; + c->x86_virt_bits = 32; #endif c->x86_cache_alignment = c->x86_clflush_size; @@ -635,12 +654,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) void __init early_cpu_init(void) { - struct cpu_dev **cdev; + const struct cpu_dev *const *cdev; int count = 0; - printk("KERNEL supported cpus:\n"); + printk(KERN_INFO "KERNEL supported cpus:\n"); for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) { - struct cpu_dev *cpudev = *cdev; + const struct cpu_dev *cpudev = *cdev; unsigned int j; if (count >= X86_VENDOR_NUM) @@ -651,7 +670,7 @@ void __init early_cpu_init(void) for (j = 0; j < 2; j++) { if (!cpudev->c_ident[j]) continue; - printk(" %s %s\n", cpudev->c_vendor, + printk(KERN_INFO " %s %s\n", cpudev->c_vendor, cpudev->c_ident[j]); } } @@ -727,9 +746,13 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) c->x86_coreid_bits = 0; #ifdef CONFIG_X86_64 c->x86_clflush_size = 64; + c->x86_phys_bits = 36; + c->x86_virt_bits = 48; #else c->cpuid_level = -1; /* CPUID not detected */ c->x86_clflush_size = 32; + c->x86_phys_bits = 32; + c->x86_virt_bits = 32; #endif c->x86_cache_alignment = c->x86_clflush_size; memset(&c->x86_capability, 0, sizeof c->x86_capability); @@ -760,8 +783,8 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) squash_the_stupid_serial_number(c); /* - * The vendor-specific functions might have changed features. Now - * we do "generic changes." + * The vendor-specific functions might have changed features. + * Now we do "generic changes." */ /* Filter out anything that depends on CPUID levels we don't have */ @@ -769,7 +792,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) /* If the model name is still unset, do table lookup. */ if (!c->x86_model_id[0]) { - char *p; + const char *p; p = table_lookup_model(c); if (p) strcpy(c->x86_model_id, p); @@ -825,6 +848,7 @@ static void vgetcpu_set_mode(void) void __init identify_boot_cpu(void) { identify_cpu(&boot_cpu_data); + init_c1e_mask(); #ifdef CONFIG_X86_32 sysenter_setup(); enable_sep_cpu(); @@ -845,11 +869,11 @@ void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c) } struct msr_range { - unsigned min; - unsigned max; + unsigned min; + unsigned max; }; -static struct msr_range msr_range_array[] __cpuinitdata = { +static const struct msr_range msr_range_array[] __cpuinitconst = { { 0x00000000, 0x00000418}, { 0xc0000000, 0xc000040b}, { 0xc0010000, 0xc0010142}, @@ -858,14 +882,15 @@ static struct msr_range msr_range_array[] __cpuinitdata = { static void __cpuinit print_cpu_msr(void) { + unsigned index_min, index_max; unsigned index; u64 val; int i; - unsigned index_min, index_max; for (i = 0; i < ARRAY_SIZE(msr_range_array); i++) { index_min = msr_range_array[i].min; index_max = msr_range_array[i].max; + for (index = index_min; index < index_max; index++) { if (rdmsrl_amd_safe(index, &val)) continue; @@ -875,6 +900,7 @@ static void __cpuinit print_cpu_msr(void) } static int show_msr __cpuinitdata; + static __init int setup_show_msr(char *arg) { int num; @@ -896,12 +922,14 @@ __setup("noclflush", setup_noclflush); void __cpuinit print_cpu_info(struct cpuinfo_x86 *c) { - char *vendor = NULL; + const char *vendor = NULL; - if (c->x86_vendor < X86_VENDOR_NUM) + if (c->x86_vendor < X86_VENDOR_NUM) { vendor = this_cpu->c_vendor; - else if (c->cpuid_level >= 0) - vendor = c->x86_vendor_id; + } else { + if (c->cpuid_level >= 0) + vendor = c->x86_vendor_id; + } if (vendor && !strstr(c->x86_model_id, vendor)) printk(KERN_CONT "%s ", vendor); @@ -928,10 +956,12 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c) static __init int setup_disablecpuid(char *arg) { int bit; + if (get_option(&arg, &bit) && bit < NCAPINTS*32) setup_clear_cpu_cap(bit); else return 0; + return 1; } __setup("clearcpuid=", setup_disablecpuid); @@ -941,6 +971,7 @@ struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table }; DEFINE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __aligned(PAGE_SIZE); + DEFINE_PER_CPU(char *, irq_stack_ptr) = init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64; @@ -950,12 +981,21 @@ EXPORT_PER_CPU_SYMBOL(kernel_stack); DEFINE_PER_CPU(unsigned int, irq_count) = -1; +/* + * Special IST stacks which the CPU switches to when it calls + * an IST-marked descriptor entry. Up to 7 stacks (hardware + * limit), all of them are 4K, except the debug stack which + * is 8K. + */ +static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { + [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, + [DEBUG_STACK - 1] = DEBUG_STKSZ +}; + static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]) __aligned(PAGE_SIZE); -extern asmlinkage void ignore_sysret(void); - /* May not be marked __init: used by software suspend */ void syscall_init(void) { @@ -985,7 +1025,7 @@ unsigned long kernel_eflags; */ DEFINE_PER_CPU(struct orig_ist, orig_ist); -#else /* x86_64 */ +#else /* CONFIG_X86_64 */ #ifdef CONFIG_CC_STACKPROTECTOR DEFINE_PER_CPU(unsigned long, stack_canary); @@ -997,9 +1037,26 @@ struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs) memset(regs, 0, sizeof(struct pt_regs)); regs->fs = __KERNEL_PERCPU; regs->gs = __KERNEL_STACK_CANARY; + return regs; } -#endif /* x86_64 */ +#endif /* CONFIG_X86_64 */ + +/* + * Clear all 6 debug registers: + */ +static void clear_all_debug_regs(void) +{ + int i; + + for (i = 0; i < 8; i++) { + /* Ignore db4, db5 */ + if ((i == 4) || (i == 5)) + continue; + + set_debugreg(0, i); + } +} /* * cpu_init() initializes state that is per-CPU. Some data is already @@ -1009,15 +1066,20 @@ struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs) * A lot of state is already set up in PDA init for 64 bit */ #ifdef CONFIG_X86_64 + void __cpuinit cpu_init(void) { - int cpu = stack_smp_processor_id(); - struct tss_struct *t = &per_cpu(init_tss, cpu); - struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu); - unsigned long v; + struct orig_ist *orig_ist; struct task_struct *me; + struct tss_struct *t; + unsigned long v; + int cpu; int i; + cpu = stack_smp_processor_id(); + t = &per_cpu(init_tss, cpu); + orig_ist = &per_cpu(orig_ist, cpu); + #ifdef CONFIG_NUMA if (cpu != 0 && percpu_read(node_number) == 0 && cpu_to_node(cpu) != NUMA_NO_NODE) @@ -1058,19 +1120,17 @@ void __cpuinit cpu_init(void) * set up and load the per-CPU TSS */ if (!orig_ist->ist[0]) { - static const unsigned int sizes[N_EXCEPTION_STACKS] = { - [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, - [DEBUG_STACK - 1] = DEBUG_STKSZ - }; char *estacks = per_cpu(exception_stacks, cpu); + for (v = 0; v < N_EXCEPTION_STACKS; v++) { - estacks += sizes[v]; + estacks += exception_stack_sizes[v]; orig_ist->ist[v] = t->x86_tss.ist[v] = (unsigned long)estacks; } } t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); + /* * <= is required because the CPU will access up to * 8 bits beyond the end of the IO permission bitmap. @@ -1080,8 +1140,7 @@ void __cpuinit cpu_init(void) atomic_inc(&init_mm.mm_count); me->active_mm = &init_mm; - if (me->mm) - BUG(); + BUG_ON(me->mm); enter_lazy_tlb(&init_mm, me); load_sp0(t, ¤t->thread); @@ -1100,17 +1159,7 @@ void __cpuinit cpu_init(void) arch_kgdb_ops.correct_hw_break(); else #endif - { - /* - * Clear all 6 debug registers: - */ - set_debugreg(0UL, 0); - set_debugreg(0UL, 1); - set_debugreg(0UL, 2); - set_debugreg(0UL, 3); - set_debugreg(0UL, 6); - set_debugreg(0UL, 7); - } + clear_all_debug_regs(); fpu_init(); @@ -1131,7 +1180,8 @@ void __cpuinit cpu_init(void) if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) { printk(KERN_WARNING "CPU#%d already initialized!\n", cpu); - for (;;) local_irq_enable(); + for (;;) + local_irq_enable(); } printk(KERN_INFO "Initializing CPU#%d\n", cpu); @@ -1147,8 +1197,7 @@ void __cpuinit cpu_init(void) */ atomic_inc(&init_mm.mm_count); curr->active_mm = &init_mm; - if (curr->mm) - BUG(); + BUG_ON(curr->mm); enter_lazy_tlb(&init_mm, curr); load_sp0(t, thread); @@ -1161,13 +1210,7 @@ void __cpuinit cpu_init(void) __set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss); #endif - /* Clear all 6 debug registers: */ - set_debugreg(0, 0); - set_debugreg(0, 1); - set_debugreg(0, 2); - set_debugreg(0, 3); - set_debugreg(0, 6); - set_debugreg(0, 7); + clear_all_debug_regs(); /* * Force FPU initialization: @@ -1187,6 +1230,4 @@ void __cpuinit cpu_init(void) xsave_init(); } - - #endif diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index de4094a..6de9a90 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -3,33 +3,34 @@ #define ARCH_X86_CPU_H struct cpu_model_info { - int vendor; - int family; - char *model_names[16]; + int vendor; + int family; + const char *model_names[16]; }; /* attempt to consolidate cpu attributes */ struct cpu_dev { - char * c_vendor; + const char *c_vendor; /* some have two possibilities for cpuid string */ - char * c_ident[2]; + const char *c_ident[2]; struct cpu_model_info c_models[4]; - void (*c_early_init)(struct cpuinfo_x86 *c); - void (*c_init)(struct cpuinfo_x86 * c); - void (*c_identify)(struct cpuinfo_x86 * c); - unsigned int (*c_size_cache)(struct cpuinfo_x86 * c, unsigned int size); - int c_x86_vendor; + void (*c_early_init)(struct cpuinfo_x86 *); + void (*c_init)(struct cpuinfo_x86 *); + void (*c_identify)(struct cpuinfo_x86 *); + unsigned int (*c_size_cache)(struct cpuinfo_x86 *, unsigned int); + int c_x86_vendor; }; #define cpu_dev_register(cpu_devX) \ - static struct cpu_dev *__cpu_dev_##cpu_devX __used \ + static const struct cpu_dev *const __cpu_dev_##cpu_devX __used \ __attribute__((__section__(".x86_cpu_dev.init"))) = \ &cpu_devX; -extern struct cpu_dev *__x86_cpu_dev_start[], *__x86_cpu_dev_end[]; +extern const struct cpu_dev *const __x86_cpu_dev_start[], + *const __x86_cpu_dev_end[]; extern void display_cacheinfo(struct cpuinfo_x86 *c); diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c new file mode 100755 index 0000000..46e29ab --- /dev/null +++ b/arch/x86/kernel/cpu/cpu_debug.c @@ -0,0 +1,901 @@ +/* + * CPU x86 architecture debug code + * + * Copyright(C) 2009 Jaswinder Singh Rajput + * + * For licencing details see kernel-base/COPYING + */ + +#include <linux/interrupt.h> +#include <linux/compiler.h> +#include <linux/seq_file.h> +#include <linux/debugfs.h> +#include <linux/kprobes.h> +#include <linux/uaccess.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/signal.h> +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/smp.h> + +#include <asm/cpu_debug.h> +#include <asm/paravirt.h> +#include <asm/system.h> +#include <asm/traps.h> +#include <asm/apic.h> +#include <asm/desc.h> + +static DEFINE_PER_CPU(struct cpu_cpuX_base, cpu_arr[CPU_REG_ALL_BIT]); +static DEFINE_PER_CPU(struct cpu_private *, priv_arr[MAX_CPU_FILES]); +static DEFINE_PER_CPU(unsigned, cpu_modelflag); +static DEFINE_PER_CPU(int, cpu_priv_count); +static DEFINE_PER_CPU(unsigned, cpu_model); + +static DEFINE_MUTEX(cpu_debug_lock); + +static struct dentry *cpu_debugfs_dir; + +static struct cpu_debug_base cpu_base[] = { + { "mc", CPU_MC, 0 }, + { "monitor", CPU_MONITOR, 0 }, + { "time", CPU_TIME, 0 }, + { "pmc", CPU_PMC, 1 }, + { "platform", CPU_PLATFORM, 0 }, + { "apic", CPU_APIC, 0 }, + { "poweron", CPU_POWERON, 0 }, + { "control", CPU_CONTROL, 0 }, + { "features", CPU_FEATURES, 0 }, + { "lastbranch", CPU_LBRANCH, 0 }, + { "bios", CPU_BIOS, 0 }, + { "freq", CPU_FREQ, 0 }, + { "mtrr", CPU_MTRR, 0 }, + { "perf", CPU_PERF, 0 }, + { "cache", CPU_CACHE, 0 }, + { "sysenter", CPU_SYSENTER, 0 }, + { "therm", CPU_THERM, 0 }, + { "misc", CPU_MISC, 0 }, + { "debug", CPU_DEBUG, 0 }, + { "pat", CPU_PAT, 0 }, + { "vmx", CPU_VMX, 0 }, + { "call", CPU_CALL, 0 }, + { "base", CPU_BASE, 0 }, + { "ver", CPU_VER, 0 }, + { "conf", CPU_CONF, 0 }, + { "smm", CPU_SMM, 0 }, + { "svm", CPU_SVM, 0 }, + { "osvm", CPU_OSVM, 0 }, + { "tss", CPU_TSS, 0 }, + { "cr", CPU_CR, 0 }, + { "dt", CPU_DT, 0 }, + { "registers", CPU_REG_ALL, 0 }, +}; + +static struct cpu_file_base cpu_file[] = { + { "index", CPU_REG_ALL, 0 }, + { "value", CPU_REG_ALL, 1 }, +}; + +/* Intel Registers Range */ +static struct cpu_debug_range cpu_intel_range[] = { + { 0x00000000, 0x00000001, CPU_MC, CPU_INTEL_ALL }, + { 0x00000006, 0x00000007, CPU_MONITOR, CPU_CX_AT_XE }, + { 0x00000010, 0x00000010, CPU_TIME, CPU_INTEL_ALL }, + { 0x00000011, 0x00000013, CPU_PMC, CPU_INTEL_PENTIUM }, + { 0x00000017, 0x00000017, CPU_PLATFORM, CPU_PX_CX_AT_XE }, + { 0x0000001B, 0x0000001B, CPU_APIC, CPU_P6_CX_AT_XE }, + + { 0x0000002A, 0x0000002A, CPU_POWERON, CPU_PX_CX_AT_XE }, + { 0x0000002B, 0x0000002B, CPU_POWERON, CPU_INTEL_XEON }, + { 0x0000002C, 0x0000002C, CPU_FREQ, CPU_INTEL_XEON }, + { 0x0000003A, 0x0000003A, CPU_CONTROL, CPU_CX_AT_XE }, + + { 0x00000040, 0x00000043, CPU_LBRANCH, CPU_PM_CX_AT_XE }, + { 0x00000044, 0x00000047, CPU_LBRANCH, CPU_PM_CO_AT }, + { 0x00000060, 0x00000063, CPU_LBRANCH, CPU_C2_AT }, + { 0x00000064, 0x00000067, CPU_LBRANCH, CPU_INTEL_ATOM }, + + { 0x00000079, 0x00000079, CPU_BIOS, CPU_P6_CX_AT_XE }, + { 0x00000088, 0x0000008A, CPU_CACHE, CPU_INTEL_P6 }, + { 0x0000008B, 0x0000008B, CPU_BIOS, CPU_P6_CX_AT_XE }, + { 0x0000009B, 0x0000009B, CPU_MONITOR, CPU_INTEL_XEON }, + + { 0x000000C1, 0x000000C2, CPU_PMC, CPU_P6_CX_AT }, + { 0x000000CD, 0x000000CD, CPU_FREQ, CPU_CX_AT }, + { 0x000000E7, 0x000000E8, CPU_PERF, CPU_CX_AT }, + { 0x000000FE, 0x000000FE, CPU_MTRR, CPU_P6_CX_XE }, + + { 0x00000116, 0x00000116, CPU_CACHE, CPU_INTEL_P6 }, + { 0x00000118, 0x00000118, CPU_CACHE, CPU_INTEL_P6 }, + { 0x00000119, 0x00000119, CPU_CACHE, CPU_INTEL_PX }, + { 0x0000011A, 0x0000011B, CPU_CACHE, CPU_INTEL_P6 }, + { 0x0000011E, 0x0000011E, CPU_CACHE, CPU_PX_CX_AT }, + + { 0x00000174, 0x00000176, CPU_SYSENTER, CPU_P6_CX_AT_XE }, + { 0x00000179, 0x0000017A, CPU_MC, CPU_PX_CX_AT_XE }, + { 0x0000017B, 0x0000017B, CPU_MC, CPU_P6_XE }, + { 0x00000186, 0x00000187, CPU_PMC, CPU_P6_CX_AT }, + { 0x00000198, 0x00000199, CPU_PERF, CPU_PM_CX_AT_XE }, + { 0x0000019A, 0x0000019A, CPU_TIME, CPU_PM_CX_AT_XE }, + { 0x0000019B, 0x0000019D, CPU_THERM, CPU_PM_CX_AT_XE }, + { 0x000001A0, 0x000001A0, CPU_MISC, CPU_PM_CX_AT_XE }, + + { 0x000001C9, 0x000001C9, CPU_LBRANCH, CPU_PM_CX_AT }, + { 0x000001D7, 0x000001D8, CPU_LBRANCH, CPU_INTEL_XEON }, + { 0x000001D9, 0x000001D9, CPU_DEBUG, CPU_CX_AT_XE }, + { 0x000001DA, 0x000001DA, CPU_LBRANCH, CPU_INTEL_XEON }, + { 0x000001DB, 0x000001DB, CPU_LBRANCH, CPU_P6_XE }, + { 0x000001DC, 0x000001DC, CPU_LBRANCH, CPU_INTEL_P6 }, + { 0x000001DD, 0x000001DE, CPU_LBRANCH, CPU_PX_CX_AT_XE }, + { 0x000001E0, 0x000001E0, CPU_LBRANCH, CPU_INTEL_P6 }, + + { 0x00000200, 0x0000020F, CPU_MTRR, CPU_P6_CX_XE }, + { 0x00000250, 0x00000250, CPU_MTRR, CPU_P6_CX_XE }, + { 0x00000258, 0x00000259, CPU_MTRR, CPU_P6_CX_XE }, + { 0x00000268, 0x0000026F, CPU_MTRR, CPU_P6_CX_XE }, + { 0x00000277, 0x00000277, CPU_PAT, CPU_C2_AT_XE }, + { 0x000002FF, 0x000002FF, CPU_MTRR, CPU_P6_CX_XE }, + + { 0x00000300, 0x00000308, CPU_PMC, CPU_INTEL_XEON }, + { 0x00000309, 0x0000030B, CPU_PMC, CPU_C2_AT_XE }, + { 0x0000030C, 0x00000311, CPU_PMC, CPU_INTEL_XEON }, + { 0x00000345, 0x00000345, CPU_PMC, CPU_C2_AT }, + { 0x00000360, 0x00000371, CPU_PMC, CPU_INTEL_XEON }, + { 0x0000038D, 0x00000390, CPU_PMC, CPU_C2_AT }, + { 0x000003A0, 0x000003BE, CPU_PMC, CPU_INTEL_XEON }, + { 0x000003C0, 0x000003CD, CPU_PMC, CPU_INTEL_XEON }, + { 0x000003E0, 0x000003E1, CPU_PMC, CPU_INTEL_XEON }, + { 0x000003F0, 0x000003F0, CPU_PMC, CPU_INTEL_XEON }, + { 0x000003F1, 0x000003F1, CPU_PMC, CPU_C2_AT_XE }, + { 0x000003F2, 0x000003F2, CPU_PMC, CPU_INTEL_XEON }, + + { 0x00000400, 0x00000402, CPU_MC, CPU_PM_CX_AT_XE }, + { 0x00000403, 0x00000403, CPU_MC, CPU_INTEL_XEON }, + { 0x00000404, 0x00000406, CPU_MC, CPU_PM_CX_AT_XE }, + { 0x00000407, 0x00000407, CPU_MC, CPU_INTEL_XEON }, + { 0x00000408, 0x0000040A, CPU_MC, CPU_PM_CX_AT_XE }, + { 0x0000040B, 0x0000040B, CPU_MC, CPU_INTEL_XEON }, + { 0x0000040C, 0x0000040E, CPU_MC, CPU_PM_CX_XE }, + { 0x0000040F, 0x0000040F, CPU_MC, CPU_INTEL_XEON }, + { 0x00000410, 0x00000412, CPU_MC, CPU_PM_CX_AT_XE }, + { 0x00000413, 0x00000417, CPU_MC, CPU_CX_AT_XE }, + { 0x00000480, 0x0000048B, CPU_VMX, CPU_CX_AT_XE }, + + { 0x00000600, 0x00000600, CPU_DEBUG, CPU_PM_CX_AT_XE }, + { 0x00000680, 0x0000068F, CPU_LBRANCH, CPU_INTEL_XEON }, + { 0x000006C0, 0x000006CF, CPU_LBRANCH, CPU_INTEL_XEON }, + + { 0x000107CC, 0x000107D3, CPU_PMC, CPU_INTEL_XEON_MP }, + + { 0xC0000080, 0xC0000080, CPU_FEATURES, CPU_INTEL_XEON }, + { 0xC0000081, 0xC0000082, CPU_CALL, CPU_INTEL_XEON }, + { 0xC0000084, 0xC0000084, CPU_CALL, CPU_INTEL_XEON }, + { 0xC0000100, 0xC0000102, CPU_BASE, CPU_INTEL_XEON }, +}; + +/* AMD Registers Range */ +static struct cpu_debug_range cpu_amd_range[] = { + { 0x00000000, 0x00000001, CPU_MC, CPU_K10_PLUS, }, + { 0x00000010, 0x00000010, CPU_TIME, CPU_K8_PLUS, }, + { 0x0000001B, 0x0000001B, CPU_APIC, CPU_K8_PLUS, }, + { 0x0000002A, 0x0000002A, CPU_POWERON, CPU_K7_PLUS }, + { 0x0000008B, 0x0000008B, CPU_VER, CPU_K8_PLUS }, + { 0x000000FE, 0x000000FE, CPU_MTRR, CPU_K8_PLUS, }, + + { 0x00000174, 0x00000176, CPU_SYSENTER, CPU_K8_PLUS, }, + { 0x00000179, 0x0000017B, CPU_MC, CPU_K8_PLUS, }, + { 0x000001D9, 0x000001D9, CPU_DEBUG, CPU_K8_PLUS, }, + { 0x000001DB, 0x000001DE, CPU_LBRANCH, CPU_K8_PLUS, }, + + { 0x00000200, 0x0000020F, CPU_MTRR, CPU_K8_PLUS, }, + { 0x00000250, 0x00000250, CPU_MTRR, CPU_K8_PLUS, }, + { 0x00000258, 0x00000259, CPU_MTRR, CPU_K8_PLUS, }, + { 0x00000268, 0x0000026F, CPU_MTRR, CPU_K8_PLUS, }, + { 0x00000277, 0x00000277, CPU_PAT, CPU_K8_PLUS, }, + { 0x000002FF, 0x000002FF, CPU_MTRR, CPU_K8_PLUS, }, + + { 0x00000400, 0x00000413, CPU_MC, CPU_K8_PLUS, }, + + { 0xC0000080, 0xC0000080, CPU_FEATURES, CPU_AMD_ALL, }, + { 0xC0000081, 0xC0000084, CPU_CALL, CPU_K8_PLUS, }, + { 0xC0000100, 0xC0000102, CPU_BASE, CPU_K8_PLUS, }, + { 0xC0000103, 0xC0000103, CPU_TIME, CPU_K10_PLUS, }, + + { 0xC0010000, 0xC0010007, CPU_PMC, CPU_K8_PLUS, }, + { 0xC0010010, 0xC0010010, CPU_CONF, CPU_K7_PLUS, }, + { 0xC0010015, 0xC0010015, CPU_CONF, CPU_K7_PLUS, }, + { 0xC0010016, 0xC001001A, CPU_MTRR, CPU_K8_PLUS, }, + { 0xC001001D, 0xC001001D, CPU_MTRR, CPU_K8_PLUS, }, + { 0xC001001F, 0xC001001F, CPU_CONF, CPU_K8_PLUS, }, + { 0xC0010030, 0xC0010035, CPU_BIOS, CPU_K8_PLUS, }, + { 0xC0010044, 0xC0010048, CPU_MC, CPU_K8_PLUS, }, + { 0xC0010050, 0xC0010056, CPU_SMM, CPU_K0F_PLUS, }, + { 0xC0010058, 0xC0010058, CPU_CONF, CPU_K10_PLUS, }, + { 0xC0010060, 0xC0010060, CPU_CACHE, CPU_AMD_11, }, + { 0xC0010061, 0xC0010068, CPU_SMM, CPU_K10_PLUS, }, + { 0xC0010069, 0xC001006B, CPU_SMM, CPU_AMD_11, }, + { 0xC0010070, 0xC0010071, CPU_SMM, CPU_K10_PLUS, }, + { 0xC0010111, 0xC0010113, CPU_SMM, CPU_K8_PLUS, }, + { 0xC0010114, 0xC0010118, CPU_SVM, CPU_K10_PLUS, }, + { 0xC0010140, 0xC0010141, CPU_OSVM, CPU_K10_PLUS, }, + { 0xC0011022, 0xC0011023, CPU_CONF, CPU_K10_PLUS, }, +}; + + +/* Intel */ +static int get_intel_modelflag(unsigned model) +{ + int flag; + + switch (model) { + case 0x0501: + case 0x0502: + case 0x0504: + flag = CPU_INTEL_PENTIUM; + break; + case 0x0601: + case 0x0603: + case 0x0605: + case 0x0607: + case 0x0608: + case 0x060A: + case 0x060B: + flag = CPU_INTEL_P6; + break; + case 0x0609: + case 0x060D: + flag = CPU_INTEL_PENTIUM_M; + break; + case 0x060E: + flag = CPU_INTEL_CORE; + break; + case 0x060F: + case 0x0617: + flag = CPU_INTEL_CORE2; + break; + case 0x061C: + flag = CPU_INTEL_ATOM; + break; + case 0x0F00: + case 0x0F01: + case 0x0F02: + case 0x0F03: + case 0x0F04: + flag = CPU_INTEL_XEON_P4; + break; + case 0x0F06: + flag = CPU_INTEL_XEON_MP; + break; + default: + flag = CPU_NONE; + break; + } + + return flag; +} + +/* AMD */ +static int get_amd_modelflag(unsigned model) +{ + int flag; + + switch (model >> 8) { + case 0x6: + flag = CPU_AMD_K6; + break; + case 0x7: + flag = CPU_AMD_K7; + break; + case 0x8: + flag = CPU_AMD_K8; + break; + case 0xf: + flag = CPU_AMD_0F; + break; + case 0x10: + flag = CPU_AMD_10; + break; + case 0x11: + flag = CPU_AMD_11; + break; + default: + flag = CPU_NONE; + break; + } + + return flag; +} + +static int get_cpu_modelflag(unsigned cpu) +{ + int flag; + + flag = per_cpu(cpu_model, cpu); + + switch (flag >> 16) { + case X86_VENDOR_INTEL: + flag = get_intel_modelflag(flag); + break; + case X86_VENDOR_AMD: + flag = get_amd_modelflag(flag & 0xffff); + break; + default: + flag = CPU_NONE; + break; + } + + return flag; +} + +static int get_cpu_range_count(unsigned cpu) +{ + int index; + + switch (per_cpu(cpu_model, cpu) >> 16) { + case X86_VENDOR_INTEL: + index = ARRAY_SIZE(cpu_intel_range); + break; + case X86_VENDOR_AMD: + index = ARRAY_SIZE(cpu_amd_range); + break; + default: + index = 0; + break; + } + + return index; +} + +static int is_typeflag_valid(unsigned cpu, unsigned flag) +{ + unsigned vendor, modelflag; + int i, index; + + /* Standard Registers should be always valid */ + if (flag >= CPU_TSS) + return 1; + + modelflag = per_cpu(cpu_modelflag, cpu); + vendor = per_cpu(cpu_model, cpu) >> 16; + index = get_cpu_range_count(cpu); + + for (i = 0; i < index; i++) { + switch (vendor) { + case X86_VENDOR_INTEL: + if ((cpu_intel_range[i].model & modelflag) && + (cpu_intel_range[i].flag & flag)) + return 1; + break; + case X86_VENDOR_AMD: + if ((cpu_amd_range[i].model & modelflag) && + (cpu_amd_range[i].flag & flag)) + return 1; + break; + } + } + + /* Invalid */ + return 0; +} + +static unsigned get_cpu_range(unsigned cpu, unsigned *min, unsigned *max, + int index, unsigned flag) +{ + unsigned modelflag; + + modelflag = per_cpu(cpu_modelflag, cpu); + *max = 0; + switch (per_cpu(cpu_model, cpu) >> 16) { + case X86_VENDOR_INTEL: + if ((cpu_intel_range[index].model & modelflag) && + (cpu_intel_range[index].flag & flag)) { + *min = cpu_intel_range[index].min; + *max = cpu_intel_range[index].max; + } + break; + case X86_VENDOR_AMD: + if ((cpu_amd_range[index].model & modelflag) && + (cpu_amd_range[index].flag & flag)) { + *min = cpu_amd_range[index].min; + *max = cpu_amd_range[index].max; + } + break; + } + + return *max; +} + +/* This function can also be called with seq = NULL for printk */ +static void print_cpu_data(struct seq_file *seq, unsigned type, + u32 low, u32 high) +{ + struct cpu_private *priv; + u64 val = high; + + if (seq) { + priv = seq->private; + if (priv->file) { + val = (val << 32) | low; + seq_printf(seq, "0x%llx\n", val); + } else + seq_printf(seq, " %08x: %08x_%08x\n", + type, high, low); + } else + printk(KERN_INFO " %08x: %08x_%08x\n", type, high, low); +} + +/* This function can also be called with seq = NULL for printk */ +static void print_msr(struct seq_file *seq, unsigned cpu, unsigned flag) +{ + unsigned msr, msr_min, msr_max; + struct cpu_private *priv; + u32 low, high; + int i, range; + + if (seq) { + priv = seq->private; + if (priv->file) { + if (!rdmsr_safe_on_cpu(priv->cpu, priv->reg, + &low, &high)) + print_cpu_data(seq, priv->reg, low, high); + return; + } + } + + range = get_cpu_range_count(cpu); + + for (i = 0; i < range; i++) { + if (!get_cpu_range(cpu, &msr_min, &msr_max, i, flag)) + continue; + + for (msr = msr_min; msr <= msr_max; msr++) { + if (rdmsr_safe_on_cpu(cpu, msr, &low, &high)) + continue; + print_cpu_data(seq, msr, low, high); + } + } +} + +static void print_tss(void *arg) +{ + struct pt_regs *regs = task_pt_regs(current); + struct seq_file *seq = arg; + unsigned int seg; + + seq_printf(seq, " RAX\t: %016lx\n", regs->ax); + seq_printf(seq, " RBX\t: %016lx\n", regs->bx); + seq_printf(seq, " RCX\t: %016lx\n", regs->cx); + seq_printf(seq, " RDX\t: %016lx\n", regs->dx); + + seq_printf(seq, " RSI\t: %016lx\n", regs->si); + seq_printf(seq, " RDI\t: %016lx\n", regs->di); + seq_printf(seq, " RBP\t: %016lx\n", regs->bp); + seq_printf(seq, " ESP\t: %016lx\n", regs->sp); + +#ifdef CONFIG_X86_64 + seq_printf(seq, " R08\t: %016lx\n", regs->r8); + seq_printf(seq, " R09\t: %016lx\n", regs->r9); + seq_printf(seq, " R10\t: %016lx\n", regs->r10); + seq_printf(seq, " R11\t: %016lx\n", regs->r11); + seq_printf(seq, " R12\t: %016lx\n", regs->r12); + seq_printf(seq, " R13\t: %016lx\n", regs->r13); + seq_printf(seq, " R14\t: %016lx\n", regs->r14); + seq_printf(seq, " R15\t: %016lx\n", regs->r15); +#endif + + asm("movl %%cs,%0" : "=r" (seg)); + seq_printf(seq, " CS\t: %04x\n", seg); + asm("movl %%ds,%0" : "=r" (seg)); + seq_printf(seq, " DS\t: %04x\n", seg); + seq_printf(seq, " SS\t: %04lx\n", regs->ss & 0xffff); + asm("movl %%es,%0" : "=r" (seg)); + seq_printf(seq, " ES\t: %04x\n", seg); + asm("movl %%fs,%0" : "=r" (seg)); + seq_printf(seq, " FS\t: %04x\n", seg); + asm("movl %%gs,%0" : "=r" (seg)); + seq_printf(seq, " GS\t: %04x\n", seg); + + seq_printf(seq, " EFLAGS\t: %016lx\n", regs->flags); + + seq_printf(seq, " EIP\t: %016lx\n", regs->ip); +} + +static void print_cr(void *arg) +{ + struct seq_file *seq = arg; + + seq_printf(seq, " cr0\t: %016lx\n", read_cr0()); + seq_printf(seq, " cr2\t: %016lx\n", read_cr2()); + seq_printf(seq, " cr3\t: %016lx\n", read_cr3()); + seq_printf(seq, " cr4\t: %016lx\n", read_cr4_safe()); +#ifdef CONFIG_X86_64 + seq_printf(seq, " cr8\t: %016lx\n", read_cr8()); +#endif +} + +static void print_desc_ptr(char *str, struct seq_file *seq, struct desc_ptr dt) +{ + seq_printf(seq, " %s\t: %016llx\n", str, (u64)(dt.address | dt.size)); +} + +static void print_dt(void *seq) +{ + struct desc_ptr dt; + unsigned long ldt; + + /* IDT */ + store_idt((struct desc_ptr *)&dt); + print_desc_ptr("IDT", seq, dt); + + /* GDT */ + store_gdt((struct desc_ptr *)&dt); + print_desc_ptr("GDT", seq, dt); + + /* LDT */ + store_ldt(ldt); + seq_printf(seq, " LDT\t: %016lx\n", ldt); + + /* TR */ + store_tr(ldt); + seq_printf(seq, " TR\t: %016lx\n", ldt); +} + +static void print_dr(void *arg) +{ + struct seq_file *seq = arg; + unsigned long dr; + int i; + + for (i = 0; i < 8; i++) { + /* Ignore db4, db5 */ + if ((i == 4) || (i == 5)) + continue; + get_debugreg(dr, i); + seq_printf(seq, " dr%d\t: %016lx\n", i, dr); + } + + seq_printf(seq, "\n MSR\t:\n"); +} + +static void print_apic(void *arg) +{ + struct seq_file *seq = arg; + +#ifdef CONFIG_X86_LOCAL_APIC + seq_printf(seq, " LAPIC\t:\n"); + seq_printf(seq, " ID\t\t: %08x\n", apic_read(APIC_ID) >> 24); + seq_printf(seq, " LVR\t\t: %08x\n", apic_read(APIC_LVR)); + seq_printf(seq, " TASKPRI\t: %08x\n", apic_read(APIC_TASKPRI)); + seq_printf(seq, " ARBPRI\t\t: %08x\n", apic_read(APIC_ARBPRI)); + seq_printf(seq, " PROCPRI\t: %08x\n", apic_read(APIC_PROCPRI)); + seq_printf(seq, " LDR\t\t: %08x\n", apic_read(APIC_LDR)); + seq_printf(seq, " DFR\t\t: %08x\n", apic_read(APIC_DFR)); + seq_printf(seq, " SPIV\t\t: %08x\n", apic_read(APIC_SPIV)); + seq_printf(seq, " ISR\t\t: %08x\n", apic_read(APIC_ISR)); + seq_printf(seq, " ESR\t\t: %08x\n", apic_read(APIC_ESR)); + seq_printf(seq, " ICR\t\t: %08x\n", apic_read(APIC_ICR)); + seq_printf(seq, " ICR2\t\t: %08x\n", apic_read(APIC_ICR2)); + seq_printf(seq, " LVTT\t\t: %08x\n", apic_read(APIC_LVTT)); + seq_printf(seq, " LVTTHMR\t: %08x\n", apic_read(APIC_LVTTHMR)); + seq_printf(seq, " LVTPC\t\t: %08x\n", apic_read(APIC_LVTPC)); + seq_printf(seq, " LVT0\t\t: %08x\n", apic_read(APIC_LVT0)); + seq_printf(seq, " LVT1\t\t: %08x\n", apic_read(APIC_LVT1)); + seq_printf(seq, " LVTERR\t\t: %08x\n", apic_read(APIC_LVTERR)); + seq_printf(seq, " TMICT\t\t: %08x\n", apic_read(APIC_TMICT)); + seq_printf(seq, " TMCCT\t\t: %08x\n", apic_read(APIC_TMCCT)); + seq_printf(seq, " TDCR\t\t: %08x\n", apic_read(APIC_TDCR)); +#endif /* CONFIG_X86_LOCAL_APIC */ + + seq_printf(seq, "\n MSR\t:\n"); +} + +static int cpu_seq_show(struct seq_file *seq, void *v) +{ + struct cpu_private *priv = seq->private; + + if (priv == NULL) + return -EINVAL; + + switch (cpu_base[priv->type].flag) { + case CPU_TSS: + smp_call_function_single(priv->cpu, print_tss, seq, 1); + break; + case CPU_CR: + smp_call_function_single(priv->cpu, print_cr, seq, 1); + break; + case CPU_DT: + smp_call_function_single(priv->cpu, print_dt, seq, 1); + break; + case CPU_DEBUG: + if (priv->file == CPU_INDEX_BIT) + smp_call_function_single(priv->cpu, print_dr, seq, 1); + print_msr(seq, priv->cpu, cpu_base[priv->type].flag); + break; + case CPU_APIC: + if (priv->file == CPU_INDEX_BIT) + smp_call_function_single(priv->cpu, print_apic, seq, 1); + print_msr(seq, priv->cpu, cpu_base[priv->type].flag); + break; + + default: + print_msr(seq, priv->cpu, cpu_base[priv->type].flag); + break; + } + seq_printf(seq, "\n"); + + return 0; +} + +static void *cpu_seq_start(struct seq_file *seq, loff_t *pos) +{ + if (*pos == 0) /* One time is enough ;-) */ + return seq; + + return NULL; +} + +static void *cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + (*pos)++; + + return cpu_seq_start(seq, pos); +} + +static void cpu_seq_stop(struct seq_file *seq, void *v) +{ +} + +static const struct seq_operations cpu_seq_ops = { + .start = cpu_seq_start, + .next = cpu_seq_next, + .stop = cpu_seq_stop, + .show = cpu_seq_show, +}; + +static int cpu_seq_open(struct inode *inode, struct file *file) +{ + struct cpu_private *priv = inode->i_private; + struct seq_file *seq; + int err; + + err = seq_open(file, &cpu_seq_ops); + if (!err) { + seq = file->private_data; + seq->private = priv; + } + + return err; +} + +static int write_msr(struct cpu_private *priv, u64 val) +{ + u32 low, high; + + high = (val >> 32) & 0xffffffff; + low = val & 0xffffffff; + + if (!wrmsr_safe_on_cpu(priv->cpu, priv->reg, low, high)) + return 0; + + return -EPERM; +} + +static int write_cpu_register(struct cpu_private *priv, const char *buf) +{ + int ret = -EPERM; + u64 val; + + ret = strict_strtoull(buf, 0, &val); + if (ret < 0) + return ret; + + /* Supporting only MSRs */ + if (priv->type < CPU_TSS_BIT) + return write_msr(priv, val); + + return ret; +} + +static ssize_t cpu_write(struct file *file, const char __user *ubuf, + size_t count, loff_t *off) +{ + struct seq_file *seq = file->private_data; + struct cpu_private *priv = seq->private; + char buf[19]; + + if ((priv == NULL) || (count >= sizeof(buf))) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, count)) + return -EFAULT; + + buf[count] = 0; + + if ((cpu_base[priv->type].write) && (cpu_file[priv->file].write)) + if (!write_cpu_register(priv, buf)) + return count; + + return -EACCES; +} + +static const struct file_operations cpu_fops = { + .owner = THIS_MODULE, + .open = cpu_seq_open, + .read = seq_read, + .write = cpu_write, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int cpu_create_file(unsigned cpu, unsigned type, unsigned reg, + unsigned file, struct dentry *dentry) +{ + struct cpu_private *priv = NULL; + + /* Already intialized */ + if (file == CPU_INDEX_BIT) + if (per_cpu(cpu_arr[type].init, cpu)) + return 0; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (priv == NULL) + return -ENOMEM; + + priv->cpu = cpu; + priv->type = type; + priv->reg = reg; + priv->file = file; + mutex_lock(&cpu_debug_lock); + per_cpu(priv_arr[type], cpu) = priv; + per_cpu(cpu_priv_count, cpu)++; + mutex_unlock(&cpu_debug_lock); + + if (file) + debugfs_create_file(cpu_file[file].name, S_IRUGO, + dentry, (void *)priv, &cpu_fops); + else { + debugfs_create_file(cpu_base[type].name, S_IRUGO, + per_cpu(cpu_arr[type].dentry, cpu), + (void *)priv, &cpu_fops); + mutex_lock(&cpu_debug_lock); + per_cpu(cpu_arr[type].init, cpu) = 1; + mutex_unlock(&cpu_debug_lock); + } + + return 0; +} + +static int cpu_init_regfiles(unsigned cpu, unsigned int type, unsigned reg, + struct dentry *dentry) +{ + unsigned file; + int err = 0; + + for (file = 0; file < ARRAY_SIZE(cpu_file); file++) { + err = cpu_create_file(cpu, type, reg, file, dentry); + if (err) + return err; + } + + return err; +} + +static int cpu_init_msr(unsigned cpu, unsigned type, struct dentry *dentry) +{ + struct dentry *cpu_dentry = NULL; + unsigned reg, reg_min, reg_max; + int i, range, err = 0; + char reg_dir[12]; + u32 low, high; + + range = get_cpu_range_count(cpu); + + for (i = 0; i < range; i++) { + if (!get_cpu_range(cpu, ®_min, ®_max, i, + cpu_base[type].flag)) + continue; + + for (reg = reg_min; reg <= reg_max; reg++) { + if (rdmsr_safe_on_cpu(cpu, reg, &low, &high)) + continue; + + sprintf(reg_dir, "0x%x", reg); + cpu_dentry = debugfs_create_dir(reg_dir, dentry); + err = cpu_init_regfiles(cpu, type, reg, cpu_dentry); + if (err) + return err; + } + } + + return err; +} + +static int cpu_init_allreg(unsigned cpu, struct dentry *dentry) +{ + struct dentry *cpu_dentry = NULL; + unsigned type; + int err = 0; + + for (type = 0; type < ARRAY_SIZE(cpu_base) - 1; type++) { + if (!is_typeflag_valid(cpu, cpu_base[type].flag)) + continue; + cpu_dentry = debugfs_create_dir(cpu_base[type].name, dentry); + per_cpu(cpu_arr[type].dentry, cpu) = cpu_dentry; + + if (type < CPU_TSS_BIT) + err = cpu_init_msr(cpu, type, cpu_dentry); + else + err = cpu_create_file(cpu, type, 0, CPU_INDEX_BIT, + cpu_dentry); + if (err) + return err; + } + + return err; +} + +static int cpu_init_cpu(void) +{ + struct dentry *cpu_dentry = NULL; + struct cpuinfo_x86 *cpui; + char cpu_dir[12]; + unsigned cpu; + int err = 0; + + for (cpu = 0; cpu < nr_cpu_ids; cpu++) { + cpui = &cpu_data(cpu); + if (!cpu_has(cpui, X86_FEATURE_MSR)) + continue; + per_cpu(cpu_model, cpu) = ((cpui->x86_vendor << 16) | + (cpui->x86 << 8) | + (cpui->x86_model)); + per_cpu(cpu_modelflag, cpu) = get_cpu_modelflag(cpu); + + sprintf(cpu_dir, "cpu%d", cpu); + cpu_dentry = debugfs_create_dir(cpu_dir, cpu_debugfs_dir); + err = cpu_init_allreg(cpu, cpu_dentry); + + pr_info("cpu%d(%d) debug files %d\n", + cpu, nr_cpu_ids, per_cpu(cpu_priv_count, cpu)); + if (per_cpu(cpu_priv_count, cpu) > MAX_CPU_FILES) { + pr_err("Register files count %d exceeds limit %d\n", + per_cpu(cpu_priv_count, cpu), MAX_CPU_FILES); + per_cpu(cpu_priv_count, cpu) = MAX_CPU_FILES; + err = -ENFILE; + } + if (err) + return err; + } + + return err; +} + +static int __init cpu_debug_init(void) +{ + cpu_debugfs_dir = debugfs_create_dir("cpu", arch_debugfs_dir); + + return cpu_init_cpu(); +} + +static void __exit cpu_debug_exit(void) +{ + int i, cpu; + + if (cpu_debugfs_dir) + debugfs_remove_recursive(cpu_debugfs_dir); + + for (cpu = 0; cpu < nr_cpu_ids; cpu++) + for (i = 0; i < per_cpu(cpu_priv_count, cpu); i++) + kfree(per_cpu(priv_arr[i], cpu)); +} + +module_init(cpu_debug_init); +module_exit(cpu_debug_exit); + +MODULE_AUTHOR("Jaswinder Singh Rajput"); +MODULE_DESCRIPTION("CPU Debug module"); +MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig index 65792c2..52c8398 100644 --- a/arch/x86/kernel/cpu/cpufreq/Kconfig +++ b/arch/x86/kernel/cpu/cpufreq/Kconfig @@ -87,30 +87,15 @@ config X86_POWERNOW_K7_ACPI config X86_POWERNOW_K8 tristate "AMD Opteron/Athlon64 PowerNow!" select CPU_FREQ_TABLE + depends on ACPI && ACPI_PROCESSOR help - This adds the CPUFreq driver for mobile AMD Opteron/Athlon64 processors. + This adds the CPUFreq driver for K8/K10 Opteron/Athlon64 processors. To compile this driver as a module, choose M here: the module will be called powernow-k8. For details, take a look at <file:Documentation/cpu-freq/>. - If in doubt, say N. - -config X86_POWERNOW_K8_ACPI - bool - prompt "ACPI Support" if X86_32 - depends on ACPI && X86_POWERNOW_K8 && ACPI_PROCESSOR - depends on !(X86_POWERNOW_K8 = y && ACPI_PROCESSOR = m) - default y - help - This provides access to the K8s Processor Performance States via ACPI. - This driver is probably required for CPUFreq to work with multi-socket and - SMP systems. It is not required on at least some single-socket yet - multi-core systems, even if SMP is enabled. - - It is safe to say Y here. - config X86_GX_SUSPMOD tristate "Cyrix MediaGX/NatSemi Geode Suspend Modulation" depends on X86_32 && PCI diff --git a/arch/x86/kernel/cpu/cpufreq/Makefile b/arch/x86/kernel/cpu/cpufreq/Makefile index 560f776..509296d 100644 --- a/arch/x86/kernel/cpu/cpufreq/Makefile +++ b/arch/x86/kernel/cpu/cpufreq/Makefile @@ -1,6 +1,11 @@ +# Link order matters. K8 is preferred to ACPI because of firmware bugs in early +# K8 systems. ACPI is preferred to all other hardware-specific drivers. +# speedstep-* is preferred over p4-clockmod. + +obj-$(CONFIG_X86_POWERNOW_K8) += powernow-k8.o +obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o obj-$(CONFIG_X86_POWERNOW_K6) += powernow-k6.o obj-$(CONFIG_X86_POWERNOW_K7) += powernow-k7.o -obj-$(CONFIG_X86_POWERNOW_K8) += powernow-k8.o obj-$(CONFIG_X86_LONGHAUL) += longhaul.o obj-$(CONFIG_X86_E_POWERSAVER) += e_powersaver.o obj-$(CONFIG_ELAN_CPUFREQ) += elanfreq.o @@ -10,7 +15,6 @@ obj-$(CONFIG_X86_GX_SUSPMOD) += gx-suspmod.o obj-$(CONFIG_X86_SPEEDSTEP_ICH) += speedstep-ich.o obj-$(CONFIG_X86_SPEEDSTEP_LIB) += speedstep-lib.o obj-$(CONFIG_X86_SPEEDSTEP_SMI) += speedstep-smi.o -obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO) += speedstep-centrino.o obj-$(CONFIG_X86_P4_CLOCKMOD) += p4-clockmod.o obj-$(CONFIG_X86_CPUFREQ_NFORCE2) += cpufreq-nforce2.o diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 4b1c319..19f6b9d 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -1,5 +1,5 @@ /* - * acpi-cpufreq.c - ACPI Processor P-States Driver ($Revision: 1.4 $) + * acpi-cpufreq.c - ACPI Processor P-States Driver * * Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com> * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> @@ -33,19 +33,21 @@ #include <linux/cpufreq.h> #include <linux/compiler.h> #include <linux/dmi.h> -#include <linux/ftrace.h> +#include <trace/power.h> #include <linux/acpi.h> +#include <linux/io.h> +#include <linux/delay.h> +#include <linux/uaccess.h> + #include <acpi/processor.h> -#include <asm/io.h> #include <asm/msr.h> #include <asm/processor.h> #include <asm/cpufeature.h> -#include <asm/delay.h> -#include <asm/uaccess.h> -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "acpi-cpufreq", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "acpi-cpufreq", msg) MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski"); MODULE_DESCRIPTION("ACPI Processor P-States Driver"); @@ -70,6 +72,8 @@ struct acpi_cpufreq_data { static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data); +DEFINE_TRACE(power_mark); + /* acpi_perf_data is a pointer to percpu data. */ static struct acpi_processor_performance *acpi_perf_data; @@ -95,7 +99,7 @@ static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data) perf = data->acpi_data; - for (i=0; i<perf->state_count; i++) { + for (i = 0; i < perf->state_count; i++) { if (value == perf->states[i].status) return data->freq_table[i].frequency; } @@ -110,7 +114,7 @@ static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data) msr &= INTEL_MSR_RANGE; perf = data->acpi_data; - for (i=0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) { + for (i = 0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) { if (msr == perf->states[data->freq_table[i].index].status) return data->freq_table[i].frequency; } @@ -138,15 +142,13 @@ struct io_addr { u8 bit_width; }; -typedef union { - struct msr_addr msr; - struct io_addr io; -} drv_addr_union; - struct drv_cmd { unsigned int type; const struct cpumask *mask; - drv_addr_union addr; + union { + struct msr_addr msr; + struct io_addr io; + } addr; u32 val; }; @@ -369,7 +371,7 @@ static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq, unsigned int cur_freq; unsigned int i; - for (i=0; i<100; i++) { + for (i = 0; i < 100; i++) { cur_freq = extract_freq(get_cur_val(mask), data); if (cur_freq == freq) return 1; @@ -494,7 +496,7 @@ acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu) unsigned long freq; unsigned long freqn = perf->states[0].core_frequency * 1000; - for (i=0; i<(perf->state_count-1); i++) { + for (i = 0; i < (perf->state_count-1); i++) { freq = freqn; freqn = perf->states[i+1].core_frequency * 1000; if ((2 * cpu_khz) > (freqn + freq)) { @@ -601,7 +603,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) if (!data) return -ENOMEM; - data->acpi_data = percpu_ptr(acpi_perf_data, cpu); + data->acpi_data = per_cpu_ptr(acpi_perf_data, cpu); per_cpu(drv_data, cpu) = data; if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) @@ -673,17 +675,29 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) /* detect transition latency */ policy->cpuinfo.transition_latency = 0; - for (i=0; i<perf->state_count; i++) { + for (i = 0; i < perf->state_count; i++) { if ((perf->states[i].transition_latency * 1000) > policy->cpuinfo.transition_latency) policy->cpuinfo.transition_latency = perf->states[i].transition_latency * 1000; } + /* Check for high latency (>20uS) from buggy BIOSes, like on T42 */ + if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE && + policy->cpuinfo.transition_latency > 20 * 1000) { + static int print_once; + policy->cpuinfo.transition_latency = 20 * 1000; + if (!print_once) { + print_once = 1; + printk(KERN_INFO "Capping off P-state tranision latency" + " at 20 uS\n"); + } + } + data->max_freq = perf->states[0].core_frequency * 1000; /* table init */ - for (i=0; i<perf->state_count; i++) { - if (i>0 && perf->states[i].core_frequency >= + for (i = 0; i < perf->state_count; i++) { + if (i > 0 && perf->states[i].core_frequency >= data->freq_table[valid_states-1].frequency / 1000) continue; diff --git a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c index 965ea52..733093d 100644 --- a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c +++ b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c @@ -32,7 +32,7 @@ * nforce2_chipset: * FSB is changed using the chipset */ -static struct pci_dev *nforce2_chipset_dev; +static struct pci_dev *nforce2_dev; /* fid: * multiplier * 10 @@ -56,7 +56,9 @@ MODULE_PARM_DESC(fid, "CPU multiplier to use (11.5 = 115)"); MODULE_PARM_DESC(min_fsb, "Minimum FSB to use, if not defined: current FSB - 50"); -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "cpufreq-nforce2", msg) +#define PFX "cpufreq-nforce2: " +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "cpufreq-nforce2", msg) /** * nforce2_calc_fsb - calculate FSB @@ -118,11 +120,11 @@ static void nforce2_write_pll(int pll) int temp; /* Set the pll addr. to 0x00 */ - pci_write_config_dword(nforce2_chipset_dev, NFORCE2_PLLADR, 0); + pci_write_config_dword(nforce2_dev, NFORCE2_PLLADR, 0); /* Now write the value in all 64 registers */ for (temp = 0; temp <= 0x3f; temp++) - pci_write_config_dword(nforce2_chipset_dev, NFORCE2_PLLREG, pll); + pci_write_config_dword(nforce2_dev, NFORCE2_PLLREG, pll); return; } @@ -139,8 +141,8 @@ static unsigned int nforce2_fsb_read(int bootfsb) u32 fsb, temp = 0; /* Get chipset boot FSB from subdevice 5 (FSB at boot-time) */ - nforce2_sub5 = pci_get_subsys(PCI_VENDOR_ID_NVIDIA, - 0x01EF, PCI_ANY_ID, PCI_ANY_ID, NULL); + nforce2_sub5 = pci_get_subsys(PCI_VENDOR_ID_NVIDIA, 0x01EF, + PCI_ANY_ID, PCI_ANY_ID, NULL); if (!nforce2_sub5) return 0; @@ -148,13 +150,13 @@ static unsigned int nforce2_fsb_read(int bootfsb) fsb /= 1000000; /* Check if PLL register is already set */ - pci_read_config_byte(nforce2_chipset_dev, NFORCE2_PLLENABLE, (u8 *)&temp); + pci_read_config_byte(nforce2_dev, NFORCE2_PLLENABLE, (u8 *)&temp); if (bootfsb || !temp) return fsb; /* Use PLL register FSB value */ - pci_read_config_dword(nforce2_chipset_dev, NFORCE2_PLLREG, &temp); + pci_read_config_dword(nforce2_dev, NFORCE2_PLLREG, &temp); fsb = nforce2_calc_fsb(temp); return fsb; @@ -174,18 +176,18 @@ static int nforce2_set_fsb(unsigned int fsb) int pll = 0; if ((fsb > max_fsb) || (fsb < NFORCE2_MIN_FSB)) { - printk(KERN_ERR "cpufreq: FSB %d is out of range!\n", fsb); + printk(KERN_ERR PFX "FSB %d is out of range!\n", fsb); return -EINVAL; } tfsb = nforce2_fsb_read(0); if (!tfsb) { - printk(KERN_ERR "cpufreq: Error while reading the FSB\n"); + printk(KERN_ERR PFX "Error while reading the FSB\n"); return -EINVAL; } /* First write? Then set actual value */ - pci_read_config_byte(nforce2_chipset_dev, NFORCE2_PLLENABLE, (u8 *)&temp); + pci_read_config_byte(nforce2_dev, NFORCE2_PLLENABLE, (u8 *)&temp); if (!temp) { pll = nforce2_calc_pll(tfsb); @@ -197,7 +199,7 @@ static int nforce2_set_fsb(unsigned int fsb) /* Enable write access */ temp = 0x01; - pci_write_config_byte(nforce2_chipset_dev, NFORCE2_PLLENABLE, (u8)temp); + pci_write_config_byte(nforce2_dev, NFORCE2_PLLENABLE, (u8)temp); diff = tfsb - fsb; @@ -222,7 +224,7 @@ static int nforce2_set_fsb(unsigned int fsb) } temp = 0x40; - pci_write_config_byte(nforce2_chipset_dev, NFORCE2_PLLADR, (u8)temp); + pci_write_config_byte(nforce2_dev, NFORCE2_PLLADR, (u8)temp); return 0; } @@ -244,7 +246,8 @@ static unsigned int nforce2_get(unsigned int cpu) * nforce2_target - set a new CPUFreq policy * @policy: new policy * @target_freq: the target frequency - * @relation: how that frequency relates to achieved frequency (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H) + * @relation: how that frequency relates to achieved frequency + * (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H) * * Sets a new CPUFreq policy. */ @@ -276,7 +279,7 @@ static int nforce2_target(struct cpufreq_policy *policy, /* local_irq_save(flags); */ if (nforce2_set_fsb(target_fsb) < 0) - printk(KERN_ERR "cpufreq: Changing FSB to %d failed\n", + printk(KERN_ERR PFX "Changing FSB to %d failed\n", target_fsb); else dprintk("Changed FSB successfully to %d\n", @@ -327,8 +330,8 @@ static int nforce2_cpu_init(struct cpufreq_policy *policy) /* FIX: Get FID from CPU */ if (!fid) { if (!cpu_khz) { - printk(KERN_WARNING - "cpufreq: cpu_khz not set, can't calculate multiplier!\n"); + printk(KERN_WARNING PFX + "cpu_khz not set, can't calculate multiplier!\n"); return -ENODEV; } @@ -343,7 +346,7 @@ static int nforce2_cpu_init(struct cpufreq_policy *policy) } } - printk(KERN_INFO "cpufreq: FSB currently at %i MHz, FID %d.%d\n", fsb, + printk(KERN_INFO PFX "FSB currently at %i MHz, FID %d.%d\n", fsb, fid / 10, fid % 10); /* Set maximum FSB to FSB at boot time */ @@ -392,17 +395,18 @@ static struct cpufreq_driver nforce2_driver = { */ static unsigned int nforce2_detect_chipset(void) { - nforce2_chipset_dev = pci_get_subsys(PCI_VENDOR_ID_NVIDIA, + nforce2_dev = pci_get_subsys(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE2, PCI_ANY_ID, PCI_ANY_ID, NULL); - if (nforce2_chipset_dev == NULL) + if (nforce2_dev == NULL) return -ENODEV; - printk(KERN_INFO "cpufreq: Detected nForce2 chipset revision %X\n", - nforce2_chipset_dev->revision); - printk(KERN_INFO - "cpufreq: FSB changing is maybe unstable and can lead to crashes and data loss.\n"); + printk(KERN_INFO PFX "Detected nForce2 chipset revision %X\n", + nforce2_dev->revision); + printk(KERN_INFO PFX + "FSB changing is maybe unstable and can lead to " + "crashes and data loss.\n"); return 0; } @@ -420,7 +424,7 @@ static int __init nforce2_init(void) /* detect chipset */ if (nforce2_detect_chipset()) { - printk(KERN_ERR "cpufreq: No nForce2 chipset.\n"); + printk(KERN_INFO PFX "No nForce2 chipset.\n"); return -ENODEV; } diff --git a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c index 41ab3f0..35a257d 100644 --- a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c +++ b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c @@ -12,12 +12,12 @@ #include <linux/cpufreq.h> #include <linux/ioport.h> #include <linux/slab.h> +#include <linux/timex.h> +#include <linux/io.h> +#include <linux/delay.h> #include <asm/msr.h> #include <asm/tsc.h> -#include <asm/timex.h> -#include <asm/io.h> -#include <asm/delay.h> #define EPS_BRAND_C7M 0 #define EPS_BRAND_C7 1 @@ -184,7 +184,7 @@ static int eps_cpu_init(struct cpufreq_policy *policy) break; } - switch(brand) { + switch (brand) { case EPS_BRAND_C7M: printk(KERN_CONT "C7-M\n"); break; @@ -218,17 +218,20 @@ static int eps_cpu_init(struct cpufreq_policy *policy) /* Print voltage and multiplier */ rdmsr(MSR_IA32_PERF_STATUS, lo, hi); current_voltage = lo & 0xff; - printk(KERN_INFO "eps: Current voltage = %dmV\n", current_voltage * 16 + 700); + printk(KERN_INFO "eps: Current voltage = %dmV\n", + current_voltage * 16 + 700); current_multiplier = (lo >> 8) & 0xff; printk(KERN_INFO "eps: Current multiplier = %d\n", current_multiplier); /* Print limits */ max_voltage = hi & 0xff; - printk(KERN_INFO "eps: Highest voltage = %dmV\n", max_voltage * 16 + 700); + printk(KERN_INFO "eps: Highest voltage = %dmV\n", + max_voltage * 16 + 700); max_multiplier = (hi >> 8) & 0xff; printk(KERN_INFO "eps: Highest multiplier = %d\n", max_multiplier); min_voltage = (hi >> 16) & 0xff; - printk(KERN_INFO "eps: Lowest voltage = %dmV\n", min_voltage * 16 + 700); + printk(KERN_INFO "eps: Lowest voltage = %dmV\n", + min_voltage * 16 + 700); min_multiplier = (hi >> 24) & 0xff; printk(KERN_INFO "eps: Lowest multiplier = %d\n", min_multiplier); @@ -318,7 +321,7 @@ static int eps_cpu_exit(struct cpufreq_policy *policy) return 0; } -static struct freq_attr* eps_attr[] = { +static struct freq_attr *eps_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -356,7 +359,7 @@ static void __exit eps_exit(void) cpufreq_unregister_driver(&eps_driver); } -MODULE_AUTHOR("Rafa³ Bilski <rafalbilski@interia.pl>"); +MODULE_AUTHOR("Rafal Bilski <rafalbilski@interia.pl>"); MODULE_DESCRIPTION("Enhanced PowerSaver driver for VIA C7 CPU's."); MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/cpufreq/elanfreq.c b/arch/x86/kernel/cpu/cpufreq/elanfreq.c index fe613c9..006b278 100644 --- a/arch/x86/kernel/cpu/cpufreq/elanfreq.c +++ b/arch/x86/kernel/cpu/cpufreq/elanfreq.c @@ -184,7 +184,8 @@ static int elanfreq_target(struct cpufreq_policy *policy, { unsigned int newstate = 0; - if (cpufreq_frequency_table_target(policy, &elanfreq_table[0], target_freq, relation, &newstate)) + if (cpufreq_frequency_table_target(policy, &elanfreq_table[0], + target_freq, relation, &newstate)) return -EINVAL; elanfreq_set_cpu_state(newstate); @@ -301,7 +302,8 @@ static void __exit elanfreq_exit(void) module_param(max_freq, int, 0444); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Robert Schwebel <r.schwebel@pengutronix.de>, Sven Geggus <sven@geggus.net>"); +MODULE_AUTHOR("Robert Schwebel <r.schwebel@pengutronix.de>, " + "Sven Geggus <sven@geggus.net>"); MODULE_DESCRIPTION("cpufreq driver for AMD's Elan CPUs"); module_init(elanfreq_init); diff --git a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c index 9d9eae8..ac27ec2 100644 --- a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c +++ b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c @@ -79,8 +79,9 @@ #include <linux/smp.h> #include <linux/cpufreq.h> #include <linux/pci.h> +#include <linux/errno.h> + #include <asm/processor-cyrix.h> -#include <asm/errno.h> /* PCI config registers, all at F0 */ #define PCI_PMER1 0x80 /* power management enable register 1 */ @@ -122,8 +123,8 @@ static struct gxfreq_params *gx_params; static int stock_freq; /* PCI bus clock - defaults to 30.000 if cpu_khz is not available */ -static int pci_busclk = 0; -module_param (pci_busclk, int, 0444); +static int pci_busclk; +module_param(pci_busclk, int, 0444); /* maximum duration for which the cpu may be suspended * (32us * MAX_DURATION). If no parameter is given, this defaults @@ -132,7 +133,7 @@ module_param (pci_busclk, int, 0444); * is suspended -- processing power is just 0.39% of what it used to be, * though. 781.25 kHz(!) for a 200 MHz processor -- wow. */ static int max_duration = 255; -module_param (max_duration, int, 0444); +module_param(max_duration, int, 0444); /* For the default policy, we want at least some processing power * - let's say 5%. (min = maxfreq / POLICY_MIN_DIV) @@ -140,7 +141,8 @@ module_param (max_duration, int, 0444); #define POLICY_MIN_DIV 20 -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "gx-suspmod", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "gx-suspmod", msg) /** * we can detect a core multipiler from dir0_lsb @@ -166,12 +168,20 @@ static int gx_freq_mult[16] = { * Low Level chipset interface * ****************************************************************/ static struct pci_device_id gx_chipset_tbl[] __initdata = { - { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY, PCI_ANY_ID, PCI_ANY_ID }, - { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5520, PCI_ANY_ID, PCI_ANY_ID }, - { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5510, PCI_ANY_ID, PCI_ANY_ID }, + { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY, + PCI_ANY_ID, PCI_ANY_ID }, + { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5520, + PCI_ANY_ID, PCI_ANY_ID }, + { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5510, + PCI_ANY_ID, PCI_ANY_ID }, { 0, }, }; +static void gx_write_byte(int reg, int value) +{ + pci_write_config_byte(gx_params->cs55x0, reg, value); +} + /** * gx_detect_chipset: * @@ -200,7 +210,8 @@ static __init struct pci_dev *gx_detect_chipset(void) /** * gx_get_cpuspeed: * - * Finds out at which efficient frequency the Cyrix MediaGX/NatSemi Geode CPU runs. + * Finds out at which efficient frequency the Cyrix MediaGX/NatSemi + * Geode CPU runs. */ static unsigned int gx_get_cpuspeed(unsigned int cpu) { @@ -217,17 +228,18 @@ static unsigned int gx_get_cpuspeed(unsigned int cpu) * **/ -static unsigned int gx_validate_speed(unsigned int khz, u8 *on_duration, u8 *off_duration) +static unsigned int gx_validate_speed(unsigned int khz, u8 *on_duration, + u8 *off_duration) { unsigned int i; u8 tmp_on, tmp_off; int old_tmp_freq = stock_freq; int tmp_freq; - *off_duration=1; - *on_duration=0; + *off_duration = 1; + *on_duration = 0; - for (i=max_duration; i>0; i--) { + for (i = max_duration; i > 0; i--) { tmp_off = ((khz * i) / stock_freq) & 0xff; tmp_on = i - tmp_off; tmp_freq = (stock_freq * tmp_off) / i; @@ -259,26 +271,34 @@ static void gx_set_cpuspeed(unsigned int khz) freqs.cpu = 0; freqs.old = gx_get_cpuspeed(0); - new_khz = gx_validate_speed(khz, &gx_params->on_duration, &gx_params->off_duration); + new_khz = gx_validate_speed(khz, &gx_params->on_duration, + &gx_params->off_duration); freqs.new = new_khz; cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); local_irq_save(flags); - if (new_khz != stock_freq) { /* if new khz == 100% of CPU speed, it is special case */ + + + if (new_khz != stock_freq) { + /* if new khz == 100% of CPU speed, it is special case */ switch (gx_params->cs55x0->device) { case PCI_DEVICE_ID_CYRIX_5530_LEGACY: pmer1 = gx_params->pci_pmer1 | IRQ_SPDUP | VID_SPDUP; /* FIXME: need to test other values -- Zwane,Miura */ - pci_write_config_byte(gx_params->cs55x0, PCI_IRQTC, 4); /* typical 2 to 4ms */ - pci_write_config_byte(gx_params->cs55x0, PCI_VIDTC, 100);/* typical 50 to 100ms */ - pci_write_config_byte(gx_params->cs55x0, PCI_PMER1, pmer1); - - if (gx_params->cs55x0->revision < 0x10) { /* CS5530(rev 1.2, 1.3) */ - suscfg = gx_params->pci_suscfg | SUSMOD; - } else { /* CS5530A,B.. */ - suscfg = gx_params->pci_suscfg | SUSMOD | PWRSVE; + /* typical 2 to 4ms */ + gx_write_byte(PCI_IRQTC, 4); + /* typical 50 to 100ms */ + gx_write_byte(PCI_VIDTC, 100); + gx_write_byte(PCI_PMER1, pmer1); + + if (gx_params->cs55x0->revision < 0x10) { + /* CS5530(rev 1.2, 1.3) */ + suscfg = gx_params->pci_suscfg|SUSMOD; + } else { + /* CS5530A,B.. */ + suscfg = gx_params->pci_suscfg|SUSMOD|PWRSVE; } break; case PCI_DEVICE_ID_CYRIX_5520: @@ -294,13 +314,13 @@ static void gx_set_cpuspeed(unsigned int khz) suscfg = gx_params->pci_suscfg & ~(SUSMOD); gx_params->off_duration = 0; gx_params->on_duration = 0; - dprintk("suspend modulation disabled: cpu runs 100 percent speed.\n"); + dprintk("suspend modulation disabled: cpu runs 100%% speed.\n"); } - pci_write_config_byte(gx_params->cs55x0, PCI_MODOFF, gx_params->off_duration); - pci_write_config_byte(gx_params->cs55x0, PCI_MODON, gx_params->on_duration); + gx_write_byte(PCI_MODOFF, gx_params->off_duration); + gx_write_byte(PCI_MODON, gx_params->on_duration); - pci_write_config_byte(gx_params->cs55x0, PCI_SUSCFG, suscfg); + gx_write_byte(PCI_SUSCFG, suscfg); pci_read_config_byte(gx_params->cs55x0, PCI_SUSCFG, &suscfg); local_irq_restore(flags); @@ -334,7 +354,8 @@ static int cpufreq_gx_verify(struct cpufreq_policy *policy) return -EINVAL; policy->cpu = 0; - cpufreq_verify_within_limits(policy, (stock_freq / max_duration), stock_freq); + cpufreq_verify_within_limits(policy, (stock_freq / max_duration), + stock_freq); /* it needs to be assured that at least one supported frequency is * within policy->min and policy->max. If it is not, policy->max @@ -354,7 +375,8 @@ static int cpufreq_gx_verify(struct cpufreq_policy *policy) policy->max = tmp_freq; if (policy->max < policy->min) policy->max = policy->min; - cpufreq_verify_within_limits(policy, (stock_freq / max_duration), stock_freq); + cpufreq_verify_within_limits(policy, (stock_freq / max_duration), + stock_freq); return 0; } @@ -398,18 +420,18 @@ static int cpufreq_gx_cpu_init(struct cpufreq_policy *policy) return -ENODEV; /* determine maximum frequency */ - if (pci_busclk) { + if (pci_busclk) maxfreq = pci_busclk * gx_freq_mult[getCx86(CX86_DIR1) & 0x0f]; - } else if (cpu_khz) { + else if (cpu_khz) maxfreq = cpu_khz; - } else { + else maxfreq = 30000 * gx_freq_mult[getCx86(CX86_DIR1) & 0x0f]; - } + stock_freq = maxfreq; curfreq = gx_get_cpuspeed(0); dprintk("cpu max frequency is %d.\n", maxfreq); - dprintk("cpu current frequency is %dkHz.\n",curfreq); + dprintk("cpu current frequency is %dkHz.\n", curfreq); /* setup basic struct for cpufreq API */ policy->cpu = 0; @@ -447,7 +469,8 @@ static int __init cpufreq_gx_init(void) struct pci_dev *gx_pci; /* Test if we have the right hardware */ - if ((gx_pci = gx_detect_chipset()) == NULL) + gx_pci = gx_detect_chipset(); + if (gx_pci == NULL) return -ENODEV; /* check whether module parameters are sane */ @@ -468,9 +491,11 @@ static int __init cpufreq_gx_init(void) pci_read_config_byte(params->cs55x0, PCI_PMER1, &(params->pci_pmer1)); pci_read_config_byte(params->cs55x0, PCI_PMER2, &(params->pci_pmer2)); pci_read_config_byte(params->cs55x0, PCI_MODON, &(params->on_duration)); - pci_read_config_byte(params->cs55x0, PCI_MODOFF, &(params->off_duration)); + pci_read_config_byte(params->cs55x0, PCI_MODOFF, + &(params->off_duration)); - if ((ret = cpufreq_register_driver(&gx_suspmod_driver))) { + ret = cpufreq_register_driver(&gx_suspmod_driver); + if (ret) { kfree(params); return ret; /* register error! */ } @@ -485,9 +510,9 @@ static void __exit cpufreq_gx_exit(void) kfree(gx_params); } -MODULE_AUTHOR ("Hiroshi Miura <miura@da-cha.org>"); -MODULE_DESCRIPTION ("Cpufreq driver for Cyrix MediaGX and NatSemi Geode"); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Hiroshi Miura <miura@da-cha.org>"); +MODULE_DESCRIPTION("Cpufreq driver for Cyrix MediaGX and NatSemi Geode"); +MODULE_LICENSE("GPL"); module_init(cpufreq_gx_init); module_exit(cpufreq_gx_exit); diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c index a4cff5d..0bd48e6 100644 --- a/arch/x86/kernel/cpu/cpufreq/longhaul.c +++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c @@ -30,12 +30,12 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/delay.h> +#include <linux/timex.h> +#include <linux/io.h> +#include <linux/acpi.h> +#include <linux/kernel.h> #include <asm/msr.h> -#include <asm/timex.h> -#include <asm/io.h> -#include <asm/acpi.h> -#include <linux/acpi.h> #include <acpi/processor.h> #include "longhaul.h" @@ -58,7 +58,7 @@ #define USE_NORTHBRIDGE (1 << 2) static int cpu_model; -static unsigned int numscales=16; +static unsigned int numscales = 16; static unsigned int fsb; static const struct mV_pos *vrm_mV_table; @@ -67,8 +67,8 @@ static const unsigned char *mV_vrm_table; static unsigned int highest_speed, lowest_speed; /* kHz */ static unsigned int minmult, maxmult; static int can_scale_voltage; -static struct acpi_processor *pr = NULL; -static struct acpi_processor_cx *cx = NULL; +static struct acpi_processor *pr; +static struct acpi_processor_cx *cx; static u32 acpi_regs_addr; static u8 longhaul_flags; static unsigned int longhaul_index; @@ -78,12 +78,13 @@ static int scale_voltage; static int disable_acpi_c3; static int revid_errata; -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "longhaul", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "longhaul", msg) /* Clock ratios multiplied by 10 */ -static int clock_ratio[32]; -static int eblcr_table[32]; +static int mults[32]; +static int eblcr[32]; static int longhaul_version; static struct cpufreq_frequency_table *longhaul_table; @@ -93,7 +94,7 @@ static char speedbuffer[8]; static char *print_speed(int speed) { if (speed < 1000) { - snprintf(speedbuffer, sizeof(speedbuffer),"%dMHz", speed); + snprintf(speedbuffer, sizeof(speedbuffer), "%dMHz", speed); return speedbuffer; } @@ -122,27 +123,28 @@ static unsigned int calc_speed(int mult) static int longhaul_get_cpu_mult(void) { - unsigned long invalue=0,lo, hi; + unsigned long invalue = 0, lo, hi; - rdmsr (MSR_IA32_EBL_CR_POWERON, lo, hi); - invalue = (lo & (1<<22|1<<23|1<<24|1<<25)) >>22; - if (longhaul_version==TYPE_LONGHAUL_V2 || longhaul_version==TYPE_POWERSAVER) { + rdmsr(MSR_IA32_EBL_CR_POWERON, lo, hi); + invalue = (lo & (1<<22|1<<23|1<<24|1<<25))>>22; + if (longhaul_version == TYPE_LONGHAUL_V2 || + longhaul_version == TYPE_POWERSAVER) { if (lo & (1<<27)) - invalue+=16; + invalue += 16; } - return eblcr_table[invalue]; + return eblcr[invalue]; } /* For processor with BCR2 MSR */ -static void do_longhaul1(unsigned int clock_ratio_index) +static void do_longhaul1(unsigned int mults_index) { union msr_bcr2 bcr2; rdmsrl(MSR_VIA_BCR2, bcr2.val); /* Enable software clock multiplier */ bcr2.bits.ESOFTBF = 1; - bcr2.bits.CLOCKMUL = clock_ratio_index & 0xff; + bcr2.bits.CLOCKMUL = mults_index & 0xff; /* Sync to timer tick */ safe_halt(); @@ -161,7 +163,7 @@ static void do_longhaul1(unsigned int clock_ratio_index) /* For processor with Longhaul MSR */ -static void do_powersaver(int cx_address, unsigned int clock_ratio_index, +static void do_powersaver(int cx_address, unsigned int mults_index, unsigned int dir) { union msr_longhaul longhaul; @@ -173,11 +175,11 @@ static void do_powersaver(int cx_address, unsigned int clock_ratio_index, longhaul.bits.RevisionKey = longhaul.bits.RevisionID; else longhaul.bits.RevisionKey = 0; - longhaul.bits.SoftBusRatio = clock_ratio_index & 0xf; - longhaul.bits.SoftBusRatio4 = (clock_ratio_index & 0x10) >> 4; + longhaul.bits.SoftBusRatio = mults_index & 0xf; + longhaul.bits.SoftBusRatio4 = (mults_index & 0x10) >> 4; /* Setup new voltage */ if (can_scale_voltage) - longhaul.bits.SoftVID = (clock_ratio_index >> 8) & 0x1f; + longhaul.bits.SoftVID = (mults_index >> 8) & 0x1f; /* Sync to timer tick */ safe_halt(); /* Raise voltage if necessary */ @@ -240,14 +242,14 @@ static void do_powersaver(int cx_address, unsigned int clock_ratio_index, /** * longhaul_set_cpu_frequency() - * @clock_ratio_index : bitpattern of the new multiplier. + * @mults_index : bitpattern of the new multiplier. * * Sets a new clock ratio. */ static void longhaul_setstate(unsigned int table_index) { - unsigned int clock_ratio_index; + unsigned int mults_index; int speed, mult; struct cpufreq_freqs freqs; unsigned long flags; @@ -256,9 +258,9 @@ static void longhaul_setstate(unsigned int table_index) u32 bm_timeout = 1000; unsigned int dir = 0; - clock_ratio_index = longhaul_table[table_index].index; + mults_index = longhaul_table[table_index].index; /* Safety precautions */ - mult = clock_ratio[clock_ratio_index & 0x1f]; + mult = mults[mults_index & 0x1f]; if (mult == -1) return; speed = calc_speed(mult); @@ -274,7 +276,7 @@ static void longhaul_setstate(unsigned int table_index) cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); - dprintk ("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n", + dprintk("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n", fsb, mult/10, mult%10, print_speed(speed/1000)); retry_loop: preempt_disable(); @@ -282,8 +284,8 @@ retry_loop: pic2_mask = inb(0xA1); pic1_mask = inb(0x21); /* works on C3. save mask. */ - outb(0xFF,0xA1); /* Overkill */ - outb(0xFE,0x21); /* TMR0 only */ + outb(0xFF, 0xA1); /* Overkill */ + outb(0xFE, 0x21); /* TMR0 only */ /* Wait while PCI bus is busy. */ if (acpi_regs_addr && (longhaul_flags & USE_NORTHBRIDGE @@ -303,7 +305,7 @@ retry_loop: outb(3, 0x22); } else if ((pr != NULL) && pr->flags.bm_control) { /* Disable bus master arbitration */ - acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1); + acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 1); } switch (longhaul_version) { @@ -312,7 +314,7 @@ retry_loop: * Software controlled multipliers only. */ case TYPE_LONGHAUL_V1: - do_longhaul1(clock_ratio_index); + do_longhaul1(mults_index); break; /* @@ -326,10 +328,10 @@ retry_loop: case TYPE_POWERSAVER: if (longhaul_flags & USE_ACPI_C3) { /* Don't allow wakeup */ - acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 0); - do_powersaver(cx->address, clock_ratio_index, dir); + acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, 0); + do_powersaver(cx->address, mults_index, dir); } else { - do_powersaver(0, clock_ratio_index, dir); + do_powersaver(0, mults_index, dir); } break; } @@ -339,10 +341,10 @@ retry_loop: outb(0, 0x22); } else if ((pr != NULL) && pr->flags.bm_control) { /* Enable bus master arbitration */ - acpi_set_register(ACPI_BITREG_ARB_DISABLE, 0); + acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 0); } - outb(pic2_mask,0xA1); /* restore mask */ - outb(pic1_mask,0x21); + outb(pic2_mask, 0xA1); /* restore mask */ + outb(pic1_mask, 0x21); local_irq_restore(flags); preempt_enable(); @@ -392,7 +394,8 @@ retry_loop: cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); if (!bm_timeout) - printk(KERN_INFO PFX "Warning: Timeout while waiting for idle PCI bus.\n"); + printk(KERN_INFO PFX "Warning: Timeout while waiting for " + "idle PCI bus.\n"); } /* @@ -458,31 +461,32 @@ static int __init longhaul_get_ranges(void) break; } - dprintk ("MinMult:%d.%dx MaxMult:%d.%dx\n", + dprintk("MinMult:%d.%dx MaxMult:%d.%dx\n", minmult/10, minmult%10, maxmult/10, maxmult%10); highest_speed = calc_speed(maxmult); lowest_speed = calc_speed(minmult); - dprintk ("FSB:%dMHz Lowest speed: %s Highest speed:%s\n", fsb, + dprintk("FSB:%dMHz Lowest speed: %s Highest speed:%s\n", fsb, print_speed(lowest_speed/1000), print_speed(highest_speed/1000)); if (lowest_speed == highest_speed) { - printk (KERN_INFO PFX "highestspeed == lowest, aborting.\n"); + printk(KERN_INFO PFX "highestspeed == lowest, aborting.\n"); return -EINVAL; } if (lowest_speed > highest_speed) { - printk (KERN_INFO PFX "nonsense! lowest (%d > %d) !\n", + printk(KERN_INFO PFX "nonsense! lowest (%d > %d) !\n", lowest_speed, highest_speed); return -EINVAL; } - longhaul_table = kmalloc((numscales + 1) * sizeof(struct cpufreq_frequency_table), GFP_KERNEL); - if(!longhaul_table) + longhaul_table = kmalloc((numscales + 1) * sizeof(*longhaul_table), + GFP_KERNEL); + if (!longhaul_table) return -ENOMEM; for (j = 0; j < numscales; j++) { - ratio = clock_ratio[j]; + ratio = mults[j]; if (ratio == -1) continue; if (ratio > maxmult || ratio < minmult) @@ -507,13 +511,10 @@ static int __init longhaul_get_ranges(void) } } if (min_i != j) { - unsigned int temp; - temp = longhaul_table[j].frequency; - longhaul_table[j].frequency = longhaul_table[min_i].frequency; - longhaul_table[min_i].frequency = temp; - temp = longhaul_table[j].index; - longhaul_table[j].index = longhaul_table[min_i].index; - longhaul_table[min_i].index = temp; + swap(longhaul_table[j].frequency, + longhaul_table[min_i].frequency); + swap(longhaul_table[j].index, + longhaul_table[min_i].index); } } @@ -521,7 +522,7 @@ static int __init longhaul_get_ranges(void) /* Find index we are running on */ for (j = 0; j < k; j++) { - if (clock_ratio[longhaul_table[j].index & 0x1f] == mult) { + if (mults[longhaul_table[j].index & 0x1f] == mult) { longhaul_index = j; break; } @@ -559,20 +560,22 @@ static void __init longhaul_setup_voltagescaling(void) maxvid = vrm_mV_table[longhaul.bits.MaximumVID]; if (minvid.mV == 0 || maxvid.mV == 0 || minvid.mV > maxvid.mV) { - printk (KERN_INFO PFX "Bogus values Min:%d.%03d Max:%d.%03d. " + printk(KERN_INFO PFX "Bogus values Min:%d.%03d Max:%d.%03d. " "Voltage scaling disabled.\n", - minvid.mV/1000, minvid.mV%1000, maxvid.mV/1000, maxvid.mV%1000); + minvid.mV/1000, minvid.mV%1000, + maxvid.mV/1000, maxvid.mV%1000); return; } if (minvid.mV == maxvid.mV) { - printk (KERN_INFO PFX "Claims to support voltage scaling but min & max are " - "both %d.%03d. Voltage scaling disabled\n", + printk(KERN_INFO PFX "Claims to support voltage scaling but " + "min & max are both %d.%03d. " + "Voltage scaling disabled\n", maxvid.mV/1000, maxvid.mV%1000); return; } - /* How many voltage steps */ + /* How many voltage steps*/ numvscales = maxvid.pos - minvid.pos + 1; printk(KERN_INFO PFX "Max VID=%d.%03d " @@ -586,7 +589,7 @@ static void __init longhaul_setup_voltagescaling(void) j = longhaul.bits.MinMHzBR; if (longhaul.bits.MinMHzBR4) j += 16; - min_vid_speed = eblcr_table[j]; + min_vid_speed = eblcr[j]; if (min_vid_speed == -1) return; switch (longhaul.bits.MinMHzFSB) { @@ -617,7 +620,8 @@ static void __init longhaul_setup_voltagescaling(void) pos = minvid.pos; longhaul_table[j].index |= mV_vrm_table[pos] << 8; vid = vrm_mV_table[mV_vrm_table[pos]]; - printk(KERN_INFO PFX "f: %d kHz, index: %d, vid: %d mV\n", speed, j, vid.mV); + printk(KERN_INFO PFX "f: %d kHz, index: %d, vid: %d mV\n", + speed, j, vid.mV); j++; } @@ -640,7 +644,8 @@ static int longhaul_target(struct cpufreq_policy *policy, unsigned int dir = 0; u8 vid, current_vid; - if (cpufreq_frequency_table_target(policy, longhaul_table, target_freq, relation, &table_index)) + if (cpufreq_frequency_table_target(policy, longhaul_table, target_freq, + relation, &table_index)) return -EINVAL; /* Don't set same frequency again */ @@ -656,7 +661,8 @@ static int longhaul_target(struct cpufreq_policy *policy, * this in hardware, C3 is old and we need to do this * in software. */ i = longhaul_index; - current_vid = (longhaul_table[longhaul_index].index >> 8) & 0x1f; + current_vid = (longhaul_table[longhaul_index].index >> 8); + current_vid &= 0x1f; if (table_index > longhaul_index) dir = 1; while (i != table_index) { @@ -691,9 +697,9 @@ static acpi_status longhaul_walk_callback(acpi_handle obj_handle, { struct acpi_device *d; - if ( acpi_bus_get_device(obj_handle, &d) ) { + if (acpi_bus_get_device(obj_handle, &d)) return 0; - } + *return_value = acpi_driver_data(d); return 1; } @@ -750,7 +756,7 @@ static int longhaul_setup_southbridge(void) /* Find VT8235 southbridge */ dev = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235, NULL); if (dev == NULL) - /* Find VT8237 southbridge */ + /* Find VT8237 southbridge */ dev = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237, NULL); if (dev != NULL) { @@ -769,7 +775,8 @@ static int longhaul_setup_southbridge(void) if (pci_cmd & 1 << 7) { pci_read_config_dword(dev, 0x88, &acpi_regs_addr); acpi_regs_addr &= 0xff00; - printk(KERN_INFO PFX "ACPI I/O at 0x%x\n", acpi_regs_addr); + printk(KERN_INFO PFX "ACPI I/O at 0x%x\n", + acpi_regs_addr); } pci_dev_put(dev); @@ -781,7 +788,7 @@ static int longhaul_setup_southbridge(void) static int __init longhaul_cpu_init(struct cpufreq_policy *policy) { struct cpuinfo_x86 *c = &cpu_data(0); - char *cpuname=NULL; + char *cpuname = NULL; int ret; u32 lo, hi; @@ -791,8 +798,8 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) cpu_model = CPU_SAMUEL; cpuname = "C3 'Samuel' [C5A]"; longhaul_version = TYPE_LONGHAUL_V1; - memcpy (clock_ratio, samuel1_clock_ratio, sizeof(samuel1_clock_ratio)); - memcpy (eblcr_table, samuel1_eblcr, sizeof(samuel1_eblcr)); + memcpy(mults, samuel1_mults, sizeof(samuel1_mults)); + memcpy(eblcr, samuel1_eblcr, sizeof(samuel1_eblcr)); break; case 7: @@ -803,10 +810,8 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) cpuname = "C3 'Samuel 2' [C5B]"; /* Note, this is not a typo, early Samuel2's had * Samuel1 ratios. */ - memcpy(clock_ratio, samuel1_clock_ratio, - sizeof(samuel1_clock_ratio)); - memcpy(eblcr_table, samuel2_eblcr, - sizeof(samuel2_eblcr)); + memcpy(mults, samuel1_mults, sizeof(samuel1_mults)); + memcpy(eblcr, samuel2_eblcr, sizeof(samuel2_eblcr)); break; case 1 ... 15: longhaul_version = TYPE_LONGHAUL_V1; @@ -817,10 +822,8 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) cpu_model = CPU_EZRA; cpuname = "C3 'Ezra' [C5C]"; } - memcpy(clock_ratio, ezra_clock_ratio, - sizeof(ezra_clock_ratio)); - memcpy(eblcr_table, ezra_eblcr, - sizeof(ezra_eblcr)); + memcpy(mults, ezra_mults, sizeof(ezra_mults)); + memcpy(eblcr, ezra_eblcr, sizeof(ezra_eblcr)); break; } break; @@ -829,18 +832,16 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) cpu_model = CPU_EZRA_T; cpuname = "C3 'Ezra-T' [C5M]"; longhaul_version = TYPE_POWERSAVER; - numscales=32; - memcpy (clock_ratio, ezrat_clock_ratio, sizeof(ezrat_clock_ratio)); - memcpy (eblcr_table, ezrat_eblcr, sizeof(ezrat_eblcr)); + numscales = 32; + memcpy(mults, ezrat_mults, sizeof(ezrat_mults)); + memcpy(eblcr, ezrat_eblcr, sizeof(ezrat_eblcr)); break; case 9: longhaul_version = TYPE_POWERSAVER; numscales = 32; - memcpy(clock_ratio, - nehemiah_clock_ratio, - sizeof(nehemiah_clock_ratio)); - memcpy(eblcr_table, nehemiah_eblcr, sizeof(nehemiah_eblcr)); + memcpy(mults, nehemiah_mults, sizeof(nehemiah_mults)); + memcpy(eblcr, nehemiah_eblcr, sizeof(nehemiah_eblcr)); switch (c->x86_mask) { case 0 ... 1: cpu_model = CPU_NEHEMIAH; @@ -869,14 +870,14 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) longhaul_version = TYPE_LONGHAUL_V1; } - printk (KERN_INFO PFX "VIA %s CPU detected. ", cpuname); + printk(KERN_INFO PFX "VIA %s CPU detected. ", cpuname); switch (longhaul_version) { case TYPE_LONGHAUL_V1: case TYPE_LONGHAUL_V2: - printk ("Longhaul v%d supported.\n", longhaul_version); + printk(KERN_CONT "Longhaul v%d supported.\n", longhaul_version); break; case TYPE_POWERSAVER: - printk ("Powersaver supported.\n"); + printk(KERN_CONT "Powersaver supported.\n"); break; }; @@ -940,7 +941,7 @@ static int __devexit longhaul_cpu_exit(struct cpufreq_policy *policy) return 0; } -static struct freq_attr* longhaul_attr[] = { +static struct freq_attr *longhaul_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -966,13 +967,15 @@ static int __init longhaul_init(void) #ifdef CONFIG_SMP if (num_online_cpus() > 1) { - printk(KERN_ERR PFX "More than 1 CPU detected, longhaul disabled.\n"); + printk(KERN_ERR PFX "More than 1 CPU detected, " + "longhaul disabled.\n"); return -ENODEV; } #endif #ifdef CONFIG_X86_IO_APIC if (cpu_has_apic) { - printk(KERN_ERR PFX "APIC detected. Longhaul is currently broken in this configuration.\n"); + printk(KERN_ERR PFX "APIC detected. Longhaul is currently " + "broken in this configuration.\n"); return -ENODEV; } #endif @@ -993,8 +996,8 @@ static void __exit longhaul_exit(void) { int i; - for (i=0; i < numscales; i++) { - if (clock_ratio[i] == maxmult) { + for (i = 0; i < numscales; i++) { + if (mults[i] == maxmult) { longhaul_setstate(i); break; } @@ -1007,11 +1010,11 @@ static void __exit longhaul_exit(void) /* Even if BIOS is exporting ACPI C3 state, and it is used * with success when CPU is idle, this state doesn't * trigger frequency transition in some cases. */ -module_param (disable_acpi_c3, int, 0644); +module_param(disable_acpi_c3, int, 0644); MODULE_PARM_DESC(disable_acpi_c3, "Don't use ACPI C3 support"); /* Change CPU voltage with frequency. Very usefull to save * power, but most VIA C3 processors aren't supporting it. */ -module_param (scale_voltage, int, 0644); +module_param(scale_voltage, int, 0644); MODULE_PARM_DESC(scale_voltage, "Scale voltage of processor"); /* Force revision key to 0 for processors which doesn't * support voltage scaling, but are introducing itself as @@ -1019,9 +1022,9 @@ MODULE_PARM_DESC(scale_voltage, "Scale voltage of processor"); module_param(revid_errata, int, 0644); MODULE_PARM_DESC(revid_errata, "Ignore CPU Revision ID"); -MODULE_AUTHOR ("Dave Jones <davej@redhat.com>"); -MODULE_DESCRIPTION ("Longhaul driver for VIA Cyrix processors."); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Dave Jones <davej@redhat.com>"); +MODULE_DESCRIPTION("Longhaul driver for VIA Cyrix processors."); +MODULE_LICENSE("GPL"); late_initcall(longhaul_init); module_exit(longhaul_exit); diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.h b/arch/x86/kernel/cpu/cpufreq/longhaul.h index 4fcc320..e2360a4 100644 --- a/arch/x86/kernel/cpu/cpufreq/longhaul.h +++ b/arch/x86/kernel/cpu/cpufreq/longhaul.h @@ -49,14 +49,14 @@ union msr_longhaul { /* * Clock ratio tables. Div/Mod by 10 to get ratio. - * The eblcr ones specify the ratio read from the CPU. - * The clock_ratio ones specify what to write to the CPU. + * The eblcr values specify the ratio read from the CPU. + * The mults values specify what to write to the CPU. */ /* * VIA C3 Samuel 1 & Samuel 2 (stepping 0) */ -static const int __initdata samuel1_clock_ratio[16] = { +static const int __initdata samuel1_mults[16] = { -1, /* 0000 -> RESERVED */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -119,7 +119,7 @@ static const int __initdata samuel2_eblcr[16] = { /* * VIA C3 Ezra */ -static const int __initdata ezra_clock_ratio[16] = { +static const int __initdata ezra_mults[16] = { 100, /* 0000 -> 10.0x */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -160,7 +160,7 @@ static const int __initdata ezra_eblcr[16] = { /* * VIA C3 (Ezra-T) [C5M]. */ -static const int __initdata ezrat_clock_ratio[32] = { +static const int __initdata ezrat_mults[32] = { 100, /* 0000 -> 10.0x */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -235,7 +235,7 @@ static const int __initdata ezrat_eblcr[32] = { /* * VIA C3 Nehemiah */ -static const int __initdata nehemiah_clock_ratio[32] = { +static const int __initdata nehemiah_mults[32] = { 100, /* 0000 -> 10.0x */ -1, /* 0001 -> 16.0x */ 40, /* 0010 -> 4.0x */ diff --git a/arch/x86/kernel/cpu/cpufreq/longrun.c b/arch/x86/kernel/cpu/cpufreq/longrun.c index 777a7ff..da5f70f 100644 --- a/arch/x86/kernel/cpu/cpufreq/longrun.c +++ b/arch/x86/kernel/cpu/cpufreq/longrun.c @@ -11,12 +11,13 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/cpufreq.h> +#include <linux/timex.h> #include <asm/msr.h> #include <asm/processor.h> -#include <asm/timex.h> -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "longrun", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "longrun", msg) static struct cpufreq_driver longrun_driver; @@ -51,7 +52,7 @@ static void __init longrun_get_policy(struct cpufreq_policy *policy) msr_lo &= 0x0000007F; msr_hi &= 0x0000007F; - if ( longrun_high_freq <= longrun_low_freq ) { + if (longrun_high_freq <= longrun_low_freq) { /* Assume degenerate Longrun table */ policy->min = policy->max = longrun_high_freq; } else { @@ -79,7 +80,7 @@ static int longrun_set_policy(struct cpufreq_policy *policy) if (!policy) return -EINVAL; - if ( longrun_high_freq <= longrun_low_freq ) { + if (longrun_high_freq <= longrun_low_freq) { /* Assume degenerate Longrun table */ pctg_lo = pctg_hi = 100; } else { @@ -152,7 +153,7 @@ static unsigned int longrun_get(unsigned int cpu) cpuid(0x80860007, &eax, &ebx, &ecx, &edx); dprintk("cpuid eax is %u\n", eax); - return (eax * 1000); + return eax * 1000; } /** @@ -196,7 +197,8 @@ static unsigned int __init longrun_determine_freqs(unsigned int *low_freq, rdmsr(MSR_TMTA_LRTI_VOLT_MHZ, msr_lo, msr_hi); *high_freq = msr_lo * 1000; /* to kHz */ - dprintk("longrun table interface told %u - %u kHz\n", *low_freq, *high_freq); + dprintk("longrun table interface told %u - %u kHz\n", + *low_freq, *high_freq); if (*low_freq > *high_freq) *low_freq = *high_freq; @@ -219,7 +221,7 @@ static unsigned int __init longrun_determine_freqs(unsigned int *low_freq, cpuid(0x80860007, &eax, &ebx, &ecx, &edx); /* try decreasing in 10% steps, some processors react only * on some barrier values */ - for (try_hi = 80; try_hi > 0 && ecx > 90; try_hi -=10) { + for (try_hi = 80; try_hi > 0 && ecx > 90; try_hi -= 10) { /* set to 0 to try_hi perf_pctg */ msr_lo &= 0xFFFFFF80; msr_hi &= 0xFFFFFF80; @@ -236,7 +238,7 @@ static unsigned int __init longrun_determine_freqs(unsigned int *low_freq, /* performance_pctg = (current_freq - low_freq)/(high_freq - low_freq) * eqals - * low_freq * ( 1 - perf_pctg) = (cur_freq - high_freq * perf_pctg) + * low_freq * (1 - perf_pctg) = (cur_freq - high_freq * perf_pctg) * * high_freq * perf_pctg is stored tempoarily into "ebx". */ @@ -317,9 +319,10 @@ static void __exit longrun_exit(void) } -MODULE_AUTHOR ("Dominik Brodowski <linux@brodo.de>"); -MODULE_DESCRIPTION ("LongRun driver for Transmeta Crusoe and Efficeon processors."); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>"); +MODULE_DESCRIPTION("LongRun driver for Transmeta Crusoe and " + "Efficeon processors."); +MODULE_LICENSE("GPL"); module_init(longrun_init); module_exit(longrun_exit); diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index b585e04c..6ac55bd 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -27,15 +27,17 @@ #include <linux/cpufreq.h> #include <linux/slab.h> #include <linux/cpumask.h> +#include <linux/timex.h> #include <asm/processor.h> #include <asm/msr.h> -#include <asm/timex.h> +#include <asm/timer.h> #include "speedstep-lib.h" #define PFX "p4-clockmod: " -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "p4-clockmod", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "p4-clockmod", msg) /* * Duty Cycle (3bits), note DC_DISABLE is not specified in @@ -58,7 +60,8 @@ static int cpufreq_p4_setdc(unsigned int cpu, unsigned int newstate) { u32 l, h; - if (!cpu_online(cpu) || (newstate > DC_DISABLE) || (newstate == DC_RESV)) + if (!cpu_online(cpu) || + (newstate > DC_DISABLE) || (newstate == DC_RESV)) return -EINVAL; rdmsr_on_cpu(cpu, MSR_IA32_THERM_STATUS, &l, &h); @@ -66,7 +69,8 @@ static int cpufreq_p4_setdc(unsigned int cpu, unsigned int newstate) if (l & 0x01) dprintk("CPU#%d currently thermal throttled\n", cpu); - if (has_N44_O17_errata[cpu] && (newstate == DC_25PT || newstate == DC_DFLT)) + if (has_N44_O17_errata[cpu] && + (newstate == DC_25PT || newstate == DC_DFLT)) newstate = DC_38PT; rdmsr_on_cpu(cpu, MSR_IA32_THERM_CONTROL, &l, &h); @@ -112,7 +116,8 @@ static int cpufreq_p4_target(struct cpufreq_policy *policy, struct cpufreq_freqs freqs; int i; - if (cpufreq_frequency_table_target(policy, &p4clockmod_table[0], target_freq, relation, &newstate)) + if (cpufreq_frequency_table_target(policy, &p4clockmod_table[0], + target_freq, relation, &newstate)) return -EINVAL; freqs.old = cpufreq_p4_get(policy->cpu); @@ -127,7 +132,8 @@ static int cpufreq_p4_target(struct cpufreq_policy *policy, cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); } - /* run on each logical CPU, see section 13.15.3 of IA32 Intel Architecture Software + /* run on each logical CPU, + * see section 13.15.3 of IA32 Intel Architecture Software * Developer's Manual, Volume 3 */ for_each_cpu(i, policy->cpus) @@ -153,28 +159,30 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c) { if (c->x86 == 0x06) { if (cpu_has(c, X86_FEATURE_EST)) - printk(KERN_WARNING PFX "Warning: EST-capable CPU detected. " - "The acpi-cpufreq module offers voltage scaling" - " in addition of frequency scaling. You should use " - "that instead of p4-clockmod, if possible.\n"); + printk(KERN_WARNING PFX "Warning: EST-capable CPU " + "detected. The acpi-cpufreq module offers " + "voltage scaling in addition of frequency " + "scaling. You should use that instead of " + "p4-clockmod, if possible.\n"); switch (c->x86_model) { case 0x0E: /* Core */ case 0x0F: /* Core Duo */ case 0x16: /* Celeron Core */ p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; - return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PCORE); + return speedstep_get_frequency(SPEEDSTEP_CPU_PCORE); case 0x0D: /* Pentium M (Dothan) */ p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; /* fall through */ case 0x09: /* Pentium M (Banias) */ - return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PM); + return speedstep_get_frequency(SPEEDSTEP_CPU_PM); } } if (c->x86 != 0xF) { if (!cpu_has(c, X86_FEATURE_EST)) - printk(KERN_WARNING PFX "Unknown p4-clockmod-capable CPU. " - "Please send an e-mail to <cpufreq@vger.kernel.org>\n"); + printk(KERN_WARNING PFX "Unknown CPU. " + "Please send an e-mail to " + "<cpufreq@vger.kernel.org>\n"); return 0; } @@ -182,16 +190,16 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c) * throttling is active or not. */ p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; - if (speedstep_detect_processor() == SPEEDSTEP_PROCESSOR_P4M) { + if (speedstep_detect_processor() == SPEEDSTEP_CPU_P4M) { printk(KERN_WARNING PFX "Warning: Pentium 4-M detected. " "The speedstep-ich or acpi cpufreq modules offer " "voltage scaling in addition of frequency scaling. " "You should use either one instead of p4-clockmod, " "if possible.\n"); - return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_P4M); + return speedstep_get_frequency(SPEEDSTEP_CPU_P4M); } - return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_P4D); + return speedstep_get_frequency(SPEEDSTEP_CPU_P4D); } @@ -203,7 +211,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) unsigned int i; #ifdef CONFIG_SMP - cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu)); + cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu)); #endif /* Errata workaround */ @@ -217,14 +225,20 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) dprintk("has errata -- disabling low frequencies\n"); } + if (speedstep_detect_processor() == SPEEDSTEP_CPU_P4D && + c->x86_model < 2) { + /* switch to maximum frequency and measure result */ + cpufreq_p4_setdc(policy->cpu, DC_DISABLE); + recalibrate_cpu_khz(); + } /* get max frequency */ stock_freq = cpufreq_p4_get_frequency(c); if (!stock_freq) return -EINVAL; /* table init */ - for (i=1; (p4clockmod_table[i].frequency != CPUFREQ_TABLE_END); i++) { - if ((i<2) && (has_N44_O17_errata[policy->cpu])) + for (i = 1; (p4clockmod_table[i].frequency != CPUFREQ_TABLE_END); i++) { + if ((i < 2) && (has_N44_O17_errata[policy->cpu])) p4clockmod_table[i].frequency = CPUFREQ_ENTRY_INVALID; else p4clockmod_table[i].frequency = (stock_freq * i)/8; @@ -232,7 +246,10 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) cpufreq_frequency_table_get_attr(p4clockmod_table, policy->cpu); /* cpuinfo and default policy values */ - policy->cpuinfo.transition_latency = 1000000; /* assumed */ + + /* the transition latency is set to be 1 higher than the maximum + * transition latency of the ondemand governor */ + policy->cpuinfo.transition_latency = 10000001; policy->cur = stock_freq; return cpufreq_frequency_table_cpuinfo(policy, &p4clockmod_table[0]); @@ -258,12 +275,12 @@ static unsigned int cpufreq_p4_get(unsigned int cpu) l = DC_DISABLE; if (l != DC_DISABLE) - return (stock_freq * l / 8); + return stock_freq * l / 8; return stock_freq; } -static struct freq_attr* p4clockmod_attr[] = { +static struct freq_attr *p4clockmod_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -277,7 +294,6 @@ static struct cpufreq_driver p4clockmod_driver = { .name = "p4-clockmod", .owner = THIS_MODULE, .attr = p4clockmod_attr, - .hide_interface = 1, }; @@ -299,9 +315,10 @@ static int __init cpufreq_p4_init(void) ret = cpufreq_register_driver(&p4clockmod_driver); if (!ret) - printk(KERN_INFO PFX "P4/Xeon(TM) CPU On-Demand Clock Modulation available\n"); + printk(KERN_INFO PFX "P4/Xeon(TM) CPU On-Demand Clock " + "Modulation available\n"); - return (ret); + return ret; } @@ -311,9 +328,9 @@ static void __exit cpufreq_p4_exit(void) } -MODULE_AUTHOR ("Zwane Mwaikambo <zwane@commfireservices.com>"); -MODULE_DESCRIPTION ("cpufreq driver for Pentium(TM) 4/Xeon(TM)"); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Zwane Mwaikambo <zwane@commfireservices.com>"); +MODULE_DESCRIPTION("cpufreq driver for Pentium(TM) 4/Xeon(TM)"); +MODULE_LICENSE("GPL"); late_initcall(cpufreq_p4_init); module_exit(cpufreq_p4_exit); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c index c1ac579..f10dea4 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c @@ -1,6 +1,7 @@ /* * This file was based upon code in Powertweak Linux (http://powertweak.sf.net) - * (C) 2000-2003 Dave Jones, Arjan van de Ven, Janne Pänkälä, Dominik Brodowski. + * (C) 2000-2003 Dave Jones, Arjan van de Ven, Janne Pänkälä, + * Dominik Brodowski. * * Licensed under the terms of the GNU GPL License version 2. * @@ -13,14 +14,15 @@ #include <linux/cpufreq.h> #include <linux/ioport.h> #include <linux/slab.h> - -#include <asm/msr.h> #include <linux/timex.h> #include <linux/io.h> +#include <asm/msr.h> + #define POWERNOW_IOPORT 0xfff0 /* it doesn't matter where, as long as it is unused */ +#define PFX "powernow-k6: " static unsigned int busfreq; /* FSB, in 10 kHz */ static unsigned int max_multiplier; @@ -47,8 +49,8 @@ static struct cpufreq_frequency_table clock_ratio[] = { */ static int powernow_k6_get_cpu_multiplier(void) { - u64 invalue = 0; - u32 msrval; + u64 invalue = 0; + u32 msrval; msrval = POWERNOW_IOPORT + 0x1; wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */ @@ -68,12 +70,12 @@ static int powernow_k6_get_cpu_multiplier(void) */ static void powernow_k6_set_state(unsigned int best_i) { - unsigned long outvalue = 0, invalue = 0; - unsigned long msrval; - struct cpufreq_freqs freqs; + unsigned long outvalue = 0, invalue = 0; + unsigned long msrval; + struct cpufreq_freqs freqs; if (clock_ratio[best_i].index > max_multiplier) { - printk(KERN_ERR "cpufreq: invalid target frequency\n"); + printk(KERN_ERR PFX "invalid target frequency\n"); return; } @@ -119,7 +121,8 @@ static int powernow_k6_verify(struct cpufreq_policy *policy) * powernow_k6_setpolicy - sets a new CPUFreq policy * @policy: new policy * @target_freq: the target frequency - * @relation: how that frequency relates to achieved frequency (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H) + * @relation: how that frequency relates to achieved frequency + * (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H) * * sets a new CPUFreq policy */ @@ -127,9 +130,10 @@ static int powernow_k6_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { - unsigned int newstate = 0; + unsigned int newstate = 0; - if (cpufreq_frequency_table_target(policy, &clock_ratio[0], target_freq, relation, &newstate)) + if (cpufreq_frequency_table_target(policy, &clock_ratio[0], + target_freq, relation, &newstate)) return -EINVAL; powernow_k6_set_state(newstate); @@ -140,7 +144,7 @@ static int powernow_k6_target(struct cpufreq_policy *policy, static int powernow_k6_cpu_init(struct cpufreq_policy *policy) { - unsigned int i; + unsigned int i, f; int result; if (policy->cpu != 0) @@ -152,10 +156,11 @@ static int powernow_k6_cpu_init(struct cpufreq_policy *policy) /* table init */ for (i = 0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) { - if (clock_ratio[i].index > max_multiplier) + f = clock_ratio[i].index; + if (f > max_multiplier) clock_ratio[i].frequency = CPUFREQ_ENTRY_INVALID; else - clock_ratio[i].frequency = busfreq * clock_ratio[i].index; + clock_ratio[i].frequency = busfreq * f; } /* cpuinfo and default policy values */ @@ -185,7 +190,9 @@ static int powernow_k6_cpu_exit(struct cpufreq_policy *policy) static unsigned int powernow_k6_get(unsigned int cpu) { - return busfreq * powernow_k6_get_cpu_multiplier(); + unsigned int ret; + ret = (busfreq * powernow_k6_get_cpu_multiplier()); + return ret; } static struct freq_attr *powernow_k6_attr[] = { @@ -221,7 +228,7 @@ static int __init powernow_k6_init(void) return -ENODEV; if (!request_region(POWERNOW_IOPORT, 16, "PowerNow!")) { - printk("cpufreq: PowerNow IOPORT region already used.\n"); + printk(KERN_INFO PFX "PowerNow IOPORT region already used.\n"); return -EIO; } @@ -246,7 +253,8 @@ static void __exit powernow_k6_exit(void) } -MODULE_AUTHOR("Arjan van de Ven, Dave Jones <davej@redhat.com>, Dominik Brodowski <linux@brodo.de>"); +MODULE_AUTHOR("Arjan van de Ven, Dave Jones <davej@redhat.com>, " + "Dominik Brodowski <linux@brodo.de>"); MODULE_DESCRIPTION("PowerNow! driver for AMD K6-2+ / K6-3+ processors."); MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c index 1b446d7..3c28ccd 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c @@ -6,10 +6,12 @@ * Licensed under the terms of the GNU GPL License version 2. * Based upon datasheets & sample CPUs kindly provided by AMD. * - * Errata 5: Processor may fail to execute a FID/VID change in presence of interrupt. - * - We cli/sti on stepping A0 CPUs around the FID/VID transition. - * Errata 15: Processors with half frequency multipliers may hang upon wakeup from disconnect. - * - We disable half multipliers if ACPI is used on A0 stepping CPUs. + * Errata 5: + * CPU may fail to execute a FID/VID change in presence of interrupt. + * - We cli/sti on stepping A0 CPUs around the FID/VID transition. + * Errata 15: + * CPU with half frequency multipliers may hang upon wakeup from disconnect. + * - We disable half multipliers if ACPI is used on A0 stepping CPUs. */ #include <linux/kernel.h> @@ -20,11 +22,11 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/dmi.h> +#include <linux/timex.h> +#include <linux/io.h> +#include <asm/timer.h> /* Needed for recalibrate_cpu_khz() */ #include <asm/msr.h> -#include <asm/timer.h> -#include <asm/timex.h> -#include <asm/io.h> #include <asm/system.h> #ifdef CONFIG_X86_POWERNOW_K7_ACPI @@ -58,9 +60,9 @@ struct pst_s { union powernow_acpi_control_t { struct { unsigned long fid:5, - vid:5, - sgtc:20, - res1:2; + vid:5, + sgtc:20, + res1:2; } bits; unsigned long val; }; @@ -94,14 +96,15 @@ static struct cpufreq_frequency_table *powernow_table; static unsigned int can_scale_bus; static unsigned int can_scale_vid; -static unsigned int minimum_speed=-1; +static unsigned int minimum_speed = -1; static unsigned int maximum_speed; static unsigned int number_scales; static unsigned int fsb; static unsigned int latency; static char have_a0; -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "powernow-k7", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "powernow-k7", msg) static int check_fsb(unsigned int fsbspeed) { @@ -109,7 +112,7 @@ static int check_fsb(unsigned int fsbspeed) unsigned int f = fsb / 1000; delta = (fsbspeed > f) ? fsbspeed - f : f - fsbspeed; - return (delta < 5); + return delta < 5; } static int check_powernow(void) @@ -117,24 +120,26 @@ static int check_powernow(void) struct cpuinfo_x86 *c = &cpu_data(0); unsigned int maxei, eax, ebx, ecx, edx; - if ((c->x86_vendor != X86_VENDOR_AMD) || (c->x86 !=6)) { + if ((c->x86_vendor != X86_VENDOR_AMD) || (c->x86 != 6)) { #ifdef MODULE - printk (KERN_INFO PFX "This module only works with AMD K7 CPUs\n"); + printk(KERN_INFO PFX "This module only works with " + "AMD K7 CPUs\n"); #endif return 0; } /* Get maximum capabilities */ - maxei = cpuid_eax (0x80000000); + maxei = cpuid_eax(0x80000000); if (maxei < 0x80000007) { /* Any powernow info ? */ #ifdef MODULE - printk (KERN_INFO PFX "No powernow capabilities detected\n"); + printk(KERN_INFO PFX "No powernow capabilities detected\n"); #endif return 0; } if ((c->x86_model == 6) && (c->x86_mask == 0)) { - printk (KERN_INFO PFX "K7 660[A0] core detected, enabling errata workarounds\n"); + printk(KERN_INFO PFX "K7 660[A0] core detected, " + "enabling errata workarounds\n"); have_a0 = 1; } @@ -144,37 +149,42 @@ static int check_powernow(void) if (!(edx & (1 << 1 | 1 << 2))) return 0; - printk (KERN_INFO PFX "PowerNOW! Technology present. Can scale: "); + printk(KERN_INFO PFX "PowerNOW! Technology present. Can scale: "); if (edx & 1 << 1) { - printk ("frequency"); - can_scale_bus=1; + printk("frequency"); + can_scale_bus = 1; } if ((edx & (1 << 1 | 1 << 2)) == 0x6) - printk (" and "); + printk(" and "); if (edx & 1 << 2) { - printk ("voltage"); - can_scale_vid=1; + printk("voltage"); + can_scale_vid = 1; } - printk (".\n"); + printk(".\n"); return 1; } +static void invalidate_entry(unsigned int entry) +{ + powernow_table[entry].frequency = CPUFREQ_ENTRY_INVALID; +} -static int get_ranges (unsigned char *pst) +static int get_ranges(unsigned char *pst) { unsigned int j; unsigned int speed; u8 fid, vid; - powernow_table = kzalloc((sizeof(struct cpufreq_frequency_table) * (number_scales + 1)), GFP_KERNEL); + powernow_table = kzalloc((sizeof(struct cpufreq_frequency_table) * + (number_scales + 1)), GFP_KERNEL); if (!powernow_table) return -ENOMEM; - for (j=0 ; j < number_scales; j++) { + for (j = 0 ; j < number_scales; j++) { fid = *pst++; powernow_table[j].frequency = (fsb * fid_codes[fid]) / 10; @@ -182,10 +192,10 @@ static int get_ranges (unsigned char *pst) speed = powernow_table[j].frequency; - if ((fid_codes[fid] % 10)==5) { + if ((fid_codes[fid] % 10) == 5) { #ifdef CONFIG_X86_POWERNOW_K7_ACPI if (have_a0 == 1) - powernow_table[j].frequency = CPUFREQ_ENTRY_INVALID; + invalidate_entry(j); #endif } @@ -197,7 +207,7 @@ static int get_ranges (unsigned char *pst) vid = *pst++; powernow_table[j].index |= (vid << 8); /* upper 8 bits */ - dprintk (" FID: 0x%x (%d.%dx [%dMHz]) " + dprintk(" FID: 0x%x (%d.%dx [%dMHz]) " "VID: 0x%x (%d.%03dV)\n", fid, fid_codes[fid] / 10, fid_codes[fid] % 10, speed/1000, vid, mobile_vid_table[vid]/1000, @@ -214,13 +224,13 @@ static void change_FID(int fid) { union msr_fidvidctl fidvidctl; - rdmsrl (MSR_K7_FID_VID_CTL, fidvidctl.val); + rdmsrl(MSR_K7_FID_VID_CTL, fidvidctl.val); if (fidvidctl.bits.FID != fid) { fidvidctl.bits.SGTC = latency; fidvidctl.bits.FID = fid; fidvidctl.bits.VIDC = 0; fidvidctl.bits.FIDC = 1; - wrmsrl (MSR_K7_FID_VID_CTL, fidvidctl.val); + wrmsrl(MSR_K7_FID_VID_CTL, fidvidctl.val); } } @@ -229,18 +239,18 @@ static void change_VID(int vid) { union msr_fidvidctl fidvidctl; - rdmsrl (MSR_K7_FID_VID_CTL, fidvidctl.val); + rdmsrl(MSR_K7_FID_VID_CTL, fidvidctl.val); if (fidvidctl.bits.VID != vid) { fidvidctl.bits.SGTC = latency; fidvidctl.bits.VID = vid; fidvidctl.bits.FIDC = 0; fidvidctl.bits.VIDC = 1; - wrmsrl (MSR_K7_FID_VID_CTL, fidvidctl.val); + wrmsrl(MSR_K7_FID_VID_CTL, fidvidctl.val); } } -static void change_speed (unsigned int index) +static void change_speed(unsigned int index) { u8 fid, vid; struct cpufreq_freqs freqs; @@ -257,7 +267,7 @@ static void change_speed (unsigned int index) freqs.cpu = 0; - rdmsrl (MSR_K7_FID_VID_STATUS, fidvidstatus.val); + rdmsrl(MSR_K7_FID_VID_STATUS, fidvidstatus.val); cfid = fidvidstatus.bits.CFID; freqs.old = fsb * fid_codes[cfid] / 10; @@ -321,12 +331,14 @@ static int powernow_acpi_init(void) goto err1; } - if (acpi_processor_perf->control_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) { + if (acpi_processor_perf->control_register.space_id != + ACPI_ADR_SPACE_FIXED_HARDWARE) { retval = -ENODEV; goto err2; } - if (acpi_processor_perf->status_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) { + if (acpi_processor_perf->status_register.space_id != + ACPI_ADR_SPACE_FIXED_HARDWARE) { retval = -ENODEV; goto err2; } @@ -338,7 +350,8 @@ static int powernow_acpi_init(void) goto err2; } - powernow_table = kzalloc((number_scales + 1) * (sizeof(struct cpufreq_frequency_table)), GFP_KERNEL); + powernow_table = kzalloc((sizeof(struct cpufreq_frequency_table) * + (number_scales + 1)), GFP_KERNEL); if (!powernow_table) { retval = -ENOMEM; goto err2; @@ -352,7 +365,7 @@ static int powernow_acpi_init(void) unsigned int speed, speed_mhz; pc.val = (unsigned long) state->control; - dprintk ("acpi: P%d: %d MHz %d mW %d uS control %08x SGTC %d\n", + dprintk("acpi: P%d: %d MHz %d mW %d uS control %08x SGTC %d\n", i, (u32) state->core_frequency, (u32) state->power, @@ -381,12 +394,12 @@ static int powernow_acpi_init(void) if (speed % 1000 > 0) speed_mhz++; - if ((fid_codes[fid] % 10)==5) { + if ((fid_codes[fid] % 10) == 5) { if (have_a0 == 1) - powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; + invalidate_entry(i); } - dprintk (" FID: 0x%x (%d.%dx [%dMHz]) " + dprintk(" FID: 0x%x (%d.%dx [%dMHz]) " "VID: 0x%x (%d.%03dV)\n", fid, fid_codes[fid] / 10, fid_codes[fid] % 10, speed_mhz, vid, mobile_vid_table[vid]/1000, @@ -422,7 +435,8 @@ err1: err05: kfree(acpi_processor_perf); err0: - printk(KERN_WARNING PFX "ACPI perflib can not be used in this platform\n"); + printk(KERN_WARNING PFX "ACPI perflib can not be used on " + "this platform\n"); acpi_processor_perf = NULL; return retval; } @@ -435,7 +449,14 @@ static int powernow_acpi_init(void) } #endif -static int powernow_decode_bios (int maxfid, int startvid) +static void print_pst_entry(struct pst_s *pst, unsigned int j) +{ + dprintk("PST:%d (@%p)\n", j, pst); + dprintk(" cpuid: 0x%x fsb: %d maxFID: 0x%x startvid: 0x%x\n", + pst->cpuid, pst->fsbspeed, pst->maxfid, pst->startvid); +} + +static int powernow_decode_bios(int maxfid, int startvid) { struct psb_s *psb; struct pst_s *pst; @@ -446,61 +467,67 @@ static int powernow_decode_bios (int maxfid, int startvid) etuple = cpuid_eax(0x80000001); - for (i=0xC0000; i < 0xffff0 ; i+=16) { + for (i = 0xC0000; i < 0xffff0 ; i += 16) { p = phys_to_virt(i); - if (memcmp(p, "AMDK7PNOW!", 10) == 0){ - dprintk ("Found PSB header at %p\n", p); + if (memcmp(p, "AMDK7PNOW!", 10) == 0) { + dprintk("Found PSB header at %p\n", p); psb = (struct psb_s *) p; - dprintk ("Table version: 0x%x\n", psb->tableversion); + dprintk("Table version: 0x%x\n", psb->tableversion); if (psb->tableversion != 0x12) { - printk (KERN_INFO PFX "Sorry, only v1.2 tables supported right now\n"); + printk(KERN_INFO PFX "Sorry, only v1.2 tables" + " supported right now\n"); return -ENODEV; } - dprintk ("Flags: 0x%x\n", psb->flags); - if ((psb->flags & 1)==0) { - dprintk ("Mobile voltage regulator\n"); - } else { - dprintk ("Desktop voltage regulator\n"); - } + dprintk("Flags: 0x%x\n", psb->flags); + if ((psb->flags & 1) == 0) + dprintk("Mobile voltage regulator\n"); + else + dprintk("Desktop voltage regulator\n"); latency = psb->settlingtime; if (latency < 100) { - printk(KERN_INFO PFX "BIOS set settling time to %d microseconds. " - "Should be at least 100. Correcting.\n", latency); + printk(KERN_INFO PFX "BIOS set settling time " + "to %d microseconds. " + "Should be at least 100. " + "Correcting.\n", latency); latency = 100; } - dprintk ("Settling Time: %d microseconds.\n", psb->settlingtime); - dprintk ("Has %d PST tables. (Only dumping ones relevant to this CPU).\n", psb->numpst); + dprintk("Settling Time: %d microseconds.\n", + psb->settlingtime); + dprintk("Has %d PST tables. (Only dumping ones " + "relevant to this CPU).\n", + psb->numpst); - p += sizeof (struct psb_s); + p += sizeof(struct psb_s); pst = (struct pst_s *) p; - for (j=0; j<psb->numpst; j++) { + for (j = 0; j < psb->numpst; j++) { pst = (struct pst_s *) p; number_scales = pst->numpstates; - if ((etuple == pst->cpuid) && check_fsb(pst->fsbspeed) && - (maxfid==pst->maxfid) && (startvid==pst->startvid)) - { - dprintk ("PST:%d (@%p)\n", j, pst); - dprintk (" cpuid: 0x%x fsb: %d maxFID: 0x%x startvid: 0x%x\n", - pst->cpuid, pst->fsbspeed, pst->maxfid, pst->startvid); - - ret = get_ranges ((char *) pst + sizeof (struct pst_s)); + if ((etuple == pst->cpuid) && + check_fsb(pst->fsbspeed) && + (maxfid == pst->maxfid) && + (startvid == pst->startvid)) { + print_pst_entry(pst, j); + p = (char *)pst + sizeof(struct pst_s); + ret = get_ranges(p); return ret; } else { unsigned int k; - p = (char *) pst + sizeof (struct pst_s); - for (k=0; k<number_scales; k++) - p+=2; + p = (char *)pst + sizeof(struct pst_s); + for (k = 0; k < number_scales; k++) + p += 2; } } - printk (KERN_INFO PFX "No PST tables match this cpuid (0x%x)\n", etuple); - printk (KERN_INFO PFX "This is indicative of a broken BIOS.\n"); + printk(KERN_INFO PFX "No PST tables match this cpuid " + "(0x%x)\n", etuple); + printk(KERN_INFO PFX "This is indicative of a broken " + "BIOS.\n"); return -EINVAL; } @@ -511,13 +538,14 @@ static int powernow_decode_bios (int maxfid, int startvid) } -static int powernow_target (struct cpufreq_policy *policy, +static int powernow_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { unsigned int newstate; - if (cpufreq_frequency_table_target(policy, powernow_table, target_freq, relation, &newstate)) + if (cpufreq_frequency_table_target(policy, powernow_table, target_freq, + relation, &newstate)) return -EINVAL; change_speed(newstate); @@ -526,7 +554,7 @@ static int powernow_target (struct cpufreq_policy *policy, } -static int powernow_verify (struct cpufreq_policy *policy) +static int powernow_verify(struct cpufreq_policy *policy) { return cpufreq_frequency_table_verify(policy, powernow_table); } @@ -566,18 +594,23 @@ static unsigned int powernow_get(unsigned int cpu) if (cpu) return 0; - rdmsrl (MSR_K7_FID_VID_STATUS, fidvidstatus.val); + rdmsrl(MSR_K7_FID_VID_STATUS, fidvidstatus.val); cfid = fidvidstatus.bits.CFID; - return (fsb * fid_codes[cfid] / 10); + return fsb * fid_codes[cfid] / 10; } static int __init acer_cpufreq_pst(const struct dmi_system_id *d) { - printk(KERN_WARNING "%s laptop with broken PST tables in BIOS detected.\n", d->ident); - printk(KERN_WARNING "You need to downgrade to 3A21 (09/09/2002), or try a newer BIOS than 3A71 (01/20/2003)\n"); - printk(KERN_WARNING "cpufreq scaling has been disabled as a result of this.\n"); + printk(KERN_WARNING PFX + "%s laptop with broken PST tables in BIOS detected.\n", + d->ident); + printk(KERN_WARNING PFX + "You need to downgrade to 3A21 (09/09/2002), or try a newer " + "BIOS than 3A71 (01/20/2003)\n"); + printk(KERN_WARNING PFX + "cpufreq scaling has been disabled as a result of this.\n"); return 0; } @@ -598,7 +631,7 @@ static struct dmi_system_id __initdata powernow_dmi_table[] = { { } }; -static int __init powernow_cpu_init (struct cpufreq_policy *policy) +static int __init powernow_cpu_init(struct cpufreq_policy *policy) { union msr_fidvidstatus fidvidstatus; int result; @@ -606,7 +639,7 @@ static int __init powernow_cpu_init (struct cpufreq_policy *policy) if (policy->cpu != 0) return -ENODEV; - rdmsrl (MSR_K7_FID_VID_STATUS, fidvidstatus.val); + rdmsrl(MSR_K7_FID_VID_STATUS, fidvidstatus.val); recalibrate_cpu_khz(); @@ -618,19 +651,21 @@ static int __init powernow_cpu_init (struct cpufreq_policy *policy) dprintk("FSB: %3dMHz\n", fsb/1000); if (dmi_check_system(powernow_dmi_table) || acpi_force) { - printk (KERN_INFO PFX "PSB/PST known to be broken. Trying ACPI instead\n"); + printk(KERN_INFO PFX "PSB/PST known to be broken. " + "Trying ACPI instead\n"); result = powernow_acpi_init(); } else { - result = powernow_decode_bios(fidvidstatus.bits.MFID, fidvidstatus.bits.SVID); + result = powernow_decode_bios(fidvidstatus.bits.MFID, + fidvidstatus.bits.SVID); if (result) { - printk (KERN_INFO PFX "Trying ACPI perflib\n"); + printk(KERN_INFO PFX "Trying ACPI perflib\n"); maximum_speed = 0; minimum_speed = -1; latency = 0; result = powernow_acpi_init(); if (result) { - printk (KERN_INFO PFX "ACPI and legacy methods failed\n"); - printk (KERN_INFO PFX "See http://www.codemonkey.org.uk/projects/cpufreq/powernow-k7.html\n"); + printk(KERN_INFO PFX + "ACPI and legacy methods failed\n"); } } else { /* SGTC use the bus clock as timer */ @@ -642,10 +677,11 @@ static int __init powernow_cpu_init (struct cpufreq_policy *policy) if (result) return result; - printk (KERN_INFO PFX "Minimum speed %d MHz. Maximum speed %d MHz.\n", + printk(KERN_INFO PFX "Minimum speed %d MHz. Maximum speed %d MHz.\n", minimum_speed/1000, maximum_speed/1000); - policy->cpuinfo.transition_latency = cpufreq_scale(2000000UL, fsb, latency); + policy->cpuinfo.transition_latency = + cpufreq_scale(2000000UL, fsb, latency); policy->cur = powernow_get(0); @@ -654,7 +690,8 @@ static int __init powernow_cpu_init (struct cpufreq_policy *policy) return cpufreq_frequency_table_cpuinfo(policy, powernow_table); } -static int powernow_cpu_exit (struct cpufreq_policy *policy) { +static int powernow_cpu_exit(struct cpufreq_policy *policy) +{ cpufreq_frequency_table_put_attr(policy->cpu); #ifdef CONFIG_X86_POWERNOW_K7_ACPI @@ -669,7 +706,7 @@ static int powernow_cpu_exit (struct cpufreq_policy *policy) { return 0; } -static struct freq_attr* powernow_table_attr[] = { +static struct freq_attr *powernow_table_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -685,15 +722,15 @@ static struct cpufreq_driver powernow_driver = { .attr = powernow_table_attr, }; -static int __init powernow_init (void) +static int __init powernow_init(void) { - if (check_powernow()==0) + if (check_powernow() == 0) return -ENODEV; return cpufreq_register_driver(&powernow_driver); } -static void __exit powernow_exit (void) +static void __exit powernow_exit(void) { cpufreq_unregister_driver(&powernow_driver); } @@ -701,9 +738,9 @@ static void __exit powernow_exit (void) module_param(acpi_force, int, 0444); MODULE_PARM_DESC(acpi_force, "Force ACPI to be used."); -MODULE_AUTHOR ("Dave Jones <davej@redhat.com>"); -MODULE_DESCRIPTION ("Powernow driver for AMD K7 processors."); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Dave Jones <davej@redhat.com>"); +MODULE_DESCRIPTION("Powernow driver for AMD K7 processors."); +MODULE_LICENSE("GPL"); late_initcall(powernow_init); module_exit(powernow_exit); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 6428aa1..4709ead 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -33,16 +33,14 @@ #include <linux/string.h> #include <linux/cpumask.h> #include <linux/sched.h> /* for current / set_cpus_allowed() */ +#include <linux/io.h> +#include <linux/delay.h> #include <asm/msr.h> -#include <asm/io.h> -#include <asm/delay.h> -#ifdef CONFIG_X86_POWERNOW_K8_ACPI #include <linux/acpi.h> #include <linux/mutex.h> #include <acpi/processor.h> -#endif #define PFX "powernow-k8: " #define VERSION "version 2.20.00" @@ -56,7 +54,10 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data); static int cpu_family = CPU_OPTERON; #ifndef CONFIG_SMP -DEFINE_PER_CPU(cpumask_t, cpu_core_map); +static inline const struct cpumask *cpu_core_mask(int cpu) +{ + return cpumask_of(0); +} #endif /* Return a frequency in MHz, given an input fid */ @@ -71,7 +72,8 @@ static u32 find_khz_freq_from_fid(u32 fid) return 1000 * find_freq_from_fid(fid); } -static u32 find_khz_freq_from_pstate(struct cpufreq_frequency_table *data, u32 pstate) +static u32 find_khz_freq_from_pstate(struct cpufreq_frequency_table *data, + u32 pstate) { return data[pstate].frequency; } @@ -186,7 +188,9 @@ static int write_new_fid(struct powernow_k8_data *data, u32 fid) return 1; } - lo = fid | (data->currvid << MSR_C_LO_VID_SHIFT) | MSR_C_LO_INIT_FID_VID; + lo = fid; + lo |= (data->currvid << MSR_C_LO_VID_SHIFT); + lo |= MSR_C_LO_INIT_FID_VID; dprintk("writing fid 0x%x, lo 0x%x, hi 0x%x\n", fid, lo, data->plllock * PLL_LOCK_CONVERSION); @@ -194,7 +198,9 @@ static int write_new_fid(struct powernow_k8_data *data, u32 fid) do { wrmsr(MSR_FIDVID_CTL, lo, data->plllock * PLL_LOCK_CONVERSION); if (i++ > 100) { - printk(KERN_ERR PFX "Hardware error - pending bit very stuck - no further pstate changes possible\n"); + printk(KERN_ERR PFX + "Hardware error - pending bit very stuck - " + "no further pstate changes possible\n"); return 1; } } while (query_current_values_with_pending_wait(data)); @@ -202,14 +208,16 @@ static int write_new_fid(struct powernow_k8_data *data, u32 fid) count_off_irt(data); if (savevid != data->currvid) { - printk(KERN_ERR PFX "vid change on fid trans, old 0x%x, new 0x%x\n", - savevid, data->currvid); + printk(KERN_ERR PFX + "vid change on fid trans, old 0x%x, new 0x%x\n", + savevid, data->currvid); return 1; } if (fid != data->currfid) { - printk(KERN_ERR PFX "fid trans failed, fid 0x%x, curr 0x%x\n", fid, - data->currfid); + printk(KERN_ERR PFX + "fid trans failed, fid 0x%x, curr 0x%x\n", fid, + data->currfid); return 1; } @@ -228,7 +236,9 @@ static int write_new_vid(struct powernow_k8_data *data, u32 vid) return 1; } - lo = data->currfid | (vid << MSR_C_LO_VID_SHIFT) | MSR_C_LO_INIT_FID_VID; + lo = data->currfid; + lo |= (vid << MSR_C_LO_VID_SHIFT); + lo |= MSR_C_LO_INIT_FID_VID; dprintk("writing vid 0x%x, lo 0x%x, hi 0x%x\n", vid, lo, STOP_GRANT_5NS); @@ -236,20 +246,24 @@ static int write_new_vid(struct powernow_k8_data *data, u32 vid) do { wrmsr(MSR_FIDVID_CTL, lo, STOP_GRANT_5NS); if (i++ > 100) { - printk(KERN_ERR PFX "internal error - pending bit very stuck - no further pstate changes possible\n"); + printk(KERN_ERR PFX "internal error - pending bit " + "very stuck - no further pstate " + "changes possible\n"); return 1; } } while (query_current_values_with_pending_wait(data)); if (savefid != data->currfid) { - printk(KERN_ERR PFX "fid changed on vid trans, old 0x%x new 0x%x\n", + printk(KERN_ERR PFX "fid changed on vid trans, old " + "0x%x new 0x%x\n", savefid, data->currfid); return 1; } if (vid != data->currvid) { - printk(KERN_ERR PFX "vid trans failed, vid 0x%x, curr 0x%x\n", vid, - data->currvid); + printk(KERN_ERR PFX "vid trans failed, vid 0x%x, " + "curr 0x%x\n", + vid, data->currvid); return 1; } @@ -261,7 +275,8 @@ static int write_new_vid(struct powernow_k8_data *data, u32 vid) * Decreasing vid codes represent increasing voltages: * vid of 0 is 1.550V, vid of 0x1e is 0.800V, vid of VID_OFF is off. */ -static int decrease_vid_code_by_step(struct powernow_k8_data *data, u32 reqvid, u32 step) +static int decrease_vid_code_by_step(struct powernow_k8_data *data, + u32 reqvid, u32 step) { if ((data->currvid - reqvid) > step) reqvid = data->currvid - step; @@ -283,7 +298,8 @@ static int transition_pstate(struct powernow_k8_data *data, u32 pstate) } /* Change Opteron/Athlon64 fid and vid, by the 3 phases. */ -static int transition_fid_vid(struct powernow_k8_data *data, u32 reqfid, u32 reqvid) +static int transition_fid_vid(struct powernow_k8_data *data, + u32 reqfid, u32 reqvid) { if (core_voltage_pre_transition(data, reqvid)) return 1; @@ -298,7 +314,8 @@ static int transition_fid_vid(struct powernow_k8_data *data, u32 reqfid, u32 req return 1; if ((reqfid != data->currfid) || (reqvid != data->currvid)) { - printk(KERN_ERR PFX "failed (cpu%d): req 0x%x 0x%x, curr 0x%x 0x%x\n", + printk(KERN_ERR PFX "failed (cpu%d): req 0x%x 0x%x, " + "curr 0x%x 0x%x\n", smp_processor_id(), reqfid, reqvid, data->currfid, data->currvid); return 1; @@ -311,13 +328,15 @@ static int transition_fid_vid(struct powernow_k8_data *data, u32 reqfid, u32 req } /* Phase 1 - core voltage transition ... setup voltage */ -static int core_voltage_pre_transition(struct powernow_k8_data *data, u32 reqvid) +static int core_voltage_pre_transition(struct powernow_k8_data *data, + u32 reqvid) { u32 rvosteps = data->rvo; u32 savefid = data->currfid; u32 maxvid, lo; - dprintk("ph1 (cpu%d): start, currfid 0x%x, currvid 0x%x, reqvid 0x%x, rvo 0x%x\n", + dprintk("ph1 (cpu%d): start, currfid 0x%x, currvid 0x%x, " + "reqvid 0x%x, rvo 0x%x\n", smp_processor_id(), data->currfid, data->currvid, reqvid, data->rvo); @@ -340,7 +359,7 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data, u32 reqvid } else { dprintk("ph1: changing vid for rvo, req 0x%x\n", data->currvid - 1); - if (decrease_vid_code_by_step(data, data->currvid - 1, 1)) + if (decrease_vid_code_by_step(data, data->currvid-1, 1)) return 1; rvosteps--; } @@ -350,7 +369,8 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data, u32 reqvid return 1; if (savefid != data->currfid) { - printk(KERN_ERR PFX "ph1 err, currfid changed 0x%x\n", data->currfid); + printk(KERN_ERR PFX "ph1 err, currfid changed 0x%x\n", + data->currfid); return 1; } @@ -363,20 +383,24 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data, u32 reqvid /* Phase 2 - core frequency transition */ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid) { - u32 vcoreqfid, vcocurrfid, vcofiddiff, fid_interval, savevid = data->currvid; + u32 vcoreqfid, vcocurrfid, vcofiddiff; + u32 fid_interval, savevid = data->currvid; - if ((reqfid < HI_FID_TABLE_BOTTOM) && (data->currfid < HI_FID_TABLE_BOTTOM)) { - printk(KERN_ERR PFX "ph2: illegal lo-lo transition 0x%x 0x%x\n", - reqfid, data->currfid); + if ((reqfid < HI_FID_TABLE_BOTTOM) && + (data->currfid < HI_FID_TABLE_BOTTOM)) { + printk(KERN_ERR PFX "ph2: illegal lo-lo transition " + "0x%x 0x%x\n", reqfid, data->currfid); return 1; } if (data->currfid == reqfid) { - printk(KERN_ERR PFX "ph2 null fid transition 0x%x\n", data->currfid); + printk(KERN_ERR PFX "ph2 null fid transition 0x%x\n", + data->currfid); return 0; } - dprintk("ph2 (cpu%d): starting, currfid 0x%x, currvid 0x%x, reqfid 0x%x\n", + dprintk("ph2 (cpu%d): starting, currfid 0x%x, currvid 0x%x, " + "reqfid 0x%x\n", smp_processor_id(), data->currfid, data->currvid, reqfid); @@ -390,14 +414,14 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid) if (reqfid > data->currfid) { if (data->currfid > LO_FID_TABLE_TOP) { - if (write_new_fid(data, data->currfid + fid_interval)) { + if (write_new_fid(data, + data->currfid + fid_interval)) return 1; - } } else { if (write_new_fid - (data, 2 + convert_fid_to_vco_fid(data->currfid))) { + (data, + 2 + convert_fid_to_vco_fid(data->currfid))) return 1; - } } } else { if (write_new_fid(data, data->currfid - fid_interval)) @@ -417,7 +441,8 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid) if (data->currfid != reqfid) { printk(KERN_ERR PFX - "ph2: mismatch, failed fid transition, curr 0x%x, req 0x%x\n", + "ph2: mismatch, failed fid transition, " + "curr 0x%x, req 0x%x\n", data->currfid, reqfid); return 1; } @@ -435,7 +460,8 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid) } /* Phase 3 - core voltage transition flow ... jump to the final vid. */ -static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvid) +static int core_voltage_post_transition(struct powernow_k8_data *data, + u32 reqvid) { u32 savefid = data->currfid; u32 savereqvid = reqvid; @@ -457,7 +483,8 @@ static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvi if (data->currvid != reqvid) { printk(KERN_ERR PFX - "ph3: failed vid transition\n, req 0x%x, curr 0x%x", + "ph3: failed vid transition\n, " + "req 0x%x, curr 0x%x", reqvid, data->currvid); return 1; } @@ -508,7 +535,8 @@ static int check_supported_cpu(unsigned int cpu) if ((eax & CPUID_XFAM) == CPUID_XFAM_K8) { if (((eax & CPUID_USE_XFAM_XMOD) != CPUID_USE_XFAM_XMOD) || ((eax & CPUID_XMOD) > CPUID_XMOD_REV_MASK)) { - printk(KERN_INFO PFX "Processor cpuid %x not supported\n", eax); + printk(KERN_INFO PFX + "Processor cpuid %x not supported\n", eax); goto out; } @@ -520,8 +548,10 @@ static int check_supported_cpu(unsigned int cpu) } cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx); - if ((edx & P_STATE_TRANSITION_CAPABLE) != P_STATE_TRANSITION_CAPABLE) { - printk(KERN_INFO PFX "Power state transitions not supported\n"); + if ((edx & P_STATE_TRANSITION_CAPABLE) + != P_STATE_TRANSITION_CAPABLE) { + printk(KERN_INFO PFX + "Power state transitions not supported\n"); goto out; } } else { /* must be a HW Pstate capable processor */ @@ -539,7 +569,8 @@ out: return rc; } -static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst, u8 maxvid) +static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst, + u8 maxvid) { unsigned int j; u8 lastfid = 0xff; @@ -550,12 +581,14 @@ static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst, u8 j, pst[j].vid); return -EINVAL; } - if (pst[j].vid < data->rvo) { /* vid + rvo >= 0 */ + if (pst[j].vid < data->rvo) { + /* vid + rvo >= 0 */ printk(KERN_ERR FW_BUG PFX "0 vid exceeded with pstate" " %d\n", j); return -ENODEV; } - if (pst[j].vid < maxvid + data->rvo) { /* vid + rvo >= maxvid */ + if (pst[j].vid < maxvid + data->rvo) { + /* vid + rvo >= maxvid */ printk(KERN_ERR FW_BUG PFX "maxvid exceeded with pstate" " %d\n", j); return -ENODEV; @@ -579,23 +612,31 @@ static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst, u8 return -EINVAL; } if (lastfid > LO_FID_TABLE_TOP) - printk(KERN_INFO FW_BUG PFX "first fid not from lo freq table\n"); + printk(KERN_INFO FW_BUG PFX + "first fid not from lo freq table\n"); return 0; } +static void invalidate_entry(struct powernow_k8_data *data, unsigned int entry) +{ + data->powernow_table[entry].frequency = CPUFREQ_ENTRY_INVALID; +} + static void print_basics(struct powernow_k8_data *data) { int j; for (j = 0; j < data->numps; j++) { - if (data->powernow_table[j].frequency != CPUFREQ_ENTRY_INVALID) { + if (data->powernow_table[j].frequency != + CPUFREQ_ENTRY_INVALID) { if (cpu_family == CPU_HW_PSTATE) { - printk(KERN_INFO PFX " %d : pstate %d (%d MHz)\n", - j, + printk(KERN_INFO PFX + " %d : pstate %d (%d MHz)\n", j, data->powernow_table[j].index, data->powernow_table[j].frequency/1000); } else { - printk(KERN_INFO PFX " %d : fid 0x%x (%d MHz), vid 0x%x\n", + printk(KERN_INFO PFX + " %d : fid 0x%x (%d MHz), vid 0x%x\n", j, data->powernow_table[j].index & 0xff, data->powernow_table[j].frequency/1000, @@ -604,20 +645,25 @@ static void print_basics(struct powernow_k8_data *data) } } if (data->batps) - printk(KERN_INFO PFX "Only %d pstates on battery\n", data->batps); + printk(KERN_INFO PFX "Only %d pstates on battery\n", + data->batps); } -static int fill_powernow_table(struct powernow_k8_data *data, struct pst_s *pst, u8 maxvid) +static int fill_powernow_table(struct powernow_k8_data *data, + struct pst_s *pst, u8 maxvid) { struct cpufreq_frequency_table *powernow_table; unsigned int j; - if (data->batps) { /* use ACPI support to get full speed on mains power */ - printk(KERN_WARNING PFX "Only %d pstates usable (use ACPI driver for full range\n", data->batps); + if (data->batps) { + /* use ACPI support to get full speed on mains power */ + printk(KERN_WARNING PFX + "Only %d pstates usable (use ACPI driver for full " + "range\n", data->batps); data->numps = data->batps; } - for ( j=1; j<data->numps; j++ ) { + for (j = 1; j < data->numps; j++) { if (pst[j-1].fid >= pst[j].fid) { printk(KERN_ERR PFX "PST out of sequence\n"); return -EINVAL; @@ -640,9 +686,11 @@ static int fill_powernow_table(struct powernow_k8_data *data, struct pst_s *pst, } for (j = 0; j < data->numps; j++) { + int freq; powernow_table[j].index = pst[j].fid; /* lower 8 bits */ powernow_table[j].index |= (pst[j].vid << 8); /* upper 8 bits */ - powernow_table[j].frequency = find_khz_freq_from_fid(pst[j].fid); + freq = find_khz_freq_from_fid(pst[j].fid); + powernow_table[j].frequency = freq; } powernow_table[data->numps].frequency = CPUFREQ_TABLE_END; powernow_table[data->numps].index = 0; @@ -654,11 +702,12 @@ static int fill_powernow_table(struct powernow_k8_data *data, struct pst_s *pst, dprintk("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid); data->powernow_table = powernow_table; - if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu) + if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu) print_basics(data); for (j = 0; j < data->numps; j++) - if ((pst[j].fid==data->currfid) && (pst[j].vid==data->currvid)) + if ((pst[j].fid == data->currfid) && + (pst[j].vid == data->currvid)) return 0; dprintk("currfid/vid do not match PST, ignoring\n"); @@ -698,7 +747,8 @@ static int find_psb_table(struct powernow_k8_data *data) } data->vstable = psb->vstable; - dprintk("voltage stabilization time: %d(*20us)\n", data->vstable); + dprintk("voltage stabilization time: %d(*20us)\n", + data->vstable); dprintk("flags2: 0x%x\n", psb->flags2); data->rvo = psb->flags2 & 3; @@ -713,11 +763,12 @@ static int find_psb_table(struct powernow_k8_data *data) dprintk("numpst: 0x%x\n", psb->num_tables); cpst = psb->num_tables; - if ((psb->cpuid == 0x00000fc0) || (psb->cpuid == 0x00000fe0) ){ + if ((psb->cpuid == 0x00000fc0) || + (psb->cpuid == 0x00000fe0)) { thiscpuid = cpuid_eax(CPUID_PROCESSOR_SIGNATURE); - if ((thiscpuid == 0x00000fc0) || (thiscpuid == 0x00000fe0) ) { + if ((thiscpuid == 0x00000fc0) || + (thiscpuid == 0x00000fe0)) cpst = 1; - } } if (cpst != 1) { printk(KERN_ERR FW_BUG PFX "numpst must be 1\n"); @@ -732,7 +783,8 @@ static int find_psb_table(struct powernow_k8_data *data) data->numps = psb->numps; dprintk("numpstates: 0x%x\n", data->numps); - return fill_powernow_table(data, (struct pst_s *)(psb+1), maxvid); + return fill_powernow_table(data, + (struct pst_s *)(psb+1), maxvid); } /* * If you see this message, complain to BIOS manufacturer. If @@ -745,28 +797,31 @@ static int find_psb_table(struct powernow_k8_data *data) * BIOS and Kernel Developer's Guide, which is available on * www.amd.com */ - printk(KERN_ERR PFX "BIOS error - no PSB or ACPI _PSS objects\n"); + printk(KERN_ERR FW_BUG PFX "No PSB or ACPI _PSS objects\n"); return -ENODEV; } -#ifdef CONFIG_X86_POWERNOW_K8_ACPI -static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index) +static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, + unsigned int index) { + acpi_integer control; + if (!data->acpi_data.state_count || (cpu_family == CPU_HW_PSTATE)) return; - data->irt = (data->acpi_data.states[index].control >> IRT_SHIFT) & IRT_MASK; - data->rvo = (data->acpi_data.states[index].control >> RVO_SHIFT) & RVO_MASK; - data->exttype = (data->acpi_data.states[index].control >> EXT_TYPE_SHIFT) & EXT_TYPE_MASK; - data->plllock = (data->acpi_data.states[index].control >> PLL_L_SHIFT) & PLL_L_MASK; - data->vidmvs = 1 << ((data->acpi_data.states[index].control >> MVS_SHIFT) & MVS_MASK); - data->vstable = (data->acpi_data.states[index].control >> VST_SHIFT) & VST_MASK; -} + control = data->acpi_data.states[index].control; data->irt = (control + >> IRT_SHIFT) & IRT_MASK; data->rvo = (control >> + RVO_SHIFT) & RVO_MASK; data->exttype = (control + >> EXT_TYPE_SHIFT) & EXT_TYPE_MASK; + data->plllock = (control >> PLL_L_SHIFT) & PLL_L_MASK; data->vidmvs = 1 + << ((control >> MVS_SHIFT) & MVS_MASK); data->vstable = + (control >> VST_SHIFT) & VST_MASK; } static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) { struct cpufreq_frequency_table *powernow_table; int ret_val = -ENODEV; + acpi_integer space_id; if (acpi_processor_register_performance(&data->acpi_data, data->cpu)) { dprintk("register performance failed: bad ACPI data\n"); @@ -779,11 +834,12 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) goto err_out; } - if ((data->acpi_data.control_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) || - (data->acpi_data.status_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) { + space_id = data->acpi_data.control_register.space_id; + if ((space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) || + (space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) { dprintk("Invalid control/status registers (%x - %x)\n", data->acpi_data.control_register.space_id, - data->acpi_data.status_register.space_id); + space_id); goto err_out; } @@ -802,13 +858,14 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) if (ret_val) goto err_out_mem; - powernow_table[data->acpi_data.state_count].frequency = CPUFREQ_TABLE_END; + powernow_table[data->acpi_data.state_count].frequency = + CPUFREQ_TABLE_END; powernow_table[data->acpi_data.state_count].index = 0; data->powernow_table = powernow_table; /* fill in data */ data->numps = data->acpi_data.state_count; - if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu) + if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu) print_basics(data); powernow_k8_acpi_pst_values(data, 0); @@ -830,13 +887,15 @@ err_out_mem: err_out: acpi_processor_unregister_performance(&data->acpi_data, data->cpu); - /* data->acpi_data.state_count informs us at ->exit() whether ACPI was used */ + /* data->acpi_data.state_count informs us at ->exit() + * whether ACPI was used */ data->acpi_data.state_count = 0; return ret_val; } -static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table) +static int fill_powernow_table_pstate(struct powernow_k8_data *data, + struct cpufreq_frequency_table *powernow_table) { int i; u32 hi = 0, lo = 0; @@ -848,84 +907,101 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpuf index = data->acpi_data.states[i].control & HW_PSTATE_MASK; if (index > data->max_hw_pstate) { - printk(KERN_ERR PFX "invalid pstate %d - bad value %d.\n", i, index); - printk(KERN_ERR PFX "Please report to BIOS manufacturer\n"); - powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; + printk(KERN_ERR PFX "invalid pstate %d - " + "bad value %d.\n", i, index); + printk(KERN_ERR PFX "Please report to BIOS " + "manufacturer\n"); + invalidate_entry(data, i); continue; } rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi); if (!(hi & HW_PSTATE_VALID_MASK)) { dprintk("invalid pstate %d, ignoring\n", index); - powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; + invalidate_entry(data, i); continue; } powernow_table[i].index = index; - powernow_table[i].frequency = data->acpi_data.states[i].core_frequency * 1000; + powernow_table[i].frequency = + data->acpi_data.states[i].core_frequency * 1000; } return 0; } -static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table) +static int fill_powernow_table_fidvid(struct powernow_k8_data *data, + struct cpufreq_frequency_table *powernow_table) { int i; int cntlofreq = 0; + for (i = 0; i < data->acpi_data.state_count; i++) { u32 fid; u32 vid; + u32 freq, index; + acpi_integer status, control; if (data->exttype) { - fid = data->acpi_data.states[i].status & EXT_FID_MASK; - vid = (data->acpi_data.states[i].status >> VID_SHIFT) & EXT_VID_MASK; + status = data->acpi_data.states[i].status; + fid = status & EXT_FID_MASK; + vid = (status >> VID_SHIFT) & EXT_VID_MASK; } else { - fid = data->acpi_data.states[i].control & FID_MASK; - vid = (data->acpi_data.states[i].control >> VID_SHIFT) & VID_MASK; + control = data->acpi_data.states[i].control; + fid = control & FID_MASK; + vid = (control >> VID_SHIFT) & VID_MASK; } dprintk(" %d : fid 0x%x, vid 0x%x\n", i, fid, vid); - powernow_table[i].index = fid; /* lower 8 bits */ - powernow_table[i].index |= (vid << 8); /* upper 8 bits */ - powernow_table[i].frequency = find_khz_freq_from_fid(fid); + index = fid | (vid<<8); + powernow_table[i].index = index; + + freq = find_khz_freq_from_fid(fid); + powernow_table[i].frequency = freq; /* verify frequency is OK */ - if ((powernow_table[i].frequency > (MAX_FREQ * 1000)) || - (powernow_table[i].frequency < (MIN_FREQ * 1000))) { - dprintk("invalid freq %u kHz, ignoring\n", powernow_table[i].frequency); - powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; + if ((freq > (MAX_FREQ * 1000)) || (freq < (MIN_FREQ * 1000))) { + dprintk("invalid freq %u kHz, ignoring\n", freq); + invalidate_entry(data, i); continue; } - /* verify voltage is OK - BIOSs are using "off" to indicate invalid */ + /* verify voltage is OK - + * BIOSs are using "off" to indicate invalid */ if (vid == VID_OFF) { dprintk("invalid vid %u, ignoring\n", vid); - powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; + invalidate_entry(data, i); continue; } /* verify only 1 entry from the lo frequency table */ if (fid < HI_FID_TABLE_BOTTOM) { if (cntlofreq) { - /* if both entries are the same, ignore this one ... */ - if ((powernow_table[i].frequency != powernow_table[cntlofreq].frequency) || - (powernow_table[i].index != powernow_table[cntlofreq].index)) { - printk(KERN_ERR PFX "Too many lo freq table entries\n"); + /* if both entries are the same, + * ignore this one ... */ + if ((freq != powernow_table[cntlofreq].frequency) || + (index != powernow_table[cntlofreq].index)) { + printk(KERN_ERR PFX + "Too many lo freq table " + "entries\n"); return 1; } - dprintk("double low frequency table entry, ignoring it.\n"); - powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; + dprintk("double low frequency table entry, " + "ignoring it.\n"); + invalidate_entry(data, i); continue; } else cntlofreq = i; } - if (powernow_table[i].frequency != (data->acpi_data.states[i].core_frequency * 1000)) { - printk(KERN_INFO PFX "invalid freq entries %u kHz vs. %u kHz\n", - powernow_table[i].frequency, - (unsigned int) (data->acpi_data.states[i].core_frequency * 1000)); - powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; + if (freq != (data->acpi_data.states[i].core_frequency * 1000)) { + printk(KERN_INFO PFX "invalid freq entries " + "%u kHz vs. %u kHz\n", freq, + (unsigned int) + (data->acpi_data.states[i].core_frequency + * 1000)); + invalidate_entry(data, i); continue; } } @@ -935,7 +1011,8 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpuf static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) { if (data->acpi_data.state_count) - acpi_processor_unregister_performance(&data->acpi_data, data->cpu); + acpi_processor_unregister_performance(&data->acpi_data, + data->cpu); free_cpumask_var(data->acpi_data.shared_cpu_map); } @@ -953,15 +1030,9 @@ static int get_transition_latency(struct powernow_k8_data *data) return 1000 * max_latency; } -#else -static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) { return -ENODEV; } -static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) { return; } -static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index) { return; } -static int get_transition_latency(struct powernow_k8_data *data) { return 0; } -#endif /* CONFIG_X86_POWERNOW_K8_ACPI */ - /* Take a frequency, and issue the fid/vid transition command */ -static int transition_frequency_fidvid(struct powernow_k8_data *data, unsigned int index) +static int transition_frequency_fidvid(struct powernow_k8_data *data, + unsigned int index) { u32 fid = 0; u32 vid = 0; @@ -989,7 +1060,8 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data, unsigned i return 0; } - if ((fid < HI_FID_TABLE_BOTTOM) && (data->currfid < HI_FID_TABLE_BOTTOM)) { + if ((fid < HI_FID_TABLE_BOTTOM) && + (data->currfid < HI_FID_TABLE_BOTTOM)) { printk(KERN_ERR PFX "ignoring illegal change in lo freq table-%x to 0x%x\n", data->currfid, fid); @@ -1017,7 +1089,8 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data, unsigned i } /* Take a frequency, and issue the hardware pstate transition command */ -static int transition_frequency_pstate(struct powernow_k8_data *data, unsigned int index) +static int transition_frequency_pstate(struct powernow_k8_data *data, + unsigned int index) { u32 pstate = 0; int res, i; @@ -1029,7 +1102,8 @@ static int transition_frequency_pstate(struct powernow_k8_data *data, unsigned i pstate = index & HW_PSTATE_MASK; if (pstate > data->max_hw_pstate) return 0; - freqs.old = find_khz_freq_from_pstate(data->powernow_table, data->currpstate); + freqs.old = find_khz_freq_from_pstate(data->powernow_table, + data->currpstate); freqs.new = find_khz_freq_from_pstate(data->powernow_table, pstate); for_each_cpu_mask_nr(i, *(data->available_cores)) { @@ -1048,7 +1122,8 @@ static int transition_frequency_pstate(struct powernow_k8_data *data, unsigned i } /* Driver entry point to switch to the target frequency */ -static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsigned relation) +static int powernowk8_target(struct cpufreq_policy *pol, + unsigned targfreq, unsigned relation) { cpumask_t oldmask; struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu); @@ -1087,14 +1162,18 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi dprintk("targ: curr fid 0x%x, vid 0x%x\n", data->currfid, data->currvid); - if ((checkvid != data->currvid) || (checkfid != data->currfid)) { + if ((checkvid != data->currvid) || + (checkfid != data->currfid)) { printk(KERN_INFO PFX - "error - out of sync, fix 0x%x 0x%x, vid 0x%x 0x%x\n", - checkfid, data->currfid, checkvid, data->currvid); + "error - out of sync, fix 0x%x 0x%x, " + "vid 0x%x 0x%x\n", + checkfid, data->currfid, + checkvid, data->currvid); } } - if (cpufreq_frequency_table_target(pol, data->powernow_table, targfreq, relation, &newstate)) + if (cpufreq_frequency_table_target(pol, data->powernow_table, + targfreq, relation, &newstate)) goto err_out; mutex_lock(&fidvid_mutex); @@ -1114,7 +1193,8 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi mutex_unlock(&fidvid_mutex); if (cpu_family == CPU_HW_PSTATE) - pol->cur = find_khz_freq_from_pstate(data->powernow_table, newstate); + pol->cur = find_khz_freq_from_pstate(data->powernow_table, + newstate); else pol->cur = find_khz_freq_from_fid(data->currfid); ret = 0; @@ -1141,6 +1221,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) struct powernow_k8_data *data; cpumask_t oldmask; int rc; + static int print_once; if (!cpu_online(pol->cpu)) return -ENODEV; @@ -1163,33 +1244,31 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) * an UP version, and is deprecated by AMD. */ if (num_online_cpus() != 1) { -#ifndef CONFIG_ACPI_PROCESSOR - printk(KERN_ERR PFX "ACPI Processor support is required " - "for SMP systems but is absent. Please load the " - "ACPI Processor module before starting this " - "driver.\n"); -#else - printk(KERN_ERR FW_BUG PFX "Your BIOS does not provide" - " ACPI _PSS objects in a way that Linux " - "understands. Please report this to the Linux " - "ACPI maintainers and complain to your BIOS " - "vendor.\n"); -#endif - kfree(data); - return -ENODEV; + /* + * Replace this one with print_once as soon as such a + * thing gets introduced + */ + if (!print_once) { + WARN_ONCE(1, KERN_ERR FW_BUG PFX "Your BIOS " + "does not provide ACPI _PSS objects " + "in a way that Linux understands. " + "Please report this to the Linux ACPI" + " maintainers and complain to your " + "BIOS vendor.\n"); + print_once++; + } + goto err_out; } if (pol->cpu != 0) { printk(KERN_ERR FW_BUG PFX "No ACPI _PSS objects for " "CPU other than CPU0. Complain to your BIOS " "vendor.\n"); - kfree(data); - return -ENODEV; + goto err_out; } rc = find_psb_table(data); - if (rc) { - kfree(data); - return -ENODEV; - } + if (rc) + goto err_out; + /* Take a crude guess here. * That guess was in microseconds, so multiply with 1000 */ pol->cpuinfo.transition_latency = ( @@ -1204,16 +1283,16 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) if (smp_processor_id() != pol->cpu) { printk(KERN_ERR PFX "limiting to cpu %u failed\n", pol->cpu); - goto err_out; + goto err_out_unmask; } if (pending_bit_stuck()) { printk(KERN_ERR PFX "failing init, change pending bit set\n"); - goto err_out; + goto err_out_unmask; } if (query_current_values_with_pending_wait(data)) - goto err_out; + goto err_out_unmask; if (cpu_family == CPU_OPTERON) fidvid_msr_init(); @@ -1224,11 +1303,12 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) if (cpu_family == CPU_HW_PSTATE) cpumask_copy(pol->cpus, cpumask_of(pol->cpu)); else - cpumask_copy(pol->cpus, &per_cpu(cpu_core_map, pol->cpu)); + cpumask_copy(pol->cpus, cpu_core_mask(pol->cpu)); data->available_cores = pol->cpus; if (cpu_family == CPU_HW_PSTATE) - pol->cur = find_khz_freq_from_pstate(data->powernow_table, data->currpstate); + pol->cur = find_khz_freq_from_pstate(data->powernow_table, + data->currpstate); else pol->cur = find_khz_freq_from_fid(data->currfid); dprintk("policy current frequency %d kHz\n", pol->cur); @@ -1245,7 +1325,8 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) cpufreq_frequency_table_get_attr(data->powernow_table, pol->cpu); if (cpu_family == CPU_HW_PSTATE) - dprintk("cpu_init done, current pstate 0x%x\n", data->currpstate); + dprintk("cpu_init done, current pstate 0x%x\n", + data->currpstate); else dprintk("cpu_init done, current fid 0x%x, vid 0x%x\n", data->currfid, data->currvid); @@ -1254,15 +1335,16 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) return 0; -err_out: +err_out_unmask: set_cpus_allowed_ptr(current, &oldmask); powernow_k8_cpu_exit_acpi(data); +err_out: kfree(data); return -ENODEV; } -static int __devexit powernowk8_cpu_exit (struct cpufreq_policy *pol) +static int __devexit powernowk8_cpu_exit(struct cpufreq_policy *pol) { struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu); @@ -1279,14 +1361,14 @@ static int __devexit powernowk8_cpu_exit (struct cpufreq_policy *pol) return 0; } -static unsigned int powernowk8_get (unsigned int cpu) +static unsigned int powernowk8_get(unsigned int cpu) { struct powernow_k8_data *data; cpumask_t oldmask = current->cpus_allowed; unsigned int khz = 0; unsigned int first; - first = first_cpu(per_cpu(cpu_core_map, cpu)); + first = cpumask_first(cpu_core_mask(cpu)); data = per_cpu(powernow_data, first); if (!data) @@ -1315,7 +1397,7 @@ out: return khz; } -static struct freq_attr* powernow_k8_attr[] = { +static struct freq_attr *powernow_k8_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -1360,7 +1442,8 @@ static void __exit powernowk8_exit(void) cpufreq_unregister_driver(&cpufreq_amd64_driver); } -MODULE_AUTHOR("Paul Devriendt <paul.devriendt@amd.com> and Mark Langsdorf <mark.langsdorf@amd.com>"); +MODULE_AUTHOR("Paul Devriendt <paul.devriendt@amd.com> and " + "Mark Langsdorf <mark.langsdorf@amd.com>"); MODULE_DESCRIPTION("AMD Athlon 64 and Opteron processor frequency driver."); MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h index 8ecc75b..6c6698f 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h @@ -45,11 +45,10 @@ struct powernow_k8_data { * frequency is in kHz */ struct cpufreq_frequency_table *powernow_table; -#ifdef CONFIG_X86_POWERNOW_K8_ACPI /* the acpi table needs to be kept. it's only available if ACPI was * used to determine valid frequency/vid/fid states */ struct acpi_processor_performance acpi_data; -#endif + /* we need to keep track of associated cores, but let cpufreq * handle hotplug events - so just point at cpufreq pol->cpus * structure */ @@ -222,10 +221,8 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid); static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index); -#ifdef CONFIG_X86_POWERNOW_K8_ACPI static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table); static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table); -#endif #ifdef CONFIG_SMP static inline void define_siblings(int cpu, cpumask_t cpu_sharedcore_mask[]) diff --git a/arch/x86/kernel/cpu/cpufreq/sc520_freq.c b/arch/x86/kernel/cpu/cpufreq/sc520_freq.c index 42da9bd..435a996 100644 --- a/arch/x86/kernel/cpu/cpufreq/sc520_freq.c +++ b/arch/x86/kernel/cpu/cpufreq/sc520_freq.c @@ -19,17 +19,19 @@ #include <linux/delay.h> #include <linux/cpufreq.h> +#include <linux/timex.h> +#include <linux/io.h> #include <asm/msr.h> -#include <asm/timex.h> -#include <asm/io.h> #define MMCR_BASE 0xfffef000 /* The default base address */ #define OFFS_CPUCTL 0x2 /* CPU Control Register */ static __u8 __iomem *cpuctl; -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "sc520_freq", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "sc520_freq", msg) +#define PFX "sc520_freq: " static struct cpufreq_frequency_table sc520_freq_table[] = { {0x01, 100000}, @@ -43,7 +45,8 @@ static unsigned int sc520_freq_get_cpu_frequency(unsigned int cpu) switch (clockspeed_reg & 0x03) { default: - printk(KERN_ERR "sc520_freq: error: cpuctl register has unexpected value %02x\n", clockspeed_reg); + printk(KERN_ERR PFX "error: cpuctl register has unexpected " + "value %02x\n", clockspeed_reg); case 0x01: return 100000; case 0x02: @@ -51,7 +54,7 @@ static unsigned int sc520_freq_get_cpu_frequency(unsigned int cpu) } } -static void sc520_freq_set_cpu_state (unsigned int state) +static void sc520_freq_set_cpu_state(unsigned int state) { struct cpufreq_freqs freqs; @@ -76,18 +79,19 @@ static void sc520_freq_set_cpu_state (unsigned int state) cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); }; -static int sc520_freq_verify (struct cpufreq_policy *policy) +static int sc520_freq_verify(struct cpufreq_policy *policy) { return cpufreq_frequency_table_verify(policy, &sc520_freq_table[0]); } -static int sc520_freq_target (struct cpufreq_policy *policy, +static int sc520_freq_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { unsigned int newstate = 0; - if (cpufreq_frequency_table_target(policy, sc520_freq_table, target_freq, relation, &newstate)) + if (cpufreq_frequency_table_target(policy, sc520_freq_table, + target_freq, relation, &newstate)) return -EINVAL; sc520_freq_set_cpu_state(newstate); @@ -116,7 +120,7 @@ static int sc520_freq_cpu_init(struct cpufreq_policy *policy) result = cpufreq_frequency_table_cpuinfo(policy, sc520_freq_table); if (result) - return (result); + return result; cpufreq_frequency_table_get_attr(sc520_freq_table, policy->cpu); @@ -131,7 +135,7 @@ static int sc520_freq_cpu_exit(struct cpufreq_policy *policy) } -static struct freq_attr* sc520_freq_attr[] = { +static struct freq_attr *sc520_freq_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -155,13 +159,13 @@ static int __init sc520_freq_init(void) int err; /* Test if we have the right hardware */ - if(c->x86_vendor != X86_VENDOR_AMD || - c->x86 != 4 || c->x86_model != 9) { + if (c->x86_vendor != X86_VENDOR_AMD || + c->x86 != 4 || c->x86_model != 9) { dprintk("no Elan SC520 processor found!\n"); return -ENODEV; } cpuctl = ioremap((unsigned long)(MMCR_BASE + OFFS_CPUCTL), 1); - if(!cpuctl) { + if (!cpuctl) { printk(KERN_ERR "sc520_freq: error: failed to remap memory\n"); return -ENOMEM; } diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c index dedc1e9..016c1a4 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c @@ -39,7 +39,7 @@ static struct pci_dev *speedstep_chipset_dev; /* speedstep_processor */ -static unsigned int speedstep_processor = 0; +static unsigned int speedstep_processor; static u32 pmbase; @@ -54,7 +54,8 @@ static struct cpufreq_frequency_table speedstep_freqs[] = { }; -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "speedstep-ich", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "speedstep-ich", msg) /** @@ -62,7 +63,7 @@ static struct cpufreq_frequency_table speedstep_freqs[] = { * * Returns: -ENODEV if no register could be found */ -static int speedstep_find_register (void) +static int speedstep_find_register(void) { if (!speedstep_chipset_dev) return -ENODEV; @@ -90,7 +91,7 @@ static int speedstep_find_register (void) * * Tries to change the SpeedStep state. */ -static void speedstep_set_state (unsigned int state) +static void speedstep_set_state(unsigned int state) { u8 pm2_blk; u8 value; @@ -133,11 +134,11 @@ static void speedstep_set_state (unsigned int state) dprintk("read at pmbase 0x%x + 0x50 returned 0x%x\n", pmbase, value); - if (state == (value & 0x1)) { - dprintk("change to %u MHz succeeded\n", (speedstep_get_processor_frequency(speedstep_processor) / 1000)); - } else { - printk (KERN_ERR "cpufreq: change failed - I/O error\n"); - } + if (state == (value & 0x1)) + dprintk("change to %u MHz succeeded\n", + speedstep_get_frequency(speedstep_processor) / 1000); + else + printk(KERN_ERR "cpufreq: change failed - I/O error\n"); return; } @@ -149,7 +150,7 @@ static void speedstep_set_state (unsigned int state) * Tries to activate the SpeedStep status and control registers. * Returns -EINVAL on an unsupported chipset, and zero on success. */ -static int speedstep_activate (void) +static int speedstep_activate(void) { u16 value = 0; @@ -175,20 +176,18 @@ static int speedstep_activate (void) * functions. Returns the SPEEDSTEP_CHIPSET_-number for the detected * chipset, or zero on failure. */ -static unsigned int speedstep_detect_chipset (void) +static unsigned int speedstep_detect_chipset(void) { speedstep_chipset_dev = pci_get_subsys(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801DB_12, - PCI_ANY_ID, - PCI_ANY_ID, + PCI_ANY_ID, PCI_ANY_ID, NULL); if (speedstep_chipset_dev) return 4; /* 4-M */ speedstep_chipset_dev = pci_get_subsys(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_12, - PCI_ANY_ID, - PCI_ANY_ID, + PCI_ANY_ID, PCI_ANY_ID, NULL); if (speedstep_chipset_dev) return 3; /* 3-M */ @@ -196,8 +195,7 @@ static unsigned int speedstep_detect_chipset (void) speedstep_chipset_dev = pci_get_subsys(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801BA_10, - PCI_ANY_ID, - PCI_ANY_ID, + PCI_ANY_ID, PCI_ANY_ID, NULL); if (speedstep_chipset_dev) { /* speedstep.c causes lockups on Dell Inspirons 8000 and @@ -208,8 +206,7 @@ static unsigned int speedstep_detect_chipset (void) hostbridge = pci_get_subsys(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82815_MC, - PCI_ANY_ID, - PCI_ANY_ID, + PCI_ANY_ID, PCI_ANY_ID, NULL); if (!hostbridge) @@ -236,7 +233,7 @@ static unsigned int _speedstep_get(const struct cpumask *cpus) cpus_allowed = current->cpus_allowed; set_cpus_allowed_ptr(current, cpus); - speed = speedstep_get_processor_frequency(speedstep_processor); + speed = speedstep_get_frequency(speedstep_processor); set_cpus_allowed_ptr(current, &cpus_allowed); dprintk("detected %u kHz as current frequency\n", speed); return speed; @@ -251,11 +248,12 @@ static unsigned int speedstep_get(unsigned int cpu) * speedstep_target - set a new CPUFreq policy * @policy: new policy * @target_freq: the target frequency - * @relation: how that frequency relates to achieved frequency (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H) + * @relation: how that frequency relates to achieved frequency + * (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H) * * Sets a new CPUFreq policy. */ -static int speedstep_target (struct cpufreq_policy *policy, +static int speedstep_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { @@ -264,7 +262,8 @@ static int speedstep_target (struct cpufreq_policy *policy, cpumask_t cpus_allowed; int i; - if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0], target_freq, relation, &newstate)) + if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0], + target_freq, relation, &newstate)) return -EINVAL; freqs.old = _speedstep_get(policy->cpus); @@ -308,7 +307,7 @@ static int speedstep_target (struct cpufreq_policy *policy, * Limit must be within speedstep_low_freq and speedstep_high_freq, with * at least one border included. */ -static int speedstep_verify (struct cpufreq_policy *policy) +static int speedstep_verify(struct cpufreq_policy *policy) { return cpufreq_frequency_table_verify(policy, &speedstep_freqs[0]); } @@ -322,7 +321,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) /* only run on CPU to be set, or on its sibling */ #ifdef CONFIG_SMP - cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu)); + cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu)); #endif cpus_allowed = current->cpus_allowed; @@ -344,7 +343,8 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) return -EIO; dprintk("currently at %s speed setting - %i MHz\n", - (speed == speedstep_freqs[SPEEDSTEP_LOW].frequency) ? "low" : "high", + (speed == speedstep_freqs[SPEEDSTEP_LOW].frequency) + ? "low" : "high", (speed / 1000)); /* cpuinfo and default policy values */ @@ -352,9 +352,9 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) result = cpufreq_frequency_table_cpuinfo(policy, speedstep_freqs); if (result) - return (result); + return result; - cpufreq_frequency_table_get_attr(speedstep_freqs, policy->cpu); + cpufreq_frequency_table_get_attr(speedstep_freqs, policy->cpu); return 0; } @@ -366,7 +366,7 @@ static int speedstep_cpu_exit(struct cpufreq_policy *policy) return 0; } -static struct freq_attr* speedstep_attr[] = { +static struct freq_attr *speedstep_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -396,13 +396,15 @@ static int __init speedstep_init(void) /* detect processor */ speedstep_processor = speedstep_detect_processor(); if (!speedstep_processor) { - dprintk("Intel(R) SpeedStep(TM) capable processor not found\n"); + dprintk("Intel(R) SpeedStep(TM) capable processor " + "not found\n"); return -ENODEV; } /* detect chipset */ if (!speedstep_detect_chipset()) { - dprintk("Intel(R) SpeedStep(TM) for this chipset not (yet) available.\n"); + dprintk("Intel(R) SpeedStep(TM) for this chipset not " + "(yet) available.\n"); return -ENODEV; } @@ -431,9 +433,11 @@ static void __exit speedstep_exit(void) } -MODULE_AUTHOR ("Dave Jones <davej@redhat.com>, Dominik Brodowski <linux@brodo.de>"); -MODULE_DESCRIPTION ("Speedstep driver for Intel mobile processors on chipsets with ICH-M southbridges."); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Dave Jones <davej@redhat.com>, " + "Dominik Brodowski <linux@brodo.de>"); +MODULE_DESCRIPTION("Speedstep driver for Intel mobile processors on chipsets " + "with ICH-M southbridges."); +MODULE_LICENSE("GPL"); module_init(speedstep_init); module_exit(speedstep_exit); diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c index cdac7d6..2e3c686 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c @@ -16,12 +16,16 @@ #include <linux/slab.h> #include <asm/msr.h> +#include <asm/tsc.h> #include "speedstep-lib.h" -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "speedstep-lib", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "speedstep-lib", msg) + +#define PFX "speedstep-lib: " #ifdef CONFIG_X86_SPEEDSTEP_RELAXED_CAP_CHECK -static int relaxed_check = 0; +static int relaxed_check; #else #define relaxed_check 0 #endif @@ -30,14 +34,14 @@ static int relaxed_check = 0; * GET PROCESSOR CORE SPEED IN KHZ * *********************************************************************/ -static unsigned int pentium3_get_frequency (unsigned int processor) +static unsigned int pentium3_get_frequency(unsigned int processor) { - /* See table 14 of p3_ds.pdf and table 22 of 29834003.pdf */ + /* See table 14 of p3_ds.pdf and table 22 of 29834003.pdf */ struct { unsigned int ratio; /* Frequency Multiplier (x10) */ u8 bitmap; /* power on configuration bits [27, 25:22] (in MSR 0x2a) */ - } msr_decode_mult [] = { + } msr_decode_mult[] = { { 30, 0x01 }, { 35, 0x05 }, { 40, 0x02 }, @@ -52,7 +56,7 @@ static unsigned int pentium3_get_frequency (unsigned int processor) { 85, 0x26 }, { 90, 0x20 }, { 100, 0x2b }, - { 0, 0xff } /* error or unknown value */ + { 0, 0xff } /* error or unknown value */ }; /* PIII(-M) FSB settings: see table b1-b of 24547206.pdf */ @@ -60,7 +64,7 @@ static unsigned int pentium3_get_frequency (unsigned int processor) unsigned int value; /* Front Side Bus speed in MHz */ u8 bitmap; /* power on configuration bits [18: 19] (in MSR 0x2a) */ - } msr_decode_fsb [] = { + } msr_decode_fsb[] = { { 66, 0x0 }, { 100, 0x2 }, { 133, 0x1 }, @@ -85,7 +89,7 @@ static unsigned int pentium3_get_frequency (unsigned int processor) } /* decode the multiplier */ - if (processor == SPEEDSTEP_PROCESSOR_PIII_C_EARLY) { + if (processor == SPEEDSTEP_CPU_PIII_C_EARLY) { dprintk("workaround for early PIIIs\n"); msr_lo &= 0x03c00000; } else @@ -97,9 +101,10 @@ static unsigned int pentium3_get_frequency (unsigned int processor) j++; } - dprintk("speed is %u\n", (msr_decode_mult[j].ratio * msr_decode_fsb[i].value * 100)); + dprintk("speed is %u\n", + (msr_decode_mult[j].ratio * msr_decode_fsb[i].value * 100)); - return (msr_decode_mult[j].ratio * msr_decode_fsb[i].value * 100); + return msr_decode_mult[j].ratio * msr_decode_fsb[i].value * 100; } @@ -112,20 +117,23 @@ static unsigned int pentiumM_get_frequency(void) /* see table B-2 of 24547212.pdf */ if (msr_lo & 0x00040000) { - printk(KERN_DEBUG "speedstep-lib: PM - invalid FSB: 0x%x 0x%x\n", msr_lo, msr_tmp); + printk(KERN_DEBUG PFX "PM - invalid FSB: 0x%x 0x%x\n", + msr_lo, msr_tmp); return 0; } msr_tmp = (msr_lo >> 22) & 0x1f; - dprintk("bits 22-26 are 0x%x, speed is %u\n", msr_tmp, (msr_tmp * 100 * 1000)); + dprintk("bits 22-26 are 0x%x, speed is %u\n", + msr_tmp, (msr_tmp * 100 * 1000)); - return (msr_tmp * 100 * 1000); + return msr_tmp * 100 * 1000; } static unsigned int pentium_core_get_frequency(void) { u32 fsb = 0; u32 msr_lo, msr_tmp; + int ret; rdmsr(MSR_FSB_FREQ, msr_lo, msr_tmp); /* see table B-2 of 25366920.pdf */ @@ -153,12 +161,15 @@ static unsigned int pentium_core_get_frequency(void) } rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp); - dprintk("PCORE - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp); + dprintk("PCORE - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", + msr_lo, msr_tmp); msr_tmp = (msr_lo >> 22) & 0x1f; - dprintk("bits 22-26 are 0x%x, speed is %u\n", msr_tmp, (msr_tmp * fsb)); + dprintk("bits 22-26 are 0x%x, speed is %u\n", + msr_tmp, (msr_tmp * fsb)); - return (msr_tmp * fsb); + ret = (msr_tmp * fsb); + return ret; } @@ -167,6 +178,16 @@ static unsigned int pentium4_get_frequency(void) struct cpuinfo_x86 *c = &boot_cpu_data; u32 msr_lo, msr_hi, mult; unsigned int fsb = 0; + unsigned int ret; + u8 fsb_code; + + /* Pentium 4 Model 0 and 1 do not have the Core Clock Frequency + * to System Bus Frequency Ratio Field in the Processor Frequency + * Configuration Register of the MSR. Therefore the current + * frequency cannot be calculated and has to be measured. + */ + if (c->x86_model < 2) + return cpu_khz; rdmsr(0x2c, msr_lo, msr_hi); @@ -177,62 +198,61 @@ static unsigned int pentium4_get_frequency(void) * revision #12 in Table B-1: MSRs in the Pentium 4 and * Intel Xeon Processors, on page B-4 and B-5. */ - if (c->x86_model < 2) + fsb_code = (msr_lo >> 16) & 0x7; + switch (fsb_code) { + case 0: fsb = 100 * 1000; - else { - u8 fsb_code = (msr_lo >> 16) & 0x7; - switch (fsb_code) { - case 0: - fsb = 100 * 1000; - break; - case 1: - fsb = 13333 * 10; - break; - case 2: - fsb = 200 * 1000; - break; - } + break; + case 1: + fsb = 13333 * 10; + break; + case 2: + fsb = 200 * 1000; + break; } if (!fsb) - printk(KERN_DEBUG "speedstep-lib: couldn't detect FSB speed. Please send an e-mail to <linux@brodo.de>\n"); + printk(KERN_DEBUG PFX "couldn't detect FSB speed. " + "Please send an e-mail to <linux@brodo.de>\n"); /* Multiplier. */ mult = msr_lo >> 24; - dprintk("P4 - FSB %u kHz; Multiplier %u; Speed %u kHz\n", fsb, mult, (fsb * mult)); + dprintk("P4 - FSB %u kHz; Multiplier %u; Speed %u kHz\n", + fsb, mult, (fsb * mult)); - return (fsb * mult); + ret = (fsb * mult); + return ret; } -unsigned int speedstep_get_processor_frequency(unsigned int processor) +unsigned int speedstep_get_frequency(unsigned int processor) { switch (processor) { - case SPEEDSTEP_PROCESSOR_PCORE: + case SPEEDSTEP_CPU_PCORE: return pentium_core_get_frequency(); - case SPEEDSTEP_PROCESSOR_PM: + case SPEEDSTEP_CPU_PM: return pentiumM_get_frequency(); - case SPEEDSTEP_PROCESSOR_P4D: - case SPEEDSTEP_PROCESSOR_P4M: + case SPEEDSTEP_CPU_P4D: + case SPEEDSTEP_CPU_P4M: return pentium4_get_frequency(); - case SPEEDSTEP_PROCESSOR_PIII_T: - case SPEEDSTEP_PROCESSOR_PIII_C: - case SPEEDSTEP_PROCESSOR_PIII_C_EARLY: + case SPEEDSTEP_CPU_PIII_T: + case SPEEDSTEP_CPU_PIII_C: + case SPEEDSTEP_CPU_PIII_C_EARLY: return pentium3_get_frequency(processor); default: return 0; }; return 0; } -EXPORT_SYMBOL_GPL(speedstep_get_processor_frequency); +EXPORT_SYMBOL_GPL(speedstep_get_frequency); /********************************************************************* * DETECT SPEEDSTEP-CAPABLE PROCESSOR * *********************************************************************/ -unsigned int speedstep_detect_processor (void) +unsigned int speedstep_detect_processor(void) { struct cpuinfo_x86 *c = &cpu_data(0); u32 ebx, msr_lo, msr_hi; @@ -261,7 +281,7 @@ unsigned int speedstep_detect_processor (void) * sample has ebx = 0x0f, production has 0x0e. */ if ((ebx == 0x0e) || (ebx == 0x0f)) - return SPEEDSTEP_PROCESSOR_P4M; + return SPEEDSTEP_CPU_P4M; break; case 7: /* @@ -272,7 +292,7 @@ unsigned int speedstep_detect_processor (void) * samples are only of B-stepping... */ if (ebx == 0x0e) - return SPEEDSTEP_PROCESSOR_P4M; + return SPEEDSTEP_CPU_P4M; break; case 9: /* @@ -288,10 +308,13 @@ unsigned int speedstep_detect_processor (void) * M-P4-Ms may have either ebx=0xe or 0xf [see above] * M-P4/533 have either ebx=0xe or 0xf. [25317607.pdf] * also, M-P4M HTs have ebx=0x8, too - * For now, they are distinguished by the model_id string + * For now, they are distinguished by the model_id + * string */ - if ((ebx == 0x0e) || (strstr(c->x86_model_id,"Mobile Intel(R) Pentium(R) 4") != NULL)) - return SPEEDSTEP_PROCESSOR_P4M; + if ((ebx == 0x0e) || + (strstr(c->x86_model_id, + "Mobile Intel(R) Pentium(R) 4") != NULL)) + return SPEEDSTEP_CPU_P4M; break; default: break; @@ -301,7 +324,8 @@ unsigned int speedstep_detect_processor (void) switch (c->x86_model) { case 0x0B: /* Intel PIII [Tualatin] */ - /* cpuid_ebx(1) is 0x04 for desktop PIII, 0x06 for mobile PIII-M */ + /* cpuid_ebx(1) is 0x04 for desktop PIII, + * 0x06 for mobile PIII-M */ ebx = cpuid_ebx(0x00000001); dprintk("ebx is %x\n", ebx); @@ -313,14 +337,15 @@ unsigned int speedstep_detect_processor (void) /* So far all PIII-M processors support SpeedStep. See * Intel's 24540640.pdf of June 2003 */ - return SPEEDSTEP_PROCESSOR_PIII_T; + return SPEEDSTEP_CPU_PIII_T; case 0x08: /* Intel PIII [Coppermine] */ /* all mobile PIII Coppermines have FSB 100 MHz * ==> sort out a few desktop PIIIs. */ rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_hi); - dprintk("Coppermine: MSR_IA32_EBL_CR_POWERON is 0x%x, 0x%x\n", msr_lo, msr_hi); + dprintk("Coppermine: MSR_IA32_EBL_CR_POWERON is 0x%x, 0x%x\n", + msr_lo, msr_hi); msr_lo &= 0x00c0000; if (msr_lo != 0x0080000) return 0; @@ -332,13 +357,15 @@ unsigned int speedstep_detect_processor (void) * bit 56 or 57 is set */ rdmsr(MSR_IA32_PLATFORM_ID, msr_lo, msr_hi); - dprintk("Coppermine: MSR_IA32_PLATFORM ID is 0x%x, 0x%x\n", msr_lo, msr_hi); - if ((msr_hi & (1<<18)) && (relaxed_check ? 1 : (msr_hi & (3<<24)))) { + dprintk("Coppermine: MSR_IA32_PLATFORM ID is 0x%x, 0x%x\n", + msr_lo, msr_hi); + if ((msr_hi & (1<<18)) && + (relaxed_check ? 1 : (msr_hi & (3<<24)))) { if (c->x86_mask == 0x01) { dprintk("early PIII version\n"); - return SPEEDSTEP_PROCESSOR_PIII_C_EARLY; + return SPEEDSTEP_CPU_PIII_C_EARLY; } else - return SPEEDSTEP_PROCESSOR_PIII_C; + return SPEEDSTEP_CPU_PIII_C; } default: @@ -369,7 +396,7 @@ unsigned int speedstep_get_freqs(unsigned int processor, dprintk("trying to determine both speeds\n"); /* get current speed */ - prev_speed = speedstep_get_processor_frequency(processor); + prev_speed = speedstep_get_frequency(processor); if (!prev_speed) return -EIO; @@ -379,7 +406,7 @@ unsigned int speedstep_get_freqs(unsigned int processor, /* switch to low state */ set_state(SPEEDSTEP_LOW); - *low_speed = speedstep_get_processor_frequency(processor); + *low_speed = speedstep_get_frequency(processor); if (!*low_speed) { ret = -EIO; goto out; @@ -398,7 +425,7 @@ unsigned int speedstep_get_freqs(unsigned int processor, if (transition_latency) do_gettimeofday(&tv2); - *high_speed = speedstep_get_processor_frequency(processor); + *high_speed = speedstep_get_frequency(processor); if (!*high_speed) { ret = -EIO; goto out; @@ -426,9 +453,12 @@ unsigned int speedstep_get_freqs(unsigned int processor, /* check if the latency measurement is too high or too low * and set it to a safe value (500uSec) in that case */ - if (*transition_latency > 10000000 || *transition_latency < 50000) { - printk (KERN_WARNING "speedstep: frequency transition measured seems out of " - "range (%u nSec), falling back to a safe one of %u nSec.\n", + if (*transition_latency > 10000000 || + *transition_latency < 50000) { + printk(KERN_WARNING PFX "frequency transition " + "measured seems out of range (%u " + "nSec), falling back to a safe one of" + "%u nSec.\n", *transition_latency, 500000); *transition_latency = 500000; } @@ -436,15 +466,16 @@ unsigned int speedstep_get_freqs(unsigned int processor, out: local_irq_restore(flags); - return (ret); + return ret; } EXPORT_SYMBOL_GPL(speedstep_get_freqs); #ifdef CONFIG_X86_SPEEDSTEP_RELAXED_CAP_CHECK module_param(relaxed_check, int, 0444); -MODULE_PARM_DESC(relaxed_check, "Don't do all checks for speedstep capability."); +MODULE_PARM_DESC(relaxed_check, + "Don't do all checks for speedstep capability."); #endif -MODULE_AUTHOR ("Dominik Brodowski <linux@brodo.de>"); -MODULE_DESCRIPTION ("Library for Intel SpeedStep 1 or 2 cpufreq drivers."); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>"); +MODULE_DESCRIPTION("Library for Intel SpeedStep 1 or 2 cpufreq drivers."); +MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h index b11bcc6..2b6c04e 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h @@ -12,17 +12,17 @@ /* processors */ -#define SPEEDSTEP_PROCESSOR_PIII_C_EARLY 0x00000001 /* Coppermine core */ -#define SPEEDSTEP_PROCESSOR_PIII_C 0x00000002 /* Coppermine core */ -#define SPEEDSTEP_PROCESSOR_PIII_T 0x00000003 /* Tualatin core */ -#define SPEEDSTEP_PROCESSOR_P4M 0x00000004 /* P4-M */ +#define SPEEDSTEP_CPU_PIII_C_EARLY 0x00000001 /* Coppermine core */ +#define SPEEDSTEP_CPU_PIII_C 0x00000002 /* Coppermine core */ +#define SPEEDSTEP_CPU_PIII_T 0x00000003 /* Tualatin core */ +#define SPEEDSTEP_CPU_P4M 0x00000004 /* P4-M */ /* the following processors are not speedstep-capable and are not auto-detected * in speedstep_detect_processor(). However, their speed can be detected using - * the speedstep_get_processor_frequency() call. */ -#define SPEEDSTEP_PROCESSOR_PM 0xFFFFFF03 /* Pentium M */ -#define SPEEDSTEP_PROCESSOR_P4D 0xFFFFFF04 /* desktop P4 */ -#define SPEEDSTEP_PROCESSOR_PCORE 0xFFFFFF05 /* Core */ + * the speedstep_get_frequency() call. */ +#define SPEEDSTEP_CPU_PM 0xFFFFFF03 /* Pentium M */ +#define SPEEDSTEP_CPU_P4D 0xFFFFFF04 /* desktop P4 */ +#define SPEEDSTEP_CPU_PCORE 0xFFFFFF05 /* Core */ /* speedstep states -- only two of them */ @@ -34,7 +34,7 @@ extern unsigned int speedstep_detect_processor (void); /* detect the current speed (in khz) of the processor */ -extern unsigned int speedstep_get_processor_frequency(unsigned int processor); +extern unsigned int speedstep_get_frequency(unsigned int processor); /* detect the low and high speeds of the processor. The callback diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c index 8a85c93..befea08 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c @@ -19,8 +19,8 @@ #include <linux/cpufreq.h> #include <linux/slab.h> #include <linux/delay.h> +#include <linux/io.h> #include <asm/ist.h> -#include <asm/io.h> #include "speedstep-lib.h" @@ -30,12 +30,12 @@ * If user gives it, these are used. * */ -static int smi_port = 0; -static int smi_cmd = 0; -static unsigned int smi_sig = 0; +static int smi_port; +static int smi_cmd; +static unsigned int smi_sig; /* info about the processor */ -static unsigned int speedstep_processor = 0; +static unsigned int speedstep_processor; /* * There are only two frequency states for each processor. Values @@ -56,12 +56,13 @@ static struct cpufreq_frequency_table speedstep_freqs[] = { * of DMA activity going on? */ #define SMI_TRIES 5 -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "speedstep-smi", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "speedstep-smi", msg) /** * speedstep_smi_ownership */ -static int speedstep_smi_ownership (void) +static int speedstep_smi_ownership(void) { u32 command, result, magic, dummy; u32 function = GET_SPEEDSTEP_OWNER; @@ -70,16 +71,18 @@ static int speedstep_smi_ownership (void) command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); magic = virt_to_phys(magic_data); - dprintk("trying to obtain ownership with command %x at port %x\n", command, smi_port); + dprintk("trying to obtain ownership with command %x at port %x\n", + command, smi_port); __asm__ __volatile__( "push %%ebp\n" "out %%al, (%%dx)\n" "pop %%ebp\n" - : "=D" (result), "=a" (dummy), "=b" (dummy), "=c" (dummy), "=d" (dummy), - "=S" (dummy) + : "=D" (result), + "=a" (dummy), "=b" (dummy), "=c" (dummy), "=d" (dummy), + "=S" (dummy) : "a" (command), "b" (function), "c" (0), "d" (smi_port), - "D" (0), "S" (magic) + "D" (0), "S" (magic) : "memory" ); @@ -97,10 +100,10 @@ static int speedstep_smi_ownership (void) * even hangs [cf. bugme.osdl.org # 1422] on earlier systems. Empirical testing * shows that the latter occurs if !(ist_info.event & 0xFFFF). */ -static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high) +static int speedstep_smi_get_freqs(unsigned int *low, unsigned int *high) { u32 command, result = 0, edi, high_mhz, low_mhz, dummy; - u32 state=0; + u32 state = 0; u32 function = GET_SPEEDSTEP_FREQS; if (!(ist_info.event & 0xFFFF)) { @@ -110,17 +113,25 @@ static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high) command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); - dprintk("trying to determine frequencies with command %x at port %x\n", command, smi_port); + dprintk("trying to determine frequencies with command %x at port %x\n", + command, smi_port); __asm__ __volatile__( "push %%ebp\n" "out %%al, (%%dx)\n" "pop %%ebp" - : "=a" (result), "=b" (high_mhz), "=c" (low_mhz), "=d" (state), "=D" (edi), "=S" (dummy) - : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0), "D" (0) + : "=a" (result), + "=b" (high_mhz), + "=c" (low_mhz), + "=d" (state), "=D" (edi), "=S" (dummy) + : "a" (command), + "b" (function), + "c" (state), + "d" (smi_port), "S" (0), "D" (0) ); - dprintk("result %x, low_freq %u, high_freq %u\n", result, low_mhz, high_mhz); + dprintk("result %x, low_freq %u, high_freq %u\n", + result, low_mhz, high_mhz); /* abort if results are obviously incorrect... */ if ((high_mhz + low_mhz) < 600) @@ -137,26 +148,30 @@ static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high) * @state: processor frequency state (SPEEDSTEP_LOW or SPEEDSTEP_HIGH) * */ -static int speedstep_get_state (void) +static int speedstep_get_state(void) { - u32 function=GET_SPEEDSTEP_STATE; + u32 function = GET_SPEEDSTEP_STATE; u32 result, state, edi, command, dummy; command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); - dprintk("trying to determine current setting with command %x at port %x\n", command, smi_port); + dprintk("trying to determine current setting with command %x " + "at port %x\n", command, smi_port); __asm__ __volatile__( "push %%ebp\n" "out %%al, (%%dx)\n" "pop %%ebp\n" - : "=a" (result), "=b" (state), "=D" (edi), "=c" (dummy), "=d" (dummy), "=S" (dummy) - : "a" (command), "b" (function), "c" (0), "d" (smi_port), "S" (0), "D" (0) + : "=a" (result), + "=b" (state), "=D" (edi), + "=c" (dummy), "=d" (dummy), "=S" (dummy) + : "a" (command), "b" (function), "c" (0), + "d" (smi_port), "S" (0), "D" (0) ); dprintk("state is %x, result is %x\n", state, result); - return (state & 1); + return state & 1; } @@ -165,11 +180,11 @@ static int speedstep_get_state (void) * @state: new processor frequency state (SPEEDSTEP_LOW or SPEEDSTEP_HIGH) * */ -static void speedstep_set_state (unsigned int state) +static void speedstep_set_state(unsigned int state) { unsigned int result = 0, command, new_state, dummy; unsigned long flags; - unsigned int function=SET_SPEEDSTEP_STATE; + unsigned int function = SET_SPEEDSTEP_STATE; unsigned int retry = 0; if (state > 0x1) @@ -180,11 +195,14 @@ static void speedstep_set_state (unsigned int state) command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); - dprintk("trying to set frequency to state %u with command %x at port %x\n", state, command, smi_port); + dprintk("trying to set frequency to state %u " + "with command %x at port %x\n", + state, command, smi_port); do { if (retry) { - dprintk("retry %u, previous result %u, waiting...\n", retry, result); + dprintk("retry %u, previous result %u, waiting...\n", + retry, result); mdelay(retry * 50); } retry++; @@ -192,20 +210,26 @@ static void speedstep_set_state (unsigned int state) "push %%ebp\n" "out %%al, (%%dx)\n" "pop %%ebp" - : "=b" (new_state), "=D" (result), "=c" (dummy), "=a" (dummy), - "=d" (dummy), "=S" (dummy) - : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0), "D" (0) + : "=b" (new_state), "=D" (result), + "=c" (dummy), "=a" (dummy), + "=d" (dummy), "=S" (dummy) + : "a" (command), "b" (function), "c" (state), + "d" (smi_port), "S" (0), "D" (0) ); } while ((new_state != state) && (retry <= SMI_TRIES)); /* enable IRQs */ local_irq_restore(flags); - if (new_state == state) { - dprintk("change to %u MHz succeeded after %u tries with result %u\n", (speedstep_freqs[new_state].frequency / 1000), retry, result); - } else { - printk(KERN_ERR "cpufreq: change to state %u failed with new_state %u and result %u\n", state, new_state, result); - } + if (new_state == state) + dprintk("change to %u MHz succeeded after %u tries " + "with result %u\n", + (speedstep_freqs[new_state].frequency / 1000), + retry, result); + else + printk(KERN_ERR "cpufreq: change to state %u " + "failed with new_state %u and result %u\n", + state, new_state, result); return; } @@ -219,13 +243,14 @@ static void speedstep_set_state (unsigned int state) * * Sets a new CPUFreq policy/freq. */ -static int speedstep_target (struct cpufreq_policy *policy, +static int speedstep_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { unsigned int newstate = 0; struct cpufreq_freqs freqs; - if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0], target_freq, relation, &newstate)) + if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0], + target_freq, relation, &newstate)) return -EINVAL; freqs.old = speedstep_freqs[speedstep_get_state()].frequency; @@ -250,7 +275,7 @@ static int speedstep_target (struct cpufreq_policy *policy, * Limit must be within speedstep_low_freq and speedstep_high_freq, with * at least one border included. */ -static int speedstep_verify (struct cpufreq_policy *policy) +static int speedstep_verify(struct cpufreq_policy *policy) { return cpufreq_frequency_table_verify(policy, &speedstep_freqs[0]); } @@ -259,7 +284,8 @@ static int speedstep_verify (struct cpufreq_policy *policy) static int speedstep_cpu_init(struct cpufreq_policy *policy) { int result; - unsigned int speed,state; + unsigned int speed, state; + unsigned int *low, *high; /* capability check */ if (policy->cpu != 0) @@ -272,19 +298,23 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) } /* detect low and high frequency */ - result = speedstep_smi_get_freqs(&speedstep_freqs[SPEEDSTEP_LOW].frequency, - &speedstep_freqs[SPEEDSTEP_HIGH].frequency); + low = &speedstep_freqs[SPEEDSTEP_LOW].frequency; + high = &speedstep_freqs[SPEEDSTEP_HIGH].frequency; + + result = speedstep_smi_get_freqs(low, high); if (result) { - /* fall back to speedstep_lib.c dection mechanism: try both states out */ - dprintk("could not detect low and high frequencies by SMI call.\n"); + /* fall back to speedstep_lib.c dection mechanism: + * try both states out */ + dprintk("could not detect low and high frequencies " + "by SMI call.\n"); result = speedstep_get_freqs(speedstep_processor, - &speedstep_freqs[SPEEDSTEP_LOW].frequency, - &speedstep_freqs[SPEEDSTEP_HIGH].frequency, + low, high, NULL, &speedstep_set_state); if (result) { - dprintk("could not detect two different speeds -- aborting.\n"); + dprintk("could not detect two different speeds" + " -- aborting.\n"); return result; } else dprintk("workaround worked.\n"); @@ -295,7 +325,8 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) speed = speedstep_freqs[state].frequency; dprintk("currently at %s speed setting - %i MHz\n", - (speed == speedstep_freqs[SPEEDSTEP_LOW].frequency) ? "low" : "high", + (speed == speedstep_freqs[SPEEDSTEP_LOW].frequency) + ? "low" : "high", (speed / 1000)); /* cpuinfo and default policy values */ @@ -304,7 +335,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) result = cpufreq_frequency_table_cpuinfo(policy, speedstep_freqs); if (result) - return (result); + return result; cpufreq_frequency_table_get_attr(speedstep_freqs, policy->cpu); @@ -321,7 +352,7 @@ static unsigned int speedstep_get(unsigned int cpu) { if (cpu) return -ENODEV; - return speedstep_get_processor_frequency(speedstep_processor); + return speedstep_get_frequency(speedstep_processor); } @@ -335,7 +366,7 @@ static int speedstep_resume(struct cpufreq_policy *policy) return result; } -static struct freq_attr* speedstep_attr[] = { +static struct freq_attr *speedstep_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -364,21 +395,23 @@ static int __init speedstep_init(void) speedstep_processor = speedstep_detect_processor(); switch (speedstep_processor) { - case SPEEDSTEP_PROCESSOR_PIII_T: - case SPEEDSTEP_PROCESSOR_PIII_C: - case SPEEDSTEP_PROCESSOR_PIII_C_EARLY: + case SPEEDSTEP_CPU_PIII_T: + case SPEEDSTEP_CPU_PIII_C: + case SPEEDSTEP_CPU_PIII_C_EARLY: break; default: speedstep_processor = 0; } if (!speedstep_processor) { - dprintk ("No supported Intel CPU detected.\n"); + dprintk("No supported Intel CPU detected.\n"); return -ENODEV; } - dprintk("signature:0x%.8lx, command:0x%.8lx, event:0x%.8lx, perf_level:0x%.8lx.\n", - ist_info.signature, ist_info.command, ist_info.event, ist_info.perf_level); + dprintk("signature:0x%.8lx, command:0x%.8lx, " + "event:0x%.8lx, perf_level:0x%.8lx.\n", + ist_info.signature, ist_info.command, + ist_info.event, ist_info.perf_level); /* Error if no IST-SMI BIOS or no PARM sig= 'ISGE' aka 'Intel Speedstep Gate E' */ @@ -416,17 +449,20 @@ static void __exit speedstep_exit(void) cpufreq_unregister_driver(&speedstep_driver); } -module_param(smi_port, int, 0444); -module_param(smi_cmd, int, 0444); -module_param(smi_sig, uint, 0444); +module_param(smi_port, int, 0444); +module_param(smi_cmd, int, 0444); +module_param(smi_sig, uint, 0444); -MODULE_PARM_DESC(smi_port, "Override the BIOS-given IST port with this value -- Intel's default setting is 0xb2"); -MODULE_PARM_DESC(smi_cmd, "Override the BIOS-given IST command with this value -- Intel's default setting is 0x82"); -MODULE_PARM_DESC(smi_sig, "Set to 1 to fake the IST signature when using the SMI interface."); +MODULE_PARM_DESC(smi_port, "Override the BIOS-given IST port with this value " + "-- Intel's default setting is 0xb2"); +MODULE_PARM_DESC(smi_cmd, "Override the BIOS-given IST command with this value " + "-- Intel's default setting is 0x82"); +MODULE_PARM_DESC(smi_sig, "Set to 1 to fake the IST signature when using the " + "SMI interface."); -MODULE_AUTHOR ("Hiroshi Miura"); -MODULE_DESCRIPTION ("Speedstep driver for IST applet SMI interface."); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Hiroshi Miura"); +MODULE_DESCRIPTION("Speedstep driver for IST applet SMI interface."); +MODULE_LICENSE("GPL"); module_init(speedstep_init); module_exit(speedstep_exit); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index ffd0f5e..593171e 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -61,23 +61,23 @@ static void __cpuinit do_cyrix_devid(unsigned char *dir0, unsigned char *dir1) */ static unsigned char Cx86_dir0_msb __cpuinitdata = 0; -static char Cx86_model[][9] __cpuinitdata = { +static const char __cpuinitconst Cx86_model[][9] = { "Cx486", "Cx486", "5x86 ", "6x86", "MediaGX ", "6x86MX ", "M II ", "Unknown" }; -static char Cx486_name[][5] __cpuinitdata = { +static const char __cpuinitconst Cx486_name[][5] = { "SLC", "DLC", "SLC2", "DLC2", "SRx", "DRx", "SRx2", "DRx2" }; -static char Cx486S_name[][4] __cpuinitdata = { +static const char __cpuinitconst Cx486S_name[][4] = { "S", "S2", "Se", "S2e" }; -static char Cx486D_name[][4] __cpuinitdata = { +static const char __cpuinitconst Cx486D_name[][4] = { "DX", "DX2", "?", "?", "?", "DX4" }; static char Cx86_cb[] __cpuinitdata = "?.5x Core/Bus Clock"; -static char cyrix_model_mult1[] __cpuinitdata = "12??43"; -static char cyrix_model_mult2[] __cpuinitdata = "12233445"; +static const char __cpuinitconst cyrix_model_mult1[] = "12??43"; +static const char __cpuinitconst cyrix_model_mult2[] = "12233445"; /* * Reset the slow-loop (SLOP) bit on the 686(L) which is set by some old @@ -435,7 +435,7 @@ static void __cpuinit cyrix_identify(struct cpuinfo_x86 *c) } } -static struct cpu_dev cyrix_cpu_dev __cpuinitdata = { +static const struct cpu_dev __cpuinitconst cyrix_cpu_dev = { .c_vendor = "Cyrix", .c_ident = { "CyrixInstead" }, .c_early_init = early_init_cyrix, @@ -446,7 +446,7 @@ static struct cpu_dev cyrix_cpu_dev __cpuinitdata = { cpu_dev_register(cyrix_cpu_dev); -static struct cpu_dev nsc_cpu_dev __cpuinitdata = { +static const struct cpu_dev __cpuinitconst nsc_cpu_dev = { .c_vendor = "NSC", .c_ident = { "Geode by NSC" }, .c_init = init_nsc, diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 25c559b..7437fa1 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -4,6 +4,7 @@ #include <linux/string.h> #include <linux/bitops.h> #include <linux/smp.h> +#include <linux/sched.h> #include <linux/thread_info.h> #include <linux/module.h> @@ -13,6 +14,7 @@ #include <asm/uaccess.h> #include <asm/ds.h> #include <asm/bugs.h> +#include <asm/cpu.h> #ifdef CONFIG_X86_64 #include <asm/topology.h> @@ -53,13 +55,23 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) c->x86_cache_alignment = 128; #endif + /* CPUID workaround for 0F33/0F34 CPU */ + if (c->x86 == 0xF && c->x86_model == 0x3 + && (c->x86_mask == 0x3 || c->x86_mask == 0x4)) + c->x86_phys_bits = 36; + /* * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate - * with P/T states and does not stop in deep C-states + * with P/T states and does not stop in deep C-states. + * + * It is also reliable across cores and sockets. (but not across + * cabinets - we turn it off in that case explicitly.) */ if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); + set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE); + sched_clock_stable = 1; } /* @@ -110,6 +122,28 @@ static void __cpuinit trap_init_f00f_bug(void) } #endif +static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + /* calling is from identify_secondary_cpu() ? */ + if (c->cpu_index == boot_cpu_id) + return; + + /* + * Mask B, Pentium, but not Pentium MMX + */ + if (c->x86 == 5 && + c->x86_mask >= 1 && c->x86_mask <= 4 && + c->x86_model <= 3) { + /* + * Remember we have B step Pentia with bugs + */ + WARN_ONCE(1, "WARNING: SMP operation may be unreliable" + "with B stepping processors.\n"); + } +#endif +} + static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) { unsigned long lo, hi; @@ -186,6 +220,8 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_NUMAQ numaq_tsc_disable(); #endif + + intel_smp_check(c); } #else static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) @@ -385,7 +421,7 @@ static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 *c, unsigned i } #endif -static struct cpu_dev intel_cpu_dev __cpuinitdata = { +static const struct cpu_dev __cpuinitconst intel_cpu_dev = { .c_vendor = "Intel", .c_ident = { "GenuineIntel" }, #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 7293508..483eda9 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -32,7 +32,7 @@ struct _cache_table }; /* all the cache descriptor types we care about (no TLB or trace cache entries) */ -static struct _cache_table cache_table[] __cpuinitdata = +static const struct _cache_table __cpuinitconst cache_table[] = { { 0x06, LVL_1_INST, 8 }, /* 4-way set assoc, 32 byte line size */ { 0x08, LVL_1_INST, 16 }, /* 4-way set assoc, 32 byte line size */ @@ -159,7 +159,7 @@ struct _cpuid4_info_regs { unsigned long can_disable; }; -#ifdef CONFIG_PCI +#if defined(CONFIG_PCI) && defined(CONFIG_SYSFS) static struct pci_device_id k8_nb_id[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1103) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1203) }, @@ -206,15 +206,15 @@ union l3_cache { unsigned val; }; -static unsigned short assocs[] __cpuinitdata = { +static const unsigned short __cpuinitconst assocs[] = { [1] = 1, [2] = 2, [4] = 4, [6] = 8, [8] = 16, [0xa] = 32, [0xb] = 48, [0xc] = 64, [0xf] = 0xffff // ?? }; -static unsigned char levels[] __cpuinitdata = { 1, 1, 2, 3 }; -static unsigned char types[] __cpuinitdata = { 1, 2, 3, 3 }; +static const unsigned char __cpuinitconst levels[] = { 1, 1, 2, 3 }; +static const unsigned char __cpuinitconst types[] = { 1, 2, 3, 3 }; static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, @@ -324,15 +324,6 @@ __cpuinit cpuid4_cache_lookup_regs(int index, return 0; } -static int -__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf) -{ - struct _cpuid4_info_regs *leaf_regs = - (struct _cpuid4_info_regs *)this_leaf; - - return cpuid4_cache_lookup_regs(index, leaf_regs); -} - static int __cpuinit find_num_cache_leaves(void) { unsigned int eax, ebx, ecx, edx; @@ -508,6 +499,8 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) return l2; } +#ifdef CONFIG_SYSFS + /* pointer to _cpuid4_info array (for each cache leaf) */ static DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info); #define CPUID4_INFO_IDX(x, y) (&((per_cpu(cpuid4_info, x))[y])) @@ -571,6 +564,15 @@ static void __cpuinit free_cache_attributes(unsigned int cpu) per_cpu(cpuid4_info, cpu) = NULL; } +static int +__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf) +{ + struct _cpuid4_info_regs *leaf_regs = + (struct _cpuid4_info_regs *)this_leaf; + + return cpuid4_cache_lookup_regs(index, leaf_regs); +} + static void __cpuinit get_cpu_leaves(void *_retval) { int j, *retval = _retval, cpu = smp_processor_id(); @@ -612,8 +614,6 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu) return retval; } -#ifdef CONFIG_SYSFS - #include <linux/kobject.h> #include <linux/sysfs.h> diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile index d7d2323..b2f8982 100644 --- a/arch/x86/kernel/cpu/mcheck/Makefile +++ b/arch/x86/kernel/cpu/mcheck/Makefile @@ -4,3 +4,4 @@ obj-$(CONFIG_X86_32) += k7.o p4.o p5.o p6.o winchip.o obj-$(CONFIG_X86_MCE_INTEL) += mce_intel_64.o obj-$(CONFIG_X86_MCE_AMD) += mce_amd_64.o obj-$(CONFIG_X86_MCE_NONFATAL) += non-fatal.o +obj-$(CONFIG_X86_MCE_THRESHOLD) += threshold.o diff --git a/arch/x86/kernel/cpu/mcheck/mce_32.c b/arch/x86/kernel/cpu/mcheck/mce_32.c index dfaebce..3552119 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_32.c +++ b/arch/x86/kernel/cpu/mcheck/mce_32.c @@ -60,20 +60,6 @@ void mcheck_init(struct cpuinfo_x86 *c) } } -static unsigned long old_cr4 __initdata; - -void __init stop_mce(void) -{ - old_cr4 = read_cr4(); - clear_in_cr4(X86_CR4_MCE); -} - -void __init restart_mce(void) -{ - if (old_cr4 & X86_CR4_MCE) - set_in_cr4(X86_CR4_MCE); -} - static int __init mcheck_disable(char *str) { mce_disabled = 1; diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c index fe79985..863f895 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c @@ -3,6 +3,8 @@ * K8 parts Copyright 2002,2003 Andi Kleen, SuSE Labs. * Rest from unknown author(s). * 2004 Andi Kleen. Rewrote most of it. + * Copyright 2008 Intel Corporation + * Author: Andi Kleen */ #include <linux/init.h> @@ -24,6 +26,9 @@ #include <linux/ctype.h> #include <linux/kmod.h> #include <linux/kdebug.h> +#include <linux/kobject.h> +#include <linux/sysfs.h> +#include <linux/ratelimit.h> #include <asm/processor.h> #include <asm/msr.h> #include <asm/mce.h> @@ -32,7 +37,6 @@ #include <asm/idle.h> #define MISC_MCELOG_MINOR 227 -#define NR_SYSFS_BANKS 6 atomic_t mce_entry; @@ -47,7 +51,7 @@ static int mce_dont_init; */ static int tolerant = 1; static int banks; -static unsigned long bank[NR_SYSFS_BANKS] = { [0 ... NR_SYSFS_BANKS-1] = ~0UL }; +static u64 *bank; static unsigned long notify_user; static int rip_msr; static int mce_bootlog = -1; @@ -58,6 +62,19 @@ static char *trigger_argv[2] = { trigger, NULL }; static DECLARE_WAIT_QUEUE_HEAD(mce_wait); +/* MCA banks polled by the period polling timer for corrected events */ +DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = { + [0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL +}; + +/* Do initial initialization of a struct mce */ +void mce_setup(struct mce *m) +{ + memset(m, 0, sizeof(struct mce)); + m->cpu = smp_processor_id(); + rdtscll(m->tsc); +} + /* * Lockless MCE logging infrastructure. * This avoids deadlocks on printk locks without having to break locks. Also @@ -119,11 +136,11 @@ static void print_mce(struct mce *m) print_symbol("{%s}", m->ip); printk("\n"); } - printk(KERN_EMERG "TSC %Lx ", m->tsc); + printk(KERN_EMERG "TSC %llx ", m->tsc); if (m->addr) - printk("ADDR %Lx ", m->addr); + printk("ADDR %llx ", m->addr); if (m->misc) - printk("MISC %Lx ", m->misc); + printk("MISC %llx ", m->misc); printk("\n"); printk(KERN_EMERG "This is not a software problem!\n"); printk(KERN_EMERG "Run through mcelog --ascii to decode " @@ -149,8 +166,10 @@ static void mce_panic(char *msg, struct mce *backup, unsigned long start) panic(msg); } -static int mce_available(struct cpuinfo_x86 *c) +int mce_available(struct cpuinfo_x86 *c) { + if (mce_dont_init) + return 0; return cpu_has(c, X86_FEATURE_MCE) && cpu_has(c, X86_FEATURE_MCA); } @@ -172,7 +191,77 @@ static inline void mce_get_rip(struct mce *m, struct pt_regs *regs) } /* - * The actual machine check handler + * Poll for corrected events or events that happened before reset. + * Those are just logged through /dev/mcelog. + * + * This is executed in standard interrupt context. + */ +void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) +{ + struct mce m; + int i; + + mce_setup(&m); + + rdmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus); + for (i = 0; i < banks; i++) { + if (!bank[i] || !test_bit(i, *b)) + continue; + + m.misc = 0; + m.addr = 0; + m.bank = i; + m.tsc = 0; + + barrier(); + rdmsrl(MSR_IA32_MC0_STATUS + i*4, m.status); + if (!(m.status & MCI_STATUS_VAL)) + continue; + + /* + * Uncorrected events are handled by the exception handler + * when it is enabled. But when the exception is disabled log + * everything. + * + * TBD do the same check for MCI_STATUS_EN here? + */ + if ((m.status & MCI_STATUS_UC) && !(flags & MCP_UC)) + continue; + + if (m.status & MCI_STATUS_MISCV) + rdmsrl(MSR_IA32_MC0_MISC + i*4, m.misc); + if (m.status & MCI_STATUS_ADDRV) + rdmsrl(MSR_IA32_MC0_ADDR + i*4, m.addr); + + if (!(flags & MCP_TIMESTAMP)) + m.tsc = 0; + /* + * Don't get the IP here because it's unlikely to + * have anything to do with the actual error location. + */ + + mce_log(&m); + add_taint(TAINT_MACHINE_CHECK); + + /* + * Clear state for this bank. + */ + wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0); + } + + /* + * Don't clear MCG_STATUS here because it's only defined for + * exceptions. + */ +} + +/* + * The actual machine check handler. This only handles real + * exceptions when something got corrupted coming in through int 18. + * + * This is executed in NMI context not subject to normal locking rules. This + * implies that most kernel services cannot be safely used. Don't even + * think about putting a printk in there! */ void do_machine_check(struct pt_regs * regs, long error_code) { @@ -190,17 +279,18 @@ void do_machine_check(struct pt_regs * regs, long error_code) * error. */ int kill_it = 0; + DECLARE_BITMAP(toclear, MAX_NR_BANKS); atomic_inc(&mce_entry); - if ((regs - && notify_die(DIE_NMI, "machine check", regs, error_code, + if (notify_die(DIE_NMI, "machine check", regs, error_code, 18, SIGKILL) == NOTIFY_STOP) - || !banks) + goto out2; + if (!banks) goto out2; - memset(&m, 0, sizeof(struct mce)); - m.cpu = smp_processor_id(); + mce_setup(&m); + rdmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus); /* if the restart IP is not valid, we're done for */ if (!(m.mcgstatus & MCG_STATUS_RIPV)) @@ -210,18 +300,32 @@ void do_machine_check(struct pt_regs * regs, long error_code) barrier(); for (i = 0; i < banks; i++) { - if (i < NR_SYSFS_BANKS && !bank[i]) + __clear_bit(i, toclear); + if (!bank[i]) continue; m.misc = 0; m.addr = 0; m.bank = i; - m.tsc = 0; rdmsrl(MSR_IA32_MC0_STATUS + i*4, m.status); if ((m.status & MCI_STATUS_VAL) == 0) continue; + /* + * Non uncorrected errors are handled by machine_check_poll + * Leave them alone. + */ + if ((m.status & MCI_STATUS_UC) == 0) + continue; + + /* + * Set taint even when machine check was not enabled. + */ + add_taint(TAINT_MACHINE_CHECK); + + __set_bit(i, toclear); + if (m.status & MCI_STATUS_EN) { /* if PCC was set, there's no way out */ no_way_out |= !!(m.status & MCI_STATUS_PCC); @@ -235,6 +339,12 @@ void do_machine_check(struct pt_regs * regs, long error_code) no_way_out = 1; kill_it = 1; } + } else { + /* + * Machine check event was not enabled. Clear, but + * ignore. + */ + continue; } if (m.status & MCI_STATUS_MISCV) @@ -243,10 +353,7 @@ void do_machine_check(struct pt_regs * regs, long error_code) rdmsrl(MSR_IA32_MC0_ADDR + i*4, m.addr); mce_get_rip(&m, regs); - if (error_code >= 0) - rdtscll(m.tsc); - if (error_code != -2) - mce_log(&m); + mce_log(&m); /* Did this bank cause the exception? */ /* Assume that the bank with uncorrectable errors did it, @@ -255,14 +362,8 @@ void do_machine_check(struct pt_regs * regs, long error_code) panicm = m; panicm_found = 1; } - - add_taint(TAINT_MACHINE_CHECK); } - /* Never do anything final in the polling timer */ - if (!regs) - goto out; - /* If we didn't find an uncorrectable error, pick the last one (shouldn't happen, just being safe). */ if (!panicm_found) @@ -309,10 +410,11 @@ void do_machine_check(struct pt_regs * regs, long error_code) /* notify userspace ASAP */ set_thread_flag(TIF_MCE_NOTIFY); - out: /* the last thing we do is clear state */ - for (i = 0; i < banks; i++) - wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0); + for (i = 0; i < banks; i++) { + if (test_bit(i, toclear)) + wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0); + } wrmsrl(MSR_IA32_MCG_STATUS, 0); out2: atomic_dec(&mce_entry); @@ -332,15 +434,13 @@ void do_machine_check(struct pt_regs * regs, long error_code) * and historically has been the register value of the * MSR_IA32_THERMAL_STATUS (Intel) msr. */ -void mce_log_therm_throt_event(unsigned int cpu, __u64 status) +void mce_log_therm_throt_event(__u64 status) { struct mce m; - memset(&m, 0, sizeof(m)); - m.cpu = cpu; + mce_setup(&m); m.bank = MCE_THERMAL_BANK; m.status = status; - rdtscll(m.tsc); mce_log(&m); } #endif /* CONFIG_X86_MCE_INTEL */ @@ -353,18 +453,18 @@ void mce_log_therm_throt_event(unsigned int cpu, __u64 status) static int check_interval = 5 * 60; /* 5 minutes */ static int next_interval; /* in jiffies */ -static void mcheck_timer(struct work_struct *work); -static DECLARE_DELAYED_WORK(mcheck_work, mcheck_timer); +static void mcheck_timer(unsigned long); +static DEFINE_PER_CPU(struct timer_list, mce_timer); -static void mcheck_check_cpu(void *info) +static void mcheck_timer(unsigned long data) { - if (mce_available(¤t_cpu_data)) - do_machine_check(NULL, 0); -} + struct timer_list *t = &per_cpu(mce_timer, data); -static void mcheck_timer(struct work_struct *work) -{ - on_each_cpu(mcheck_check_cpu, NULL, 1); + WARN_ON(smp_processor_id() != data); + + if (mce_available(¤t_cpu_data)) + machine_check_poll(MCP_TIMESTAMP, + &__get_cpu_var(mce_poll_banks)); /* * Alert userspace if needed. If we logged an MCE, reduce the @@ -377,31 +477,41 @@ static void mcheck_timer(struct work_struct *work) (int)round_jiffies_relative(check_interval*HZ)); } - schedule_delayed_work(&mcheck_work, next_interval); + t->expires = jiffies + next_interval; + add_timer(t); +} + +static void mce_do_trigger(struct work_struct *work) +{ + call_usermodehelper(trigger, trigger_argv, NULL, UMH_NO_WAIT); } +static DECLARE_WORK(mce_trigger_work, mce_do_trigger); + /* - * This is only called from process context. This is where we do - * anything we need to alert userspace about new MCEs. This is called - * directly from the poller and also from entry.S and idle, thanks to - * TIF_MCE_NOTIFY. + * Notify the user(s) about new machine check events. + * Can be called from interrupt context, but not from machine check/NMI + * context. */ int mce_notify_user(void) { + /* Not more than two messages every minute */ + static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); + clear_thread_flag(TIF_MCE_NOTIFY); if (test_and_clear_bit(0, ¬ify_user)) { - static unsigned long last_print; - unsigned long now = jiffies; - wake_up_interruptible(&mce_wait); - if (trigger[0]) - call_usermodehelper(trigger, trigger_argv, NULL, - UMH_NO_WAIT); - if (time_after_eq(now, last_print + (check_interval*HZ))) { - last_print = now; + /* + * There is no risk of missing notifications because + * work_pending is always cleared before the function is + * executed. + */ + if (trigger[0] && !work_pending(&mce_trigger_work)) + schedule_work(&mce_trigger_work); + + if (__ratelimit(&ratelimit)) printk(KERN_INFO "Machine check events logged\n"); - } return 1; } @@ -425,63 +535,78 @@ static struct notifier_block mce_idle_notifier = { static __init int periodic_mcheck_init(void) { - next_interval = check_interval * HZ; - if (next_interval) - schedule_delayed_work(&mcheck_work, - round_jiffies_relative(next_interval)); - idle_notifier_register(&mce_idle_notifier); - return 0; + idle_notifier_register(&mce_idle_notifier); + return 0; } __initcall(periodic_mcheck_init); - /* * Initialize Machine Checks for a CPU. */ -static void mce_init(void *dummy) +static int mce_cap_init(void) { u64 cap; - int i; + unsigned b; rdmsrl(MSR_IA32_MCG_CAP, cap); - banks = cap & 0xff; - if (banks > MCE_EXTENDED_BANK) { - banks = MCE_EXTENDED_BANK; - printk(KERN_INFO "MCE: warning: using only %d banks\n", - MCE_EXTENDED_BANK); + b = cap & 0xff; + if (b > MAX_NR_BANKS) { + printk(KERN_WARNING + "MCE: Using only %u machine check banks out of %u\n", + MAX_NR_BANKS, b); + b = MAX_NR_BANKS; } + + /* Don't support asymmetric configurations today */ + WARN_ON(banks != 0 && b != banks); + banks = b; + if (!bank) { + bank = kmalloc(banks * sizeof(u64), GFP_KERNEL); + if (!bank) + return -ENOMEM; + memset(bank, 0xff, banks * sizeof(u64)); + } + /* Use accurate RIP reporting if available. */ if ((cap & (1<<9)) && ((cap >> 16) & 0xff) >= 9) rip_msr = MSR_IA32_MCG_EIP; - /* Log the machine checks left over from the previous reset. - This also clears all registers */ - do_machine_check(NULL, mce_bootlog ? -1 : -2); + return 0; +} + +static void mce_init(void *dummy) +{ + u64 cap; + int i; + mce_banks_t all_banks; + + /* + * Log the machine checks left over from the previous reset. + */ + bitmap_fill(all_banks, MAX_NR_BANKS); + machine_check_poll(MCP_UC, &all_banks); set_in_cr4(X86_CR4_MCE); + rdmsrl(MSR_IA32_MCG_CAP, cap); if (cap & MCG_CTL_P) wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff); for (i = 0; i < banks; i++) { - if (i < NR_SYSFS_BANKS) - wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]); - else - wrmsrl(MSR_IA32_MC0_CTL+4*i, ~0UL); - + wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]); wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0); } } /* Add per CPU specific workarounds here */ -static void __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c) +static void mce_cpu_quirks(struct cpuinfo_x86 *c) { /* This should be disabled by the BIOS, but isn't always */ if (c->x86_vendor == X86_VENDOR_AMD) { - if(c->x86 == 15) + if (c->x86 == 15 && banks > 4) /* disable GART TBL walk error reporting, which trips off incorrectly with the IOMMU & 3ware & Cerberus. */ - clear_bit(10, &bank[4]); + clear_bit(10, (unsigned long *)&bank[4]); if(c->x86 <= 17 && mce_bootlog < 0) /* Lots of broken BIOS around that don't clear them by default and leave crap in there. Don't log. */ @@ -504,20 +629,38 @@ static void mce_cpu_features(struct cpuinfo_x86 *c) } } +static void mce_init_timer(void) +{ + struct timer_list *t = &__get_cpu_var(mce_timer); + + /* data race harmless because everyone sets to the same value */ + if (!next_interval) + next_interval = check_interval * HZ; + if (!next_interval) + return; + setup_timer(t, mcheck_timer, smp_processor_id()); + t->expires = round_jiffies(jiffies + next_interval); + add_timer(t); +} + /* * Called for each booted CPU to set up machine checks. * Must be called with preempt off. */ void __cpuinit mcheck_init(struct cpuinfo_x86 *c) { - mce_cpu_quirks(c); + if (!mce_available(c)) + return; - if (mce_dont_init || - !mce_available(c)) + if (mce_cap_init() < 0) { + mce_dont_init = 1; return; + } + mce_cpu_quirks(c); mce_init(NULL); mce_cpu_features(c); + mce_init_timer(); } /* @@ -573,7 +716,7 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, { unsigned long *cpu_tsc; static DEFINE_MUTEX(mce_read_mutex); - unsigned next; + unsigned prev, next; char __user *buf = ubuf; int i, err; @@ -592,25 +735,32 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, } err = 0; - for (i = 0; i < next; i++) { - unsigned long start = jiffies; - - while (!mcelog.entry[i].finished) { - if (time_after_eq(jiffies, start + 2)) { - memset(mcelog.entry + i,0, sizeof(struct mce)); - goto timeout; + prev = 0; + do { + for (i = prev; i < next; i++) { + unsigned long start = jiffies; + + while (!mcelog.entry[i].finished) { + if (time_after_eq(jiffies, start + 2)) { + memset(mcelog.entry + i, 0, + sizeof(struct mce)); + goto timeout; + } + cpu_relax(); } - cpu_relax(); + smp_rmb(); + err |= copy_to_user(buf, mcelog.entry + i, + sizeof(struct mce)); + buf += sizeof(struct mce); +timeout: + ; } - smp_rmb(); - err |= copy_to_user(buf, mcelog.entry + i, sizeof(struct mce)); - buf += sizeof(struct mce); - timeout: - ; - } - memset(mcelog.entry, 0, next * sizeof(struct mce)); - mcelog.next = 0; + memset(mcelog.entry + prev, 0, + (next - prev) * sizeof(struct mce)); + prev = next; + next = cmpxchg(&mcelog.next, prev, 0); + } while (next != prev); synchronize_sched(); @@ -680,20 +830,6 @@ static struct miscdevice mce_log_device = { &mce_chrdev_ops, }; -static unsigned long old_cr4 __initdata; - -void __init stop_mce(void) -{ - old_cr4 = read_cr4(); - clear_in_cr4(X86_CR4_MCE); -} - -void __init restart_mce(void) -{ - if (old_cr4 & X86_CR4_MCE) - set_in_cr4(X86_CR4_MCE); -} - /* * Old style boot options parsing. Only for compatibility. */ @@ -703,8 +839,7 @@ static int __init mcheck_disable(char *str) return 1; } -/* mce=off disables machine check. Note you can re-enable it later - using sysfs. +/* mce=off disables machine check. mce=TOLERANCELEVEL (number, see above) mce=bootlog Log MCEs from before booting. Disabled by default on AMD. mce=nobootlog Don't log MCEs from before booting. */ @@ -728,6 +863,29 @@ __setup("mce=", mcheck_enable); * Sysfs support */ +/* + * Disable machine checks on suspend and shutdown. We can't really handle + * them later. + */ +static int mce_disable(void) +{ + int i; + + for (i = 0; i < banks; i++) + wrmsrl(MSR_IA32_MC0_CTL + i*4, 0); + return 0; +} + +static int mce_suspend(struct sys_device *dev, pm_message_t state) +{ + return mce_disable(); +} + +static int mce_shutdown(struct sys_device *dev) +{ + return mce_disable(); +} + /* On resume clear all MCE state. Don't want to see leftovers from the BIOS. Only one CPU is active at this time, the others get readded later using CPU hotplug. */ @@ -738,20 +896,24 @@ static int mce_resume(struct sys_device *dev) return 0; } +static void mce_cpu_restart(void *data) +{ + del_timer_sync(&__get_cpu_var(mce_timer)); + if (mce_available(¤t_cpu_data)) + mce_init(NULL); + mce_init_timer(); +} + /* Reinit MCEs after user configuration changes */ static void mce_restart(void) { - if (next_interval) - cancel_delayed_work(&mcheck_work); - /* Timer race is harmless here */ - on_each_cpu(mce_init, NULL, 1); next_interval = check_interval * HZ; - if (next_interval) - schedule_delayed_work(&mcheck_work, - round_jiffies_relative(next_interval)); + on_each_cpu(mce_cpu_restart, NULL, 1); } static struct sysdev_class mce_sysclass = { + .suspend = mce_suspend, + .shutdown = mce_shutdown, .resume = mce_resume, .name = "machinecheck", }; @@ -778,16 +940,26 @@ void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu) __cpuinit } \ static SYSDEV_ATTR(name, 0644, show_ ## name, set_ ## name); -/* - * TBD should generate these dynamically based on number of available banks. - * Have only 6 contol banks in /sysfs until then. - */ -ACCESSOR(bank0ctl,bank[0],mce_restart()) -ACCESSOR(bank1ctl,bank[1],mce_restart()) -ACCESSOR(bank2ctl,bank[2],mce_restart()) -ACCESSOR(bank3ctl,bank[3],mce_restart()) -ACCESSOR(bank4ctl,bank[4],mce_restart()) -ACCESSOR(bank5ctl,bank[5],mce_restart()) +static struct sysdev_attribute *bank_attrs; + +static ssize_t show_bank(struct sys_device *s, struct sysdev_attribute *attr, + char *buf) +{ + u64 b = bank[attr - bank_attrs]; + return sprintf(buf, "%llx\n", b); +} + +static ssize_t set_bank(struct sys_device *s, struct sysdev_attribute *attr, + const char *buf, size_t siz) +{ + char *end; + u64 new = simple_strtoull(buf, &end, 0); + if (end == buf) + return -EINVAL; + bank[attr - bank_attrs] = new; + mce_restart(); + return end-buf; +} static ssize_t show_trigger(struct sys_device *s, struct sysdev_attribute *attr, char *buf) @@ -814,13 +986,11 @@ static SYSDEV_ATTR(trigger, 0644, show_trigger, set_trigger); static SYSDEV_INT_ATTR(tolerant, 0644, tolerant); ACCESSOR(check_interval,check_interval,mce_restart()) static struct sysdev_attribute *mce_attributes[] = { - &attr_bank0ctl, &attr_bank1ctl, &attr_bank2ctl, - &attr_bank3ctl, &attr_bank4ctl, &attr_bank5ctl, &attr_tolerant.attr, &attr_check_interval, &attr_trigger, NULL }; -static cpumask_t mce_device_initialized = CPU_MASK_NONE; +static cpumask_var_t mce_device_initialized; /* Per cpu sysdev init. All of the cpus still share the same ctl bank */ static __cpuinit int mce_create_device(unsigned int cpu) @@ -845,11 +1015,22 @@ static __cpuinit int mce_create_device(unsigned int cpu) if (err) goto error; } - cpu_set(cpu, mce_device_initialized); + for (i = 0; i < banks; i++) { + err = sysdev_create_file(&per_cpu(device_mce, cpu), + &bank_attrs[i]); + if (err) + goto error2; + } + cpumask_set_cpu(cpu, mce_device_initialized); return 0; +error2: + while (--i >= 0) { + sysdev_remove_file(&per_cpu(device_mce, cpu), + &bank_attrs[i]); + } error: - while (i--) { + while (--i >= 0) { sysdev_remove_file(&per_cpu(device_mce,cpu), mce_attributes[i]); } @@ -862,14 +1043,44 @@ static __cpuinit void mce_remove_device(unsigned int cpu) { int i; - if (!cpu_isset(cpu, mce_device_initialized)) + if (!cpumask_test_cpu(cpu, mce_device_initialized)) return; for (i = 0; mce_attributes[i]; i++) sysdev_remove_file(&per_cpu(device_mce,cpu), mce_attributes[i]); + for (i = 0; i < banks; i++) + sysdev_remove_file(&per_cpu(device_mce, cpu), + &bank_attrs[i]); sysdev_unregister(&per_cpu(device_mce,cpu)); - cpu_clear(cpu, mce_device_initialized); + cpumask_clear_cpu(cpu, mce_device_initialized); +} + +/* Make sure there are no machine checks on offlined CPUs. */ +static void mce_disable_cpu(void *h) +{ + int i; + unsigned long action = *(unsigned long *)h; + + if (!mce_available(¤t_cpu_data)) + return; + if (!(action & CPU_TASKS_FROZEN)) + cmci_clear(); + for (i = 0; i < banks; i++) + wrmsrl(MSR_IA32_MC0_CTL + i*4, 0); +} + +static void mce_reenable_cpu(void *h) +{ + int i; + unsigned long action = *(unsigned long *)h; + + if (!mce_available(¤t_cpu_data)) + return; + if (!(action & CPU_TASKS_FROZEN)) + cmci_reenable(); + for (i = 0; i < banks; i++) + wrmsrl(MSR_IA32_MC0_CTL + i*4, bank[i]); } /* Get notified when a cpu comes on/off. Be hotplug friendly. */ @@ -877,6 +1088,7 @@ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; + struct timer_list *t = &per_cpu(mce_timer, cpu); switch (action) { case CPU_ONLINE: @@ -891,6 +1103,21 @@ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb, threshold_cpu_callback(action, cpu); mce_remove_device(cpu); break; + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + del_timer_sync(t); + smp_call_function_single(cpu, mce_disable_cpu, &action, 1); + break; + case CPU_DOWN_FAILED: + case CPU_DOWN_FAILED_FROZEN: + t->expires = round_jiffies(jiffies + next_interval); + add_timer_on(t, cpu); + smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); + break; + case CPU_POST_DEAD: + /* intentionally ignoring frozen here */ + cmci_rediscover(cpu); + break; } return NOTIFY_OK; } @@ -899,6 +1126,34 @@ static struct notifier_block mce_cpu_notifier __cpuinitdata = { .notifier_call = mce_cpu_callback, }; +static __init int mce_init_banks(void) +{ + int i; + + bank_attrs = kzalloc(sizeof(struct sysdev_attribute) * banks, + GFP_KERNEL); + if (!bank_attrs) + return -ENOMEM; + + for (i = 0; i < banks; i++) { + struct sysdev_attribute *a = &bank_attrs[i]; + a->attr.name = kasprintf(GFP_KERNEL, "bank%d", i); + if (!a->attr.name) + goto nomem; + a->attr.mode = 0644; + a->show = show_bank; + a->store = set_bank; + } + return 0; + +nomem: + while (--i >= 0) + kfree(bank_attrs[i].attr.name); + kfree(bank_attrs); + bank_attrs = NULL; + return -ENOMEM; +} + static __init int mce_init_device(void) { int err; @@ -906,6 +1161,13 @@ static __init int mce_init_device(void) if (!mce_available(&boot_cpu_data)) return -EIO; + + alloc_cpumask_var(&mce_device_initialized, GFP_KERNEL); + + err = mce_init_banks(); + if (err) + return err; + err = sysdev_class_register(&mce_sysclass); if (err) return err; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c index 9817506..56dde9c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c @@ -79,6 +79,8 @@ static unsigned char shared_bank[NR_BANKS] = { static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */ +static void amd_threshold_interrupt(void); + /* * CPU Initialization */ @@ -90,7 +92,8 @@ struct thresh_restart { }; /* must be called with correct cpu affinity */ -static long threshold_restart_bank(void *_tr) +/* Called via smp_call_function_single() */ +static void threshold_restart_bank(void *_tr) { struct thresh_restart *tr = _tr; u32 mci_misc_hi, mci_misc_lo; @@ -117,7 +120,6 @@ static long threshold_restart_bank(void *_tr) mci_misc_hi |= MASK_COUNT_EN_HI; wrmsr(tr->b->address, mci_misc_lo, mci_misc_hi); - return 0; } /* cpu init entry point, called from mce.c with preempt off */ @@ -174,6 +176,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) tr.reset = 0; tr.old_limit = 0; threshold_restart_bank(&tr); + + mce_threshold_vector = amd_threshold_interrupt; } } } @@ -187,19 +191,13 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) * the interrupt goes off when error_count reaches threshold_limit. * the handler will simply log mcelog w/ software defined bank number. */ -asmlinkage void mce_threshold_interrupt(void) +static void amd_threshold_interrupt(void) { unsigned int bank, block; struct mce m; u32 low = 0, high = 0, address = 0; - ack_APIC_irq(); - exit_idle(); - irq_enter(); - - memset(&m, 0, sizeof(m)); - rdtscll(m.tsc); - m.cpu = smp_processor_id(); + mce_setup(&m); /* assume first bank caused it */ for (bank = 0; bank < NR_BANKS; ++bank) { @@ -233,7 +231,8 @@ asmlinkage void mce_threshold_interrupt(void) /* Log the machine check that caused the threshold event. */ - do_machine_check(NULL, 0); + machine_check_poll(MCP_TIMESTAMP, + &__get_cpu_var(mce_poll_banks)); if (high & MASK_OVERFLOW_HI) { rdmsrl(address, m.misc); @@ -243,13 +242,10 @@ asmlinkage void mce_threshold_interrupt(void) + bank * NR_BLOCKS + block; mce_log(&m); - goto out; + return; } } } -out: - inc_irq_stat(irq_threshold_count); - irq_exit(); } /* @@ -283,7 +279,7 @@ static ssize_t store_interrupt_enable(struct threshold_block *b, tr.b = b; tr.reset = 0; tr.old_limit = 0; - work_on_cpu(b->cpu, threshold_restart_bank, &tr); + smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1); return end - buf; } @@ -305,23 +301,32 @@ static ssize_t store_threshold_limit(struct threshold_block *b, tr.b = b; tr.reset = 0; - work_on_cpu(b->cpu, threshold_restart_bank, &tr); + smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1); return end - buf; } -static long local_error_count(void *_b) +struct threshold_block_cross_cpu { + struct threshold_block *tb; + long retval; +}; + +static void local_error_count_handler(void *_tbcc) { - struct threshold_block *b = _b; + struct threshold_block_cross_cpu *tbcc = _tbcc; + struct threshold_block *b = tbcc->tb; u32 low, high; rdmsr(b->address, low, high); - return (high & 0xFFF) - (THRESHOLD_MAX - b->threshold_limit); + tbcc->retval = (high & 0xFFF) - (THRESHOLD_MAX - b->threshold_limit); } static ssize_t show_error_count(struct threshold_block *b, char *buf) { - return sprintf(buf, "%lx\n", work_on_cpu(b->cpu, local_error_count, b)); + struct threshold_block_cross_cpu tbcc = { .tb = b, }; + + smp_call_function_single(b->cpu, local_error_count_handler, &tbcc, 1); + return sprintf(buf, "%lx\n", tbcc.retval); } static ssize_t store_error_count(struct threshold_block *b, @@ -329,7 +334,7 @@ static ssize_t store_error_count(struct threshold_block *b, { struct thresh_restart tr = { .b = b, .reset = 1, .old_limit = 0 }; - work_on_cpu(b->cpu, threshold_restart_bank, &tr); + smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1); return 1; } @@ -398,7 +403,7 @@ static __cpuinit int allocate_threshold_blocks(unsigned int cpu, if ((bank >= NR_BANKS) || (block >= NR_BLOCKS)) return 0; - if (rdmsr_safe(address, &low, &high)) + if (rdmsr_safe_on_cpu(cpu, address, &low, &high)) return 0; if (!(high & MASK_VALID_HI)) { @@ -462,12 +467,11 @@ out_free: return err; } -static __cpuinit long local_allocate_threshold_blocks(void *_bank) +static __cpuinit long +local_allocate_threshold_blocks(int cpu, unsigned int bank) { - unsigned int *bank = _bank; - - return allocate_threshold_blocks(smp_processor_id(), *bank, 0, - MSR_IA32_MC0_MISC + *bank * 4); + return allocate_threshold_blocks(cpu, bank, 0, + MSR_IA32_MC0_MISC + bank * 4); } /* symlinks sibling shared banks to first core. first core owns dir/files. */ @@ -481,7 +485,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) #ifdef CONFIG_SMP if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */ - i = cpumask_first(&per_cpu(cpu_core_map, cpu)); + i = cpumask_first(cpu_core_mask(cpu)); /* first core not up yet */ if (cpu_data(i).cpu_core_id) @@ -501,7 +505,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (err) goto out; - cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu)); + cpumask_copy(b->cpus, cpu_core_mask(cpu)); per_cpu(threshold_banks, cpu)[bank] = b; goto out; } @@ -525,12 +529,12 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) #ifndef CONFIG_SMP cpumask_setall(b->cpus); #else - cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu)); + cpumask_copy(b->cpus, cpu_core_mask(cpu)); #endif per_cpu(threshold_banks, cpu)[bank] = b; - err = work_on_cpu(cpu, local_allocate_threshold_blocks, &bank); + err = local_allocate_threshold_blocks(cpu, bank); if (err) goto out_free; diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c index aa5e287..d6b72df 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c @@ -1,6 +1,8 @@ /* * Intel specific MCE features. * Copyright 2004 Zwane Mwaikambo <zwane@linuxpower.ca> + * Copyright (C) 2008, 2009 Intel Corporation + * Author: Andi Kleen */ #include <linux/init.h> @@ -13,6 +15,7 @@ #include <asm/hw_irq.h> #include <asm/idle.h> #include <asm/therm_throt.h> +#include <asm/apic.h> asmlinkage void smp_thermal_interrupt(void) { @@ -25,7 +28,7 @@ asmlinkage void smp_thermal_interrupt(void) rdmsrl(MSR_IA32_THERM_STATUS, msr_val); if (therm_throt_process(msr_val & 1)) - mce_log_therm_throt_event(smp_processor_id(), msr_val); + mce_log_therm_throt_event(msr_val); inc_irq_stat(irq_thermal_count); irq_exit(); @@ -85,7 +88,209 @@ static void intel_init_thermal(struct cpuinfo_x86 *c) return; } +/* + * Support for Intel Correct Machine Check Interrupts. This allows + * the CPU to raise an interrupt when a corrected machine check happened. + * Normally we pick those up using a regular polling timer. + * Also supports reliable discovery of shared banks. + */ + +static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned); + +/* + * cmci_discover_lock protects against parallel discovery attempts + * which could race against each other. + */ +static DEFINE_SPINLOCK(cmci_discover_lock); + +#define CMCI_THRESHOLD 1 + +static int cmci_supported(int *banks) +{ + u64 cap; + + /* + * Vendor check is not strictly needed, but the initial + * initialization is vendor keyed and this + * makes sure none of the backdoors are entered otherwise. + */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return 0; + if (!cpu_has_apic || lapic_get_maxlvt() < 6) + return 0; + rdmsrl(MSR_IA32_MCG_CAP, cap); + *banks = min_t(unsigned, MAX_NR_BANKS, cap & 0xff); + return !!(cap & MCG_CMCI_P); +} + +/* + * The interrupt handler. This is called on every event. + * Just call the poller directly to log any events. + * This could in theory increase the threshold under high load, + * but doesn't for now. + */ +static void intel_threshold_interrupt(void) +{ + machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); + mce_notify_user(); +} + +static void print_update(char *type, int *hdr, int num) +{ + if (*hdr == 0) + printk(KERN_INFO "CPU %d MCA banks", smp_processor_id()); + *hdr = 1; + printk(KERN_CONT " %s:%d", type, num); +} + +/* + * Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks + * on this CPU. Use the algorithm recommended in the SDM to discover shared + * banks. + */ +static void cmci_discover(int banks, int boot) +{ + unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned); + int hdr = 0; + int i; + + spin_lock(&cmci_discover_lock); + for (i = 0; i < banks; i++) { + u64 val; + + if (test_bit(i, owned)) + continue; + + rdmsrl(MSR_IA32_MC0_CTL2 + i, val); + + /* Already owned by someone else? */ + if (val & CMCI_EN) { + if (test_and_clear_bit(i, owned) || boot) + print_update("SHD", &hdr, i); + __clear_bit(i, __get_cpu_var(mce_poll_banks)); + continue; + } + + val |= CMCI_EN | CMCI_THRESHOLD; + wrmsrl(MSR_IA32_MC0_CTL2 + i, val); + rdmsrl(MSR_IA32_MC0_CTL2 + i, val); + + /* Did the enable bit stick? -- the bank supports CMCI */ + if (val & CMCI_EN) { + if (!test_and_set_bit(i, owned) || boot) + print_update("CMCI", &hdr, i); + __clear_bit(i, __get_cpu_var(mce_poll_banks)); + } else { + WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks))); + } + } + spin_unlock(&cmci_discover_lock); + if (hdr) + printk(KERN_CONT "\n"); +} + +/* + * Just in case we missed an event during initialization check + * all the CMCI owned banks. + */ +void cmci_recheck(void) +{ + unsigned long flags; + int banks; + + if (!mce_available(¤t_cpu_data) || !cmci_supported(&banks)) + return; + local_irq_save(flags); + machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); + local_irq_restore(flags); +} + +/* + * Disable CMCI on this CPU for all banks it owns when it goes down. + * This allows other CPUs to claim the banks on rediscovery. + */ +void cmci_clear(void) +{ + int i; + int banks; + u64 val; + + if (!cmci_supported(&banks)) + return; + spin_lock(&cmci_discover_lock); + for (i = 0; i < banks; i++) { + if (!test_bit(i, __get_cpu_var(mce_banks_owned))) + continue; + /* Disable CMCI */ + rdmsrl(MSR_IA32_MC0_CTL2 + i, val); + val &= ~(CMCI_EN|CMCI_THRESHOLD_MASK); + wrmsrl(MSR_IA32_MC0_CTL2 + i, val); + __clear_bit(i, __get_cpu_var(mce_banks_owned)); + } + spin_unlock(&cmci_discover_lock); +} + +/* + * After a CPU went down cycle through all the others and rediscover + * Must run in process context. + */ +void cmci_rediscover(int dying) +{ + int banks; + int cpu; + cpumask_var_t old; + + if (!cmci_supported(&banks)) + return; + if (!alloc_cpumask_var(&old, GFP_KERNEL)) + return; + cpumask_copy(old, ¤t->cpus_allowed); + + for_each_online_cpu (cpu) { + if (cpu == dying) + continue; + if (set_cpus_allowed_ptr(current, cpumask_of(cpu))) + continue; + /* Recheck banks in case CPUs don't all have the same */ + if (cmci_supported(&banks)) + cmci_discover(banks, 0); + } + + set_cpus_allowed_ptr(current, old); + free_cpumask_var(old); +} + +/* + * Reenable CMCI on this CPU in case a CPU down failed. + */ +void cmci_reenable(void) +{ + int banks; + if (cmci_supported(&banks)) + cmci_discover(banks, 0); +} + +static void intel_init_cmci(void) +{ + int banks; + + if (!cmci_supported(&banks)) + return; + + mce_threshold_vector = intel_threshold_interrupt; + cmci_discover(banks, 1); + /* + * For CPU #0 this runs with still disabled APIC, but that's + * ok because only the vector is set up. We still do another + * check for the banks later for CPU #0 just to make sure + * to not miss any events. + */ + apic_write(APIC_LVTCMCI, THRESHOLD_APIC_VECTOR|APIC_DM_FIXED); + cmci_recheck(); +} + void mce_intel_feature_init(struct cpuinfo_x86 *c) { intel_init_thermal(c); + intel_init_cmci(); } diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c new file mode 100644 index 0000000..23ee9e7 --- /dev/null +++ b/arch/x86/kernel/cpu/mcheck/threshold.c @@ -0,0 +1,29 @@ +/* + * Common corrected MCE threshold handler code: + */ +#include <linux/interrupt.h> +#include <linux/kernel.h> + +#include <asm/irq_vectors.h> +#include <asm/apic.h> +#include <asm/idle.h> +#include <asm/mce.h> + +static void default_threshold_interrupt(void) +{ + printk(KERN_ERR "Unexpected threshold interrupt at vector %x\n", + THRESHOLD_APIC_VECTOR); +} + +void (*mce_threshold_vector)(void) = default_threshold_interrupt; + +asmlinkage void mce_threshold_interrupt(void) +{ + exit_idle(); + irq_enter(); + inc_irq_stat(irq_threshold_count); + mce_threshold_vector(); + irq_exit(); + /* Ack only at the end to avoid potential reentry */ + ack_APIC_irq(); +} diff --git a/arch/x86/kernel/cpu/mtrr/Makefile b/arch/x86/kernel/cpu/mtrr/Makefile index 191fc05..f4361b5 100644 --- a/arch/x86/kernel/cpu/mtrr/Makefile +++ b/arch/x86/kernel/cpu/mtrr/Makefile @@ -1,3 +1,3 @@ -obj-y := main.o if.o generic.o state.o +obj-y := main.o if.o generic.o state.o cleanup.o obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c new file mode 100644 index 0000000..ce0fe4b --- /dev/null +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -0,0 +1,1101 @@ +/* MTRR (Memory Type Range Register) cleanup + + Copyright (C) 2009 Yinghai Lu + + This library is free software; you can redistribute it and/or + modify it under the terms of the GNU Library General Public + License as published by the Free Software Foundation; either + version 2 of the License, or (at your option) any later version. + + This library 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 + Library General Public License for more details. + + You should have received a copy of the GNU Library General Public + License along with this library; if not, write to the Free + Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. +*/ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/smp.h> +#include <linux/cpu.h> +#include <linux/mutex.h> +#include <linux/sort.h> + +#include <asm/e820.h> +#include <asm/mtrr.h> +#include <asm/uaccess.h> +#include <asm/processor.h> +#include <asm/msr.h> +#include <asm/kvm_para.h> +#include "mtrr.h" + +/* should be related to MTRR_VAR_RANGES nums */ +#define RANGE_NUM 256 + +struct res_range { + unsigned long start; + unsigned long end; +}; + +static int __init +add_range(struct res_range *range, int nr_range, unsigned long start, + unsigned long end) +{ + /* out of slots */ + if (nr_range >= RANGE_NUM) + return nr_range; + + range[nr_range].start = start; + range[nr_range].end = end; + + nr_range++; + + return nr_range; +} + +static int __init +add_range_with_merge(struct res_range *range, int nr_range, unsigned long start, + unsigned long end) +{ + int i; + + /* try to merge it with old one */ + for (i = 0; i < nr_range; i++) { + unsigned long final_start, final_end; + unsigned long common_start, common_end; + + if (!range[i].end) + continue; + + common_start = max(range[i].start, start); + common_end = min(range[i].end, end); + if (common_start > common_end + 1) + continue; + + final_start = min(range[i].start, start); + final_end = max(range[i].end, end); + + range[i].start = final_start; + range[i].end = final_end; + return nr_range; + } + + /* need to add that */ + return add_range(range, nr_range, start, end); +} + +static void __init +subtract_range(struct res_range *range, unsigned long start, unsigned long end) +{ + int i, j; + + for (j = 0; j < RANGE_NUM; j++) { + if (!range[j].end) + continue; + + if (start <= range[j].start && end >= range[j].end) { + range[j].start = 0; + range[j].end = 0; + continue; + } + + if (start <= range[j].start && end < range[j].end && + range[j].start < end + 1) { + range[j].start = end + 1; + continue; + } + + + if (start > range[j].start && end >= range[j].end && + range[j].end > start - 1) { + range[j].end = start - 1; + continue; + } + + if (start > range[j].start && end < range[j].end) { + /* find the new spare */ + for (i = 0; i < RANGE_NUM; i++) { + if (range[i].end == 0) + break; + } + if (i < RANGE_NUM) { + range[i].end = range[j].end; + range[i].start = end + 1; + } else { + printk(KERN_ERR "run of slot in ranges\n"); + } + range[j].end = start - 1; + continue; + } + } +} + +static int __init cmp_range(const void *x1, const void *x2) +{ + const struct res_range *r1 = x1; + const struct res_range *r2 = x2; + long start1, start2; + + start1 = r1->start; + start2 = r2->start; + + return start1 - start2; +} + +struct var_mtrr_range_state { + unsigned long base_pfn; + unsigned long size_pfn; + mtrr_type type; +}; + +static struct var_mtrr_range_state __initdata range_state[RANGE_NUM]; +static int __initdata debug_print; + +static int __init +x86_get_mtrr_mem_range(struct res_range *range, int nr_range, + unsigned long extra_remove_base, + unsigned long extra_remove_size) +{ + unsigned long base, size; + mtrr_type type; + int i; + + for (i = 0; i < num_var_ranges; i++) { + type = range_state[i].type; + if (type != MTRR_TYPE_WRBACK) + continue; + base = range_state[i].base_pfn; + size = range_state[i].size_pfn; + nr_range = add_range_with_merge(range, nr_range, base, + base + size - 1); + } + if (debug_print) { + printk(KERN_DEBUG "After WB checking\n"); + for (i = 0; i < nr_range; i++) + printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", + range[i].start, range[i].end + 1); + } + + /* take out UC ranges */ + for (i = 0; i < num_var_ranges; i++) { + type = range_state[i].type; + if (type != MTRR_TYPE_UNCACHABLE && + type != MTRR_TYPE_WRPROT) + continue; + size = range_state[i].size_pfn; + if (!size) + continue; + base = range_state[i].base_pfn; + if (base < (1<<(20-PAGE_SHIFT)) && mtrr_state.have_fixed && + (mtrr_state.enabled & 1)) { + /* Var MTRR contains UC entry below 1M? Skip it: */ + printk(KERN_WARNING "WARNING: BIOS bug: VAR MTRR %d " + "contains strange UC entry under 1M, check " + "with your system vendor!\n", i); + if (base + size <= (1<<(20-PAGE_SHIFT))) + continue; + size -= (1<<(20-PAGE_SHIFT)) - base; + base = 1<<(20-PAGE_SHIFT); + } + subtract_range(range, base, base + size - 1); + } + if (extra_remove_size) + subtract_range(range, extra_remove_base, + extra_remove_base + extra_remove_size - 1); + + /* get new range num */ + nr_range = 0; + for (i = 0; i < RANGE_NUM; i++) { + if (!range[i].end) + continue; + nr_range++; + } + if (debug_print) { + printk(KERN_DEBUG "After UC checking\n"); + for (i = 0; i < nr_range; i++) + printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", + range[i].start, range[i].end + 1); + } + + /* sort the ranges */ + sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL); + if (debug_print) { + printk(KERN_DEBUG "After sorting\n"); + for (i = 0; i < nr_range; i++) + printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", + range[i].start, range[i].end + 1); + } + + /* clear those is not used */ + for (i = nr_range; i < RANGE_NUM; i++) + memset(&range[i], 0, sizeof(range[i])); + + return nr_range; +} + +static struct res_range __initdata range[RANGE_NUM]; +static int __initdata nr_range; + +#ifdef CONFIG_MTRR_SANITIZER + +static unsigned long __init sum_ranges(struct res_range *range, int nr_range) +{ + unsigned long sum; + int i; + + sum = 0; + for (i = 0; i < nr_range; i++) + sum += range[i].end + 1 - range[i].start; + + return sum; +} + +static int enable_mtrr_cleanup __initdata = + CONFIG_MTRR_SANITIZER_ENABLE_DEFAULT; + +static int __init disable_mtrr_cleanup_setup(char *str) +{ + enable_mtrr_cleanup = 0; + return 0; +} +early_param("disable_mtrr_cleanup", disable_mtrr_cleanup_setup); + +static int __init enable_mtrr_cleanup_setup(char *str) +{ + enable_mtrr_cleanup = 1; + return 0; +} +early_param("enable_mtrr_cleanup", enable_mtrr_cleanup_setup); + +static int __init mtrr_cleanup_debug_setup(char *str) +{ + debug_print = 1; + return 0; +} +early_param("mtrr_cleanup_debug", mtrr_cleanup_debug_setup); + +struct var_mtrr_state { + unsigned long range_startk; + unsigned long range_sizek; + unsigned long chunk_sizek; + unsigned long gran_sizek; + unsigned int reg; +}; + +static void __init +set_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek, + unsigned char type, unsigned int address_bits) +{ + u32 base_lo, base_hi, mask_lo, mask_hi; + u64 base, mask; + + if (!sizek) { + fill_mtrr_var_range(reg, 0, 0, 0, 0); + return; + } + + mask = (1ULL << address_bits) - 1; + mask &= ~((((u64)sizek) << 10) - 1); + + base = ((u64)basek) << 10; + + base |= type; + mask |= 0x800; + + base_lo = base & ((1ULL<<32) - 1); + base_hi = base >> 32; + + mask_lo = mask & ((1ULL<<32) - 1); + mask_hi = mask >> 32; + + fill_mtrr_var_range(reg, base_lo, base_hi, mask_lo, mask_hi); +} + +static void __init +save_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek, + unsigned char type) +{ + range_state[reg].base_pfn = basek >> (PAGE_SHIFT - 10); + range_state[reg].size_pfn = sizek >> (PAGE_SHIFT - 10); + range_state[reg].type = type; +} + +static void __init +set_var_mtrr_all(unsigned int address_bits) +{ + unsigned long basek, sizek; + unsigned char type; + unsigned int reg; + + for (reg = 0; reg < num_var_ranges; reg++) { + basek = range_state[reg].base_pfn << (PAGE_SHIFT - 10); + sizek = range_state[reg].size_pfn << (PAGE_SHIFT - 10); + type = range_state[reg].type; + + set_var_mtrr(reg, basek, sizek, type, address_bits); + } +} + +static unsigned long to_size_factor(unsigned long sizek, char *factorp) +{ + char factor; + unsigned long base = sizek; + + if (base & ((1<<10) - 1)) { + /* not MB alignment */ + factor = 'K'; + } else if (base & ((1<<20) - 1)) { + factor = 'M'; + base >>= 10; + } else { + factor = 'G'; + base >>= 20; + } + + *factorp = factor; + + return base; +} + +static unsigned int __init +range_to_mtrr(unsigned int reg, unsigned long range_startk, + unsigned long range_sizek, unsigned char type) +{ + if (!range_sizek || (reg >= num_var_ranges)) + return reg; + + while (range_sizek) { + unsigned long max_align, align; + unsigned long sizek; + + /* Compute the maximum size I can make a range */ + if (range_startk) + max_align = ffs(range_startk) - 1; + else + max_align = 32; + align = fls(range_sizek) - 1; + if (align > max_align) + align = max_align; + + sizek = 1 << align; + if (debug_print) { + char start_factor = 'K', size_factor = 'K'; + unsigned long start_base, size_base; + + start_base = to_size_factor(range_startk, + &start_factor), + size_base = to_size_factor(sizek, &size_factor), + + printk(KERN_DEBUG "Setting variable MTRR %d, " + "base: %ld%cB, range: %ld%cB, type %s\n", + reg, start_base, start_factor, + size_base, size_factor, + (type == MTRR_TYPE_UNCACHABLE) ? "UC" : + ((type == MTRR_TYPE_WRBACK) ? "WB" : "Other") + ); + } + save_var_mtrr(reg++, range_startk, sizek, type); + range_startk += sizek; + range_sizek -= sizek; + if (reg >= num_var_ranges) + break; + } + return reg; +} + +static unsigned __init +range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek, + unsigned long sizek) +{ + unsigned long hole_basek, hole_sizek; + unsigned long second_basek, second_sizek; + unsigned long range0_basek, range0_sizek; + unsigned long range_basek, range_sizek; + unsigned long chunk_sizek; + unsigned long gran_sizek; + + hole_basek = 0; + hole_sizek = 0; + second_basek = 0; + second_sizek = 0; + chunk_sizek = state->chunk_sizek; + gran_sizek = state->gran_sizek; + + /* align with gran size, prevent small block used up MTRRs */ + range_basek = ALIGN(state->range_startk, gran_sizek); + if ((range_basek > basek) && basek) + return second_sizek; + state->range_sizek -= (range_basek - state->range_startk); + range_sizek = ALIGN(state->range_sizek, gran_sizek); + + while (range_sizek > state->range_sizek) { + range_sizek -= gran_sizek; + if (!range_sizek) + return 0; + } + state->range_sizek = range_sizek; + + /* try to append some small hole */ + range0_basek = state->range_startk; + range0_sizek = ALIGN(state->range_sizek, chunk_sizek); + + /* no increase */ + if (range0_sizek == state->range_sizek) { + if (debug_print) + printk(KERN_DEBUG "rangeX: %016lx - %016lx\n", + range0_basek<<10, + (range0_basek + state->range_sizek)<<10); + state->reg = range_to_mtrr(state->reg, range0_basek, + state->range_sizek, MTRR_TYPE_WRBACK); + return 0; + } + + /* only cut back, when it is not the last */ + if (sizek) { + while (range0_basek + range0_sizek > (basek + sizek)) { + if (range0_sizek >= chunk_sizek) + range0_sizek -= chunk_sizek; + else + range0_sizek = 0; + + if (!range0_sizek) + break; + } + } + +second_try: + range_basek = range0_basek + range0_sizek; + + /* one hole in the middle */ + if (range_basek > basek && range_basek <= (basek + sizek)) + second_sizek = range_basek - basek; + + if (range0_sizek > state->range_sizek) { + + /* one hole in middle or at end */ + hole_sizek = range0_sizek - state->range_sizek - second_sizek; + + /* hole size should be less than half of range0 size */ + if (hole_sizek >= (range0_sizek >> 1) && + range0_sizek >= chunk_sizek) { + range0_sizek -= chunk_sizek; + second_sizek = 0; + hole_sizek = 0; + + goto second_try; + } + } + + if (range0_sizek) { + if (debug_print) + printk(KERN_DEBUG "range0: %016lx - %016lx\n", + range0_basek<<10, + (range0_basek + range0_sizek)<<10); + state->reg = range_to_mtrr(state->reg, range0_basek, + range0_sizek, MTRR_TYPE_WRBACK); + } + + if (range0_sizek < state->range_sizek) { + /* need to handle left over */ + range_sizek = state->range_sizek - range0_sizek; + + if (debug_print) + printk(KERN_DEBUG "range: %016lx - %016lx\n", + range_basek<<10, + (range_basek + range_sizek)<<10); + state->reg = range_to_mtrr(state->reg, range_basek, + range_sizek, MTRR_TYPE_WRBACK); + } + + if (hole_sizek) { + hole_basek = range_basek - hole_sizek - second_sizek; + if (debug_print) + printk(KERN_DEBUG "hole: %016lx - %016lx\n", + hole_basek<<10, + (hole_basek + hole_sizek)<<10); + state->reg = range_to_mtrr(state->reg, hole_basek, + hole_sizek, MTRR_TYPE_UNCACHABLE); + } + + return second_sizek; +} + +static void __init +set_var_mtrr_range(struct var_mtrr_state *state, unsigned long base_pfn, + unsigned long size_pfn) +{ + unsigned long basek, sizek; + unsigned long second_sizek = 0; + + if (state->reg >= num_var_ranges) + return; + + basek = base_pfn << (PAGE_SHIFT - 10); + sizek = size_pfn << (PAGE_SHIFT - 10); + + /* See if I can merge with the last range */ + if ((basek <= 1024) || + (state->range_startk + state->range_sizek == basek)) { + unsigned long endk = basek + sizek; + state->range_sizek = endk - state->range_startk; + return; + } + /* Write the range mtrrs */ + if (state->range_sizek != 0) + second_sizek = range_to_mtrr_with_hole(state, basek, sizek); + + /* Allocate an msr */ + state->range_startk = basek + second_sizek; + state->range_sizek = sizek - second_sizek; +} + +/* mininum size of mtrr block that can take hole */ +static u64 mtrr_chunk_size __initdata = (256ULL<<20); + +static int __init parse_mtrr_chunk_size_opt(char *p) +{ + if (!p) + return -EINVAL; + mtrr_chunk_size = memparse(p, &p); + return 0; +} +early_param("mtrr_chunk_size", parse_mtrr_chunk_size_opt); + +/* granity of mtrr of block */ +static u64 mtrr_gran_size __initdata; + +static int __init parse_mtrr_gran_size_opt(char *p) +{ + if (!p) + return -EINVAL; + mtrr_gran_size = memparse(p, &p); + return 0; +} +early_param("mtrr_gran_size", parse_mtrr_gran_size_opt); + +static int nr_mtrr_spare_reg __initdata = + CONFIG_MTRR_SANITIZER_SPARE_REG_NR_DEFAULT; + +static int __init parse_mtrr_spare_reg(char *arg) +{ + if (arg) + nr_mtrr_spare_reg = simple_strtoul(arg, NULL, 0); + return 0; +} + +early_param("mtrr_spare_reg_nr", parse_mtrr_spare_reg); + +static int __init +x86_setup_var_mtrrs(struct res_range *range, int nr_range, + u64 chunk_size, u64 gran_size) +{ + struct var_mtrr_state var_state; + int i; + int num_reg; + + var_state.range_startk = 0; + var_state.range_sizek = 0; + var_state.reg = 0; + var_state.chunk_sizek = chunk_size >> 10; + var_state.gran_sizek = gran_size >> 10; + + memset(range_state, 0, sizeof(range_state)); + + /* Write the range etc */ + for (i = 0; i < nr_range; i++) + set_var_mtrr_range(&var_state, range[i].start, + range[i].end - range[i].start + 1); + + /* Write the last range */ + if (var_state.range_sizek != 0) + range_to_mtrr_with_hole(&var_state, 0, 0); + + num_reg = var_state.reg; + /* Clear out the extra MTRR's */ + while (var_state.reg < num_var_ranges) { + save_var_mtrr(var_state.reg, 0, 0, 0); + var_state.reg++; + } + + return num_reg; +} + +struct mtrr_cleanup_result { + unsigned long gran_sizek; + unsigned long chunk_sizek; + unsigned long lose_cover_sizek; + unsigned int num_reg; + int bad; +}; + +/* + * gran_size: 64K, 128K, 256K, 512K, 1M, 2M, ..., 2G + * chunk size: gran_size, ..., 2G + * so we need (1+16)*8 + */ +#define NUM_RESULT 136 +#define PSHIFT (PAGE_SHIFT - 10) + +static struct mtrr_cleanup_result __initdata result[NUM_RESULT]; +static unsigned long __initdata min_loss_pfn[RANGE_NUM]; + +static void __init print_out_mtrr_range_state(void) +{ + int i; + char start_factor = 'K', size_factor = 'K'; + unsigned long start_base, size_base; + mtrr_type type; + + for (i = 0; i < num_var_ranges; i++) { + + size_base = range_state[i].size_pfn << (PAGE_SHIFT - 10); + if (!size_base) + continue; + + size_base = to_size_factor(size_base, &size_factor), + start_base = range_state[i].base_pfn << (PAGE_SHIFT - 10); + start_base = to_size_factor(start_base, &start_factor), + type = range_state[i].type; + + printk(KERN_DEBUG "reg %d, base: %ld%cB, range: %ld%cB, type %s\n", + i, start_base, start_factor, + size_base, size_factor, + (type == MTRR_TYPE_UNCACHABLE) ? "UC" : + ((type == MTRR_TYPE_WRPROT) ? "WP" : + ((type == MTRR_TYPE_WRBACK) ? "WB" : "Other")) + ); + } +} + +static int __init mtrr_need_cleanup(void) +{ + int i; + mtrr_type type; + unsigned long size; + /* extra one for all 0 */ + int num[MTRR_NUM_TYPES + 1]; + + /* check entries number */ + memset(num, 0, sizeof(num)); + for (i = 0; i < num_var_ranges; i++) { + type = range_state[i].type; + size = range_state[i].size_pfn; + if (type >= MTRR_NUM_TYPES) + continue; + if (!size) + type = MTRR_NUM_TYPES; + if (type == MTRR_TYPE_WRPROT) + type = MTRR_TYPE_UNCACHABLE; + num[type]++; + } + + /* check if we got UC entries */ + if (!num[MTRR_TYPE_UNCACHABLE]) + return 0; + + /* check if we only had WB and UC */ + if (num[MTRR_TYPE_WRBACK] + num[MTRR_TYPE_UNCACHABLE] != + num_var_ranges - num[MTRR_NUM_TYPES]) + return 0; + + return 1; +} + +static unsigned long __initdata range_sums; +static void __init mtrr_calc_range_state(u64 chunk_size, u64 gran_size, + unsigned long extra_remove_base, + unsigned long extra_remove_size, + int i) +{ + int num_reg; + static struct res_range range_new[RANGE_NUM]; + static int nr_range_new; + unsigned long range_sums_new; + + /* convert ranges to var ranges state */ + num_reg = x86_setup_var_mtrrs(range, nr_range, + chunk_size, gran_size); + + /* we got new setting in range_state, check it */ + memset(range_new, 0, sizeof(range_new)); + nr_range_new = x86_get_mtrr_mem_range(range_new, 0, + extra_remove_base, extra_remove_size); + range_sums_new = sum_ranges(range_new, nr_range_new); + + result[i].chunk_sizek = chunk_size >> 10; + result[i].gran_sizek = gran_size >> 10; + result[i].num_reg = num_reg; + if (range_sums < range_sums_new) { + result[i].lose_cover_sizek = + (range_sums_new - range_sums) << PSHIFT; + result[i].bad = 1; + } else + result[i].lose_cover_sizek = + (range_sums - range_sums_new) << PSHIFT; + + /* double check it */ + if (!result[i].bad && !result[i].lose_cover_sizek) { + if (nr_range_new != nr_range || + memcmp(range, range_new, sizeof(range))) + result[i].bad = 1; + } + + if (!result[i].bad && (range_sums - range_sums_new < + min_loss_pfn[num_reg])) { + min_loss_pfn[num_reg] = + range_sums - range_sums_new; + } +} + +static void __init mtrr_print_out_one_result(int i) +{ + char gran_factor, chunk_factor, lose_factor; + unsigned long gran_base, chunk_base, lose_base; + + gran_base = to_size_factor(result[i].gran_sizek, &gran_factor), + chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor), + lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor), + printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t", + result[i].bad ? "*BAD*" : " ", + gran_base, gran_factor, chunk_base, chunk_factor); + printk(KERN_CONT "num_reg: %d \tlose cover RAM: %s%ld%c\n", + result[i].num_reg, result[i].bad ? "-" : "", + lose_base, lose_factor); +} + +static int __init mtrr_search_optimal_index(void) +{ + int i; + int num_reg_good; + int index_good; + + if (nr_mtrr_spare_reg >= num_var_ranges) + nr_mtrr_spare_reg = num_var_ranges - 1; + num_reg_good = -1; + for (i = num_var_ranges - nr_mtrr_spare_reg; i > 0; i--) { + if (!min_loss_pfn[i]) + num_reg_good = i; + } + + index_good = -1; + if (num_reg_good != -1) { + for (i = 0; i < NUM_RESULT; i++) { + if (!result[i].bad && + result[i].num_reg == num_reg_good && + !result[i].lose_cover_sizek) { + index_good = i; + break; + } + } + } + + return index_good; +} + + +int __init mtrr_cleanup(unsigned address_bits) +{ + unsigned long extra_remove_base, extra_remove_size; + unsigned long base, size, def, dummy; + mtrr_type type; + u64 chunk_size, gran_size; + int index_good; + int i; + + if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1) + return 0; + rdmsr(MTRRdefType_MSR, def, dummy); + def &= 0xff; + if (def != MTRR_TYPE_UNCACHABLE) + return 0; + + /* get it and store it aside */ + memset(range_state, 0, sizeof(range_state)); + for (i = 0; i < num_var_ranges; i++) { + mtrr_if->get(i, &base, &size, &type); + range_state[i].base_pfn = base; + range_state[i].size_pfn = size; + range_state[i].type = type; + } + + /* check if we need handle it and can handle it */ + if (!mtrr_need_cleanup()) + return 0; + + /* print original var MTRRs at first, for debugging: */ + printk(KERN_DEBUG "original variable MTRRs\n"); + print_out_mtrr_range_state(); + + memset(range, 0, sizeof(range)); + extra_remove_size = 0; + extra_remove_base = 1 << (32 - PAGE_SHIFT); + if (mtrr_tom2) + extra_remove_size = + (mtrr_tom2 >> PAGE_SHIFT) - extra_remove_base; + nr_range = x86_get_mtrr_mem_range(range, 0, extra_remove_base, + extra_remove_size); + /* + * [0, 1M) should always be coverred by var mtrr with WB + * and fixed mtrrs should take effective before var mtrr for it + */ + nr_range = add_range_with_merge(range, nr_range, 0, + (1ULL<<(20 - PAGE_SHIFT)) - 1); + /* sort the ranges */ + sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL); + + range_sums = sum_ranges(range, nr_range); + printk(KERN_INFO "total RAM coverred: %ldM\n", + range_sums >> (20 - PAGE_SHIFT)); + + if (mtrr_chunk_size && mtrr_gran_size) { + i = 0; + mtrr_calc_range_state(mtrr_chunk_size, mtrr_gran_size, + extra_remove_base, extra_remove_size, i); + + mtrr_print_out_one_result(i); + + if (!result[i].bad) { + set_var_mtrr_all(address_bits); + printk(KERN_DEBUG "New variable MTRRs\n"); + print_out_mtrr_range_state(); + return 1; + } + printk(KERN_INFO "invalid mtrr_gran_size or mtrr_chunk_size, " + "will find optimal one\n"); + } + + i = 0; + memset(min_loss_pfn, 0xff, sizeof(min_loss_pfn)); + memset(result, 0, sizeof(result)); + for (gran_size = (1ULL<<16); gran_size < (1ULL<<32); gran_size <<= 1) { + + for (chunk_size = gran_size; chunk_size < (1ULL<<32); + chunk_size <<= 1) { + + if (i >= NUM_RESULT) + continue; + + mtrr_calc_range_state(chunk_size, gran_size, + extra_remove_base, extra_remove_size, i); + if (debug_print) { + mtrr_print_out_one_result(i); + printk(KERN_INFO "\n"); + } + + i++; + } + } + + /* try to find the optimal index */ + index_good = mtrr_search_optimal_index(); + + if (index_good != -1) { + printk(KERN_INFO "Found optimal setting for mtrr clean up\n"); + i = index_good; + mtrr_print_out_one_result(i); + + /* convert ranges to var ranges state */ + chunk_size = result[i].chunk_sizek; + chunk_size <<= 10; + gran_size = result[i].gran_sizek; + gran_size <<= 10; + x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size); + set_var_mtrr_all(address_bits); + printk(KERN_DEBUG "New variable MTRRs\n"); + print_out_mtrr_range_state(); + return 1; + } else { + /* print out all */ + for (i = 0; i < NUM_RESULT; i++) + mtrr_print_out_one_result(i); + } + + printk(KERN_INFO "mtrr_cleanup: can not find optimal value\n"); + printk(KERN_INFO "please specify mtrr_gran_size/mtrr_chunk_size\n"); + + return 0; +} +#else +int __init mtrr_cleanup(unsigned address_bits) +{ + return 0; +} +#endif + +static int disable_mtrr_trim; + +static int __init disable_mtrr_trim_setup(char *str) +{ + disable_mtrr_trim = 1; + return 0; +} +early_param("disable_mtrr_trim", disable_mtrr_trim_setup); + +/* + * Newer AMD K8s and later CPUs have a special magic MSR way to force WB + * for memory >4GB. Check for that here. + * Note this won't check if the MTRRs < 4GB where the magic bit doesn't + * apply to are wrong, but so far we don't know of any such case in the wild. + */ +#define Tom2Enabled (1U << 21) +#define Tom2ForceMemTypeWB (1U << 22) + +int __init amd_special_default_mtrr(void) +{ + u32 l, h; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return 0; + if (boot_cpu_data.x86 < 0xf || boot_cpu_data.x86 > 0x11) + return 0; + /* In case some hypervisor doesn't pass SYSCFG through */ + if (rdmsr_safe(MSR_K8_SYSCFG, &l, &h) < 0) + return 0; + /* + * Memory between 4GB and top of mem is forced WB by this magic bit. + * Reserved before K8RevF, but should be zero there. + */ + if ((l & (Tom2Enabled | Tom2ForceMemTypeWB)) == + (Tom2Enabled | Tom2ForceMemTypeWB)) + return 1; + return 0; +} + +static u64 __init real_trim_memory(unsigned long start_pfn, + unsigned long limit_pfn) +{ + u64 trim_start, trim_size; + trim_start = start_pfn; + trim_start <<= PAGE_SHIFT; + trim_size = limit_pfn; + trim_size <<= PAGE_SHIFT; + trim_size -= trim_start; + + return e820_update_range(trim_start, trim_size, E820_RAM, + E820_RESERVED); +} +/** + * mtrr_trim_uncached_memory - trim RAM not covered by MTRRs + * @end_pfn: ending page frame number + * + * Some buggy BIOSes don't setup the MTRRs properly for systems with certain + * memory configurations. This routine checks that the highest MTRR matches + * the end of memory, to make sure the MTRRs having a write back type cover + * all of the memory the kernel is intending to use. If not, it'll trim any + * memory off the end by adjusting end_pfn, removing it from the kernel's + * allocation pools, warning the user with an obnoxious message. + */ +int __init mtrr_trim_uncached_memory(unsigned long end_pfn) +{ + unsigned long i, base, size, highest_pfn = 0, def, dummy; + mtrr_type type; + u64 total_trim_size; + + /* extra one for all 0 */ + int num[MTRR_NUM_TYPES + 1]; + /* + * Make sure we only trim uncachable memory on machines that + * support the Intel MTRR architecture: + */ + if (!is_cpu(INTEL) || disable_mtrr_trim) + return 0; + rdmsr(MTRRdefType_MSR, def, dummy); + def &= 0xff; + if (def != MTRR_TYPE_UNCACHABLE) + return 0; + + /* get it and store it aside */ + memset(range_state, 0, sizeof(range_state)); + for (i = 0; i < num_var_ranges; i++) { + mtrr_if->get(i, &base, &size, &type); + range_state[i].base_pfn = base; + range_state[i].size_pfn = size; + range_state[i].type = type; + } + + /* Find highest cached pfn */ + for (i = 0; i < num_var_ranges; i++) { + type = range_state[i].type; + if (type != MTRR_TYPE_WRBACK) + continue; + base = range_state[i].base_pfn; + size = range_state[i].size_pfn; + if (highest_pfn < base + size) + highest_pfn = base + size; + } + + /* kvm/qemu doesn't have mtrr set right, don't trim them all */ + if (!highest_pfn) { + printk(KERN_INFO "CPU MTRRs all blank - virtualized system.\n"); + return 0; + } + + /* check entries number */ + memset(num, 0, sizeof(num)); + for (i = 0; i < num_var_ranges; i++) { + type = range_state[i].type; + if (type >= MTRR_NUM_TYPES) + continue; + size = range_state[i].size_pfn; + if (!size) + type = MTRR_NUM_TYPES; + num[type]++; + } + + /* no entry for WB? */ + if (!num[MTRR_TYPE_WRBACK]) + return 0; + + /* check if we only had WB and UC */ + if (num[MTRR_TYPE_WRBACK] + num[MTRR_TYPE_UNCACHABLE] != + num_var_ranges - num[MTRR_NUM_TYPES]) + return 0; + + memset(range, 0, sizeof(range)); + nr_range = 0; + if (mtrr_tom2) { + range[nr_range].start = (1ULL<<(32 - PAGE_SHIFT)); + range[nr_range].end = (mtrr_tom2 >> PAGE_SHIFT) - 1; + if (highest_pfn < range[nr_range].end + 1) + highest_pfn = range[nr_range].end + 1; + nr_range++; + } + nr_range = x86_get_mtrr_mem_range(range, nr_range, 0, 0); + + total_trim_size = 0; + /* check the head */ + if (range[0].start) + total_trim_size += real_trim_memory(0, range[0].start); + /* check the holes */ + for (i = 0; i < nr_range - 1; i++) { + if (range[i].end + 1 < range[i+1].start) + total_trim_size += real_trim_memory(range[i].end + 1, + range[i+1].start); + } + /* check the top */ + i = nr_range - 1; + if (range[i].end + 1 < end_pfn) + total_trim_size += real_trim_memory(range[i].end + 1, + end_pfn); + + if (total_trim_size) { + printk(KERN_WARNING "WARNING: BIOS bug: CPU MTRRs don't cover" + " all of memory, losing %lluMB of RAM.\n", + total_trim_size >> 20); + + if (!changed_by_mtrr_cleanup) + WARN_ON(1); + + printk(KERN_INFO "update e820 for mtrr\n"); + update_e820(); + + return 1; + } + + return 0; +} + diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 0c0a455..0b776c0 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -33,13 +33,31 @@ u64 mtrr_tom2; struct mtrr_state_type mtrr_state = {}; EXPORT_SYMBOL_GPL(mtrr_state); -static int __initdata mtrr_show; -static int __init mtrr_debug(char *opt) +/** + * BIOS is expected to clear MtrrFixDramModEn bit, see for example + * "BIOS and Kernel Developer's Guide for the AMD Athlon 64 and AMD + * Opteron Processors" (26094 Rev. 3.30 February 2006), section + * "13.2.1.2 SYSCFG Register": "The MtrrFixDramModEn bit should be set + * to 1 during BIOS initalization of the fixed MTRRs, then cleared to + * 0 for operation." + */ +static inline void k8_check_syscfg_dram_mod_en(void) { - mtrr_show = 1; - return 0; + u32 lo, hi; + + if (!((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && + (boot_cpu_data.x86 >= 0x0f))) + return; + + rdmsr(MSR_K8_SYSCFG, lo, hi); + if (lo & K8_MTRRFIXRANGE_DRAM_MODIFY) { + printk(KERN_ERR FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]" + " not cleared by BIOS, clearing this bit\n", + smp_processor_id()); + lo &= ~K8_MTRRFIXRANGE_DRAM_MODIFY; + mtrr_wrmsr(MSR_K8_SYSCFG, lo, hi); + } } -early_param("mtrr.show", mtrr_debug); /* * Returns the effective MTRR type for the region @@ -174,6 +192,8 @@ get_fixed_ranges(mtrr_type * frs) unsigned int *p = (unsigned int *) frs; int i; + k8_check_syscfg_dram_mod_en(); + rdmsr(MTRRfix64K_00000_MSR, p[0], p[1]); for (i = 0; i < 2; i++) @@ -188,18 +208,94 @@ void mtrr_save_fixed_ranges(void *info) get_fixed_ranges(mtrr_state.fixed_ranges); } -static void print_fixed(unsigned base, unsigned step, const mtrr_type*types) +static unsigned __initdata last_fixed_start; +static unsigned __initdata last_fixed_end; +static mtrr_type __initdata last_fixed_type; + +static void __init print_fixed_last(void) +{ + if (!last_fixed_end) + return; + + printk(KERN_DEBUG " %05X-%05X %s\n", last_fixed_start, + last_fixed_end - 1, mtrr_attrib_to_str(last_fixed_type)); + + last_fixed_end = 0; +} + +static void __init update_fixed_last(unsigned base, unsigned end, + mtrr_type type) +{ + last_fixed_start = base; + last_fixed_end = end; + last_fixed_type = type; +} + +static void __init print_fixed(unsigned base, unsigned step, + const mtrr_type *types) { unsigned i; - for (i = 0; i < 8; ++i, ++types, base += step) - printk(KERN_INFO "MTRR %05X-%05X %s\n", - base, base + step - 1, mtrr_attrib_to_str(*types)); + for (i = 0; i < 8; ++i, ++types, base += step) { + if (last_fixed_end == 0) { + update_fixed_last(base, base + step, *types); + continue; + } + if (last_fixed_end == base && last_fixed_type == *types) { + last_fixed_end = base + step; + continue; + } + /* new segments: gap or different type */ + print_fixed_last(); + update_fixed_last(base, base + step, *types); + } } static void prepare_set(void); static void post_set(void); +static void __init print_mtrr_state(void) +{ + unsigned int i; + int high_width; + + printk(KERN_DEBUG "MTRR default type: %s\n", + mtrr_attrib_to_str(mtrr_state.def_type)); + if (mtrr_state.have_fixed) { + printk(KERN_DEBUG "MTRR fixed ranges %sabled:\n", + mtrr_state.enabled & 1 ? "en" : "dis"); + print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0); + for (i = 0; i < 2; ++i) + print_fixed(0x80000 + i * 0x20000, 0x04000, mtrr_state.fixed_ranges + (i + 1) * 8); + for (i = 0; i < 8; ++i) + print_fixed(0xC0000 + i * 0x08000, 0x01000, mtrr_state.fixed_ranges + (i + 3) * 8); + + /* tail */ + print_fixed_last(); + } + printk(KERN_DEBUG "MTRR variable ranges %sabled:\n", + mtrr_state.enabled & 2 ? "en" : "dis"); + high_width = ((size_or_mask ? ffs(size_or_mask) - 1 : 32) - (32 - PAGE_SHIFT) + 3) / 4; + for (i = 0; i < num_var_ranges; ++i) { + if (mtrr_state.var_ranges[i].mask_lo & (1 << 11)) + printk(KERN_DEBUG " %u base %0*X%05X000 mask %0*X%05X000 %s\n", + i, + high_width, + mtrr_state.var_ranges[i].base_hi, + mtrr_state.var_ranges[i].base_lo >> 12, + high_width, + mtrr_state.var_ranges[i].mask_hi, + mtrr_state.var_ranges[i].mask_lo >> 12, + mtrr_attrib_to_str(mtrr_state.var_ranges[i].base_lo & 0xff)); + else + printk(KERN_DEBUG " %u disabled\n", i); + } + if (mtrr_tom2) { + printk(KERN_DEBUG "TOM2: %016llx aka %lldM\n", + mtrr_tom2, mtrr_tom2>>20); + } +} + /* Grab all of the MTRR state for this CPU into *state */ void __init get_mtrr_state(void) { @@ -231,41 +327,9 @@ void __init get_mtrr_state(void) mtrr_tom2 |= low; mtrr_tom2 &= 0xffffff800000ULL; } - if (mtrr_show) { - int high_width; - - printk(KERN_INFO "MTRR default type: %s\n", mtrr_attrib_to_str(mtrr_state.def_type)); - if (mtrr_state.have_fixed) { - printk(KERN_INFO "MTRR fixed ranges %sabled:\n", - mtrr_state.enabled & 1 ? "en" : "dis"); - print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0); - for (i = 0; i < 2; ++i) - print_fixed(0x80000 + i * 0x20000, 0x04000, mtrr_state.fixed_ranges + (i + 1) * 8); - for (i = 0; i < 8; ++i) - print_fixed(0xC0000 + i * 0x08000, 0x01000, mtrr_state.fixed_ranges + (i + 3) * 8); - } - printk(KERN_INFO "MTRR variable ranges %sabled:\n", - mtrr_state.enabled & 2 ? "en" : "dis"); - high_width = ((size_or_mask ? ffs(size_or_mask) - 1 : 32) - (32 - PAGE_SHIFT) + 3) / 4; - for (i = 0; i < num_var_ranges; ++i) { - if (mtrr_state.var_ranges[i].mask_lo & (1 << 11)) - printk(KERN_INFO "MTRR %u base %0*X%05X000 mask %0*X%05X000 %s\n", - i, - high_width, - mtrr_state.var_ranges[i].base_hi, - mtrr_state.var_ranges[i].base_lo >> 12, - high_width, - mtrr_state.var_ranges[i].mask_hi, - mtrr_state.var_ranges[i].mask_lo >> 12, - mtrr_attrib_to_str(mtrr_state.var_ranges[i].base_lo & 0xff)); - else - printk(KERN_INFO "MTRR %u disabled\n", i); - } - if (mtrr_tom2) { - printk(KERN_INFO "TOM2: %016llx aka %lldM\n", - mtrr_tom2, mtrr_tom2>>20); - } - } + + print_mtrr_state(); + mtrr_state_set = 1; /* PAT setup for BP. We need to go through sync steps here */ @@ -308,27 +372,10 @@ void mtrr_wrmsr(unsigned msr, unsigned a, unsigned b) } /** - * Enable and allow read/write of extended fixed-range MTRR bits on K8 CPUs - * see AMD publication no. 24593, chapter 3.2.1 for more information - */ -static inline void k8_enable_fixed_iorrs(void) -{ - unsigned lo, hi; - - rdmsr(MSR_K8_SYSCFG, lo, hi); - mtrr_wrmsr(MSR_K8_SYSCFG, lo - | K8_MTRRFIXRANGE_DRAM_ENABLE - | K8_MTRRFIXRANGE_DRAM_MODIFY, hi); -} - -/** * set_fixed_range - checks & updates a fixed-range MTRR if it differs from the value it should have * @msr: MSR address of the MTTR which should be checked and updated * @changed: pointer which indicates whether the MTRR needed to be changed * @msrwords: pointer to the MSR values which the MSR should have - * - * If K8 extentions are wanted, update the K8 SYSCFG MSR also. - * See AMD publication no. 24593, chapter 7.8.1, page 233 for more information. */ static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords) { @@ -337,10 +384,6 @@ static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords) rdmsr(msr, lo, hi); if (lo != msrwords[0] || hi != msrwords[1]) { - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD && - (boot_cpu_data.x86 >= 0x0f && boot_cpu_data.x86 <= 0x11) && - ((msrwords[0] | msrwords[1]) & K8_MTRR_RDMEM_WRMEM_MASK)) - k8_enable_fixed_iorrs(); mtrr_wrmsr(msr, msrwords[0], msrwords[1]); *changed = true; } @@ -376,22 +419,31 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, { unsigned int mask_lo, mask_hi, base_lo, base_hi; unsigned int tmp, hi; + int cpu; + + /* + * get_mtrr doesn't need to update mtrr_state, also it could be called + * from any cpu, so try to print it out directly. + */ + cpu = get_cpu(); rdmsr(MTRRphysMask_MSR(reg), mask_lo, mask_hi); + if ((mask_lo & 0x800) == 0) { /* Invalid (i.e. free) range */ *base = 0; *size = 0; *type = 0; - return; + goto out_put_cpu; } rdmsr(MTRRphysBase_MSR(reg), base_lo, base_hi); - /* Work out the shifted address mask. */ + /* Work out the shifted address mask: */ tmp = mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT; mask_lo = size_or_mask | tmp; - /* Expand tmp with high bits to all 1s*/ + + /* Expand tmp with high bits to all 1s: */ hi = fls(tmp); if (hi > 0) { tmp |= ~((1<<(hi - 1)) - 1); @@ -402,11 +454,16 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, } } - /* This works correctly if size is a power of two, i.e. a - contiguous range. */ + /* + * This works correctly if size is a power of two, i.e. a + * contiguous range: + */ *size = -mask_lo; *base = base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT; *type = base_lo & 0xff; + +out_put_cpu: + put_cpu(); } /** @@ -419,6 +476,8 @@ static int set_fixed_ranges(mtrr_type * frs) bool changed = false; int block=-1, range; + k8_check_syscfg_dram_mod_en(); + while (fixed_range_blocks[++block].ranges) for (range=0; range < fixed_range_blocks[block].ranges; range++) set_fixed_range(fixed_range_blocks[block].base_msr + range, diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 4c42146..fb73a52 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -377,10 +377,6 @@ static const struct file_operations mtrr_fops = { .release = mtrr_close, }; - -static struct proc_dir_entry *proc_root_mtrr; - - static int mtrr_seq_show(struct seq_file *seq, void *offset) { char factor; @@ -423,11 +419,7 @@ static int __init mtrr_if_init(void) (!cpu_has(c, X86_FEATURE_CENTAUR_MCR))) return -ENODEV; - proc_root_mtrr = - proc_create("mtrr", S_IWUSR | S_IRUGO, NULL, &mtrr_fops); - - if (proc_root_mtrr) - proc_root_mtrr->owner = THIS_MODULE; + proc_create("mtrr", S_IWUSR | S_IRUGO, NULL, &mtrr_fops); return 0; } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 236a401..03cda01 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -574,7 +574,7 @@ struct mtrr_value { unsigned long lsize; }; -static struct mtrr_value mtrr_state[MTRR_MAX_VAR_RANGES]; +static struct mtrr_value mtrr_value[MTRR_MAX_VAR_RANGES]; static int mtrr_save(struct sys_device * sysdev, pm_message_t state) { @@ -582,9 +582,9 @@ static int mtrr_save(struct sys_device * sysdev, pm_message_t state) for (i = 0; i < num_var_ranges; i++) { mtrr_if->get(i, - &mtrr_state[i].lbase, - &mtrr_state[i].lsize, - &mtrr_state[i].ltype); + &mtrr_value[i].lbase, + &mtrr_value[i].lsize, + &mtrr_value[i].ltype); } return 0; } @@ -594,11 +594,11 @@ static int mtrr_restore(struct sys_device * sysdev) int i; for (i = 0; i < num_var_ranges; i++) { - if (mtrr_state[i].lsize) + if (mtrr_value[i].lsize) set_mtrr(i, - mtrr_state[i].lbase, - mtrr_state[i].lsize, - mtrr_state[i].ltype); + mtrr_value[i].lbase, + mtrr_value[i].lsize, + mtrr_value[i].ltype); } return 0; } @@ -610,1058 +610,7 @@ static struct sysdev_driver mtrr_sysdev_driver = { .resume = mtrr_restore, }; -/* should be related to MTRR_VAR_RANGES nums */ -#define RANGE_NUM 256 - -struct res_range { - unsigned long start; - unsigned long end; -}; - -static int __init -add_range(struct res_range *range, int nr_range, unsigned long start, - unsigned long end) -{ - /* out of slots */ - if (nr_range >= RANGE_NUM) - return nr_range; - - range[nr_range].start = start; - range[nr_range].end = end; - - nr_range++; - - return nr_range; -} - -static int __init -add_range_with_merge(struct res_range *range, int nr_range, unsigned long start, - unsigned long end) -{ - int i; - - /* try to merge it with old one */ - for (i = 0; i < nr_range; i++) { - unsigned long final_start, final_end; - unsigned long common_start, common_end; - - if (!range[i].end) - continue; - - common_start = max(range[i].start, start); - common_end = min(range[i].end, end); - if (common_start > common_end + 1) - continue; - - final_start = min(range[i].start, start); - final_end = max(range[i].end, end); - - range[i].start = final_start; - range[i].end = final_end; - return nr_range; - } - - /* need to add that */ - return add_range(range, nr_range, start, end); -} - -static void __init -subtract_range(struct res_range *range, unsigned long start, unsigned long end) -{ - int i, j; - - for (j = 0; j < RANGE_NUM; j++) { - if (!range[j].end) - continue; - - if (start <= range[j].start && end >= range[j].end) { - range[j].start = 0; - range[j].end = 0; - continue; - } - - if (start <= range[j].start && end < range[j].end && - range[j].start < end + 1) { - range[j].start = end + 1; - continue; - } - - - if (start > range[j].start && end >= range[j].end && - range[j].end > start - 1) { - range[j].end = start - 1; - continue; - } - - if (start > range[j].start && end < range[j].end) { - /* find the new spare */ - for (i = 0; i < RANGE_NUM; i++) { - if (range[i].end == 0) - break; - } - if (i < RANGE_NUM) { - range[i].end = range[j].end; - range[i].start = end + 1; - } else { - printk(KERN_ERR "run of slot in ranges\n"); - } - range[j].end = start - 1; - continue; - } - } -} - -static int __init cmp_range(const void *x1, const void *x2) -{ - const struct res_range *r1 = x1; - const struct res_range *r2 = x2; - long start1, start2; - - start1 = r1->start; - start2 = r2->start; - - return start1 - start2; -} - -struct var_mtrr_range_state { - unsigned long base_pfn; - unsigned long size_pfn; - mtrr_type type; -}; - -static struct var_mtrr_range_state __initdata range_state[RANGE_NUM]; -static int __initdata debug_print; - -static int __init -x86_get_mtrr_mem_range(struct res_range *range, int nr_range, - unsigned long extra_remove_base, - unsigned long extra_remove_size) -{ - unsigned long i, base, size; - mtrr_type type; - - for (i = 0; i < num_var_ranges; i++) { - type = range_state[i].type; - if (type != MTRR_TYPE_WRBACK) - continue; - base = range_state[i].base_pfn; - size = range_state[i].size_pfn; - nr_range = add_range_with_merge(range, nr_range, base, - base + size - 1); - } - if (debug_print) { - printk(KERN_DEBUG "After WB checking\n"); - for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", - range[i].start, range[i].end + 1); - } - - /* take out UC ranges */ - for (i = 0; i < num_var_ranges; i++) { - type = range_state[i].type; - if (type != MTRR_TYPE_UNCACHABLE && - type != MTRR_TYPE_WRPROT) - continue; - size = range_state[i].size_pfn; - if (!size) - continue; - base = range_state[i].base_pfn; - subtract_range(range, base, base + size - 1); - } - if (extra_remove_size) - subtract_range(range, extra_remove_base, - extra_remove_base + extra_remove_size - 1); - - /* get new range num */ - nr_range = 0; - for (i = 0; i < RANGE_NUM; i++) { - if (!range[i].end) - continue; - nr_range++; - } - if (debug_print) { - printk(KERN_DEBUG "After UC checking\n"); - for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", - range[i].start, range[i].end + 1); - } - - /* sort the ranges */ - sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL); - if (debug_print) { - printk(KERN_DEBUG "After sorting\n"); - for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", - range[i].start, range[i].end + 1); - } - - /* clear those is not used */ - for (i = nr_range; i < RANGE_NUM; i++) - memset(&range[i], 0, sizeof(range[i])); - - return nr_range; -} - -static struct res_range __initdata range[RANGE_NUM]; -static int __initdata nr_range; - -#ifdef CONFIG_MTRR_SANITIZER - -static unsigned long __init sum_ranges(struct res_range *range, int nr_range) -{ - unsigned long sum; - int i; - - sum = 0; - for (i = 0; i < nr_range; i++) - sum += range[i].end + 1 - range[i].start; - - return sum; -} - -static int enable_mtrr_cleanup __initdata = - CONFIG_MTRR_SANITIZER_ENABLE_DEFAULT; - -static int __init disable_mtrr_cleanup_setup(char *str) -{ - enable_mtrr_cleanup = 0; - return 0; -} -early_param("disable_mtrr_cleanup", disable_mtrr_cleanup_setup); - -static int __init enable_mtrr_cleanup_setup(char *str) -{ - enable_mtrr_cleanup = 1; - return 0; -} -early_param("enable_mtrr_cleanup", enable_mtrr_cleanup_setup); - -static int __init mtrr_cleanup_debug_setup(char *str) -{ - debug_print = 1; - return 0; -} -early_param("mtrr_cleanup_debug", mtrr_cleanup_debug_setup); - -struct var_mtrr_state { - unsigned long range_startk; - unsigned long range_sizek; - unsigned long chunk_sizek; - unsigned long gran_sizek; - unsigned int reg; -}; - -static void __init -set_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek, - unsigned char type, unsigned int address_bits) -{ - u32 base_lo, base_hi, mask_lo, mask_hi; - u64 base, mask; - - if (!sizek) { - fill_mtrr_var_range(reg, 0, 0, 0, 0); - return; - } - - mask = (1ULL << address_bits) - 1; - mask &= ~((((u64)sizek) << 10) - 1); - - base = ((u64)basek) << 10; - - base |= type; - mask |= 0x800; - - base_lo = base & ((1ULL<<32) - 1); - base_hi = base >> 32; - - mask_lo = mask & ((1ULL<<32) - 1); - mask_hi = mask >> 32; - - fill_mtrr_var_range(reg, base_lo, base_hi, mask_lo, mask_hi); -} - -static void __init -save_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek, - unsigned char type) -{ - range_state[reg].base_pfn = basek >> (PAGE_SHIFT - 10); - range_state[reg].size_pfn = sizek >> (PAGE_SHIFT - 10); - range_state[reg].type = type; -} - -static void __init -set_var_mtrr_all(unsigned int address_bits) -{ - unsigned long basek, sizek; - unsigned char type; - unsigned int reg; - - for (reg = 0; reg < num_var_ranges; reg++) { - basek = range_state[reg].base_pfn << (PAGE_SHIFT - 10); - sizek = range_state[reg].size_pfn << (PAGE_SHIFT - 10); - type = range_state[reg].type; - - set_var_mtrr(reg, basek, sizek, type, address_bits); - } -} - -static unsigned long to_size_factor(unsigned long sizek, char *factorp) -{ - char factor; - unsigned long base = sizek; - - if (base & ((1<<10) - 1)) { - /* not MB alignment */ - factor = 'K'; - } else if (base & ((1<<20) - 1)){ - factor = 'M'; - base >>= 10; - } else { - factor = 'G'; - base >>= 20; - } - - *factorp = factor; - - return base; -} - -static unsigned int __init -range_to_mtrr(unsigned int reg, unsigned long range_startk, - unsigned long range_sizek, unsigned char type) -{ - if (!range_sizek || (reg >= num_var_ranges)) - return reg; - - while (range_sizek) { - unsigned long max_align, align; - unsigned long sizek; - - /* Compute the maximum size I can make a range */ - if (range_startk) - max_align = ffs(range_startk) - 1; - else - max_align = 32; - align = fls(range_sizek) - 1; - if (align > max_align) - align = max_align; - - sizek = 1 << align; - if (debug_print) { - char start_factor = 'K', size_factor = 'K'; - unsigned long start_base, size_base; - - start_base = to_size_factor(range_startk, &start_factor), - size_base = to_size_factor(sizek, &size_factor), - - printk(KERN_DEBUG "Setting variable MTRR %d, " - "base: %ld%cB, range: %ld%cB, type %s\n", - reg, start_base, start_factor, - size_base, size_factor, - (type == MTRR_TYPE_UNCACHABLE)?"UC": - ((type == MTRR_TYPE_WRBACK)?"WB":"Other") - ); - } - save_var_mtrr(reg++, range_startk, sizek, type); - range_startk += sizek; - range_sizek -= sizek; - if (reg >= num_var_ranges) - break; - } - return reg; -} - -static unsigned __init -range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek, - unsigned long sizek) -{ - unsigned long hole_basek, hole_sizek; - unsigned long second_basek, second_sizek; - unsigned long range0_basek, range0_sizek; - unsigned long range_basek, range_sizek; - unsigned long chunk_sizek; - unsigned long gran_sizek; - - hole_basek = 0; - hole_sizek = 0; - second_basek = 0; - second_sizek = 0; - chunk_sizek = state->chunk_sizek; - gran_sizek = state->gran_sizek; - - /* align with gran size, prevent small block used up MTRRs */ - range_basek = ALIGN(state->range_startk, gran_sizek); - if ((range_basek > basek) && basek) - return second_sizek; - state->range_sizek -= (range_basek - state->range_startk); - range_sizek = ALIGN(state->range_sizek, gran_sizek); - - while (range_sizek > state->range_sizek) { - range_sizek -= gran_sizek; - if (!range_sizek) - return 0; - } - state->range_sizek = range_sizek; - - /* try to append some small hole */ - range0_basek = state->range_startk; - range0_sizek = ALIGN(state->range_sizek, chunk_sizek); - - /* no increase */ - if (range0_sizek == state->range_sizek) { - if (debug_print) - printk(KERN_DEBUG "rangeX: %016lx - %016lx\n", - range0_basek<<10, - (range0_basek + state->range_sizek)<<10); - state->reg = range_to_mtrr(state->reg, range0_basek, - state->range_sizek, MTRR_TYPE_WRBACK); - return 0; - } - - /* only cut back, when it is not the last */ - if (sizek) { - while (range0_basek + range0_sizek > (basek + sizek)) { - if (range0_sizek >= chunk_sizek) - range0_sizek -= chunk_sizek; - else - range0_sizek = 0; - - if (!range0_sizek) - break; - } - } - -second_try: - range_basek = range0_basek + range0_sizek; - - /* one hole in the middle */ - if (range_basek > basek && range_basek <= (basek + sizek)) - second_sizek = range_basek - basek; - - if (range0_sizek > state->range_sizek) { - - /* one hole in middle or at end */ - hole_sizek = range0_sizek - state->range_sizek - second_sizek; - - /* hole size should be less than half of range0 size */ - if (hole_sizek >= (range0_sizek >> 1) && - range0_sizek >= chunk_sizek) { - range0_sizek -= chunk_sizek; - second_sizek = 0; - hole_sizek = 0; - - goto second_try; - } - } - - if (range0_sizek) { - if (debug_print) - printk(KERN_DEBUG "range0: %016lx - %016lx\n", - range0_basek<<10, - (range0_basek + range0_sizek)<<10); - state->reg = range_to_mtrr(state->reg, range0_basek, - range0_sizek, MTRR_TYPE_WRBACK); - } - - if (range0_sizek < state->range_sizek) { - /* need to handle left over */ - range_sizek = state->range_sizek - range0_sizek; - - if (debug_print) - printk(KERN_DEBUG "range: %016lx - %016lx\n", - range_basek<<10, - (range_basek + range_sizek)<<10); - state->reg = range_to_mtrr(state->reg, range_basek, - range_sizek, MTRR_TYPE_WRBACK); - } - - if (hole_sizek) { - hole_basek = range_basek - hole_sizek - second_sizek; - if (debug_print) - printk(KERN_DEBUG "hole: %016lx - %016lx\n", - hole_basek<<10, - (hole_basek + hole_sizek)<<10); - state->reg = range_to_mtrr(state->reg, hole_basek, - hole_sizek, MTRR_TYPE_UNCACHABLE); - } - - return second_sizek; -} - -static void __init -set_var_mtrr_range(struct var_mtrr_state *state, unsigned long base_pfn, - unsigned long size_pfn) -{ - unsigned long basek, sizek; - unsigned long second_sizek = 0; - - if (state->reg >= num_var_ranges) - return; - - basek = base_pfn << (PAGE_SHIFT - 10); - sizek = size_pfn << (PAGE_SHIFT - 10); - - /* See if I can merge with the last range */ - if ((basek <= 1024) || - (state->range_startk + state->range_sizek == basek)) { - unsigned long endk = basek + sizek; - state->range_sizek = endk - state->range_startk; - return; - } - /* Write the range mtrrs */ - if (state->range_sizek != 0) - second_sizek = range_to_mtrr_with_hole(state, basek, sizek); - - /* Allocate an msr */ - state->range_startk = basek + second_sizek; - state->range_sizek = sizek - second_sizek; -} - -/* mininum size of mtrr block that can take hole */ -static u64 mtrr_chunk_size __initdata = (256ULL<<20); - -static int __init parse_mtrr_chunk_size_opt(char *p) -{ - if (!p) - return -EINVAL; - mtrr_chunk_size = memparse(p, &p); - return 0; -} -early_param("mtrr_chunk_size", parse_mtrr_chunk_size_opt); - -/* granity of mtrr of block */ -static u64 mtrr_gran_size __initdata; - -static int __init parse_mtrr_gran_size_opt(char *p) -{ - if (!p) - return -EINVAL; - mtrr_gran_size = memparse(p, &p); - return 0; -} -early_param("mtrr_gran_size", parse_mtrr_gran_size_opt); - -static int nr_mtrr_spare_reg __initdata = - CONFIG_MTRR_SANITIZER_SPARE_REG_NR_DEFAULT; - -static int __init parse_mtrr_spare_reg(char *arg) -{ - if (arg) - nr_mtrr_spare_reg = simple_strtoul(arg, NULL, 0); - return 0; -} - -early_param("mtrr_spare_reg_nr", parse_mtrr_spare_reg); - -static int __init -x86_setup_var_mtrrs(struct res_range *range, int nr_range, - u64 chunk_size, u64 gran_size) -{ - struct var_mtrr_state var_state; - int i; - int num_reg; - - var_state.range_startk = 0; - var_state.range_sizek = 0; - var_state.reg = 0; - var_state.chunk_sizek = chunk_size >> 10; - var_state.gran_sizek = gran_size >> 10; - - memset(range_state, 0, sizeof(range_state)); - - /* Write the range etc */ - for (i = 0; i < nr_range; i++) - set_var_mtrr_range(&var_state, range[i].start, - range[i].end - range[i].start + 1); - - /* Write the last range */ - if (var_state.range_sizek != 0) - range_to_mtrr_with_hole(&var_state, 0, 0); - - num_reg = var_state.reg; - /* Clear out the extra MTRR's */ - while (var_state.reg < num_var_ranges) { - save_var_mtrr(var_state.reg, 0, 0, 0); - var_state.reg++; - } - - return num_reg; -} - -struct mtrr_cleanup_result { - unsigned long gran_sizek; - unsigned long chunk_sizek; - unsigned long lose_cover_sizek; - unsigned int num_reg; - int bad; -}; - -/* - * gran_size: 64K, 128K, 256K, 512K, 1M, 2M, ..., 2G - * chunk size: gran_size, ..., 2G - * so we need (1+16)*8 - */ -#define NUM_RESULT 136 -#define PSHIFT (PAGE_SHIFT - 10) - -static struct mtrr_cleanup_result __initdata result[NUM_RESULT]; -static unsigned long __initdata min_loss_pfn[RANGE_NUM]; - -static void __init print_out_mtrr_range_state(void) -{ - int i; - char start_factor = 'K', size_factor = 'K'; - unsigned long start_base, size_base; - mtrr_type type; - - for (i = 0; i < num_var_ranges; i++) { - - size_base = range_state[i].size_pfn << (PAGE_SHIFT - 10); - if (!size_base) - continue; - - size_base = to_size_factor(size_base, &size_factor), - start_base = range_state[i].base_pfn << (PAGE_SHIFT - 10); - start_base = to_size_factor(start_base, &start_factor), - type = range_state[i].type; - - printk(KERN_DEBUG "reg %d, base: %ld%cB, range: %ld%cB, type %s\n", - i, start_base, start_factor, - size_base, size_factor, - (type == MTRR_TYPE_UNCACHABLE) ? "UC" : - ((type == MTRR_TYPE_WRPROT) ? "WP" : - ((type == MTRR_TYPE_WRBACK) ? "WB" : "Other")) - ); - } -} - -static int __init mtrr_need_cleanup(void) -{ - int i; - mtrr_type type; - unsigned long size; - /* extra one for all 0 */ - int num[MTRR_NUM_TYPES + 1]; - - /* check entries number */ - memset(num, 0, sizeof(num)); - for (i = 0; i < num_var_ranges; i++) { - type = range_state[i].type; - size = range_state[i].size_pfn; - if (type >= MTRR_NUM_TYPES) - continue; - if (!size) - type = MTRR_NUM_TYPES; - if (type == MTRR_TYPE_WRPROT) - type = MTRR_TYPE_UNCACHABLE; - num[type]++; - } - - /* check if we got UC entries */ - if (!num[MTRR_TYPE_UNCACHABLE]) - return 0; - - /* check if we only had WB and UC */ - if (num[MTRR_TYPE_WRBACK] + num[MTRR_TYPE_UNCACHABLE] != - num_var_ranges - num[MTRR_NUM_TYPES]) - return 0; - - return 1; -} - -static unsigned long __initdata range_sums; -static void __init mtrr_calc_range_state(u64 chunk_size, u64 gran_size, - unsigned long extra_remove_base, - unsigned long extra_remove_size, - int i) -{ - int num_reg; - static struct res_range range_new[RANGE_NUM]; - static int nr_range_new; - unsigned long range_sums_new; - - /* convert ranges to var ranges state */ - num_reg = x86_setup_var_mtrrs(range, nr_range, - chunk_size, gran_size); - - /* we got new setting in range_state, check it */ - memset(range_new, 0, sizeof(range_new)); - nr_range_new = x86_get_mtrr_mem_range(range_new, 0, - extra_remove_base, extra_remove_size); - range_sums_new = sum_ranges(range_new, nr_range_new); - - result[i].chunk_sizek = chunk_size >> 10; - result[i].gran_sizek = gran_size >> 10; - result[i].num_reg = num_reg; - if (range_sums < range_sums_new) { - result[i].lose_cover_sizek = - (range_sums_new - range_sums) << PSHIFT; - result[i].bad = 1; - } else - result[i].lose_cover_sizek = - (range_sums - range_sums_new) << PSHIFT; - - /* double check it */ - if (!result[i].bad && !result[i].lose_cover_sizek) { - if (nr_range_new != nr_range || - memcmp(range, range_new, sizeof(range))) - result[i].bad = 1; - } - - if (!result[i].bad && (range_sums - range_sums_new < - min_loss_pfn[num_reg])) { - min_loss_pfn[num_reg] = - range_sums - range_sums_new; - } -} - -static void __init mtrr_print_out_one_result(int i) -{ - char gran_factor, chunk_factor, lose_factor; - unsigned long gran_base, chunk_base, lose_base; - - gran_base = to_size_factor(result[i].gran_sizek, &gran_factor), - chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor), - lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor), - printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t", - result[i].bad ? "*BAD*" : " ", - gran_base, gran_factor, chunk_base, chunk_factor); - printk(KERN_CONT "num_reg: %d \tlose cover RAM: %s%ld%c\n", - result[i].num_reg, result[i].bad ? "-" : "", - lose_base, lose_factor); -} - -static int __init mtrr_search_optimal_index(void) -{ - int i; - int num_reg_good; - int index_good; - - if (nr_mtrr_spare_reg >= num_var_ranges) - nr_mtrr_spare_reg = num_var_ranges - 1; - num_reg_good = -1; - for (i = num_var_ranges - nr_mtrr_spare_reg; i > 0; i--) { - if (!min_loss_pfn[i]) - num_reg_good = i; - } - - index_good = -1; - if (num_reg_good != -1) { - for (i = 0; i < NUM_RESULT; i++) { - if (!result[i].bad && - result[i].num_reg == num_reg_good && - !result[i].lose_cover_sizek) { - index_good = i; - break; - } - } - } - - return index_good; -} - - -static int __init mtrr_cleanup(unsigned address_bits) -{ - unsigned long extra_remove_base, extra_remove_size; - unsigned long base, size, def, dummy; - mtrr_type type; - u64 chunk_size, gran_size; - int index_good; - int i; - - if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1) - return 0; - rdmsr(MTRRdefType_MSR, def, dummy); - def &= 0xff; - if (def != MTRR_TYPE_UNCACHABLE) - return 0; - - /* get it and store it aside */ - memset(range_state, 0, sizeof(range_state)); - for (i = 0; i < num_var_ranges; i++) { - mtrr_if->get(i, &base, &size, &type); - range_state[i].base_pfn = base; - range_state[i].size_pfn = size; - range_state[i].type = type; - } - - /* check if we need handle it and can handle it */ - if (!mtrr_need_cleanup()) - return 0; - - /* print original var MTRRs at first, for debugging: */ - printk(KERN_DEBUG "original variable MTRRs\n"); - print_out_mtrr_range_state(); - - memset(range, 0, sizeof(range)); - extra_remove_size = 0; - extra_remove_base = 1 << (32 - PAGE_SHIFT); - if (mtrr_tom2) - extra_remove_size = - (mtrr_tom2 >> PAGE_SHIFT) - extra_remove_base; - nr_range = x86_get_mtrr_mem_range(range, 0, extra_remove_base, - extra_remove_size); - /* - * [0, 1M) should always be coverred by var mtrr with WB - * and fixed mtrrs should take effective before var mtrr for it - */ - nr_range = add_range_with_merge(range, nr_range, 0, - (1ULL<<(20 - PAGE_SHIFT)) - 1); - /* sort the ranges */ - sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL); - - range_sums = sum_ranges(range, nr_range); - printk(KERN_INFO "total RAM coverred: %ldM\n", - range_sums >> (20 - PAGE_SHIFT)); - - if (mtrr_chunk_size && mtrr_gran_size) { - i = 0; - mtrr_calc_range_state(mtrr_chunk_size, mtrr_gran_size, - extra_remove_base, extra_remove_size, i); - - mtrr_print_out_one_result(i); - - if (!result[i].bad) { - set_var_mtrr_all(address_bits); - return 1; - } - printk(KERN_INFO "invalid mtrr_gran_size or mtrr_chunk_size, " - "will find optimal one\n"); - } - - i = 0; - memset(min_loss_pfn, 0xff, sizeof(min_loss_pfn)); - memset(result, 0, sizeof(result)); - for (gran_size = (1ULL<<16); gran_size < (1ULL<<32); gran_size <<= 1) { - - for (chunk_size = gran_size; chunk_size < (1ULL<<32); - chunk_size <<= 1) { - - if (i >= NUM_RESULT) - continue; - - mtrr_calc_range_state(chunk_size, gran_size, - extra_remove_base, extra_remove_size, i); - if (debug_print) { - mtrr_print_out_one_result(i); - printk(KERN_INFO "\n"); - } - - i++; - } - } - - /* try to find the optimal index */ - index_good = mtrr_search_optimal_index(); - - if (index_good != -1) { - printk(KERN_INFO "Found optimal setting for mtrr clean up\n"); - i = index_good; - mtrr_print_out_one_result(i); - - /* convert ranges to var ranges state */ - chunk_size = result[i].chunk_sizek; - chunk_size <<= 10; - gran_size = result[i].gran_sizek; - gran_size <<= 10; - x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size); - set_var_mtrr_all(address_bits); - printk(KERN_DEBUG "New variable MTRRs\n"); - print_out_mtrr_range_state(); - return 1; - } else { - /* print out all */ - for (i = 0; i < NUM_RESULT; i++) - mtrr_print_out_one_result(i); - } - - printk(KERN_INFO "mtrr_cleanup: can not find optimal value\n"); - printk(KERN_INFO "please specify mtrr_gran_size/mtrr_chunk_size\n"); - - return 0; -} -#else -static int __init mtrr_cleanup(unsigned address_bits) -{ - return 0; -} -#endif - -static int __initdata changed_by_mtrr_cleanup; - -static int disable_mtrr_trim; - -static int __init disable_mtrr_trim_setup(char *str) -{ - disable_mtrr_trim = 1; - return 0; -} -early_param("disable_mtrr_trim", disable_mtrr_trim_setup); - -/* - * Newer AMD K8s and later CPUs have a special magic MSR way to force WB - * for memory >4GB. Check for that here. - * Note this won't check if the MTRRs < 4GB where the magic bit doesn't - * apply to are wrong, but so far we don't know of any such case in the wild. - */ -#define Tom2Enabled (1U << 21) -#define Tom2ForceMemTypeWB (1U << 22) - -int __init amd_special_default_mtrr(void) -{ - u32 l, h; - - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) - return 0; - if (boot_cpu_data.x86 < 0xf || boot_cpu_data.x86 > 0x11) - return 0; - /* In case some hypervisor doesn't pass SYSCFG through */ - if (rdmsr_safe(MSR_K8_SYSCFG, &l, &h) < 0) - return 0; - /* - * Memory between 4GB and top of mem is forced WB by this magic bit. - * Reserved before K8RevF, but should be zero there. - */ - if ((l & (Tom2Enabled | Tom2ForceMemTypeWB)) == - (Tom2Enabled | Tom2ForceMemTypeWB)) - return 1; - return 0; -} - -static u64 __init real_trim_memory(unsigned long start_pfn, - unsigned long limit_pfn) -{ - u64 trim_start, trim_size; - trim_start = start_pfn; - trim_start <<= PAGE_SHIFT; - trim_size = limit_pfn; - trim_size <<= PAGE_SHIFT; - trim_size -= trim_start; - - return e820_update_range(trim_start, trim_size, E820_RAM, - E820_RESERVED); -} -/** - * mtrr_trim_uncached_memory - trim RAM not covered by MTRRs - * @end_pfn: ending page frame number - * - * Some buggy BIOSes don't setup the MTRRs properly for systems with certain - * memory configurations. This routine checks that the highest MTRR matches - * the end of memory, to make sure the MTRRs having a write back type cover - * all of the memory the kernel is intending to use. If not, it'll trim any - * memory off the end by adjusting end_pfn, removing it from the kernel's - * allocation pools, warning the user with an obnoxious message. - */ -int __init mtrr_trim_uncached_memory(unsigned long end_pfn) -{ - unsigned long i, base, size, highest_pfn = 0, def, dummy; - mtrr_type type; - u64 total_trim_size; - - /* extra one for all 0 */ - int num[MTRR_NUM_TYPES + 1]; - /* - * Make sure we only trim uncachable memory on machines that - * support the Intel MTRR architecture: - */ - if (!is_cpu(INTEL) || disable_mtrr_trim) - return 0; - rdmsr(MTRRdefType_MSR, def, dummy); - def &= 0xff; - if (def != MTRR_TYPE_UNCACHABLE) - return 0; - - /* get it and store it aside */ - memset(range_state, 0, sizeof(range_state)); - for (i = 0; i < num_var_ranges; i++) { - mtrr_if->get(i, &base, &size, &type); - range_state[i].base_pfn = base; - range_state[i].size_pfn = size; - range_state[i].type = type; - } - - /* Find highest cached pfn */ - for (i = 0; i < num_var_ranges; i++) { - type = range_state[i].type; - if (type != MTRR_TYPE_WRBACK) - continue; - base = range_state[i].base_pfn; - size = range_state[i].size_pfn; - if (highest_pfn < base + size) - highest_pfn = base + size; - } - - /* kvm/qemu doesn't have mtrr set right, don't trim them all */ - if (!highest_pfn) { - printk(KERN_INFO "CPU MTRRs all blank - virtualized system.\n"); - return 0; - } - - /* check entries number */ - memset(num, 0, sizeof(num)); - for (i = 0; i < num_var_ranges; i++) { - type = range_state[i].type; - if (type >= MTRR_NUM_TYPES) - continue; - size = range_state[i].size_pfn; - if (!size) - type = MTRR_NUM_TYPES; - num[type]++; - } - - /* no entry for WB? */ - if (!num[MTRR_TYPE_WRBACK]) - return 0; - - /* check if we only had WB and UC */ - if (num[MTRR_TYPE_WRBACK] + num[MTRR_TYPE_UNCACHABLE] != - num_var_ranges - num[MTRR_NUM_TYPES]) - return 0; - - memset(range, 0, sizeof(range)); - nr_range = 0; - if (mtrr_tom2) { - range[nr_range].start = (1ULL<<(32 - PAGE_SHIFT)); - range[nr_range].end = (mtrr_tom2 >> PAGE_SHIFT) - 1; - if (highest_pfn < range[nr_range].end + 1) - highest_pfn = range[nr_range].end + 1; - nr_range++; - } - nr_range = x86_get_mtrr_mem_range(range, nr_range, 0, 0); - - total_trim_size = 0; - /* check the head */ - if (range[0].start) - total_trim_size += real_trim_memory(0, range[0].start); - /* check the holes */ - for (i = 0; i < nr_range - 1; i++) { - if (range[i].end + 1 < range[i+1].start) - total_trim_size += real_trim_memory(range[i].end + 1, - range[i+1].start); - } - /* check the top */ - i = nr_range - 1; - if (range[i].end + 1 < end_pfn) - total_trim_size += real_trim_memory(range[i].end + 1, - end_pfn); - - if (total_trim_size) { - printk(KERN_WARNING "WARNING: BIOS bug: CPU MTRRs don't cover" - " all of memory, losing %lluMB of RAM.\n", - total_trim_size >> 20); - - if (!changed_by_mtrr_cleanup) - WARN_ON(1); - - printk(KERN_INFO "update e820 for mtrr\n"); - update_e820(); - - return 1; - } - - return 0; -} +int __initdata changed_by_mtrr_cleanup; /** * mtrr_bp_init - initialize mtrrs on the boot CPU diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index ffd6040..77f67f7 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -79,6 +79,7 @@ extern struct mtrr_ops * mtrr_if; extern unsigned int num_var_ranges; extern u64 mtrr_tom2; +extern struct mtrr_state_type mtrr_state; void mtrr_state_warn(void); const char *mtrr_attrib_to_str(int x); @@ -88,3 +89,6 @@ void mtrr_wrmsr(unsigned, unsigned, unsigned); int amd_init_mtrr(void); int cyrix_init_mtrr(void); int centaur_init_mtrr(void); + +extern int changed_by_mtrr_cleanup; +extern int mtrr_cleanup(unsigned address_bits); diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 01b1244..f93047f 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -7,15 +7,14 @@ /* * Get CPU information for use by the procfs. */ -#ifdef CONFIG_X86_32 static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, unsigned int cpu) { -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP if (c->x86_max_cores * smp_num_siblings > 1) { seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); seq_printf(m, "siblings\t: %d\n", - cpus_weight(per_cpu(cpu_core_map, cpu))); + cpumask_weight(cpu_sibling_mask(cpu))); seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); seq_printf(m, "apicid\t\t: %d\n", c->apicid); @@ -24,6 +23,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, #endif } +#ifdef CONFIG_X86_32 static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) { /* @@ -50,22 +50,6 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) c->wp_works_ok ? "yes" : "no"); } #else -static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, - unsigned int cpu) -{ -#ifdef CONFIG_SMP - if (c->x86_max_cores * smp_num_siblings > 1) { - seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); - seq_printf(m, "siblings\t: %d\n", - cpus_weight(per_cpu(cpu_core_map, cpu))); - seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); - seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); - seq_printf(m, "apicid\t\t: %d\n", c->apicid); - seq_printf(m, "initial apicid\t: %d\n", c->initial_apicid); - } -#endif -} - static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) { seq_printf(m, @@ -159,9 +143,9 @@ static int show_cpuinfo(struct seq_file *m, void *v) static void *c_start(struct seq_file *m, loff_t *pos) { if (*pos == 0) /* just in case, cpu 0 is not the first */ - *pos = first_cpu(cpu_online_map); + *pos = cpumask_first(cpu_online_mask); else - *pos = next_cpu_nr(*pos - 1, cpu_online_map); + *pos = cpumask_next(*pos - 1, cpu_online_mask); if ((*pos) < nr_cpu_ids) return &cpu_data(*pos); return NULL; diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 52b3fef..bb62b3e 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -98,7 +98,7 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c) #endif } -static struct cpu_dev transmeta_cpu_dev __cpuinitdata = { +static const struct cpu_dev __cpuinitconst transmeta_cpu_dev = { .c_vendor = "Transmeta", .c_ident = { "GenuineTMx86", "TransmetaCPU" }, .c_early_init = early_init_transmeta, diff --git a/arch/x86/kernel/cpu/umc.c b/arch/x86/kernel/cpu/umc.c index e777f79..fd2c37b 100644 --- a/arch/x86/kernel/cpu/umc.c +++ b/arch/x86/kernel/cpu/umc.c @@ -8,7 +8,7 @@ * so no special init takes place. */ -static struct cpu_dev umc_cpu_dev __cpuinitdata = { +static const struct cpu_dev __cpuinitconst umc_cpu_dev = { .c_vendor = "UMC", .c_ident = { "UMC UMC UMC" }, .c_models = { diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c index 169a120..87b67e3 100644 --- a/arch/x86/kernel/ds.c +++ b/arch/x86/kernel/ds.c @@ -729,7 +729,7 @@ struct pebs_tracer *ds_request_pebs(struct task_struct *task, spin_unlock_irqrestore(&ds_lock, irq); - ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts); + ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_pebs); ds_resume_pebs(tracer); return tracer; @@ -1029,5 +1029,4 @@ void ds_copy_thread(struct task_struct *tsk, struct task_struct *father) void ds_exit_thread(struct task_struct *tsk) { - WARN_ON(tsk->thread.ds_ctx); } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 87d103d..95ea5fa 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -10,10 +10,12 @@ #include <linux/kdebug.h> #include <linux/module.h> #include <linux/ptrace.h> +#include <linux/ftrace.h> #include <linux/kexec.h> #include <linux/bug.h> #include <linux/nmi.h> #include <linux/sysfs.h> +#include <linux/ftrace.h> #include <asm/stacktrace.h> @@ -195,6 +197,11 @@ unsigned __kprobes long oops_begin(void) int cpu; unsigned long flags; + /* notify the hw-branch tracer so it may disable tracing and + add the last trace to the trace buffer - + the earlier this happens, the more useful the trace. */ + trace_hw_branch_oops(); + oops_enter(); /* racy, but better than risking deadlock. */ diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 508bec1..ef2c356 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -110,19 +110,50 @@ int __init e820_all_mapped(u64 start, u64 end, unsigned type) /* * Add a memory region to the kernel e820 map. */ -void __init e820_add_region(u64 start, u64 size, int type) +static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size, + int type) { - int x = e820.nr_map; + int x = e820x->nr_map; - if (x == ARRAY_SIZE(e820.map)) { + if (x == ARRAY_SIZE(e820x->map)) { printk(KERN_ERR "Ooops! Too many entries in the memory map!\n"); return; } - e820.map[x].addr = start; - e820.map[x].size = size; - e820.map[x].type = type; - e820.nr_map++; + e820x->map[x].addr = start; + e820x->map[x].size = size; + e820x->map[x].type = type; + e820x->nr_map++; +} + +void __init e820_add_region(u64 start, u64 size, int type) +{ + __e820_add_region(&e820, start, size, type); +} + +static void __init e820_print_type(u32 type) +{ + switch (type) { + case E820_RAM: + case E820_RESERVED_KERN: + printk(KERN_CONT "(usable)"); + break; + case E820_RESERVED: + printk(KERN_CONT "(reserved)"); + break; + case E820_ACPI: + printk(KERN_CONT "(ACPI data)"); + break; + case E820_NVS: + printk(KERN_CONT "(ACPI NVS)"); + break; + case E820_UNUSABLE: + printk(KERN_CONT "(unusable)"); + break; + default: + printk(KERN_CONT "type %u", type); + break; + } } void __init e820_print_map(char *who) @@ -134,27 +165,8 @@ void __init e820_print_map(char *who) (unsigned long long) e820.map[i].addr, (unsigned long long) (e820.map[i].addr + e820.map[i].size)); - switch (e820.map[i].type) { - case E820_RAM: - case E820_RESERVED_KERN: - printk(KERN_CONT "(usable)\n"); - break; - case E820_RESERVED: - printk(KERN_CONT "(reserved)\n"); - break; - case E820_ACPI: - printk(KERN_CONT "(ACPI data)\n"); - break; - case E820_NVS: - printk(KERN_CONT "(ACPI NVS)\n"); - break; - case E820_UNUSABLE: - printk("(unusable)\n"); - break; - default: - printk(KERN_CONT "type %u\n", e820.map[i].type); - break; - } + e820_print_type(e820.map[i].type); + printk(KERN_CONT "\n"); } } @@ -221,7 +233,7 @@ void __init e820_print_map(char *who) */ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, - int *pnr_map) + u32 *pnr_map) { struct change_member { struct e820entry *pbios; /* pointer to original bios entry */ @@ -417,11 +429,12 @@ static int __init append_e820_map(struct e820entry *biosmap, int nr_map) return __append_e820_map(biosmap, nr_map); } -static u64 __init e820_update_range_map(struct e820map *e820x, u64 start, +static u64 __init __e820_update_range(struct e820map *e820x, u64 start, u64 size, unsigned old_type, unsigned new_type) { - int i; + u64 end; + unsigned int i; u64 real_updated_size = 0; BUG_ON(old_type == new_type); @@ -429,27 +442,55 @@ static u64 __init e820_update_range_map(struct e820map *e820x, u64 start, if (size > (ULLONG_MAX - start)) size = ULLONG_MAX - start; - for (i = 0; i < e820.nr_map; i++) { + end = start + size; + printk(KERN_DEBUG "e820 update range: %016Lx - %016Lx ", + (unsigned long long) start, + (unsigned long long) end); + e820_print_type(old_type); + printk(KERN_CONT " ==> "); + e820_print_type(new_type); + printk(KERN_CONT "\n"); + + for (i = 0; i < e820x->nr_map; i++) { struct e820entry *ei = &e820x->map[i]; u64 final_start, final_end; + u64 ei_end; + if (ei->type != old_type) continue; - /* totally covered? */ - if (ei->addr >= start && - (ei->addr + ei->size) <= (start + size)) { + + ei_end = ei->addr + ei->size; + /* totally covered by new range? */ + if (ei->addr >= start && ei_end <= end) { ei->type = new_type; real_updated_size += ei->size; continue; } + + /* new range is totally covered? */ + if (ei->addr < start && ei_end > end) { + __e820_add_region(e820x, start, size, new_type); + __e820_add_region(e820x, end, ei_end - end, ei->type); + ei->size = start - ei->addr; + real_updated_size += size; + continue; + } + /* partially covered */ final_start = max(start, ei->addr); - final_end = min(start + size, ei->addr + ei->size); + final_end = min(end, ei_end); if (final_start >= final_end) continue; - e820_add_region(final_start, final_end - final_start, - new_type); + + __e820_add_region(e820x, final_start, final_end - final_start, + new_type); + real_updated_size += final_end - final_start; + /* + * left range could be head or tail, so need to update + * size at first. + */ ei->size -= final_end - final_start; if (ei->addr < final_start) continue; @@ -461,13 +502,13 @@ static u64 __init e820_update_range_map(struct e820map *e820x, u64 start, u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, unsigned new_type) { - return e820_update_range_map(&e820, start, size, old_type, new_type); + return __e820_update_range(&e820, start, size, old_type, new_type); } static u64 __init e820_update_range_saved(u64 start, u64 size, unsigned old_type, unsigned new_type) { - return e820_update_range_map(&e820_saved, start, size, old_type, + return __e820_update_range(&e820_saved, start, size, old_type, new_type); } @@ -511,7 +552,7 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, void __init update_e820(void) { - int nr_map; + u32 nr_map; nr_map = e820.nr_map; if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map)) @@ -522,7 +563,7 @@ void __init update_e820(void) } static void __init update_e820_saved(void) { - int nr_map; + u32 nr_map; nr_map = e820_saved.nr_map; if (sanitize_e820_map(e820_saved.map, ARRAY_SIZE(e820_saved.map), &nr_map)) @@ -1020,8 +1061,8 @@ u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align) continue; return addr; } - return -1UL; + return -1ULL; } /* @@ -1034,13 +1075,22 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) u64 start; start = startt; - while (size < sizet) + while (size < sizet && (start + 1)) start = find_e820_area_size(start, &size, align); if (size < sizet) return 0; +#ifdef CONFIG_X86_32 + if (start >= MAXMEM) + return 0; + if (start + size > MAXMEM) + size = MAXMEM - start; +#endif + addr = round_down(start + size - sizet, align); + if (addr < start) + return 0; e820_update_range(addr, sizet, E820_RAM, E820_RESERVED); e820_update_range_saved(addr, sizet, E820_RAM, E820_RESERVED); printk(KERN_INFO "update e820 for early_reserve_e820\n"); @@ -1253,7 +1303,7 @@ early_param("memmap", parse_memmap_opt); void __init finish_e820_parsing(void) { if (userdef) { - int nr = e820.nr_map; + u32 nr = e820.nr_map; if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr) < 0) early_panic("Invalid user supplied memory map"); @@ -1336,7 +1386,7 @@ void __init e820_reserve_resources_late(void) char *__init default_machine_specific_memory_setup(void) { char *who = "BIOS-e820"; - int new_nr; + u32 new_nr; /* * Try to copy the BIOS-supplied E820-map. * diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 639ad98..335f049 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -250,7 +250,7 @@ static int dbgp_wait_until_complete(void) return (ctrl & DBGP_ERROR) ? -DBGP_ERRCODE(ctrl) : DBGP_LEN(ctrl); } -static void dbgp_mdelay(int ms) +static void __init dbgp_mdelay(int ms) { int i; @@ -311,7 +311,7 @@ static void dbgp_set_data(const void *buf, int size) writel(hi, &ehci_debug->data47); } -static void dbgp_get_data(void *buf, int size) +static void __init dbgp_get_data(void *buf, int size) { unsigned char *bytes = buf; u32 lo, hi; @@ -355,7 +355,7 @@ static int dbgp_bulk_write(unsigned devnum, unsigned endpoint, return ret; } -static int dbgp_bulk_read(unsigned devnum, unsigned endpoint, void *data, +static int __init dbgp_bulk_read(unsigned devnum, unsigned endpoint, void *data, int size) { u32 pids, addr, ctrl; @@ -386,8 +386,8 @@ static int dbgp_bulk_read(unsigned devnum, unsigned endpoint, void *data, return ret; } -static int dbgp_control_msg(unsigned devnum, int requesttype, int request, - int value, int index, void *data, int size) +static int __init dbgp_control_msg(unsigned devnum, int requesttype, + int request, int value, int index, void *data, int size) { u32 pids, addr, ctrl; struct usb_ctrlrequest req; @@ -489,7 +489,7 @@ static u32 __init find_dbgp(int ehci_num, u32 *rbus, u32 *rslot, u32 *rfunc) return 0; } -static int ehci_reset_port(int port) +static int __init ehci_reset_port(int port) { u32 portsc; u32 delay_time, delay; @@ -532,7 +532,7 @@ static int ehci_reset_port(int port) return -EBUSY; } -static int ehci_wait_for_port(int port) +static int __init ehci_wait_for_port(int port) { u32 status; int ret, reps; @@ -557,13 +557,13 @@ static inline void dbgp_printk(const char *fmt, ...) { } typedef void (*set_debug_port_t)(int port); -static void default_set_debug_port(int port) +static void __init default_set_debug_port(int port) { } -static set_debug_port_t set_debug_port = default_set_debug_port; +static set_debug_port_t __initdata set_debug_port = default_set_debug_port; -static void nvidia_set_debug_port(int port) +static void __init nvidia_set_debug_port(int port) { u32 dword; dword = read_pci_config(ehci_dev.bus, ehci_dev.slot, ehci_dev.func, diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c index b205272..1736acc 100644 --- a/arch/x86/kernel/efi.c +++ b/arch/x86/kernel/efi.c @@ -469,7 +469,7 @@ void __init efi_enter_virtual_mode(void) efi_memory_desc_t *md; efi_status_t status; unsigned long size; - u64 end, systab, addr, npages; + u64 end, systab, addr, npages, end_pfn; void *p, *va; efi.systab = NULL; @@ -481,7 +481,10 @@ void __init efi_enter_virtual_mode(void) size = md->num_pages << EFI_PAGE_SHIFT; end = md->phys_addr + size; - if (PFN_UP(end) <= max_low_pfn_mapped) + end_pfn = PFN_UP(end); + if (end_pfn <= max_low_pfn_mapped + || (end_pfn > (1UL << (32 - PAGE_SHIFT)) + && end_pfn <= max_pfn_mapped)) va = __va(md->phys_addr); else va = efi_ioremap(md->phys_addr, size); diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c index a4ee291..22c3b78 100644 --- a/arch/x86/kernel/efi_64.c +++ b/arch/x86/kernel/efi_64.c @@ -100,24 +100,11 @@ void __init efi_call_phys_epilog(void) void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size) { - static unsigned pages_mapped __initdata; - unsigned i, pages; - unsigned long offset; + unsigned long last_map_pfn; - pages = PFN_UP(phys_addr + size) - PFN_DOWN(phys_addr); - offset = phys_addr & ~PAGE_MASK; - phys_addr &= PAGE_MASK; - - if (pages_mapped + pages > MAX_EFI_IO_PAGES) + last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size); + if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) return NULL; - for (i = 0; i < pages; i++) { - __set_fixmap(FIX_EFI_IO_MAP_FIRST_PAGE - pages_mapped, - phys_addr, PAGE_KERNEL); - phys_addr += PAGE_SIZE; - pages_mapped++; - } - - return (void __iomem *)__fix_to_virt(FIX_EFI_IO_MAP_FIRST_PAGE - \ - (pages_mapped - pages)) + offset; + return (void __iomem *)__va(phys_addr); } diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 899e893..c929add 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -442,8 +442,7 @@ sysenter_past_esp: GET_THREAD_INFO(%ebp) - /* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */ - testw $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) + testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) jnz sysenter_audit sysenter_do_call: cmpl $(nr_syscalls), %eax @@ -454,7 +453,7 @@ sysenter_do_call: DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx - testw $_TIF_ALLWORK_MASK, %cx + testl $_TIF_ALLWORK_MASK, %ecx jne sysexit_audit sysenter_exit: /* if something modifies registers it must also disable sysexit */ @@ -468,7 +467,7 @@ sysenter_exit: #ifdef CONFIG_AUDITSYSCALL sysenter_audit: - testw $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp) + testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp) jnz syscall_trace_entry addl $4,%esp CFI_ADJUST_CFA_OFFSET -4 @@ -485,7 +484,7 @@ sysenter_audit: jmp sysenter_do_call sysexit_audit: - testw $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %cx + testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx jne syscall_exit_work TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_ANY) @@ -498,7 +497,7 @@ sysexit_audit: DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx - testw $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %cx + testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx jne syscall_exit_work movl PT_EAX(%esp),%eax /* reload syscall return value */ jmp sysenter_exit @@ -523,8 +522,7 @@ ENTRY(system_call) SAVE_ALL GET_THREAD_INFO(%ebp) # system call tracing in operation / emulation - /* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */ - testw $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) + testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) jnz syscall_trace_entry cmpl $(nr_syscalls), %eax jae syscall_badsys @@ -538,7 +536,7 @@ syscall_exit: # between sampling and the iret TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx - testw $_TIF_ALLWORK_MASK, %cx # current->work + testl $_TIF_ALLWORK_MASK, %ecx # current->work jne syscall_exit_work restore_all: @@ -673,7 +671,7 @@ END(syscall_trace_entry) # perform syscall exit tracing ALIGN syscall_exit_work: - testb $_TIF_WORK_SYSCALL_EXIT, %cl + testl $_TIF_WORK_SYSCALL_EXIT, %ecx jz work_pending TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_ANY) # could let syscall_trace_leave() call diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 24c7031..3f129d9 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -368,6 +368,7 @@ ENTRY(save_rest) END(save_rest) /* save complete stack frame */ + .pushsection .kprobes.text, "ax" ENTRY(save_paranoid) XCPT_FRAME 1 RDI+8 cld @@ -396,6 +397,7 @@ ENTRY(save_paranoid) 1: ret CFI_ENDPROC END(save_paranoid) + .popsection /* * A newly forked process directly context switches into this address. @@ -416,7 +418,6 @@ ENTRY(ret_from_fork) GET_THREAD_INFO(%rcx) - CFI_REMEMBER_STATE RESTORE_REST testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread? @@ -428,7 +429,6 @@ ENTRY(ret_from_fork) RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET jmp ret_from_sys_call # go to the SYSRET fastpath - CFI_RESTORE_STATE CFI_ENDPROC END(ret_from_fork) @@ -984,6 +984,8 @@ apicinterrupt UV_BAU_MESSAGE \ #endif apicinterrupt LOCAL_TIMER_VECTOR \ apic_timer_interrupt smp_apic_timer_interrupt +apicinterrupt GENERIC_INTERRUPT_VECTOR \ + generic_interrupt smp_generic_interrupt #ifdef CONFIG_SMP apicinterrupt INVALIDATE_TLB_VECTOR_START+0 \ diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 231bdd3..61df775 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -18,6 +18,7 @@ #include <linux/init.h> #include <linux/list.h> +#include <asm/cacheflush.h> #include <asm/ftrace.h> #include <linux/ftrace.h> #include <asm/nops.h> @@ -26,6 +27,18 @@ #ifdef CONFIG_DYNAMIC_FTRACE +int ftrace_arch_code_modify_prepare(void) +{ + set_kernel_text_rw(); + return 0; +} + +int ftrace_arch_code_modify_post_process(void) +{ + set_kernel_text_ro(); + return 0; +} + union ftrace_code_union { char code[MCOUNT_INSN_SIZE]; struct { @@ -66,11 +79,11 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) * * 1) Put the instruction pointer into the IP buffer * and the new code into the "code" buffer. - * 2) Set a flag that says we are modifying code - * 3) Wait for any running NMIs to finish. - * 4) Write the code - * 5) clear the flag. - * 6) Wait for any running NMIs to finish. + * 2) Wait for any running NMIs to finish and set a flag that says + * we are modifying code, it is done in an atomic operation. + * 3) Write the code + * 4) clear the flag. + * 5) Wait for any running NMIs to finish. * * If an NMI is executed, the first thing it does is to call * "ftrace_nmi_enter". This will check if the flag is set to write @@ -82,9 +95,9 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) * are the same as what exists. */ -static atomic_t in_nmi = ATOMIC_INIT(0); +#define MOD_CODE_WRITE_FLAG (1 << 31) /* set when NMI should do the write */ +static atomic_t nmi_running = ATOMIC_INIT(0); static int mod_code_status; /* holds return value of text write */ -static int mod_code_write; /* set when NMI should do the write */ static void *mod_code_ip; /* holds the IP to write to */ static void *mod_code_newcode; /* holds the text to write to the IP */ @@ -101,6 +114,20 @@ int ftrace_arch_read_dyn_info(char *buf, int size) return r; } +static void clear_mod_flag(void) +{ + int old = atomic_read(&nmi_running); + + for (;;) { + int new = old & ~MOD_CODE_WRITE_FLAG; + + if (old == new) + break; + + old = atomic_cmpxchg(&nmi_running, old, new); + } +} + static void ftrace_mod_code(void) { /* @@ -111,37 +138,52 @@ static void ftrace_mod_code(void) */ mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode, MCOUNT_INSN_SIZE); + + /* if we fail, then kill any new writers */ + if (mod_code_status) + clear_mod_flag(); } void ftrace_nmi_enter(void) { - atomic_inc(&in_nmi); - /* Must have in_nmi seen before reading write flag */ - smp_mb(); - if (mod_code_write) { + if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) { + smp_rmb(); ftrace_mod_code(); atomic_inc(&nmi_update_count); } + /* Must have previous changes seen before executions */ + smp_mb(); } void ftrace_nmi_exit(void) { - /* Finish all executions before clearing in_nmi */ - smp_wmb(); - atomic_dec(&in_nmi); + /* Finish all executions before clearing nmi_running */ + smp_mb(); + atomic_dec(&nmi_running); +} + +static void wait_for_nmi_and_set_mod_flag(void) +{ + if (!atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG)) + return; + + do { + cpu_relax(); + } while (atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG)); + + nmi_wait_count++; } static void wait_for_nmi(void) { - int waited = 0; + if (!atomic_read(&nmi_running)) + return; - while (atomic_read(&in_nmi)) { - waited = 1; + do { cpu_relax(); - } + } while (atomic_read(&nmi_running)); - if (waited) - nmi_wait_count++; + nmi_wait_count++; } static int @@ -151,14 +193,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code) mod_code_newcode = new_code; /* The buffers need to be visible before we let NMIs write them */ - smp_wmb(); - - mod_code_write = 1; - - /* Make sure write bit is visible before we wait on NMIs */ smp_mb(); - wait_for_nmi(); + wait_for_nmi_and_set_mod_flag(); /* Make sure all running NMIs have finished before we write the code */ smp_mb(); @@ -166,13 +203,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code) ftrace_mod_code(); /* Make sure the write happens before clearing the bit */ - smp_wmb(); - - mod_code_write = 0; - - /* make sure NMIs see the cleared bit */ smp_mb(); + clear_mod_flag(); wait_for_nmi(); return mod_code_status; @@ -368,100 +401,8 @@ int ftrace_disable_ftrace_graph_caller(void) return ftrace_mod_jmp(ip, old_offset, new_offset); } -#else /* CONFIG_DYNAMIC_FTRACE */ - -/* - * These functions are picked from those used on - * this page for dynamic ftrace. They have been - * simplified to ignore all traces in NMI context. - */ -static atomic_t in_nmi; - -void ftrace_nmi_enter(void) -{ - atomic_inc(&in_nmi); -} - -void ftrace_nmi_exit(void) -{ - atomic_dec(&in_nmi); -} - #endif /* !CONFIG_DYNAMIC_FTRACE */ -/* Add a function return address to the trace stack on thread info.*/ -static int push_return_trace(unsigned long ret, unsigned long long time, - unsigned long func, int *depth) -{ - int index; - - if (!current->ret_stack) - return -EBUSY; - - /* The return trace stack is full */ - if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) { - atomic_inc(¤t->trace_overrun); - return -EBUSY; - } - - index = ++current->curr_ret_stack; - barrier(); - current->ret_stack[index].ret = ret; - current->ret_stack[index].func = func; - current->ret_stack[index].calltime = time; - *depth = index; - - return 0; -} - -/* Retrieve a function return address to the trace stack on thread info.*/ -static void pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret) -{ - int index; - - index = current->curr_ret_stack; - - if (unlikely(index < 0)) { - ftrace_graph_stop(); - WARN_ON(1); - /* Might as well panic, otherwise we have no where to go */ - *ret = (unsigned long)panic; - return; - } - - *ret = current->ret_stack[index].ret; - trace->func = current->ret_stack[index].func; - trace->calltime = current->ret_stack[index].calltime; - trace->overrun = atomic_read(¤t->trace_overrun); - trace->depth = index; - barrier(); - current->curr_ret_stack--; - -} - -/* - * Send the trace to the ring-buffer. - * @return the original return address. - */ -unsigned long ftrace_return_to_handler(void) -{ - struct ftrace_graph_ret trace; - unsigned long ret; - - pop_return_trace(&trace, &ret); - trace.rettime = cpu_clock(raw_smp_processor_id()); - ftrace_graph_return(&trace); - - if (unlikely(!ret)) { - ftrace_graph_stop(); - WARN_ON(1); - /* Might as well panic. What else to do? */ - ret = (unsigned long)panic; - } - - return ret; -} - /* * Hook the return address and push it in the stack of return addrs * in current thread info. @@ -469,14 +410,13 @@ unsigned long ftrace_return_to_handler(void) void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) { unsigned long old; - unsigned long long calltime; int faulted; struct ftrace_graph_ent trace; unsigned long return_hooker = (unsigned long) &return_to_handler; /* Nmi's are currently unsupported */ - if (unlikely(atomic_read(&in_nmi))) + if (unlikely(in_nmi())) return; if (unlikely(atomic_read(¤t->tracing_graph_pause))) @@ -512,17 +452,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - if (unlikely(!__kernel_text_address(old))) { - ftrace_graph_stop(); - *parent = old; - WARN_ON(1); - return; - } - - calltime = cpu_clock(raw_smp_processor_id()); - - if (push_return_trace(old, calltime, - self_addr, &trace.depth) == -EBUSY) { + if (ftrace_push_return_trace(old, self_addr, &trace.depth) == -EBUSY) { *parent = old; return; } @@ -536,3 +466,66 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) } } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +#ifdef CONFIG_FTRACE_SYSCALLS + +extern unsigned long __start_syscalls_metadata[]; +extern unsigned long __stop_syscalls_metadata[]; +extern unsigned long *sys_call_table; + +static struct syscall_metadata **syscalls_metadata; + +static struct syscall_metadata *find_syscall_meta(unsigned long *syscall) +{ + struct syscall_metadata *start; + struct syscall_metadata *stop; + char str[KSYM_SYMBOL_LEN]; + + + start = (struct syscall_metadata *)__start_syscalls_metadata; + stop = (struct syscall_metadata *)__stop_syscalls_metadata; + kallsyms_lookup((unsigned long) syscall, NULL, NULL, NULL, str); + + for ( ; start < stop; start++) { + if (start->name && !strcmp(start->name, str)) + return start; + } + return NULL; +} + +struct syscall_metadata *syscall_nr_to_meta(int nr) +{ + if (!syscalls_metadata || nr >= FTRACE_SYSCALL_MAX || nr < 0) + return NULL; + + return syscalls_metadata[nr]; +} + +void arch_init_ftrace_syscalls(void) +{ + int i; + struct syscall_metadata *meta; + unsigned long **psys_syscall_table = &sys_call_table; + static atomic_t refs; + + if (atomic_inc_return(&refs) != 1) + goto end; + + syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * + FTRACE_SYSCALL_MAX, GFP_KERNEL); + if (!syscalls_metadata) { + WARN_ON(1); + return; + } + + for (i = 0; i < FTRACE_SYSCALL_MAX; i++) { + meta = find_syscall_meta(psys_syscall_table[i]); + syscalls_metadata[i] = meta; + } + return; + + /* Paranoid: avoid overflow */ +end: + atomic_dec(&refs); +} +#endif diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index ac108d1..3f8579f 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -18,7 +18,7 @@ void __init i386_start_kernel(void) { reserve_trampoline_memory(); - reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS"); + reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ @@ -29,9 +29,6 @@ void __init i386_start_kernel(void) reserve_early(ramdisk_image, ramdisk_end, "RAMDISK"); } #endif - reserve_early(init_pg_tables_start, init_pg_tables_end, - "INIT_PG_TABLE"); - reserve_ebda_region(); /* diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index f5b2722..70eaa85 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -100,7 +100,7 @@ void __init x86_64_start_reservations(char *real_mode_data) reserve_trampoline_memory(); - reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS"); + reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index c32ca19..3068388 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -38,42 +38,40 @@ #define X86_VENDOR_ID new_cpu_data+CPUINFO_x86_vendor_id /* - * This is how much memory *in addition to the memory covered up to - * and including _end* we need mapped initially. + * This is how much memory in addition to the memory covered up to + * and including _end we need mapped initially. * We need: - * - one bit for each possible page, but only in low memory, which means - * 2^32/4096/8 = 128K worst case (4G/4G split.) - * - enough space to map all low memory, which means - * (2^32/4096) / 1024 pages (worst case, non PAE) - * (2^32/4096) / 512 + 4 pages (worst case for PAE) - * - a few pages for allocator use before the kernel pagetable has - * been set up + * (KERNEL_IMAGE_SIZE/4096) / 1024 pages (worst case, non PAE) + * (KERNEL_IMAGE_SIZE/4096) / 512 + 4 pages (worst case for PAE) * * Modulo rounding, each megabyte assigned here requires a kilobyte of * memory, which is currently unreclaimed. * * This should be a multiple of a page. + * + * KERNEL_IMAGE_SIZE should be greater than pa(_end) + * and small than max_low_pfn, otherwise will waste some page table entries */ -LOW_PAGES = 1<<(32-PAGE_SHIFT_asm) - -/* - * To preserve the DMA pool in PAGEALLOC kernels, we'll allocate - * pagetables from above the 16MB DMA limit, so we'll have to set - * up pagetables 16MB more (worst-case): - */ -#ifdef CONFIG_DEBUG_PAGEALLOC -LOW_PAGES = LOW_PAGES + 0x1000000 -#endif #if PTRS_PER_PMD > 1 -PAGE_TABLE_SIZE = (LOW_PAGES / PTRS_PER_PMD) + PTRS_PER_PGD +#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD) #else -PAGE_TABLE_SIZE = (LOW_PAGES / PTRS_PER_PGD) +#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD) #endif -BOOTBITMAP_SIZE = LOW_PAGES / 8 -ALLOCATOR_SLOP = 4 -INIT_MAP_BEYOND_END = BOOTBITMAP_SIZE + (PAGE_TABLE_SIZE + ALLOCATOR_SLOP)*PAGE_SIZE_asm +/* Enough space to fit pagetables for the low memory linear map */ +MAPPING_BEYOND_END = \ + PAGE_TABLE_SIZE(((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) << PAGE_SHIFT + +/* + * Worst-case size of the kernel mapping we need to make: + * the worst-case size of the kernel itself, plus the extra we need + * to map for the linear map. + */ +KERNEL_PAGES = (KERNEL_IMAGE_SIZE + MAPPING_BEYOND_END)>>PAGE_SHIFT + +INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE_asm +RESERVE_BRK(pagetables, INIT_MAP_SIZE) /* * 32-bit kernel entrypoint; only used by the boot CPU. On entry, @@ -166,10 +164,10 @@ num_subarch_entries = (. - subarch_entries) / 4 /* * Initialize page tables. This creates a PDE and a set of page - * tables, which are located immediately beyond _end. The variable - * init_pg_tables_end is set up to point to the first "safe" location. + * tables, which are located immediately beyond __brk_base. The variable + * _brk_end is set up to point to the first "safe" location. * Mappings are created both at virtual address 0 (identity mapping) - * and PAGE_OFFSET for up to _end+sizeof(page tables)+INIT_MAP_BEYOND_END. + * and PAGE_OFFSET for up to _end. * * Note that the stack is not yet set up! */ @@ -190,8 +188,7 @@ default_entry: xorl %ebx,%ebx /* %ebx is kept at zero */ - movl $pa(pg0), %edi - movl %edi, pa(init_pg_tables_start) + movl $pa(__brk_base), %edi movl $pa(swapper_pg_pmd), %edx movl $PTE_IDENT_ATTR, %eax 10: @@ -209,14 +206,14 @@ default_entry: loop 11b /* - * End condition: we must map up to and including INIT_MAP_BEYOND_END - * bytes beyond the end of our own page tables. + * End condition: we must map up to the end + MAPPING_BEYOND_END. */ - leal (INIT_MAP_BEYOND_END+PTE_IDENT_ATTR)(%edi),%ebp + movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp cmpl %ebp,%eax jb 10b 1: - movl %edi,pa(init_pg_tables_end) + addl $__PAGE_OFFSET, %edi + movl %edi, pa(_brk_end) shrl $12, %eax movl %eax, pa(max_pfn_mapped) @@ -227,8 +224,7 @@ default_entry: page_pde_offset = (__PAGE_OFFSET >> 20); - movl $pa(pg0), %edi - movl %edi, pa(init_pg_tables_start) + movl $pa(__brk_base), %edi movl $pa(swapper_pg_dir), %edx movl $PTE_IDENT_ATTR, %eax 10: @@ -242,14 +238,13 @@ page_pde_offset = (__PAGE_OFFSET >> 20); addl $0x1000,%eax loop 11b /* - * End condition: we must map up to and including INIT_MAP_BEYOND_END - * bytes beyond the end of our own page tables; the +0x007 is - * the attribute bits + * End condition: we must map up to the end + MAPPING_BEYOND_END. */ - leal (INIT_MAP_BEYOND_END+PTE_IDENT_ATTR)(%edi),%ebp + movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp cmpl %ebp,%eax jb 10b - movl %edi,pa(init_pg_tables_end) + addl $__PAGE_OFFSET, %edi + movl %edi, pa(_brk_end) shrl $12, %eax movl %eax, pa(max_pfn_mapped) @@ -636,6 +631,7 @@ swapper_pg_fixmap: .fill 1024,4,0 ENTRY(empty_zero_page) .fill 4096,1,0 + /* * This starts the data section. */ diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index a00545f..648b3a2 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -80,6 +80,7 @@ static inline void hpet_clear_mapping(void) */ static int boot_hpet_disable; int hpet_force_user; +static int hpet_verbose; static int __init hpet_setup(char *str) { @@ -88,6 +89,8 @@ static int __init hpet_setup(char *str) boot_hpet_disable = 1; if (!strncmp("force", str, 5)) hpet_force_user = 1; + if (!strncmp("verbose", str, 7)) + hpet_verbose = 1; } return 1; } @@ -119,6 +122,43 @@ int is_hpet_enabled(void) } EXPORT_SYMBOL_GPL(is_hpet_enabled); +static void _hpet_print_config(const char *function, int line) +{ + u32 i, timers, l, h; + printk(KERN_INFO "hpet: %s(%d):\n", function, line); + l = hpet_readl(HPET_ID); + h = hpet_readl(HPET_PERIOD); + timers = ((l & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT) + 1; + printk(KERN_INFO "hpet: ID: 0x%x, PERIOD: 0x%x\n", l, h); + l = hpet_readl(HPET_CFG); + h = hpet_readl(HPET_STATUS); + printk(KERN_INFO "hpet: CFG: 0x%x, STATUS: 0x%x\n", l, h); + l = hpet_readl(HPET_COUNTER); + h = hpet_readl(HPET_COUNTER+4); + printk(KERN_INFO "hpet: COUNTER_l: 0x%x, COUNTER_h: 0x%x\n", l, h); + + for (i = 0; i < timers; i++) { + l = hpet_readl(HPET_Tn_CFG(i)); + h = hpet_readl(HPET_Tn_CFG(i)+4); + printk(KERN_INFO "hpet: T%d: CFG_l: 0x%x, CFG_h: 0x%x\n", + i, l, h); + l = hpet_readl(HPET_Tn_CMP(i)); + h = hpet_readl(HPET_Tn_CMP(i)+4); + printk(KERN_INFO "hpet: T%d: CMP_l: 0x%x, CMP_h: 0x%x\n", + i, l, h); + l = hpet_readl(HPET_Tn_ROUTE(i)); + h = hpet_readl(HPET_Tn_ROUTE(i)+4); + printk(KERN_INFO "hpet: T%d ROUTE_l: 0x%x, ROUTE_h: 0x%x\n", + i, l, h); + } +} + +#define hpet_print_config() \ +do { \ + if (hpet_verbose) \ + _hpet_print_config(__FUNCTION__, __LINE__); \ +} while (0) + /* * When the hpet driver (/dev/hpet) is enabled, we need to reserve * timer 0 and timer 1 in case of RTC emulation. @@ -191,27 +231,37 @@ static struct clock_event_device hpet_clockevent = { .rating = 50, }; -static void hpet_start_counter(void) +static void hpet_stop_counter(void) { unsigned long cfg = hpet_readl(HPET_CFG); - cfg &= ~HPET_CFG_ENABLE; hpet_writel(cfg, HPET_CFG); hpet_writel(0, HPET_COUNTER); hpet_writel(0, HPET_COUNTER + 4); +} + +static void hpet_start_counter(void) +{ + unsigned long cfg = hpet_readl(HPET_CFG); cfg |= HPET_CFG_ENABLE; hpet_writel(cfg, HPET_CFG); } +static void hpet_restart_counter(void) +{ + hpet_stop_counter(); + hpet_start_counter(); +} + static void hpet_resume_device(void) { force_hpet_resume(); } -static void hpet_restart_counter(void) +static void hpet_resume_counter(void) { hpet_resume_device(); - hpet_start_counter(); + hpet_restart_counter(); } static void hpet_enable_legacy_int(void) @@ -259,29 +309,23 @@ static int hpet_setup_msi_irq(unsigned int irq); static void hpet_set_mode(enum clock_event_mode mode, struct clock_event_device *evt, int timer) { - unsigned long cfg, cmp, now; + unsigned long cfg; uint64_t delta; switch (mode) { case CLOCK_EVT_MODE_PERIODIC: + hpet_stop_counter(); delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult; delta >>= evt->shift; - now = hpet_readl(HPET_COUNTER); - cmp = now + (unsigned long) delta; cfg = hpet_readl(HPET_Tn_CFG(timer)); /* Make sure we use edge triggered interrupts */ cfg &= ~HPET_TN_LEVEL; cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL | HPET_TN_32BIT; hpet_writel(cfg, HPET_Tn_CFG(timer)); - /* - * The first write after writing TN_SETVAL to the - * config register sets the counter value, the second - * write sets the period. - */ - hpet_writel(cmp, HPET_Tn_CMP(timer)); - udelay(1); hpet_writel((unsigned long) delta, HPET_Tn_CMP(timer)); + hpet_start_counter(); + hpet_print_config(); break; case CLOCK_EVT_MODE_ONESHOT: @@ -308,6 +352,7 @@ static void hpet_set_mode(enum clock_event_mode mode, irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); enable_irq(hdev->irq); } + hpet_print_config(); break; } } @@ -526,6 +571,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) num_timers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT); num_timers++; /* Value read out starts from 0 */ + hpet_print_config(); hpet_devs = kzalloc(sizeof(struct hpet_dev) * num_timers, GFP_KERNEL); if (!hpet_devs) @@ -695,7 +741,7 @@ static struct clocksource clocksource_hpet = { .mask = HPET_MASK, .shift = HPET_SHIFT, .flags = CLOCK_SOURCE_IS_CONTINUOUS, - .resume = hpet_restart_counter, + .resume = hpet_resume_counter, #ifdef CONFIG_X86_64 .vread = vread_hpet, #endif @@ -707,7 +753,7 @@ static int hpet_clocksource_register(void) cycle_t t1; /* Start the counter */ - hpet_start_counter(); + hpet_restart_counter(); /* Verify whether hpet counter works */ t1 = read_hpet(); @@ -793,6 +839,7 @@ int __init hpet_enable(void) * information and the number of channels */ id = hpet_readl(HPET_ID); + hpet_print_config(); #ifdef CONFIG_HPET_EMULATE_RTC /* @@ -845,6 +892,7 @@ static __init int hpet_late_init(void) return -ENODEV; hpet_reserve_platform_timers(hpet_readl(HPET_ID)); + hpet_print_config(); for_each_online_cpu(cpu) { hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu); diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index b0f61f0..f2f8540 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -136,7 +136,7 @@ int init_fpu(struct task_struct *tsk) #ifdef CONFIG_X86_32 if (!HAVE_HWFP) { memset(tsk->thread.xstate, 0, xstate_size); - finit(); + finit_task(tsk); set_stopped_child_used_math(tsk); return 0; } diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 10f92fb..3475440 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -3,17 +3,17 @@ * */ #include <linux/clockchips.h> -#include <linux/init.h> #include <linux/interrupt.h> +#include <linux/spinlock.h> #include <linux/jiffies.h> #include <linux/module.h> -#include <linux/spinlock.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/io.h> -#include <asm/smp.h> -#include <asm/delay.h> #include <asm/i8253.h> -#include <asm/io.h> #include <asm/hpet.h> +#include <asm/smp.h> DEFINE_SPINLOCK(i8253_lock); EXPORT_SYMBOL(i8253_lock); @@ -40,7 +40,7 @@ static void init_pit_timer(enum clock_event_mode mode, { spin_lock(&i8253_lock); - switch(mode) { + switch (mode) { case CLOCK_EVT_MODE_PERIODIC: /* binary, mode 2, LSB/MSB, ch 0 */ outb_pit(0x34, PIT_MODE); @@ -95,7 +95,7 @@ static int pit_next_event(unsigned long delta, struct clock_event_device *evt) * registered. This mechanism replaces the previous #ifdef LOCAL_APIC - * !using_apic_timer decisions in do_timer_interrupt_hook() */ -static struct clock_event_device pit_clockevent = { +static struct clock_event_device pit_ce = { .name = "pit", .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, .set_mode = init_pit_timer, @@ -114,15 +114,13 @@ void __init setup_pit_timer(void) * Start pit with the boot cpu mask and make it global after the * IO_APIC has been initialized. */ - pit_clockevent.cpumask = cpumask_of(smp_processor_id()); - pit_clockevent.mult = div_sc(CLOCK_TICK_RATE, NSEC_PER_SEC, - pit_clockevent.shift); - pit_clockevent.max_delta_ns = - clockevent_delta2ns(0x7FFF, &pit_clockevent); - pit_clockevent.min_delta_ns = - clockevent_delta2ns(0xF, &pit_clockevent); - clockevents_register_device(&pit_clockevent); - global_clock_event = &pit_clockevent; + pit_ce.cpumask = cpumask_of(smp_processor_id()); + pit_ce.mult = div_sc(CLOCK_TICK_RATE, NSEC_PER_SEC, pit_ce.shift); + pit_ce.max_delta_ns = clockevent_delta2ns(0x7FFF, &pit_ce); + pit_ce.min_delta_ns = clockevent_delta2ns(0xF, &pit_ce); + + clockevents_register_device(&pit_ce); + global_clock_event = &pit_ce; } #ifndef CONFIG_X86_64 @@ -133,11 +131,11 @@ void __init setup_pit_timer(void) */ static cycle_t pit_read(void) { + static int old_count; + static u32 old_jifs; unsigned long flags; int count; u32 jifs; - static int old_count; - static u32 old_jifs; spin_lock_irqsave(&i8253_lock, flags); /* @@ -179,9 +177,9 @@ static cycle_t pit_read(void) * Previous attempts to handle these cases intelligently were * buggy, so we just do the simple thing now. */ - if (count > old_count && jifs == old_jifs) { + if (count > old_count && jifs == old_jifs) count = old_count; - } + old_count = count; old_jifs = jifs; @@ -192,13 +190,13 @@ static cycle_t pit_read(void) return (cycle_t)(jifs * LATCH) + count; } -static struct clocksource clocksource_pit = { - .name = "pit", - .rating = 110, - .read = pit_read, - .mask = CLOCKSOURCE_MASK(32), - .mult = 0, - .shift = 20, +static struct clocksource pit_cs = { + .name = "pit", + .rating = 110, + .read = pit_read, + .mask = CLOCKSOURCE_MASK(32), + .mult = 0, + .shift = 20, }; static void pit_disable_clocksource(void) @@ -206,9 +204,9 @@ static void pit_disable_clocksource(void) /* * Use mult to check whether it is registered or not */ - if (clocksource_pit.mult) { - clocksource_unregister(&clocksource_pit); - clocksource_pit.mult = 0; + if (pit_cs.mult) { + clocksource_unregister(&pit_cs); + pit_cs.mult = 0; } } @@ -222,13 +220,13 @@ static int __init init_pit_clocksource(void) * - when local APIC timer is active (PIT is switched off) */ if (num_possible_cpus() > 1 || is_hpet_enabled() || - pit_clockevent.mode != CLOCK_EVT_MODE_PERIODIC) + pit_ce.mode != CLOCK_EVT_MODE_PERIODIC) return 0; - clocksource_pit.mult = clocksource_hz2mult(CLOCK_TICK_RATE, - clocksource_pit.shift); - return clocksource_register(&clocksource_pit); + pit_cs.mult = clocksource_hz2mult(CLOCK_TICK_RATE, pit_cs.shift); + + return clocksource_register(&pit_cs); } arch_initcall(init_pit_clocksource); -#endif +#endif /* !CONFIG_X86_64 */ diff --git a/arch/x86/kernel/io_delay.c b/arch/x86/kernel/io_delay.c index 720d260..a979b5b 100644 --- a/arch/x86/kernel/io_delay.c +++ b/arch/x86/kernel/io_delay.c @@ -7,10 +7,10 @@ */ #include <linux/kernel.h> #include <linux/module.h> -#include <linux/init.h> #include <linux/delay.h> +#include <linux/init.h> #include <linux/dmi.h> -#include <asm/io.h> +#include <linux/io.h> int io_delay_type __read_mostly = CONFIG_DEFAULT_IO_DELAY_TYPE; @@ -47,8 +47,7 @@ EXPORT_SYMBOL(native_io_delay); static int __init dmi_io_delay_0xed_port(const struct dmi_system_id *id) { if (io_delay_type == CONFIG_IO_DELAY_TYPE_0X80) { - printk(KERN_NOTICE "%s: using 0xed I/O delay port\n", - id->ident); + pr_notice("%s: using 0xed I/O delay port\n", id->ident); io_delay_type = CONFIG_IO_DELAY_TYPE_0XED; } @@ -64,40 +63,40 @@ static struct dmi_system_id __initdata io_delay_0xed_port_dmi_table[] = { .callback = dmi_io_delay_0xed_port, .ident = "Compaq Presario V6000", .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"), - DMI_MATCH(DMI_BOARD_NAME, "30B7") + DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"), + DMI_MATCH(DMI_BOARD_NAME, "30B7") } }, { .callback = dmi_io_delay_0xed_port, .ident = "HP Pavilion dv9000z", .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"), - DMI_MATCH(DMI_BOARD_NAME, "30B9") + DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"), + DMI_MATCH(DMI_BOARD_NAME, "30B9") } }, { .callback = dmi_io_delay_0xed_port, .ident = "HP Pavilion dv6000", .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"), - DMI_MATCH(DMI_BOARD_NAME, "30B8") + DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"), + DMI_MATCH(DMI_BOARD_NAME, "30B8") } }, { .callback = dmi_io_delay_0xed_port, .ident = "HP Pavilion tx1000", .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"), - DMI_MATCH(DMI_BOARD_NAME, "30BF") + DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"), + DMI_MATCH(DMI_BOARD_NAME, "30BF") } }, { .callback = dmi_io_delay_0xed_port, .ident = "Presario F700", .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"), - DMI_MATCH(DMI_BOARD_NAME, "30D3") + DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"), + DMI_MATCH(DMI_BOARD_NAME, "30D3") } }, { } diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index e41980a..99c4d30 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -85,19 +85,8 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) t->io_bitmap_max = bytes; -#ifdef CONFIG_X86_32 - /* - * Sets the lazy trigger so that the next I/O operation will - * reload the correct bitmap. - * Reset the owner so that a process switch will not set - * tss->io_bitmap_base to IO_BITMAP_OFFSET. - */ - tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY; - tss->io_bitmap_owner = NULL; -#else /* Update the TSS: */ memcpy(tss->io_bitmap, t->io_bitmap_ptr, bytes_updated); -#endif put_cpu(); diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 7c95c89..9c27543 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -15,6 +15,9 @@ atomic_t irq_err_count; +/* Function pointer for generic interrupt vector handling */ +void (*generic_interrupt_extension)(void) = NULL; + /* * 'what should we do if we get a hw irq event on an illegal vector'. * each architecture has to answer this themselves. @@ -42,59 +45,64 @@ void ack_bad_irq(unsigned int irq) /* * /proc/interrupts printing: */ -static int show_other_interrupts(struct seq_file *p) +static int show_other_interrupts(struct seq_file *p, int prec) { int j; - seq_printf(p, "NMI: "); + seq_printf(p, "%*s: ", prec, "NMI"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->__nmi_count); seq_printf(p, " Non-maskable interrupts\n"); #ifdef CONFIG_X86_LOCAL_APIC - seq_printf(p, "LOC: "); + seq_printf(p, "%*s: ", prec, "LOC"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->apic_timer_irqs); seq_printf(p, " Local timer interrupts\n"); + + seq_printf(p, "%*s: ", prec, "SPU"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count); + seq_printf(p, " Spurious interrupts\n"); seq_printf(p, "CNT: "); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs); seq_printf(p, " Performance counter interrupts\n"); #endif + if (generic_interrupt_extension) { + seq_printf(p, "PLT: "); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->generic_irqs); + seq_printf(p, " Platform interrupts\n"); + } #ifdef CONFIG_SMP - seq_printf(p, "RES: "); + seq_printf(p, "%*s: ", prec, "RES"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_resched_count); seq_printf(p, " Rescheduling interrupts\n"); - seq_printf(p, "CAL: "); + seq_printf(p, "%*s: ", prec, "CAL"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_call_count); seq_printf(p, " Function call interrupts\n"); - seq_printf(p, "TLB: "); + seq_printf(p, "%*s: ", prec, "TLB"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count); seq_printf(p, " TLB shootdowns\n"); #endif #ifdef CONFIG_X86_MCE - seq_printf(p, "TRM: "); + seq_printf(p, "%*s: ", prec, "TRM"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_thermal_count); seq_printf(p, " Thermal event interrupts\n"); # ifdef CONFIG_X86_64 - seq_printf(p, "THR: "); + seq_printf(p, "%*s: ", prec, "THR"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count); seq_printf(p, " Threshold APIC interrupts\n"); # endif #endif -#ifdef CONFIG_X86_LOCAL_APIC - seq_printf(p, "SPU: "); - for_each_online_cpu(j) - seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count); - seq_printf(p, " Spurious interrupts\n"); -#endif - seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count)); + seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count)); #if defined(CONFIG_X86_IO_APIC) - seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count)); + seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count)); #endif return 0; } @@ -102,19 +110,22 @@ static int show_other_interrupts(struct seq_file *p) int show_interrupts(struct seq_file *p, void *v) { unsigned long flags, any_count = 0; - int i = *(loff_t *) v, j; + int i = *(loff_t *) v, j, prec; struct irqaction *action; struct irq_desc *desc; if (i > nr_irqs) return 0; + for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec) + j *= 10; + if (i == nr_irqs) - return show_other_interrupts(p); + return show_other_interrupts(p, prec); /* print header */ if (i == 0) { - seq_printf(p, " "); + seq_printf(p, "%*s", prec + 8, ""); for_each_online_cpu(j) seq_printf(p, "CPU%-8d", j); seq_putc(p, '\n'); @@ -125,23 +136,15 @@ int show_interrupts(struct seq_file *p, void *v) return 0; spin_lock_irqsave(&desc->lock, flags); -#ifndef CONFIG_SMP - any_count = kstat_irqs(i); -#else for_each_online_cpu(j) any_count |= kstat_irqs_cpu(i, j); -#endif action = desc->action; if (!action && !any_count) goto out; - seq_printf(p, "%3d: ", i); -#ifndef CONFIG_SMP - seq_printf(p, "%10u ", kstat_irqs(i)); -#else + seq_printf(p, "%*d: ", prec, i); for_each_online_cpu(j) seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); -#endif seq_printf(p, " %8s", desc->chip->name); seq_printf(p, "-%-8s", desc->name); @@ -166,8 +169,11 @@ u64 arch_irq_stat_cpu(unsigned int cpu) #ifdef CONFIG_X86_LOCAL_APIC sum += irq_stats(cpu)->apic_timer_irqs; + sum += irq_stats(cpu)->irq_spurious_count; sum += irq_stats(cpu)->apic_perf_irqs; #endif + if (generic_interrupt_extension) + sum += irq_stats(cpu)->generic_irqs; #ifdef CONFIG_SMP sum += irq_stats(cpu)->irq_resched_count; sum += irq_stats(cpu)->irq_call_count; @@ -179,9 +185,6 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += irq_stats(cpu)->irq_threshold_count; #endif #endif -#ifdef CONFIG_X86_LOCAL_APIC - sum += irq_stats(cpu)->irq_spurious_count; -#endif return sum; } @@ -231,4 +234,27 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs) return 1; } +/* + * Handler for GENERIC_INTERRUPT_VECTOR. + */ +void smp_generic_interrupt(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + + ack_APIC_irq(); + + exit_idle(); + + irq_enter(); + + inc_irq_stat(generic_irqs); + + if (generic_interrupt_extension) + generic_interrupt_extension(); + + irq_exit(); + + set_irq_regs(old_regs); +} + EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq); diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 9dc6b2b..3b09634 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -16,6 +16,7 @@ #include <linux/cpu.h> #include <linux/delay.h> #include <linux/uaccess.h> +#include <linux/percpu.h> #include <asm/apic.h> @@ -55,13 +56,13 @@ static inline void print_stack_overflow(void) { } union irq_ctx { struct thread_info tinfo; u32 stack[THREAD_SIZE/sizeof(u32)]; -}; +} __attribute__((aligned(PAGE_SIZE))); -static union irq_ctx *hardirq_ctx[NR_CPUS] __read_mostly; -static union irq_ctx *softirq_ctx[NR_CPUS] __read_mostly; +static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx); +static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx); -static char softirq_stack[NR_CPUS * THREAD_SIZE] __page_aligned_bss; -static char hardirq_stack[NR_CPUS * THREAD_SIZE] __page_aligned_bss; +static DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, hardirq_stack); +static DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, softirq_stack); static void call_on_stack(void *func, void *stack) { @@ -81,7 +82,7 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) u32 *isp, arg1, arg2; curctx = (union irq_ctx *) current_thread_info(); - irqctx = hardirq_ctx[smp_processor_id()]; + irqctx = __get_cpu_var(hardirq_ctx); /* * this is where we switch to the IRQ stack. However, if we are @@ -125,34 +126,34 @@ void __cpuinit irq_ctx_init(int cpu) { union irq_ctx *irqctx; - if (hardirq_ctx[cpu]) + if (per_cpu(hardirq_ctx, cpu)) return; - irqctx = (union irq_ctx*) &hardirq_stack[cpu*THREAD_SIZE]; + irqctx = &per_cpu(hardirq_stack, cpu); irqctx->tinfo.task = NULL; irqctx->tinfo.exec_domain = NULL; irqctx->tinfo.cpu = cpu; irqctx->tinfo.preempt_count = HARDIRQ_OFFSET; irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); - hardirq_ctx[cpu] = irqctx; + per_cpu(hardirq_ctx, cpu) = irqctx; - irqctx = (union irq_ctx *) &softirq_stack[cpu*THREAD_SIZE]; + irqctx = &per_cpu(softirq_stack, cpu); irqctx->tinfo.task = NULL; irqctx->tinfo.exec_domain = NULL; irqctx->tinfo.cpu = cpu; irqctx->tinfo.preempt_count = 0; irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); - softirq_ctx[cpu] = irqctx; + per_cpu(softirq_ctx, cpu) = irqctx; printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n", - cpu, hardirq_ctx[cpu], softirq_ctx[cpu]); + cpu, per_cpu(hardirq_ctx, cpu), per_cpu(softirq_ctx, cpu)); } void irq_ctx_exit(int cpu) { - hardirq_ctx[cpu] = NULL; + per_cpu(hardirq_ctx, cpu) = NULL; } asmlinkage void do_softirq(void) @@ -169,7 +170,7 @@ asmlinkage void do_softirq(void) if (local_softirq_pending()) { curctx = current_thread_info(); - irqctx = softirq_ctx[smp_processor_id()]; + irqctx = __get_cpu_var(softirq_ctx); irqctx->tinfo.task = curctx->task; irqctx->tinfo.previous_esp = current_stack_pointer; diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c index f3e11cb2..925d87c 100644 --- a/arch/x86/kernel/irqinit_32.c +++ b/arch/x86/kernel/irqinit_32.c @@ -50,7 +50,6 @@ static irqreturn_t math_error_irq(int cpl, void *dev_id) */ static struct irqaction fpu_irq = { .handler = math_error_irq, - .mask = CPU_MASK_NONE, .name = "fpu", }; @@ -83,7 +82,6 @@ void __init init_ISA_irqs(void) */ static struct irqaction irq2 = { .handler = no_action, - .mask = CPU_MASK_NONE, .name = "cascade", }; @@ -160,6 +158,9 @@ static void __init apic_intr_init(void) /* self generated IPI for local APIC timer */ alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); + /* generic IPI for platform specific use */ + alloc_intr_gate(GENERIC_INTERRUPT_VECTOR, generic_interrupt); + /* IPI vectors for APIC spurious and error interrupts */ alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt); diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c index 16e1fc6..665e2ab 100644 --- a/arch/x86/kernel/irqinit_64.c +++ b/arch/x86/kernel/irqinit_64.c @@ -45,7 +45,6 @@ static struct irqaction irq2 = { .handler = no_action, - .mask = CPU_MASK_NONE, .name = "cascade", }; DEFINE_PER_CPU(vector_irq_t, vector_irq) = { @@ -147,6 +146,9 @@ static void __init apic_intr_init(void) /* self generated IPI for local APIC timer */ alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); + /* generic IPI for platform specific use */ + alloc_intr_gate(GENERIC_INTERRUPT_VECTOR, generic_interrupt); + /* IPI vectors for APIC spurious and error interrupts */ alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt); diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index ff7d3b0..e444357 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -8,11 +8,11 @@ */ #include <linux/debugfs.h> #include <linux/uaccess.h> -#include <linux/stat.h> +#include <linux/module.h> #include <linux/init.h> +#include <linux/stat.h> #include <linux/io.h> #include <linux/mm.h> -#include <linux/module.h> #include <asm/setup.h> @@ -26,9 +26,8 @@ struct setup_data_node { u32 len; }; -static ssize_t -setup_data_read(struct file *file, char __user *user_buf, size_t count, - loff_t *ppos) +static ssize_t setup_data_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) { struct setup_data_node *node = file->private_data; unsigned long remain; @@ -39,20 +38,21 @@ setup_data_read(struct file *file, char __user *user_buf, size_t count, if (pos < 0) return -EINVAL; + if (pos >= node->len) return 0; if (count > node->len - pos) count = node->len - pos; + pa = node->paddr + sizeof(struct setup_data) + pos; pg = pfn_to_page((pa + count - 1) >> PAGE_SHIFT); if (PageHighMem(pg)) { p = ioremap_cache(pa, count); if (!p) return -ENXIO; - } else { + } else p = __va(pa); - } remain = copy_to_user(user_buf, p, count); @@ -70,12 +70,13 @@ setup_data_read(struct file *file, char __user *user_buf, size_t count, static int setup_data_open(struct inode *inode, struct file *file) { file->private_data = inode->i_private; + return 0; } static const struct file_operations fops_setup_data = { - .read = setup_data_read, - .open = setup_data_open, + .read = setup_data_read, + .open = setup_data_open, }; static int __init @@ -84,57 +85,50 @@ create_setup_data_node(struct dentry *parent, int no, { struct dentry *d, *type, *data; char buf[16]; - int error; sprintf(buf, "%d", no); d = debugfs_create_dir(buf, parent); - if (!d) { - error = -ENOMEM; - goto err_return; - } + if (!d) + return -ENOMEM; + type = debugfs_create_x32("type", S_IRUGO, d, &node->type); - if (!type) { - error = -ENOMEM; + if (!type) goto err_dir; - } + data = debugfs_create_file("data", S_IRUGO, d, node, &fops_setup_data); - if (!data) { - error = -ENOMEM; + if (!data) goto err_type; - } + return 0; err_type: debugfs_remove(type); err_dir: debugfs_remove(d); -err_return: - return error; + return -ENOMEM; } static int __init create_setup_data_nodes(struct dentry *parent) { struct setup_data_node *node; struct setup_data *data; - int error, no = 0; + int error = -ENOMEM; struct dentry *d; struct page *pg; u64 pa_data; + int no = 0; d = debugfs_create_dir("setup_data", parent); - if (!d) { - error = -ENOMEM; - goto err_return; - } + if (!d) + return -ENOMEM; pa_data = boot_params.hdr.setup_data; while (pa_data) { node = kmalloc(sizeof(*node), GFP_KERNEL); - if (!node) { - error = -ENOMEM; + if (!node) goto err_dir; - } + pg = pfn_to_page((pa_data+sizeof(*data)-1) >> PAGE_SHIFT); if (PageHighMem(pg)) { data = ioremap_cache(pa_data, sizeof(*data)); @@ -143,9 +137,8 @@ static int __init create_setup_data_nodes(struct dentry *parent) error = -ENXIO; goto err_dir; } - } else { + } else data = __va(pa_data); - } node->paddr = pa_data; node->type = data->type; @@ -159,11 +152,11 @@ static int __init create_setup_data_nodes(struct dentry *parent) goto err_dir; no++; } + return 0; err_dir: debugfs_remove(d); -err_return: return error; } @@ -175,28 +168,26 @@ static struct debugfs_blob_wrapper boot_params_blob = { static int __init boot_params_kdebugfs_init(void) { struct dentry *dbp, *version, *data; - int error; + int error = -ENOMEM; dbp = debugfs_create_dir("boot_params", NULL); - if (!dbp) { - error = -ENOMEM; - goto err_return; - } + if (!dbp) + return -ENOMEM; + version = debugfs_create_x16("version", S_IRUGO, dbp, &boot_params.hdr.version); - if (!version) { - error = -ENOMEM; + if (!version) goto err_dir; - } + data = debugfs_create_blob("data", S_IRUGO, dbp, &boot_params_blob); - if (!data) { - error = -ENOMEM; + if (!data) goto err_version; - } + error = create_setup_data_nodes(dbp); if (error) goto err_data; + return 0; err_data: @@ -205,10 +196,9 @@ err_version: debugfs_remove(version); err_dir: debugfs_remove(dbp); -err_return: return error; } -#endif +#endif /* CONFIG_DEBUG_BOOT_PARAMS */ static int __init arch_kdebugfs_init(void) { diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index e948b28..7b5169d 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -193,6 +193,9 @@ static int __kprobes can_boost(kprobe_opcode_t *opcodes) kprobe_opcode_t opcode; kprobe_opcode_t *orig_opcodes = opcodes; + if (search_exception_tables((unsigned long)opcodes)) + return 0; /* Page fault may occur on this address. */ + retry: if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1) return 0; @@ -635,13 +638,13 @@ static void __used __kprobes kretprobe_trampoline_holder(void) #else " pushf\n" /* - * Skip cs, ip, orig_ax. + * Skip cs, ip, orig_ax and gs. * trampoline_handler() will plug in these values */ - " subl $12, %esp\n" + " subl $16, %esp\n" " pushl %fs\n" - " pushl %ds\n" " pushl %es\n" + " pushl %ds\n" " pushl %eax\n" " pushl %ebp\n" " pushl %edi\n" @@ -652,10 +655,10 @@ static void __used __kprobes kretprobe_trampoline_holder(void) " movl %esp, %eax\n" " call trampoline_handler\n" /* Move flags to cs */ - " movl 52(%esp), %edx\n" - " movl %edx, 48(%esp)\n" + " movl 56(%esp), %edx\n" + " movl %edx, 52(%esp)\n" /* Replace saved flags with true return address. */ - " movl %eax, 52(%esp)\n" + " movl %eax, 56(%esp)\n" " popl %ebx\n" " popl %ecx\n" " popl %edx\n" @@ -663,8 +666,8 @@ static void __used __kprobes kretprobe_trampoline_holder(void) " popl %edi\n" " popl %ebp\n" " popl %eax\n" - /* Skip ip, orig_ax, es, ds, fs */ - " addl $20, %esp\n" + /* Skip ds, es, fs, gs, orig_ax and ip */ + " addl $24, %esp\n" " popf\n" #endif " ret\n"); @@ -688,6 +691,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) regs->cs = __KERNEL_CS; #else regs->cs = __KERNEL_CS | get_kernel_rpl(); + regs->gs = 0; #endif regs->ip = trampoline_address; regs->orig_ax = ~0UL; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 478bca9..33019dd 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -138,12 +138,6 @@ static void kvm_set_pte_atomic(pte_t *ptep, pte_t pte) kvm_mmu_write(ptep, pte_val(pte)); } -static void kvm_set_pte_present(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) -{ - kvm_mmu_write(ptep, pte_val(pte)); -} - static void kvm_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -220,7 +214,6 @@ static void paravirt_ops_setup(void) #if PAGETABLE_LEVELS >= 3 #ifdef CONFIG_X86_PAE pv_mmu_ops.set_pte_atomic = kvm_set_pte_atomic; - pv_mmu_ops.set_pte_present = kvm_set_pte_present; pv_mmu_ops.pte_clear = kvm_pte_clear; pv_mmu_ops.pmd_clear = kvm_pmd_clear; #endif diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index f5fc8c7..e7368c1 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -14,12 +14,12 @@ #include <linux/ftrace.h> #include <linux/suspend.h> #include <linux/gfp.h> +#include <linux/io.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> -#include <asm/io.h> #include <asm/apic.h> #include <asm/cpufeature.h> #include <asm/desc.h> @@ -63,7 +63,7 @@ static void load_segments(void) "\tmovl %%eax,%%fs\n" "\tmovl %%eax,%%gs\n" "\tmovl %%eax,%%ss\n" - ::: "eax", "memory"); + : : : "eax", "memory"); #undef STR #undef __STR } @@ -205,7 +205,8 @@ void machine_kexec(struct kimage *image) if (image->preserve_context) { #ifdef CONFIG_X86_IO_APIC - /* We need to put APICs in legacy mode so that we can + /* + * We need to put APICs in legacy mode so that we can * get timer interrupts in second kernel. kexec/kdump * paths already have calls to disable_IO_APIC() in * one form or other. kexec jump path also need @@ -227,7 +228,8 @@ void machine_kexec(struct kimage *image) page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) << PAGE_SHIFT); - /* The segment registers are funny things, they have both a + /* + * The segment registers are funny things, they have both a * visible and an invisible part. Whenever the visible part is * set to a specific selector, the invisible part is loaded * with from a table in memory. At no other time is the @@ -237,11 +239,12 @@ void machine_kexec(struct kimage *image) * segments, before I zap the gdt with an invalid value. */ load_segments(); - /* The gdt & idt are now invalid. + /* + * The gdt & idt are now invalid. * If you want to load them you must set up your own idt & gdt. */ - set_gdt(phys_to_virt(0),0); - set_idt(phys_to_virt(0),0); + set_gdt(phys_to_virt(0), 0); + set_idt(phys_to_virt(0), 0); /* now call it */ image->start = relocate_kernel_ptr((unsigned long)image->head, diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 6993d51..89cea4d 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -12,11 +12,47 @@ #include <linux/reboot.h> #include <linux/numa.h> #include <linux/ftrace.h> +#include <linux/io.h> +#include <linux/suspend.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> -#include <asm/io.h> + +static int init_one_level2_page(struct kimage *image, pgd_t *pgd, + unsigned long addr) +{ + pud_t *pud; + pmd_t *pmd; + struct page *page; + int result = -ENOMEM; + + addr &= PMD_MASK; + pgd += pgd_index(addr); + if (!pgd_present(*pgd)) { + page = kimage_alloc_control_pages(image, 0); + if (!page) + goto out; + pud = (pud_t *)page_address(page); + memset(pud, 0, PAGE_SIZE); + set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); + } + pud = pud_offset(pgd, addr); + if (!pud_present(*pud)) { + page = kimage_alloc_control_pages(image, 0); + if (!page) + goto out; + pmd = (pmd_t *)page_address(page); + memset(pmd, 0, PAGE_SIZE); + set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); + } + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) + set_pmd(pmd, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC)); + result = 0; +out: + return result; +} static void init_level2_page(pmd_t *level2p, unsigned long addr) { @@ -83,9 +119,8 @@ static int init_level4_page(struct kimage *image, pgd_t *level4p, } level3p = (pud_t *)page_address(page); result = init_level3_page(image, level3p, addr, last_addr); - if (result) { + if (result) goto out; - } set_pgd(level4p++, __pgd(__pa(level3p) | _KERNPG_TABLE)); addr += PGDIR_SIZE; } @@ -156,6 +191,13 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) result = init_level4_page(image, level4p, 0, max_pfn << PAGE_SHIFT); if (result) return result; + /* + * image->start may be outside 0 ~ max_pfn, for example when + * jump back to original kernel from kexeced kernel + */ + result = init_one_level2_page(image, level4p, image->start); + if (result) + return result; return init_transition_pgtable(image, level4p); } @@ -229,20 +271,45 @@ void machine_kexec(struct kimage *image) { unsigned long page_list[PAGES_NR]; void *control_page; + int save_ftrace_enabled; - tracer_disable(); +#ifdef CONFIG_KEXEC_JUMP + if (kexec_image->preserve_context) + save_processor_state(); +#endif + + save_ftrace_enabled = __ftrace_enabled_save(); /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); + if (image->preserve_context) { +#ifdef CONFIG_X86_IO_APIC + /* + * We need to put APICs in legacy mode so that we can + * get timer interrupts in second kernel. kexec/kdump + * paths already have calls to disable_IO_APIC() in + * one form or other. kexec jump path also need + * one. + */ + disable_IO_APIC(); +#endif + } + control_page = page_address(image->control_code_page) + PAGE_SIZE; - memcpy(control_page, relocate_kernel, PAGE_SIZE); + memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE); page_list[PA_CONTROL_PAGE] = virt_to_phys(control_page); + page_list[VA_CONTROL_PAGE] = (unsigned long)control_page; page_list[PA_TABLE_PAGE] = (unsigned long)__pa(page_address(image->control_code_page)); - /* The segment registers are funny things, they have both a + if (image->type == KEXEC_TYPE_DEFAULT) + page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) + << PAGE_SHIFT); + + /* + * The segment registers are funny things, they have both a * visible and an invisible part. Whenever the visible part is * set to a specific selector, the invisible part is loaded * with from a table in memory. At no other time is the @@ -252,15 +319,25 @@ void machine_kexec(struct kimage *image) * segments, before I zap the gdt with an invalid value. */ load_segments(); - /* The gdt & idt are now invalid. + /* + * The gdt & idt are now invalid. * If you want to load them you must set up your own idt & gdt. */ - set_gdt(phys_to_virt(0),0); - set_idt(phys_to_virt(0),0); + set_gdt(phys_to_virt(0), 0); + set_idt(phys_to_virt(0), 0); /* now call it */ - relocate_kernel((unsigned long)image->head, (unsigned long)page_list, - image->start); + image->start = relocate_kernel((unsigned long)image->head, + (unsigned long)page_list, + image->start, + image->preserve_context); + +#ifdef CONFIG_KEXEC_JUMP + if (kexec_image->preserve_context) + restore_processor_state(); +#endif + + __ftrace_enabled_restore(save_ftrace_enabled); } void arch_crash_save_vmcoreinfo(void) diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c index 8815f3c..846510b 100644 --- a/arch/x86/kernel/mfgpt_32.c +++ b/arch/x86/kernel/mfgpt_32.c @@ -348,7 +348,6 @@ static irqreturn_t mfgpt_tick(int irq, void *dev_id) static struct irqaction mfgptirq = { .handler = mfgpt_tick, .flags = IRQF_DISABLED | IRQF_NOBALANCING, - .mask = CPU_MASK_NONE, .name = "mfgpt-timer" }; diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index c25fdb3..453b579 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -12,31 +12,30 @@ * * Licensed under the terms of the GNU General Public * License version 2. See file COPYING for details. -*/ - + */ +#include <linux/platform_device.h> #include <linux/capability.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/sched.h> -#include <linux/cpumask.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/vmalloc.h> #include <linux/miscdevice.h> +#include <linux/firmware.h> #include <linux/spinlock.h> -#include <linux/mm.h> -#include <linux/fs.h> +#include <linux/cpumask.h> +#include <linux/pci_ids.h> +#include <linux/uaccess.h> +#include <linux/vmalloc.h> +#include <linux/kernel.h> +#include <linux/module.h> #include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/slab.h> #include <linux/cpu.h> -#include <linux/firmware.h> -#include <linux/platform_device.h> #include <linux/pci.h> -#include <linux/pci_ids.h> -#include <linux/uaccess.h> +#include <linux/fs.h> +#include <linux/mm.h> -#include <asm/msr.h> -#include <asm/processor.h> #include <asm/microcode.h> +#include <asm/processor.h> +#include <asm/msr.h> MODULE_DESCRIPTION("AMD Microcode Update Driver"); MODULE_AUTHOR("Peter Oruba"); @@ -72,8 +71,8 @@ struct microcode_header_amd { } __attribute__((packed)); struct microcode_amd { - struct microcode_header_amd hdr; - unsigned int mpb[0]; + struct microcode_header_amd hdr; + unsigned int mpb[0]; }; #define UCODE_MAX_SIZE 2048 @@ -184,8 +183,8 @@ static int get_ucode_data(void *to, const u8 *from, size_t n) return 0; } -static void *get_next_ucode(const u8 *buf, unsigned int size, - unsigned int *mc_size) +static void * +get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size) { unsigned int total_size; u8 section_hdr[UCODE_CONTAINER_SECTION_HDR]; @@ -223,7 +222,6 @@ static void *get_next_ucode(const u8 *buf, unsigned int size, return mc; } - static int install_equiv_cpu_table(const u8 *buf) { u8 *container_hdr[UCODE_CONTAINER_HEADER_SIZE]; @@ -372,4 +370,3 @@ struct microcode_ops * __init init_amd_microcode(void) { return µcode_amd_ops; } - diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index c9b721b..a0f3851 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -70,67 +70,78 @@ * Fix sigmatch() macro to handle old CPUs with pf == 0. * Thanks to Stuart Swales for pointing out this bug. */ +#include <linux/platform_device.h> #include <linux/capability.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/sched.h> +#include <linux/miscdevice.h> +#include <linux/firmware.h> #include <linux/smp_lock.h> +#include <linux/spinlock.h> #include <linux/cpumask.h> -#include <linux/module.h> -#include <linux/slab.h> +#include <linux/uaccess.h> #include <linux/vmalloc.h> -#include <linux/miscdevice.h> -#include <linux/spinlock.h> -#include <linux/mm.h> -#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/module.h> #include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/slab.h> #include <linux/cpu.h> -#include <linux/firmware.h> -#include <linux/platform_device.h> +#include <linux/fs.h> +#include <linux/mm.h> -#include <asm/msr.h> -#include <asm/uaccess.h> -#include <asm/processor.h> #include <asm/microcode.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"); -#define MICROCODE_VERSION "2.00" +#define MICROCODE_VERSION "2.00" -static struct microcode_ops *microcode_ops; +static struct microcode_ops *microcode_ops; /* no concurrent ->write()s are allowed on /dev/cpu/microcode */ static DEFINE_MUTEX(microcode_mutex); -struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; +struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; EXPORT_SYMBOL_GPL(ucode_cpu_info); #ifdef CONFIG_MICROCODE_OLD_INTERFACE +struct update_for_cpu { + const void __user *buf; + size_t size; +}; + +static long update_for_cpu(void *_ufc) +{ + struct update_for_cpu *ufc = _ufc; + int error; + + error = microcode_ops->request_microcode_user(smp_processor_id(), + ufc->buf, ufc->size); + if (error < 0) + return error; + if (!error) + microcode_ops->apply_microcode(smp_processor_id()); + return error; +} + static int do_microcode_update(const void __user *buf, size_t size) { - cpumask_t old; int error = 0; int cpu; - - old = current->cpus_allowed; + struct update_for_cpu ufc = { .buf = buf, .size = size }; for_each_online_cpu(cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; if (!uci->valid) continue; - - set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); - error = microcode_ops->request_microcode_user(cpu, buf, size); + error = work_on_cpu(cpu, update_for_cpu, &ufc); if (error < 0) - goto out; - if (!error) - microcode_ops->apply_microcode(cpu); + break; } -out: - set_cpus_allowed_ptr(current, &old); return error; } @@ -198,18 +209,33 @@ static void microcode_dev_exit(void) MODULE_ALIAS_MISCDEV(MICROCODE_MINOR); #else -#define microcode_dev_init() 0 -#define microcode_dev_exit() do { } while (0) +#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 struct platform_device *microcode_pdev; + +static long reload_for_cpu(void *unused) +{ + struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id(); + int err = 0; + + mutex_lock(µcode_mutex); + if (uci->valid) { + err = microcode_ops->request_microcode_fw(smp_processor_id(), + µcode_pdev->dev); + if (!err) + microcode_ops->apply_microcode(smp_processor_id()); + } + mutex_unlock(µcode_mutex); + return err; +} static ssize_t reload_store(struct sys_device *dev, struct sysdev_attribute *attr, const char *buf, size_t sz) { - struct ucode_cpu_info *uci = ucode_cpu_info + dev->id; char *end; unsigned long val = simple_strtoul(buf, &end, 0); int err = 0; @@ -218,21 +244,9 @@ static ssize_t reload_store(struct sys_device *dev, if (end == buf) return -EINVAL; if (val == 1) { - cpumask_t old = current->cpus_allowed; - get_online_cpus(); - if (cpu_online(cpu)) { - set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); - mutex_lock(µcode_mutex); - if (uci->valid) { - err = microcode_ops->request_microcode_fw(cpu, - µcode_pdev->dev); - if (!err) - microcode_ops->apply_microcode(cpu); - } - mutex_unlock(µcode_mutex); - set_cpus_allowed_ptr(current, &old); - } + if (cpu_online(cpu)) + err = work_on_cpu(cpu, reload_for_cpu, NULL); put_online_cpus(); } if (err) @@ -268,8 +282,8 @@ static struct attribute *mc_default_attrs[] = { }; static struct attribute_group mc_attr_group = { - .attrs = mc_default_attrs, - .name = "microcode", + .attrs = mc_default_attrs, + .name = "microcode", }; static void __microcode_fini_cpu(int cpu) @@ -328,9 +342,9 @@ static int microcode_resume_cpu(int cpu) return 0; } -static void microcode_update_cpu(int cpu) +static long microcode_update_cpu(void *unused) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id(); int err = 0; /* @@ -338,30 +352,27 @@ static void microcode_update_cpu(int cpu) * otherwise just request a firmware: */ if (uci->valid) { - err = microcode_resume_cpu(cpu); - } else { - collect_cpu_info(cpu); + err = microcode_resume_cpu(smp_processor_id()); + } else { + collect_cpu_info(smp_processor_id()); if (uci->valid && system_state == SYSTEM_RUNNING) - err = microcode_ops->request_microcode_fw(cpu, + err = microcode_ops->request_microcode_fw( + smp_processor_id(), µcode_pdev->dev); } if (!err) - microcode_ops->apply_microcode(cpu); + microcode_ops->apply_microcode(smp_processor_id()); + return err; } -static void microcode_init_cpu(int cpu) +static int microcode_init_cpu(int cpu) { - cpumask_t old = current->cpus_allowed; - - set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); - /* We should bind the task to the CPU */ - BUG_ON(raw_smp_processor_id() != cpu); - + int err; mutex_lock(µcode_mutex); - microcode_update_cpu(cpu); + err = work_on_cpu(cpu, microcode_update_cpu, NULL); mutex_unlock(µcode_mutex); - set_cpus_allowed_ptr(current, &old); + return err; } static int mc_sysdev_add(struct sys_device *sys_dev) @@ -379,8 +390,11 @@ static int mc_sysdev_add(struct sys_device *sys_dev) if (err) return err; - microcode_init_cpu(cpu); - return 0; + err = microcode_init_cpu(cpu); + if (err) + sysfs_remove_group(&sys_dev->kobj, &mc_attr_group); + + return err; } static int mc_sysdev_remove(struct sys_device *sys_dev) @@ -404,14 +418,14 @@ static int mc_sysdev_resume(struct sys_device *dev) return 0; /* only CPU 0 will apply ucode here */ - microcode_update_cpu(0); + microcode_update_cpu(NULL); return 0; } static struct sysdev_driver mc_sysdev_driver = { - .add = mc_sysdev_add, - .remove = mc_sysdev_remove, - .resume = mc_sysdev_resume, + .add = mc_sysdev_add, + .remove = mc_sysdev_remove, + .resume = mc_sysdev_resume, }; static __cpuinit int @@ -424,7 +438,9 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) switch (action) { case CPU_ONLINE: case CPU_ONLINE_FROZEN: - microcode_init_cpu(cpu); + if (microcode_init_cpu(cpu)) + printk(KERN_ERR "microcode: failed to init CPU%d\n", + cpu); case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: pr_debug("microcode: CPU%d added\n", cpu); @@ -448,7 +464,7 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) } static struct notifier_block __refdata mc_cpu_notifier = { - .notifier_call = mc_cpu_callback, + .notifier_call = mc_cpu_callback, }; static int __init microcode_init(void) diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c index 5e9f4fc..149b9ec 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/microcode_intel.c @@ -70,28 +70,28 @@ * Fix sigmatch() macro to handle old CPUs with pf == 0. * Thanks to Stuart Swales for pointing out this bug. */ +#include <linux/platform_device.h> #include <linux/capability.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/sched.h> +#include <linux/miscdevice.h> +#include <linux/firmware.h> #include <linux/smp_lock.h> +#include <linux/spinlock.h> #include <linux/cpumask.h> -#include <linux/module.h> -#include <linux/slab.h> +#include <linux/uaccess.h> #include <linux/vmalloc.h> -#include <linux/miscdevice.h> -#include <linux/spinlock.h> -#include <linux/mm.h> -#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/module.h> #include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/slab.h> #include <linux/cpu.h> -#include <linux/firmware.h> -#include <linux/platform_device.h> -#include <linux/uaccess.h> +#include <linux/fs.h> +#include <linux/mm.h> -#include <asm/msr.h> -#include <asm/processor.h> #include <asm/microcode.h> +#include <asm/processor.h> +#include <asm/msr.h> MODULE_DESCRIPTION("Microcode Update Driver"); MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>"); @@ -129,12 +129,13 @@ struct extended_sigtable { struct extended_signature sigs[0]; }; -#define DEFAULT_UCODE_DATASIZE (2000) +#define DEFAULT_UCODE_DATASIZE (2000) #define MC_HEADER_SIZE (sizeof(struct microcode_header_intel)) #define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE) #define EXT_HEADER_SIZE (sizeof(struct extended_sigtable)) #define EXT_SIGNATURE_SIZE (sizeof(struct extended_signature)) #define DWSIZE (sizeof(u32)) + #define get_totalsize(mc) \ (((struct microcode_intel *)mc)->hdr.totalsize ? \ ((struct microcode_intel *)mc)->hdr.totalsize : \ @@ -197,30 +198,31 @@ static inline int update_match_cpu(struct cpu_signature *csig, int sig, int pf) } static inline int -update_match_revision(struct microcode_header_intel *mc_header, int rev) +update_match_revision(struct microcode_header_intel *mc_header, int rev) { return (mc_header->rev <= rev) ? 0 : 1; } static int microcode_sanity_check(void *mc) { + unsigned long total_size, data_size, ext_table_size; struct microcode_header_intel *mc_header = mc; struct extended_sigtable *ext_header = NULL; - struct extended_signature *ext_sig; - unsigned long total_size, data_size, ext_table_size; 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) { printk(KERN_ERR "microcode: error! " - "Bad data size in microcode data file\n"); + "Bad data size in microcode data file\n"); return -EINVAL; } if (mc_header->ldrver != 1 || mc_header->hdrver != 1) { printk(KERN_ERR "microcode: error! " - "Unknown microcode update format\n"); + "Unknown microcode update format\n"); return -EINVAL; } ext_table_size = total_size - (MC_HEADER_SIZE + data_size); @@ -318,11 +320,15 @@ get_matching_microcode(struct cpu_signature *cpu_sig, void *mc, int rev) static void apply_microcode(int cpu) { + struct microcode_intel *mc_intel; + struct ucode_cpu_info *uci; unsigned long flags; unsigned int val[2]; - int cpu_num = raw_smp_processor_id(); - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - struct microcode_intel *mc_intel = uci->mc; + int cpu_num; + + cpu_num = raw_smp_processor_id(); + uci = ucode_cpu_info + cpu; + mc_intel = uci->mc; /* We should bind the task to the CPU */ BUG_ON(cpu_num != cpu); @@ -348,15 +354,17 @@ static void apply_microcode(int cpu) spin_unlock_irqrestore(µcode_update_lock, flags); if (val[1] != mc_intel->hdr.rev) { printk(KERN_ERR "microcode: CPU%d update from revision " - "0x%x to 0x%x failed\n", cpu_num, uci->cpu_sig.rev, val[1]); + "0x%x to 0x%x failed\n", + cpu_num, uci->cpu_sig.rev, val[1]); return; } printk(KERN_INFO "microcode: CPU%d updated from revision " - "0x%x to 0x%x, date = %04x-%02x-%02x \n", + "0x%x to 0x%x, date = %04x-%02x-%02x \n", cpu_num, uci->cpu_sig.rev, val[1], mc_intel->hdr.date & 0xffff, mc_intel->hdr.date >> 24, (mc_intel->hdr.date >> 16) & 0xff); + uci->cpu_sig.rev = val[1]; } @@ -404,18 +412,23 @@ static int generic_load_microcode(int cpu, void *data, size_t size, leftover -= mc_size; } - if (new_mc) { - if (!leftover) { - if (uci->mc) - vfree(uci->mc); - uci->mc = (struct microcode_intel *)new_mc; - pr_debug("microcode: CPU%d found a matching microcode update with" - " version 0x%x (current=0x%x)\n", - cpu, new_rev, uci->cpu_sig.rev); - } else - vfree(new_mc); + if (!new_mc) + goto out; + + if (leftover) { + vfree(new_mc); + goto out; } + if (uci->mc) + vfree(uci->mc); + uci->mc = (struct microcode_intel *)new_mc; + + pr_debug("microcode: CPU%d found a matching microcode update with" + " version 0x%x (current=0x%x)\n", + cpu, new_rev, uci->cpu_sig.rev); + + out: return (int)leftover; } diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c index 666e43d..712d15f 100644 --- a/arch/x86/kernel/mmconf-fam10h_64.c +++ b/arch/x86/kernel/mmconf-fam10h_64.c @@ -226,7 +226,7 @@ static int __devinit set_check_enable_amd_mmconf(const struct dmi_system_id *d) return 0; } -static struct dmi_system_id __devinitdata mmconf_dmi_table[] = { +static const struct dmi_system_id __cpuinitconst mmconf_dmi_table[] = { { .callback = set_check_enable_amd_mmconf, .ident = "Sun Microsystems Machine", diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 37cb1bd..dce99dc 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -109,9 +109,6 @@ static void __init MP_bus_info(struct mpc_bus *m) } else printk(KERN_WARNING "Unknown bustype %s - ignoring\n", str); } -#endif - -#ifdef CONFIG_X86_IO_APIC static int bad_ioapic(unsigned long address) { @@ -224,8 +221,12 @@ static void __init MP_intsrc_info(struct mpc_intsrc *m) if (++mp_irq_entries == MAX_IRQ_SOURCES) panic("Max # of irq sources exceeded!!\n"); } +#else /* CONFIG_X86_IO_APIC */ +static inline void __init MP_bus_info(struct mpc_bus *m) {} +static inline void __init MP_ioapic_info(struct mpc_ioapic *m) {} +static inline void __init MP_intsrc_info(struct mpc_intsrc *m) {} +#endif /* CONFIG_X86_IO_APIC */ -#endif static void __init MP_lintsrc_info(struct mpc_lintsrc *m) { @@ -275,6 +276,20 @@ static int __init smp_check_mpc(struct mpc_table *mpc, char *oem, char *str) return 1; } +static void skip_entry(unsigned char **ptr, int *count, int size) +{ + *ptr += size; + *count += size; +} + +static void __init smp_dump_mptable(struct mpc_table *mpc, unsigned char *mpt) +{ + printk(KERN_ERR "Your mptable is wrong, contact your HW vendor!\n" + "type %x\n", *mpt); + print_hex_dump(KERN_ERR, " ", DUMP_PREFIX_ADDRESS, 16, + 1, mpc, mpc->length, 1); +} + static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) { char str[16]; @@ -310,61 +325,30 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) while (count < mpc->length) { switch (*mpt) { case MP_PROCESSOR: - { - struct mpc_cpu *m = (struct mpc_cpu *)mpt; - /* ACPI may have already provided this data */ - if (!acpi_lapic) - MP_processor_info(m); - mpt += sizeof(*m); - count += sizeof(*m); - break; - } + /* ACPI may have already provided this data */ + if (!acpi_lapic) + MP_processor_info((struct mpc_cpu *)mpt); + skip_entry(&mpt, &count, sizeof(struct mpc_cpu)); + break; case MP_BUS: - { - struct mpc_bus *m = (struct mpc_bus *)mpt; -#ifdef CONFIG_X86_IO_APIC - MP_bus_info(m); -#endif - mpt += sizeof(*m); - count += sizeof(*m); - break; - } + MP_bus_info((struct mpc_bus *)mpt); + skip_entry(&mpt, &count, sizeof(struct mpc_bus)); + break; case MP_IOAPIC: - { -#ifdef CONFIG_X86_IO_APIC - struct mpc_ioapic *m = (struct mpc_ioapic *)mpt; - MP_ioapic_info(m); -#endif - mpt += sizeof(struct mpc_ioapic); - count += sizeof(struct mpc_ioapic); - break; - } + MP_ioapic_info((struct mpc_ioapic *)mpt); + skip_entry(&mpt, &count, sizeof(struct mpc_ioapic)); + break; case MP_INTSRC: - { -#ifdef CONFIG_X86_IO_APIC - struct mpc_intsrc *m = (struct mpc_intsrc *)mpt; - - MP_intsrc_info(m); -#endif - mpt += sizeof(struct mpc_intsrc); - count += sizeof(struct mpc_intsrc); - break; - } + MP_intsrc_info((struct mpc_intsrc *)mpt); + skip_entry(&mpt, &count, sizeof(struct mpc_intsrc)); + break; case MP_LINTSRC: - { - struct mpc_lintsrc *m = - (struct mpc_lintsrc *)mpt; - MP_lintsrc_info(m); - mpt += sizeof(*m); - count += sizeof(*m); - break; - } + MP_lintsrc_info((struct mpc_lintsrc *)mpt); + skip_entry(&mpt, &count, sizeof(struct mpc_lintsrc)); + break; default: /* wrong mptable */ - printk(KERN_ERR "Your mptable is wrong, contact your HW vendor!\n"); - printk(KERN_ERR "type %x\n", *mpt); - print_hex_dump(KERN_ERR, " ", DUMP_PREFIX_ADDRESS, 16, - 1, mpc, mpc->length, 1); + smp_dump_mptable(mpc, mpt); count = mpc->length; break; } @@ -558,6 +542,68 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) static struct mpf_intel *mpf_found; +static unsigned long __init get_mpc_size(unsigned long physptr) +{ + struct mpc_table *mpc; + unsigned long size; + + mpc = early_ioremap(physptr, PAGE_SIZE); + size = mpc->length; + early_iounmap(mpc, PAGE_SIZE); + apic_printk(APIC_VERBOSE, " mpc: %lx-%lx\n", physptr, physptr + size); + + return size; +} + +static int __init check_physptr(struct mpf_intel *mpf, unsigned int early) +{ + struct mpc_table *mpc; + unsigned long size; + + size = get_mpc_size(mpf->physptr); + mpc = early_ioremap(mpf->physptr, size); + /* + * Read the physical hardware table. Anything here will + * override the defaults. + */ + if (!smp_read_mpc(mpc, early)) { +#ifdef CONFIG_X86_LOCAL_APIC + smp_found_config = 0; +#endif + printk(KERN_ERR "BIOS bug, MP table errors detected!...\n" + "... disabling SMP support. (tell your hw vendor)\n"); + early_iounmap(mpc, size); + return -1; + } + early_iounmap(mpc, size); + + if (early) + return -1; + +#ifdef CONFIG_X86_IO_APIC + /* + * If there are no explicit MP IRQ entries, then we are + * broken. We set up most of the low 16 IO-APIC pins to + * ISA defaults and hope it will work. + */ + if (!mp_irq_entries) { + struct mpc_bus bus; + + printk(KERN_ERR "BIOS bug, no explicit IRQ entries, " + "using default mptable. (tell your hw vendor)\n"); + + bus.type = MP_BUS; + bus.busid = 0; + memcpy(bus.bustype, "ISA ", 6); + MP_bus_info(&bus); + + construct_default_ioirq_mptable(0); + } +#endif + + return 0; +} + /* * Scan the memory blocks for an SMP configuration block. */ @@ -611,45 +657,8 @@ static void __init __get_smp_config(unsigned int early) construct_default_ISA_mptable(mpf->feature1); } else if (mpf->physptr) { - - /* - * Read the physical hardware table. Anything here will - * override the defaults. - */ - if (!smp_read_mpc(phys_to_virt(mpf->physptr), early)) { -#ifdef CONFIG_X86_LOCAL_APIC - smp_found_config = 0; -#endif - printk(KERN_ERR - "BIOS bug, MP table errors detected!...\n"); - printk(KERN_ERR "... disabling SMP support. " - "(tell your hw vendor)\n"); - return; - } - - if (early) + if (check_physptr(mpf, early)) return; -#ifdef CONFIG_X86_IO_APIC - /* - * If there are no explicit MP IRQ entries, then we are - * broken. We set up most of the low 16 IO-APIC pins to - * ISA defaults and hope it will work. - */ - if (!mp_irq_entries) { - struct mpc_bus bus; - - printk(KERN_ERR "BIOS bug, no explicit IRQ entries, " - "using default mptable. " - "(tell your hw vendor)\n"); - - bus.type = MP_BUS; - bus.busid = 0; - memcpy(bus.bustype, "ISA ", 6); - MP_bus_info(&bus); - - construct_default_ioirq_mptable(0); - } -#endif } else BUG(); @@ -670,6 +679,31 @@ void __init get_smp_config(void) __get_smp_config(0); } +static void smp_reserve_bootmem(struct mpf_intel *mpf) +{ + unsigned long size = get_mpc_size(mpf->physptr); +#ifdef CONFIG_X86_32 + /* + * We cannot access to MPC table to compute table size yet, + * as only few megabytes from the bottom is mapped now. + * PC-9800's MPC table places on the very last of physical + * memory; so that simply reserving PAGE_SIZE from mpf->physptr + * yields BUG() in reserve_bootmem. + * also need to make sure physptr is below than max_low_pfn + * we don't need reserve the area above max_low_pfn + */ + unsigned long end = max_low_pfn * PAGE_SIZE; + + if (mpf->physptr < end) { + if (mpf->physptr + size > end) + size = end - mpf->physptr; + reserve_bootmem_generic(mpf->physptr, size, BOOTMEM_DEFAULT); + } +#else + reserve_bootmem_generic(mpf->physptr, size, BOOTMEM_DEFAULT); +#endif +} + static int __init smp_scan_config(unsigned long base, unsigned long length, unsigned reserve) { @@ -697,36 +731,10 @@ static int __init smp_scan_config(unsigned long base, unsigned long length, if (!reserve) return 1; - reserve_bootmem_generic(virt_to_phys(mpf), PAGE_SIZE, - BOOTMEM_DEFAULT); - if (mpf->physptr) { - unsigned long size = PAGE_SIZE; -#ifdef CONFIG_X86_32 - /* - * We cannot access to MPC table to compute - * table size yet, as only few megabytes from - * the bottom is mapped now. - * PC-9800's MPC table places on the very last - * of physical memory; so that simply reserving - * PAGE_SIZE from mpf->physptr yields BUG() - * in reserve_bootmem. - * also need to make sure physptr is below than - * max_low_pfn - * we don't need reserve the area above max_low_pfn - */ - unsigned long end = max_low_pfn * PAGE_SIZE; - - if (mpf->physptr < end) { - if (mpf->physptr + size > end) - size = end - mpf->physptr; - reserve_bootmem_generic(mpf->physptr, size, - BOOTMEM_DEFAULT); - } -#else - reserve_bootmem_generic(mpf->physptr, size, + reserve_bootmem_generic(virt_to_phys(mpf), sizeof(*mpf), BOOTMEM_DEFAULT); -#endif - } + if (mpf->physptr) + smp_reserve_bootmem(mpf); return 1; } @@ -829,7 +837,57 @@ static int __init get_MP_intsrc_index(struct mpc_intsrc *m) #define SPARE_SLOT_NUM 20 static struct mpc_intsrc __initdata *m_spare[SPARE_SLOT_NUM]; -#endif + +static void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) +{ + int i; + + apic_printk(APIC_VERBOSE, "OLD "); + print_MP_intsrc_info(m); + + i = get_MP_intsrc_index(m); + if (i > 0) { + assign_to_mpc_intsrc(&mp_irqs[i], m); + apic_printk(APIC_VERBOSE, "NEW "); + print_mp_irq_info(&mp_irqs[i]); + return; + } + if (!i) { + /* legacy, do nothing */ + return; + } + if (*nr_m_spare < SPARE_SLOT_NUM) { + /* + * not found (-1), or duplicated (-2) are invalid entries, + * we need to use the slot later + */ + m_spare[*nr_m_spare] = m; + *nr_m_spare += 1; + } +} +#else /* CONFIG_X86_IO_APIC */ +static inline void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {} +#endif /* CONFIG_X86_IO_APIC */ + +static int check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, + int count) +{ + if (!mpc_new_phys) { + pr_info("No spare slots, try to append...take your risk, " + "new mpc_length %x\n", count); + } else { + if (count <= mpc_new_length) + pr_info("No spare slots, try to append..., " + "new mpc_length %x\n", count); + else { + pr_err("mpc_new_length %lx is too small\n", + mpc_new_length); + return -1; + } + } + + return 0; +} static int __init replace_intsrc_all(struct mpc_table *mpc, unsigned long mpc_new_phys, @@ -837,77 +895,33 @@ static int __init replace_intsrc_all(struct mpc_table *mpc, { #ifdef CONFIG_X86_IO_APIC int i; - int nr_m_spare = 0; #endif - int count = sizeof(*mpc); + int nr_m_spare = 0; unsigned char *mpt = ((unsigned char *)mpc) + count; printk(KERN_INFO "mpc_length %x\n", mpc->length); while (count < mpc->length) { switch (*mpt) { case MP_PROCESSOR: - { - struct mpc_cpu *m = (struct mpc_cpu *)mpt; - mpt += sizeof(*m); - count += sizeof(*m); - break; - } + skip_entry(&mpt, &count, sizeof(struct mpc_cpu)); + break; case MP_BUS: - { - struct mpc_bus *m = (struct mpc_bus *)mpt; - mpt += sizeof(*m); - count += sizeof(*m); - break; - } + skip_entry(&mpt, &count, sizeof(struct mpc_bus)); + break; case MP_IOAPIC: - { - mpt += sizeof(struct mpc_ioapic); - count += sizeof(struct mpc_ioapic); - break; - } + skip_entry(&mpt, &count, sizeof(struct mpc_ioapic)); + break; case MP_INTSRC: - { -#ifdef CONFIG_X86_IO_APIC - struct mpc_intsrc *m = (struct mpc_intsrc *)mpt; - - printk(KERN_INFO "OLD "); - print_MP_intsrc_info(m); - i = get_MP_intsrc_index(m); - if (i > 0) { - assign_to_mpc_intsrc(&mp_irqs[i], m); - printk(KERN_INFO "NEW "); - print_mp_irq_info(&mp_irqs[i]); - } else if (!i) { - /* legacy, do nothing */ - } else if (nr_m_spare < SPARE_SLOT_NUM) { - /* - * not found (-1), or duplicated (-2) - * are invalid entries, - * we need to use the slot later - */ - m_spare[nr_m_spare] = m; - nr_m_spare++; - } -#endif - mpt += sizeof(struct mpc_intsrc); - count += sizeof(struct mpc_intsrc); - break; - } + check_irq_src((struct mpc_intsrc *)mpt, &nr_m_spare); + skip_entry(&mpt, &count, sizeof(struct mpc_intsrc)); + break; case MP_LINTSRC: - { - struct mpc_lintsrc *m = - (struct mpc_lintsrc *)mpt; - mpt += sizeof(*m); - count += sizeof(*m); - break; - } + skip_entry(&mpt, &count, sizeof(struct mpc_lintsrc)); + break; default: /* wrong mptable */ - printk(KERN_ERR "Your mptable is wrong, contact your HW vendor!\n"); - printk(KERN_ERR "type %x\n", *mpt); - print_hex_dump(KERN_ERR, " ", DUMP_PREFIX_ADDRESS, 16, - 1, mpc, mpc->length, 1); + smp_dump_mptable(mpc, mpt); goto out; } } @@ -924,23 +938,15 @@ static int __init replace_intsrc_all(struct mpc_table *mpc, continue; if (nr_m_spare > 0) { - printk(KERN_INFO "*NEW* found "); + apic_printk(APIC_VERBOSE, "*NEW* found\n"); nr_m_spare--; assign_to_mpc_intsrc(&mp_irqs[i], m_spare[nr_m_spare]); m_spare[nr_m_spare] = NULL; } else { struct mpc_intsrc *m = (struct mpc_intsrc *)mpt; count += sizeof(struct mpc_intsrc); - if (!mpc_new_phys) { - printk(KERN_INFO "No spare slots, try to append...take your risk, new mpc_length %x\n", count); - } else { - if (count <= mpc_new_length) - printk(KERN_INFO "No spare slots, try to append..., new mpc_length %x\n", count); - else { - printk(KERN_ERR "mpc_new_length %lx is too small\n", mpc_new_length); - goto out; - } - } + if (!check_slot(mpc_new_phys, mpc_new_length, count)) + goto out; assign_to_mpc_intsrc(&mp_irqs[i], m); mpc->length = count; mpt += sizeof(struct mpc_intsrc); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 63dd358..8e45f44 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -470,7 +470,6 @@ struct pv_mmu_ops pv_mmu_ops = { #if PAGETABLE_LEVELS >= 3 #ifdef CONFIG_X86_PAE .set_pte_atomic = native_set_pte_atomic, - .set_pte_present = native_set_pte_present, .pte_clear = native_pte_clear, .pmd_clear = native_pmd_clear, #endif diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index d28bbdc..755c21e 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -380,8 +380,9 @@ static inline struct iommu_table *find_iommu_table(struct device *dev) return tbl; } -static void calgary_unmap_sg(struct device *dev, - struct scatterlist *sglist, int nelems, int direction) +static void calgary_unmap_sg(struct device *dev, struct scatterlist *sglist, + int nelems,enum dma_data_direction dir, + struct dma_attrs *attrs) { struct iommu_table *tbl = find_iommu_table(dev); struct scatterlist *s; @@ -404,7 +405,8 @@ static void calgary_unmap_sg(struct device *dev, } static int calgary_map_sg(struct device *dev, struct scatterlist *sg, - int nelems, int direction) + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs) { struct iommu_table *tbl = find_iommu_table(dev); struct scatterlist *s; @@ -429,15 +431,14 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg, s->dma_address = (entry << PAGE_SHIFT) | s->offset; /* insert into HW table */ - tce_build(tbl, entry, npages, vaddr & PAGE_MASK, - direction); + tce_build(tbl, entry, npages, vaddr & PAGE_MASK, dir); s->dma_length = s->length; } return nelems; error: - calgary_unmap_sg(dev, sg, nelems, direction); + calgary_unmap_sg(dev, sg, nelems, dir, NULL); for_each_sg(sg, s, nelems, i) { sg->dma_address = bad_dma_address; sg->dma_length = 0; @@ -445,10 +446,12 @@ error: return 0; } -static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr, - size_t size, int direction) +static dma_addr_t calgary_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) { - void *vaddr = phys_to_virt(paddr); + void *vaddr = page_address(page) + offset; unsigned long uaddr; unsigned int npages; struct iommu_table *tbl = find_iommu_table(dev); @@ -456,17 +459,18 @@ static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr, uaddr = (unsigned long)vaddr; npages = iommu_num_pages(uaddr, size, PAGE_SIZE); - return iommu_alloc(dev, tbl, vaddr, npages, direction); + return iommu_alloc(dev, tbl, vaddr, npages, dir); } -static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle, - size_t size, int direction) +static void calgary_unmap_page(struct device *dev, dma_addr_t dma_addr, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) { struct iommu_table *tbl = find_iommu_table(dev); unsigned int npages; - npages = iommu_num_pages(dma_handle, size, PAGE_SIZE); - iommu_free(tbl, dma_handle, npages); + npages = iommu_num_pages(dma_addr, size, PAGE_SIZE); + iommu_free(tbl, dma_addr, npages); } static void* calgary_alloc_coherent(struct device *dev, size_t size, @@ -515,13 +519,13 @@ static void calgary_free_coherent(struct device *dev, size_t size, free_pages((unsigned long)vaddr, get_order(size)); } -static struct dma_mapping_ops calgary_dma_ops = { +static struct dma_map_ops calgary_dma_ops = { .alloc_coherent = calgary_alloc_coherent, .free_coherent = calgary_free_coherent, - .map_single = calgary_map_single, - .unmap_single = calgary_unmap_single, .map_sg = calgary_map_sg, .unmap_sg = calgary_unmap_sg, + .map_page = calgary_map_page, + .unmap_page = calgary_unmap_page, }; static inline void __iomem * busno_to_bbar(unsigned char num) diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index b254285..90f5b9e 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -1,4 +1,5 @@ #include <linux/dma-mapping.h> +#include <linux/dma-debug.h> #include <linux/dmar.h> #include <linux/bootmem.h> #include <linux/pci.h> @@ -12,7 +13,7 @@ static int forbid_dac __read_mostly; -struct dma_mapping_ops *dma_ops; +struct dma_map_ops *dma_ops; EXPORT_SYMBOL(dma_ops); static int iommu_sac_force __read_mostly; @@ -44,6 +45,9 @@ struct device x86_dma_fallback_dev = { }; EXPORT_SYMBOL(x86_dma_fallback_dev); +/* Number of entries preallocated for DMA-API debugging */ +#define PREALLOC_DMA_DEBUG_ENTRIES 32768 + int dma_set_mask(struct device *dev, u64 mask) { if (!dev->dma_mask || !dma_supported(dev, mask)) @@ -224,7 +228,7 @@ early_param("iommu", iommu_setup); int dma_supported(struct device *dev, u64 mask) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); #ifdef CONFIG_PCI if (mask > 0xffffffff && forbid_dac > 0) { @@ -265,6 +269,12 @@ EXPORT_SYMBOL(dma_supported); static int __init pci_iommu_init(void) { + dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); + +#ifdef CONFIG_PCI + dma_debug_add_bus(&pci_bus_type); +#endif + calgary_iommu_init(); intel_iommu_init(); @@ -290,8 +300,7 @@ fs_initcall(pci_iommu_init); static __devinit void via_no_dac(struct pci_dev *dev) { if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) { - printk(KERN_INFO - "PCI: VIA PCI bridge detected. Disabling DAC.\n"); + dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n"); forbid_dac = 1; } } diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index d5768b1..b284b58 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -255,10 +255,13 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem, } /* Map a single area into the IOMMU */ -static dma_addr_t -gart_map_single(struct device *dev, phys_addr_t paddr, size_t size, int dir) +static dma_addr_t gart_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) { unsigned long bus; + phys_addr_t paddr = page_to_phys(page) + offset; if (!dev) dev = &x86_dma_fallback_dev; @@ -275,8 +278,9 @@ gart_map_single(struct device *dev, phys_addr_t paddr, size_t size, int dir) /* * Free a DMA mapping. */ -static void gart_unmap_single(struct device *dev, dma_addr_t dma_addr, - size_t size, int direction) +static void gart_unmap_page(struct device *dev, dma_addr_t dma_addr, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) { unsigned long iommu_page; int npages; @@ -298,8 +302,8 @@ static void gart_unmap_single(struct device *dev, dma_addr_t dma_addr, /* * Wrapper for pci_unmap_single working with scatterlists. */ -static void -gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) +static void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) { struct scatterlist *s; int i; @@ -307,7 +311,7 @@ gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) for_each_sg(sg, s, nents, i) { if (!s->dma_length || !s->length) break; - gart_unmap_single(dev, s->dma_address, s->dma_length, dir); + gart_unmap_page(dev, s->dma_address, s->dma_length, dir, NULL); } } @@ -329,7 +333,7 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg, addr = dma_map_area(dev, addr, s->length, dir, 0); if (addr == bad_dma_address) { if (i > 0) - gart_unmap_sg(dev, sg, i, dir); + gart_unmap_sg(dev, sg, i, dir, NULL); nents = 0; sg[0].dma_length = 0; break; @@ -400,8 +404,8 @@ dma_map_cont(struct device *dev, struct scatterlist *start, int nelems, * DMA map all entries in a scatterlist. * Merge chunks that have page aligned sizes into a continuous mapping. */ -static int -gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) +static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) { struct scatterlist *s, *ps, *start_sg, *sgmap; int need = 0, nextneed, i, out, start; @@ -468,7 +472,7 @@ gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) error: flush_gart(); - gart_unmap_sg(dev, sg, out, dir); + gart_unmap_sg(dev, sg, out, dir, NULL); /* When it was forced or merged try again in a dumb way */ if (force_iommu || iommu_merge) { @@ -521,7 +525,7 @@ static void gart_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr) { - gart_unmap_single(dev, dma_addr, size, DMA_BIDIRECTIONAL); + gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL); free_pages((unsigned long)vaddr, get_order(size)); } @@ -707,11 +711,11 @@ static __init int init_k8_gatt(struct agp_kern_info *info) return -1; } -static struct dma_mapping_ops gart_dma_ops = { - .map_single = gart_map_single, - .unmap_single = gart_unmap_single, +static struct dma_map_ops gart_dma_ops = { .map_sg = gart_map_sg, .unmap_sg = gart_unmap_sg, + .map_page = gart_map_page, + .unmap_page = gart_unmap_page, .alloc_coherent = gart_alloc_coherent, .free_coherent = gart_free_coherent, }; diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index c70ab5a..c6d703b 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -1,14 +1,14 @@ /* Fallback functions when the main IOMMU code is not compiled in. This code is roughly equivalent to i386. */ -#include <linux/mm.h> -#include <linux/init.h> -#include <linux/pci.h> -#include <linux/string.h> #include <linux/dma-mapping.h> #include <linux/scatterlist.h> +#include <linux/string.h> +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/mm.h> -#include <asm/iommu.h> #include <asm/processor.h> +#include <asm/iommu.h> #include <asm/dma.h> static int @@ -25,19 +25,19 @@ check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size) return 1; } -static dma_addr_t -nommu_map_single(struct device *hwdev, phys_addr_t paddr, size_t size, - int direction) +static dma_addr_t nommu_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) { - dma_addr_t bus = paddr; + dma_addr_t bus = page_to_phys(page) + offset; WARN_ON(size == 0); - if (!check_addr("map_single", hwdev, bus, size)) - return bad_dma_address; + if (!check_addr("map_single", dev, bus, size)) + return bad_dma_address; flush_write_buffers(); return bus; } - /* Map a set of buffers described by scatterlist in streaming * mode for DMA. This is the scatter-gather version of the * above pci_map_single interface. Here the scatter gather list @@ -54,7 +54,8 @@ nommu_map_single(struct device *hwdev, phys_addr_t paddr, size_t size, * the same here. */ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, - int nents, int direction) + int nents, enum dma_data_direction dir, + struct dma_attrs *attrs) { struct scatterlist *s; int i; @@ -78,12 +79,12 @@ static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr, free_pages((unsigned long)vaddr, get_order(size)); } -struct dma_mapping_ops nommu_dma_ops = { - .alloc_coherent = dma_generic_alloc_coherent, - .free_coherent = nommu_free_coherent, - .map_single = nommu_map_single, - .map_sg = nommu_map_sg, - .is_phys = 1, +struct dma_map_ops nommu_dma_ops = { + .alloc_coherent = dma_generic_alloc_coherent, + .free_coherent = nommu_free_coherent, + .map_sg = nommu_map_sg, + .map_page = nommu_map_page, + .is_phys = 1, }; void __init no_iommu_init(void) diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb.c index d59c917..34f12e9 100644 --- a/arch/x86/kernel/pci-swiotlb_64.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -33,18 +33,11 @@ phys_addr_t swiotlb_bus_to_phys(dma_addr_t baddr) return baddr; } -int __weak swiotlb_arch_range_needs_mapping(void *ptr, size_t size) +int __weak swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size) { return 0; } -static dma_addr_t -swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size, - int direction) -{ - return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction); -} - static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags) { @@ -57,20 +50,20 @@ static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags); } -struct dma_mapping_ops swiotlb_dma_ops = { +struct dma_map_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, .alloc_coherent = x86_swiotlb_alloc_coherent, .free_coherent = swiotlb_free_coherent, - .map_single = swiotlb_map_single_phys, - .unmap_single = swiotlb_unmap_single, .sync_single_for_cpu = swiotlb_sync_single_for_cpu, .sync_single_for_device = swiotlb_sync_single_for_device, .sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu, .sync_single_range_for_device = swiotlb_sync_single_range_for_device, .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, .sync_sg_for_device = swiotlb_sync_sg_for_device, - .map_sg = swiotlb_map_sg, - .unmap_sg = swiotlb_unmap_sg, + .map_sg = swiotlb_map_sg_attrs, + .unmap_sg = swiotlb_unmap_sg_attrs, + .map_page = swiotlb_map_page, + .unmap_page = swiotlb_unmap_page, .dma_supported = NULL, }; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 87b69d4..ca98915 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -1,16 +1,19 @@ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/mm.h> -#include <asm/idle.h> #include <linux/smp.h> +#include <linux/prctl.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/pm.h> #include <linux/clockchips.h> -#include <linux/ftrace.h> +#include <trace/power.h> #include <asm/system.h> #include <asm/apic.h> +#include <asm/idle.h> +#include <asm/uaccess.h> +#include <asm/i387.h> unsigned long idle_halt; EXPORT_SYMBOL(idle_halt); @@ -19,6 +22,9 @@ EXPORT_SYMBOL(idle_nomwait); struct kmem_cache *task_xstate_cachep; +DEFINE_TRACE(power_start); +DEFINE_TRACE(power_end); + int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; @@ -56,6 +62,193 @@ void arch_task_cache_init(void) } /* + * Free current thread data structures etc.. + */ +void exit_thread(void) +{ + struct task_struct *me = current; + struct thread_struct *t = &me->thread; + unsigned long *bp = t->io_bitmap_ptr; + + if (bp) { + struct tss_struct *tss = &per_cpu(init_tss, get_cpu()); + + t->io_bitmap_ptr = NULL; + clear_thread_flag(TIF_IO_BITMAP); + /* + * Careful, clear this in the TSS too: + */ + memset(tss->io_bitmap, 0xff, t->io_bitmap_max); + t->io_bitmap_max = 0; + put_cpu(); + kfree(bp); + } + + ds_exit_thread(current); +} + +void flush_thread(void) +{ + struct task_struct *tsk = current; + +#ifdef CONFIG_X86_64 + if (test_tsk_thread_flag(tsk, TIF_ABI_PENDING)) { + clear_tsk_thread_flag(tsk, TIF_ABI_PENDING); + if (test_tsk_thread_flag(tsk, TIF_IA32)) { + clear_tsk_thread_flag(tsk, TIF_IA32); + } else { + set_tsk_thread_flag(tsk, TIF_IA32); + current_thread_info()->status |= TS_COMPAT; + } + } +#endif + + clear_tsk_thread_flag(tsk, TIF_DEBUG); + + tsk->thread.debugreg0 = 0; + tsk->thread.debugreg1 = 0; + tsk->thread.debugreg2 = 0; + tsk->thread.debugreg3 = 0; + tsk->thread.debugreg6 = 0; + tsk->thread.debugreg7 = 0; + memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); + /* + * Forget coprocessor state.. + */ + tsk->fpu_counter = 0; + clear_fpu(tsk); + clear_used_math(); +} + +static void hard_disable_TSC(void) +{ + write_cr4(read_cr4() | X86_CR4_TSD); +} + +void disable_TSC(void) +{ + preempt_disable(); + if (!test_and_set_thread_flag(TIF_NOTSC)) + /* + * Must flip the CPU state synchronously with + * TIF_NOTSC in the current running context. + */ + hard_disable_TSC(); + preempt_enable(); +} + +static void hard_enable_TSC(void) +{ + write_cr4(read_cr4() & ~X86_CR4_TSD); +} + +static void enable_TSC(void) +{ + preempt_disable(); + if (test_and_clear_thread_flag(TIF_NOTSC)) + /* + * Must flip the CPU state synchronously with + * TIF_NOTSC in the current running context. + */ + hard_enable_TSC(); + preempt_enable(); +} + +int get_tsc_mode(unsigned long adr) +{ + unsigned int val; + + if (test_thread_flag(TIF_NOTSC)) + val = PR_TSC_SIGSEGV; + else + val = PR_TSC_ENABLE; + + return put_user(val, (unsigned int __user *)adr); +} + +int set_tsc_mode(unsigned int val) +{ + if (val == PR_TSC_SIGSEGV) + disable_TSC(); + else if (val == PR_TSC_ENABLE) + enable_TSC(); + else + return -EINVAL; + + return 0; +} + +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, + struct tss_struct *tss) +{ + struct thread_struct *prev, *next; + + prev = &prev_p->thread; + next = &next_p->thread; + + if (test_tsk_thread_flag(next_p, TIF_DS_AREA_MSR) || + test_tsk_thread_flag(prev_p, TIF_DS_AREA_MSR)) + ds_switch_to(prev_p, next_p); + else if (next->debugctlmsr != prev->debugctlmsr) + update_debugctlmsr(next->debugctlmsr); + + if (test_tsk_thread_flag(next_p, TIF_DEBUG)) { + set_debugreg(next->debugreg0, 0); + set_debugreg(next->debugreg1, 1); + set_debugreg(next->debugreg2, 2); + set_debugreg(next->debugreg3, 3); + /* no 4 and 5 */ + set_debugreg(next->debugreg6, 6); + set_debugreg(next->debugreg7, 7); + } + + if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ + test_tsk_thread_flag(next_p, TIF_NOTSC)) { + /* prev and next are different */ + if (test_tsk_thread_flag(next_p, TIF_NOTSC)) + hard_disable_TSC(); + else + hard_enable_TSC(); + } + + if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { + /* + * Copy the relevant range of the IO bitmap. + * Normally this is 128 bytes or less: + */ + memcpy(tss->io_bitmap, next->io_bitmap_ptr, + max(prev->io_bitmap_max, next->io_bitmap_max)); + } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { + /* + * Clear any possible leftover bits: + */ + memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); + } +} + +int sys_fork(struct pt_regs *regs) +{ + return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL); +} + +/* + * This is trivial, and on the face of it looks like it + * could equally well be done in user mode. + * + * Not so, for quite unobvious reasons - register pressure. + * In user mode vfork() cannot have a stack frame, and if + * done by calling the "clone()" system call directly, you + * do not have enough call-clobbered registers to hold all + * the information you need. + */ +int sys_vfork(struct pt_regs *regs) +{ + return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0, + NULL, NULL); +} + + +/* * Idle related variables and functions */ unsigned long boot_option_idle_override = 0; @@ -135,7 +328,7 @@ void stop_this_cpu(void *dummy) /* * Remove this CPU: */ - cpu_clear(smp_processor_id(), cpu_online_map); + set_cpu_online(smp_processor_id(), false); disable_local_APIC(); for (;;) { @@ -285,12 +478,13 @@ static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c) return 1; } -static cpumask_t c1e_mask = CPU_MASK_NONE; +static cpumask_var_t c1e_mask; static int c1e_detected; void c1e_remove_cpu(int cpu) { - cpu_clear(cpu, c1e_mask); + if (c1e_mask != NULL) + cpumask_clear_cpu(cpu, c1e_mask); } /* @@ -319,8 +513,8 @@ static void c1e_idle(void) if (c1e_detected) { int cpu = smp_processor_id(); - if (!cpu_isset(cpu, c1e_mask)) { - cpu_set(cpu, c1e_mask); + if (!cpumask_test_cpu(cpu, c1e_mask)) { + cpumask_set_cpu(cpu, c1e_mask); /* * Force broadcast so ACPI can not interfere. Needs * to run with interrupts enabled as it uses @@ -372,6 +566,15 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) pm_idle = default_idle; } +void __init init_c1e_mask(void) +{ + /* If we're using c1e_idle, we need to allocate c1e_mask. */ + if (pm_idle == c1e_idle) { + alloc_cpumask_var(&c1e_mask, GFP_KERNEL); + cpumask_clear(c1e_mask); + } +} + static int __init idle_setup(char *str) { if (!str) diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 646da41..76f8f84 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -230,55 +230,6 @@ int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) } EXPORT_SYMBOL(kernel_thread); -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ - /* The process may have allocated an io port bitmap... nuke it. */ - if (unlikely(test_thread_flag(TIF_IO_BITMAP))) { - struct task_struct *tsk = current; - struct thread_struct *t = &tsk->thread; - int cpu = get_cpu(); - struct tss_struct *tss = &per_cpu(init_tss, cpu); - - kfree(t->io_bitmap_ptr); - t->io_bitmap_ptr = NULL; - clear_thread_flag(TIF_IO_BITMAP); - /* - * Careful, clear this in the TSS too: - */ - memset(tss->io_bitmap, 0xff, tss->io_bitmap_max); - t->io_bitmap_max = 0; - tss->io_bitmap_owner = NULL; - tss->io_bitmap_max = 0; - tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET; - put_cpu(); - } - - ds_exit_thread(current); -} - -void flush_thread(void) -{ - struct task_struct *tsk = current; - - tsk->thread.debugreg0 = 0; - tsk->thread.debugreg1 = 0; - tsk->thread.debugreg2 = 0; - tsk->thread.debugreg3 = 0; - tsk->thread.debugreg6 = 0; - tsk->thread.debugreg7 = 0; - memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - clear_tsk_thread_flag(tsk, TIF_DEBUG); - /* - * Forget coprocessor state.. - */ - tsk->fpu_counter = 0; - clear_fpu(tsk); - clear_used_math(); -} - void release_thread(struct task_struct *dead_task) { BUG_ON(dead_task->mm); @@ -294,7 +245,7 @@ void prepare_to_copy(struct task_struct *tsk) unlazy_fpu(tsk); } -int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, +int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { @@ -366,127 +317,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) } EXPORT_SYMBOL_GPL(start_thread); -static void hard_disable_TSC(void) -{ - write_cr4(read_cr4() | X86_CR4_TSD); -} - -void disable_TSC(void) -{ - preempt_disable(); - if (!test_and_set_thread_flag(TIF_NOTSC)) - /* - * Must flip the CPU state synchronously with - * TIF_NOTSC in the current running context. - */ - hard_disable_TSC(); - preempt_enable(); -} - -static void hard_enable_TSC(void) -{ - write_cr4(read_cr4() & ~X86_CR4_TSD); -} - -static void enable_TSC(void) -{ - preempt_disable(); - if (test_and_clear_thread_flag(TIF_NOTSC)) - /* - * Must flip the CPU state synchronously with - * TIF_NOTSC in the current running context. - */ - hard_enable_TSC(); - preempt_enable(); -} - -int get_tsc_mode(unsigned long adr) -{ - unsigned int val; - - if (test_thread_flag(TIF_NOTSC)) - val = PR_TSC_SIGSEGV; - else - val = PR_TSC_ENABLE; - - return put_user(val, (unsigned int __user *)adr); -} - -int set_tsc_mode(unsigned int val) -{ - if (val == PR_TSC_SIGSEGV) - disable_TSC(); - else if (val == PR_TSC_ENABLE) - enable_TSC(); - else - return -EINVAL; - - return 0; -} - -static noinline void -__switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss) -{ - struct thread_struct *prev, *next; - - prev = &prev_p->thread; - next = &next_p->thread; - - if (test_tsk_thread_flag(next_p, TIF_DS_AREA_MSR) || - test_tsk_thread_flag(prev_p, TIF_DS_AREA_MSR)) - ds_switch_to(prev_p, next_p); - else if (next->debugctlmsr != prev->debugctlmsr) - update_debugctlmsr(next->debugctlmsr); - - if (test_tsk_thread_flag(next_p, TIF_DEBUG)) { - set_debugreg(next->debugreg0, 0); - set_debugreg(next->debugreg1, 1); - set_debugreg(next->debugreg2, 2); - set_debugreg(next->debugreg3, 3); - /* no 4 and 5 */ - set_debugreg(next->debugreg6, 6); - set_debugreg(next->debugreg7, 7); - } - - if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ - test_tsk_thread_flag(next_p, TIF_NOTSC)) { - /* prev and next are different */ - if (test_tsk_thread_flag(next_p, TIF_NOTSC)) - hard_disable_TSC(); - else - hard_enable_TSC(); - } - - if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { - /* - * Disable the bitmap via an invalid offset. We still cache - * the previous bitmap owner and the IO bitmap contents: - */ - tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET; - return; - } - - if (likely(next == tss->io_bitmap_owner)) { - /* - * Previous owner of the bitmap (hence the bitmap content) - * matches the next task, we dont have to do anything but - * to set a valid offset in the TSS: - */ - tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; - return; - } - /* - * Lazy TSS's I/O bitmap copy. We set an invalid offset here - * and we let the task to get a GPF in case an I/O instruction - * is performed. The handler of the GPF will verify that the - * faulting task has a valid I/O bitmap and, it true, does the - * real copy and restart the instruction. This will save us - * redundant copies when the currently switched task does not - * perform any I/O during its timeslice. - */ - tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY; -} /* * switch_to(x,yn) should switch tasks from x to y. @@ -600,11 +430,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } -int sys_fork(struct pt_regs *regs) -{ - return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL); -} - int sys_clone(struct pt_regs *regs) { unsigned long clone_flags; @@ -621,21 +446,6 @@ int sys_clone(struct pt_regs *regs) } /* - * This is trivial, and on the face of it looks like it - * could equally well be done in user mode. - * - * Not so, for quite unobvious reasons - register pressure. - * In user mode vfork() cannot have a stack frame, and if - * done by calling the "clone()" system call directly, you - * do not have enough call-clobbered registers to hold all - * the information you need. - */ -int sys_vfork(struct pt_regs *regs) -{ - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0, NULL, NULL); -} - -/* * sys_execve() executes a new program. */ int sys_execve(struct pt_regs *regs) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 836ef65..b751a41 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -237,61 +237,6 @@ void show_regs(struct pt_regs *regs) show_trace(NULL, regs, (void *)(regs + 1), regs->bp); } -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ - struct task_struct *me = current; - struct thread_struct *t = &me->thread; - - if (me->thread.io_bitmap_ptr) { - struct tss_struct *tss = &per_cpu(init_tss, get_cpu()); - - kfree(t->io_bitmap_ptr); - t->io_bitmap_ptr = NULL; - clear_thread_flag(TIF_IO_BITMAP); - /* - * Careful, clear this in the TSS too: - */ - memset(tss->io_bitmap, 0xff, t->io_bitmap_max); - t->io_bitmap_max = 0; - put_cpu(); - } - - ds_exit_thread(current); -} - -void flush_thread(void) -{ - struct task_struct *tsk = current; - - if (test_tsk_thread_flag(tsk, TIF_ABI_PENDING)) { - clear_tsk_thread_flag(tsk, TIF_ABI_PENDING); - if (test_tsk_thread_flag(tsk, TIF_IA32)) { - clear_tsk_thread_flag(tsk, TIF_IA32); - } else { - set_tsk_thread_flag(tsk, TIF_IA32); - current_thread_info()->status |= TS_COMPAT; - } - } - clear_tsk_thread_flag(tsk, TIF_DEBUG); - - tsk->thread.debugreg0 = 0; - tsk->thread.debugreg1 = 0; - tsk->thread.debugreg2 = 0; - tsk->thread.debugreg3 = 0; - tsk->thread.debugreg6 = 0; - tsk->thread.debugreg7 = 0; - memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - /* - * Forget coprocessor state.. - */ - tsk->fpu_counter = 0; - clear_fpu(tsk); - clear_used_math(); -} - void release_thread(struct task_struct *dead_task) { if (dead_task->mm) { @@ -333,7 +278,7 @@ void prepare_to_copy(struct task_struct *tsk) unlazy_fpu(tsk); } -int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, +int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { @@ -425,118 +370,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) } EXPORT_SYMBOL_GPL(start_thread); -static void hard_disable_TSC(void) -{ - write_cr4(read_cr4() | X86_CR4_TSD); -} - -void disable_TSC(void) -{ - preempt_disable(); - if (!test_and_set_thread_flag(TIF_NOTSC)) - /* - * Must flip the CPU state synchronously with - * TIF_NOTSC in the current running context. - */ - hard_disable_TSC(); - preempt_enable(); -} - -static void hard_enable_TSC(void) -{ - write_cr4(read_cr4() & ~X86_CR4_TSD); -} - -static void enable_TSC(void) -{ - preempt_disable(); - if (test_and_clear_thread_flag(TIF_NOTSC)) - /* - * Must flip the CPU state synchronously with - * TIF_NOTSC in the current running context. - */ - hard_enable_TSC(); - preempt_enable(); -} - -int get_tsc_mode(unsigned long adr) -{ - unsigned int val; - - if (test_thread_flag(TIF_NOTSC)) - val = PR_TSC_SIGSEGV; - else - val = PR_TSC_ENABLE; - - return put_user(val, (unsigned int __user *)adr); -} - -int set_tsc_mode(unsigned int val) -{ - if (val == PR_TSC_SIGSEGV) - disable_TSC(); - else if (val == PR_TSC_ENABLE) - enable_TSC(); - else - return -EINVAL; - - return 0; -} - -/* - * This special macro can be used to load a debugging register - */ -#define loaddebug(thread, r) set_debugreg(thread->debugreg ## r, r) - -static inline void __switch_to_xtra(struct task_struct *prev_p, - struct task_struct *next_p, - struct tss_struct *tss) -{ - struct thread_struct *prev, *next; - - prev = &prev_p->thread, - next = &next_p->thread; - - if (test_tsk_thread_flag(next_p, TIF_DS_AREA_MSR) || - test_tsk_thread_flag(prev_p, TIF_DS_AREA_MSR)) - ds_switch_to(prev_p, next_p); - else if (next->debugctlmsr != prev->debugctlmsr) - update_debugctlmsr(next->debugctlmsr); - - if (test_tsk_thread_flag(next_p, TIF_DEBUG)) { - loaddebug(next, 0); - loaddebug(next, 1); - loaddebug(next, 2); - loaddebug(next, 3); - /* no 4 and 5 */ - loaddebug(next, 6); - loaddebug(next, 7); - } - - if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ - test_tsk_thread_flag(next_p, TIF_NOTSC)) { - /* prev and next are different */ - if (test_tsk_thread_flag(next_p, TIF_NOTSC)) - hard_disable_TSC(); - else - hard_enable_TSC(); - } - - if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { - /* - * Copy the relevant range of the IO bitmap. - * Normally this is 128 bytes or less: - */ - memcpy(tss->io_bitmap, next->io_bitmap_ptr, - max(prev->io_bitmap_max, next->io_bitmap_max)); - } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { - /* - * Clear any possible leftover bits: - */ - memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); - } -} - /* * switch_to(x,y) should switch tasks from x to y. * @@ -694,11 +527,6 @@ void set_personality_64bit(void) current->personality &= ~READ_IMPLIES_EXEC; } -asmlinkage long sys_fork(struct pt_regs *regs) -{ - return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL); -} - asmlinkage long sys_clone(unsigned long clone_flags, unsigned long newsp, void __user *parent_tid, void __user *child_tid, struct pt_regs *regs) @@ -708,22 +536,6 @@ sys_clone(unsigned long clone_flags, unsigned long newsp, return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); } -/* - * This is trivial, and on the face of it looks like it - * could equally well be done in user mode. - * - * Not so, for quite unobvious reasons - register pressure. - * In user mode vfork() cannot have a stack frame, and if - * done by calling the "clone()" system call directly, you - * do not have enough call-clobbered registers to hold all - * the information you need. - */ -asmlinkage long sys_vfork(struct pt_regs *regs) -{ - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0, - NULL, NULL); -} - unsigned long get_wchan(struct task_struct *p) { unsigned long stack; diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 3d9672e..fe9345c 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -21,6 +21,7 @@ #include <linux/audit.h> #include <linux/seccomp.h> #include <linux/signal.h> +#include <linux/ftrace.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -685,9 +686,8 @@ static int ptrace_bts_config(struct task_struct *child, if (!cfg.signal) return -EINVAL; - return -EOPNOTSUPP; - child->thread.bts_ovfl_signal = cfg.signal; + return -EOPNOTSUPP; } if ((cfg.flags & PTRACE_BTS_O_ALLOC) && @@ -1416,6 +1416,9 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs) tracehook_report_syscall_entry(regs)) ret = -1L; + if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) + ftrace_syscall_enter(regs); + if (unlikely(current->audit_context)) { if (IS_IA32) audit_syscall_entry(AUDIT_ARCH_I386, @@ -1439,6 +1442,9 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs) if (unlikely(current->audit_context)) audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax); + if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) + ftrace_syscall_exit(regs); + if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, 0); @@ -1456,6 +1462,6 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs) * system call instruction. */ if (test_thread_flag(TIF_SINGLESTEP) && - tracehook_consider_fatal_signal(current, SIGTRAP, SIG_DFL)) + tracehook_consider_fatal_signal(current, SIGTRAP)) send_sigtrap(current, regs, 0, TRAP_BRKPT); } diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 309949e..e95022e 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -74,8 +74,7 @@ static void ich_force_hpet_resume(void) if (!force_hpet_address) return; - if (rcba_base == NULL) - BUG(); + BUG_ON(rcba_base == NULL); /* read the Function Disable register, dword mode only */ val = readl(rcba_base + 0x3404); @@ -172,7 +171,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH8_4, ich_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH9_7, ich_force_enable_hpet); - +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x3a16, /* ICH10 */ + ich_force_enable_hpet); static struct pci_dev *cached_dev; diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 1cc18d4..2aef36d 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -216,6 +216,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq"), }, }, + { /* Handle problems with rebooting on Dell XPS710 */ + .callback = set_bios_reboot, + .ident = "Dell XPS710", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell XPS710"), + }, + }, { } }; diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index 2064d0a..4123553 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -17,7 +17,8 @@ #define PTR(x) (x << 2) -/* control_page + KEXEC_CONTROL_CODE_MAX_SIZE +/* + * control_page + KEXEC_CONTROL_CODE_MAX_SIZE * ~ control_page + PAGE_SIZE are used as data storage and stack for * jumping back */ @@ -76,8 +77,10 @@ relocate_kernel: movl %eax, CP_PA_SWAP_PAGE(%edi) movl %ebx, CP_PA_BACKUP_PAGES_MAP(%edi) - /* get physical address of control page now */ - /* this is impossible after page table switch */ + /* + * get physical address of control page now + * this is impossible after page table switch + */ movl PTR(PA_CONTROL_PAGE)(%ebp), %edi /* switch to new set of page tables */ @@ -97,7 +100,8 @@ identity_mapped: /* store the start address on the stack */ pushl %edx - /* Set cr0 to a known state: + /* + * Set cr0 to a known state: * - Paging disabled * - Alignment check disabled * - Write protect disabled @@ -113,7 +117,8 @@ identity_mapped: /* clear cr4 if applicable */ testl %ecx, %ecx jz 1f - /* Set cr4 to a known state: + /* + * Set cr4 to a known state: * Setting everything to zero seems safe. */ xorl %eax, %eax @@ -132,15 +137,18 @@ identity_mapped: call swap_pages addl $8, %esp - /* To be certain of avoiding problems with self-modifying code + /* + * To be certain of avoiding problems with self-modifying code * I need to execute a serializing instruction here. * So I flush the TLB, it's handy, and not processor dependent. */ xorl %eax, %eax movl %eax, %cr3 - /* set all of the registers to known values */ - /* leave %esp alone */ + /* + * set all of the registers to known values + * leave %esp alone + */ testl %esi, %esi jnz 1f diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index d32cfb2..4de8f5b 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -19,29 +19,77 @@ #define PTR(x) (x << 3) #define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) +/* + * control_page + KEXEC_CONTROL_CODE_MAX_SIZE + * ~ control_page + PAGE_SIZE are used as data storage and stack for + * jumping back + */ +#define DATA(offset) (KEXEC_CONTROL_CODE_MAX_SIZE+(offset)) + +/* Minimal CPU state */ +#define RSP DATA(0x0) +#define CR0 DATA(0x8) +#define CR3 DATA(0x10) +#define CR4 DATA(0x18) + +/* other data */ +#define CP_PA_TABLE_PAGE DATA(0x20) +#define CP_PA_SWAP_PAGE DATA(0x28) +#define CP_PA_BACKUP_PAGES_MAP DATA(0x30) + .text .align PAGE_SIZE .code64 .globl relocate_kernel relocate_kernel: - /* %rdi indirection_page + /* + * %rdi indirection_page * %rsi page_list * %rdx start address + * %rcx preserve_context */ + /* Save the CPU context, used for jumping back */ + pushq %rbx + pushq %rbp + pushq %r12 + pushq %r13 + pushq %r14 + pushq %r15 + pushf + + movq PTR(VA_CONTROL_PAGE)(%rsi), %r11 + movq %rsp, RSP(%r11) + movq %cr0, %rax + movq %rax, CR0(%r11) + movq %cr3, %rax + movq %rax, CR3(%r11) + movq %cr4, %rax + movq %rax, CR4(%r11) + /* zero out flags, and disable interrupts */ pushq $0 popfq - /* get physical address of control page now */ - /* this is impossible after page table switch */ + /* + * get physical address of control page now + * this is impossible after page table switch + */ movq PTR(PA_CONTROL_PAGE)(%rsi), %r8 /* get physical address of page table now too */ - movq PTR(PA_TABLE_PAGE)(%rsi), %rcx + movq PTR(PA_TABLE_PAGE)(%rsi), %r9 + + /* get physical address of swap page now */ + movq PTR(PA_SWAP_PAGE)(%rsi), %r10 + + /* save some information for jumping back */ + movq %r9, CP_PA_TABLE_PAGE(%r11) + movq %r10, CP_PA_SWAP_PAGE(%r11) + movq %rdi, CP_PA_BACKUP_PAGES_MAP(%r11) /* Switch to the identity mapped page tables */ - movq %rcx, %cr3 + movq %r9, %cr3 /* setup a new stack at the end of the physical control page */ lea PAGE_SIZE(%r8), %rsp @@ -55,7 +103,8 @@ identity_mapped: /* store the start address on the stack */ pushq %rdx - /* Set cr0 to a known state: + /* + * Set cr0 to a known state: * - Paging enabled * - Alignment check disabled * - Write protect disabled @@ -68,7 +117,8 @@ identity_mapped: orl $(X86_CR0_PG | X86_CR0_PE), %eax movq %rax, %cr0 - /* Set cr4 to a known state: + /* + * Set cr4 to a known state: * - physical address extension enabled */ movq $X86_CR4_PAE, %rax @@ -78,9 +128,87 @@ identity_mapped: 1: /* Flush the TLB (needed?) */ - movq %rcx, %cr3 + movq %r9, %cr3 + + movq %rcx, %r11 + call swap_pages + + /* + * To be certain of avoiding problems with self-modifying code + * I need to execute a serializing instruction here. + * So I flush the TLB by reloading %cr3 here, it's handy, + * and not processor dependent. + */ + movq %cr3, %rax + movq %rax, %cr3 + + /* + * set all of the registers to known values + * leave %rsp alone + */ + + testq %r11, %r11 + jnz 1f + xorq %rax, %rax + xorq %rbx, %rbx + xorq %rcx, %rcx + xorq %rdx, %rdx + xorq %rsi, %rsi + xorq %rdi, %rdi + xorq %rbp, %rbp + xorq %r8, %r8 + xorq %r9, %r9 + xorq %r10, %r9 + xorq %r11, %r11 + xorq %r12, %r12 + xorq %r13, %r13 + xorq %r14, %r14 + xorq %r15, %r15 + + ret + +1: + popq %rdx + leaq PAGE_SIZE(%r10), %rsp + call *%rdx + + /* get the re-entry point of the peer system */ + movq 0(%rsp), %rbp + call 1f +1: + popq %r8 + subq $(1b - relocate_kernel), %r8 + movq CP_PA_SWAP_PAGE(%r8), %r10 + movq CP_PA_BACKUP_PAGES_MAP(%r8), %rdi + movq CP_PA_TABLE_PAGE(%r8), %rax + movq %rax, %cr3 + lea PAGE_SIZE(%r8), %rsp + call swap_pages + movq $virtual_mapped, %rax + pushq %rax + ret + +virtual_mapped: + movq RSP(%r8), %rsp + movq CR4(%r8), %rax + movq %rax, %cr4 + movq CR3(%r8), %rax + movq CR0(%r8), %r8 + movq %rax, %cr3 + movq %r8, %cr0 + movq %rbp, %rax + + popf + popq %r15 + popq %r14 + popq %r13 + popq %r12 + popq %rbp + popq %rbx + ret /* Do the copies */ +swap_pages: movq %rdi, %rcx /* Put the page_list in %rcx */ xorq %rdi, %rdi xorq %rsi, %rsi @@ -112,36 +240,27 @@ identity_mapped: movq %rcx, %rsi /* For ever source page do a copy */ andq $0xfffffffffffff000, %rsi + movq %rdi, %rdx + movq %rsi, %rax + + movq %r10, %rdi movq $512, %rcx rep ; movsq - jmp 0b -3: - - /* To be certain of avoiding problems with self-modifying code - * I need to execute a serializing instruction here. - * So I flush the TLB by reloading %cr3 here, it's handy, - * and not processor dependent. - */ - movq %cr3, %rax - movq %rax, %cr3 - /* set all of the registers to known values */ - /* leave %rsp alone */ + movq %rax, %rdi + movq %rdx, %rsi + movq $512, %rcx + rep ; movsq - xorq %rax, %rax - xorq %rbx, %rbx - xorq %rcx, %rcx - xorq %rdx, %rdx - xorq %rsi, %rsi - xorq %rdi, %rdi - xorq %rbp, %rbp - xorq %r8, %r8 - xorq %r9, %r9 - xorq %r10, %r9 - xorq %r11, %r11 - xorq %r12, %r12 - xorq %r13, %r13 - xorq %r14, %r14 - xorq %r15, %r15 + movq %rdx, %rdi + movq %r10, %rsi + movq $512, %rcx + rep ; movsq + lea PAGE_SIZE(%rax), %rsi + jmp 0b +3: ret + + .globl kexec_control_code_size +.set kexec_control_code_size, . - relocate_kernel diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index dd6f2b7..5d465b2 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -1,14 +1,14 @@ /* * RTC related functions */ +#include <linux/platform_device.h> +#include <linux/mc146818rtc.h> #include <linux/acpi.h> #include <linux/bcd.h> -#include <linux/mc146818rtc.h> -#include <linux/platform_device.h> #include <linux/pnp.h> -#include <asm/time.h> #include <asm/vsyscall.h> +#include <asm/time.h> #ifdef CONFIG_X86_32 /* @@ -16,9 +16,9 @@ * register we are working with. It is required for NMI access to the * CMOS/RTC registers. See include/asm-i386/mc146818rtc.h for details. */ -volatile unsigned long cmos_lock = 0; +volatile unsigned long cmos_lock; EXPORT_SYMBOL(cmos_lock); -#endif +#endif /* CONFIG_X86_32 */ /* For two digit years assume time is always after that */ #define CMOS_YEARS_OFFS 2000 @@ -38,9 +38,9 @@ EXPORT_SYMBOL(rtc_lock); */ int mach_set_rtc_mmss(unsigned long nowtime) { - int retval = 0; int real_seconds, real_minutes, cmos_minutes; unsigned char save_control, save_freq_select; + int retval = 0; /* tell the clock it's being set */ save_control = CMOS_READ(RTC_CONTROL); @@ -72,8 +72,8 @@ int mach_set_rtc_mmss(unsigned long nowtime) real_seconds = bin2bcd(real_seconds); real_minutes = bin2bcd(real_minutes); } - CMOS_WRITE(real_seconds,RTC_SECONDS); - CMOS_WRITE(real_minutes,RTC_MINUTES); + CMOS_WRITE(real_seconds, RTC_SECONDS); + CMOS_WRITE(real_minutes, RTC_MINUTES); } else { printk(KERN_WARNING "set_rtc_mmss: can't update from %d to %d\n", @@ -151,6 +151,7 @@ unsigned char rtc_cmos_read(unsigned char addr) outb(addr, RTC_PORT(0)); val = inb(RTC_PORT(1)); lock_cmos_suffix(addr); + return val; } EXPORT_SYMBOL(rtc_cmos_read); @@ -166,8 +167,8 @@ EXPORT_SYMBOL(rtc_cmos_write); static int set_rtc_mmss(unsigned long nowtime) { - int retval; unsigned long flags; + int retval; spin_lock_irqsave(&rtc_lock, flags); retval = set_wallclock(nowtime); @@ -242,6 +243,7 @@ static __init int add_rtc_cmos(void) platform_device_register(&rtc_device); dev_info(&rtc_device.dev, "registered platform RTC device (no PNP device found)\n"); + return 0; } device_initcall(add_rtc_cmos); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 5b85759..b415843 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -112,8 +112,13 @@ #define ARCH_SETUP #endif +RESERVE_BRK(dmi_alloc, 65536); + unsigned int boot_cpu_id __read_mostly; +static __initdata unsigned long _brk_start = (unsigned long)__brk_base; +unsigned long _brk_end = (unsigned long)__brk_base; + #ifdef CONFIG_X86_64 int default_cpu_present_to_apicid(int mps_cpu) { @@ -158,12 +163,6 @@ static struct resource bss_resource = { #ifdef CONFIG_X86_32 -/* This value is set up by the early boot code to point to the value - immediately after the boot time page tables. It contains a *physical* - address, and must not be in the .bss segment! */ -unsigned long init_pg_tables_start __initdata = ~0UL; -unsigned long init_pg_tables_end __initdata = ~0UL; - static struct resource video_ram_resource = { .name = "Video RAM area", .start = 0xa0000, @@ -202,7 +201,9 @@ struct ist_info ist_info; #endif #else -struct cpuinfo_x86 boot_cpu_data __read_mostly; +struct cpuinfo_x86 boot_cpu_data __read_mostly = { + .x86_phys_bits = MAX_PHYSMEM_BITS, +}; EXPORT_SYMBOL(boot_cpu_data); #endif @@ -217,12 +218,6 @@ unsigned long mmu_cr4_features = X86_CR4_PAE; int bootloader_type; /* - * Early DMI memory - */ -int dmi_alloc_index; -char dmi_alloc_data[DMI_MAX_DATA]; - -/* * Setup options */ struct screen_info screen_info; @@ -267,6 +262,35 @@ static inline void copy_edd(void) } #endif +void * __init extend_brk(size_t size, size_t align) +{ + size_t mask = align - 1; + void *ret; + + BUG_ON(_brk_start == 0); + BUG_ON(align & mask); + + _brk_end = (_brk_end + mask) & ~mask; + BUG_ON((char *)(_brk_end + size) > __brk_limit); + + ret = (void *)_brk_end; + _brk_end += size; + + memset(ret, 0, size); + + return ret; +} + +static void __init reserve_brk(void) +{ + if (_brk_end > _brk_start) + reserve_early(__pa(_brk_start), __pa(_brk_end), "BRK"); + + /* Mark brk area as locked down and no longer taking any + new allocations */ + _brk_start = 0; +} + #ifdef CONFIG_BLK_DEV_INITRD #ifdef CONFIG_X86_32 @@ -600,19 +624,7 @@ static int __init setup_elfcorehdr(char *arg) early_param("elfcorehdr", setup_elfcorehdr); #endif -static int __init default_update_apic(void) -{ -#ifdef CONFIG_SMP - if (!apic->wakeup_cpu) - apic->wakeup_cpu = wakeup_secondary_cpu_via_init; -#endif - - return 0; -} - -static struct x86_quirks default_x86_quirks __initdata = { - .update_apic = default_update_apic, -}; +static struct x86_quirks default_x86_quirks __initdata; struct x86_quirks *x86_quirks __initdata = &default_x86_quirks; @@ -727,11 +739,7 @@ void __init setup_arch(char **cmdline_p) init_mm.start_code = (unsigned long) _text; init_mm.end_code = (unsigned long) _etext; init_mm.end_data = (unsigned long) _edata; -#ifdef CONFIG_X86_32 - init_mm.brk = init_pg_tables_end + PAGE_OFFSET; -#else - init_mm.brk = (unsigned long) &_end; -#endif + init_mm.brk = _brk_end; code_resource.start = virt_to_phys(_text); code_resource.end = virt_to_phys(_etext)-1; @@ -782,6 +790,9 @@ void __init setup_arch(char **cmdline_p) finish_e820_parsing(); + if (efi_enabled) + efi_init(); + dmi_scan_machine(); dmi_check_system(bad_bios_dmi_table); @@ -801,8 +812,6 @@ void __init setup_arch(char **cmdline_p) insert_resource(&iomem_resource, &data_resource); insert_resource(&iomem_resource, &bss_resource); - if (efi_enabled) - efi_init(); #ifdef CONFIG_X86_32 if (ppro_with_ram_bug()) { @@ -851,6 +860,8 @@ void __init setup_arch(char **cmdline_p) setup_bios_corruption_check(); #endif + reserve_brk(); + /* max_pfn_mapped is updated here */ max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT); max_pfn_mapped = max_low_pfn_mapped; @@ -875,9 +886,7 @@ void __init setup_arch(char **cmdline_p) reserve_initrd(); -#ifdef CONFIG_X86_64 vsmp_init(); -#endif io_delay_init(); @@ -1040,7 +1049,6 @@ void __init x86_quirk_trap_init(void) static struct irqaction irq0 = { .handler = timer_interrupt, .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, - .mask = CPU_MASK_NONE, .name = "timer" }; diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index d992e6c..3a97a4c 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -7,6 +7,7 @@ #include <linux/crash_dump.h> #include <linux/smp.h> #include <linux/topology.h> +#include <linux/pfn.h> #include <asm/sections.h> #include <asm/processor.h> #include <asm/setup.h> @@ -41,6 +42,295 @@ unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = { }; EXPORT_SYMBOL(__per_cpu_offset); +/* + * On x86_64 symbols referenced from code should be reachable using + * 32bit relocations. Reserve space for static percpu variables in + * modules so that they are always served from the first chunk which + * is located at the percpu segment base. On x86_32, anything can + * address anywhere. No need to reserve space in the first chunk. + */ +#ifdef CONFIG_X86_64 +#define PERCPU_FIRST_CHUNK_RESERVE PERCPU_MODULE_RESERVE +#else +#define PERCPU_FIRST_CHUNK_RESERVE 0 +#endif + +/** + * pcpu_need_numa - determine percpu allocation needs to consider NUMA + * + * If NUMA is not configured or there is only one NUMA node available, + * there is no reason to consider NUMA. This function determines + * whether percpu allocation should consider NUMA or not. + * + * RETURNS: + * true if NUMA should be considered; otherwise, false. + */ +static bool __init pcpu_need_numa(void) +{ +#ifdef CONFIG_NEED_MULTIPLE_NODES + pg_data_t *last = NULL; + unsigned int cpu; + + for_each_possible_cpu(cpu) { + int node = early_cpu_to_node(cpu); + + if (node_online(node) && NODE_DATA(node) && + last && last != NODE_DATA(node)) + return true; + + last = NODE_DATA(node); + } +#endif + return false; +} + +/** + * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu + * @cpu: cpu to allocate for + * @size: size allocation in bytes + * @align: alignment + * + * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper + * does the right thing for NUMA regardless of the current + * configuration. + * + * RETURNS: + * Pointer to the allocated area on success, NULL on failure. + */ +static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size, + unsigned long align) +{ + const unsigned long goal = __pa(MAX_DMA_ADDRESS); +#ifdef CONFIG_NEED_MULTIPLE_NODES + int node = early_cpu_to_node(cpu); + void *ptr; + + if (!node_online(node) || !NODE_DATA(node)) { + ptr = __alloc_bootmem_nopanic(size, align, goal); + pr_info("cpu %d has no node %d or node-local memory\n", + cpu, node); + pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n", + cpu, size, __pa(ptr)); + } else { + ptr = __alloc_bootmem_node_nopanic(NODE_DATA(node), + size, align, goal); + pr_debug("per cpu data for cpu%d %lu bytes on node%d at " + "%016lx\n", cpu, size, node, __pa(ptr)); + } + return ptr; +#else + return __alloc_bootmem_nopanic(size, align, goal); +#endif +} + +/* + * Remap allocator + * + * This allocator uses PMD page as unit. A PMD page is allocated for + * each cpu and each is remapped into vmalloc area using PMD mapping. + * As PMD page is quite large, only part of it is used for the first + * chunk. Unused part is returned to the bootmem allocator. + * + * So, the PMD pages are mapped twice - once to the physical mapping + * and to the vmalloc area for the first percpu chunk. The double + * mapping does add one more PMD TLB entry pressure but still is much + * better than only using 4k mappings while still being NUMA friendly. + */ +#ifdef CONFIG_NEED_MULTIPLE_NODES +static size_t pcpur_size __initdata; +static void **pcpur_ptrs __initdata; + +static struct page * __init pcpur_get_page(unsigned int cpu, int pageno) +{ + size_t off = (size_t)pageno << PAGE_SHIFT; + + if (off >= pcpur_size) + return NULL; + + return virt_to_page(pcpur_ptrs[cpu] + off); +} + +static ssize_t __init setup_pcpu_remap(size_t static_size) +{ + static struct vm_struct vm; + size_t ptrs_size, dyn_size; + unsigned int cpu; + ssize_t ret; + + /* + * If large page isn't supported, there's no benefit in doing + * this. Also, on non-NUMA, embedding is better. + */ + if (!cpu_has_pse || !pcpu_need_numa()) + return -EINVAL; + + /* + * Currently supports only single page. Supporting multiple + * pages won't be too difficult if it ever becomes necessary. + */ + pcpur_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE + + PERCPU_DYNAMIC_RESERVE); + if (pcpur_size > PMD_SIZE) { + pr_warning("PERCPU: static data is larger than large page, " + "can't use large page\n"); + return -EINVAL; + } + dyn_size = pcpur_size - static_size - PERCPU_FIRST_CHUNK_RESERVE; + + /* allocate pointer array and alloc large pages */ + ptrs_size = PFN_ALIGN(num_possible_cpus() * sizeof(pcpur_ptrs[0])); + pcpur_ptrs = alloc_bootmem(ptrs_size); + + for_each_possible_cpu(cpu) { + pcpur_ptrs[cpu] = pcpu_alloc_bootmem(cpu, PMD_SIZE, PMD_SIZE); + if (!pcpur_ptrs[cpu]) + goto enomem; + + /* + * Only use pcpur_size bytes and give back the rest. + * + * Ingo: The 2MB up-rounding bootmem is needed to make + * sure the partial 2MB page is still fully RAM - it's + * not well-specified to have a PAT-incompatible area + * (unmapped RAM, device memory, etc.) in that hole. + */ + free_bootmem(__pa(pcpur_ptrs[cpu] + pcpur_size), + PMD_SIZE - pcpur_size); + + memcpy(pcpur_ptrs[cpu], __per_cpu_load, static_size); + } + + /* allocate address and map */ + vm.flags = VM_ALLOC; + vm.size = num_possible_cpus() * PMD_SIZE; + vm_area_register_early(&vm, PMD_SIZE); + + for_each_possible_cpu(cpu) { + pmd_t *pmd; + + pmd = populate_extra_pmd((unsigned long)vm.addr + + cpu * PMD_SIZE); + set_pmd(pmd, pfn_pmd(page_to_pfn(virt_to_page(pcpur_ptrs[cpu])), + PAGE_KERNEL_LARGE)); + } + + /* we're ready, commit */ + pr_info("PERCPU: Remapped at %p with large pages, static data " + "%zu bytes\n", vm.addr, static_size); + + ret = pcpu_setup_first_chunk(pcpur_get_page, static_size, + PERCPU_FIRST_CHUNK_RESERVE, dyn_size, + PMD_SIZE, vm.addr, NULL); + goto out_free_ar; + +enomem: + for_each_possible_cpu(cpu) + if (pcpur_ptrs[cpu]) + free_bootmem(__pa(pcpur_ptrs[cpu]), PMD_SIZE); + ret = -ENOMEM; +out_free_ar: + free_bootmem(__pa(pcpur_ptrs), ptrs_size); + return ret; +} +#else +static ssize_t __init setup_pcpu_remap(size_t static_size) +{ + return -EINVAL; +} +#endif + +/* + * Embedding allocator + * + * The first chunk is sized to just contain the static area plus + * module and dynamic reserves and embedded into linear physical + * mapping so that it can use PMD mapping without additional TLB + * pressure. + */ +static ssize_t __init setup_pcpu_embed(size_t static_size) +{ + size_t reserve = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE; + + /* + * If large page isn't supported, there's no benefit in doing + * this. Also, embedding allocation doesn't play well with + * NUMA. + */ + if (!cpu_has_pse || pcpu_need_numa()) + return -EINVAL; + + return pcpu_embed_first_chunk(static_size, PERCPU_FIRST_CHUNK_RESERVE, + reserve - PERCPU_FIRST_CHUNK_RESERVE, -1); +} + +/* + * 4k page allocator + * + * This is the basic allocator. Static percpu area is allocated + * page-by-page and most of initialization is done by the generic + * setup function. + */ +static struct page **pcpu4k_pages __initdata; +static int pcpu4k_nr_static_pages __initdata; + +static struct page * __init pcpu4k_get_page(unsigned int cpu, int pageno) +{ + if (pageno < pcpu4k_nr_static_pages) + return pcpu4k_pages[cpu * pcpu4k_nr_static_pages + pageno]; + return NULL; +} + +static void __init pcpu4k_populate_pte(unsigned long addr) +{ + populate_extra_pte(addr); +} + +static ssize_t __init setup_pcpu_4k(size_t static_size) +{ + size_t pages_size; + unsigned int cpu; + int i, j; + ssize_t ret; + + pcpu4k_nr_static_pages = PFN_UP(static_size); + + /* unaligned allocations can't be freed, round up to page size */ + pages_size = PFN_ALIGN(pcpu4k_nr_static_pages * num_possible_cpus() + * sizeof(pcpu4k_pages[0])); + pcpu4k_pages = alloc_bootmem(pages_size); + + /* allocate and copy */ + j = 0; + for_each_possible_cpu(cpu) + for (i = 0; i < pcpu4k_nr_static_pages; i++) { + void *ptr; + + ptr = pcpu_alloc_bootmem(cpu, PAGE_SIZE, PAGE_SIZE); + if (!ptr) + goto enomem; + + memcpy(ptr, __per_cpu_load + i * PAGE_SIZE, PAGE_SIZE); + pcpu4k_pages[j++] = virt_to_page(ptr); + } + + /* we're ready, commit */ + pr_info("PERCPU: Allocated %d 4k pages, static data %zu bytes\n", + pcpu4k_nr_static_pages, static_size); + + ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size, + PERCPU_FIRST_CHUNK_RESERVE, -1, + -1, NULL, pcpu4k_populate_pte); + goto out_free_ar; + +enomem: + while (--j >= 0) + free_bootmem(__pa(page_address(pcpu4k_pages[j])), PAGE_SIZE); + ret = -ENOMEM; +out_free_ar: + free_bootmem(__pa(pcpu4k_pages), pages_size); + return ret; +} + static inline void setup_percpu_segment(int cpu) { #ifdef CONFIG_X86_32 @@ -61,38 +351,35 @@ static inline void setup_percpu_segment(int cpu) */ void __init setup_per_cpu_areas(void) { - ssize_t size; - char *ptr; - int cpu; - - /* Copy section for each CPU (we discard the original) */ - size = roundup(PERCPU_ENOUGH_ROOM, PAGE_SIZE); + size_t static_size = __per_cpu_end - __per_cpu_start; + unsigned int cpu; + unsigned long delta; + size_t pcpu_unit_size; + ssize_t ret; pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%d nr_node_ids:%d\n", NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids); - pr_info("PERCPU: Allocating %zd bytes of per cpu data\n", size); + /* + * Allocate percpu area. If PSE is supported, try to make use + * of large page mappings. Please read comments on top of + * each allocator for details. + */ + ret = setup_pcpu_remap(static_size); + if (ret < 0) + ret = setup_pcpu_embed(static_size); + if (ret < 0) + ret = setup_pcpu_4k(static_size); + if (ret < 0) + panic("cannot allocate static percpu area (%zu bytes, err=%zd)", + static_size, ret); - for_each_possible_cpu(cpu) { -#ifndef CONFIG_NEED_MULTIPLE_NODES - ptr = alloc_bootmem_pages(size); -#else - int node = early_cpu_to_node(cpu); - if (!node_online(node) || !NODE_DATA(node)) { - ptr = alloc_bootmem_pages(size); - pr_info("cpu %d has no node %d or node-local memory\n", - cpu, node); - pr_debug("per cpu data for cpu%d at %016lx\n", - cpu, __pa(ptr)); - } else { - ptr = alloc_bootmem_pages_node(NODE_DATA(node), size); - pr_debug("per cpu data for cpu%d on node%d at %016lx\n", - cpu, node, __pa(ptr)); - } -#endif + pcpu_unit_size = ret; - memcpy(ptr, __per_cpu_load, __per_cpu_end - __per_cpu_start); - per_cpu_offset(cpu) = ptr - __per_cpu_start; + /* alrighty, percpu areas up and running */ + delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; + for_each_possible_cpu(cpu) { + per_cpu_offset(cpu) = delta + cpu * pcpu_unit_size; per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu); per_cpu(cpu_number, cpu) = cpu; setup_percpu_segment(cpu); @@ -125,8 +412,6 @@ void __init setup_per_cpu_areas(void) */ if (cpu == boot_cpu_id) switch_to_new_gdt(cpu); - - DBG("PERCPU: cpu %4d %p\n", cpu, ptr); } /* indicate the early static arrays will soon be gone */ diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 4d34410..611615a 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -187,6 +187,77 @@ setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, /* * Set up a signal frame. */ + +/* + * Determine which stack to use.. + */ +static unsigned long align_sigframe(unsigned long sp) +{ +#ifdef CONFIG_X86_32 + /* + * Align the stack pointer according to the i386 ABI, + * i.e. so that on function entry ((sp + 4) & 15) == 0. + */ + sp = ((sp + 4) & -16ul) - 4; +#else /* !CONFIG_X86_32 */ + sp = round_down(sp, 16) - 8; +#endif + return sp; +} + +static inline void __user * +get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, + void __user **fpstate) +{ + /* Default to using normal stack */ + unsigned long sp = regs->sp; + int onsigstack = on_sig_stack(sp); + +#ifdef CONFIG_X86_64 + /* redzone */ + sp -= 128; +#endif /* CONFIG_X86_64 */ + + if (!onsigstack) { + /* This is the X/Open sanctioned signal stack switching. */ + if (ka->sa.sa_flags & SA_ONSTACK) { + if (current->sas_ss_size) + sp = current->sas_ss_sp + current->sas_ss_size; + } else { +#ifdef CONFIG_X86_32 + /* This is the legacy signal stack switching. */ + if ((regs->ss & 0xffff) != __USER_DS && + !(ka->sa.sa_flags & SA_RESTORER) && + ka->sa.sa_restorer) + sp = (unsigned long) ka->sa.sa_restorer; +#endif /* CONFIG_X86_32 */ + } + } + + if (used_math()) { + sp -= sig_xstate_size; +#ifdef CONFIG_X86_64 + sp = round_down(sp, 64); +#endif /* CONFIG_X86_64 */ + *fpstate = (void __user *)sp; + } + + sp = align_sigframe(sp - frame_size); + + /* + * If we are on the alternate signal stack and would overflow it, don't. + * Return an always-bogus address instead so we will die with SIGSEGV. + */ + if (onsigstack && !likely(on_sig_stack(sp))) + return (void __user *)-1L; + + /* save i387 state */ + if (used_math() && save_i387_xstate(*fpstate) < 0) + return (void __user *)-1L; + + return (void __user *)sp; +} + #ifdef CONFIG_X86_32 static const struct { u16 poplmovl; @@ -210,54 +281,6 @@ static const struct { 0 }; -/* - * Determine which stack to use.. - */ -static inline void __user * -get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, - void **fpstate) -{ - unsigned long sp; - - /* Default to using normal stack */ - sp = regs->sp; - - /* - * If we are on the alternate signal stack and would overflow it, don't. - * Return an always-bogus address instead so we will die with SIGSEGV. - */ - if (on_sig_stack(sp) && !likely(on_sig_stack(sp - frame_size))) - return (void __user *) -1L; - - /* This is the X/Open sanctioned signal stack switching. */ - if (ka->sa.sa_flags & SA_ONSTACK) { - if (sas_ss_flags(sp) == 0) - sp = current->sas_ss_sp + current->sas_ss_size; - } else { - /* This is the legacy signal stack switching. */ - if ((regs->ss & 0xffff) != __USER_DS && - !(ka->sa.sa_flags & SA_RESTORER) && - ka->sa.sa_restorer) - sp = (unsigned long) ka->sa.sa_restorer; - } - - if (used_math()) { - sp = sp - sig_xstate_size; - *fpstate = (struct _fpstate *) sp; - if (save_i387_xstate(*fpstate) < 0) - return (void __user *)-1L; - } - - sp -= frame_size; - /* - * Align the stack pointer according to the i386 ABI, - * i.e. so that on function entry ((sp + 4) & 15) == 0. - */ - sp = ((sp + 4) & -16ul) - 4; - - return (void __user *) sp; -} - static int __setup_frame(int sig, struct k_sigaction *ka, sigset_t *set, struct pt_regs *regs) @@ -388,24 +411,6 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, return 0; } #else /* !CONFIG_X86_32 */ -/* - * Determine which stack to use.. - */ -static void __user * -get_stack(struct k_sigaction *ka, unsigned long sp, unsigned long size) -{ - /* Default to using normal stack - redzone*/ - sp -= 128; - - /* This is the X/Open sanctioned signal stack switching. */ - if (ka->sa.sa_flags & SA_ONSTACK) { - if (sas_ss_flags(sp) == 0) - sp = current->sas_ss_sp + current->sas_ss_size; - } - - return (void __user *)round_down(sp - size, 64); -} - static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, struct pt_regs *regs) { @@ -414,15 +419,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, int err = 0; struct task_struct *me = current; - if (used_math()) { - fp = get_stack(ka, regs->sp, sig_xstate_size); - frame = (void __user *)round_down( - (unsigned long)fp - sizeof(struct rt_sigframe), 16) - 8; - - if (save_i387_xstate(fp) < 0) - return -EFAULT; - } else - frame = get_stack(ka, regs->sp, sizeof(struct rt_sigframe)) - 8; + frame = get_sigframe(ka, regs, sizeof(struct rt_sigframe), &fp); if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) return -EFAULT; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9ce6663..58d24ef 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -101,29 +101,20 @@ EXPORT_SYMBOL(smp_num_siblings); DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID; /* representing HT siblings of each logical CPU */ -DEFINE_PER_CPU(cpumask_t, cpu_sibling_map); +DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map); EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); /* representing HT and core siblings of each logical CPU */ -DEFINE_PER_CPU(cpumask_t, cpu_core_map); +DEFINE_PER_CPU(cpumask_var_t, cpu_core_map); EXPORT_PER_CPU_SYMBOL(cpu_core_map); /* Per CPU bogomips and other parameters */ DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); -static atomic_t init_deasserted; - - -/* Set if we find a B stepping CPU */ -static int __cpuinitdata smp_b_stepping; +atomic_t init_deasserted; #if defined(CONFIG_NUMA) && defined(CONFIG_X86_32) - -/* which logical CPUs are on which nodes */ -cpumask_t node_to_cpumask_map[MAX_NUMNODES] __read_mostly = - { [0 ... MAX_NUMNODES-1] = CPU_MASK_NONE }; -EXPORT_SYMBOL(node_to_cpumask_map); /* which node each logical CPU is on */ int cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 }; EXPORT_SYMBOL(cpu_to_node_map); @@ -132,7 +123,7 @@ EXPORT_SYMBOL(cpu_to_node_map); static void map_cpu_to_node(int cpu, int node) { printk(KERN_INFO "Mapping cpu %d to node %d\n", cpu, node); - cpumask_set_cpu(cpu, &node_to_cpumask_map[node]); + cpumask_set_cpu(cpu, node_to_cpumask_map[node]); cpu_to_node_map[cpu] = node; } @@ -143,7 +134,7 @@ static void unmap_cpu_to_node(int cpu) printk(KERN_INFO "Unmapping cpu %d from all nodes\n", cpu); for (node = 0; node < MAX_NUMNODES; node++) - cpumask_clear_cpu(cpu, &node_to_cpumask_map[node]); + cpumask_clear_cpu(cpu, node_to_cpumask_map[node]); cpu_to_node_map[cpu] = 0; } #else /* !(CONFIG_NUMA && CONFIG_X86_32) */ @@ -271,8 +262,6 @@ static void __cpuinit smp_callin(void) cpumask_set_cpu(cpuid, cpu_callin_mask); } -static int __cpuinitdata unsafe_smp; - /* * Activate a secondary processor. */ @@ -307,7 +296,7 @@ notrace static void __cpuinit start_secondary(void *unused) __flush_tlb_all(); #endif - /* This must be done before setting cpu_online_map */ + /* This must be done before setting cpu_online_mask */ set_cpu_sibling_map(raw_smp_processor_id()); wmb(); @@ -340,75 +329,22 @@ notrace static void __cpuinit start_secondary(void *unused) cpu_idle(); } -static void __cpuinit smp_apply_quirks(struct cpuinfo_x86 *c) +#ifdef CONFIG_CPUMASK_OFFSTACK +/* In this case, llc_shared_map is a pointer to a cpumask. */ +static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst, + const struct cpuinfo_x86 *src) { - /* - * Mask B, Pentium, but not Pentium MMX - */ - if (c->x86_vendor == X86_VENDOR_INTEL && - c->x86 == 5 && - c->x86_mask >= 1 && c->x86_mask <= 4 && - c->x86_model <= 3) - /* - * Remember we have B step Pentia with bugs - */ - smp_b_stepping = 1; - - /* - * Certain Athlons might work (for various values of 'work') in SMP - * but they are not certified as MP capable. - */ - if ((c->x86_vendor == X86_VENDOR_AMD) && (c->x86 == 6)) { - - if (num_possible_cpus() == 1) - goto valid_k7; - - /* Athlon 660/661 is valid. */ - if ((c->x86_model == 6) && ((c->x86_mask == 0) || - (c->x86_mask == 1))) - goto valid_k7; - - /* Duron 670 is valid */ - if ((c->x86_model == 7) && (c->x86_mask == 0)) - goto valid_k7; - - /* - * Athlon 662, Duron 671, and Athlon >model 7 have capability - * bit. It's worth noting that the A5 stepping (662) of some - * Athlon XP's have the MP bit set. - * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for - * more. - */ - if (((c->x86_model == 6) && (c->x86_mask >= 2)) || - ((c->x86_model == 7) && (c->x86_mask >= 1)) || - (c->x86_model > 7)) - if (cpu_has_mp) - goto valid_k7; - - /* If we get here, not a certified SMP capable AMD system. */ - unsafe_smp = 1; - } - -valid_k7: - ; + struct cpumask *llc = dst->llc_shared_map; + *dst = *src; + dst->llc_shared_map = llc; } - -static void __cpuinit smp_checks(void) +#else +static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst, + const struct cpuinfo_x86 *src) { - if (smp_b_stepping) - printk(KERN_WARNING "WARNING: SMP operation may be unreliable" - "with B stepping processors.\n"); - - /* - * Don't taint if we are running SMP kernel on a single non-MP - * approved Athlon - */ - if (unsafe_smp && num_online_cpus() > 1) { - printk(KERN_INFO "WARNING: This combination of AMD" - "processors is not suitable for SMP.\n"); - add_taint(TAINT_UNSAFE_SMP); - } + *dst = *src; } +#endif /* CONFIG_CPUMASK_OFFSTACK */ /* * The bootstrap kernel entry code has set these up. Save them for @@ -419,11 +355,10 @@ void __cpuinit smp_store_cpu_info(int id) { struct cpuinfo_x86 *c = &cpu_data(id); - *c = boot_cpu_data; + copy_cpuinfo_x86(c, &boot_cpu_data); c->cpu_index = id; if (id != 0) identify_secondary_cpu(c); - smp_apply_quirks(c); } @@ -444,15 +379,15 @@ void __cpuinit set_cpu_sibling_map(int cpu) cpumask_set_cpu(cpu, cpu_sibling_mask(i)); cpumask_set_cpu(i, cpu_core_mask(cpu)); cpumask_set_cpu(cpu, cpu_core_mask(i)); - cpumask_set_cpu(i, &c->llc_shared_map); - cpumask_set_cpu(cpu, &o->llc_shared_map); + cpumask_set_cpu(i, c->llc_shared_map); + cpumask_set_cpu(cpu, o->llc_shared_map); } } } else { cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); } - cpumask_set_cpu(cpu, &c->llc_shared_map); + cpumask_set_cpu(cpu, c->llc_shared_map); if (current_cpu_data.x86_max_cores == 1) { cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu)); @@ -463,8 +398,8 @@ void __cpuinit set_cpu_sibling_map(int cpu) for_each_cpu(i, cpu_sibling_setup_mask) { if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { - cpumask_set_cpu(i, &c->llc_shared_map); - cpumask_set_cpu(cpu, &cpu_data(i).llc_shared_map); + cpumask_set_cpu(i, c->llc_shared_map); + cpumask_set_cpu(cpu, cpu_data(i).llc_shared_map); } if (c->phys_proc_id == cpu_data(i).phys_proc_id) { cpumask_set_cpu(i, cpu_core_mask(cpu)); @@ -502,12 +437,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu) if (sched_mc_power_savings || sched_smt_power_savings) return cpu_core_mask(cpu); else - return &c->llc_shared_map; -} - -cpumask_t cpu_coregroup_map(int cpu) -{ - return *cpu_coregroup_mask(cpu); + return c->llc_shared_map; } static void impress_friends(void) @@ -614,12 +544,6 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) unsigned long send_status, accept_status = 0; int maxlvt, num_starts, j; - if (get_uv_system_type() == UV_NON_UNIQUE_APIC) { - send_status = uv_wakeup_secondary(phys_apicid, start_eip); - atomic_set(&init_deasserted, 1); - return send_status; - } - maxlvt = lapic_get_maxlvt(); /* @@ -748,7 +672,8 @@ static void __cpuinit do_fork_idle(struct work_struct *work) /* * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad * (ie clustered apic addressing mode), this is a LOGICAL apic ID. - * Returns zero if CPU booted OK, else error code from ->wakeup_cpu. + * Returns zero if CPU booted OK, else error code from + * ->wakeup_secondary_cpu. */ static int __cpuinit do_boot_cpu(int apicid, int cpu) { @@ -835,9 +760,13 @@ do_rest: } /* - * Starting actual IPI sequence... + * Kick the secondary CPU. Use the method in the APIC driver + * if it's defined - or use an INIT boot APIC message otherwise: */ - boot_error = apic->wakeup_cpu(apicid, start_ip); + if (apic->wakeup_secondary_cpu) + boot_error = apic->wakeup_secondary_cpu(apicid, start_ip); + else + boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip); if (!boot_error) { /* @@ -975,9 +904,8 @@ int __cpuinit native_cpu_up(unsigned int cpu) */ static __init void disable_smp(void) { - /* use the read/write pointers to the present and possible maps */ - cpumask_copy(&cpu_present_map, cpumask_of(0)); - cpumask_copy(&cpu_possible_map, cpumask_of(0)); + init_cpu_present(cpumask_of(0)); + init_cpu_possible(cpumask_of(0)); smpboot_clear_io_apic_irqs(); if (smp_found_config) @@ -1109,6 +1037,8 @@ static void __init smp_cpu_index_default(void) */ void __init native_smp_prepare_cpus(unsigned int max_cpus) { + unsigned int i; + preempt_disable(); smp_cpu_index_default(); current_cpu_data = boot_cpu_data; @@ -1122,6 +1052,14 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) boot_cpu_logical_apicid = logical_smp_processor_id(); #endif current_thread_info()->cpu = 0; /* needed? */ + for_each_possible_cpu(i) { + alloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL); + alloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL); + alloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL); + cpumask_clear(per_cpu(cpu_core_map, i)); + cpumask_clear(per_cpu(cpu_sibling_map, i)); + cpumask_clear(cpu_data(i).llc_shared_map); + } set_cpu_sibling_map(0); enable_IR_x2apic(); @@ -1194,7 +1132,6 @@ void __init native_smp_cpus_done(unsigned int max_cpus) pr_debug("Boot done.\n"); impress_friends(); - smp_checks(); #ifdef CONFIG_X86_IO_APIC setup_ioapic_dest(); #endif @@ -1211,11 +1148,11 @@ early_param("possible_cpus", _setup_possible_cpus); /* - * cpu_possible_map should be static, it cannot change as cpu's + * cpu_possible_mask should be static, it cannot change as cpu's * are onlined, or offlined. The reason is per-cpu data-structures * are allocated by some modules at init time, and dont expect to * do this dynamically on cpu arrival/departure. - * cpu_present_map on the other hand can change dynamically. + * cpu_present_mask on the other hand can change dynamically. * In case when cpu_hotplug is not compiled, then we resort to current * behaviour, which is cpu_possible == cpu_present. * - Ashok Raj diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index b7607c4..c3ebbb9 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -333,3 +333,5 @@ ENTRY(sys_call_table) .long sys_pipe2 .long sys_inotify_init1 .long sys_perf_counter_open + .long sys_preadv + .long sys_pwritev diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c index 241ec39..5ba343e 100644 --- a/arch/x86/kernel/time_64.c +++ b/arch/x86/kernel/time_64.c @@ -116,7 +116,6 @@ unsigned long __init calibrate_cpu(void) static struct irqaction irq0 = { .handler = timer_interrupt, .flags = IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING | IRQF_TIMER, - .mask = CPU_MASK_NONE, .name = "timer" }; @@ -125,7 +124,6 @@ void __init hpet_time_init(void) if (!hpet_enable()) setup_pit_timer(); - irq0.mask = cpumask_of_cpu(0); setup_irq(0, &irq0); } diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index f04549a..deb5ebb 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -275,6 +275,8 @@ const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade, return NULL; } +static DEFINE_PER_CPU(cpumask_var_t, uv_flush_tlb_mask); + /** * uv_flush_tlb_others - globally purge translation cache of a virtual * address or all TLB's @@ -304,8 +306,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long va, unsigned int cpu) { - static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask); - struct cpumask *flush_mask = &__get_cpu_var(flush_tlb_mask); + struct cpumask *flush_mask = __get_cpu_var(uv_flush_tlb_mask); int i; int bit; int blade; @@ -314,8 +315,6 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, int locals = 0; struct bau_desc *bau_desc; - WARN_ON(!in_atomic()); - cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu)); uv_cpu = uv_blade_processor_id(); @@ -752,16 +751,21 @@ static int __init uv_bau_init(void) int node; int nblades; int last_blade; - int cur_cpu = 0; + int cur_cpu; if (!is_uv_system()) return 0; + for_each_possible_cpu(cur_cpu) + alloc_cpumask_var_node(&per_cpu(uv_flush_tlb_mask, cur_cpu), + GFP_KERNEL, cpu_to_node(cur_cpu)); + uv_bau_retry_limit = 1; uv_nshift = uv_hub_info->n_val; uv_mmask = (1UL << uv_hub_info->n_val) - 1; nblades = 0; last_blade = -1; + cur_cpu = 0; for_each_online_node(node) { blade = uv_node_to_blade_id(node); if (blade == last_blade) diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 0fcc95a..7e45159 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -25,10 +25,10 @@ * * Send feedback to <colpatch@us.ibm.com> */ -#include <linux/init.h> -#include <linux/smp.h> #include <linux/nodemask.h> #include <linux/mmzone.h> +#include <linux/init.h> +#include <linux/smp.h> #include <asm/cpu.h> static DEFINE_PER_CPU(struct x86_cpu, cpu_devices); @@ -47,6 +47,7 @@ int __ref arch_register_cpu(int num) */ if (num) per_cpu(cpu_devices, num).cpu.hotpluggable = 1; + return register_cpu(&per_cpu(cpu_devices, num).cpu, num); } EXPORT_SYMBOL(arch_register_cpu); @@ -56,12 +57,13 @@ void arch_unregister_cpu(int num) unregister_cpu(&per_cpu(cpu_devices, num).cpu); } EXPORT_SYMBOL(arch_unregister_cpu); -#else +#else /* CONFIG_HOTPLUG_CPU */ + static int __init arch_register_cpu(int num) { return register_cpu(&per_cpu(cpu_devices, num).cpu, num); } -#endif /*CONFIG_HOTPLUG_CPU*/ +#endif /* CONFIG_HOTPLUG_CPU */ static int __init topology_init(void) { @@ -70,11 +72,11 @@ static int __init topology_init(void) #ifdef CONFIG_NUMA for_each_online_node(i) register_one_node(i); -#endif /* CONFIG_NUMA */ +#endif for_each_present_cpu(i) arch_register_cpu(i); + return 0; } - subsys_initcall(topology_init); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 1dba866..2cc162e 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -118,47 +118,6 @@ die_if_kernel(const char *str, struct pt_regs *regs, long err) if (!user_mode_vm(regs)) die(str, regs, err); } - -/* - * Perform the lazy TSS's I/O bitmap copy. If the TSS has an - * invalid offset set (the LAZY one) and the faulting thread has - * a valid I/O bitmap pointer, we copy the I/O bitmap in the TSS, - * we set the offset field correctly and return 1. - */ -static int lazy_iobitmap_copy(void) -{ - struct thread_struct *thread; - struct tss_struct *tss; - int cpu; - - cpu = get_cpu(); - tss = &per_cpu(init_tss, cpu); - thread = ¤t->thread; - - if (tss->x86_tss.io_bitmap_base == INVALID_IO_BITMAP_OFFSET_LAZY && - thread->io_bitmap_ptr) { - memcpy(tss->io_bitmap, thread->io_bitmap_ptr, - thread->io_bitmap_max); - /* - * If the previously set map was extending to higher ports - * than the current one, pad extra space with 0xff (no access). - */ - if (thread->io_bitmap_max < tss->io_bitmap_max) { - memset((char *) tss->io_bitmap + - thread->io_bitmap_max, 0xff, - tss->io_bitmap_max - thread->io_bitmap_max); - } - tss->io_bitmap_max = thread->io_bitmap_max; - tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; - tss->io_bitmap_owner = thread; - put_cpu(); - - return 1; - } - put_cpu(); - - return 0; -} #endif static void __kprobes @@ -309,11 +268,6 @@ do_general_protection(struct pt_regs *regs, long error_code) conditional_sti(regs); #ifdef CONFIG_X86_32 - if (lazy_iobitmap_copy()) { - /* restart the faulting instruction */ - return; - } - if (regs->flags & X86_VM_MASK) goto gp_in_vm86; #endif diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 83d53ce..7a567eb 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -17,20 +17,21 @@ #include <asm/delay.h> #include <asm/hypervisor.h> -unsigned int cpu_khz; /* TSC clocks / usec, not used here */ +unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); -unsigned int tsc_khz; + +unsigned int __read_mostly tsc_khz; EXPORT_SYMBOL(tsc_khz); /* * TSC can be unstable due to cpufreq or due to unsynced TSCs */ -static int tsc_unstable; +static int __read_mostly tsc_unstable; /* native_sched_clock() is called before tsc_init(), so we must start with the TSC soft disabled to prevent erroneous rdtsc usage on !cpu_has_tsc processors */ -static int tsc_disabled = -1; +static int __read_mostly tsc_disabled = -1; static int tsc_clocksource_reliable; /* @@ -273,30 +274,43 @@ static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin) * use the TSC value at the transitions to calculate a pretty * good value for the TSC frequencty. */ -static inline int pit_expect_msb(unsigned char val) +static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap) { - int count = 0; + int count; + u64 tsc = 0; for (count = 0; count < 50000; count++) { /* Ignore LSB */ inb(0x42); if (inb(0x42) != val) break; + tsc = get_cycles(); } - return count > 50; + *deltap = get_cycles() - tsc; + *tscp = tsc; + + /* + * We require _some_ success, but the quality control + * will be based on the error terms on the TSC values. + */ + return count > 5; } /* - * How many MSB values do we want to see? We aim for a - * 15ms calibration, which assuming a 2us counter read - * error should give us roughly 150 ppm precision for - * the calibration. + * How many MSB values do we want to see? We aim for + * a maximum error rate of 500ppm (in practice the + * real error is much smaller), but refuse to spend + * more than 25ms on it. */ -#define QUICK_PIT_MS 15 -#define QUICK_PIT_ITERATIONS (QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256) +#define MAX_QUICK_PIT_MS 25 +#define MAX_QUICK_PIT_ITERATIONS (MAX_QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256) static unsigned long quick_pit_calibrate(void) { + int i; + u64 tsc, delta; + unsigned long d1, d2; + /* Set the Gate high, disable speaker */ outb((inb(0x61) & ~0x02) | 0x01, 0x61); @@ -315,45 +329,52 @@ static unsigned long quick_pit_calibrate(void) outb(0xff, 0x42); outb(0xff, 0x42); - if (pit_expect_msb(0xff)) { - int i; - u64 t1, t2, delta; - unsigned char expect = 0xfe; - - t1 = get_cycles(); - for (i = 0; i < QUICK_PIT_ITERATIONS; i++, expect--) { - if (!pit_expect_msb(expect)) - goto failed; + /* + * The PIT starts counting at the next edge, so we + * need to delay for a microsecond. The easiest way + * to do that is to just read back the 16-bit counter + * once from the PIT. + */ + inb(0x42); + inb(0x42); + + if (pit_expect_msb(0xff, &tsc, &d1)) { + for (i = 1; i <= MAX_QUICK_PIT_ITERATIONS; i++) { + if (!pit_expect_msb(0xff-i, &delta, &d2)) + break; + + /* + * Iterate until the error is less than 500 ppm + */ + delta -= tsc; + if (d1+d2 < delta >> 11) + goto success; } - t2 = get_cycles(); - - /* - * Make sure we can rely on the second TSC timestamp: - */ - if (!pit_expect_msb(expect)) - goto failed; - - /* - * Ok, if we get here, then we've seen the - * MSB of the PIT decrement QUICK_PIT_ITERATIONS - * times, and each MSB had many hits, so we never - * had any sudden jumps. - * - * As a result, we can depend on there not being - * any odd delays anywhere, and the TSC reads are - * reliable. - * - * kHz = ticks / time-in-seconds / 1000; - * kHz = (t2 - t1) / (QPI * 256 / PIT_TICK_RATE) / 1000 - * kHz = ((t2 - t1) * PIT_TICK_RATE) / (QPI * 256 * 1000) - */ - delta = (t2 - t1)*PIT_TICK_RATE; - do_div(delta, QUICK_PIT_ITERATIONS*256*1000); - printk("Fast TSC calibration using PIT\n"); - return delta; } -failed: + printk("Fast TSC calibration failed\n"); return 0; + +success: + /* + * Ok, if we get here, then we've seen the + * MSB of the PIT decrement 'i' times, and the + * error has shrunk to less than 500 ppm. + * + * As a result, we can depend on there not being + * any odd delays anywhere, and the TSC reads are + * reliable (within the error). We also adjust the + * delta to the middle of the error bars, just + * because it looks nicer. + * + * kHz = ticks / time-in-seconds / 1000; + * kHz = (t2 - t1) / (I * 256 / PIT_TICK_RATE) / 1000 + * kHz = ((t2 - t1) * PIT_TICK_RATE) / (I * 256 * 1000) + */ + delta += (long)(d2 - d1)/2; + delta *= PIT_TICK_RATE; + do_div(delta, i*256*1000); + printk("Fast TSC calibration using PIT\n"); + return delta; } /** @@ -523,8 +544,6 @@ unsigned long native_calibrate_tsc(void) return tsc_pit_min; } -#ifdef CONFIG_X86_32 -/* Only called from the Powernow K7 cpu freq driver */ int recalibrate_cpu_khz(void) { #ifndef CONFIG_SMP @@ -546,7 +565,6 @@ int recalibrate_cpu_khz(void) EXPORT_SYMBOL(recalibrate_cpu_khz); -#endif /* CONFIG_X86_32 */ /* Accelerators for sched_clock() * convert from cycles(64bits) => nanoseconds (64bits) diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c new file mode 100644 index 0000000..2ffb6c5 --- /dev/null +++ b/arch/x86/kernel/uv_time.c @@ -0,0 +1,393 @@ +/* + * SGI RTC clock/timer routines. + * + * 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) 2009 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) Dimitri Sivanich + */ +#include <linux/clockchips.h> + +#include <asm/uv/uv_mmrs.h> +#include <asm/uv/uv_hub.h> +#include <asm/uv/bios.h> +#include <asm/uv/uv.h> +#include <asm/apic.h> +#include <asm/cpu.h> + +#define RTC_NAME "sgi_rtc" + +static cycle_t uv_read_rtc(void); +static int uv_rtc_next_event(unsigned long, struct clock_event_device *); +static void uv_rtc_timer_setup(enum clock_event_mode, + struct clock_event_device *); + +static struct clocksource clocksource_uv = { + .name = RTC_NAME, + .rating = 400, + .read = uv_read_rtc, + .mask = (cycle_t)UVH_RTC_REAL_TIME_CLOCK_MASK, + .shift = 10, + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; + +static struct clock_event_device clock_event_device_uv = { + .name = RTC_NAME, + .features = CLOCK_EVT_FEAT_ONESHOT, + .shift = 20, + .rating = 400, + .irq = -1, + .set_next_event = uv_rtc_next_event, + .set_mode = uv_rtc_timer_setup, + .event_handler = NULL, +}; + +static DEFINE_PER_CPU(struct clock_event_device, cpu_ced); + +/* There is one of these allocated per node */ +struct uv_rtc_timer_head { + spinlock_t lock; + /* next cpu waiting for timer, local node relative: */ + int next_cpu; + /* number of cpus on this node: */ + int ncpus; + struct { + int lcpu; /* systemwide logical cpu number */ + u64 expires; /* next timer expiration for this cpu */ + } cpu[1]; +}; + +/* + * Access to uv_rtc_timer_head via blade id. + */ +static struct uv_rtc_timer_head **blade_info __read_mostly; + +static int uv_rtc_enable; + +/* + * Hardware interface routines + */ + +/* Send IPIs to another node */ +static void uv_rtc_send_IPI(int cpu) +{ + unsigned long apicid, val; + int pnode; + + apicid = cpu_physical_id(cpu); + pnode = uv_apicid_to_pnode(apicid); + val = (1UL << UVH_IPI_INT_SEND_SHFT) | + (apicid << UVH_IPI_INT_APIC_ID_SHFT) | + (GENERIC_INTERRUPT_VECTOR << UVH_IPI_INT_VECTOR_SHFT); + + uv_write_global_mmr64(pnode, UVH_IPI_INT, val); +} + +/* Check for an RTC interrupt pending */ +static int uv_intr_pending(int pnode) +{ + return uv_read_global_mmr64(pnode, UVH_EVENT_OCCURRED0) & + UVH_EVENT_OCCURRED0_RTC1_MASK; +} + +/* Setup interrupt and return non-zero if early expiration occurred. */ +static int uv_setup_intr(int cpu, u64 expires) +{ + u64 val; + int pnode = uv_cpu_to_pnode(cpu); + + uv_write_global_mmr64(pnode, UVH_RTC1_INT_CONFIG, + UVH_RTC1_INT_CONFIG_M_MASK); + uv_write_global_mmr64(pnode, UVH_INT_CMPB, -1L); + + uv_write_global_mmr64(pnode, UVH_EVENT_OCCURRED0_ALIAS, + UVH_EVENT_OCCURRED0_RTC1_MASK); + + val = (GENERIC_INTERRUPT_VECTOR << UVH_RTC1_INT_CONFIG_VECTOR_SHFT) | + ((u64)cpu_physical_id(cpu) << UVH_RTC1_INT_CONFIG_APIC_ID_SHFT); + + /* Set configuration */ + uv_write_global_mmr64(pnode, UVH_RTC1_INT_CONFIG, val); + /* Initialize comparator value */ + uv_write_global_mmr64(pnode, UVH_INT_CMPB, expires); + + return (expires < uv_read_rtc() && !uv_intr_pending(pnode)); +} + +/* + * Per-cpu timer tracking routines + */ + +static __init void uv_rtc_deallocate_timers(void) +{ + int bid; + + for_each_possible_blade(bid) { + kfree(blade_info[bid]); + } + kfree(blade_info); +} + +/* Allocate per-node list of cpu timer expiration times. */ +static __init int uv_rtc_allocate_timers(void) +{ + int cpu; + + blade_info = kmalloc(uv_possible_blades * sizeof(void *), GFP_KERNEL); + if (!blade_info) + return -ENOMEM; + memset(blade_info, 0, uv_possible_blades * sizeof(void *)); + + for_each_present_cpu(cpu) { + int nid = cpu_to_node(cpu); + int bid = uv_cpu_to_blade_id(cpu); + int bcpu = uv_cpu_hub_info(cpu)->blade_processor_id; + struct uv_rtc_timer_head *head = blade_info[bid]; + + if (!head) { + head = kmalloc_node(sizeof(struct uv_rtc_timer_head) + + (uv_blade_nr_possible_cpus(bid) * + 2 * sizeof(u64)), + GFP_KERNEL, nid); + if (!head) { + uv_rtc_deallocate_timers(); + return -ENOMEM; + } + spin_lock_init(&head->lock); + head->ncpus = uv_blade_nr_possible_cpus(bid); + head->next_cpu = -1; + blade_info[bid] = head; + } + + head->cpu[bcpu].lcpu = cpu; + head->cpu[bcpu].expires = ULLONG_MAX; + } + + return 0; +} + +/* Find and set the next expiring timer. */ +static void uv_rtc_find_next_timer(struct uv_rtc_timer_head *head, int pnode) +{ + u64 lowest = ULLONG_MAX; + int c, bcpu = -1; + + head->next_cpu = -1; + for (c = 0; c < head->ncpus; c++) { + u64 exp = head->cpu[c].expires; + if (exp < lowest) { + bcpu = c; + lowest = exp; + } + } + if (bcpu >= 0) { + head->next_cpu = bcpu; + c = head->cpu[bcpu].lcpu; + if (uv_setup_intr(c, lowest)) + /* If we didn't set it up in time, trigger */ + uv_rtc_send_IPI(c); + } else { + uv_write_global_mmr64(pnode, UVH_RTC1_INT_CONFIG, + UVH_RTC1_INT_CONFIG_M_MASK); + } +} + +/* + * Set expiration time for current cpu. + * + * Returns 1 if we missed the expiration time. + */ +static int uv_rtc_set_timer(int cpu, u64 expires) +{ + int pnode = uv_cpu_to_pnode(cpu); + int bid = uv_cpu_to_blade_id(cpu); + struct uv_rtc_timer_head *head = blade_info[bid]; + int bcpu = uv_cpu_hub_info(cpu)->blade_processor_id; + u64 *t = &head->cpu[bcpu].expires; + unsigned long flags; + int next_cpu; + + spin_lock_irqsave(&head->lock, flags); + + next_cpu = head->next_cpu; + *t = expires; + /* Will this one be next to go off? */ + if (next_cpu < 0 || bcpu == next_cpu || + expires < head->cpu[next_cpu].expires) { + head->next_cpu = bcpu; + if (uv_setup_intr(cpu, expires)) { + *t = ULLONG_MAX; + uv_rtc_find_next_timer(head, pnode); + spin_unlock_irqrestore(&head->lock, flags); + return 1; + } + } + + spin_unlock_irqrestore(&head->lock, flags); + return 0; +} + +/* + * Unset expiration time for current cpu. + * + * Returns 1 if this timer was pending. + */ +static int uv_rtc_unset_timer(int cpu) +{ + int pnode = uv_cpu_to_pnode(cpu); + int bid = uv_cpu_to_blade_id(cpu); + struct uv_rtc_timer_head *head = blade_info[bid]; + int bcpu = uv_cpu_hub_info(cpu)->blade_processor_id; + u64 *t = &head->cpu[bcpu].expires; + unsigned long flags; + int rc = 0; + + spin_lock_irqsave(&head->lock, flags); + + if (head->next_cpu == bcpu && uv_read_rtc() >= *t) + rc = 1; + + *t = ULLONG_MAX; + + /* Was the hardware setup for this timer? */ + if (head->next_cpu == bcpu) + uv_rtc_find_next_timer(head, pnode); + + spin_unlock_irqrestore(&head->lock, flags); + + return rc; +} + + +/* + * Kernel interface routines. + */ + +/* + * Read the RTC. + */ +static cycle_t uv_read_rtc(void) +{ + return (cycle_t)uv_read_local_mmr(UVH_RTC); +} + +/* + * Program the next event, relative to now + */ +static int uv_rtc_next_event(unsigned long delta, + struct clock_event_device *ced) +{ + int ced_cpu = cpumask_first(ced->cpumask); + + return uv_rtc_set_timer(ced_cpu, delta + uv_read_rtc()); +} + +/* + * Setup the RTC timer in oneshot mode + */ +static void uv_rtc_timer_setup(enum clock_event_mode mode, + struct clock_event_device *evt) +{ + int ced_cpu = cpumask_first(evt->cpumask); + + switch (mode) { + case CLOCK_EVT_MODE_PERIODIC: + case CLOCK_EVT_MODE_ONESHOT: + case CLOCK_EVT_MODE_RESUME: + /* Nothing to do here yet */ + break; + case CLOCK_EVT_MODE_UNUSED: + case CLOCK_EVT_MODE_SHUTDOWN: + uv_rtc_unset_timer(ced_cpu); + break; + } +} + +static void uv_rtc_interrupt(void) +{ + struct clock_event_device *ced = &__get_cpu_var(cpu_ced); + int cpu = smp_processor_id(); + + if (!ced || !ced->event_handler) + return; + + if (uv_rtc_unset_timer(cpu) != 1) + return; + + ced->event_handler(ced); +} + +static int __init uv_enable_rtc(char *str) +{ + uv_rtc_enable = 1; + + return 1; +} +__setup("uvrtc", uv_enable_rtc); + +static __init void uv_rtc_register_clockevents(struct work_struct *dummy) +{ + struct clock_event_device *ced = &__get_cpu_var(cpu_ced); + + *ced = clock_event_device_uv; + ced->cpumask = cpumask_of(smp_processor_id()); + clockevents_register_device(ced); +} + +static __init int uv_rtc_setup_clock(void) +{ + int rc; + + if (!uv_rtc_enable || !is_uv_system() || generic_interrupt_extension) + return -ENODEV; + + generic_interrupt_extension = uv_rtc_interrupt; + + clocksource_uv.mult = clocksource_hz2mult(sn_rtc_cycles_per_second, + clocksource_uv.shift); + + rc = clocksource_register(&clocksource_uv); + if (rc) { + generic_interrupt_extension = NULL; + return rc; + } + + /* Setup and register clockevents */ + rc = uv_rtc_allocate_timers(); + if (rc) { + clocksource_unregister(&clocksource_uv); + generic_interrupt_extension = NULL; + return rc; + } + + clock_event_device_uv.mult = div_sc(sn_rtc_cycles_per_second, + NSEC_PER_SEC, clock_event_device_uv.shift); + + clock_event_device_uv.min_delta_ns = NSEC_PER_SEC / + sn_rtc_cycles_per_second; + + clock_event_device_uv.max_delta_ns = clocksource_uv.mask * + (NSEC_PER_SEC / sn_rtc_cycles_per_second); + + rc = schedule_on_each_cpu(uv_rtc_register_clockevents); + if (rc) { + clocksource_unregister(&clocksource_uv); + generic_interrupt_extension = NULL; + uv_rtc_deallocate_timers(); + } + + return rc; +} +arch_initcall(uv_rtc_setup_clock); diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c index 191a876..31ffc24 100644 --- a/arch/x86/kernel/visws_quirks.c +++ b/arch/x86/kernel/visws_quirks.c @@ -578,7 +578,7 @@ static struct irq_chip piix4_virtual_irq_type = { static irqreturn_t piix4_master_intr(int irq, void *dev_id) { int realirq; - irq_desc_t *desc; + struct irq_desc *desc; unsigned long flags; spin_lock_irqsave(&i8259A_lock, flags); diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index 2cc4a90..95deb9f2 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -395,11 +395,6 @@ static void vmi_set_pte_atomic(pte_t *ptep, pte_t pteval) vmi_ops.update_pte(ptep, VMI_PAGE_PT); } -static void vmi_set_pte_present(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) -{ - vmi_ops.set_pte(pte, ptep, vmi_flags_addr_defer(mm, addr, VMI_PAGE_PT, 1)); -} - static void vmi_set_pud(pud_t *pudp, pud_t pudval) { /* Um, eww */ @@ -750,7 +745,6 @@ static inline int __init activate_vmi(void) pv_mmu_ops.set_pmd = vmi_set_pmd; #ifdef CONFIG_X86_PAE pv_mmu_ops.set_pte_atomic = vmi_set_pte_atomic; - pv_mmu_ops.set_pte_present = vmi_set_pte_present; pv_mmu_ops.set_pud = vmi_set_pud; pv_mmu_ops.pte_clear = vmi_pte_clear; pv_mmu_ops.pmd_clear = vmi_pmd_clear; diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c index 33a788d..d303369 100644 --- a/arch/x86/kernel/vmiclock_32.c +++ b/arch/x86/kernel/vmiclock_32.c @@ -202,7 +202,6 @@ static struct irqaction vmi_clock_action = { .name = "vmi-timer", .handler = vmi_timer_interrupt, .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TIMER, - .mask = CPU_MASK_ALL, }; static void __devinit vmi_time_init_clockevent(void) diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S index 0d86096..62ad500 100644 --- a/arch/x86/kernel/vmlinux_32.lds.S +++ b/arch/x86/kernel/vmlinux_32.lds.S @@ -189,15 +189,24 @@ SECTIONS *(.bss) . = ALIGN(4); __bss_stop = .; - _end = . ; - /* This is where the kernel creates the early boot page tables */ + } + + .brk : AT(ADDR(.brk) - LOAD_OFFSET) { . = ALIGN(PAGE_SIZE); - pg0 = . ; + __brk_base = . ; + . += 64 * 1024 ; /* 64k alignment slop space */ + *(.brk_reservation) /* areas brk users have reserved */ + __brk_limit = . ; + } + + .end : AT(ADDR(.end) - LOAD_OFFSET) { + _end = . ; } /* Sections to be discarded */ /DISCARD/ : { *(.exitcall.exit) + *(.discard) } STABS_DEBUG @@ -205,6 +214,12 @@ SECTIONS DWARF_DEBUG } +/* + * Build-time check on the image size: + */ +ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE), + "kernel image bigger than KERNEL_IMAGE_SIZE") + #ifdef CONFIG_KEXEC /* Link time checks */ #include <asm/kexec.h> diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S index fbfced6..c874250 100644 --- a/arch/x86/kernel/vmlinux_64.lds.S +++ b/arch/x86/kernel/vmlinux_64.lds.S @@ -29,8 +29,8 @@ SECTIONS { . = __START_KERNEL; phys_startup_64 = startup_64 - LOAD_OFFSET; - _text = .; /* Text and read-only data */ .text : AT(ADDR(.text) - LOAD_OFFSET) { + _text = .; /* Text and read-only data */ /* First the code that has to be first for bootstrapping */ *(.text.head) _stext = .; @@ -61,13 +61,13 @@ SECTIONS .data : AT(ADDR(.data) - LOAD_OFFSET) { DATA_DATA CONSTRUCTORS + _edata = .; /* End of data section */ } :data - _edata = .; /* End of data section */ - . = ALIGN(PAGE_SIZE); - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) { + . = ALIGN(PAGE_SIZE); + . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); *(.data.cacheline_aligned) } . = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES); @@ -125,29 +125,29 @@ SECTIONS #undef VVIRT_OFFSET #undef VVIRT - . = ALIGN(THREAD_SIZE); /* init_task */ .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) { + . = ALIGN(THREAD_SIZE); /* init_task */ *(.data.init_task) }:data.init - . = ALIGN(PAGE_SIZE); .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) { + . = ALIGN(PAGE_SIZE); *(.data.page_aligned) } - /* might get freed after init */ - . = ALIGN(PAGE_SIZE); - __smp_alt_begin = .; - __smp_locks = .; .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) { + /* might get freed after init */ + . = ALIGN(PAGE_SIZE); + __smp_alt_begin = .; + __smp_locks = .; *(.smp_locks) + __smp_locks_end = .; + . = ALIGN(PAGE_SIZE); + __smp_alt_end = .; } - __smp_locks_end = .; - . = ALIGN(PAGE_SIZE); - __smp_alt_end = .; . = ALIGN(PAGE_SIZE); /* Init code and data */ - __init_begin = .; + __init_begin = .; /* paired with __init_end */ .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) { _sinittext = .; INIT_TEXT @@ -159,40 +159,42 @@ SECTIONS __initdata_end = .; } - . = ALIGN(16); - __setup_start = .; - .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) { *(.init.setup) } - __setup_end = .; - __initcall_start = .; + .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) { + . = ALIGN(16); + __setup_start = .; + *(.init.setup) + __setup_end = .; + } .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) { + __initcall_start = .; INITCALLS + __initcall_end = .; } - __initcall_end = .; - __con_initcall_start = .; .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) { + __con_initcall_start = .; *(.con_initcall.init) + __con_initcall_end = .; } - __con_initcall_end = .; - __x86_cpu_dev_start = .; .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) { + __x86_cpu_dev_start = .; *(.x86_cpu_dev.init) + __x86_cpu_dev_end = .; } - __x86_cpu_dev_end = .; SECURITY_INIT . = ALIGN(8); .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) { - __parainstructions = .; + __parainstructions = .; *(.parainstructions) - __parainstructions_end = .; + __parainstructions_end = .; } - . = ALIGN(8); - __alt_instructions = .; .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) { + . = ALIGN(8); + __alt_instructions = .; *(.altinstructions) + __alt_instructions_end = .; } - __alt_instructions_end = .; .altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) { *(.altinstr_replacement) } @@ -207,9 +209,11 @@ SECTIONS #ifdef CONFIG_BLK_DEV_INITRD . = ALIGN(PAGE_SIZE); - __initramfs_start = .; - .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) { *(.init.ramfs) } - __initramfs_end = .; + .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) { + __initramfs_start = .; + *(.init.ramfs) + __initramfs_end = .; + } #endif #ifdef CONFIG_SMP @@ -229,20 +233,29 @@ SECTIONS . = ALIGN(PAGE_SIZE); __init_end = .; - . = ALIGN(PAGE_SIZE); - __nosave_begin = .; .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) { - *(.data.nosave) + . = ALIGN(PAGE_SIZE); + __nosave_begin = .; + *(.data.nosave) + . = ALIGN(PAGE_SIZE); + __nosave_end = .; } :data.init2 /* use another section data.init2, see PERCPU_VADDR() above */ - . = ALIGN(PAGE_SIZE); - __nosave_end = .; - __bss_start = .; /* BSS */ .bss : AT(ADDR(.bss) - LOAD_OFFSET) { + . = ALIGN(PAGE_SIZE); + __bss_start = .; /* BSS */ *(.bss.page_aligned) *(.bss) - } - __bss_stop = .; + __bss_stop = .; + } + + .brk : AT(ADDR(.brk) - LOAD_OFFSET) { + . = ALIGN(PAGE_SIZE); + __brk_base = . ; + . += 64 * 1024 ; /* 64k alignment slop space */ + *(.brk_reservation) /* areas brk users have reserved */ + __brk_limit = . ; + } _end = . ; @@ -250,6 +263,7 @@ SECTIONS /DISCARD/ : { *(.exitcall.exit) *(.eh_frame) + *(.discard) } STABS_DEBUG @@ -275,3 +289,10 @@ ASSERT((_end - _text <= KERNEL_IMAGE_SIZE), ASSERT((per_cpu__irq_stack_union == 0), "irq_stack_union is not at start of per-cpu area"); #endif + +#ifdef CONFIG_KEXEC +#include <asm/kexec.h> + +ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE, + "kexec control code size is too big") +#endif diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index c609205..a1d804b 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -139,6 +139,7 @@ int is_vsmp_box(void) return 0; } } + #else static void __init detect_vsmp_box(void) { @@ -148,7 +149,6 @@ int is_vsmp_box(void) return 0; } #endif - void __init vsmp_init(void) { detect_vsmp_box(); diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index b81125f..a58504e 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -4,6 +4,10 @@ config HAVE_KVM bool +config HAVE_KVM_IRQCHIP + bool + default y + menuconfig VIRTUALIZATION bool "Virtualization" depends on HAVE_KVM || X86 @@ -55,7 +59,8 @@ config KVM_AMD config KVM_TRACE bool "KVM trace support" - depends on KVM && MARKERS && SYSFS + depends on KVM && SYSFS + select MARKERS select RELAY select DEBUG_FS default n diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 72bd275..c13bb92 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -201,6 +201,9 @@ static int __pit_timer_fn(struct kvm_kpit_state *ps) if (!atomic_inc_and_test(&pt->pending)) set_bit(KVM_REQ_PENDING_TIMER, &vcpu0->requests); + if (!pt->reinject) + atomic_set(&pt->pending, 1); + if (vcpu0 && waitqueue_active(&vcpu0->wq)) wake_up_interruptible(&vcpu0->wq); @@ -536,6 +539,16 @@ void kvm_pit_reset(struct kvm_pit *pit) pit->pit_state.irq_ack = 1; } +static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask) +{ + struct kvm_pit *pit = container_of(kimn, struct kvm_pit, mask_notifier); + + if (!mask) { + atomic_set(&pit->pit_state.pit_timer.pending, 0); + pit->pit_state.irq_ack = 1; + } +} + struct kvm_pit *kvm_create_pit(struct kvm *kvm) { struct kvm_pit *pit; @@ -545,9 +558,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm) if (!pit) return NULL; - mutex_lock(&kvm->lock); pit->irq_source_id = kvm_request_irq_source_id(kvm); - mutex_unlock(&kvm->lock); if (pit->irq_source_id < 0) { kfree(pit); return NULL; @@ -580,10 +591,14 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm) pit_state->irq_ack_notifier.gsi = 0; pit_state->irq_ack_notifier.irq_acked = kvm_pit_ack_irq; kvm_register_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier); + pit_state->pit_timer.reinject = true; mutex_unlock(&pit->pit_state.lock); kvm_pit_reset(pit); + pit->mask_notifier.func = pit_mask_notifer; + kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier); + return pit; } @@ -592,6 +607,8 @@ void kvm_free_pit(struct kvm *kvm) struct hrtimer *timer; if (kvm->arch.vpit) { + kvm_unregister_irq_mask_notifier(kvm, 0, + &kvm->arch.vpit->mask_notifier); mutex_lock(&kvm->arch.vpit->pit_state.lock); timer = &kvm->arch.vpit->pit_state.pit_timer.timer; hrtimer_cancel(timer); diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index 4178022..6acbe4b 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -9,6 +9,7 @@ struct kvm_kpit_timer { s64 period; /* unit: ns */ s64 scheduled; atomic_t pending; + bool reinject; }; struct kvm_kpit_channel_state { @@ -45,6 +46,7 @@ struct kvm_pit { struct kvm *kvm; struct kvm_kpit_state pit_state; int irq_source_id; + struct kvm_irq_mask_notifier mask_notifier; }; #define KVM_PIT_BASE_ADDRESS 0x40 diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 179dcb0..1ccb50c 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -32,11 +32,13 @@ #include <linux/kvm_host.h> static void pic_lock(struct kvm_pic *s) + __acquires(&s->lock) { spin_lock(&s->lock); } static void pic_unlock(struct kvm_pic *s) + __releases(&s->lock) { struct kvm *kvm = s->kvm; unsigned acks = s->pending_acks; @@ -49,7 +51,8 @@ static void pic_unlock(struct kvm_pic *s) spin_unlock(&s->lock); while (acks) { - kvm_notify_acked_irq(kvm, __ffs(acks)); + kvm_notify_acked_irq(kvm, SELECT_PIC(__ffs(acks)), + __ffs(acks)); acks &= acks - 1; } @@ -76,12 +79,13 @@ void kvm_pic_clear_isr_ack(struct kvm *kvm) /* * set irq level. If an edge is detected, then the IRR is set to 1 */ -static inline void pic_set_irq1(struct kvm_kpic_state *s, int irq, int level) +static inline int pic_set_irq1(struct kvm_kpic_state *s, int irq, int level) { - int mask; + int mask, ret = 1; mask = 1 << irq; if (s->elcr & mask) /* level triggered */ if (level) { + ret = !(s->irr & mask); s->irr |= mask; s->last_irr |= mask; } else { @@ -90,11 +94,15 @@ static inline void pic_set_irq1(struct kvm_kpic_state *s, int irq, int level) } else /* edge triggered */ if (level) { - if ((s->last_irr & mask) == 0) + if ((s->last_irr & mask) == 0) { + ret = !(s->irr & mask); s->irr |= mask; + } s->last_irr |= mask; } else s->last_irr &= ~mask; + + return (s->imr & mask) ? -1 : ret; } /* @@ -171,16 +179,19 @@ void kvm_pic_update_irq(struct kvm_pic *s) pic_unlock(s); } -void kvm_pic_set_irq(void *opaque, int irq, int level) +int kvm_pic_set_irq(void *opaque, int irq, int level) { struct kvm_pic *s = opaque; + int ret = -1; pic_lock(s); if (irq >= 0 && irq < PIC_NUM_PINS) { - pic_set_irq1(&s->pics[irq >> 3], irq & 7, level); + ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, level); pic_update_irq(s); } pic_unlock(s); + + return ret; } /* @@ -232,7 +243,7 @@ int kvm_pic_read_irq(struct kvm *kvm) } pic_update_irq(s); pic_unlock(s); - kvm_notify_acked_irq(kvm, irq); + kvm_notify_acked_irq(kvm, SELECT_PIC(irq), irq); return intno; } diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 82579ee..9f59318 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -32,6 +32,8 @@ #include "lapic.h" #define PIC_NUM_PINS 16 +#define SELECT_PIC(irq) \ + ((irq) < 8 ? KVM_IRQCHIP_PIC_MASTER : KVM_IRQCHIP_PIC_SLAVE) struct kvm; struct kvm_vcpu; diff --git a/arch/x86/kvm/kvm_svm.h b/arch/x86/kvm/kvm_svm.h index 8e5ee99..ed66e4c 100644 --- a/arch/x86/kvm/kvm_svm.h +++ b/arch/x86/kvm/kvm_svm.h @@ -18,7 +18,6 @@ static const u32 host_save_user_msrs[] = { }; #define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) -#define NUM_DB_REGS 4 struct kvm_vcpu; @@ -29,18 +28,23 @@ struct vcpu_svm { struct svm_cpu_data *svm_data; uint64_t asid_generation; - unsigned long db_regs[NUM_DB_REGS]; - u64 next_rip; u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; u64 host_gs_base; unsigned long host_cr2; - unsigned long host_db_regs[NUM_DB_REGS]; - unsigned long host_dr6; - unsigned long host_dr7; u32 *msrpm; + struct vmcb *hsave; + u64 hsave_msr; + + u64 nested_vmcb; + + /* These are the merged vectors */ + u32 *nested_msrpm; + + /* gpa pointers to the real vectors */ + u64 nested_vmcb_msrpm; }; #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 2d4477c..2a36f7f 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -145,11 +145,20 @@ struct kvm_rmap_desc { struct kvm_rmap_desc *more; }; -struct kvm_shadow_walk { - int (*entry)(struct kvm_shadow_walk *walk, struct kvm_vcpu *vcpu, - u64 addr, u64 *spte, int level); +struct kvm_shadow_walk_iterator { + u64 addr; + hpa_t shadow_addr; + int level; + u64 *sptep; + unsigned index; }; +#define for_each_shadow_entry(_vcpu, _addr, _walker) \ + for (shadow_walk_init(&(_walker), _vcpu, _addr); \ + shadow_walk_okay(&(_walker)); \ + shadow_walk_next(&(_walker))) + + struct kvm_unsync_walk { int (*entry) (struct kvm_mmu_page *sp, struct kvm_unsync_walk *walk); }; @@ -343,7 +352,6 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc, BUG_ON(!mc->nobjs); p = mc->objects[--mc->nobjs]; - memset(p, 0, size); return p; } @@ -794,10 +802,8 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, set_page_private(virt_to_page(sp->spt), (unsigned long)sp); list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&sp->oos_link); - ASSERT(is_empty_shadow_page(sp->spt)); bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS); sp->multimapped = 0; - sp->global = 1; sp->parent_pte = parent_pte; --vcpu->kvm->arch.n_free_mmu_pages; return sp; @@ -983,8 +989,8 @@ struct kvm_mmu_pages { idx < 512; \ idx = find_next_bit(bitmap, 512, idx+1)) -int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp, - int idx) +static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp, + int idx) { int i; @@ -1059,7 +1065,7 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn) index = kvm_page_table_hashfn(gfn); bucket = &kvm->arch.mmu_page_hash[index]; hlist_for_each_entry(sp, node, bucket, hash_link) - if (sp->gfn == gfn && !sp->role.metaphysical + if (sp->gfn == gfn && !sp->role.direct && !sp->role.invalid) { pgprintk("%s: found role %x\n", __func__, sp->role.word); @@ -1115,8 +1121,9 @@ struct mmu_page_path { i < pvec.nr && ({ sp = pvec.page[i].sp; 1;}); \ i = mmu_pages_next(&pvec, &parents, i)) -int mmu_pages_next(struct kvm_mmu_pages *pvec, struct mmu_page_path *parents, - int i) +static int mmu_pages_next(struct kvm_mmu_pages *pvec, + struct mmu_page_path *parents, + int i) { int n; @@ -1135,7 +1142,7 @@ int mmu_pages_next(struct kvm_mmu_pages *pvec, struct mmu_page_path *parents, return n; } -void mmu_pages_clear_parents(struct mmu_page_path *parents) +static void mmu_pages_clear_parents(struct mmu_page_path *parents) { struct kvm_mmu_page *sp; unsigned int level = 0; @@ -1193,7 +1200,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, gfn_t gfn, gva_t gaddr, unsigned level, - int metaphysical, + int direct, unsigned access, u64 *parent_pte) { @@ -1204,10 +1211,9 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp; struct hlist_node *node, *tmp; - role.word = 0; - role.glevels = vcpu->arch.mmu.root_level; + role = vcpu->arch.mmu.base_role; role.level = level; - role.metaphysical = metaphysical; + role.direct = direct; role.access = access; if (vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) { quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level)); @@ -1242,8 +1248,9 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word); sp->gfn = gfn; sp->role = role; + sp->global = role.cr4_pge; hlist_add_head(&sp->hash_link, bucket); - if (!metaphysical) { + if (!direct) { if (rmap_write_protect(vcpu->kvm, gfn)) kvm_flush_remote_tlbs(vcpu->kvm); account_shadowed(vcpu->kvm, gfn); @@ -1255,35 +1262,35 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, return sp; } -static int walk_shadow(struct kvm_shadow_walk *walker, - struct kvm_vcpu *vcpu, u64 addr) +static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator, + struct kvm_vcpu *vcpu, u64 addr) { - hpa_t shadow_addr; - int level; - int r; - u64 *sptep; - unsigned index; - - shadow_addr = vcpu->arch.mmu.root_hpa; - level = vcpu->arch.mmu.shadow_root_level; - if (level == PT32E_ROOT_LEVEL) { - shadow_addr = vcpu->arch.mmu.pae_root[(addr >> 30) & 3]; - shadow_addr &= PT64_BASE_ADDR_MASK; - if (!shadow_addr) - return 1; - --level; + iterator->addr = addr; + iterator->shadow_addr = vcpu->arch.mmu.root_hpa; + iterator->level = vcpu->arch.mmu.shadow_root_level; + if (iterator->level == PT32E_ROOT_LEVEL) { + iterator->shadow_addr + = vcpu->arch.mmu.pae_root[(addr >> 30) & 3]; + iterator->shadow_addr &= PT64_BASE_ADDR_MASK; + --iterator->level; + if (!iterator->shadow_addr) + iterator->level = 0; } +} - while (level >= PT_PAGE_TABLE_LEVEL) { - index = SHADOW_PT_INDEX(addr, level); - sptep = ((u64 *)__va(shadow_addr)) + index; - r = walker->entry(walker, vcpu, addr, sptep, level); - if (r) - return r; - shadow_addr = *sptep & PT64_BASE_ADDR_MASK; - --level; - } - return 0; +static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator) +{ + if (iterator->level < PT_PAGE_TABLE_LEVEL) + return false; + iterator->index = SHADOW_PT_INDEX(iterator->addr, iterator->level); + iterator->sptep = ((u64 *)__va(iterator->shadow_addr)) + iterator->index; + return true; +} + +static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator) +{ + iterator->shadow_addr = *iterator->sptep & PT64_BASE_ADDR_MASK; + --iterator->level; } static void kvm_mmu_page_unlink_children(struct kvm *kvm, @@ -1388,7 +1395,7 @@ static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_page_unlink_children(kvm, sp); kvm_mmu_unlink_parents(kvm, sp); kvm_flush_remote_tlbs(kvm); - if (!sp->role.invalid && !sp->role.metaphysical) + if (!sp->role.invalid && !sp->role.direct) unaccount_shadowed(kvm, sp->gfn); if (sp->unsync) kvm_unlink_unsync_page(kvm, sp); @@ -1451,7 +1458,7 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) index = kvm_page_table_hashfn(gfn); bucket = &kvm->arch.mmu_page_hash[index]; hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) - if (sp->gfn == gfn && !sp->role.metaphysical) { + if (sp->gfn == gfn && !sp->role.direct) { pgprintk("%s: gfn %lx role %x\n", __func__, gfn, sp->role.word); r = 1; @@ -1463,11 +1470,20 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) static void mmu_unshadow(struct kvm *kvm, gfn_t gfn) { + unsigned index; + struct hlist_head *bucket; struct kvm_mmu_page *sp; + struct hlist_node *node, *nn; - while ((sp = kvm_mmu_lookup_page(kvm, gfn)) != NULL) { - pgprintk("%s: zap %lx %x\n", __func__, gfn, sp->role.word); - kvm_mmu_zap_page(kvm, sp); + index = kvm_page_table_hashfn(gfn); + bucket = &kvm->arch.mmu_page_hash[index]; + hlist_for_each_entry_safe(sp, node, nn, bucket, hash_link) { + if (sp->gfn == gfn && !sp->role.direct + && !sp->role.invalid) { + pgprintk("%s: zap %lx %x\n", + __func__, gfn, sp->role.word); + kvm_mmu_zap_page(kvm, sp); + } } } @@ -1622,7 +1638,7 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) bucket = &vcpu->kvm->arch.mmu_page_hash[index]; /* don't unsync if pagetable is shadowed with multiple roles */ hlist_for_each_entry_safe(s, node, n, bucket, hash_link) { - if (s->gfn != sp->gfn || s->role.metaphysical) + if (s->gfn != sp->gfn || s->role.direct) continue; if (s->role.word != sp->role.word) return 1; @@ -1669,8 +1685,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, u64 mt_mask = shadow_mt_mask; struct kvm_mmu_page *sp = page_header(__pa(shadow_pte)); - if (!(vcpu->arch.cr4 & X86_CR4_PGE)) - global = 0; if (!global && sp->global) { sp->global = 0; if (sp->unsync) { @@ -1777,12 +1791,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, pgprintk("hfn old %lx new %lx\n", spte_to_pfn(*shadow_pte), pfn); rmap_remove(vcpu->kvm, shadow_pte); - } else { - if (largepage) - was_rmapped = is_large_pte(*shadow_pte); - else - was_rmapped = 1; - } + } else + was_rmapped = 1; } if (set_spte(vcpu, shadow_pte, pte_access, user_fault, write_fault, dirty, largepage, global, gfn, pfn, speculative, true)) { @@ -1820,67 +1830,42 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) { } -struct direct_shadow_walk { - struct kvm_shadow_walk walker; - pfn_t pfn; - int write; - int largepage; - int pt_write; -}; - -static int direct_map_entry(struct kvm_shadow_walk *_walk, - struct kvm_vcpu *vcpu, - u64 addr, u64 *sptep, int level) +static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, + int largepage, gfn_t gfn, pfn_t pfn) { - struct direct_shadow_walk *walk = - container_of(_walk, struct direct_shadow_walk, walker); + struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; + int pt_write = 0; gfn_t pseudo_gfn; - gfn_t gfn = addr >> PAGE_SHIFT; - - if (level == PT_PAGE_TABLE_LEVEL - || (walk->largepage && level == PT_DIRECTORY_LEVEL)) { - mmu_set_spte(vcpu, sptep, ACC_ALL, ACC_ALL, - 0, walk->write, 1, &walk->pt_write, - walk->largepage, 0, gfn, walk->pfn, false); - ++vcpu->stat.pf_fixed; - return 1; - } - if (*sptep == shadow_trap_nonpresent_pte) { - pseudo_gfn = (addr & PT64_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT; - sp = kvm_mmu_get_page(vcpu, pseudo_gfn, (gva_t)addr, level - 1, - 1, ACC_ALL, sptep); - if (!sp) { - pgprintk("nonpaging_map: ENOMEM\n"); - kvm_release_pfn_clean(walk->pfn); - return -ENOMEM; + for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) { + if (iterator.level == PT_PAGE_TABLE_LEVEL + || (largepage && iterator.level == PT_DIRECTORY_LEVEL)) { + mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL, + 0, write, 1, &pt_write, + largepage, 0, gfn, pfn, false); + ++vcpu->stat.pf_fixed; + break; } - set_shadow_pte(sptep, - __pa(sp->spt) - | PT_PRESENT_MASK | PT_WRITABLE_MASK - | shadow_user_mask | shadow_x_mask); - } - return 0; -} + if (*iterator.sptep == shadow_trap_nonpresent_pte) { + pseudo_gfn = (iterator.addr & PT64_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT; + sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr, + iterator.level - 1, + 1, ACC_ALL, iterator.sptep); + if (!sp) { + pgprintk("nonpaging_map: ENOMEM\n"); + kvm_release_pfn_clean(pfn); + return -ENOMEM; + } -static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, - int largepage, gfn_t gfn, pfn_t pfn) -{ - int r; - struct direct_shadow_walk walker = { - .walker = { .entry = direct_map_entry, }, - .pfn = pfn, - .largepage = largepage, - .write = write, - .pt_write = 0, - }; - - r = walk_shadow(&walker.walker, vcpu, gfn << PAGE_SHIFT); - if (r < 0) - return r; - return walker.pt_write; + set_shadow_pte(iterator.sptep, + __pa(sp->spt) + | PT_PRESENT_MASK | PT_WRITABLE_MASK + | shadow_user_mask | shadow_x_mask); + } + } + return pt_write; } static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) @@ -1962,7 +1947,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) int i; gfn_t root_gfn; struct kvm_mmu_page *sp; - int metaphysical = 0; + int direct = 0; root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT; @@ -1971,18 +1956,18 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); if (tdp_enabled) - metaphysical = 1; + direct = 1; sp = kvm_mmu_get_page(vcpu, root_gfn, 0, - PT64_ROOT_LEVEL, metaphysical, + PT64_ROOT_LEVEL, direct, ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; vcpu->arch.mmu.root_hpa = root; return; } - metaphysical = !is_paging(vcpu); + direct = !is_paging(vcpu); if (tdp_enabled) - metaphysical = 1; + direct = 1; for (i = 0; i < 4; ++i) { hpa_t root = vcpu->arch.mmu.pae_root[i]; @@ -1996,7 +1981,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) } else if (vcpu->arch.mmu.root_level == 0) root_gfn = 0; sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, - PT32_ROOT_LEVEL, metaphysical, + PT32_ROOT_LEVEL, direct, ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; @@ -2251,17 +2236,23 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) static int init_kvm_softmmu(struct kvm_vcpu *vcpu) { + int r; + ASSERT(vcpu); ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); if (!is_paging(vcpu)) - return nonpaging_init_context(vcpu); + r = nonpaging_init_context(vcpu); else if (is_long_mode(vcpu)) - return paging64_init_context(vcpu); + r = paging64_init_context(vcpu); else if (is_pae(vcpu)) - return paging32E_init_context(vcpu); + r = paging32E_init_context(vcpu); else - return paging32_init_context(vcpu); + r = paging32_init_context(vcpu); + + vcpu->arch.mmu.base_role.glevels = vcpu->arch.mmu.root_level; + + return r; } static int init_kvm_mmu(struct kvm_vcpu *vcpu) @@ -2492,7 +2483,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, index = kvm_page_table_hashfn(gfn); bucket = &vcpu->kvm->arch.mmu_page_hash[index]; hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) { - if (sp->gfn != gfn || sp->role.metaphysical || sp->role.invalid) + if (sp->gfn != gfn || sp->role.direct || sp->role.invalid) continue; pte_size = sp->role.glevels == PT32_ROOT_LEVEL ? 4 : 8; misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); @@ -3130,7 +3121,7 @@ static void audit_write_protection(struct kvm_vcpu *vcpu) gfn_t gfn; list_for_each_entry(sp, &vcpu->kvm->arch.active_mmu_pages, link) { - if (sp->role.metaphysical) + if (sp->role.direct) continue; gfn = unalias_gfn(vcpu->kvm, sp->gfn); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 258e5d5..eaab214 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -54,7 +54,7 @@ static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) static inline int is_long_mode(struct kvm_vcpu *vcpu) { #ifdef CONFIG_X86_64 - return vcpu->arch.shadow_efer & EFER_LME; + return vcpu->arch.shadow_efer & EFER_LMA; #else return 0; #endif diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 9fd78b6..6bd7020 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -25,7 +25,6 @@ #if PTTYPE == 64 #define pt_element_t u64 #define guest_walker guest_walker64 - #define shadow_walker shadow_walker64 #define FNAME(name) paging##64_##name #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK #define PT_DIR_BASE_ADDR_MASK PT64_DIR_BASE_ADDR_MASK @@ -42,7 +41,6 @@ #elif PTTYPE == 32 #define pt_element_t u32 #define guest_walker guest_walker32 - #define shadow_walker shadow_walker32 #define FNAME(name) paging##32_##name #define PT_BASE_ADDR_MASK PT32_BASE_ADDR_MASK #define PT_DIR_BASE_ADDR_MASK PT32_DIR_BASE_ADDR_MASK @@ -73,18 +71,6 @@ struct guest_walker { u32 error_code; }; -struct shadow_walker { - struct kvm_shadow_walk walker; - struct guest_walker *guest_walker; - int user_fault; - int write_fault; - int largepage; - int *ptwrite; - pfn_t pfn; - u64 *sptep; - gpa_t pte_gpa; -}; - static gfn_t gpte_to_gfn(pt_element_t gpte) { return (gpte & PT_BASE_ADDR_MASK) >> PAGE_SHIFT; @@ -283,91 +269,79 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, /* * Fetch a shadow pte for a specific level in the paging hierarchy. */ -static int FNAME(shadow_walk_entry)(struct kvm_shadow_walk *_sw, - struct kvm_vcpu *vcpu, u64 addr, - u64 *sptep, int level) +static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, + struct guest_walker *gw, + int user_fault, int write_fault, int largepage, + int *ptwrite, pfn_t pfn) { - struct shadow_walker *sw = - container_of(_sw, struct shadow_walker, walker); - struct guest_walker *gw = sw->guest_walker; unsigned access = gw->pt_access; struct kvm_mmu_page *shadow_page; - u64 spte; - int metaphysical; + u64 spte, *sptep; + int direct; gfn_t table_gfn; int r; + int level; pt_element_t curr_pte; + struct kvm_shadow_walk_iterator iterator; - if (level == PT_PAGE_TABLE_LEVEL - || (sw->largepage && level == PT_DIRECTORY_LEVEL)) { - mmu_set_spte(vcpu, sptep, access, gw->pte_access & access, - sw->user_fault, sw->write_fault, - gw->ptes[gw->level-1] & PT_DIRTY_MASK, - sw->ptwrite, sw->largepage, - gw->ptes[gw->level-1] & PT_GLOBAL_MASK, - gw->gfn, sw->pfn, false); - sw->sptep = sptep; - return 1; - } + if (!is_present_pte(gw->ptes[gw->level - 1])) + return NULL; - if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) - return 0; + for_each_shadow_entry(vcpu, addr, iterator) { + level = iterator.level; + sptep = iterator.sptep; + if (level == PT_PAGE_TABLE_LEVEL + || (largepage && level == PT_DIRECTORY_LEVEL)) { + mmu_set_spte(vcpu, sptep, access, + gw->pte_access & access, + user_fault, write_fault, + gw->ptes[gw->level-1] & PT_DIRTY_MASK, + ptwrite, largepage, + gw->ptes[gw->level-1] & PT_GLOBAL_MASK, + gw->gfn, pfn, false); + break; + } - if (is_large_pte(*sptep)) { - set_shadow_pte(sptep, shadow_trap_nonpresent_pte); - kvm_flush_remote_tlbs(vcpu->kvm); - rmap_remove(vcpu->kvm, sptep); - } + if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) + continue; - if (level == PT_DIRECTORY_LEVEL && gw->level == PT_DIRECTORY_LEVEL) { - metaphysical = 1; - if (!is_dirty_pte(gw->ptes[level - 1])) - access &= ~ACC_WRITE_MASK; - table_gfn = gpte_to_gfn(gw->ptes[level - 1]); - } else { - metaphysical = 0; - table_gfn = gw->table_gfn[level - 2]; - } - shadow_page = kvm_mmu_get_page(vcpu, table_gfn, (gva_t)addr, level-1, - metaphysical, access, sptep); - if (!metaphysical) { - r = kvm_read_guest_atomic(vcpu->kvm, gw->pte_gpa[level - 2], - &curr_pte, sizeof(curr_pte)); - if (r || curr_pte != gw->ptes[level - 2]) { - kvm_mmu_put_page(shadow_page, sptep); - kvm_release_pfn_clean(sw->pfn); - sw->sptep = NULL; - return 1; + if (is_large_pte(*sptep)) { + rmap_remove(vcpu->kvm, sptep); + set_shadow_pte(sptep, shadow_trap_nonpresent_pte); + kvm_flush_remote_tlbs(vcpu->kvm); } - } - spte = __pa(shadow_page->spt) | PT_PRESENT_MASK | PT_ACCESSED_MASK - | PT_WRITABLE_MASK | PT_USER_MASK; - *sptep = spte; - return 0; -} - -static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, - struct guest_walker *guest_walker, - int user_fault, int write_fault, int largepage, - int *ptwrite, pfn_t pfn) -{ - struct shadow_walker walker = { - .walker = { .entry = FNAME(shadow_walk_entry), }, - .guest_walker = guest_walker, - .user_fault = user_fault, - .write_fault = write_fault, - .largepage = largepage, - .ptwrite = ptwrite, - .pfn = pfn, - }; - - if (!is_present_pte(guest_walker->ptes[guest_walker->level - 1])) - return NULL; + if (level == PT_DIRECTORY_LEVEL + && gw->level == PT_DIRECTORY_LEVEL) { + direct = 1; + if (!is_dirty_pte(gw->ptes[level - 1])) + access &= ~ACC_WRITE_MASK; + table_gfn = gpte_to_gfn(gw->ptes[level - 1]); + } else { + direct = 0; + table_gfn = gw->table_gfn[level - 2]; + } + shadow_page = kvm_mmu_get_page(vcpu, table_gfn, addr, level-1, + direct, access, sptep); + if (!direct) { + r = kvm_read_guest_atomic(vcpu->kvm, + gw->pte_gpa[level - 2], + &curr_pte, sizeof(curr_pte)); + if (r || curr_pte != gw->ptes[level - 2]) { + kvm_mmu_put_page(shadow_page, sptep); + kvm_release_pfn_clean(pfn); + sptep = NULL; + break; + } + } - walk_shadow(&walker.walker, vcpu, addr); + spte = __pa(shadow_page->spt) + | PT_PRESENT_MASK | PT_ACCESSED_MASK + | PT_WRITABLE_MASK | PT_USER_MASK; + *sptep = spte; + } - return walker.sptep; + return sptep; } /* @@ -465,54 +439,56 @@ out_unlock: return 0; } -static int FNAME(shadow_invlpg_entry)(struct kvm_shadow_walk *_sw, - struct kvm_vcpu *vcpu, u64 addr, - u64 *sptep, int level) +static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) { - struct shadow_walker *sw = - container_of(_sw, struct shadow_walker, walker); - - /* FIXME: properly handle invlpg on large guest pages */ - if (level == PT_PAGE_TABLE_LEVEL || - ((level == PT_DIRECTORY_LEVEL) && is_large_pte(*sptep))) { - struct kvm_mmu_page *sp = page_header(__pa(sptep)); + struct kvm_shadow_walk_iterator iterator; + pt_element_t gpte; + gpa_t pte_gpa = -1; + int level; + u64 *sptep; + int need_flush = 0; - sw->pte_gpa = (sp->gfn << PAGE_SHIFT); - sw->pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t); + spin_lock(&vcpu->kvm->mmu_lock); - if (is_shadow_present_pte(*sptep)) { - rmap_remove(vcpu->kvm, sptep); - if (is_large_pte(*sptep)) - --vcpu->kvm->stat.lpages; + for_each_shadow_entry(vcpu, gva, iterator) { + level = iterator.level; + sptep = iterator.sptep; + + /* FIXME: properly handle invlpg on large guest pages */ + if (level == PT_PAGE_TABLE_LEVEL || + ((level == PT_DIRECTORY_LEVEL) && is_large_pte(*sptep))) { + struct kvm_mmu_page *sp = page_header(__pa(sptep)); + + pte_gpa = (sp->gfn << PAGE_SHIFT); + pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t); + + if (is_shadow_present_pte(*sptep)) { + rmap_remove(vcpu->kvm, sptep); + if (is_large_pte(*sptep)) + --vcpu->kvm->stat.lpages; + need_flush = 1; + } + set_shadow_pte(sptep, shadow_trap_nonpresent_pte); + break; } - set_shadow_pte(sptep, shadow_trap_nonpresent_pte); - return 1; - } - if (!is_shadow_present_pte(*sptep)) - return 1; - return 0; -} -static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) -{ - pt_element_t gpte; - struct shadow_walker walker = { - .walker = { .entry = FNAME(shadow_invlpg_entry), }, - .pte_gpa = -1, - }; + if (!is_shadow_present_pte(*sptep)) + break; + } - spin_lock(&vcpu->kvm->mmu_lock); - walk_shadow(&walker.walker, vcpu, gva); + if (need_flush) + kvm_flush_remote_tlbs(vcpu->kvm); spin_unlock(&vcpu->kvm->mmu_lock); - if (walker.pte_gpa == -1) + + if (pte_gpa == -1) return; - if (kvm_read_guest_atomic(vcpu->kvm, walker.pte_gpa, &gpte, + if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte, sizeof(pt_element_t))) return; if (is_present_pte(gpte) && (gpte & PT_ACCESSED_MASK)) { if (mmu_topup_memory_caches(vcpu)) return; - kvm_mmu_pte_write(vcpu, walker.pte_gpa, (const u8 *)&gpte, + kvm_mmu_pte_write(vcpu, pte_gpa, (const u8 *)&gpte, sizeof(pt_element_t), 0); } } @@ -540,7 +516,7 @@ static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu, pt_element_t pt[256 / sizeof(pt_element_t)]; gpa_t pte_gpa; - if (sp->role.metaphysical + if (sp->role.direct || (PTTYPE == 32 && sp->role.level > PT_PAGE_TABLE_LEVEL)) { nonpaging_prefetch_page(vcpu, sp); return; @@ -619,7 +595,6 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) #undef pt_element_t #undef guest_walker -#undef shadow_walker #undef FNAME #undef PT_BASE_ADDR_MASK #undef PT_INDEX diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index a9e769e..1821c20 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -38,9 +38,6 @@ MODULE_LICENSE("GPL"); #define IOPM_ALLOC_ORDER 2 #define MSRPM_ALLOC_ORDER 1 -#define DR7_GD_MASK (1 << 13) -#define DR6_BD_MASK (1 << 13) - #define SEG_TYPE_LDT 2 #define SEG_TYPE_BUSY_TSS16 3 @@ -50,6 +47,15 @@ MODULE_LICENSE("GPL"); #define DEBUGCTL_RESERVED_BITS (~(0x3fULL)) +/* Turn on to get debugging output*/ +/* #define NESTED_DEBUG */ + +#ifdef NESTED_DEBUG +#define nsvm_printk(fmt, args...) printk(KERN_INFO fmt, ## args) +#else +#define nsvm_printk(fmt, args...) do {} while(0) +#endif + /* enable NPT for AMD64 and X86 with PAE */ #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) static bool npt_enabled = true; @@ -60,14 +66,29 @@ static int npt = 1; module_param(npt, int, S_IRUGO); +static int nested = 0; +module_param(nested, int, S_IRUGO); + static void kvm_reput_irq(struct vcpu_svm *svm); static void svm_flush_tlb(struct kvm_vcpu *vcpu); +static int nested_svm_exit_handled(struct vcpu_svm *svm, bool kvm_override); +static int nested_svm_vmexit(struct vcpu_svm *svm); +static int nested_svm_vmsave(struct vcpu_svm *svm, void *nested_vmcb, + void *arg2, void *opaque); +static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, + bool has_error_code, u32 error_code); + static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) { return container_of(vcpu, struct vcpu_svm, vcpu); } +static inline bool is_nested(struct vcpu_svm *svm) +{ + return svm->nested_vmcb; +} + static unsigned long iopm_base; struct kvm_ldttss_desc { @@ -157,32 +178,6 @@ static inline void kvm_write_cr2(unsigned long val) asm volatile ("mov %0, %%cr2" :: "r" (val)); } -static inline unsigned long read_dr6(void) -{ - unsigned long dr6; - - asm volatile ("mov %%dr6, %0" : "=r" (dr6)); - return dr6; -} - -static inline void write_dr6(unsigned long val) -{ - asm volatile ("mov %0, %%dr6" :: "r" (val)); -} - -static inline unsigned long read_dr7(void) -{ - unsigned long dr7; - - asm volatile ("mov %%dr7, %0" : "=r" (dr7)); - return dr7; -} - -static inline void write_dr7(unsigned long val) -{ - asm volatile ("mov %0, %%dr7" :: "r" (val)); -} - static inline void force_new_asid(struct kvm_vcpu *vcpu) { to_svm(vcpu)->asid_generation--; @@ -198,7 +193,7 @@ static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) if (!npt_enabled && !(efer & EFER_LMA)) efer &= ~EFER_LME; - to_svm(vcpu)->vmcb->save.efer = efer | MSR_EFER_SVME_MASK; + to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME; vcpu->arch.shadow_efer = efer; } @@ -207,6 +202,11 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, { struct vcpu_svm *svm = to_svm(vcpu); + /* If we are within a nested VM we'd better #VMEXIT and let the + guest handle the exception */ + if (nested_svm_check_exception(svm, nr, has_error_code, error_code)) + return; + svm->vmcb->control.event_inj = nr | SVM_EVTINJ_VALID | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0) @@ -242,7 +242,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) kvm_rip_write(vcpu, svm->next_rip); svm->vmcb->control.int_state &= ~SVM_INTERRUPT_SHADOW_MASK; - vcpu->arch.interrupt_window_open = 1; + vcpu->arch.interrupt_window_open = (svm->vcpu.arch.hflags & HF_GIF_MASK); } static int has_svm(void) @@ -250,7 +250,7 @@ static int has_svm(void) const char *msg; if (!cpu_has_svm(&msg)) { - printk(KERN_INFO "has_svn: %s\n", msg); + printk(KERN_INFO "has_svm: %s\n", msg); return 0; } @@ -292,7 +292,7 @@ static void svm_hardware_enable(void *garbage) svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); rdmsrl(MSR_EFER, efer); - wrmsrl(MSR_EFER, efer | MSR_EFER_SVME_MASK); + wrmsrl(MSR_EFER, efer | EFER_SVME); wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(svm_data->save_area) << PAGE_SHIFT); @@ -417,6 +417,14 @@ static __init int svm_hardware_setup(void) if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); + if (boot_cpu_has(X86_FEATURE_FXSR_OPT)) + kvm_enable_efer_bits(EFER_FFXSR); + + if (nested) { + printk(KERN_INFO "kvm: Nested Virtualization enabled\n"); + kvm_enable_efer_bits(EFER_SVME); + } + for_each_online_cpu(cpu) { r = svm_cpu_init(cpu); if (r) @@ -559,7 +567,7 @@ static void init_vmcb(struct vcpu_svm *svm) init_sys_seg(&save->ldtr, SEG_TYPE_LDT); init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16); - save->efer = MSR_EFER_SVME_MASK; + save->efer = EFER_SVME; save->dr6 = 0xffff0ff0; save->dr7 = 0x400; save->rflags = 2; @@ -591,6 +599,9 @@ static void init_vmcb(struct vcpu_svm *svm) save->cr4 = 0; } force_new_asid(&svm->vcpu); + + svm->nested_vmcb = 0; + svm->vcpu.arch.hflags = HF_GIF_MASK; } static int svm_vcpu_reset(struct kvm_vcpu *vcpu) @@ -615,6 +626,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) struct vcpu_svm *svm; struct page *page; struct page *msrpm_pages; + struct page *hsave_page; + struct page *nested_msrpm_pages; int err; svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); @@ -637,14 +650,25 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); if (!msrpm_pages) goto uninit; + + nested_msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); + if (!nested_msrpm_pages) + goto uninit; + svm->msrpm = page_address(msrpm_pages); svm_vcpu_init_msrpm(svm->msrpm); + hsave_page = alloc_page(GFP_KERNEL); + if (!hsave_page) + goto uninit; + svm->hsave = page_address(hsave_page); + + svm->nested_msrpm = page_address(nested_msrpm_pages); + svm->vmcb = page_address(page); clear_page(svm->vmcb); svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; svm->asid_generation = 0; - memset(svm->db_regs, 0, sizeof(svm->db_regs)); init_vmcb(svm); fx_init(&svm->vcpu); @@ -669,6 +693,8 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT)); __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); + __free_page(virt_to_page(svm->hsave)); + __free_pages(virt_to_page(svm->nested_msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, svm); } @@ -718,6 +744,16 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) to_svm(vcpu)->vmcb->save.rflags = rflags; } +static void svm_set_vintr(struct vcpu_svm *svm) +{ + svm->vmcb->control.intercept |= 1ULL << INTERCEPT_VINTR; +} + +static void svm_clear_vintr(struct vcpu_svm *svm) +{ + svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VINTR); +} + static struct vmcb_seg *svm_seg(struct kvm_vcpu *vcpu, int seg) { struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save; @@ -760,20 +796,37 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1; var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1; - /* - * SVM always stores 0 for the 'G' bit in the CS selector in - * the VMCB on a VMEXIT. This hurts cross-vendor migration: - * Intel's VMENTRY has a check on the 'G' bit. - */ - if (seg == VCPU_SREG_CS) + switch (seg) { + case VCPU_SREG_CS: + /* + * SVM always stores 0 for the 'G' bit in the CS selector in + * the VMCB on a VMEXIT. This hurts cross-vendor migration: + * Intel's VMENTRY has a check on the 'G' bit. + */ var->g = s->limit > 0xfffff; - - /* - * Work around a bug where the busy flag in the tr selector - * isn't exposed - */ - if (seg == VCPU_SREG_TR) + break; + case VCPU_SREG_TR: + /* + * Work around a bug where the busy flag in the tr selector + * isn't exposed + */ var->type |= 0x2; + break; + case VCPU_SREG_DS: + case VCPU_SREG_ES: + case VCPU_SREG_FS: + case VCPU_SREG_GS: + /* + * The accessed bit must always be set in the segment + * descriptor cache, although it can be cleared in the + * descriptor, the cached bit always remains at 1. Since + * Intel has a check on this, set it here to support + * cross-vendor migration. + */ + if (!var->unusable) + var->type |= 0x1; + break; + } var->unusable = !var->present; } @@ -905,9 +958,37 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, } -static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) +static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - return -EOPNOTSUPP; + int old_debug = vcpu->guest_debug; + struct vcpu_svm *svm = to_svm(vcpu); + + vcpu->guest_debug = dbg->control; + + svm->vmcb->control.intercept_exceptions &= + ~((1 << DB_VECTOR) | (1 << BP_VECTOR)); + if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { + if (vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) + svm->vmcb->control.intercept_exceptions |= + 1 << DB_VECTOR; + if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) + svm->vmcb->control.intercept_exceptions |= + 1 << BP_VECTOR; + } else + vcpu->guest_debug = 0; + + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) + svm->vmcb->save.dr7 = dbg->arch.debugreg[7]; + else + svm->vmcb->save.dr7 = vcpu->arch.dr7; + + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + svm->vmcb->save.rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF; + else if (old_debug & KVM_GUESTDBG_SINGLESTEP) + svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); + + return 0; } static int svm_get_irq(struct kvm_vcpu *vcpu) @@ -949,7 +1030,29 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data) static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr) { - unsigned long val = to_svm(vcpu)->db_regs[dr]; + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long val; + + switch (dr) { + case 0 ... 3: + val = vcpu->arch.db[dr]; + break; + case 6: + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) + val = vcpu->arch.dr6; + else + val = svm->vmcb->save.dr6; + break; + case 7: + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) + val = vcpu->arch.dr7; + else + val = svm->vmcb->save.dr7; + break; + default: + val = 0; + } + KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler); return val; } @@ -959,33 +1062,40 @@ static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value, { struct vcpu_svm *svm = to_svm(vcpu); - *exception = 0; + KVMTRACE_2D(DR_WRITE, vcpu, (u32)dr, (u32)value, handler); - if (svm->vmcb->save.dr7 & DR7_GD_MASK) { - svm->vmcb->save.dr7 &= ~DR7_GD_MASK; - svm->vmcb->save.dr6 |= DR6_BD_MASK; - *exception = DB_VECTOR; - return; - } + *exception = 0; switch (dr) { case 0 ... 3: - svm->db_regs[dr] = value; + vcpu->arch.db[dr] = value; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) + vcpu->arch.eff_db[dr] = value; return; case 4 ... 5: - if (vcpu->arch.cr4 & X86_CR4_DE) { + if (vcpu->arch.cr4 & X86_CR4_DE) *exception = UD_VECTOR; + return; + case 6: + if (value & 0xffffffff00000000ULL) { + *exception = GP_VECTOR; return; } - case 7: { - if (value & ~((1ULL << 32) - 1)) { + vcpu->arch.dr6 = (value & DR6_VOLATILE) | DR6_FIXED_1; + return; + case 7: + if (value & 0xffffffff00000000ULL) { *exception = GP_VECTOR; return; } - svm->vmcb->save.dr7 = value; + vcpu->arch.dr7 = (value & DR7_VOLATILE) | DR7_FIXED_1; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { + svm->vmcb->save.dr7 = vcpu->arch.dr7; + vcpu->arch.switch_db_regs = (value & DR7_BP_EN_MASK); + } return; - } default: + /* FIXME: Possible case? */ printk(KERN_DEBUG "%s: unexpected dr %u\n", __func__, dr); *exception = UD_VECTOR; @@ -1031,6 +1141,27 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code); } +static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + if (!(svm->vcpu.guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { + kvm_queue_exception(&svm->vcpu, DB_VECTOR); + return 1; + } + kvm_run->exit_reason = KVM_EXIT_DEBUG; + kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; + kvm_run->debug.arch.exception = DB_VECTOR; + return 0; +} + +static int bp_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + kvm_run->exit_reason = KVM_EXIT_DEBUG; + kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; + kvm_run->debug.arch.exception = BP_VECTOR; + return 0; +} + static int ud_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { int er; @@ -1080,7 +1211,7 @@ static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */ - int size, down, in, string, rep; + int size, in, string; unsigned port; ++svm->vcpu.stat.io_exits; @@ -1099,8 +1230,6 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) in = (io_info & SVM_IOIO_TYPE_MASK) != 0; port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; - rep = (io_info & SVM_IOIO_REP_MASK) != 0; - down = (svm->vmcb->save.rflags & X86_EFLAGS_DF) != 0; skip_emulated_instruction(&svm->vcpu); return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port); @@ -1139,6 +1268,567 @@ static int vmmcall_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } +static int nested_svm_check_permissions(struct vcpu_svm *svm) +{ + if (!(svm->vcpu.arch.shadow_efer & EFER_SVME) + || !is_paging(&svm->vcpu)) { + kvm_queue_exception(&svm->vcpu, UD_VECTOR); + return 1; + } + + if (svm->vmcb->save.cpl) { + kvm_inject_gp(&svm->vcpu, 0); + return 1; + } + + return 0; +} + +static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, + bool has_error_code, u32 error_code) +{ + if (is_nested(svm)) { + svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = error_code; + svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; + if (nested_svm_exit_handled(svm, false)) { + nsvm_printk("VMexit -> EXCP 0x%x\n", nr); + + nested_svm_vmexit(svm); + return 1; + } + } + + return 0; +} + +static inline int nested_svm_intr(struct vcpu_svm *svm) +{ + if (is_nested(svm)) { + if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) + return 0; + + if (!(svm->vcpu.arch.hflags & HF_HIF_MASK)) + return 0; + + svm->vmcb->control.exit_code = SVM_EXIT_INTR; + + if (nested_svm_exit_handled(svm, false)) { + nsvm_printk("VMexit -> INTR\n"); + nested_svm_vmexit(svm); + return 1; + } + } + + return 0; +} + +static struct page *nested_svm_get_page(struct vcpu_svm *svm, u64 gpa) +{ + struct page *page; + + down_read(¤t->mm->mmap_sem); + page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT); + up_read(¤t->mm->mmap_sem); + + if (is_error_page(page)) { + printk(KERN_INFO "%s: could not find page at 0x%llx\n", + __func__, gpa); + kvm_release_page_clean(page); + kvm_inject_gp(&svm->vcpu, 0); + return NULL; + } + return page; +} + +static int nested_svm_do(struct vcpu_svm *svm, + u64 arg1_gpa, u64 arg2_gpa, void *opaque, + int (*handler)(struct vcpu_svm *svm, + void *arg1, + void *arg2, + void *opaque)) +{ + struct page *arg1_page; + struct page *arg2_page = NULL; + void *arg1; + void *arg2 = NULL; + int retval; + + arg1_page = nested_svm_get_page(svm, arg1_gpa); + if(arg1_page == NULL) + return 1; + + if (arg2_gpa) { + arg2_page = nested_svm_get_page(svm, arg2_gpa); + if(arg2_page == NULL) { + kvm_release_page_clean(arg1_page); + return 1; + } + } + + arg1 = kmap_atomic(arg1_page, KM_USER0); + if (arg2_gpa) + arg2 = kmap_atomic(arg2_page, KM_USER1); + + retval = handler(svm, arg1, arg2, opaque); + + kunmap_atomic(arg1, KM_USER0); + if (arg2_gpa) + kunmap_atomic(arg2, KM_USER1); + + kvm_release_page_dirty(arg1_page); + if (arg2_gpa) + kvm_release_page_dirty(arg2_page); + + return retval; +} + +static int nested_svm_exit_handled_real(struct vcpu_svm *svm, + void *arg1, + void *arg2, + void *opaque) +{ + struct vmcb *nested_vmcb = (struct vmcb *)arg1; + bool kvm_overrides = *(bool *)opaque; + u32 exit_code = svm->vmcb->control.exit_code; + + if (kvm_overrides) { + switch (exit_code) { + case SVM_EXIT_INTR: + case SVM_EXIT_NMI: + return 0; + /* For now we are always handling NPFs when using them */ + case SVM_EXIT_NPF: + if (npt_enabled) + return 0; + break; + /* When we're shadowing, trap PFs */ + case SVM_EXIT_EXCP_BASE + PF_VECTOR: + if (!npt_enabled) + return 0; + break; + default: + break; + } + } + + switch (exit_code) { + case SVM_EXIT_READ_CR0 ... SVM_EXIT_READ_CR8: { + u32 cr_bits = 1 << (exit_code - SVM_EXIT_READ_CR0); + if (nested_vmcb->control.intercept_cr_read & cr_bits) + return 1; + break; + } + case SVM_EXIT_WRITE_CR0 ... SVM_EXIT_WRITE_CR8: { + u32 cr_bits = 1 << (exit_code - SVM_EXIT_WRITE_CR0); + if (nested_vmcb->control.intercept_cr_write & cr_bits) + return 1; + break; + } + case SVM_EXIT_READ_DR0 ... SVM_EXIT_READ_DR7: { + u32 dr_bits = 1 << (exit_code - SVM_EXIT_READ_DR0); + if (nested_vmcb->control.intercept_dr_read & dr_bits) + return 1; + break; + } + case SVM_EXIT_WRITE_DR0 ... SVM_EXIT_WRITE_DR7: { + u32 dr_bits = 1 << (exit_code - SVM_EXIT_WRITE_DR0); + if (nested_vmcb->control.intercept_dr_write & dr_bits) + return 1; + break; + } + case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: { + u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE); + if (nested_vmcb->control.intercept_exceptions & excp_bits) + return 1; + break; + } + default: { + u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR); + nsvm_printk("exit code: 0x%x\n", exit_code); + if (nested_vmcb->control.intercept & exit_bits) + return 1; + } + } + + return 0; +} + +static int nested_svm_exit_handled_msr(struct vcpu_svm *svm, + void *arg1, void *arg2, + void *opaque) +{ + struct vmcb *nested_vmcb = (struct vmcb *)arg1; + u8 *msrpm = (u8 *)arg2; + u32 t0, t1; + u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + u32 param = svm->vmcb->control.exit_info_1 & 1; + + if (!(nested_vmcb->control.intercept & (1ULL << INTERCEPT_MSR_PROT))) + return 0; + + switch(msr) { + case 0 ... 0x1fff: + t0 = (msr * 2) % 8; + t1 = msr / 8; + break; + case 0xc0000000 ... 0xc0001fff: + t0 = (8192 + msr - 0xc0000000) * 2; + t1 = (t0 / 8); + t0 %= 8; + break; + case 0xc0010000 ... 0xc0011fff: + t0 = (16384 + msr - 0xc0010000) * 2; + t1 = (t0 / 8); + t0 %= 8; + break; + default: + return 1; + break; + } + if (msrpm[t1] & ((1 << param) << t0)) + return 1; + + return 0; +} + +static int nested_svm_exit_handled(struct vcpu_svm *svm, bool kvm_override) +{ + bool k = kvm_override; + + switch (svm->vmcb->control.exit_code) { + case SVM_EXIT_MSR: + return nested_svm_do(svm, svm->nested_vmcb, + svm->nested_vmcb_msrpm, NULL, + nested_svm_exit_handled_msr); + default: break; + } + + return nested_svm_do(svm, svm->nested_vmcb, 0, &k, + nested_svm_exit_handled_real); +} + +static int nested_svm_vmexit_real(struct vcpu_svm *svm, void *arg1, + void *arg2, void *opaque) +{ + struct vmcb *nested_vmcb = (struct vmcb *)arg1; + struct vmcb *hsave = svm->hsave; + u64 nested_save[] = { nested_vmcb->save.cr0, + nested_vmcb->save.cr3, + nested_vmcb->save.cr4, + nested_vmcb->save.efer, + nested_vmcb->control.intercept_cr_read, + nested_vmcb->control.intercept_cr_write, + nested_vmcb->control.intercept_dr_read, + nested_vmcb->control.intercept_dr_write, + nested_vmcb->control.intercept_exceptions, + nested_vmcb->control.intercept, + nested_vmcb->control.msrpm_base_pa, + nested_vmcb->control.iopm_base_pa, + nested_vmcb->control.tsc_offset }; + + /* Give the current vmcb to the guest */ + memcpy(nested_vmcb, svm->vmcb, sizeof(struct vmcb)); + nested_vmcb->save.cr0 = nested_save[0]; + if (!npt_enabled) + nested_vmcb->save.cr3 = nested_save[1]; + nested_vmcb->save.cr4 = nested_save[2]; + nested_vmcb->save.efer = nested_save[3]; + nested_vmcb->control.intercept_cr_read = nested_save[4]; + nested_vmcb->control.intercept_cr_write = nested_save[5]; + nested_vmcb->control.intercept_dr_read = nested_save[6]; + nested_vmcb->control.intercept_dr_write = nested_save[7]; + nested_vmcb->control.intercept_exceptions = nested_save[8]; + nested_vmcb->control.intercept = nested_save[9]; + nested_vmcb->control.msrpm_base_pa = nested_save[10]; + nested_vmcb->control.iopm_base_pa = nested_save[11]; + nested_vmcb->control.tsc_offset = nested_save[12]; + + /* We always set V_INTR_MASKING and remember the old value in hflags */ + if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) + nested_vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK; + + if ((nested_vmcb->control.int_ctl & V_IRQ_MASK) && + (nested_vmcb->control.int_vector)) { + nsvm_printk("WARNING: IRQ 0x%x still enabled on #VMEXIT\n", + nested_vmcb->control.int_vector); + } + + /* Restore the original control entries */ + svm->vmcb->control = hsave->control; + + /* Kill any pending exceptions */ + if (svm->vcpu.arch.exception.pending == true) + nsvm_printk("WARNING: Pending Exception\n"); + svm->vcpu.arch.exception.pending = false; + + /* Restore selected save entries */ + svm->vmcb->save.es = hsave->save.es; + svm->vmcb->save.cs = hsave->save.cs; + svm->vmcb->save.ss = hsave->save.ss; + svm->vmcb->save.ds = hsave->save.ds; + svm->vmcb->save.gdtr = hsave->save.gdtr; + svm->vmcb->save.idtr = hsave->save.idtr; + svm->vmcb->save.rflags = hsave->save.rflags; + svm_set_efer(&svm->vcpu, hsave->save.efer); + svm_set_cr0(&svm->vcpu, hsave->save.cr0 | X86_CR0_PE); + svm_set_cr4(&svm->vcpu, hsave->save.cr4); + if (npt_enabled) { + svm->vmcb->save.cr3 = hsave->save.cr3; + svm->vcpu.arch.cr3 = hsave->save.cr3; + } else { + kvm_set_cr3(&svm->vcpu, hsave->save.cr3); + } + kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, hsave->save.rax); + kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, hsave->save.rsp); + kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, hsave->save.rip); + svm->vmcb->save.dr7 = 0; + svm->vmcb->save.cpl = 0; + svm->vmcb->control.exit_int_info = 0; + + svm->vcpu.arch.hflags &= ~HF_GIF_MASK; + /* Exit nested SVM mode */ + svm->nested_vmcb = 0; + + return 0; +} + +static int nested_svm_vmexit(struct vcpu_svm *svm) +{ + nsvm_printk("VMexit\n"); + if (nested_svm_do(svm, svm->nested_vmcb, 0, + NULL, nested_svm_vmexit_real)) + return 1; + + kvm_mmu_reset_context(&svm->vcpu); + kvm_mmu_load(&svm->vcpu); + + return 0; +} + +static int nested_svm_vmrun_msrpm(struct vcpu_svm *svm, void *arg1, + void *arg2, void *opaque) +{ + int i; + u32 *nested_msrpm = (u32*)arg1; + for (i=0; i< PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER) / 4; i++) + svm->nested_msrpm[i] = svm->msrpm[i] | nested_msrpm[i]; + svm->vmcb->control.msrpm_base_pa = __pa(svm->nested_msrpm); + + return 0; +} + +static int nested_svm_vmrun(struct vcpu_svm *svm, void *arg1, + void *arg2, void *opaque) +{ + struct vmcb *nested_vmcb = (struct vmcb *)arg1; + struct vmcb *hsave = svm->hsave; + + /* nested_vmcb is our indicator if nested SVM is activated */ + svm->nested_vmcb = svm->vmcb->save.rax; + + /* Clear internal status */ + svm->vcpu.arch.exception.pending = false; + + /* Save the old vmcb, so we don't need to pick what we save, but + can restore everything when a VMEXIT occurs */ + memcpy(hsave, svm->vmcb, sizeof(struct vmcb)); + /* We need to remember the original CR3 in the SPT case */ + if (!npt_enabled) + hsave->save.cr3 = svm->vcpu.arch.cr3; + hsave->save.cr4 = svm->vcpu.arch.cr4; + hsave->save.rip = svm->next_rip; + + if (svm->vmcb->save.rflags & X86_EFLAGS_IF) + svm->vcpu.arch.hflags |= HF_HIF_MASK; + else + svm->vcpu.arch.hflags &= ~HF_HIF_MASK; + + /* Load the nested guest state */ + svm->vmcb->save.es = nested_vmcb->save.es; + svm->vmcb->save.cs = nested_vmcb->save.cs; + svm->vmcb->save.ss = nested_vmcb->save.ss; + svm->vmcb->save.ds = nested_vmcb->save.ds; + svm->vmcb->save.gdtr = nested_vmcb->save.gdtr; + svm->vmcb->save.idtr = nested_vmcb->save.idtr; + svm->vmcb->save.rflags = nested_vmcb->save.rflags; + svm_set_efer(&svm->vcpu, nested_vmcb->save.efer); + svm_set_cr0(&svm->vcpu, nested_vmcb->save.cr0); + svm_set_cr4(&svm->vcpu, nested_vmcb->save.cr4); + if (npt_enabled) { + svm->vmcb->save.cr3 = nested_vmcb->save.cr3; + svm->vcpu.arch.cr3 = nested_vmcb->save.cr3; + } else { + kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3); + kvm_mmu_reset_context(&svm->vcpu); + } + svm->vmcb->save.cr2 = nested_vmcb->save.cr2; + kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax); + kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp); + kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip); + /* In case we don't even reach vcpu_run, the fields are not updated */ + svm->vmcb->save.rax = nested_vmcb->save.rax; + svm->vmcb->save.rsp = nested_vmcb->save.rsp; + svm->vmcb->save.rip = nested_vmcb->save.rip; + svm->vmcb->save.dr7 = nested_vmcb->save.dr7; + svm->vmcb->save.dr6 = nested_vmcb->save.dr6; + svm->vmcb->save.cpl = nested_vmcb->save.cpl; + + /* We don't want a nested guest to be more powerful than the guest, + so all intercepts are ORed */ + svm->vmcb->control.intercept_cr_read |= + nested_vmcb->control.intercept_cr_read; + svm->vmcb->control.intercept_cr_write |= + nested_vmcb->control.intercept_cr_write; + svm->vmcb->control.intercept_dr_read |= + nested_vmcb->control.intercept_dr_read; + svm->vmcb->control.intercept_dr_write |= + nested_vmcb->control.intercept_dr_write; + svm->vmcb->control.intercept_exceptions |= + nested_vmcb->control.intercept_exceptions; + + svm->vmcb->control.intercept |= nested_vmcb->control.intercept; + + svm->nested_vmcb_msrpm = nested_vmcb->control.msrpm_base_pa; + + force_new_asid(&svm->vcpu); + svm->vmcb->control.exit_int_info = nested_vmcb->control.exit_int_info; + svm->vmcb->control.exit_int_info_err = nested_vmcb->control.exit_int_info_err; + svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK; + if (nested_vmcb->control.int_ctl & V_IRQ_MASK) { + nsvm_printk("nSVM Injecting Interrupt: 0x%x\n", + nested_vmcb->control.int_ctl); + } + if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK) + svm->vcpu.arch.hflags |= HF_VINTR_MASK; + else + svm->vcpu.arch.hflags &= ~HF_VINTR_MASK; + + nsvm_printk("nSVM exit_int_info: 0x%x | int_state: 0x%x\n", + nested_vmcb->control.exit_int_info, + nested_vmcb->control.int_state); + + svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; + svm->vmcb->control.int_state = nested_vmcb->control.int_state; + svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset; + if (nested_vmcb->control.event_inj & SVM_EVTINJ_VALID) + nsvm_printk("Injecting Event: 0x%x\n", + nested_vmcb->control.event_inj); + svm->vmcb->control.event_inj = nested_vmcb->control.event_inj; + svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err; + + svm->vcpu.arch.hflags |= HF_GIF_MASK; + + return 0; +} + +static int nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) +{ + to_vmcb->save.fs = from_vmcb->save.fs; + to_vmcb->save.gs = from_vmcb->save.gs; + to_vmcb->save.tr = from_vmcb->save.tr; + to_vmcb->save.ldtr = from_vmcb->save.ldtr; + to_vmcb->save.kernel_gs_base = from_vmcb->save.kernel_gs_base; + to_vmcb->save.star = from_vmcb->save.star; + to_vmcb->save.lstar = from_vmcb->save.lstar; + to_vmcb->save.cstar = from_vmcb->save.cstar; + to_vmcb->save.sfmask = from_vmcb->save.sfmask; + to_vmcb->save.sysenter_cs = from_vmcb->save.sysenter_cs; + to_vmcb->save.sysenter_esp = from_vmcb->save.sysenter_esp; + to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip; + + return 1; +} + +static int nested_svm_vmload(struct vcpu_svm *svm, void *nested_vmcb, + void *arg2, void *opaque) +{ + return nested_svm_vmloadsave((struct vmcb *)nested_vmcb, svm->vmcb); +} + +static int nested_svm_vmsave(struct vcpu_svm *svm, void *nested_vmcb, + void *arg2, void *opaque) +{ + return nested_svm_vmloadsave(svm->vmcb, (struct vmcb *)nested_vmcb); +} + +static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + if (nested_svm_check_permissions(svm)) + return 1; + + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + + nested_svm_do(svm, svm->vmcb->save.rax, 0, NULL, nested_svm_vmload); + + return 1; +} + +static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + if (nested_svm_check_permissions(svm)) + return 1; + + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + + nested_svm_do(svm, svm->vmcb->save.rax, 0, NULL, nested_svm_vmsave); + + return 1; +} + +static int vmrun_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + nsvm_printk("VMrun\n"); + if (nested_svm_check_permissions(svm)) + return 1; + + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + + if (nested_svm_do(svm, svm->vmcb->save.rax, 0, + NULL, nested_svm_vmrun)) + return 1; + + if (nested_svm_do(svm, svm->nested_vmcb_msrpm, 0, + NULL, nested_svm_vmrun_msrpm)) + return 1; + + return 1; +} + +static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + if (nested_svm_check_permissions(svm)) + return 1; + + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + + svm->vcpu.arch.hflags |= HF_GIF_MASK; + + return 1; +} + +static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + if (nested_svm_check_permissions(svm)) + return 1; + + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + + svm->vcpu.arch.hflags &= ~HF_GIF_MASK; + + /* After a CLGI no interrupts should come */ + svm_clear_vintr(svm); + svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; + + return 1; +} + static int invalid_op_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { @@ -1250,6 +1940,15 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) case MSR_IA32_LASTINTTOIP: *data = svm->vmcb->save.last_excp_to; break; + case MSR_VM_HSAVE_PA: + *data = svm->hsave_msr; + break; + case MSR_VM_CR: + *data = 0; + break; + case MSR_IA32_UCODE_REV: + *data = 0x01000065; + break; default: return kvm_get_msr_common(vcpu, ecx, data); } @@ -1344,6 +2043,9 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) pr_unimpl(vcpu, "unimplemented perfctr wrmsr: 0x%x data 0x%llx\n", ecx, data); break; + case MSR_VM_HSAVE_PA: + svm->hsave_msr = data; + break; default: return kvm_set_msr_common(vcpu, ecx, data); } @@ -1380,7 +2082,7 @@ static int interrupt_window_interception(struct vcpu_svm *svm, { KVMTRACE_0D(PEND_INTR, &svm->vcpu, handler); - svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VINTR); + svm_clear_vintr(svm); svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; /* * If the user space waits to inject interrupts, exit as soon as @@ -1417,6 +2119,8 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm, [SVM_EXIT_WRITE_DR3] = emulate_on_interception, [SVM_EXIT_WRITE_DR5] = emulate_on_interception, [SVM_EXIT_WRITE_DR7] = emulate_on_interception, + [SVM_EXIT_EXCP_BASE + DB_VECTOR] = db_interception, + [SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception, [SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception, [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, @@ -1436,12 +2140,12 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm, [SVM_EXIT_MSR] = msr_interception, [SVM_EXIT_TASK_SWITCH] = task_switch_interception, [SVM_EXIT_SHUTDOWN] = shutdown_interception, - [SVM_EXIT_VMRUN] = invalid_op_interception, + [SVM_EXIT_VMRUN] = vmrun_interception, [SVM_EXIT_VMMCALL] = vmmcall_interception, - [SVM_EXIT_VMLOAD] = invalid_op_interception, - [SVM_EXIT_VMSAVE] = invalid_op_interception, - [SVM_EXIT_STGI] = invalid_op_interception, - [SVM_EXIT_CLGI] = invalid_op_interception, + [SVM_EXIT_VMLOAD] = vmload_interception, + [SVM_EXIT_VMSAVE] = vmsave_interception, + [SVM_EXIT_STGI] = stgi_interception, + [SVM_EXIT_CLGI] = clgi_interception, [SVM_EXIT_SKINIT] = invalid_op_interception, [SVM_EXIT_WBINVD] = emulate_on_interception, [SVM_EXIT_MONITOR] = invalid_op_interception, @@ -1457,6 +2161,17 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) KVMTRACE_3D(VMEXIT, vcpu, exit_code, (u32)svm->vmcb->save.rip, (u32)((u64)svm->vmcb->save.rip >> 32), entryexit); + if (is_nested(svm)) { + nsvm_printk("nested handle_exit: 0x%x | 0x%lx | 0x%lx | 0x%lx\n", + exit_code, svm->vmcb->control.exit_info_1, + svm->vmcb->control.exit_info_2, svm->vmcb->save.rip); + if (nested_svm_exit_handled(svm, true)) { + nested_svm_vmexit(svm); + nsvm_printk("-> #VMEXIT\n"); + return 1; + } + } + if (npt_enabled) { int mmu_reload = 0; if ((vcpu->arch.cr0 ^ svm->vmcb->save.cr0) & X86_CR0_PG) { @@ -1544,6 +2259,8 @@ static void svm_set_irq(struct kvm_vcpu *vcpu, int irq) { struct vcpu_svm *svm = to_svm(vcpu); + nested_svm_intr(svm); + svm_inject_irq(svm, irq); } @@ -1589,11 +2306,17 @@ static void svm_intr_assist(struct kvm_vcpu *vcpu) if (!kvm_cpu_has_interrupt(vcpu)) goto out; + if (nested_svm_intr(svm)) + goto out; + + if (!(svm->vcpu.arch.hflags & HF_GIF_MASK)) + goto out; + if (!(vmcb->save.rflags & X86_EFLAGS_IF) || (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || (vmcb->control.event_inj & SVM_EVTINJ_VALID)) { /* unable to deliver irq, set pending irq */ - vmcb->control.intercept |= (1ULL << INTERCEPT_VINTR); + svm_set_vintr(svm); svm_inject_irq(svm, 0x0); goto out; } @@ -1615,7 +2338,8 @@ static void kvm_reput_irq(struct vcpu_svm *svm) } svm->vcpu.arch.interrupt_window_open = - !(control->int_state & SVM_INTERRUPT_SHADOW_MASK); + !(control->int_state & SVM_INTERRUPT_SHADOW_MASK) && + (svm->vcpu.arch.hflags & HF_GIF_MASK); } static void svm_do_inject_vector(struct vcpu_svm *svm) @@ -1637,9 +2361,13 @@ static void do_interrupt_requests(struct kvm_vcpu *vcpu, struct vcpu_svm *svm = to_svm(vcpu); struct vmcb_control_area *control = &svm->vmcb->control; + if (nested_svm_intr(svm)) + return; + svm->vcpu.arch.interrupt_window_open = (!(control->int_state & SVM_INTERRUPT_SHADOW_MASK) && - (svm->vmcb->save.rflags & X86_EFLAGS_IF)); + (svm->vmcb->save.rflags & X86_EFLAGS_IF) && + (svm->vcpu.arch.hflags & HF_GIF_MASK)); if (svm->vcpu.arch.interrupt_window_open && svm->vcpu.arch.irq_summary) /* @@ -1652,9 +2380,9 @@ static void do_interrupt_requests(struct kvm_vcpu *vcpu, */ if (!svm->vcpu.arch.interrupt_window_open && (svm->vcpu.arch.irq_summary || kvm_run->request_interrupt_window)) - control->intercept |= 1ULL << INTERCEPT_VINTR; - else - control->intercept &= ~(1ULL << INTERCEPT_VINTR); + svm_set_vintr(svm); + else + svm_clear_vintr(svm); } static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) @@ -1662,22 +2390,6 @@ static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) return 0; } -static void save_db_regs(unsigned long *db_regs) -{ - asm volatile ("mov %%dr0, %0" : "=r"(db_regs[0])); - asm volatile ("mov %%dr1, %0" : "=r"(db_regs[1])); - asm volatile ("mov %%dr2, %0" : "=r"(db_regs[2])); - asm volatile ("mov %%dr3, %0" : "=r"(db_regs[3])); -} - -static void load_db_regs(unsigned long *db_regs) -{ - asm volatile ("mov %0, %%dr0" : : "r"(db_regs[0])); - asm volatile ("mov %0, %%dr1" : : "r"(db_regs[1])); - asm volatile ("mov %0, %%dr2" : : "r"(db_regs[2])); - asm volatile ("mov %0, %%dr3" : : "r"(db_regs[3])); -} - static void svm_flush_tlb(struct kvm_vcpu *vcpu) { force_new_asid(vcpu); @@ -1736,19 +2448,12 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) gs_selector = kvm_read_gs(); ldt_selector = kvm_read_ldt(); svm->host_cr2 = kvm_read_cr2(); - svm->host_dr6 = read_dr6(); - svm->host_dr7 = read_dr7(); - svm->vmcb->save.cr2 = vcpu->arch.cr2; + if (!is_nested(svm)) + svm->vmcb->save.cr2 = vcpu->arch.cr2; /* required for live migration with NPT */ if (npt_enabled) svm->vmcb->save.cr3 = vcpu->arch.cr3; - if (svm->vmcb->save.dr7 & 0xff) { - write_dr7(0); - save_db_regs(svm->host_db_regs); - load_db_regs(svm->db_regs); - } - clgi(); local_irq_enable(); @@ -1824,16 +2529,11 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) #endif ); - if ((svm->vmcb->save.dr7 & 0xff)) - load_db_regs(svm->host_db_regs); - vcpu->arch.cr2 = svm->vmcb->save.cr2; vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax; vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; - write_dr6(svm->host_dr6); - write_dr7(svm->host_dr7); kvm_write_cr2(svm->host_cr2); kvm_load_fs(fs_selector); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 7611af5..bb48133 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -91,6 +91,7 @@ struct vcpu_vmx { } rmode; int vpid; bool emulation_required; + enum emulation_result invalid_state_emulation_result; /* Support for vnmi-less CPUs */ int soft_vnmi_blocked; @@ -189,21 +190,21 @@ static inline int is_page_fault(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == - (INTR_TYPE_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK); + (INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK); } static inline int is_no_device(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == - (INTR_TYPE_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK); + (INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK); } static inline int is_invalid_opcode(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == - (INTR_TYPE_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK); + (INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK); } static inline int is_external_interrupt(u32 intr_info) @@ -480,8 +481,13 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) eb = (1u << PF_VECTOR) | (1u << UD_VECTOR); if (!vcpu->fpu_active) eb |= 1u << NM_VECTOR; - if (vcpu->guest_debug.enabled) - eb |= 1u << DB_VECTOR; + if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { + if (vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) + eb |= 1u << DB_VECTOR; + if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) + eb |= 1u << BP_VECTOR; + } if (vcpu->arch.rmode.active) eb = ~0; if (vm_need_ept()) @@ -747,29 +753,33 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error_code, u32 error_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 intr_info = nr | INTR_INFO_VALID_MASK; - if (has_error_code) + if (has_error_code) { vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); + intr_info |= INTR_INFO_DELIVER_CODE_MASK; + } if (vcpu->arch.rmode.active) { vmx->rmode.irq.pending = true; vmx->rmode.irq.vector = nr; vmx->rmode.irq.rip = kvm_rip_read(vcpu); - if (nr == BP_VECTOR) + if (nr == BP_VECTOR || nr == OF_VECTOR) vmx->rmode.irq.rip++; - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - nr | INTR_TYPE_SOFT_INTR - | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0) - | INTR_INFO_VALID_MASK); + intr_info |= INTR_TYPE_SOFT_INTR; + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info); vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1); kvm_rip_write(vcpu, vmx->rmode.irq.rip - 1); return; } - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - nr | INTR_TYPE_EXCEPTION - | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0) - | INTR_INFO_VALID_MASK); + if (nr == BP_VECTOR || nr == OF_VECTOR) { + vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1); + intr_info |= INTR_TYPE_SOFT_EXCEPTION; + } else + intr_info |= INTR_TYPE_HARD_EXCEPTION; + + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info); } static bool vmx_exception_injected(struct kvm_vcpu *vcpu) @@ -856,11 +866,8 @@ static u64 guest_read_tsc(void) * writes 'guest_tsc' into guest's timestamp counter "register" * guest_tsc = host_tsc + tsc_offset ==> tsc_offset = guest_tsc - host_tsc */ -static void guest_write_tsc(u64 guest_tsc) +static void guest_write_tsc(u64 guest_tsc, u64 host_tsc) { - u64 host_tsc; - - rdtscll(host_tsc); vmcs_write64(TSC_OFFSET, guest_tsc - host_tsc); } @@ -925,14 +932,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_msr_entry *msr; + u64 host_tsc; int ret = 0; switch (msr_index) { -#ifdef CONFIG_X86_64 case MSR_EFER: vmx_load_host_state(vmx); ret = kvm_set_msr_common(vcpu, msr_index, data); break; +#ifdef CONFIG_X86_64 case MSR_FS_BASE: vmcs_writel(GUEST_FS_BASE, data); break; @@ -950,7 +958,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_TIME_STAMP_COUNTER: - guest_write_tsc(data); + rdtscll(host_tsc); + guest_write_tsc(data, host_tsc); break; case MSR_P6_PERFCTR0: case MSR_P6_PERFCTR1: @@ -999,40 +1008,28 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) } } -static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) +static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - unsigned long dr7 = 0x400; - int old_singlestep; - - old_singlestep = vcpu->guest_debug.singlestep; - - vcpu->guest_debug.enabled = dbg->enabled; - if (vcpu->guest_debug.enabled) { - int i; + int old_debug = vcpu->guest_debug; + unsigned long flags; - dr7 |= 0x200; /* exact */ - for (i = 0; i < 4; ++i) { - if (!dbg->breakpoints[i].enabled) - continue; - vcpu->guest_debug.bp[i] = dbg->breakpoints[i].address; - dr7 |= 2 << (i*2); /* global enable */ - dr7 |= 0 << (i*4+16); /* execution breakpoint */ - } + vcpu->guest_debug = dbg->control; + if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)) + vcpu->guest_debug = 0; - vcpu->guest_debug.singlestep = dbg->singlestep; - } else - vcpu->guest_debug.singlestep = 0; - - if (old_singlestep && !vcpu->guest_debug.singlestep) { - unsigned long flags; + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) + vmcs_writel(GUEST_DR7, dbg->arch.debugreg[7]); + else + vmcs_writel(GUEST_DR7, vcpu->arch.dr7); - flags = vmcs_readl(GUEST_RFLAGS); + flags = vmcs_readl(GUEST_RFLAGS); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + flags |= X86_EFLAGS_TF | X86_EFLAGS_RF; + else if (old_debug & KVM_GUESTDBG_SINGLESTEP) flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - vmcs_writel(GUEST_RFLAGS, flags); - } + vmcs_writel(GUEST_RFLAGS, flags); update_exception_bitmap(vcpu); - vmcs_writel(GUEST_DR7, dr7); return 0; } @@ -1433,6 +1430,29 @@ continue_rmode: init_rmode(vcpu->kvm); } +static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER); + + vcpu->arch.shadow_efer = efer; + if (!msr) + return; + if (efer & EFER_LMA) { + vmcs_write32(VM_ENTRY_CONTROLS, + vmcs_read32(VM_ENTRY_CONTROLS) | + VM_ENTRY_IA32E_MODE); + msr->data = efer; + } else { + vmcs_write32(VM_ENTRY_CONTROLS, + vmcs_read32(VM_ENTRY_CONTROLS) & + ~VM_ENTRY_IA32E_MODE); + + msr->data = efer & ~EFER_LME; + } + setup_msrs(vmx); +} + #ifdef CONFIG_X86_64 static void enter_lmode(struct kvm_vcpu *vcpu) @@ -1447,13 +1467,8 @@ static void enter_lmode(struct kvm_vcpu *vcpu) (guest_tr_ar & ~AR_TYPE_MASK) | AR_TYPE_BUSY_64_TSS); } - vcpu->arch.shadow_efer |= EFER_LMA; - - find_msr_entry(to_vmx(vcpu), MSR_EFER)->data |= EFER_LMA | EFER_LME; - vmcs_write32(VM_ENTRY_CONTROLS, - vmcs_read32(VM_ENTRY_CONTROLS) - | VM_ENTRY_IA32E_MODE); + vmx_set_efer(vcpu, vcpu->arch.shadow_efer); } static void exit_lmode(struct kvm_vcpu *vcpu) @@ -1612,30 +1627,6 @@ static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) vmcs_writel(GUEST_CR4, hw_cr4); } -static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER); - - vcpu->arch.shadow_efer = efer; - if (!msr) - return; - if (efer & EFER_LMA) { - vmcs_write32(VM_ENTRY_CONTROLS, - vmcs_read32(VM_ENTRY_CONTROLS) | - VM_ENTRY_IA32E_MODE); - msr->data = efer; - - } else { - vmcs_write32(VM_ENTRY_CONTROLS, - vmcs_read32(VM_ENTRY_CONTROLS) & - ~VM_ENTRY_IA32E_MODE); - - msr->data = efer & ~EFER_LME; - } - setup_msrs(vmx); -} - static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) { struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; @@ -1653,7 +1644,7 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu, var->limit = vmcs_read32(sf->limit); var->selector = vmcs_read16(sf->selector); ar = vmcs_read32(sf->ar_bytes); - if (ar & AR_UNUSABLE_MASK) + if ((ar & AR_UNUSABLE_MASK) && !emulate_invalid_guest_state) ar = 0; var->type = ar & 15; var->s = (ar >> 4) & 1; @@ -1788,14 +1779,16 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu) vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); cs_rpl = cs.selector & SELECTOR_RPL_MASK; + if (cs.unusable) + return false; if (~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_ACCESSES_MASK)) return false; if (!cs.s) return false; - if (!(~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_WRITEABLE_MASK))) { + if (cs.type & AR_TYPE_WRITEABLE_MASK) { if (cs.dpl > cs_rpl) return false; - } else if (cs.type & AR_TYPE_CODE_MASK) { + } else { if (cs.dpl != cs_rpl) return false; } @@ -1814,7 +1807,9 @@ static bool stack_segment_valid(struct kvm_vcpu *vcpu) vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); ss_rpl = ss.selector & SELECTOR_RPL_MASK; - if ((ss.type != 3) || (ss.type != 7)) + if (ss.unusable) + return true; + if (ss.type != 3 && ss.type != 7) return false; if (!ss.s) return false; @@ -1834,6 +1829,8 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg) vmx_get_segment(vcpu, &var, seg); rpl = var.selector & SELECTOR_RPL_MASK; + if (var.unusable) + return true; if (!var.s) return false; if (!var.present) @@ -1855,9 +1852,11 @@ static bool tr_valid(struct kvm_vcpu *vcpu) vmx_get_segment(vcpu, &tr, VCPU_SREG_TR); + if (tr.unusable) + return false; if (tr.selector & SELECTOR_TI_MASK) /* TI = 1 */ return false; - if ((tr.type != 3) || (tr.type != 11)) /* TODO: Check if guest is in IA32e mode */ + if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */ return false; if (!tr.present) return false; @@ -1871,6 +1870,8 @@ static bool ldtr_valid(struct kvm_vcpu *vcpu) vmx_get_segment(vcpu, &ldtr, VCPU_SREG_LDTR); + if (ldtr.unusable) + return true; if (ldtr.selector & SELECTOR_TI_MASK) /* TI = 1 */ return false; if (ldtr.type != 2) @@ -2112,7 +2113,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) { u32 host_sysenter_cs, msr_low, msr_high; u32 junk; - u64 host_pat; + u64 host_pat, tsc_this, tsc_base; unsigned long a; struct descriptor_table dt; int i; @@ -2240,6 +2241,12 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK); + tsc_base = vmx->vcpu.kvm->arch.vm_init_tsc; + rdtscll(tsc_this); + if (tsc_this < vmx->vcpu.kvm->arch.vm_init_tsc) + tsc_base = tsc_this; + + guest_write_tsc(0, tsc_base); return 0; } @@ -2319,7 +2326,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) kvm_rip_write(vcpu, 0); kvm_register_write(vcpu, VCPU_REGS_RSP, 0); - /* todo: dr0 = dr1 = dr2 = dr3 = 0; dr6 = 0xffff0ff0 */ vmcs_writel(GUEST_DR7, 0x400); vmcs_writel(GUEST_GDTR_BASE, 0); @@ -2332,8 +2338,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); - guest_write_tsc(0); - /* Special registers */ vmcs_write64(GUEST_IA32_DEBUGCTL, 0); @@ -2486,6 +2490,11 @@ static void do_interrupt_requests(struct kvm_vcpu *vcpu, { vmx_update_window_states(vcpu); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_STI | + GUEST_INTR_STATE_MOV_SS); + if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) { if (vcpu->arch.interrupt.pending) { enable_nmi_window(vcpu); @@ -2536,24 +2545,6 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) return 0; } -static void kvm_guest_debug_pre(struct kvm_vcpu *vcpu) -{ - struct kvm_guest_debug *dbg = &vcpu->guest_debug; - - set_debugreg(dbg->bp[0], 0); - set_debugreg(dbg->bp[1], 1); - set_debugreg(dbg->bp[2], 2); - set_debugreg(dbg->bp[3], 3); - - if (dbg->singlestep) { - unsigned long flags; - - flags = vmcs_readl(GUEST_RFLAGS); - flags |= X86_EFLAGS_TF | X86_EFLAGS_RF; - vmcs_writel(GUEST_RFLAGS, flags); - } -} - static int handle_rmode_exception(struct kvm_vcpu *vcpu, int vec, u32 err_code) { @@ -2570,9 +2561,17 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, * the required debugging infrastructure rework. */ switch (vec) { - case DE_VECTOR: case DB_VECTOR: + if (vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) + return 0; + kvm_queue_exception(vcpu, vec); + return 1; case BP_VECTOR: + if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) + return 0; + /* fall through */ + case DE_VECTOR: case OF_VECTOR: case BR_VECTOR: case UD_VECTOR: @@ -2589,8 +2588,8 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 intr_info, error_code; - unsigned long cr2, rip; + u32 intr_info, ex_no, error_code; + unsigned long cr2, rip, dr6; u32 vect_info; enum emulation_result er; @@ -2649,14 +2648,30 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } - if ((intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK)) == - (INTR_TYPE_EXCEPTION | 1)) { + ex_no = intr_info & INTR_INFO_VECTOR_MASK; + switch (ex_no) { + case DB_VECTOR: + dr6 = vmcs_readl(EXIT_QUALIFICATION); + if (!(vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { + vcpu->arch.dr6 = dr6 | DR6_FIXED_1; + kvm_queue_exception(vcpu, DB_VECTOR); + return 1; + } + kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1; + kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7); + /* fall through */ + case BP_VECTOR: kvm_run->exit_reason = KVM_EXIT_DEBUG; - return 0; + kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip; + kvm_run->debug.arch.exception = ex_no; + break; + default: + kvm_run->exit_reason = KVM_EXIT_EXCEPTION; + kvm_run->ex.exception = ex_no; + kvm_run->ex.error_code = error_code; + break; } - kvm_run->exit_reason = KVM_EXIT_EXCEPTION; - kvm_run->ex.exception = intr_info & INTR_INFO_VECTOR_MASK; - kvm_run->ex.error_code = error_code; return 0; } @@ -2677,7 +2692,7 @@ static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { unsigned long exit_qualification; - int size, down, in, string, rep; + int size, in, string; unsigned port; ++vcpu->stat.io_exits; @@ -2693,8 +2708,6 @@ static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) size = (exit_qualification & 7) + 1; in = (exit_qualification & 8) != 0; - down = (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_DF) != 0; - rep = (exit_qualification & 32) != 0; port = exit_qualification >> 16; skip_emulated_instruction(vcpu); @@ -2795,21 +2808,44 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) unsigned long val; int dr, reg; - /* - * FIXME: this code assumes the host is debugging the guest. - * need to deal with guest debugging itself too. - */ + dr = vmcs_readl(GUEST_DR7); + if (dr & DR7_GD) { + /* + * As the vm-exit takes precedence over the debug trap, we + * need to emulate the latter, either for the host or the + * guest debugging itself. + */ + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { + kvm_run->debug.arch.dr6 = vcpu->arch.dr6; + kvm_run->debug.arch.dr7 = dr; + kvm_run->debug.arch.pc = + vmcs_readl(GUEST_CS_BASE) + + vmcs_readl(GUEST_RIP); + kvm_run->debug.arch.exception = DB_VECTOR; + kvm_run->exit_reason = KVM_EXIT_DEBUG; + return 0; + } else { + vcpu->arch.dr7 &= ~DR7_GD; + vcpu->arch.dr6 |= DR6_BD; + vmcs_writel(GUEST_DR7, vcpu->arch.dr7); + kvm_queue_exception(vcpu, DB_VECTOR); + return 1; + } + } + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - dr = exit_qualification & 7; - reg = (exit_qualification >> 8) & 15; - if (exit_qualification & 16) { - /* mov from dr */ + dr = exit_qualification & DEBUG_REG_ACCESS_NUM; + reg = DEBUG_REG_ACCESS_REG(exit_qualification); + if (exit_qualification & TYPE_MOV_FROM_DR) { switch (dr) { + case 0 ... 3: + val = vcpu->arch.db[dr]; + break; case 6: - val = 0xffff0ff0; + val = vcpu->arch.dr6; break; case 7: - val = 0x400; + val = vcpu->arch.dr7; break; default: val = 0; @@ -2817,7 +2853,38 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_register_write(vcpu, reg, val); KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler); } else { - /* mov to dr */ + val = vcpu->arch.regs[reg]; + switch (dr) { + case 0 ... 3: + vcpu->arch.db[dr] = val; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) + vcpu->arch.eff_db[dr] = val; + break; + case 4 ... 5: + if (vcpu->arch.cr4 & X86_CR4_DE) + kvm_queue_exception(vcpu, UD_VECTOR); + break; + case 6: + if (val & 0xffffffff00000000ULL) { + kvm_queue_exception(vcpu, GP_VECTOR); + break; + } + vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1; + break; + case 7: + if (val & 0xffffffff00000000ULL) { + kvm_queue_exception(vcpu, GP_VECTOR); + break; + } + vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { + vmcs_writel(GUEST_DR7, vcpu->arch.dr7); + vcpu->arch.switch_db_regs = + (val & DR7_BP_EN_MASK); + } + break; + } + KVMTRACE_2D(DR_WRITE, vcpu, (u32)dr, (u32)val, handler); } skip_emulated_instruction(vcpu); return 1; @@ -2968,17 +3035,25 @@ static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } tss_selector = exit_qualification; - return kvm_task_switch(vcpu, tss_selector, reason); + if (!kvm_task_switch(vcpu, tss_selector, reason)) + return 0; + + /* clear all local breakpoint enable flags */ + vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55); + + /* + * TODO: What about debug traps on tss switch? + * Are we supposed to inject them and update dr6? + */ + + return 1; } static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { u64 exit_qualification; - enum emulation_result er; gpa_t gpa; - unsigned long hva; int gla_validity; - int r; exit_qualification = vmcs_read64(EXIT_QUALIFICATION); @@ -3001,32 +3076,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); - hva = gfn_to_hva(vcpu->kvm, gpa >> PAGE_SHIFT); - if (!kvm_is_error_hva(hva)) { - r = kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0); - if (r < 0) { - printk(KERN_ERR "EPT: Not enough memory!\n"); - return -ENOMEM; - } - return 1; - } else { - /* must be MMIO */ - er = emulate_instruction(vcpu, kvm_run, 0, 0, 0); - - if (er == EMULATE_FAIL) { - printk(KERN_ERR - "EPT: Fail to handle EPT violation vmexit!er is %d\n", - er); - printk(KERN_ERR "EPT: GPA: 0x%lx, GVA: 0x%lx\n", - (long unsigned int)vmcs_read64(GUEST_PHYSICAL_ADDRESS), - (long unsigned int)vmcs_read64(GUEST_LINEAR_ADDRESS)); - printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n", - (long unsigned int)exit_qualification); - return -ENOTSUPP; - } else if (er == EMULATE_DO_MMIO) - return 0; - } - return 1; + return kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0); } static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) @@ -3046,7 +3096,7 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { struct vcpu_vmx *vmx = to_vmx(vcpu); - int err; + enum emulation_result err = EMULATE_DONE; preempt_enable(); local_irq_enable(); @@ -3071,10 +3121,7 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu, local_irq_disable(); preempt_disable(); - /* Guest state should be valid now except if we need to - * emulate an MMIO */ - if (guest_state_valid(vcpu)) - vmx->emulation_required = 0; + vmx->invalid_state_emulation_result = err; } /* @@ -3123,8 +3170,11 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) /* If we need to emulate an MMIO from handle_invalid_guest_state * we just return 0 */ - if (vmx->emulation_required && emulate_invalid_guest_state) - return 0; + if (vmx->emulation_required && emulate_invalid_guest_state) { + if (guest_state_valid(vcpu)) + vmx->emulation_required = 0; + return vmx->invalid_state_emulation_result != EMULATE_DO_MMIO; + } /* Access CR3 don't cause VMExit in paging mode, so we need * to sync with guest real CR3. */ @@ -3238,7 +3288,8 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx) vmx->vcpu.arch.nmi_injected = false; } kvm_clear_exception_queue(&vmx->vcpu); - if (idtv_info_valid && type == INTR_TYPE_EXCEPTION) { + if (idtv_info_valid && (type == INTR_TYPE_HARD_EXCEPTION || + type == INTR_TYPE_SOFT_EXCEPTION)) { if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { error = vmcs_read32(IDT_VECTORING_ERROR_CODE); kvm_queue_exception_e(&vmx->vcpu, vector, error); @@ -3259,6 +3310,11 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu) vmx_update_window_states(vcpu); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_STI | + GUEST_INTR_STATE_MOV_SS); + if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) { if (vcpu->arch.interrupt.pending) { enable_nmi_window(vcpu); @@ -3347,6 +3403,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) */ vmcs_writel(HOST_CR0, read_cr0()); + set_debugreg(vcpu->arch.dr6, 6); + asm( /* Store host registers */ "push %%"R"dx; push %%"R"bp;" @@ -3441,6 +3499,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)); vcpu->arch.regs_dirty = 0; + get_debugreg(vcpu->arch.dr6, 6); + vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); if (vmx->rmode.irq.pending) fixup_rmode_irq(vmx); @@ -3595,7 +3655,6 @@ static struct kvm_x86_ops vmx_x86_ops = { .vcpu_put = vmx_vcpu_put, .set_guest_debug = set_guest_debug, - .guest_debug_pre = kvm_guest_debug_pre, .get_msr = vmx_get_msr, .set_msr = vmx_set_msr, .get_segment_base = vmx_get_segment_base, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 758b7a1..8ca100a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -36,6 +36,7 @@ #include <linux/highmem.h> #include <linux/iommu.h> #include <linux/intel-iommu.h> +#include <linux/cpufreq.h> #include <asm/uaccess.h> #include <asm/msr.h> @@ -69,6 +70,8 @@ static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffffeULL; static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, + u32 function, u32 index); struct kvm_x86_ops *kvm_x86_ops; EXPORT_SYMBOL_GPL(kvm_x86_ops); @@ -173,6 +176,7 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr, u32 error_code) { ++vcpu->stat.pf_guest; + if (vcpu->arch.exception.pending) { if (vcpu->arch.exception.nr == PF_VECTOR) { printk(KERN_DEBUG "kvm: inject_page_fault:" @@ -361,6 +365,7 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) } kvm_x86_ops->set_cr4(vcpu, cr4); vcpu->arch.cr4 = cr4; + vcpu->arch.mmu.base_role.cr4_pge = (cr4 & X86_CR4_PGE) && !tdp_enabled; kvm_mmu_sync_global(vcpu); kvm_mmu_reset_context(vcpu); } @@ -442,6 +447,11 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_get_cr8); +static inline u32 bit(int bitno) +{ + return 1 << (bitno & 31); +} + /* * List of msr numbers which we expose to userspace through KVM_GET_MSRS * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. @@ -456,7 +466,7 @@ static u32 msrs_to_save[] = { MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif MSR_IA32_TIME_STAMP_COUNTER, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, - MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT + MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA }; static unsigned num_msrs_to_save; @@ -481,6 +491,28 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer) return; } + if (efer & EFER_FFXSR) { + struct kvm_cpuid_entry2 *feat; + + feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) { + printk(KERN_DEBUG "set_efer: #GP, enable FFXSR w/o CPUID capability\n"); + kvm_inject_gp(vcpu, 0); + return; + } + } + + if (efer & EFER_SVME) { + struct kvm_cpuid_entry2 *feat; + + feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) { + printk(KERN_DEBUG "set_efer: #GP, enable SVM w/o SVM\n"); + kvm_inject_gp(vcpu, 0); + return; + } + } + kvm_x86_ops->set_efer(vcpu, efer); efer &= ~EFER_LMA; @@ -586,6 +618,8 @@ static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info * hv_clock->tsc_to_system_mul); } +static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz); + static void kvm_write_guest_time(struct kvm_vcpu *v) { struct timespec ts; @@ -596,9 +630,9 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) if ((!vcpu->time_page)) return; - if (unlikely(vcpu->hv_clock_tsc_khz != tsc_khz)) { - kvm_set_time_scale(tsc_khz, &vcpu->hv_clock); - vcpu->hv_clock_tsc_khz = tsc_khz; + if (unlikely(vcpu->hv_clock_tsc_khz != __get_cpu_var(cpu_tsc_khz))) { + kvm_set_time_scale(__get_cpu_var(cpu_tsc_khz), &vcpu->hv_clock); + vcpu->hv_clock_tsc_khz = __get_cpu_var(cpu_tsc_khz); } /* Keep irq disabled to prevent changes to the clock */ @@ -629,6 +663,16 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT); } +static int kvm_request_guest_time_update(struct kvm_vcpu *v) +{ + struct kvm_vcpu_arch *vcpu = &v->arch; + + if (!vcpu->time_page) + return 0; + set_bit(KVM_REQ_KVMCLOCK_UPDATE, &v->requests); + return 1; +} + static bool msr_mtrr_valid(unsigned msr) { switch (msr) { @@ -722,6 +766,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) break; case MSR_IA32_UCODE_REV: case MSR_IA32_UCODE_WRITE: + case MSR_VM_HSAVE_PA: break; case 0x200 ... 0x2ff: return set_msr_mtrr(vcpu, msr, data); @@ -758,7 +803,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) vcpu->arch.time_page = NULL; } - kvm_write_guest_time(vcpu); + kvm_request_guest_time_update(vcpu); break; } default: @@ -843,6 +888,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_LASTBRANCHTOIP: case MSR_IA32_LASTINTFROMIP: case MSR_IA32_LASTINTTOIP: + case MSR_VM_HSAVE_PA: data = 0; break; case MSR_MTRRcap: @@ -967,10 +1013,13 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_MMU_SHADOW_CACHE_CONTROL: case KVM_CAP_SET_TSS_ADDR: case KVM_CAP_EXT_CPUID: + case KVM_CAP_CLOCKSOURCE: case KVM_CAP_PIT: case KVM_CAP_NOP_IO_DELAY: case KVM_CAP_MP_STATE: case KVM_CAP_SYNC_MMU: + case KVM_CAP_REINJECT_CONTROL: + case KVM_CAP_IRQ_INJECT_STATUS: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -991,9 +1040,6 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_IOMMU: r = iommu_found(); break; - case KVM_CAP_CLOCKSOURCE: - r = boot_cpu_has(X86_FEATURE_CONSTANT_TSC); - break; default: r = 0; break; @@ -1044,7 +1090,7 @@ long kvm_arch_dev_ioctl(struct file *filp, if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) goto out; r = kvm_dev_ioctl_get_supported_cpuid(&cpuid, - cpuid_arg->entries); + cpuid_arg->entries); if (r) goto out; @@ -1064,7 +1110,7 @@ out: void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { kvm_x86_ops->vcpu_load(vcpu, cpu); - kvm_write_guest_time(vcpu); + kvm_request_guest_time_update(vcpu); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -1142,8 +1188,8 @@ out: } static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, - struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) + struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) { int r; @@ -1162,8 +1208,8 @@ out: } static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, - struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) + struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) { int r; @@ -1172,7 +1218,7 @@ static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, goto out; r = -EFAULT; if (copy_to_user(entries, &vcpu->arch.cpuid_entries, - vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2))) + vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2))) goto out; return 0; @@ -1181,18 +1227,13 @@ out: return r; } -static inline u32 bit(int bitno) -{ - return 1 << (bitno & 31); -} - static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index) + u32 index) { entry->function = function; entry->index = index; cpuid_count(entry->function, entry->index, - &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); + &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); entry->flags = 0; } @@ -1222,15 +1263,17 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, #ifdef CONFIG_X86_64 bit(X86_FEATURE_LM) | #endif + bit(X86_FEATURE_FXSR_OPT) | bit(X86_FEATURE_MMXEXT) | bit(X86_FEATURE_3DNOWEXT) | bit(X86_FEATURE_3DNOW); const u32 kvm_supported_word3_x86_features = bit(X86_FEATURE_XMM3) | bit(X86_FEATURE_CX16); const u32 kvm_supported_word6_x86_features = - bit(X86_FEATURE_LAHF_LM) | bit(X86_FEATURE_CMP_LEGACY); + bit(X86_FEATURE_LAHF_LM) | bit(X86_FEATURE_CMP_LEGACY) | + bit(X86_FEATURE_SVM); - /* all func 2 cpuid_count() should be called on the same cpu */ + /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); do_cpuid_1_ent(entry, function, index); ++*nent; @@ -1304,7 +1347,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, } static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) + struct kvm_cpuid_entry2 __user *entries) { struct kvm_cpuid_entry2 *cpuid_entries; int limit, nent = 0, r = -E2BIG; @@ -1321,7 +1364,7 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, limit = cpuid_entries[0].eax; for (func = 1; func <= limit && nent < cpuid->nent; ++func) do_cpuid_ent(&cpuid_entries[nent], func, 0, - &nent, cpuid->nent); + &nent, cpuid->nent); r = -E2BIG; if (nent >= cpuid->nent) goto out_free; @@ -1330,10 +1373,10 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, limit = cpuid_entries[nent - 1].eax; for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func) do_cpuid_ent(&cpuid_entries[nent], func, 0, - &nent, cpuid->nent); + &nent, cpuid->nent); r = -EFAULT; if (copy_to_user(entries, cpuid_entries, - nent * sizeof(struct kvm_cpuid_entry2))) + nent * sizeof(struct kvm_cpuid_entry2))) goto out_free; cpuid->nent = nent; r = 0; @@ -1477,7 +1520,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) goto out; r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid, - cpuid_arg->entries); + cpuid_arg->entries); if (r) goto out; break; @@ -1490,7 +1533,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) goto out; r = kvm_vcpu_ioctl_get_cpuid2(vcpu, &cpuid, - cpuid_arg->entries); + cpuid_arg->entries); if (r) goto out; r = -EFAULT; @@ -1710,6 +1753,15 @@ static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) return r; } +static int kvm_vm_ioctl_reinject(struct kvm *kvm, + struct kvm_reinject_control *control) +{ + if (!kvm->arch.vpit) + return -ENXIO; + kvm->arch.vpit->pit_state.pit_timer.reinject = control->pit_reinject; + return 0; +} + /* * Get (and clear) the dirty memory log for a memory slot. */ @@ -1807,13 +1859,26 @@ long kvm_arch_vm_ioctl(struct file *filp, } } else goto out; + r = kvm_setup_default_irq_routing(kvm); + if (r) { + kfree(kvm->arch.vpic); + kfree(kvm->arch.vioapic); + goto out; + } break; case KVM_CREATE_PIT: + mutex_lock(&kvm->lock); + r = -EEXIST; + if (kvm->arch.vpit) + goto create_pit_unlock; r = -ENOMEM; kvm->arch.vpit = kvm_create_pit(kvm); if (kvm->arch.vpit) r = 0; + create_pit_unlock: + mutex_unlock(&kvm->lock); break; + case KVM_IRQ_LINE_STATUS: case KVM_IRQ_LINE: { struct kvm_irq_level irq_event; @@ -1821,10 +1886,17 @@ long kvm_arch_vm_ioctl(struct file *filp, if (copy_from_user(&irq_event, argp, sizeof irq_event)) goto out; if (irqchip_in_kernel(kvm)) { + __s32 status; mutex_lock(&kvm->lock); - kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, - irq_event.irq, irq_event.level); + status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, + irq_event.irq, irq_event.level); mutex_unlock(&kvm->lock); + if (ioctl == KVM_IRQ_LINE_STATUS) { + irq_event.status = status; + if (copy_to_user(argp, &irq_event, + sizeof irq_event)) + goto out; + } r = 0; } break; @@ -1907,6 +1979,17 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; break; } + case KVM_REINJECT_CONTROL: { + struct kvm_reinject_control control; + r = -EFAULT; + if (copy_from_user(&control, argp, sizeof(control))) + goto out; + r = kvm_vm_ioctl_reinject(kvm, &control); + if (r) + goto out; + r = 0; + break; + } default: ; } @@ -1960,10 +2043,38 @@ static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu, return dev; } -int emulator_read_std(unsigned long addr, - void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) +static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes, + struct kvm_vcpu *vcpu) +{ + void *data = val; + int r = X86EMUL_CONTINUE; + + while (bytes) { + gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); + unsigned offset = addr & (PAGE_SIZE-1); + unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset); + int ret; + + if (gpa == UNMAPPED_GVA) { + r = X86EMUL_PROPAGATE_FAULT; + goto out; + } + ret = kvm_read_guest(vcpu->kvm, gpa, data, toread); + if (ret < 0) { + r = X86EMUL_UNHANDLEABLE; + goto out; + } + + bytes -= toread; + data += toread; + addr += toread; + } +out: + return r; +} + +static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes, + struct kvm_vcpu *vcpu) { void *data = val; int r = X86EMUL_CONTINUE; @@ -1971,27 +2082,27 @@ int emulator_read_std(unsigned long addr, while (bytes) { gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); unsigned offset = addr & (PAGE_SIZE-1); - unsigned tocopy = min(bytes, (unsigned)PAGE_SIZE - offset); + unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; if (gpa == UNMAPPED_GVA) { r = X86EMUL_PROPAGATE_FAULT; goto out; } - ret = kvm_read_guest(vcpu->kvm, gpa, data, tocopy); + ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite); if (ret < 0) { r = X86EMUL_UNHANDLEABLE; goto out; } - bytes -= tocopy; - data += tocopy; - addr += tocopy; + bytes -= towrite; + data += towrite; + addr += towrite; } out: return r; } -EXPORT_SYMBOL_GPL(emulator_read_std); + static int emulator_read_emulated(unsigned long addr, void *val, @@ -2013,8 +2124,8 @@ static int emulator_read_emulated(unsigned long addr, if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) goto mmio; - if (emulator_read_std(addr, val, bytes, vcpu) - == X86EMUL_CONTINUE) + if (kvm_read_guest_virt(addr, val, bytes, vcpu) + == X86EMUL_CONTINUE) return X86EMUL_CONTINUE; if (gpa == UNMAPPED_GVA) return X86EMUL_PROPAGATE_FAULT; @@ -2217,7 +2328,7 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS); - emulator_read_std(rip_linear, (void *)opcodes, 4, vcpu); + kvm_read_guest_virt(rip_linear, (void *)opcodes, 4, vcpu); printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n", context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]); @@ -2225,7 +2336,7 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) EXPORT_SYMBOL_GPL(kvm_report_emulation_failure); static struct x86_emulate_ops emulate_ops = { - .read_std = emulator_read_std, + .read_std = kvm_read_guest_virt, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, .cmpxchg_emulated = emulator_cmpxchg_emulated, @@ -2327,40 +2438,19 @@ int emulate_instruction(struct kvm_vcpu *vcpu, } EXPORT_SYMBOL_GPL(emulate_instruction); -static void free_pio_guest_pages(struct kvm_vcpu *vcpu) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(vcpu->arch.pio.guest_pages); ++i) - if (vcpu->arch.pio.guest_pages[i]) { - kvm_release_page_dirty(vcpu->arch.pio.guest_pages[i]); - vcpu->arch.pio.guest_pages[i] = NULL; - } -} - static int pio_copy_data(struct kvm_vcpu *vcpu) { void *p = vcpu->arch.pio_data; - void *q; + gva_t q = vcpu->arch.pio.guest_gva; unsigned bytes; - int nr_pages = vcpu->arch.pio.guest_pages[1] ? 2 : 1; + int ret; - q = vmap(vcpu->arch.pio.guest_pages, nr_pages, VM_READ|VM_WRITE, - PAGE_KERNEL); - if (!q) { - free_pio_guest_pages(vcpu); - return -ENOMEM; - } - q += vcpu->arch.pio.guest_page_offset; bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count; if (vcpu->arch.pio.in) - memcpy(q, p, bytes); + ret = kvm_write_guest_virt(q, p, bytes, vcpu); else - memcpy(p, q, bytes); - q -= vcpu->arch.pio.guest_page_offset; - vunmap(q); - free_pio_guest_pages(vcpu); - return 0; + ret = kvm_read_guest_virt(q, p, bytes, vcpu); + return ret; } int complete_pio(struct kvm_vcpu *vcpu) @@ -2471,7 +2561,6 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, vcpu->arch.pio.in = in; vcpu->arch.pio.string = 0; vcpu->arch.pio.down = 0; - vcpu->arch.pio.guest_page_offset = 0; vcpu->arch.pio.rep = 0; if (vcpu->run->io.direction == KVM_EXIT_IO_IN) @@ -2499,9 +2588,7 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, gva_t address, int rep, unsigned port) { unsigned now, in_page; - int i, ret = 0; - int nr_pages = 1; - struct page *page; + int ret = 0; struct kvm_io_device *pio_dev; vcpu->run->exit_reason = KVM_EXIT_IO; @@ -2513,7 +2600,6 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, vcpu->arch.pio.in = in; vcpu->arch.pio.string = 1; vcpu->arch.pio.down = down; - vcpu->arch.pio.guest_page_offset = offset_in_page(address); vcpu->arch.pio.rep = rep; if (vcpu->run->io.direction == KVM_EXIT_IO_IN) @@ -2533,15 +2619,8 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, else in_page = offset_in_page(address) + size; now = min(count, (unsigned long)in_page / size); - if (!now) { - /* - * String I/O straddles page boundary. Pin two guest pages - * so that we satisfy atomicity constraints. Do just one - * transaction to avoid complexity. - */ - nr_pages = 2; + if (!now) now = 1; - } if (down) { /* * String I/O in reverse. Yuck. Kill the guest, fix later. @@ -2556,15 +2635,7 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, if (vcpu->arch.pio.cur_count == vcpu->arch.pio.count) kvm_x86_ops->skip_emulated_instruction(vcpu); - for (i = 0; i < nr_pages; ++i) { - page = gva_to_page(vcpu, address + i * PAGE_SIZE); - vcpu->arch.pio.guest_pages[i] = page; - if (!page) { - kvm_inject_gp(vcpu, 0); - free_pio_guest_pages(vcpu); - return 1; - } - } + vcpu->arch.pio.guest_gva = address; pio_dev = vcpu_find_pio_dev(vcpu, port, vcpu->arch.pio.cur_count, @@ -2572,7 +2643,11 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, if (!vcpu->arch.pio.in) { /* string PIO write */ ret = pio_copy_data(vcpu); - if (ret >= 0 && pio_dev) { + if (ret == X86EMUL_PROPAGATE_FAULT) { + kvm_inject_gp(vcpu, 0); + return 1; + } + if (ret == 0 && pio_dev) { pio_string_write(pio_dev, vcpu); complete_pio(vcpu); if (vcpu->arch.pio.count == 0) @@ -2587,9 +2662,72 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, } EXPORT_SYMBOL_GPL(kvm_emulate_pio_string); +static void bounce_off(void *info) +{ + /* nothing */ +} + +static unsigned int ref_freq; +static unsigned long tsc_khz_ref; + +static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct cpufreq_freqs *freq = data; + struct kvm *kvm; + struct kvm_vcpu *vcpu; + int i, send_ipi = 0; + + if (!ref_freq) + ref_freq = freq->old; + + if (val == CPUFREQ_PRECHANGE && freq->old > freq->new) + return 0; + if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new) + return 0; + per_cpu(cpu_tsc_khz, freq->cpu) = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new); + + spin_lock(&kvm_lock); + list_for_each_entry(kvm, &vm_list, vm_list) { + for (i = 0; i < KVM_MAX_VCPUS; ++i) { + vcpu = kvm->vcpus[i]; + if (!vcpu) + continue; + if (vcpu->cpu != freq->cpu) + continue; + if (!kvm_request_guest_time_update(vcpu)) + continue; + if (vcpu->cpu != smp_processor_id()) + send_ipi++; + } + } + spin_unlock(&kvm_lock); + + if (freq->old < freq->new && send_ipi) { + /* + * We upscale the frequency. Must make the guest + * doesn't see old kvmclock values while running with + * the new frequency, otherwise we risk the guest sees + * time go backwards. + * + * In case we update the frequency for another cpu + * (which might be in guest context) send an interrupt + * to kick the cpu out of guest context. Next time + * guest context is entered kvmclock will be updated, + * so the guest will not see stale values. + */ + smp_call_function_single(freq->cpu, bounce_off, NULL, 1); + } + return 0; +} + +static struct notifier_block kvmclock_cpufreq_notifier_block = { + .notifier_call = kvmclock_cpufreq_notifier +}; + int kvm_arch_init(void *opaque) { - int r; + int r, cpu; struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque; if (kvm_x86_ops) { @@ -2620,6 +2758,15 @@ int kvm_arch_init(void *opaque) kvm_mmu_set_base_ptes(PT_PRESENT_MASK); kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0, 0); + + for_each_possible_cpu(cpu) + per_cpu(cpu_tsc_khz, cpu) = tsc_khz; + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + tsc_khz_ref = tsc_khz; + cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, + CPUFREQ_TRANSITION_NOTIFIER); + } + return 0; out: @@ -2827,25 +2974,20 @@ static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e, if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index) return 0; if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) && - !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT)) + !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT)) return 0; return 1; } -void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, + u32 function, u32 index) { int i; - u32 function, index; - struct kvm_cpuid_entry2 *e, *best; + struct kvm_cpuid_entry2 *best = NULL; - function = kvm_register_read(vcpu, VCPU_REGS_RAX); - index = kvm_register_read(vcpu, VCPU_REGS_RCX); - kvm_register_write(vcpu, VCPU_REGS_RAX, 0); - kvm_register_write(vcpu, VCPU_REGS_RBX, 0); - kvm_register_write(vcpu, VCPU_REGS_RCX, 0); - kvm_register_write(vcpu, VCPU_REGS_RDX, 0); - best = NULL; for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { + struct kvm_cpuid_entry2 *e; + e = &vcpu->arch.cpuid_entries[i]; if (is_matching_cpuid_entry(e, function, index)) { if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) @@ -2860,6 +3002,21 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) if (!best || e->function > best->function) best = e; } + return best; +} + +void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) +{ + u32 function, index; + struct kvm_cpuid_entry2 *best; + + function = kvm_register_read(vcpu, VCPU_REGS_RAX); + index = kvm_register_read(vcpu, VCPU_REGS_RCX); + kvm_register_write(vcpu, VCPU_REGS_RAX, 0); + kvm_register_write(vcpu, VCPU_REGS_RBX, 0); + kvm_register_write(vcpu, VCPU_REGS_RCX, 0); + kvm_register_write(vcpu, VCPU_REGS_RDX, 0); + best = kvm_find_cpuid_entry(vcpu, function, index); if (best) { kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax); kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx); @@ -2945,6 +3102,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (vcpu->requests) { if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests)) __kvm_migrate_timers(vcpu); + if (test_and_clear_bit(KVM_REQ_KVMCLOCK_UPDATE, &vcpu->requests)) + kvm_write_guest_time(vcpu); if (test_and_clear_bit(KVM_REQ_MMU_SYNC, &vcpu->requests)) kvm_mmu_sync_roots(vcpu); if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests)) @@ -2979,9 +3138,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) goto out; } - if (vcpu->guest_debug.enabled) - kvm_x86_ops->guest_debug_pre(vcpu); - vcpu->guest_mode = 1; /* * Make sure that guest_mode assignment won't happen after @@ -3002,10 +3158,34 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_guest_enter(); + get_debugreg(vcpu->arch.host_dr6, 6); + get_debugreg(vcpu->arch.host_dr7, 7); + if (unlikely(vcpu->arch.switch_db_regs)) { + get_debugreg(vcpu->arch.host_db[0], 0); + get_debugreg(vcpu->arch.host_db[1], 1); + get_debugreg(vcpu->arch.host_db[2], 2); + get_debugreg(vcpu->arch.host_db[3], 3); + + set_debugreg(0, 7); + set_debugreg(vcpu->arch.eff_db[0], 0); + set_debugreg(vcpu->arch.eff_db[1], 1); + set_debugreg(vcpu->arch.eff_db[2], 2); + set_debugreg(vcpu->arch.eff_db[3], 3); + } KVMTRACE_0D(VMENTRY, vcpu, entryexit); kvm_x86_ops->run(vcpu, kvm_run); + if (unlikely(vcpu->arch.switch_db_regs)) { + set_debugreg(0, 7); + set_debugreg(vcpu->arch.host_db[0], 0); + set_debugreg(vcpu->arch.host_db[1], 1); + set_debugreg(vcpu->arch.host_db[2], 2); + set_debugreg(vcpu->arch.host_db[3], 3); + } + set_debugreg(vcpu->arch.host_dr6, 6); + set_debugreg(vcpu->arch.host_dr7, 7); + vcpu->guest_mode = 0; local_irq_enable(); @@ -3192,7 +3372,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) /* * Don't leak debug flags in case they were set for guest debugging */ - if (vcpu->guest_debug.enabled && vcpu->guest_debug.singlestep) + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); vcpu_put(vcpu); @@ -3811,15 +3991,32 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, return 0; } -int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg) +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) { - int r; + int i, r; vcpu_load(vcpu); + if ((dbg->control & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) == + (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) { + for (i = 0; i < KVM_NR_DB_REGS; ++i) + vcpu->arch.eff_db[i] = dbg->arch.debugreg[i]; + vcpu->arch.switch_db_regs = + (dbg->arch.debugreg[7] & DR7_BP_EN_MASK); + } else { + for (i = 0; i < KVM_NR_DB_REGS; i++) + vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK); + } + r = kvm_x86_ops->set_guest_debug(vcpu, dbg); + if (dbg->control & KVM_GUESTDBG_INJECT_DB) + kvm_queue_exception(vcpu, DB_VECTOR); + else if (dbg->control & KVM_GUESTDBG_INJECT_BP) + kvm_queue_exception(vcpu, BP_VECTOR); + vcpu_put(vcpu); return r; @@ -4007,6 +4204,11 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) vcpu->arch.nmi_pending = false; vcpu->arch.nmi_injected = false; + vcpu->arch.switch_db_regs = 0; + memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); + vcpu->arch.dr6 = DR6_FIXED_1; + vcpu->arch.dr7 = DR7_FIXED_1; + return kvm_x86_ops->vcpu_reset(vcpu); } @@ -4100,6 +4302,8 @@ struct kvm *kvm_arch_create_vm(void) /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); + rdtscll(kvm->arch.vm_init_tsc); + return kvm; } diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c index d174db7..ca91749 100644 --- a/arch/x86/kvm/x86_emulate.c +++ b/arch/x86/kvm/x86_emulate.c @@ -178,7 +178,7 @@ static u32 opcode_table[256] = { 0, ImplicitOps | Stack, 0, 0, ByteOp | DstMem | SrcImm | ModRM | Mov, DstMem | SrcImm | ModRM | Mov, /* 0xC8 - 0xCF */ - 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, ImplicitOps | Stack, 0, 0, 0, 0, /* 0xD0 - 0xD7 */ ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM, ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM, @@ -1136,18 +1136,19 @@ static inline void emulate_push(struct x86_emulate_ctxt *ctxt) } static int emulate_pop(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops) + struct x86_emulate_ops *ops, + void *dest, int len) { struct decode_cache *c = &ctxt->decode; int rc; rc = ops->read_emulated(register_address(c, ss_base(ctxt), c->regs[VCPU_REGS_RSP]), - &c->src.val, c->src.bytes, ctxt->vcpu); + dest, len, ctxt->vcpu); if (rc != 0) return rc; - register_address_increment(c, &c->regs[VCPU_REGS_RSP], c->src.bytes); + register_address_increment(c, &c->regs[VCPU_REGS_RSP], len); return rc; } @@ -1157,11 +1158,9 @@ static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt, struct decode_cache *c = &ctxt->decode; int rc; - c->src.bytes = c->dst.bytes; - rc = emulate_pop(ctxt, ops); + rc = emulate_pop(ctxt, ops, &c->dst.val, c->dst.bytes); if (rc != 0) return rc; - c->dst.val = c->src.val; return 0; } @@ -1279,6 +1278,25 @@ static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt, return 0; } +static int emulate_ret_far(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) +{ + struct decode_cache *c = &ctxt->decode; + int rc; + unsigned long cs; + + rc = emulate_pop(ctxt, ops, &c->eip, c->op_bytes); + if (rc) + return rc; + if (c->op_bytes == 4) + c->eip = (u32)c->eip; + rc = emulate_pop(ctxt, ops, &cs, c->op_bytes); + if (rc) + return rc; + rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)cs, 1, VCPU_SREG_CS); + return rc; +} + static inline int writeback(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { @@ -1467,11 +1485,9 @@ special_insn: break; case 0x58 ... 0x5f: /* pop reg */ pop_instruction: - c->src.bytes = c->op_bytes; - rc = emulate_pop(ctxt, ops); + rc = emulate_pop(ctxt, ops, &c->dst.val, c->op_bytes); if (rc != 0) goto done; - c->dst.val = c->src.val; break; case 0x63: /* movsxd */ if (ctxt->mode != X86EMUL_MODE_PROT64) @@ -1738,6 +1754,11 @@ special_insn: mov: c->dst.val = c->src.val; break; + case 0xcb: /* ret far */ + rc = emulate_ret_far(ctxt, ops); + if (rc) + goto done; + break; case 0xd0 ... 0xd1: /* Grp2 */ c->src.val = 1; emulate_grp2(ctxt); @@ -1908,11 +1929,16 @@ twobyte_insn: c->dst.type = OP_NONE; break; case 3: /* lidt/vmmcall */ - if (c->modrm_mod == 3 && c->modrm_rm == 1) { - rc = kvm_fix_hypercall(ctxt->vcpu); - if (rc) - goto done; - kvm_emulate_hypercall(ctxt->vcpu); + if (c->modrm_mod == 3) { + switch (c->modrm_rm) { + case 1: + rc = kvm_fix_hypercall(ctxt->vcpu); + if (rc) + goto done; + break; + default: + goto cannot_emulate; + } } else { rc = read_descriptor(ctxt, ops, c->src.ptr, &size, &address, diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index f3a5305..e94a11e 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -107,7 +107,7 @@ static void async_hcall(unsigned long call, unsigned long arg1, local_irq_save(flags); if (lguest_data.hcall_status[next_call] != 0xFF) { /* Table full, so do normal hcall which will flush table. */ - hcall(call, arg1, arg2, arg3); + kvm_hypercall3(call, arg1, arg2, arg3); } else { lguest_data.hcalls[next_call].arg0 = call; lguest_data.hcalls[next_call].arg1 = arg1; @@ -134,13 +134,32 @@ static void async_hcall(unsigned long call, unsigned long arg1, * * So, when we're in lazy mode, we call async_hcall() to store the call for * future processing: */ -static void lazy_hcall(unsigned long call, +static void lazy_hcall1(unsigned long call, + unsigned long arg1) +{ + if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) + kvm_hypercall1(call, arg1); + else + async_hcall(call, arg1, 0, 0); +} + +static void lazy_hcall2(unsigned long call, + unsigned long arg1, + unsigned long arg2) +{ + if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) + kvm_hypercall2(call, arg1, arg2); + else + async_hcall(call, arg1, arg2, 0); +} + +static void lazy_hcall3(unsigned long call, unsigned long arg1, unsigned long arg2, unsigned long arg3) { if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - hcall(call, arg1, arg2, arg3); + kvm_hypercall3(call, arg1, arg2, arg3); else async_hcall(call, arg1, arg2, arg3); } @@ -150,7 +169,7 @@ static void lazy_hcall(unsigned long call, static void lguest_leave_lazy_mode(void) { paravirt_leave_lazy(paravirt_get_lazy_mode()); - hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0); + kvm_hypercall0(LHCALL_FLUSH_ASYNC); } /*G:033 @@ -229,7 +248,7 @@ static void lguest_write_idt_entry(gate_desc *dt, /* Keep the local copy up to date. */ native_write_idt_entry(dt, entrynum, g); /* Tell Host about this new entry. */ - hcall(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1]); + kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1]); } /* Changing to a different IDT is very rare: we keep the IDT up-to-date every @@ -241,7 +260,7 @@ static void lguest_load_idt(const struct desc_ptr *desc) struct desc_struct *idt = (void *)desc->address; for (i = 0; i < (desc->size+1)/8; i++) - hcall(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b); + kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b); } /* @@ -261,8 +280,8 @@ static void lguest_load_idt(const struct desc_ptr *desc) */ static void lguest_load_gdt(const struct desc_ptr *desc) { - BUG_ON((desc->size+1)/8 != GDT_ENTRIES); - hcall(LHCALL_LOAD_GDT, __pa(desc->address), GDT_ENTRIES, 0); + BUG_ON((desc->size + 1) / 8 != GDT_ENTRIES); + kvm_hypercall2(LHCALL_LOAD_GDT, __pa(desc->address), GDT_ENTRIES); } /* For a single GDT entry which changes, we do the lazy thing: alter our GDT, @@ -272,7 +291,7 @@ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum, const void *desc, int type) { native_write_gdt_entry(dt, entrynum, desc, type); - hcall(LHCALL_LOAD_GDT, __pa(dt), GDT_ENTRIES, 0); + kvm_hypercall2(LHCALL_LOAD_GDT, __pa(dt), GDT_ENTRIES); } /* OK, I lied. There are three "thread local storage" GDT entries which change @@ -284,7 +303,7 @@ static void lguest_load_tls(struct thread_struct *t, unsigned int cpu) * can't handle us removing entries we're currently using. So we clear * the GS register here: if it's needed it'll be reloaded anyway. */ lazy_load_gs(0); - lazy_hcall(LHCALL_LOAD_TLS, __pa(&t->tls_array), cpu, 0); + lazy_hcall2(LHCALL_LOAD_TLS, __pa(&t->tls_array), cpu); } /*G:038 That's enough excitement for now, back to ploughing through each of @@ -348,6 +367,11 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx, * flush_tlb_user() for both user and kernel mappings unless * the Page Global Enable (PGE) feature bit is set. */ *dx |= 0x00002000; + /* We also lie, and say we're family id 5. 6 or greater + * leads to a rdmsr in early_init_intel which we can't handle. + * Family ID is returned as bits 8-12 in ax. */ + *ax &= 0xFFFFF0FF; + *ax |= 0x00000500; break; case 0x80000000: /* Futureproof this a little: if they ask how much extended @@ -377,7 +401,7 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx, static unsigned long current_cr0; static void lguest_write_cr0(unsigned long val) { - lazy_hcall(LHCALL_TS, val & X86_CR0_TS, 0, 0); + lazy_hcall1(LHCALL_TS, val & X86_CR0_TS); current_cr0 = val; } @@ -391,7 +415,7 @@ static unsigned long lguest_read_cr0(void) * the vowels have been optimized out. */ static void lguest_clts(void) { - lazy_hcall(LHCALL_TS, 0, 0, 0); + lazy_hcall1(LHCALL_TS, 0); current_cr0 &= ~X86_CR0_TS; } @@ -413,7 +437,7 @@ static bool cr3_changed = false; static void lguest_write_cr3(unsigned long cr3) { lguest_data.pgdir = cr3; - lazy_hcall(LHCALL_NEW_PGTABLE, cr3, 0, 0); + lazy_hcall1(LHCALL_NEW_PGTABLE, cr3); cr3_changed = true; } @@ -485,11 +509,17 @@ static void lguest_write_cr4(unsigned long val) * into a process' address space. We set the entry then tell the Host the * toplevel and address this corresponds to. The Guest uses one pagetable per * process, so we need to tell the Host which one we're changing (mm->pgd). */ +static void lguest_pte_update(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + lazy_hcall3(LHCALL_SET_PTE, __pa(mm->pgd), addr, ptep->pte_low); +} + static void lguest_set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pteval) { *ptep = pteval; - lazy_hcall(LHCALL_SET_PTE, __pa(mm->pgd), addr, pteval.pte_low); + lguest_pte_update(mm, addr, ptep); } /* The Guest calls this to set a top-level entry. Again, we set the entry then @@ -498,8 +528,8 @@ static void lguest_set_pte_at(struct mm_struct *mm, unsigned long addr, static void lguest_set_pmd(pmd_t *pmdp, pmd_t pmdval) { *pmdp = pmdval; - lazy_hcall(LHCALL_SET_PMD, __pa(pmdp)&PAGE_MASK, - (__pa(pmdp)&(PAGE_SIZE-1))/4, 0); + lazy_hcall2(LHCALL_SET_PMD, __pa(pmdp) & PAGE_MASK, + (__pa(pmdp) & (PAGE_SIZE - 1)) / 4); } /* There are a couple of legacy places where the kernel sets a PTE, but we @@ -515,7 +545,7 @@ static void lguest_set_pte(pte_t *ptep, pte_t pteval) { *ptep = pteval; if (cr3_changed) - lazy_hcall(LHCALL_FLUSH_TLB, 1, 0, 0); + lazy_hcall1(LHCALL_FLUSH_TLB, 1); } /* Unfortunately for Lguest, the pv_mmu_ops for page tables were based on @@ -531,7 +561,7 @@ static void lguest_set_pte(pte_t *ptep, pte_t pteval) static void lguest_flush_tlb_single(unsigned long addr) { /* Simply set it to zero: if it was not, it will fault back in. */ - lazy_hcall(LHCALL_SET_PTE, lguest_data.pgdir, addr, 0); + lazy_hcall3(LHCALL_SET_PTE, lguest_data.pgdir, addr, 0); } /* This is what happens after the Guest has removed a large number of entries. @@ -539,7 +569,7 @@ static void lguest_flush_tlb_single(unsigned long addr) * have changed, ie. virtual addresses below PAGE_OFFSET. */ static void lguest_flush_tlb_user(void) { - lazy_hcall(LHCALL_FLUSH_TLB, 0, 0, 0); + lazy_hcall1(LHCALL_FLUSH_TLB, 0); } /* This is called when the kernel page tables have changed. That's not very @@ -547,7 +577,7 @@ static void lguest_flush_tlb_user(void) * slow), so it's worth separating this from the user flushing above. */ static void lguest_flush_tlb_kernel(void) { - lazy_hcall(LHCALL_FLUSH_TLB, 1, 0, 0); + lazy_hcall1(LHCALL_FLUSH_TLB, 1); } /* @@ -594,19 +624,21 @@ static void __init lguest_init_IRQ(void) /* Some systems map "vectors" to interrupts weirdly. Lguest has * a straightforward 1 to 1 mapping, so force that here. */ __get_cpu_var(vector_irq)[vector] = i; - if (vector != SYSCALL_VECTOR) { - set_intr_gate(vector, - interrupt[vector-FIRST_EXTERNAL_VECTOR]); - set_irq_chip_and_handler_name(i, &lguest_irq_controller, - handle_level_irq, - "level"); - } + if (vector != SYSCALL_VECTOR) + set_intr_gate(vector, interrupt[i]); } /* This call is required to set up for 4k stacks, where we have * separate stacks for hard and soft interrupts. */ irq_ctx_init(smp_processor_id()); } +void lguest_setup_irq(unsigned int irq) +{ + irq_to_desc_alloc_cpu(irq, 0); + set_irq_chip_and_handler_name(irq, &lguest_irq_controller, + handle_level_irq, "level"); +} + /* * Time. * @@ -682,7 +714,7 @@ static int lguest_clockevent_set_next_event(unsigned long delta, } /* Please wake us this far in the future. */ - hcall(LHCALL_SET_CLOCKEVENT, delta, 0, 0); + kvm_hypercall1(LHCALL_SET_CLOCKEVENT, delta); return 0; } @@ -693,7 +725,7 @@ static void lguest_clockevent_set_mode(enum clock_event_mode mode, case CLOCK_EVT_MODE_UNUSED: case CLOCK_EVT_MODE_SHUTDOWN: /* A 0 argument shuts the clock down. */ - hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0); + kvm_hypercall0(LHCALL_SET_CLOCKEVENT); break; case CLOCK_EVT_MODE_ONESHOT: /* This is what we expect. */ @@ -768,8 +800,8 @@ static void lguest_time_init(void) static void lguest_load_sp0(struct tss_struct *tss, struct thread_struct *thread) { - lazy_hcall(LHCALL_SET_STACK, __KERNEL_DS|0x1, thread->sp0, - THREAD_SIZE/PAGE_SIZE); + lazy_hcall3(LHCALL_SET_STACK, __KERNEL_DS | 0x1, thread->sp0, + THREAD_SIZE / PAGE_SIZE); } /* Let's just say, I wouldn't do debugging under a Guest. */ @@ -842,7 +874,7 @@ static void set_lguest_basic_apic_ops(void) /* STOP! Until an interrupt comes in. */ static void lguest_safe_halt(void) { - hcall(LHCALL_HALT, 0, 0, 0); + kvm_hypercall0(LHCALL_HALT); } /* The SHUTDOWN hypercall takes a string to describe what's happening, and @@ -852,7 +884,8 @@ static void lguest_safe_halt(void) * rather than virtual addresses, so we use __pa() here. */ static void lguest_power_off(void) { - hcall(LHCALL_SHUTDOWN, __pa("Power down"), LGUEST_SHUTDOWN_POWEROFF, 0); + kvm_hypercall2(LHCALL_SHUTDOWN, __pa("Power down"), + LGUEST_SHUTDOWN_POWEROFF); } /* @@ -862,7 +895,7 @@ static void lguest_power_off(void) */ static int lguest_panic(struct notifier_block *nb, unsigned long l, void *p) { - hcall(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF, 0); + kvm_hypercall2(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF); /* The hcall won't return, but to keep gcc happy, we're "done". */ return NOTIFY_DONE; } @@ -903,7 +936,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count) len = sizeof(scratch) - 1; scratch[len] = '\0'; memcpy(scratch, buf, len); - hcall(LHCALL_NOTIFY, __pa(scratch), 0, 0); + kvm_hypercall1(LHCALL_NOTIFY, __pa(scratch)); /* This routine returns the number of bytes actually written. */ return len; @@ -913,7 +946,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count) * Launcher to reboot us. */ static void lguest_restart(char *reason) { - hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0); + kvm_hypercall2(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART); } /*G:050 @@ -1033,6 +1066,8 @@ __init void lguest_init(void) pv_mmu_ops.read_cr3 = lguest_read_cr3; pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu; pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mode; + pv_mmu_ops.pte_update = lguest_pte_update; + pv_mmu_ops.pte_update_defer = lguest_pte_update; #ifdef CONFIG_X86_LOCAL_APIC /* apic read/write intercepts */ @@ -1051,14 +1086,6 @@ __init void lguest_init(void) * lguest_init() where the rest of the fairly chaotic boot setup * occurs. */ - /* The native boot code sets up initial page tables immediately after - * the kernel itself, and sets init_pg_tables_end so they're not - * clobbered. The Launcher places our initial pagetables somewhere at - * the top of our physical memory, so we don't need extra space: set - * init_pg_tables_end to the end of the kernel. */ - init_pg_tables_start = __pa(pg0); - init_pg_tables_end = __pa(pg0); - /* As described in head_32.S, we map the first 128M of memory. */ max_pfn_mapped = (128*1024*1024) >> PAGE_SHIFT; diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S index 10b9bd3..f795419 100644 --- a/arch/x86/lguest/i386_head.S +++ b/arch/x86/lguest/i386_head.S @@ -27,8 +27,8 @@ ENTRY(lguest_entry) /* We make the "initialization" hypercall now to tell the Host about * us, and also find out where it put our page tables. */ movl $LHCALL_LGUEST_INIT, %eax - movl $lguest_data - __PAGE_OFFSET, %edx - int $LGUEST_TRAP_ENTRY + movl $lguest_data - __PAGE_OFFSET, %ebx + .byte 0x0f,0x01,0xc1 /* KVM_HYPERCALL */ /* Set up the initial stack so we can run C code. */ movl $(init_thread_union+THREAD_SIZE),%esp diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index c22981f..ad5441e 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -1,30 +1,38 @@ /* Copyright 2002 Andi Kleen */ #include <linux/linkage.h> -#include <asm/dwarf2.h> + #include <asm/cpufeature.h> +#include <asm/dwarf2.h> /* * memcpy - Copy a memory block. * - * Input: - * rdi destination - * rsi source - * rdx count - * + * Input: + * rdi destination + * rsi source + * rdx count + * * Output: * rax original destination - */ + */ +/* + * memcpy_c() - fast string ops (REP MOVSQ) based variant. + * + * Calls to this get patched into the kernel image via the + * alternative instructions framework: + */ ALIGN memcpy_c: CFI_STARTPROC - movq %rdi,%rax - movl %edx,%ecx - shrl $3,%ecx - andl $7,%edx + movq %rdi, %rax + + movl %edx, %ecx + shrl $3, %ecx + andl $7, %edx rep movsq - movl %edx,%ecx + movl %edx, %ecx rep movsb ret CFI_ENDPROC @@ -33,99 +41,110 @@ ENDPROC(memcpy_c) ENTRY(__memcpy) ENTRY(memcpy) CFI_STARTPROC - pushq %rbx - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET rbx, 0 - movq %rdi,%rax - movl %edx,%ecx - shrl $6,%ecx + /* + * Put the number of full 64-byte blocks into %ecx. + * Tail portion is handled at the end: + */ + movq %rdi, %rax + movl %edx, %ecx + shrl $6, %ecx jz .Lhandle_tail .p2align 4 .Lloop_64: + /* + * We decrement the loop index here - and the zero-flag is + * checked at the end of the loop (instructions inbetween do + * not change the zero flag): + */ decl %ecx - movq (%rsi),%r11 - movq 8(%rsi),%r8 + /* + * Move in blocks of 4x16 bytes: + */ + movq 0*8(%rsi), %r11 + movq 1*8(%rsi), %r8 + movq %r11, 0*8(%rdi) + movq %r8, 1*8(%rdi) - movq %r11,(%rdi) - movq %r8,1*8(%rdi) + movq 2*8(%rsi), %r9 + movq 3*8(%rsi), %r10 + movq %r9, 2*8(%rdi) + movq %r10, 3*8(%rdi) - movq 2*8(%rsi),%r9 - movq 3*8(%rsi),%r10 + movq 4*8(%rsi), %r11 + movq 5*8(%rsi), %r8 + movq %r11, 4*8(%rdi) + movq %r8, 5*8(%rdi) - movq %r9,2*8(%rdi) - movq %r10,3*8(%rdi) + movq 6*8(%rsi), %r9 + movq 7*8(%rsi), %r10 + movq %r9, 6*8(%rdi) + movq %r10, 7*8(%rdi) - movq 4*8(%rsi),%r11 - movq 5*8(%rsi),%r8 + leaq 64(%rsi), %rsi + leaq 64(%rdi), %rdi - movq %r11,4*8(%rdi) - movq %r8,5*8(%rdi) - - movq 6*8(%rsi),%r9 - movq 7*8(%rsi),%r10 - - movq %r9,6*8(%rdi) - movq %r10,7*8(%rdi) - - leaq 64(%rsi),%rsi - leaq 64(%rdi),%rdi jnz .Lloop_64 .Lhandle_tail: - movl %edx,%ecx - andl $63,%ecx - shrl $3,%ecx + movl %edx, %ecx + andl $63, %ecx + shrl $3, %ecx jz .Lhandle_7 + .p2align 4 .Lloop_8: decl %ecx - movq (%rsi),%r8 - movq %r8,(%rdi) - leaq 8(%rdi),%rdi - leaq 8(%rsi),%rsi + movq (%rsi), %r8 + movq %r8, (%rdi) + leaq 8(%rdi), %rdi + leaq 8(%rsi), %rsi jnz .Lloop_8 .Lhandle_7: - movl %edx,%ecx - andl $7,%ecx - jz .Lende + movl %edx, %ecx + andl $7, %ecx + jz .Lend + .p2align 4 .Lloop_1: - movb (%rsi),%r8b - movb %r8b,(%rdi) + movb (%rsi), %r8b + movb %r8b, (%rdi) incq %rdi incq %rsi decl %ecx jnz .Lloop_1 -.Lende: - popq %rbx - CFI_ADJUST_CFA_OFFSET -8 - CFI_RESTORE rbx +.Lend: ret -.Lfinal: CFI_ENDPROC ENDPROC(memcpy) ENDPROC(__memcpy) - /* Some CPUs run faster using the string copy instructions. - It is also a lot simpler. Use this when possible */ + /* + * Some CPUs run faster using the string copy instructions. + * It is also a lot simpler. Use this when possible: + */ - .section .altinstr_replacement,"ax" + .section .altinstr_replacement, "ax" 1: .byte 0xeb /* jmp <disp8> */ .byte (memcpy_c - memcpy) - (2f - 1b) /* offset */ 2: .previous - .section .altinstructions,"a" + + .section .altinstructions, "a" .align 8 .quad memcpy .quad 1b .byte X86_FEATURE_REP_GOOD - /* Replace only beginning, memcpy is used to apply alternatives, so it - * is silly to overwrite itself with nops - reboot is only outcome... */ + + /* + * Replace only beginning, memcpy is used to apply alternatives, + * so it is silly to overwrite itself with nops - reboot is the + * only outcome... + */ .byte 2b - 1b .byte 2b - 1b .previous diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c index 491e737..aa09870 100644 --- a/arch/x86/math-emu/fpu_aux.c +++ b/arch/x86/math-emu/fpu_aux.c @@ -30,20 +30,29 @@ static void fclex(void) } /* Needs to be externally visible */ -void finit(void) +void finit_task(struct task_struct *tsk) { - control_word = 0x037f; - partial_status = 0; - top = 0; /* We don't keep top in the status word internally. */ - fpu_tag_word = 0xffff; + struct i387_soft_struct *soft = &tsk->thread.xstate->soft; + struct address *oaddr, *iaddr; + soft->cwd = 0x037f; + soft->swd = 0; + soft->ftop = 0; /* We don't keep top in the status word internally. */ + soft->twd = 0xffff; /* The behaviour is different from that detailed in Section 15.1.6 of the Intel manual */ - operand_address.offset = 0; - operand_address.selector = 0; - instruction_address.offset = 0; - instruction_address.selector = 0; - instruction_address.opcode = 0; - no_ip_update = 1; + oaddr = (struct address *)&soft->foo; + oaddr->offset = 0; + oaddr->selector = 0; + iaddr = (struct address *)&soft->fip; + iaddr->offset = 0; + iaddr->selector = 0; + iaddr->opcode = 0; + soft->no_update = 1; +} + +void finit(void) +{ + finit_task(current); } /* diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 2b938a3..fdd30d0 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,4 +1,4 @@ -obj-y := init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ +obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ pat.o pgtable.o gup.o obj-$(CONFIG_SMP) += tlb.o @@ -14,7 +14,7 @@ obj-$(CONFIG_MMIOTRACE) += mmiotrace.o mmiotrace-y := kmmio.o pf_in.o mmio-mod.o obj-$(CONFIG_MMIOTRACE_TEST) += testmmiotrace.o -obj-$(CONFIG_NUMA) += numa_$(BITS).o +obj-$(CONFIG_NUMA) += numa.o numa_$(BITS).o obj-$(CONFIG_K8_NUMA) += k8topology_64.o obj-$(CONFIG_ACPI_NUMA) += srat_$(BITS).o diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index bcc079c..8126e8d 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -1,5 +1,6 @@ #include <linux/highmem.h> #include <linux/module.h> +#include <linux/swap.h> /* for totalram_pages */ void *kmap(struct page *page) { @@ -18,49 +19,6 @@ void kunmap(struct page *page) kunmap_high(page); } -static void debug_kmap_atomic_prot(enum km_type type) -{ -#ifdef CONFIG_DEBUG_HIGHMEM - static unsigned warn_count = 10; - - if (unlikely(warn_count == 0)) - return; - - if (unlikely(in_interrupt())) { - if (in_irq()) { - if (type != KM_IRQ0 && type != KM_IRQ1 && - type != KM_BIO_SRC_IRQ && type != KM_BIO_DST_IRQ && - type != KM_BOUNCE_READ) { - WARN_ON(1); - warn_count--; - } - } else if (!irqs_disabled()) { /* softirq */ - if (type != KM_IRQ0 && type != KM_IRQ1 && - type != KM_SOFTIRQ0 && type != KM_SOFTIRQ1 && - type != KM_SKB_SUNRPC_DATA && - type != KM_SKB_DATA_SOFTIRQ && - type != KM_BOUNCE_READ) { - WARN_ON(1); - warn_count--; - } - } - } - - if (type == KM_IRQ0 || type == KM_IRQ1 || type == KM_BOUNCE_READ || - type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ) { - if (!irqs_disabled()) { - WARN_ON(1); - warn_count--; - } - } else if (type == KM_SOFTIRQ0 || type == KM_SOFTIRQ1) { - if (irq_count() == 0 && !irqs_disabled()) { - WARN_ON(1); - warn_count--; - } - } -#endif -} - /* * kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because * no global lock is needed and because the kmap code must perform a global TLB @@ -80,7 +38,7 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) if (!PageHighMem(page)) return page_address(page); - debug_kmap_atomic_prot(type); + debug_kmap_atomic(type); idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); @@ -120,22 +78,13 @@ void kunmap_atomic(void *kvaddr, enum km_type type) pagefault_enable(); } -/* This is the same as kmap_atomic() but can map memory that doesn't +/* + * This is the same as kmap_atomic() but can map memory that doesn't * have a struct page associated with it. */ void *kmap_atomic_pfn(unsigned long pfn, enum km_type type) { - enum fixed_addresses idx; - unsigned long vaddr; - - pagefault_disable(); - - idx = type + KM_TYPE_NR*smp_processor_id(); - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - set_pte(kmap_pte-idx, pfn_pte(pfn, kmap_prot)); - arch_flush_lazy_mmu_mode(); - - return (void*) vaddr; + return kmap_atomic_prot_pfn(pfn, type, kmap_prot); } EXPORT_SYMBOL_GPL(kmap_atomic_pfn); /* temporarily in use by i915 GEM until vmap */ @@ -156,3 +105,27 @@ EXPORT_SYMBOL(kmap); EXPORT_SYMBOL(kunmap); EXPORT_SYMBOL(kmap_atomic); EXPORT_SYMBOL(kunmap_atomic); + +void __init set_highmem_pages_init(void) +{ + struct zone *zone; + int nid; + + for_each_zone(zone) { + unsigned long zone_start_pfn, zone_end_pfn; + + if (!is_highmem(zone)) + continue; + + zone_start_pfn = zone->zone_start_pfn; + zone_end_pfn = zone_start_pfn + zone->spanned_pages; + + nid = zone_to_nid(zone); + printk(KERN_INFO "Initializing %s for node %d (%08lx:%08lx)\n", + zone->name, nid, zone_start_pfn, zone_end_pfn); + + add_highpages_with_active_regions(nid, zone_start_pfn, + zone_end_pfn); + } + totalram_pages += totalhigh_pages; +} diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c new file mode 100644 index 0000000..fd3da1d --- /dev/null +++ b/arch/x86/mm/init.c @@ -0,0 +1,393 @@ +#include <linux/ioport.h> +#include <linux/swap.h> + +#include <asm/cacheflush.h> +#include <asm/e820.h> +#include <asm/init.h> +#include <asm/page.h> +#include <asm/page_types.h> +#include <asm/sections.h> +#include <asm/system.h> +#include <asm/tlbflush.h> + +unsigned long __initdata e820_table_start; +unsigned long __meminitdata e820_table_end; +unsigned long __meminitdata e820_table_top; + +int after_bootmem; + +int direct_gbpages +#ifdef CONFIG_DIRECT_GBPAGES + = 1 +#endif +; + +static void __init find_early_table_space(unsigned long end, int use_pse, + int use_gbpages) +{ + unsigned long puds, pmds, ptes, tables, start; + + puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; + tables = roundup(puds * sizeof(pud_t), PAGE_SIZE); + + if (use_gbpages) { + unsigned long extra; + + extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT); + pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT; + } else + pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT; + + tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE); + + if (use_pse) { + unsigned long extra; + + extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT); +#ifdef CONFIG_X86_32 + extra += PMD_SIZE; +#endif + ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT; + } else + ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT; + + tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE); + +#ifdef CONFIG_X86_32 + /* for fixmap */ + tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE); +#endif + + /* + * RED-PEN putting page tables only on node 0 could + * cause a hotspot and fill up ZONE_DMA. The page tables + * need roughly 0.5KB per GB. + */ +#ifdef CONFIG_X86_32 + start = 0x7000; + e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT, + tables, PAGE_SIZE); +#else /* CONFIG_X86_64 */ + start = 0x8000; + e820_table_start = find_e820_area(start, end, tables, PAGE_SIZE); +#endif + if (e820_table_start == -1UL) + panic("Cannot find space for the kernel page tables"); + + e820_table_start >>= PAGE_SHIFT; + e820_table_end = e820_table_start; + e820_table_top = e820_table_start + (tables >> PAGE_SHIFT); + + printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n", + end, e820_table_start << PAGE_SHIFT, e820_table_top << PAGE_SHIFT); +} + +struct map_range { + unsigned long start; + unsigned long end; + unsigned page_size_mask; +}; + +#ifdef CONFIG_X86_32 +#define NR_RANGE_MR 3 +#else /* CONFIG_X86_64 */ +#define NR_RANGE_MR 5 +#endif + +static int __meminit save_mr(struct map_range *mr, int nr_range, + unsigned long start_pfn, unsigned long end_pfn, + unsigned long page_size_mask) +{ + if (start_pfn < end_pfn) { + if (nr_range >= NR_RANGE_MR) + panic("run out of range for init_memory_mapping\n"); + mr[nr_range].start = start_pfn<<PAGE_SHIFT; + mr[nr_range].end = end_pfn<<PAGE_SHIFT; + mr[nr_range].page_size_mask = page_size_mask; + nr_range++; + } + + return nr_range; +} + +#ifdef CONFIG_X86_64 +static void __init init_gbpages(void) +{ + if (direct_gbpages && cpu_has_gbpages) + printk(KERN_INFO "Using GB pages for direct mapping\n"); + else + direct_gbpages = 0; +} +#else +static inline void init_gbpages(void) +{ +} +#endif + +/* + * Setup the direct mapping of the physical memory at PAGE_OFFSET. + * This runs before bootmem is initialized and gets pages directly from + * the physical memory. To access them they are temporarily mapped. + */ +unsigned long __init_refok init_memory_mapping(unsigned long start, + unsigned long end) +{ + unsigned long page_size_mask = 0; + unsigned long start_pfn, end_pfn; + unsigned long ret = 0; + unsigned long pos; + + struct map_range mr[NR_RANGE_MR]; + int nr_range, i; + int use_pse, use_gbpages; + + printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end); + + if (!after_bootmem) + init_gbpages(); + +#ifdef CONFIG_DEBUG_PAGEALLOC + /* + * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages. + * This will simplify cpa(), which otherwise needs to support splitting + * large pages into small in interrupt context, etc. + */ + use_pse = use_gbpages = 0; +#else + use_pse = cpu_has_pse; + use_gbpages = direct_gbpages; +#endif + +#ifdef CONFIG_X86_32 +#ifdef CONFIG_X86_PAE + set_nx(); + if (nx_enabled) + printk(KERN_INFO "NX (Execute Disable) protection: active\n"); +#endif + + /* Enable PSE if available */ + if (cpu_has_pse) + set_in_cr4(X86_CR4_PSE); + + /* Enable PGE if available */ + if (cpu_has_pge) { + set_in_cr4(X86_CR4_PGE); + __supported_pte_mask |= _PAGE_GLOBAL; + } +#endif + + if (use_gbpages) + page_size_mask |= 1 << PG_LEVEL_1G; + if (use_pse) + page_size_mask |= 1 << PG_LEVEL_2M; + + memset(mr, 0, sizeof(mr)); + nr_range = 0; + + /* head if not big page alignment ? */ + start_pfn = start >> PAGE_SHIFT; + pos = start_pfn << PAGE_SHIFT; +#ifdef CONFIG_X86_32 + /* + * Don't use a large page for the first 2/4MB of memory + * because there are often fixed size MTRRs in there + * and overlapping MTRRs into large pages can cause + * slowdowns. + */ + if (pos == 0) + end_pfn = 1<<(PMD_SHIFT - PAGE_SHIFT); + else + end_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT) + << (PMD_SHIFT - PAGE_SHIFT); +#else /* CONFIG_X86_64 */ + end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT) + << (PMD_SHIFT - PAGE_SHIFT); +#endif + if (end_pfn > (end >> PAGE_SHIFT)) + end_pfn = end >> PAGE_SHIFT; + if (start_pfn < end_pfn) { + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); + pos = end_pfn << PAGE_SHIFT; + } + + /* big page (2M) range */ + start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT) + << (PMD_SHIFT - PAGE_SHIFT); +#ifdef CONFIG_X86_32 + end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); +#else /* CONFIG_X86_64 */ + end_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT) + << (PUD_SHIFT - PAGE_SHIFT); + if (end_pfn > ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT))) + end_pfn = ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT)); +#endif + + if (start_pfn < end_pfn) { + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, + page_size_mask & (1<<PG_LEVEL_2M)); + pos = end_pfn << PAGE_SHIFT; + } + +#ifdef CONFIG_X86_64 + /* big page (1G) range */ + start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT) + << (PUD_SHIFT - PAGE_SHIFT); + end_pfn = (end >> PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT); + if (start_pfn < end_pfn) { + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, + page_size_mask & + ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G))); + pos = end_pfn << PAGE_SHIFT; + } + + /* tail is not big page (1G) alignment */ + start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT) + << (PMD_SHIFT - PAGE_SHIFT); + end_pfn = (end >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); + if (start_pfn < end_pfn) { + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, + page_size_mask & (1<<PG_LEVEL_2M)); + pos = end_pfn << PAGE_SHIFT; + } +#endif + + /* tail is not big page (2M) alignment */ + start_pfn = pos>>PAGE_SHIFT; + end_pfn = end>>PAGE_SHIFT; + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); + + /* try to merge same page size and continuous */ + for (i = 0; nr_range > 1 && i < nr_range - 1; i++) { + unsigned long old_start; + if (mr[i].end != mr[i+1].start || + mr[i].page_size_mask != mr[i+1].page_size_mask) + continue; + /* move it */ + old_start = mr[i].start; + memmove(&mr[i], &mr[i+1], + (nr_range - 1 - i) * sizeof(struct map_range)); + mr[i--].start = old_start; + nr_range--; + } + + for (i = 0; i < nr_range; i++) + printk(KERN_DEBUG " %010lx - %010lx page %s\n", + mr[i].start, mr[i].end, + (mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":( + (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k")); + + /* + * Find space for the kernel direct mapping tables. + * + * Later we should allocate these tables in the local node of the + * memory mapped. Unfortunately this is done currently before the + * nodes are discovered. + */ + if (!after_bootmem) + find_early_table_space(end, use_pse, use_gbpages); + +#ifdef CONFIG_X86_32 + for (i = 0; i < nr_range; i++) + kernel_physical_mapping_init(mr[i].start, mr[i].end, + mr[i].page_size_mask); + ret = end; +#else /* CONFIG_X86_64 */ + for (i = 0; i < nr_range; i++) + ret = kernel_physical_mapping_init(mr[i].start, mr[i].end, + mr[i].page_size_mask); +#endif + +#ifdef CONFIG_X86_32 + early_ioremap_page_table_range_init(); + + load_cr3(swapper_pg_dir); +#endif + +#ifdef CONFIG_X86_64 + if (!after_bootmem) + mmu_cr4_features = read_cr4(); +#endif + __flush_tlb_all(); + + if (!after_bootmem && e820_table_end > e820_table_start) + reserve_early(e820_table_start << PAGE_SHIFT, + e820_table_end << PAGE_SHIFT, "PGTABLE"); + + if (!after_bootmem) + early_memtest(start, end); + + return ret >> PAGE_SHIFT; +} + + +/* + * devmem_is_allowed() checks to see if /dev/mem access to a certain address + * is valid. The argument is a physical page number. + * + * + * On x86, access has to be given to the first megabyte of ram because that area + * contains bios code and data regions used by X and dosemu and similar apps. + * Access has to be given to non-kernel-ram areas as well, these contain the PCI + * mmio resources as well as potential bios/acpi data regions. + */ +int devmem_is_allowed(unsigned long pagenr) +{ + if (pagenr <= 256) + return 1; + if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) + return 0; + if (!page_is_ram(pagenr)) + return 1; + return 0; +} + +void free_init_pages(char *what, unsigned long begin, unsigned long end) +{ + unsigned long addr = begin; + + if (addr >= end) + return; + + /* + * If debugging page accesses then do not free this memory but + * mark them not present - any buggy init-section access will + * create a kernel page fault: + */ +#ifdef CONFIG_DEBUG_PAGEALLOC + printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n", + begin, PAGE_ALIGN(end)); + set_memory_np(begin, (end - begin) >> PAGE_SHIFT); +#else + /* + * We just marked the kernel text read only above, now that + * we are going to free part of that, we need to make that + * writeable first. + */ + set_memory_rw(begin, (end - begin) >> PAGE_SHIFT); + + printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10); + + for (; addr < end; addr += PAGE_SIZE) { + ClearPageReserved(virt_to_page(addr)); + init_page_count(virt_to_page(addr)); + memset((void *)(addr & ~(PAGE_SIZE-1)), + POISON_FREE_INITMEM, PAGE_SIZE); + free_page(addr); + totalram_pages++; + } +#endif +} + +void free_initmem(void) +{ + free_init_pages("unused kernel memory", + (unsigned long)(&__init_begin), + (unsigned long)(&__init_end)); +} + +#ifdef CONFIG_BLK_DEV_INITRD +void free_initrd_mem(unsigned long start, unsigned long end) +{ + free_init_pages("initrd memory", start, end); +} +#endif diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 06708ee..749559e 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -49,8 +49,7 @@ #include <asm/paravirt.h> #include <asm/setup.h> #include <asm/cacheflush.h> - -unsigned int __VMALLOC_RESERVE = 128 << 20; +#include <asm/init.h> unsigned long max_low_pfn_mapped; unsigned long max_pfn_mapped; @@ -60,19 +59,14 @@ unsigned long highstart_pfn, highend_pfn; static noinline int do_test_wp_bit(void); - -static unsigned long __initdata table_start; -static unsigned long __meminitdata table_end; -static unsigned long __meminitdata table_top; - -static int __initdata after_init_bootmem; +bool __read_mostly __vmalloc_start_set = false; static __init void *alloc_low_page(void) { - unsigned long pfn = table_end++; + unsigned long pfn = e820_table_end++; void *adr; - if (pfn >= table_top) + if (pfn >= e820_table_top) panic("alloc_low_page: ran out of memory"); adr = __va(pfn * PAGE_SIZE); @@ -92,7 +86,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd) #ifdef CONFIG_X86_PAE if (!(pgd_val(*pgd) & _PAGE_PRESENT)) { - if (after_init_bootmem) + if (after_bootmem) pmd_table = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE); else pmd_table = (pmd_t *)alloc_low_page(); @@ -119,7 +113,7 @@ static pte_t * __init one_page_table_init(pmd_t *pmd) if (!(pmd_val(*pmd) & _PAGE_PRESENT)) { pte_t *page_table = NULL; - if (after_init_bootmem) { + if (after_bootmem) { #ifdef CONFIG_DEBUG_PAGEALLOC page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE); #endif @@ -137,6 +131,23 @@ static pte_t * __init one_page_table_init(pmd_t *pmd) return pte_offset_kernel(pmd, 0); } +pmd_t * __init populate_extra_pmd(unsigned long vaddr) +{ + int pgd_idx = pgd_index(vaddr); + int pmd_idx = pmd_index(vaddr); + + return one_md_table_init(swapper_pg_dir + pgd_idx) + pmd_idx; +} + +pte_t * __init populate_extra_pte(unsigned long vaddr) +{ + int pte_idx = pte_index(vaddr); + pmd_t *pmd; + + pmd = populate_extra_pmd(vaddr); + return one_page_table_init(pmd) + pte_idx; +} + static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd, unsigned long vaddr, pte_t *lastpte) { @@ -153,12 +164,12 @@ static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd, if (pmd_idx_kmap_begin != pmd_idx_kmap_end && (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end - && ((__pa(pte) >> PAGE_SHIFT) < table_start - || (__pa(pte) >> PAGE_SHIFT) >= table_end)) { + && ((__pa(pte) >> PAGE_SHIFT) < e820_table_start + || (__pa(pte) >> PAGE_SHIFT) >= e820_table_end)) { pte_t *newpte; int i; - BUG_ON(after_init_bootmem); + BUG_ON(after_bootmem); newpte = alloc_low_page(); for (i = 0; i < PTRS_PER_PTE; i++) set_pte(newpte + i, pte[i]); @@ -227,11 +238,14 @@ static inline int is_kernel_text(unsigned long addr) * of max_low_pfn pages, by creating page tables starting from address * PAGE_OFFSET: */ -static void __init kernel_physical_mapping_init(pgd_t *pgd_base, - unsigned long start_pfn, - unsigned long end_pfn, - int use_pse) +unsigned long __init +kernel_physical_mapping_init(unsigned long start, + unsigned long end, + unsigned long page_size_mask) { + int use_pse = page_size_mask == (1<<PG_LEVEL_2M); + unsigned long start_pfn, end_pfn; + pgd_t *pgd_base = swapper_pg_dir; int pgd_idx, pmd_idx, pte_ofs; unsigned long pfn; pgd_t *pgd; @@ -240,6 +254,9 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base, unsigned pages_2m, pages_4k; int mapping_iter; + start_pfn = start >> PAGE_SHIFT; + end_pfn = end >> PAGE_SHIFT; + /* * First iteration will setup identity mapping using large/small pages * based on use_pse, with other attributes same as set by @@ -354,26 +371,6 @@ repeat: mapping_iter = 2; goto repeat; } -} - -/* - * devmem_is_allowed() checks to see if /dev/mem access to a certain address - * is valid. The argument is a physical page number. - * - * - * On x86, access has to be given to the first megabyte of ram because that area - * contains bios code and data regions used by X and dosemu and similar apps. - * Access has to be given to non-kernel-ram areas as well, these contain the PCI - * mmio resources as well as potential bios/acpi data regions. - */ -int devmem_is_allowed(unsigned long pagenr) -{ - if (pagenr <= 256) - return 1; - if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) - return 0; - if (!page_is_ram(pagenr)) - return 1; return 0; } @@ -469,22 +466,10 @@ void __init add_highpages_with_active_regions(int nid, unsigned long start_pfn, work_with_active_regions(nid, add_highpages_work_fn, &data); } -#ifndef CONFIG_NUMA -static void __init set_highmem_pages_init(void) -{ - add_highpages_with_active_regions(0, highstart_pfn, highend_pfn); - - totalram_pages += totalhigh_pages; -} -#endif /* !CONFIG_NUMA */ - #else static inline void permanent_kmaps_init(pgd_t *pgd_base) { } -static inline void set_highmem_pages_init(void) -{ -} #endif /* CONFIG_HIGHMEM */ void __init native_pagetable_setup_start(pgd_t *base) @@ -542,8 +527,9 @@ void __init native_pagetable_setup_done(pgd_t *base) * be partially populated, and so it avoids stomping on any existing * mappings. */ -static void __init early_ioremap_page_table_range_init(pgd_t *pgd_base) +void __init early_ioremap_page_table_range_init(void) { + pgd_t *pgd_base = swapper_pg_dir; unsigned long vaddr, end; /* @@ -638,7 +624,7 @@ static int __init noexec_setup(char *str) } early_param("noexec", noexec_setup); -static void __init set_nx(void) +void __init set_nx(void) { unsigned int v[4], l, h; @@ -790,6 +776,8 @@ void __init initmem_init(unsigned long start_pfn, #ifdef CONFIG_FLATMEM max_mapnr = num_physpages; #endif + __vmalloc_start_set = true; + printk(KERN_NOTICE "%ldMB LOWMEM available.\n", pages_to_mb(max_low_pfn)); @@ -811,176 +799,66 @@ static void __init zone_sizes_init(void) free_area_init_nodes(max_zone_pfns); } +static unsigned long __init setup_node_bootmem(int nodeid, + unsigned long start_pfn, + unsigned long end_pfn, + unsigned long bootmap) +{ + unsigned long bootmap_size; + + /* don't touch min_low_pfn */ + bootmap_size = init_bootmem_node(NODE_DATA(nodeid), + bootmap >> PAGE_SHIFT, + start_pfn, end_pfn); + printk(KERN_INFO " node %d low ram: %08lx - %08lx\n", + nodeid, start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT); + printk(KERN_INFO " node %d bootmap %08lx - %08lx\n", + nodeid, bootmap, bootmap + bootmap_size); + free_bootmem_with_active_regions(nodeid, end_pfn); + early_res_to_bootmem(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT); + + return bootmap + bootmap_size; +} + void __init setup_bootmem_allocator(void) { - int i; + int nodeid; unsigned long bootmap_size, bootmap; /* * Initialize the boot-time allocator (with low memory only): */ bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT; - bootmap = find_e820_area(min_low_pfn<<PAGE_SHIFT, - max_pfn_mapped<<PAGE_SHIFT, bootmap_size, + bootmap = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, bootmap_size, PAGE_SIZE); if (bootmap == -1L) panic("Cannot find bootmem map of size %ld\n", bootmap_size); reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP"); - /* don't touch min_low_pfn */ - bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT, - min_low_pfn, max_low_pfn); printk(KERN_INFO " mapped low ram: 0 - %08lx\n", max_pfn_mapped<<PAGE_SHIFT); - printk(KERN_INFO " low ram: %08lx - %08lx\n", - min_low_pfn<<PAGE_SHIFT, max_low_pfn<<PAGE_SHIFT); - printk(KERN_INFO " bootmap %08lx - %08lx\n", - bootmap, bootmap + bootmap_size); - for_each_online_node(i) - free_bootmem_with_active_regions(i, max_low_pfn); - early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT); - - after_init_bootmem = 1; -} - -static void __init find_early_table_space(unsigned long end, int use_pse) -{ - unsigned long puds, pmds, ptes, tables, start; - - puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; - tables = PAGE_ALIGN(puds * sizeof(pud_t)); - - pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT; - tables += PAGE_ALIGN(pmds * sizeof(pmd_t)); + printk(KERN_INFO " low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT); - if (use_pse) { - unsigned long extra; + for_each_online_node(nodeid) { + unsigned long start_pfn, end_pfn; - extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT); - extra += PMD_SIZE; - ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT; - } else - ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT; - - tables += PAGE_ALIGN(ptes * sizeof(pte_t)); - - /* for fixmap */ - tables += PAGE_ALIGN(__end_of_fixed_addresses * sizeof(pte_t)); - - /* - * RED-PEN putting page tables only on node 0 could - * cause a hotspot and fill up ZONE_DMA. The page tables - * need roughly 0.5KB per GB. - */ - start = 0x7000; - table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT, - tables, PAGE_SIZE); - if (table_start == -1UL) - panic("Cannot find space for the kernel page tables"); - - table_start >>= PAGE_SHIFT; - table_end = table_start; - table_top = table_start + (tables>>PAGE_SHIFT); - - printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n", - end, table_start << PAGE_SHIFT, - (table_start << PAGE_SHIFT) + tables); -} - -unsigned long __init_refok init_memory_mapping(unsigned long start, - unsigned long end) -{ - pgd_t *pgd_base = swapper_pg_dir; - unsigned long start_pfn, end_pfn; - unsigned long big_page_start; -#ifdef CONFIG_DEBUG_PAGEALLOC - /* - * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages. - * This will simplify cpa(), which otherwise needs to support splitting - * large pages into small in interrupt context, etc. - */ - int use_pse = 0; +#ifdef CONFIG_NEED_MULTIPLE_NODES + start_pfn = node_start_pfn[nodeid]; + end_pfn = node_end_pfn[nodeid]; + if (start_pfn > max_low_pfn) + continue; + if (end_pfn > max_low_pfn) + end_pfn = max_low_pfn; #else - int use_pse = cpu_has_pse; -#endif - - /* - * Find space for the kernel direct mapping tables. - */ - if (!after_init_bootmem) - find_early_table_space(end, use_pse); - -#ifdef CONFIG_X86_PAE - set_nx(); - if (nx_enabled) - printk(KERN_INFO "NX (Execute Disable) protection: active\n"); + start_pfn = 0; + end_pfn = max_low_pfn; #endif - - /* Enable PSE if available */ - if (cpu_has_pse) - set_in_cr4(X86_CR4_PSE); - - /* Enable PGE if available */ - if (cpu_has_pge) { - set_in_cr4(X86_CR4_PGE); - __supported_pte_mask |= _PAGE_GLOBAL; + bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn, + bootmap); } - /* - * Don't use a large page for the first 2/4MB of memory - * because there are often fixed size MTRRs in there - * and overlapping MTRRs into large pages can cause - * slowdowns. - */ - big_page_start = PMD_SIZE; - - if (start < big_page_start) { - start_pfn = start >> PAGE_SHIFT; - end_pfn = min(big_page_start>>PAGE_SHIFT, end>>PAGE_SHIFT); - } else { - /* head is not big page alignment ? */ - start_pfn = start >> PAGE_SHIFT; - end_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT) - << (PMD_SHIFT - PAGE_SHIFT); - } - if (start_pfn < end_pfn) - kernel_physical_mapping_init(pgd_base, start_pfn, end_pfn, 0); - - /* big page range */ - start_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT) - << (PMD_SHIFT - PAGE_SHIFT); - if (start_pfn < (big_page_start >> PAGE_SHIFT)) - start_pfn = big_page_start >> PAGE_SHIFT; - end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); - if (start_pfn < end_pfn) - kernel_physical_mapping_init(pgd_base, start_pfn, end_pfn, - use_pse); - - /* tail is not big page alignment ? */ - start_pfn = end_pfn; - if (start_pfn > (big_page_start>>PAGE_SHIFT)) { - end_pfn = end >> PAGE_SHIFT; - if (start_pfn < end_pfn) - kernel_physical_mapping_init(pgd_base, start_pfn, - end_pfn, 0); - } - - early_ioremap_page_table_range_init(pgd_base); - - load_cr3(swapper_pg_dir); - - __flush_tlb_all(); - - if (!after_init_bootmem) - reserve_early(table_start << PAGE_SHIFT, - table_end << PAGE_SHIFT, "PGTABLE"); - - if (!after_init_bootmem) - early_memtest(start, end); - - return end >> PAGE_SHIFT; + after_bootmem = 1; } - /* * paging_init() sets up the page tables - note that the first 8MB are * already mapped by head.S. @@ -1176,17 +1054,47 @@ static noinline int do_test_wp_bit(void) const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); +static int kernel_set_to_readonly; + +void set_kernel_text_rw(void) +{ + unsigned long start = PFN_ALIGN(_text); + unsigned long size = PFN_ALIGN(_etext) - start; + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read write\n", + start, start+size); + + set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT); +} + +void set_kernel_text_ro(void) +{ + unsigned long start = PFN_ALIGN(_text); + unsigned long size = PFN_ALIGN(_etext) - start; + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read only\n", + start, start+size); + + set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); +} + void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_text); unsigned long size = PFN_ALIGN(_etext) - start; -#ifndef CONFIG_DYNAMIC_FTRACE - /* Dynamic tracing modifies the kernel text section */ set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); printk(KERN_INFO "Write protecting the kernel text: %luk\n", size >> 10); + kernel_set_to_readonly = 1; + #ifdef CONFIG_CPA_DEBUG printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n", start, start+size); @@ -1195,7 +1103,6 @@ void mark_rodata_ro(void) printk(KERN_INFO "Testing CPA: write protecting again\n"); set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT); #endif -#endif /* CONFIG_DYNAMIC_FTRACE */ start += size; size = (unsigned long)__end_rodata - start; @@ -1214,52 +1121,6 @@ void mark_rodata_ro(void) } #endif -void free_init_pages(char *what, unsigned long begin, unsigned long end) -{ -#ifdef CONFIG_DEBUG_PAGEALLOC - /* - * If debugging page accesses then do not free this memory but - * mark them not present - any buggy init-section access will - * create a kernel page fault: - */ - printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n", - begin, PAGE_ALIGN(end)); - set_memory_np(begin, (end - begin) >> PAGE_SHIFT); -#else - unsigned long addr; - - /* - * We just marked the kernel text read only above, now that - * we are going to free part of that, we need to make that - * writeable first. - */ - set_memory_rw(begin, (end - begin) >> PAGE_SHIFT); - - for (addr = begin; addr < end; addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE); - free_page(addr); - totalram_pages++; - } - printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10); -#endif -} - -void free_initmem(void) -{ - free_init_pages("unused kernel memory", - (unsigned long)(&__init_begin), - (unsigned long)(&__init_end)); -} - -#ifdef CONFIG_BLK_DEV_INITRD -void free_initrd_mem(unsigned long start, unsigned long end) -{ - free_init_pages("initrd memory", start, end); -} -#endif - int __init reserve_bootmem_generic(unsigned long phys, unsigned long len, int flags) { diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index b135225..1753e80 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -48,6 +48,7 @@ #include <asm/kdebug.h> #include <asm/numa.h> #include <asm/cacheflush.h> +#include <asm/init.h> /* * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries. @@ -61,12 +62,6 @@ static unsigned long dma_reserve __initdata; DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); -int direct_gbpages -#ifdef CONFIG_DIRECT_GBPAGES - = 1 -#endif -; - static int __init parse_direct_gbpages_off(char *arg) { direct_gbpages = 0; @@ -87,12 +82,10 @@ early_param("gbpages", parse_direct_gbpages_on); * around without checking the pgd every time. */ -int after_bootmem; - pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP; EXPORT_SYMBOL_GPL(__supported_pte_mask); -static int do_not_nx __cpuinitdata; +static int disable_nx __cpuinitdata; /* * noexec=on|off @@ -107,9 +100,9 @@ static int __init nonx_setup(char *str) return -EINVAL; if (!strncmp(str, "on", 2)) { __supported_pte_mask |= _PAGE_NX; - do_not_nx = 0; + disable_nx = 0; } else if (!strncmp(str, "off", 3)) { - do_not_nx = 1; + disable_nx = 1; __supported_pte_mask &= ~_PAGE_NX; } return 0; @@ -121,7 +114,7 @@ void __cpuinit check_efer(void) unsigned long efer; rdmsrl(MSR_EFER, efer); - if (!(efer & EFER_NX) || do_not_nx) + if (!(efer & EFER_NX) || disable_nx) __supported_pte_mask &= ~_PAGE_NX; } @@ -168,34 +161,51 @@ static __ref void *spp_getpage(void) return ptr; } -void -set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) +static pud_t *fill_pud(pgd_t *pgd, unsigned long vaddr) { - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + if (pgd_none(*pgd)) { + pud_t *pud = (pud_t *)spp_getpage(); + pgd_populate(&init_mm, pgd, pud); + if (pud != pud_offset(pgd, 0)) + printk(KERN_ERR "PAGETABLE BUG #00! %p <-> %p\n", + pud, pud_offset(pgd, 0)); + } + return pud_offset(pgd, vaddr); +} - pud = pud_page + pud_index(vaddr); +static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr) +{ if (pud_none(*pud)) { - pmd = (pmd_t *) spp_getpage(); + pmd_t *pmd = (pmd_t *) spp_getpage(); pud_populate(&init_mm, pud, pmd); - if (pmd != pmd_offset(pud, 0)) { + if (pmd != pmd_offset(pud, 0)) printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n", - pmd, pmd_offset(pud, 0)); - return; - } + pmd, pmd_offset(pud, 0)); } - pmd = pmd_offset(pud, vaddr); + return pmd_offset(pud, vaddr); +} + +static pte_t *fill_pte(pmd_t *pmd, unsigned long vaddr) +{ if (pmd_none(*pmd)) { - pte = (pte_t *) spp_getpage(); + pte_t *pte = (pte_t *) spp_getpage(); pmd_populate_kernel(&init_mm, pmd, pte); - if (pte != pte_offset_kernel(pmd, 0)) { + if (pte != pte_offset_kernel(pmd, 0)) printk(KERN_ERR "PAGETABLE BUG #02!\n"); - return; - } } + return pte_offset_kernel(pmd, vaddr); +} + +void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) +{ + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pud = pud_page + pud_index(vaddr); + pmd = fill_pmd(pud, vaddr); + pte = fill_pte(pmd, vaddr); - pte = pte_offset_kernel(pmd, vaddr); set_pte(pte, new_pte); /* @@ -205,8 +215,7 @@ set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) __flush_tlb_one(vaddr); } -void -set_pte_vaddr(unsigned long vaddr, pte_t pteval) +void set_pte_vaddr(unsigned long vaddr, pte_t pteval) { pgd_t *pgd; pud_t *pud_page; @@ -223,6 +232,24 @@ set_pte_vaddr(unsigned long vaddr, pte_t pteval) set_pte_vaddr_pud(pud_page, vaddr, pteval); } +pmd_t * __init populate_extra_pmd(unsigned long vaddr) +{ + pgd_t *pgd; + pud_t *pud; + + pgd = pgd_offset_k(vaddr); + pud = fill_pud(pgd, vaddr); + return fill_pmd(pud, vaddr); +} + +pte_t * __init populate_extra_pte(unsigned long vaddr) +{ + pmd_t *pmd; + + pmd = populate_extra_pmd(vaddr); + return fill_pte(pmd, vaddr); +} + /* * Create large page table mappings for a range of physical addresses. */ @@ -291,13 +318,9 @@ void __init cleanup_highmap(void) } } -static unsigned long __initdata table_start; -static unsigned long __meminitdata table_end; -static unsigned long __meminitdata table_top; - static __ref void *alloc_low_page(unsigned long *phys) { - unsigned long pfn = table_end++; + unsigned long pfn = e820_table_end++; void *adr; if (after_bootmem) { @@ -307,7 +330,7 @@ static __ref void *alloc_low_page(unsigned long *phys) return adr; } - if (pfn >= table_top) + if (pfn >= e820_table_top) panic("alloc_low_page: ran out of memory"); adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE); @@ -547,58 +570,10 @@ phys_pud_update(pgd_t *pgd, unsigned long addr, unsigned long end, return phys_pud_init(pud, addr, end, page_size_mask); } -static void __init find_early_table_space(unsigned long end, int use_pse, - int use_gbpages) -{ - unsigned long puds, pmds, ptes, tables, start; - - puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; - tables = roundup(puds * sizeof(pud_t), PAGE_SIZE); - if (use_gbpages) { - unsigned long extra; - extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT); - pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT; - } else - pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT; - tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE); - - if (use_pse) { - unsigned long extra; - extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT); - ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT; - } else - ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT; - tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE); - - /* - * RED-PEN putting page tables only on node 0 could - * cause a hotspot and fill up ZONE_DMA. The page tables - * need roughly 0.5KB per GB. - */ - start = 0x8000; - table_start = find_e820_area(start, end, tables, PAGE_SIZE); - if (table_start == -1UL) - panic("Cannot find space for the kernel page tables"); - - table_start >>= PAGE_SHIFT; - table_end = table_start; - table_top = table_start + (tables >> PAGE_SHIFT); - - printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n", - end, table_start << PAGE_SHIFT, table_top << PAGE_SHIFT); -} - -static void __init init_gbpages(void) -{ - if (direct_gbpages && cpu_has_gbpages) - printk(KERN_INFO "Using GB pages for direct mapping\n"); - else - direct_gbpages = 0; -} - -static unsigned long __meminit kernel_physical_mapping_init(unsigned long start, - unsigned long end, - unsigned long page_size_mask) +unsigned long __init +kernel_physical_mapping_init(unsigned long start, + unsigned long end, + unsigned long page_size_mask) { unsigned long next, last_map_addr = end; @@ -635,176 +610,6 @@ static unsigned long __meminit kernel_physical_mapping_init(unsigned long start, return last_map_addr; } -struct map_range { - unsigned long start; - unsigned long end; - unsigned page_size_mask; -}; - -#define NR_RANGE_MR 5 - -static int save_mr(struct map_range *mr, int nr_range, - unsigned long start_pfn, unsigned long end_pfn, - unsigned long page_size_mask) -{ - - if (start_pfn < end_pfn) { - if (nr_range >= NR_RANGE_MR) - panic("run out of range for init_memory_mapping\n"); - mr[nr_range].start = start_pfn<<PAGE_SHIFT; - mr[nr_range].end = end_pfn<<PAGE_SHIFT; - mr[nr_range].page_size_mask = page_size_mask; - nr_range++; - } - - return nr_range; -} - -/* - * Setup the direct mapping of the physical memory at PAGE_OFFSET. - * This runs before bootmem is initialized and gets pages directly from - * the physical memory. To access them they are temporarily mapped. - */ -unsigned long __init_refok init_memory_mapping(unsigned long start, - unsigned long end) -{ - unsigned long last_map_addr = 0; - unsigned long page_size_mask = 0; - unsigned long start_pfn, end_pfn; - unsigned long pos; - - struct map_range mr[NR_RANGE_MR]; - int nr_range, i; - int use_pse, use_gbpages; - - printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end); - - /* - * Find space for the kernel direct mapping tables. - * - * Later we should allocate these tables in the local node of the - * memory mapped. Unfortunately this is done currently before the - * nodes are discovered. - */ - if (!after_bootmem) - init_gbpages(); - -#ifdef CONFIG_DEBUG_PAGEALLOC - /* - * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages. - * This will simplify cpa(), which otherwise needs to support splitting - * large pages into small in interrupt context, etc. - */ - use_pse = use_gbpages = 0; -#else - use_pse = cpu_has_pse; - use_gbpages = direct_gbpages; -#endif - - if (use_gbpages) - page_size_mask |= 1 << PG_LEVEL_1G; - if (use_pse) - page_size_mask |= 1 << PG_LEVEL_2M; - - memset(mr, 0, sizeof(mr)); - nr_range = 0; - - /* head if not big page alignment ?*/ - start_pfn = start >> PAGE_SHIFT; - pos = start_pfn << PAGE_SHIFT; - end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT) - << (PMD_SHIFT - PAGE_SHIFT); - if (end_pfn > (end >> PAGE_SHIFT)) - end_pfn = end >> PAGE_SHIFT; - if (start_pfn < end_pfn) { - nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); - pos = end_pfn << PAGE_SHIFT; - } - - /* big page (2M) range*/ - start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT) - << (PMD_SHIFT - PAGE_SHIFT); - end_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT) - << (PUD_SHIFT - PAGE_SHIFT); - if (end_pfn > ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT))) - end_pfn = ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT)); - if (start_pfn < end_pfn) { - nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, - page_size_mask & (1<<PG_LEVEL_2M)); - pos = end_pfn << PAGE_SHIFT; - } - - /* big page (1G) range */ - start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT) - << (PUD_SHIFT - PAGE_SHIFT); - end_pfn = (end >> PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT); - if (start_pfn < end_pfn) { - nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, - page_size_mask & - ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G))); - pos = end_pfn << PAGE_SHIFT; - } - - /* tail is not big page (1G) alignment */ - start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT) - << (PMD_SHIFT - PAGE_SHIFT); - end_pfn = (end >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); - if (start_pfn < end_pfn) { - nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, - page_size_mask & (1<<PG_LEVEL_2M)); - pos = end_pfn << PAGE_SHIFT; - } - - /* tail is not big page (2M) alignment */ - start_pfn = pos>>PAGE_SHIFT; - end_pfn = end>>PAGE_SHIFT; - nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); - - /* try to merge same page size and continuous */ - for (i = 0; nr_range > 1 && i < nr_range - 1; i++) { - unsigned long old_start; - if (mr[i].end != mr[i+1].start || - mr[i].page_size_mask != mr[i+1].page_size_mask) - continue; - /* move it */ - old_start = mr[i].start; - memmove(&mr[i], &mr[i+1], - (nr_range - 1 - i) * sizeof (struct map_range)); - mr[i--].start = old_start; - nr_range--; - } - - for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG " %010lx - %010lx page %s\n", - mr[i].start, mr[i].end, - (mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":( - (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k")); - - if (!after_bootmem) - find_early_table_space(end, use_pse, use_gbpages); - - for (i = 0; i < nr_range; i++) - last_map_addr = kernel_physical_mapping_init( - mr[i].start, mr[i].end, - mr[i].page_size_mask); - - if (!after_bootmem) - mmu_cr4_features = read_cr4(); - __flush_tlb_all(); - - if (!after_bootmem && table_end > table_start) - reserve_early(table_start << PAGE_SHIFT, - table_end << PAGE_SHIFT, "PGTABLE"); - - printk(KERN_INFO "last_map_addr: %lx end: %lx\n", - last_map_addr, end); - - if (!after_bootmem) - early_memtest(start, end); - - return last_map_addr >> PAGE_SHIFT; -} - #ifndef CONFIG_NUMA void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn) { @@ -876,28 +681,6 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif /* CONFIG_MEMORY_HOTPLUG */ -/* - * devmem_is_allowed() checks to see if /dev/mem access to a certain address - * is valid. The argument is a physical page number. - * - * - * On x86, access has to be given to the first megabyte of ram because that area - * contains bios code and data regions used by X and dosemu and similar apps. - * Access has to be given to non-kernel-ram areas as well, these contain the PCI - * mmio resources as well as potential bios/acpi data regions. - */ -int devmem_is_allowed(unsigned long pagenr) -{ - if (pagenr <= 256) - return 1; - if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) - return 0; - if (!page_is_ram(pagenr)) - return 1; - return 0; -} - - static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules, kcore_vsyscall; @@ -947,46 +730,39 @@ void __init mem_init(void) initsize >> 10); } -void free_init_pages(char *what, unsigned long begin, unsigned long end) +#ifdef CONFIG_DEBUG_RODATA +const int rodata_test_data = 0xC3; +EXPORT_SYMBOL_GPL(rodata_test_data); + +static int kernel_set_to_readonly; + +void set_kernel_text_rw(void) { - unsigned long addr = begin; + unsigned long start = PFN_ALIGN(_stext); + unsigned long end = PFN_ALIGN(__start_rodata); - if (addr >= end) + if (!kernel_set_to_readonly) return; - /* - * If debugging page accesses then do not free this memory but - * mark them not present - any buggy init-section access will - * create a kernel page fault: - */ -#ifdef CONFIG_DEBUG_PAGEALLOC - printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n", - begin, PAGE_ALIGN(end)); - set_memory_np(begin, (end - begin) >> PAGE_SHIFT); -#else - printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10); - - for (; addr < end; addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - memset((void *)(addr & ~(PAGE_SIZE-1)), - POISON_FREE_INITMEM, PAGE_SIZE); - free_page(addr); - totalram_pages++; - } -#endif + pr_debug("Set kernel text: %lx - %lx for read write\n", + start, end); + + set_memory_rw(start, (end - start) >> PAGE_SHIFT); } -void free_initmem(void) +void set_kernel_text_ro(void) { - free_init_pages("unused kernel memory", - (unsigned long)(&__init_begin), - (unsigned long)(&__init_end)); -} + unsigned long start = PFN_ALIGN(_stext); + unsigned long end = PFN_ALIGN(__start_rodata); -#ifdef CONFIG_DEBUG_RODATA -const int rodata_test_data = 0xC3; -EXPORT_SYMBOL_GPL(rodata_test_data); + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read only\n", + start, end); + + set_memory_ro(start, (end - start) >> PAGE_SHIFT); +} void mark_rodata_ro(void) { @@ -994,15 +770,12 @@ void mark_rodata_ro(void) unsigned long rodata_start = ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK; -#ifdef CONFIG_DYNAMIC_FTRACE - /* Dynamic tracing modifies the kernel text section */ - start = rodata_start; -#endif - printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); set_memory_ro(start, (end - start) >> PAGE_SHIFT); + kernel_set_to_readonly = 1; + /* * The rodata section (but not the kernel text!) should also be * not-executable. @@ -1022,13 +795,6 @@ void mark_rodata_ro(void) #endif -#ifdef CONFIG_BLK_DEV_INITRD -void free_initrd_mem(unsigned long start, unsigned long end) -{ - free_init_pages("initrd memory", start, end); -} -#endif - int __init reserve_bootmem_generic(unsigned long phys, unsigned long len, int flags) { diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index 04102d4..8056545 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -19,10 +19,11 @@ #include <asm/iomap.h> #include <asm/pat.h> #include <linux/module.h> +#include <linux/highmem.h> int is_io_mapping_possible(resource_size_t base, unsigned long size) { -#ifndef CONFIG_X86_PAE +#if !defined(CONFIG_X86_PAE) && defined(CONFIG_PHYS_ADDR_T_64BIT) /* There is no way to map greater than 1 << 32 address without PAE */ if (base + size > 0x100000000ULL) return 0; @@ -31,16 +32,28 @@ int is_io_mapping_possible(resource_size_t base, unsigned long size) } EXPORT_SYMBOL_GPL(is_io_mapping_possible); -/* Map 'pfn' using fixed map 'type' and protections 'prot' - */ -void * -iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) +void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) { enum fixed_addresses idx; unsigned long vaddr; pagefault_disable(); + debug_kmap_atomic(type); + idx = type + KM_TYPE_NR * smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + set_pte(kmap_pte - idx, pfn_pte(pfn, prot)); + arch_flush_lazy_mmu_mode(); + + return (void *)vaddr; +} + +/* + * Map 'pfn' using fixed map 'type' and protections 'prot' + */ +void * +iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) +{ /* * For non-PAT systems, promote PAGE_KERNEL_WC to PAGE_KERNEL_UC_MINUS. * PAGE_KERNEL_WC maps to PWT, which translates to uncached if the @@ -50,12 +63,7 @@ iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC)) prot = PAGE_KERNEL_UC_MINUS; - idx = type + KM_TYPE_NR*smp_processor_id(); - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - set_pte(kmap_pte-idx, pfn_pte(pfn, prot)); - arch_flush_lazy_mmu_mode(); - - return (void*) vaddr; + return kmap_atomic_prot_pfn(pfn, type, prot); } EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 433f7bd..0dfa09d 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -22,13 +22,17 @@ #include <asm/pgalloc.h> #include <asm/pat.h> -#ifdef CONFIG_X86_64 - -static inline int phys_addr_valid(unsigned long addr) +static inline int phys_addr_valid(resource_size_t addr) { - return addr < (1UL << boot_cpu_data.x86_phys_bits); +#ifdef CONFIG_PHYS_ADDR_T_64BIT + return !(addr >> boot_cpu_data.x86_phys_bits); +#else + return 1; +#endif } +#ifdef CONFIG_X86_64 + unsigned long __phys_addr(unsigned long x) { if (x >= __START_KERNEL_map) { @@ -38,8 +42,7 @@ unsigned long __phys_addr(unsigned long x) } else { VIRTUAL_BUG_ON(x < PAGE_OFFSET); x -= PAGE_OFFSET; - VIRTUAL_BUG_ON(system_state == SYSTEM_BOOTING ? x > MAXMEM : - !phys_addr_valid(x)); + VIRTUAL_BUG_ON(!phys_addr_valid(x)); } return x; } @@ -56,10 +59,8 @@ bool __virt_addr_valid(unsigned long x) if (x < PAGE_OFFSET) return false; x -= PAGE_OFFSET; - if (system_state == SYSTEM_BOOTING ? - x > MAXMEM : !phys_addr_valid(x)) { + if (!phys_addr_valid(x)) return false; - } } return pfn_valid(x >> PAGE_SHIFT); @@ -68,18 +69,12 @@ EXPORT_SYMBOL(__virt_addr_valid); #else -static inline int phys_addr_valid(unsigned long addr) -{ - return 1; -} - #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { - /* VMALLOC_* aren't constants; not available at the boot time */ + /* VMALLOC_* aren't constants */ VIRTUAL_BUG_ON(x < PAGE_OFFSET); - VIRTUAL_BUG_ON(system_state != SYSTEM_BOOTING && - is_vmalloc_addr((void *) x)); + VIRTUAL_BUG_ON(__vmalloc_start_set && is_vmalloc_addr((void *) x)); return x - PAGE_OFFSET; } EXPORT_SYMBOL(__phys_addr); @@ -89,7 +84,9 @@ bool __virt_addr_valid(unsigned long x) { if (x < PAGE_OFFSET) return false; - if (system_state != SYSTEM_BOOTING && is_vmalloc_addr((void *) x)) + if (__vmalloc_start_set && is_vmalloc_addr((void *) x)) + return false; + if (x >= FIXADDR_START) return false; return pfn_valid((x - PAGE_OFFSET) >> PAGE_SHIFT); } @@ -508,13 +505,19 @@ static inline pte_t * __init early_ioremap_pte(unsigned long addr) return &bm_pte[pte_index(addr)]; } +static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata; + void __init early_ioremap_init(void) { pmd_t *pmd; + int i; if (early_ioremap_debug) printk(KERN_INFO "early_ioremap_init()\n"); + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) + slot_virt[i] = __fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i); + pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)); memset(bm_pte, 0, sizeof(bm_pte)); pmd_populate_kernel(&init_mm, pmd, bm_pte); @@ -581,6 +584,7 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx) static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata; static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata; + static int __init check_early_ioremap_leak(void) { int count = 0; @@ -602,7 +606,8 @@ static int __init check_early_ioremap_leak(void) } late_initcall(check_early_ioremap_leak); -static void __init __iomem *__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) +static void __init __iomem * +__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) { unsigned long offset, last_addr; unsigned int nrpages; @@ -668,9 +673,9 @@ static void __init __iomem *__early_ioremap(unsigned long phys_addr, unsigned lo --nrpages; } if (early_ioremap_debug) - printk(KERN_CONT "%08lx + %08lx\n", offset, fix_to_virt(idx0)); + printk(KERN_CONT "%08lx + %08lx\n", offset, slot_virt[slot]); - prev_map[slot] = (void __iomem *)(offset + fix_to_virt(idx0)); + prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]); return prev_map[slot]; } @@ -738,8 +743,3 @@ void __init early_iounmap(void __iomem *addr, unsigned long size) } prev_map[slot] = NULL; } - -void __this_fixmap_does_not_exist(void) -{ - WARN_ON(1); -} diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 9f20503..4f115e0 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -310,7 +310,7 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs) struct kmmio_context *ctx = &get_cpu_var(kmmio_ctx); if (!ctx->active) { - pr_warning("kmmio: spurious debug trap on CPU %d.\n", + pr_debug("kmmio: spurious debug trap on CPU %d.\n", smp_processor_id()); goto out; } @@ -451,23 +451,24 @@ static void rcu_free_kmmio_fault_pages(struct rcu_head *head) static void remove_kmmio_fault_pages(struct rcu_head *head) { - struct kmmio_delayed_release *dr = container_of( - head, - struct kmmio_delayed_release, - rcu); + struct kmmio_delayed_release *dr = + container_of(head, struct kmmio_delayed_release, rcu); struct kmmio_fault_page *p = dr->release_list; struct kmmio_fault_page **prevp = &dr->release_list; unsigned long flags; + spin_lock_irqsave(&kmmio_lock, flags); while (p) { - if (!p->count) + if (!p->count) { list_del_rcu(&p->list); - else + prevp = &p->release_next; + } else { *prevp = p->release_next; - prevp = &p->release_next; + } p = p->release_next; } spin_unlock_irqrestore(&kmmio_lock, flags); + /* This is the real RCU destroy call. */ call_rcu(&dr->rcu, rcu_free_kmmio_fault_pages); } diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c index 0bcd788..605c8be 100644 --- a/arch/x86/mm/memtest.c +++ b/arch/x86/mm/memtest.c @@ -100,6 +100,9 @@ static int __init parse_memtest(char *arg) { if (arg) memtest_pattern = simple_strtoul(arg, NULL, 0); + else + memtest_pattern = ARRAY_SIZE(patterns); + return 0; } diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index 2c4baa8..c9342ed 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -378,27 +378,34 @@ static void clear_trace_list(void) } #ifdef CONFIG_HOTPLUG_CPU -static cpumask_t downed_cpus; +static cpumask_var_t downed_cpus; static void enter_uniprocessor(void) { int cpu; int err; + if (downed_cpus == NULL && + !alloc_cpumask_var(&downed_cpus, GFP_KERNEL)) { + pr_notice(NAME "Failed to allocate mask\n"); + goto out; + } + get_online_cpus(); - downed_cpus = cpu_online_map; - cpu_clear(first_cpu(cpu_online_map), downed_cpus); + cpumask_copy(downed_cpus, cpu_online_mask); + cpumask_clear_cpu(cpumask_first(cpu_online_mask), downed_cpus); if (num_online_cpus() > 1) pr_notice(NAME "Disabling non-boot CPUs...\n"); put_online_cpus(); - for_each_cpu_mask(cpu, downed_cpus) { + for_each_cpu(cpu, downed_cpus) { err = cpu_down(cpu); if (!err) pr_info(NAME "CPU%d is down.\n", cpu); else pr_err(NAME "Error taking CPU%d down: %d\n", cpu, err); } +out: if (num_online_cpus() > 1) pr_warning(NAME "multiple CPUs still online, " "may miss events.\n"); @@ -411,10 +418,10 @@ static void __ref leave_uniprocessor(void) int cpu; int err; - if (cpus_weight(downed_cpus) == 0) + if (downed_cpus == NULL || cpumask_weight(downed_cpus) == 0) return; pr_notice(NAME "Re-enabling CPUs...\n"); - for_each_cpu_mask(cpu, downed_cpus) { + for_each_cpu(cpu, downed_cpus) { err = cpu_up(cpu); if (!err) pr_info(NAME "enabled CPU%d.\n", cpu); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c new file mode 100644 index 0000000..550df48 --- /dev/null +++ b/arch/x86/mm/numa.c @@ -0,0 +1,67 @@ +/* Common code for 32 and 64-bit NUMA */ +#include <linux/topology.h> +#include <linux/module.h> +#include <linux/bootmem.h> + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +# define DBG(x...) printk(KERN_DEBUG x) +#else +# define DBG(x...) +#endif + +/* + * Which logical CPUs are on which nodes + */ +cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; +EXPORT_SYMBOL(node_to_cpumask_map); + +/* + * Allocate node_to_cpumask_map based on number of available nodes + * Requires node_possible_map to be valid. + * + * Note: node_to_cpumask() is not valid until after this is done. + * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) + */ +void __init setup_node_to_cpumask_map(void) +{ + unsigned int node, num = 0; + + /* setup nr_node_ids if not done yet */ + if (nr_node_ids == MAX_NUMNODES) { + for_each_node_mask(node, node_possible_map) + num = node; + nr_node_ids = num + 1; + } + + /* allocate the map */ + for (node = 0; node < nr_node_ids; node++) + alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]); + + /* cpumask_of_node() will now work */ + pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids); +} + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +/* + * Returns a pointer to the bitmask of CPUs on Node 'node'. + */ +const struct cpumask *cpumask_of_node(int node) +{ + if (node >= nr_node_ids) { + printk(KERN_WARNING + "cpumask_of_node(%d): node > nr_node_ids(%d)\n", + node, nr_node_ids); + dump_stack(); + return cpu_none_mask; + } + if (node_to_cpumask_map[node] == NULL) { + printk(KERN_WARNING + "cpumask_of_node(%d): no node_to_cpumask_map!\n", + node); + dump_stack(); + return cpu_online_mask; + } + return node_to_cpumask_map[node]; +} +EXPORT_SYMBOL(cpumask_of_node); +#endif diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 3957cd6..3daefa0 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -416,39 +416,14 @@ void __init initmem_init(unsigned long start_pfn, for_each_online_node(nid) propagate_e820_map_node(nid); - for_each_online_node(nid) + for_each_online_node(nid) { memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); + NODE_DATA(nid)->bdata = &bootmem_node_data[nid]; + } - NODE_DATA(0)->bdata = &bootmem_node_data[0]; setup_bootmem_allocator(); } -void __init set_highmem_pages_init(void) -{ -#ifdef CONFIG_HIGHMEM - struct zone *zone; - int nid; - - for_each_zone(zone) { - unsigned long zone_start_pfn, zone_end_pfn; - - if (!is_highmem(zone)) - continue; - - zone_start_pfn = zone->zone_start_pfn; - zone_end_pfn = zone_start_pfn + zone->spanned_pages; - - nid = zone_to_nid(zone); - printk(KERN_INFO "Initializing %s for node %d (%08lx:%08lx)\n", - zone->name, nid, zone_start_pfn, zone_end_pfn); - - add_highpages_with_active_regions(nid, zone_start_pfn, - zone_end_pfn); - } - totalram_pages += totalhigh_pages; -#endif -} - #ifdef CONFIG_MEMORY_HOTPLUG static int paddr_to_nid(u64 addr) { diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 64c9cf0..d73aaa8 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -20,12 +20,6 @@ #include <asm/acpi.h> #include <asm/k8.h> -#ifdef CONFIG_DEBUG_PER_CPU_MAPS -# define DBG(x...) printk(KERN_DEBUG x) -#else -# define DBG(x...) -#endif - struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); @@ -49,12 +43,6 @@ DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE); EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map); /* - * Which logical CPUs are on which nodes - */ -cpumask_t *node_to_cpumask_map; -EXPORT_SYMBOL(node_to_cpumask_map); - -/* * Given a shift value, try to populate memnodemap[] * Returns : * 1 if OK @@ -661,36 +649,6 @@ void __init init_cpu_to_node(void) #endif -/* - * Allocate node_to_cpumask_map based on number of available nodes - * Requires node_possible_map to be valid. - * - * Note: node_to_cpumask() is not valid until after this is done. - * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) - */ -void __init setup_node_to_cpumask_map(void) -{ - unsigned int node, num = 0; - cpumask_t *map; - - /* setup nr_node_ids if not done yet */ - if (nr_node_ids == MAX_NUMNODES) { - for_each_node_mask(node, node_possible_map) - num = node; - nr_node_ids = num + 1; - } - - /* allocate the map */ - map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t)); - DBG("node_to_cpumask_map at %p for %d nodes\n", map, nr_node_ids); - - pr_debug("Node to cpumask map at %p for %d nodes\n", - map, nr_node_ids); - - /* node_to_cpumask() will now work */ - node_to_cpumask_map = map; -} - void __cpuinit numa_set_node(int cpu, int node) { int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map); @@ -723,12 +681,12 @@ void __cpuinit numa_clear_node(int cpu) void __cpuinit numa_add_cpu(int cpu) { - cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); + cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); } void __cpuinit numa_remove_cpu(int cpu) { - cpu_clear(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); + cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); } #else /* CONFIG_DEBUG_PER_CPU_MAPS */ @@ -739,20 +697,20 @@ void __cpuinit numa_remove_cpu(int cpu) static void __cpuinit numa_set_cpumask(int cpu, int enable) { int node = early_cpu_to_node(cpu); - cpumask_t *mask; + struct cpumask *mask; char buf[64]; - if (node_to_cpumask_map == NULL) { - printk(KERN_ERR "node_to_cpumask_map NULL\n"); + mask = node_to_cpumask_map[node]; + if (mask == NULL) { + printk(KERN_ERR "node_to_cpumask_map[%i] NULL\n", node); dump_stack(); return; } - mask = &node_to_cpumask_map[node]; if (enable) - cpu_set(cpu, *mask); + cpumask_set_cpu(cpu, mask); else - cpu_clear(cpu, *mask); + cpumask_clear_cpu(cpu, mask); cpulist_scnprintf(buf, sizeof(buf), mask); printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n", @@ -799,59 +757,6 @@ int early_cpu_to_node(int cpu) return per_cpu(x86_cpu_to_node_map, cpu); } - -/* empty cpumask */ -static const cpumask_t cpu_mask_none; - -/* - * Returns a pointer to the bitmask of CPUs on Node 'node'. - */ -const cpumask_t *cpumask_of_node(int node) -{ - if (node_to_cpumask_map == NULL) { - printk(KERN_WARNING - "cpumask_of_node(%d): no node_to_cpumask_map!\n", - node); - dump_stack(); - return (const cpumask_t *)&cpu_online_map; - } - if (node >= nr_node_ids) { - printk(KERN_WARNING - "cpumask_of_node(%d): node > nr_node_ids(%d)\n", - node, nr_node_ids); - dump_stack(); - return &cpu_mask_none; - } - return &node_to_cpumask_map[node]; -} -EXPORT_SYMBOL(cpumask_of_node); - -/* - * Returns a bitmask of CPUs on Node 'node'. - * - * Side note: this function creates the returned cpumask on the stack - * so with a high NR_CPUS count, excessive stack space is used. The - * node_to_cpumask_ptr function should be used whenever possible. - */ -cpumask_t node_to_cpumask(int node) -{ - if (node_to_cpumask_map == NULL) { - printk(KERN_WARNING - "node_to_cpumask(%d): no node_to_cpumask_map!\n", node); - dump_stack(); - return cpu_online_map; - } - if (node >= nr_node_ids) { - printk(KERN_WARNING - "node_to_cpumask(%d): node > nr_node_ids(%d)\n", - node, nr_node_ids); - dump_stack(); - return cpu_mask_none; - } - return node_to_cpumask_map[node]; -} -EXPORT_SYMBOL(node_to_cpumask); - /* * --------- end of debug versions of the numa functions --------- */ diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 8253bc9..d71e1b6 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -16,6 +16,7 @@ #include <asm/processor.h> #include <asm/tlbflush.h> #include <asm/sections.h> +#include <asm/setup.h> #include <asm/uaccess.h> #include <asm/pgalloc.h> #include <asm/proto.h> @@ -33,6 +34,7 @@ struct cpa_data { unsigned long pfn; unsigned force_split : 1; int curpage; + struct page **pages; }; /* @@ -45,6 +47,7 @@ static DEFINE_SPINLOCK(cpa_lock); #define CPA_FLUSHTLB 1 #define CPA_ARRAY 2 +#define CPA_PAGES_ARRAY 4 #ifdef CONFIG_PROC_FS static unsigned long direct_pages_count[PG_LEVEL_NUM]; @@ -95,7 +98,7 @@ static inline unsigned long highmap_start_pfn(void) static inline unsigned long highmap_end_pfn(void) { - return __pa(roundup((unsigned long)_end, PMD_SIZE)) >> PAGE_SHIFT; + return __pa(roundup(_brk_end, PMD_SIZE)) >> PAGE_SHIFT; } #endif @@ -201,10 +204,10 @@ static void cpa_flush_range(unsigned long start, int numpages, int cache) } } -static void cpa_flush_array(unsigned long *start, int numpages, int cache) +static void cpa_flush_array(unsigned long *start, int numpages, int cache, + int in_flags, struct page **pages) { unsigned int i, level; - unsigned long *addr; BUG_ON(irqs_disabled()); @@ -225,14 +228,22 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache) * will cause all other CPUs to flush the same * cachelines: */ - for (i = 0, addr = start; i < numpages; i++, addr++) { - pte_t *pte = lookup_address(*addr, &level); + for (i = 0; i < numpages; i++) { + unsigned long addr; + pte_t *pte; + + if (in_flags & CPA_PAGES_ARRAY) + addr = (unsigned long)page_address(pages[i]); + else + addr = start[i]; + + pte = lookup_address(addr, &level); /* * Only flush present addresses: */ if (pte && (pte_val(*pte) & _PAGE_PRESENT)) - clflush_cache_range((void *) *addr, PAGE_SIZE); + clflush_cache_range((void *)addr, PAGE_SIZE); } } @@ -522,6 +533,17 @@ static int split_large_page(pte_t *kpte, unsigned long address) * primary protection behavior: */ __set_pmd_pte(kpte, address, mk_pte(base, __pgprot(_KERNPG_TABLE))); + + /* + * Intel Atom errata AAH41 workaround. + * + * The real fix should be in hw or in a microcode update, but + * we also probabilistically try to reduce the window of having + * a large TLB mixed with 4K TLBs while instruction fetches are + * going on. + */ + __flush_tlb_all(); + base = NULL; out_unlock: @@ -573,7 +595,9 @@ static int __change_page_attr(struct cpa_data *cpa, int primary) unsigned int level; pte_t *kpte, old_pte; - if (cpa->flags & CPA_ARRAY) + if (cpa->flags & CPA_PAGES_ARRAY) + address = (unsigned long)page_address(cpa->pages[cpa->curpage]); + else if (cpa->flags & CPA_ARRAY) address = cpa->vaddr[cpa->curpage]; else address = *cpa->vaddr; @@ -676,7 +700,9 @@ static int cpa_process_alias(struct cpa_data *cpa) * No need to redo, when the primary call touched the direct * mapping already: */ - if (cpa->flags & CPA_ARRAY) + if (cpa->flags & CPA_PAGES_ARRAY) + vaddr = (unsigned long)page_address(cpa->pages[cpa->curpage]); + else if (cpa->flags & CPA_ARRAY) vaddr = cpa->vaddr[cpa->curpage]; else vaddr = *cpa->vaddr; @@ -687,7 +713,7 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa = *cpa; temp_cpa_vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT); alias_cpa.vaddr = &temp_cpa_vaddr; - alias_cpa.flags &= ~CPA_ARRAY; + alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); ret = __change_page_attr_set_clr(&alias_cpa, 0); @@ -700,7 +726,7 @@ static int cpa_process_alias(struct cpa_data *cpa) * No need to redo, when the primary call touched the high * mapping already: */ - if (within(vaddr, (unsigned long) _text, (unsigned long) _end)) + if (within(vaddr, (unsigned long) _text, _brk_end)) return 0; /* @@ -713,7 +739,7 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa = *cpa; temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + __START_KERNEL_map - phys_base; alias_cpa.vaddr = &temp_cpa_vaddr; - alias_cpa.flags &= ~CPA_ARRAY; + alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); /* * The high mapping range is imprecise, so ignore the return value. @@ -734,7 +760,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) */ cpa->numpages = numpages; /* for array changes, we can't use large page */ - if (cpa->flags & CPA_ARRAY) + if (cpa->flags & (CPA_ARRAY | CPA_PAGES_ARRAY)) cpa->numpages = 1; if (!debug_pagealloc) @@ -758,7 +784,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) */ BUG_ON(cpa->numpages > numpages); numpages -= cpa->numpages; - if (cpa->flags & CPA_ARRAY) + if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) cpa->curpage++; else *cpa->vaddr += cpa->numpages * PAGE_SIZE; @@ -775,7 +801,8 @@ static inline int cache_attr(pgprot_t attr) static int change_page_attr_set_clr(unsigned long *addr, int numpages, pgprot_t mask_set, pgprot_t mask_clr, - int force_split, int array) + int force_split, int in_flag, + struct page **pages) { struct cpa_data cpa; int ret, cache, checkalias; @@ -790,15 +817,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, return 0; /* Ensure we are PAGE_SIZE aligned */ - if (!array) { - if (*addr & ~PAGE_MASK) { - *addr &= PAGE_MASK; - /* - * People should not be passing in unaligned addresses: - */ - WARN_ON_ONCE(1); - } - } else { + if (in_flag & CPA_ARRAY) { int i; for (i = 0; i < numpages; i++) { if (addr[i] & ~PAGE_MASK) { @@ -806,6 +825,18 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, WARN_ON_ONCE(1); } } + } else if (!(in_flag & CPA_PAGES_ARRAY)) { + /* + * in_flag of CPA_PAGES_ARRAY implies it is aligned. + * No need to cehck in that case + */ + if (*addr & ~PAGE_MASK) { + *addr &= PAGE_MASK; + /* + * People should not be passing in unaligned addresses: + */ + WARN_ON_ONCE(1); + } } /* Must avoid aliasing mappings in the highmem code */ @@ -821,6 +852,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, arch_flush_lazy_mmu_mode(); cpa.vaddr = addr; + cpa.pages = pages; cpa.numpages = numpages; cpa.mask_set = mask_set; cpa.mask_clr = mask_clr; @@ -828,8 +860,8 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, cpa.curpage = 0; cpa.force_split = force_split; - if (array) - cpa.flags |= CPA_ARRAY; + if (in_flag & (CPA_ARRAY | CPA_PAGES_ARRAY)) + cpa.flags |= in_flag; /* No alias checking for _NX bit modifications */ checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX; @@ -855,9 +887,10 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, * wbindv): */ if (!ret && cpu_has_clflush) { - if (cpa.flags & CPA_ARRAY) - cpa_flush_array(addr, numpages, cache); - else + if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) { + cpa_flush_array(addr, numpages, cache, + cpa.flags, pages); + } else cpa_flush_range(*addr, numpages, cache); } else cpa_flush_all(cache); @@ -877,14 +910,28 @@ static inline int change_page_attr_set(unsigned long *addr, int numpages, pgprot_t mask, int array) { return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0), 0, - array); + (array ? CPA_ARRAY : 0), NULL); } static inline int change_page_attr_clear(unsigned long *addr, int numpages, pgprot_t mask, int array) { return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask, 0, - array); + (array ? CPA_ARRAY : 0), NULL); +} + +static inline int cpa_set_pages_array(struct page **pages, int numpages, + pgprot_t mask) +{ + return change_page_attr_set_clr(NULL, numpages, mask, __pgprot(0), 0, + CPA_PAGES_ARRAY, pages); +} + +static inline int cpa_clear_pages_array(struct page **pages, int numpages, + pgprot_t mask) +{ + return change_page_attr_set_clr(NULL, numpages, __pgprot(0), mask, 0, + CPA_PAGES_ARRAY, pages); } int _set_memory_uc(unsigned long addr, int numpages) @@ -1032,7 +1079,7 @@ int set_memory_np(unsigned long addr, int numpages) int set_memory_4k(unsigned long addr, int numpages) { return change_page_attr_set_clr(&addr, numpages, __pgprot(0), - __pgprot(0), 1, 0); + __pgprot(0), 1, 0, NULL); } int set_pages_uc(struct page *page, int numpages) @@ -1043,6 +1090,35 @@ int set_pages_uc(struct page *page, int numpages) } EXPORT_SYMBOL(set_pages_uc); +int set_pages_array_uc(struct page **pages, int addrinarray) +{ + unsigned long start; + unsigned long end; + int i; + int free_idx; + + for (i = 0; i < addrinarray; i++) { + start = (unsigned long)page_address(pages[i]); + end = start + PAGE_SIZE; + if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL)) + goto err_out; + } + + if (cpa_set_pages_array(pages, addrinarray, + __pgprot(_PAGE_CACHE_UC_MINUS)) == 0) { + return 0; /* Success */ + } +err_out: + free_idx = i; + for (i = 0; i < free_idx; i++) { + start = (unsigned long)page_address(pages[i]); + end = start + PAGE_SIZE; + free_memtype(start, end); + } + return -EINVAL; +} +EXPORT_SYMBOL(set_pages_array_uc); + int set_pages_wb(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); @@ -1051,6 +1127,26 @@ int set_pages_wb(struct page *page, int numpages) } EXPORT_SYMBOL(set_pages_wb); +int set_pages_array_wb(struct page **pages, int addrinarray) +{ + int retval; + unsigned long start; + unsigned long end; + int i; + + retval = cpa_clear_pages_array(pages, addrinarray, + __pgprot(_PAGE_CACHE_MASK)); + + for (i = 0; i < addrinarray; i++) { + start = (unsigned long)page_address(pages[i]); + end = start + PAGE_SIZE; + free_memtype(start, end); + } + + return retval; +} +EXPORT_SYMBOL(set_pages_array_wb); + int set_pages_x(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 2ed3715..640339e 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -677,10 +677,11 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, is_ram = pat_pagerange_is_ram(paddr, paddr + size); /* - * reserve_pfn_range() doesn't support RAM pages. + * reserve_pfn_range() doesn't support RAM pages. Maintain the current + * behavior with RAM pages by returning success. */ if (is_ram != 0) - return -EINVAL; + return 0; ret = reserve_memtype(paddr, paddr + size, want_flags, &flags); if (ret) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 86f2ffc..5b7c7c84 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -313,6 +313,24 @@ int ptep_clear_flush_young(struct vm_area_struct *vma, return young; } +/** + * reserve_top_address - reserves a hole in the top of kernel address space + * @reserve - size of hole to reserve + * + * Can be used to relocate the fixmap area and poke a hole in the top + * of kernel address space to make room for a hypervisor. + */ +void __init reserve_top_address(unsigned long reserve) +{ +#ifdef CONFIG_X86_32 + BUG_ON(fixmaps_set > 0); + printk(KERN_INFO "Reserving virtual address space above 0x%08x\n", + (int)-reserve); + __FIXADDR_TOP = -reserve - PAGE_SIZE; + __VMALLOC_RESERVE += reserve; +#endif +} + int fixmaps_set; void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 0951db9..46c8834 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -20,6 +20,8 @@ #include <asm/tlb.h> #include <asm/tlbflush.h> +unsigned int __VMALLOC_RESERVE = 128 << 20; + /* * Associate a virtual page frame with a given physical page frame * and protection flags for that frame. @@ -48,7 +50,7 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval) } pte = pte_offset_kernel(pmd, vaddr); if (pte_val(pteval)) - set_pte_present(&init_mm, vaddr, pte, pteval); + set_pte_at(&init_mm, vaddr, pte, pteval); else pte_clear(&init_mm, vaddr, pte); @@ -97,22 +99,6 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) unsigned long __FIXADDR_TOP = 0xfffff000; EXPORT_SYMBOL(__FIXADDR_TOP); -/** - * reserve_top_address - reserves a hole in the top of kernel address space - * @reserve - size of hole to reserve - * - * Can be used to relocate the fixmap area and poke a hole in the top - * of kernel address space to make room for a hypervisor. - */ -void __init reserve_top_address(unsigned long reserve) -{ - BUG_ON(fixmaps_set > 0); - printk(KERN_INFO "Reserving virtual address space above 0x%08x\n", - (int)-reserve); - __FIXADDR_TOP = -reserve - PAGE_SIZE; - __VMALLOC_RESERVE += reserve; -} - /* * vmalloc=size forces the vmalloc area to be exactly 'size' * bytes. This can be used to increase (or decrease) the diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 574c8bc..c7d272b 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -116,6 +116,36 @@ void __init acpi_numa_slit_init(struct acpi_table_slit *slit) reserve_early(phys, phys + length, "ACPI SLIT"); } +/* Callback for Proximity Domain -> x2APIC mapping */ +void __init +acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) +{ + int pxm, node; + int apic_id; + + if (srat_disabled()) + return; + if (pa->header.length < sizeof(struct acpi_srat_x2apic_cpu_affinity)) { + bad_srat(); + return; + } + if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0) + return; + pxm = pa->proximity_domain; + node = setup_node(pxm); + if (node < 0) { + printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm); + bad_srat(); + return; + } + + apic_id = pa->apic_id; + apicid_to_node[apic_id] = node; + acpi_numa = 1; + printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n", + pxm, apic_id, node); +} + /* Callback for Proximity Domain -> LAPIC mapping */ void __init acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index a654d59..821e970 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -187,11 +187,6 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask, cpumask, cpumask_of(smp_processor_id())); /* - * Make the above memory operations globally visible before - * sending the IPI. - */ - smp_mb(); - /* * We have to send the IPI only to * CPUs affected. */ diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c index 4c4a51c..819b131 100644 --- a/arch/x86/oprofile/op_model_p4.c +++ b/arch/x86/oprofile/op_model_p4.c @@ -380,7 +380,7 @@ static unsigned int get_stagger(void) { #ifdef CONFIG_SMP int cpu = smp_processor_id(); - return (cpu != first_cpu(per_cpu(cpu_sibling_map, cpu))); + return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map)); #endif return 0; } diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 82d22fc..8c362b9 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -90,7 +90,7 @@ static int __devinit can_skip_ioresource_align(const struct dmi_system_id *d) return 0; } -static struct dmi_system_id can_skip_pciprobe_dmi_table[] __devinitdata = { +static const struct dmi_system_id can_skip_pciprobe_dmi_table[] __devinitconst = { /* * Systems where PCI IO resource ISA alignment can be skipped * when the ISA enable bit in the bridge control is not set @@ -183,7 +183,7 @@ static int __devinit assign_all_busses(const struct dmi_system_id *d) } #endif -static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = { +static const struct dmi_system_id __devinitconst pciprobe_dmi_table[] = { #ifdef __i386__ /* * Laptops which need pci=assign-busses to see Cardbus cards diff --git a/arch/x86/pci/early.c b/arch/x86/pci/early.c index f6adf2c..aaf26ae 100644 --- a/arch/x86/pci/early.c +++ b/arch/x86/pci/early.c @@ -69,11 +69,12 @@ void early_dump_pci_device(u8 bus, u8 slot, u8 func) int j; u32 val; - printk(KERN_INFO "PCI: %02x:%02x:%02x", bus, slot, func); + printk(KERN_INFO "pci 0000:%02x:%02x.%d config space:", + bus, slot, func); for (i = 0; i < 256; i += 4) { if (!(i & 0x0f)) - printk("\n%04x:",i); + printk("\n %02x:",i); val = read_pci_config(bus, slot, func, i); for (j = 0; j < 4; j++) { @@ -96,20 +97,22 @@ void early_dump_pci_devices(void) for (func = 0; func < 8; func++) { u32 class; u8 type; + class = read_pci_config(bus, slot, func, PCI_CLASS_REVISION); if (class == 0xffffffff) - break; + continue; early_dump_pci_device(bus, slot, func); - /* No multi-function device? */ - type = read_pci_config_byte(bus, slot, func, + if (func == 0) { + type = read_pci_config_byte(bus, slot, + func, PCI_HEADER_TYPE); - if (!(type & 0x80)) - break; + if (!(type & 0x80)) + break; + } } } } } - diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 7d388d5..6dd8955 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -356,7 +356,7 @@ static void __devinit pci_fixup_video(struct pci_dev *pdev) DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, pci_fixup_video); -static struct dmi_system_id __devinitdata msi_k8t_dmi_table[] = { +static const struct dmi_system_id __devinitconst msi_k8t_dmi_table[] = { { .ident = "MSI-K8T-Neo2Fir", .matches = { @@ -413,7 +413,7 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237, */ static u16 toshiba_line_size; -static struct dmi_system_id __devinitdata toshiba_ohci1394_dmi_table[] = { +static const struct dmi_system_id __devinitconst toshiba_ohci1394_dmi_table[] = { { .ident = "Toshiba PS5 based laptop", .matches = { @@ -495,26 +495,6 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SIEMENS, 0x0015, pci_siemens_interrupt_controller); /* - * Regular PCI devices have 256 bytes, but AMD Family 10h/11h CPUs have - * 4096 bytes configuration space for each function of their processor - * configuration space. - */ -static void amd_cpu_pci_cfg_space_size(struct pci_dev *dev) -{ - dev->cfg_size = pci_cfg_space_size_ext(dev); -} -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1200, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1201, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1202, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1203, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1204, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1300, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1301, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1302, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1303, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1304, amd_cpu_pci_cfg_space_size); - -/* * SB600: Disable BAR1 on device 14.0 to avoid HPET resources from * confusing the PCI engine: */ diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 5ead808..f1817f7 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -258,24 +258,7 @@ void pcibios_set_master(struct pci_dev *dev) pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat); } -static void pci_unmap_page_range(struct vm_area_struct *vma) -{ - u64 addr = (u64)vma->vm_pgoff << PAGE_SHIFT; - free_memtype(addr, addr + vma->vm_end - vma->vm_start); -} - -static void pci_track_mmap_page_range(struct vm_area_struct *vma) -{ - u64 addr = (u64)vma->vm_pgoff << PAGE_SHIFT; - unsigned long flags = pgprot_val(vma->vm_page_prot) - & _PAGE_CACHE_MASK; - - reserve_memtype(addr, addr + vma->vm_end - vma->vm_start, flags, NULL); -} - static struct vm_operations_struct pci_mmap_ops = { - .open = pci_track_mmap_page_range, - .close = pci_unmap_page_range, .access = generic_access_phys, }; @@ -283,11 +266,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, enum pci_mmap_state mmap_state, int write_combine) { unsigned long prot; - u64 addr = vma->vm_pgoff << PAGE_SHIFT; - unsigned long len = vma->vm_end - vma->vm_start; - unsigned long flags; - unsigned long new_flags; - int retval; /* I/O space cannot be accessed via normal processor loads and * stores on this platform. @@ -308,27 +286,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, vma->vm_page_prot = __pgprot(prot); - flags = pgprot_val(vma->vm_page_prot) & _PAGE_CACHE_MASK; - retval = reserve_memtype(addr, addr + len, flags, &new_flags); - if (retval) - return retval; - - if (flags != new_flags) { - if (!is_new_memtype_allowed(flags, new_flags)) { - free_memtype(addr, addr+len); - return -EINVAL; - } - flags = new_flags; - } - - if (((vma->vm_pgoff < max_low_pfn_mapped) || - (vma->vm_pgoff >= (1UL<<(32 - PAGE_SHIFT)) && - vma->vm_pgoff < max_pfn_mapped)) && - ioremap_change_attr((unsigned long)__va(addr), len, flags)) { - free_memtype(addr, addr + len); - return -EINVAL; - } - if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, vma->vm_end - vma->vm_start, vma->vm_page_prot)) diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c index f1065b1..4061bb0 100644 --- a/arch/x86/pci/legacy.c +++ b/arch/x86/pci/legacy.c @@ -50,8 +50,6 @@ static int __init pci_legacy_init(void) if (pci_root_bus) pci_bus_add_devices(pci_root_bus); - pcibios_fixup_peer_bridges(); - return 0; } @@ -67,6 +65,7 @@ int __init pci_subsys_init(void) pci_visws_init(); #endif pci_legacy_init(); + pcibios_fixup_peer_bridges(); pcibios_irq_init(); pcibios_init(); diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 89bf924..905bb52 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -14,6 +14,7 @@ #include <linux/init.h> #include <linux/acpi.h> #include <linux/bitmap.h> +#include <linux/sort.h> #include <asm/e820.h> #include <asm/pci_x86.h> @@ -24,24 +25,49 @@ /* Indicate if the mmcfg resources have been placed into the resource table. */ static int __initdata pci_mmcfg_resources_inserted; +static __init int extend_mmcfg(int num) +{ + struct acpi_mcfg_allocation *new; + int new_num = pci_mmcfg_config_num + num; + + new = kzalloc(sizeof(pci_mmcfg_config[0]) * new_num, GFP_KERNEL); + if (!new) + return -1; + + if (pci_mmcfg_config) { + memcpy(new, pci_mmcfg_config, + sizeof(pci_mmcfg_config[0]) * new_num); + kfree(pci_mmcfg_config); + } + pci_mmcfg_config = new; + + return 0; +} + +static __init void fill_one_mmcfg(u64 addr, int segment, int start, int end) +{ + int i = pci_mmcfg_config_num; + + pci_mmcfg_config_num++; + pci_mmcfg_config[i].address = addr; + pci_mmcfg_config[i].pci_segment = segment; + pci_mmcfg_config[i].start_bus_number = start; + pci_mmcfg_config[i].end_bus_number = end; +} + static const char __init *pci_mmcfg_e7520(void) { u32 win; raw_pci_ops->read(0, 0, PCI_DEVFN(0, 0), 0xce, 2, &win); win = win & 0xf000; - if(win == 0x0000 || win == 0xf000) - pci_mmcfg_config_num = 0; - else { - pci_mmcfg_config_num = 1; - pci_mmcfg_config = kzalloc(sizeof(pci_mmcfg_config[0]), GFP_KERNEL); - if (!pci_mmcfg_config) - return NULL; - pci_mmcfg_config[0].address = win << 16; - pci_mmcfg_config[0].pci_segment = 0; - pci_mmcfg_config[0].start_bus_number = 0; - pci_mmcfg_config[0].end_bus_number = 255; - } + if (win == 0x0000 || win == 0xf000) + return NULL; + + if (extend_mmcfg(1) == -1) + return NULL; + + fill_one_mmcfg(win << 16, 0, 0, 255); return "Intel Corporation E7520 Memory Controller Hub"; } @@ -50,13 +76,11 @@ static const char __init *pci_mmcfg_intel_945(void) { u32 pciexbar, mask = 0, len = 0; - pci_mmcfg_config_num = 1; - raw_pci_ops->read(0, 0, PCI_DEVFN(0, 0), 0x48, 4, &pciexbar); /* Enable bit */ if (!(pciexbar & 1)) - pci_mmcfg_config_num = 0; + return NULL; /* Size bits */ switch ((pciexbar >> 1) & 3) { @@ -73,28 +97,23 @@ static const char __init *pci_mmcfg_intel_945(void) len = 0x04000000U; break; default: - pci_mmcfg_config_num = 0; + return NULL; } /* Errata #2, things break when not aligned on a 256Mb boundary */ /* Can only happen in 64M/128M mode */ if ((pciexbar & mask) & 0x0fffffffU) - pci_mmcfg_config_num = 0; + return NULL; /* Don't hit the APIC registers and their friends */ if ((pciexbar & mask) >= 0xf0000000U) - pci_mmcfg_config_num = 0; - - if (pci_mmcfg_config_num) { - pci_mmcfg_config = kzalloc(sizeof(pci_mmcfg_config[0]), GFP_KERNEL); - if (!pci_mmcfg_config) - return NULL; - pci_mmcfg_config[0].address = pciexbar & mask; - pci_mmcfg_config[0].pci_segment = 0; - pci_mmcfg_config[0].start_bus_number = 0; - pci_mmcfg_config[0].end_bus_number = (len >> 20) - 1; - } + return NULL; + + if (extend_mmcfg(1) == -1) + return NULL; + + fill_one_mmcfg(pciexbar & mask, 0, 0, (len >> 20) - 1); return "Intel Corporation 945G/GZ/P/PL Express Memory Controller Hub"; } @@ -138,22 +157,77 @@ static const char __init *pci_mmcfg_amd_fam10h(void) busnbits = 8; } - pci_mmcfg_config_num = (1 << segnbits); - pci_mmcfg_config = kzalloc(sizeof(pci_mmcfg_config[0]) * - pci_mmcfg_config_num, GFP_KERNEL); - if (!pci_mmcfg_config) + if (extend_mmcfg(1 << segnbits) == -1) return NULL; - for (i = 0; i < (1 << segnbits); i++) { - pci_mmcfg_config[i].address = base + (1<<28) * i; - pci_mmcfg_config[i].pci_segment = i; - pci_mmcfg_config[i].start_bus_number = 0; - pci_mmcfg_config[i].end_bus_number = (1 << busnbits) - 1; - } + for (i = 0; i < (1 << segnbits); i++) + fill_one_mmcfg(base + (1<<28) * i, i, 0, (1 << busnbits) - 1); return "AMD Family 10h NB"; } +static bool __initdata mcp55_checked; +static const char __init *pci_mmcfg_nvidia_mcp55(void) +{ + int bus; + int mcp55_mmconf_found = 0; + + static const u32 extcfg_regnum = 0x90; + static const u32 extcfg_regsize = 4; + static const u32 extcfg_enable_mask = 1<<31; + static const u32 extcfg_start_mask = 0xff<<16; + static const int extcfg_start_shift = 16; + static const u32 extcfg_size_mask = 0x3<<28; + static const int extcfg_size_shift = 28; + static const int extcfg_sizebus[] = {0x100, 0x80, 0x40, 0x20}; + static const u32 extcfg_base_mask[] = {0x7ff8, 0x7ffc, 0x7ffe, 0x7fff}; + static const int extcfg_base_lshift = 25; + + /* + * do check if amd fam10h already took over + */ + if (!acpi_disabled || pci_mmcfg_config_num || mcp55_checked) + return NULL; + + mcp55_checked = true; + for (bus = 0; bus < 256; bus++) { + u64 base; + u32 l, extcfg; + u16 vendor, device; + int start, size_index, end; + + raw_pci_ops->read(0, bus, PCI_DEVFN(0, 0), 0, 4, &l); + vendor = l & 0xffff; + device = (l >> 16) & 0xffff; + + if (PCI_VENDOR_ID_NVIDIA != vendor || 0x0369 != device) + continue; + + raw_pci_ops->read(0, bus, PCI_DEVFN(0, 0), extcfg_regnum, + extcfg_regsize, &extcfg); + + if (!(extcfg & extcfg_enable_mask)) + continue; + + if (extend_mmcfg(1) == -1) + continue; + + size_index = (extcfg & extcfg_size_mask) >> extcfg_size_shift; + base = extcfg & extcfg_base_mask[size_index]; + /* base could > 4G */ + base <<= extcfg_base_lshift; + start = (extcfg & extcfg_start_mask) >> extcfg_start_shift; + end = start + extcfg_sizebus[size_index] - 1; + fill_one_mmcfg(base, 0, start, end); + mcp55_mmconf_found++; + } + + if (!mcp55_mmconf_found) + return NULL; + + return "nVidia MCP55"; +} + struct pci_mmcfg_hostbridge_probe { u32 bus; u32 devfn; @@ -171,8 +245,52 @@ static struct pci_mmcfg_hostbridge_probe pci_mmcfg_probes[] __initdata = { 0x1200, pci_mmcfg_amd_fam10h }, { 0xff, PCI_DEVFN(0, 0), PCI_VENDOR_ID_AMD, 0x1200, pci_mmcfg_amd_fam10h }, + { 0, PCI_DEVFN(0, 0), PCI_VENDOR_ID_NVIDIA, + 0x0369, pci_mmcfg_nvidia_mcp55 }, }; +static int __init cmp_mmcfg(const void *x1, const void *x2) +{ + const typeof(pci_mmcfg_config[0]) *m1 = x1; + const typeof(pci_mmcfg_config[0]) *m2 = x2; + int start1, start2; + + start1 = m1->start_bus_number; + start2 = m2->start_bus_number; + + return start1 - start2; +} + +static void __init pci_mmcfg_check_end_bus_number(void) +{ + int i; + typeof(pci_mmcfg_config[0]) *cfg, *cfgx; + + /* sort them at first */ + sort(pci_mmcfg_config, pci_mmcfg_config_num, + sizeof(pci_mmcfg_config[0]), cmp_mmcfg, NULL); + + /* last one*/ + if (pci_mmcfg_config_num > 0) { + i = pci_mmcfg_config_num - 1; + cfg = &pci_mmcfg_config[i]; + if (cfg->end_bus_number < cfg->start_bus_number) + cfg->end_bus_number = 255; + } + + /* don't overlap please */ + for (i = 0; i < pci_mmcfg_config_num - 1; i++) { + cfg = &pci_mmcfg_config[i]; + cfgx = &pci_mmcfg_config[i+1]; + + if (cfg->end_bus_number < cfg->start_bus_number) + cfg->end_bus_number = 255; + + if (cfg->end_bus_number >= cfgx->start_bus_number) + cfg->end_bus_number = cfgx->start_bus_number - 1; + } +} + static int __init pci_mmcfg_check_hostbridge(void) { u32 l; @@ -186,31 +304,33 @@ static int __init pci_mmcfg_check_hostbridge(void) pci_mmcfg_config_num = 0; pci_mmcfg_config = NULL; - name = NULL; - for (i = 0; !name && i < ARRAY_SIZE(pci_mmcfg_probes); i++) { + for (i = 0; i < ARRAY_SIZE(pci_mmcfg_probes); i++) { bus = pci_mmcfg_probes[i].bus; devfn = pci_mmcfg_probes[i].devfn; raw_pci_ops->read(0, bus, devfn, 0, 4, &l); vendor = l & 0xffff; device = (l >> 16) & 0xffff; + name = NULL; if (pci_mmcfg_probes[i].vendor == vendor && pci_mmcfg_probes[i].device == device) name = pci_mmcfg_probes[i].probe(); - } - if (name) { - printk(KERN_INFO "PCI: Found %s %s MMCONFIG support.\n", - name, pci_mmcfg_config_num ? "with" : "without"); + if (name) + printk(KERN_INFO "PCI: Found %s with MMCONFIG support.\n", + name); } - return name != NULL; + /* some end_bus_number is crazy, fix it */ + pci_mmcfg_check_end_bus_number(); + + return pci_mmcfg_config_num != 0; } static void __init pci_mmcfg_insert_resources(void) { -#define PCI_MMCFG_RESOURCE_NAME_LEN 19 +#define PCI_MMCFG_RESOURCE_NAME_LEN 24 int i; struct resource *res; char *names; @@ -228,9 +348,10 @@ static void __init pci_mmcfg_insert_resources(void) struct acpi_mcfg_allocation *cfg = &pci_mmcfg_config[i]; num_buses = cfg->end_bus_number - cfg->start_bus_number + 1; res->name = names; - snprintf(names, PCI_MMCFG_RESOURCE_NAME_LEN, "PCI MMCONFIG %u", - cfg->pci_segment); - res->start = cfg->address; + snprintf(names, PCI_MMCFG_RESOURCE_NAME_LEN, + "PCI MMCONFIG %u [%02x-%02x]", cfg->pci_segment, + cfg->start_bus_number, cfg->end_bus_number); + res->start = cfg->address + (cfg->start_bus_number << 20); res->end = res->start + (num_buses << 20) - 1; res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; insert_resource(&iomem_resource, res); @@ -354,8 +475,6 @@ static void __init pci_mmcfg_reject_broken(int early) (pci_mmcfg_config[0].address == 0)) return; - cfg = &pci_mmcfg_config[0]; - for (i = 0; i < pci_mmcfg_config_num; i++) { int valid = 0; u64 addr, size; @@ -423,10 +542,10 @@ static void __init __pci_mmcfg_init(int early) known_bridge = 1; } - if (!known_bridge) { + if (!known_bridge) acpi_table_parse(ACPI_SIG_MCFG, acpi_parse_mcfg); - pci_mmcfg_reject_broken(early); - } + + pci_mmcfg_reject_broken(early); if ((pci_mmcfg_config_num == 0) || (pci_mmcfg_config == NULL) || diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c index 30007ff..94349f8 100644 --- a/arch/x86/pci/mmconfig_64.c +++ b/arch/x86/pci/mmconfig_64.c @@ -112,13 +112,18 @@ static struct pci_raw_ops pci_mmcfg = { static void __iomem * __init mcfg_ioremap(struct acpi_mcfg_allocation *cfg) { void __iomem *addr; - u32 size; - - size = (cfg->end_bus_number + 1) << 20; - addr = ioremap_nocache(cfg->address, size); + u64 start, size; + + start = cfg->start_bus_number; + start <<= 20; + start += cfg->address; + size = cfg->end_bus_number + 1 - cfg->start_bus_number; + size <<= 20; + addr = ioremap_nocache(start, size); if (addr) { printk(KERN_INFO "PCI: Using MMCONFIG at %Lx - %Lx\n", - cfg->address, cfg->address + size - 1); + start, start + size - 1); + addr -= cfg->start_bus_number << 20; } return addr; } @@ -157,7 +162,7 @@ void __init pci_mmcfg_arch_free(void) for (i = 0; i < pci_mmcfg_config_num; ++i) { if (pci_mmcfg_virt[i].virt) { - iounmap(pci_mmcfg_virt[i].virt); + iounmap(pci_mmcfg_virt[i].virt + (pci_mmcfg_virt[i].cfg->start_bus_number << 20)); pci_mmcfg_virt[i].virt = NULL; pci_mmcfg_virt[i].cfg = NULL; } diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile index 9ff4d5b..58b32db 100644 --- a/arch/x86/power/Makefile +++ b/arch/x86/power/Makefile @@ -1,2 +1,7 @@ +# __restore_processor_state() restores %gs after S3 resume and so should not +# itself be stack-protected +nostackp := $(call cc-option, -fno-stack-protector) +CFLAGS_cpu_$(BITS).o := $(nostackp) + obj-$(CONFIG_PM_SLEEP) += cpu_$(BITS).o obj-$(CONFIG_HIBERNATION) += hibernate_$(BITS).o hibernate_asm_$(BITS).o diff --git a/arch/x86/power/cpu_32.c b/arch/x86/power/cpu_32.c index 274d060..ce702c5 100644 --- a/arch/x86/power/cpu_32.c +++ b/arch/x86/power/cpu_32.c @@ -12,6 +12,7 @@ #include <asm/mtrr.h> #include <asm/mce.h> #include <asm/xcr.h> +#include <asm/suspend.h> static struct saved_context saved_context; diff --git a/arch/x86/power/cpu_64.c b/arch/x86/power/cpu_64.c index e3b6cf7..5343540 100644 --- a/arch/x86/power/cpu_64.c +++ b/arch/x86/power/cpu_64.c @@ -15,6 +15,7 @@ #include <asm/pgtable.h> #include <asm/mtrr.h> #include <asm/xcr.h> +#include <asm/suspend.h> static void fix_processor_context(void); diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 6dd000d..65fdc86 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -14,6 +14,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/mtrr.h> +#include <asm/suspend.h> /* References to section boundaries */ extern const void __nosave_begin, __nosave_end; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c52f403..82cd39a 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -103,7 +103,7 @@ static void xen_vcpu_setup(int cpu) vcpup = &per_cpu(xen_vcpu_info, cpu); - info.mfn = virt_to_mfn(vcpup); + info.mfn = arbitrary_virt_to_mfn(vcpup); info.offset = offset_in_page(vcpup); printk(KERN_DEBUG "trying to map vcpu_info %d at %p, mfn %llx, offset %d\n", @@ -301,8 +301,10 @@ static void xen_load_gdt(const struct desc_ptr *dtr) frames = mcs.args; for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) { - frames[f] = virt_to_mfn(va); + frames[f] = arbitrary_virt_to_mfn((void *)va); + make_lowmem_page_readonly((void *)va); + make_lowmem_page_readonly(mfn_to_virt(frames[f])); } MULTI_set_gdt(mcs.mc, frames, size / sizeof(struct desc_struct)); @@ -314,7 +316,7 @@ static void load_TLS_descriptor(struct thread_struct *t, unsigned int cpu, unsigned int i) { struct desc_struct *gdt = get_cpu_gdt_table(cpu); - xmaddr_t maddr = virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]); + xmaddr_t maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]); struct multicall_space mc = __xen_mc_entry(0); MULTI_update_descriptor(mc.mc, maddr.maddr, t->tls_array[i]); @@ -488,7 +490,7 @@ static void xen_write_gdt_entry(struct desc_struct *dt, int entry, break; default: { - xmaddr_t maddr = virt_to_machine(&dt[entry]); + xmaddr_t maddr = arbitrary_virt_to_machine(&dt[entry]); xen_mc_flush(); if (HYPERVISOR_update_descriptor(maddr.maddr, *(u64 *)desc)) diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 319bd40..db3802f 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -276,6 +276,13 @@ void set_phys_to_machine(unsigned long pfn, unsigned long mfn) p2m_top[topidx][idx] = mfn; } +unsigned long arbitrary_virt_to_mfn(void *vaddr) +{ + xmaddr_t maddr = arbitrary_virt_to_machine(vaddr); + + return PFN_DOWN(maddr.maddr); +} + xmaddr_t arbitrary_virt_to_machine(void *vaddr) { unsigned long address = (unsigned long)vaddr; @@ -1716,9 +1723,9 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, { pmd_t *kernel_pmd; - init_pg_tables_start = __pa(pgd); - init_pg_tables_end = __pa(pgd) + xen_start_info->nr_pt_frames*PAGE_SIZE; - max_pfn_mapped = PFN_DOWN(init_pg_tables_end + 512*1024); + max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) + + xen_start_info->nr_pt_frames * PAGE_SIZE + + 512*1024); kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD); @@ -1863,7 +1870,6 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = { #ifdef CONFIG_X86_PAE .set_pte_atomic = xen_set_pte_atomic, - .set_pte_present = xen_set_pte_at, .pte_clear = xen_pte_clear, .pmd_clear = xen_pmd_clear, #endif /* CONFIG_X86_PAE */ diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 035582a..585a6e3 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -158,7 +158,7 @@ static void __init xen_fill_possible_map(void) rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL); if (rc >= 0) { num_processors++; - cpu_set(i, cpu_possible_map); + set_cpu_possible(i, true); } } } @@ -197,7 +197,7 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus) while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) { for (cpu = nr_cpu_ids - 1; !cpu_possible(cpu); cpu--) continue; - cpu_clear(cpu, cpu_possible_map); + set_cpu_possible(cpu, false); } for_each_possible_cpu (cpu) { @@ -210,7 +210,7 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus) if (IS_ERR(idle)) panic("failed fork for CPU %d", cpu); - cpu_set(cpu, cpu_present_map); + set_cpu_present(cpu, true); } } @@ -219,6 +219,7 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) { struct vcpu_guest_context *ctxt; struct desc_struct *gdt; + unsigned long gdt_mfn; if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map)) return 0; @@ -248,9 +249,12 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) ctxt->ldt_ents = 0; BUG_ON((unsigned long)gdt & ~PAGE_MASK); + + gdt_mfn = arbitrary_virt_to_mfn(gdt); make_lowmem_page_readonly(gdt); + make_lowmem_page_readonly(mfn_to_virt(gdt_mfn)); - ctxt->gdt_frames[0] = virt_to_mfn(gdt); + ctxt->gdt_frames[0] = gdt_mfn; ctxt->gdt_ents = GDT_ENTRIES; ctxt->user_regs.cs = __KERNEL_CS; |