diff options
Diffstat (limited to 'arch/x86')
141 files changed, 3617 insertions, 3696 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 55298e89157..0896008f750 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -45,10 +45,12 @@ config X86 select HAVE_GENERIC_DMA_COHERENT if X86_32 select HAVE_EFFICIENT_UNALIGNED_ACCESS select USER_STACKTRACE_SUPPORT + select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_DMA_API_DEBUG select HAVE_KERNEL_GZIP select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_LZMA + select HAVE_KERNEL_LZO select HAVE_HW_BREAKPOINT select PERF_EVENTS select ANON_INODES @@ -988,12 +990,6 @@ 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 @@ -1246,6 +1242,11 @@ config ARCH_MEMORY_PROBE def_bool X86_64 depends on MEMORY_HOTPLUG +config ILLEGAL_POINTER_VALUE + hex + default 0 if X86_32 + default 0xdead000000000000 if X86_64 + source "mm/Kconfig" config HIGHPTE diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 9d38a13b4ce..a19829374e6 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -396,7 +396,7 @@ config X86_TSC config X86_CMPXCHG64 def_bool y - depends on !M386 && !M486 + depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM # this should be set for all -march=.. options where the compiler # generates cmov. diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 78b32be55e9..0a43dc515e4 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -135,9 +135,7 @@ drivers-$(CONFIG_OPROFILE) += arch/x86/oprofile/ # suspend and hibernation support drivers-$(CONFIG_PM) += arch/x86/power/ -ifeq ($(CONFIG_X86_32),y) drivers-$(CONFIG_FB) += arch/x86/video/ -endif #### # boot loader support. Several targets are kept for legacy purposes diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index f8ed0658404..fbb47daf245 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -4,11 +4,12 @@ # create a compressed vmlinux image from the original vmlinux # -targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma head_$(BITS).o misc.o piggy.o +targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.lzo head_$(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_32) := -march=i386 cflags-$(CONFIG_X86_64) := -mcmodel=small KBUILD_CFLAGS += $(cflags-y) KBUILD_CFLAGS += $(call cc-option,-ffreestanding) @@ -48,10 +49,13 @@ $(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE $(call if_changed,bzip2) $(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE $(call if_changed,lzma) +$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE + $(call if_changed,lzo) suffix-$(CONFIG_KERNEL_GZIP) := gz suffix-$(CONFIG_KERNEL_BZIP2) := bz2 suffix-$(CONFIG_KERNEL_LZMA) := lzma +suffix-$(CONFIG_KERNEL_LZO) := lzo quiet_cmd_mkpiggy = MKPIGGY $@ cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false ) diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 842b2a36174..88042e812d3 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -19,11 +19,6 @@ #define _ASM_X86_DESC_H 1 #endif -#ifdef CONFIG_X86_64 -#define _LINUX_STRING_H_ 1 -#define __LINUX_BITMAP_H 1 -#endif - #include <linux/linkage.h> #include <linux/screen_info.h> #include <linux/elf.h> @@ -131,8 +126,8 @@ static void error(char *m); static struct boot_params *real_mode; /* Pointer to real-mode data */ static int quiet; -static void *memset(void *s, int c, unsigned n); -void *memcpy(void *dest, const void *src, unsigned n); +void *memset(void *s, int c, size_t n); +void *memcpy(void *dest, const void *src, size_t n); static void __putstr(int, const char *); #define putstr(__x) __putstr(0, __x) @@ -162,6 +157,10 @@ static int lines, cols; #include "../../../../lib/decompress_unlzma.c" #endif +#ifdef CONFIG_KERNEL_LZO +#include "../../../../lib/decompress_unlzo.c" +#endif + static void scroll(void) { int i; @@ -219,7 +218,7 @@ static void __putstr(int error, const char *s) outb(0xff & (pos >> 1), vidport+1); } -static void *memset(void *s, int c, unsigned n) +void *memset(void *s, int c, size_t n) { int i; char *ss = s; @@ -229,7 +228,7 @@ static void *memset(void *s, int c, unsigned n) return s; } -void *memcpy(void *dest, const void *src, unsigned n) +void *memcpy(void *dest, const void *src, size_t n) { int i; const char *s = src; diff --git a/arch/x86/boot/mkcpustr.c b/arch/x86/boot/mkcpustr.c index 8ef60f20b37..919257f526f 100644 --- a/arch/x86/boot/mkcpustr.c +++ b/arch/x86/boot/mkcpustr.c @@ -22,7 +22,7 @@ int main(void) int i, j; const char *str; - printf("static const char x86_cap_strs[] = \n"); + printf("static const char x86_cap_strs[] =\n"); for (i = 0; i < NCAPINTS; i++) { for (j = 0; j < 32; j++) { diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 2a4d073d2cf..9046e4af66c 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -297,7 +297,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) * size limits imposed on them by creating programs with large * arrays in the data or bss. */ - rlim = current->signal->rlim[RLIMIT_DATA].rlim_cur; + rlim = rlimit(RLIMIT_DATA); if (rlim >= RLIM_INFINITY) rlim = ~0; if (ex.a_data + ex.a_bss > rlim) @@ -308,14 +308,15 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) if (retval) return retval; - regs->cs = __USER32_CS; - regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 = - regs->r13 = regs->r14 = regs->r15 = 0; - /* OK, This is the point of no return */ set_personality(PER_LINUX); set_thread_flag(TIF_IA32); - clear_thread_flag(TIF_ABI_PENDING); + + setup_new_exec(bprm); + + regs->cs = __USER32_CS; + regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 = + regs->r13 = regs->r14 = regs->r15 = 0; current->mm->end_code = ex.a_text + (current->mm->start_code = N_TXTADDR(ex)); diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 3b5b828767b..f1e253ceba4 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -65,12 +65,17 @@ extern void alternatives_smp_module_add(struct module *mod, char *name, void *text, void *text_end); extern void alternatives_smp_module_del(struct module *mod); extern void alternatives_smp_switch(int smp); +extern int alternatives_text_reserved(void *start, void *end); #else static inline void alternatives_smp_module_add(struct module *mod, char *name, void *locks, void *locks_end, void *text, void *text_end) {} static inline void alternatives_smp_module_del(struct module *mod) {} static inline void alternatives_smp_switch(int smp) {} +static inline int alternatives_text_reserved(void *start, void *end) +{ + return 0; +} #endif /* CONFIG_SMP */ /* alternative assembly primitive: */ diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h index 4d817f9e6e7..d2544f1d705 100644 --- a/arch/x86/include/asm/amd_iommu_proto.h +++ b/arch/x86/include/asm/amd_iommu_proto.h @@ -31,6 +31,7 @@ extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu); extern int amd_iommu_init_devices(void); extern void amd_iommu_uninit_devices(void); extern void amd_iommu_init_notifier(void); +extern void amd_iommu_init_api(void); #ifndef CONFIG_AMD_IOMMU_STATS static inline void amd_iommu_stats_init(void) { } diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 8baaa719fa7..8f8217b9bda 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -187,10 +187,10 @@ static inline int atomic_add_return(int i, atomic_t *v) #ifdef CONFIG_M386 no_xadd: /* Legacy 386 processor */ - local_irq_save(flags); + raw_local_irq_save(flags); __i = atomic_read(v); atomic_set(v, i + __i); - local_irq_restore(flags); + raw_local_irq_restore(flags); return i + __i; #endif } diff --git a/arch/x86/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h deleted file mode 100644 index d96c1ee3a95..00000000000 --- a/arch/x86/include/asm/cpu_debug.h +++ /dev/null @@ -1,127 +0,0 @@ -#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) - -#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 */ -}; - -#endif /* _ASM_X86_CPU_DEBUG_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 637e1ec963c..0cd82d06861 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -168,6 +168,10 @@ #define X86_FEATURE_FLEXPRIORITY (8*32+ 2) /* Intel FlexPriority */ #define X86_FEATURE_EPT (8*32+ 3) /* Intel Extended Page Table */ #define X86_FEATURE_VPID (8*32+ 4) /* Intel Virtual Processor ID */ +#define X86_FEATURE_NPT (8*32+5) /* AMD Nested Page Table support */ +#define X86_FEATURE_LBRV (8*32+6) /* AMD LBR Virtualization support */ +#define X86_FEATURE_SVML (8*32+7) /* "svm_lock" AMD SVM locking MSR */ +#define X86_FEATURE_NRIPS (8*32+8) /* "nrip_save" AMD SVM next_rip save */ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index 8240f76b531..b81002f2361 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -14,6 +14,9 @@ which debugging register was responsible for the trap. The other bits are either reserved or not of interest to us. */ +/* Define reserved bits in DR6 which are always set to 1 */ +#define DR6_RESERVED (0xFFFF0FF0) + #define DR_TRAP0 (0x1) /* db0 */ #define DR_TRAP1 (0x2) /* db1 */ #define DR_TRAP2 (0x4) /* db2 */ diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index b4501ee223a..f2ad2163109 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -170,10 +170,7 @@ static inline void elf_common_init(struct thread_struct *t, } #define ELF_PLAT_INIT(_r, load_addr) \ -do { \ - elf_common_init(¤t->thread, _r, 0); \ - clear_thread_flag(TIF_IA32); \ -} while (0) + elf_common_init(¤t->thread, _r, 0) #define COMPAT_ELF_PLAT_INIT(regs, load_addr) \ elf_common_init(¤t->thread, regs, __USER_DS) @@ -181,14 +178,8 @@ do { \ void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp); #define compat_start_thread start_thread_ia32 -#define COMPAT_SET_PERSONALITY(ex) \ -do { \ - if (test_thread_flag(TIF_IA32)) \ - clear_thread_flag(TIF_ABI_PENDING); \ - else \ - set_thread_flag(TIF_ABI_PENDING); \ - current->personality |= force_personality32; \ -} while (0) +void set_personality_ia32(void); +#define COMPAT_SET_PERSONALITY(ex) set_personality_ia32() #define COMPAT_ELF_PLATFORM ("i686") diff --git a/arch/x86/include/asm/fb.h b/arch/x86/include/asm/fb.h index 53018464aea..2519d0679d9 100644 --- a/arch/x86/include/asm/fb.h +++ b/arch/x86/include/asm/fb.h @@ -12,10 +12,6 @@ static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, pgprot_val(vma->vm_page_prot) |= _PAGE_PCD; } -#ifdef CONFIG_X86_32 extern int fb_is_primary_device(struct fb_info *info); -#else -static inline int fb_is_primary_device(struct fb_info *info) { return 0; } -#endif #endif /* _ASM_X86_FB_H */ diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index 5d89fd2a369..1d5c08a1bdf 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -67,6 +67,7 @@ extern unsigned long hpet_address; extern unsigned long force_hpet_address; extern u8 hpet_blockid; extern int hpet_force_user; +extern u8 hpet_msi_disable; extern int is_hpet_enabled(void); extern int hpet_enable(void); extern void hpet_disable(void); diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 73739322b6d..a1dcfa3ab17 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -1,8 +1,42 @@ #ifndef _ASM_X86_IO_H #define _ASM_X86_IO_H +/* + * This file contains the definitions for the x86 IO instructions + * inb/inw/inl/outb/outw/outl and the "string versions" of the same + * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing" + * versions of the single-IO instructions (inb_p/inw_p/..). + * + * This file is not meant to be obfuscating: it's just complicated + * to (a) handle it all in a way that makes gcc able to optimize it + * as well as possible and (b) trying to avoid writing the same thing + * over and over again with slight variations and possibly making a + * mistake somewhere. + */ + +/* + * Thanks to James van Artsdalen for a better timing-fix than + * the two short jumps: using outb's to a nonexistent port seems + * to guarantee better timings even on fast machines. + * + * On the other hand, I'd like to be sure of a non-existent port: + * I feel a bit unsafe about using 0x80 (should be safe, though) + * + * Linus + */ + + /* + * Bit simplified and optimized by Jan Hubicka + * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999. + * + * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added, + * isa_read[wl] and isa_write[wl] fixed + * - Arnaldo Carvalho de Melo <acme@conectiva.com.br> + */ + #define ARCH_HAS_IOREMAP_WC +#include <linux/string.h> #include <linux/compiler.h> #include <asm-generic/int-ll64.h> #include <asm/page.h> @@ -173,11 +207,126 @@ static inline void __iomem *ioremap(resource_size_t offset, unsigned long size) extern void iounmap(volatile void __iomem *addr); -#ifdef CONFIG_X86_32 -# include "io_32.h" +#ifdef __KERNEL__ + +#include <asm-generic/iomap.h> + +#include <linux/vmalloc.h> + +/* + * Convert a virtual cached pointer to an uncached pointer + */ +#define xlate_dev_kmem_ptr(p) p + +static inline void +memset_io(volatile void __iomem *addr, unsigned char val, size_t count) +{ + memset((void __force *)addr, val, count); +} + +static inline void +memcpy_fromio(void *dst, const volatile void __iomem *src, size_t count) +{ + memcpy(dst, (const void __force *)src, count); +} + +static inline void +memcpy_toio(volatile void __iomem *dst, const void *src, size_t count) +{ + memcpy((void __force *)dst, src, count); +} + +/* + * ISA space is 'always mapped' on a typical x86 system, no need to + * explicitly ioremap() it. The fact that the ISA IO space is mapped + * to PAGE_OFFSET is pure coincidence - it does not mean ISA values + * are physical addresses. The following constant pointer can be + * used as the IO-area pointer (it can be iounmapped as well, so the + * analogy with PCI is quite large): + */ +#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET)) + +/* + * Cache management + * + * This needed for two cases + * 1. Out of order aware processors + * 2. Accidentally out of order processors (PPro errata #51) + */ + +static inline void flush_write_buffers(void) +{ +#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE) + asm volatile("lock; addl $0,0(%%esp)": : :"memory"); +#endif +} + +#endif /* __KERNEL__ */ + +extern void native_io_delay(void); + +extern int io_delay_type; +extern void io_delay_init(void); + +#if defined(CONFIG_PARAVIRT) +#include <asm/paravirt.h> #else -# include "io_64.h" + +static inline void slow_down_io(void) +{ + native_io_delay(); +#ifdef REALLY_SLOW_IO + native_io_delay(); + native_io_delay(); + native_io_delay(); #endif +} + +#endif + +#define BUILDIO(bwl, bw, type) \ +static inline void out##bwl(unsigned type value, int port) \ +{ \ + asm volatile("out" #bwl " %" #bw "0, %w1" \ + : : "a"(value), "Nd"(port)); \ +} \ + \ +static inline unsigned type in##bwl(int port) \ +{ \ + unsigned type value; \ + asm volatile("in" #bwl " %w1, %" #bw "0" \ + : "=a"(value) : "Nd"(port)); \ + return value; \ +} \ + \ +static inline void out##bwl##_p(unsigned type value, int port) \ +{ \ + out##bwl(value, port); \ + slow_down_io(); \ +} \ + \ +static inline unsigned type in##bwl##_p(int port) \ +{ \ + unsigned type value = in##bwl(port); \ + slow_down_io(); \ + return value; \ +} \ + \ +static inline void outs##bwl(int port, const void *addr, unsigned long count) \ +{ \ + asm volatile("rep; outs" #bwl \ + : "+S"(addr), "+c"(count) : "d"(port)); \ +} \ + \ +static inline void ins##bwl(int port, void *addr, unsigned long count) \ +{ \ + asm volatile("rep; ins" #bwl \ + : "+D"(addr), "+c"(count) : "d"(port)); \ +} + +BUILDIO(b, b, char) +BUILDIO(w, w, short) +BUILDIO(l, , int) extern void *xlate_dev_mem_ptr(unsigned long phys); extern void unxlate_dev_mem_ptr(unsigned long phys, void *addr); diff --git a/arch/x86/include/asm/io_32.h b/arch/x86/include/asm/io_32.h deleted file mode 100644 index a299900f592..00000000000 --- a/arch/x86/include/asm/io_32.h +++ /dev/null @@ -1,196 +0,0 @@ -#ifndef _ASM_X86_IO_32_H -#define _ASM_X86_IO_32_H - -#include <linux/string.h> -#include <linux/compiler.h> - -/* - * This file contains the definitions for the x86 IO instructions - * inb/inw/inl/outb/outw/outl and the "string versions" of the same - * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing" - * versions of the single-IO instructions (inb_p/inw_p/..). - * - * This file is not meant to be obfuscating: it's just complicated - * to (a) handle it all in a way that makes gcc able to optimize it - * as well as possible and (b) trying to avoid writing the same thing - * over and over again with slight variations and possibly making a - * mistake somewhere. - */ - -/* - * Thanks to James van Artsdalen for a better timing-fix than - * the two short jumps: using outb's to a nonexistent port seems - * to guarantee better timings even on fast machines. - * - * On the other hand, I'd like to be sure of a non-existent port: - * I feel a bit unsafe about using 0x80 (should be safe, though) - * - * Linus - */ - - /* - * Bit simplified and optimized by Jan Hubicka - * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999. - * - * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added, - * isa_read[wl] and isa_write[wl] fixed - * - Arnaldo Carvalho de Melo <acme@conectiva.com.br> - */ - -#define XQUAD_PORTIO_BASE 0xfe400000 -#define XQUAD_PORTIO_QUAD 0x40000 /* 256k per quad. */ - -#ifdef __KERNEL__ - -#include <asm-generic/iomap.h> - -#include <linux/vmalloc.h> - -/* - * Convert a virtual cached pointer to an uncached pointer - */ -#define xlate_dev_kmem_ptr(p) p - -static inline void -memset_io(volatile void __iomem *addr, unsigned char val, int count) -{ - memset((void __force *)addr, val, count); -} - -static inline void -memcpy_fromio(void *dst, const volatile void __iomem *src, int count) -{ - __memcpy(dst, (const void __force *)src, count); -} - -static inline void -memcpy_toio(volatile void __iomem *dst, const void *src, int count) -{ - __memcpy((void __force *)dst, src, count); -} - -/* - * ISA space is 'always mapped' on a typical x86 system, no need to - * explicitly ioremap() it. The fact that the ISA IO space is mapped - * to PAGE_OFFSET is pure coincidence - it does not mean ISA values - * are physical addresses. The following constant pointer can be - * used as the IO-area pointer (it can be iounmapped as well, so the - * analogy with PCI is quite large): - */ -#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET)) - -/* - * Cache management - * - * This needed for two cases - * 1. Out of order aware processors - * 2. Accidentally out of order processors (PPro errata #51) - */ - -#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE) - -static inline void flush_write_buffers(void) -{ - asm volatile("lock; addl $0,0(%%esp)": : :"memory"); -} - -#else - -#define flush_write_buffers() do { } while (0) - -#endif - -#endif /* __KERNEL__ */ - -extern void native_io_delay(void); - -extern int io_delay_type; -extern void io_delay_init(void); - -#if defined(CONFIG_PARAVIRT) -#include <asm/paravirt.h> -#else - -static inline void slow_down_io(void) -{ - native_io_delay(); -#ifdef REALLY_SLOW_IO - native_io_delay(); - native_io_delay(); - native_io_delay(); -#endif -} - -#endif - -#define __BUILDIO(bwl, bw, type) \ -static inline void out##bwl(unsigned type value, int port) \ -{ \ - out##bwl##_local(value, port); \ -} \ - \ -static inline unsigned type in##bwl(int port) \ -{ \ - return in##bwl##_local(port); \ -} - -#define BUILDIO(bwl, bw, type) \ -static inline void out##bwl##_local(unsigned type value, int port) \ -{ \ - asm volatile("out" #bwl " %" #bw "0, %w1" \ - : : "a"(value), "Nd"(port)); \ -} \ - \ -static inline unsigned type in##bwl##_local(int port) \ -{ \ - unsigned type value; \ - asm volatile("in" #bwl " %w1, %" #bw "0" \ - : "=a"(value) : "Nd"(port)); \ - return value; \ -} \ - \ -static inline void out##bwl##_local_p(unsigned type value, int port) \ -{ \ - out##bwl##_local(value, port); \ - slow_down_io(); \ -} \ - \ -static inline unsigned type in##bwl##_local_p(int port) \ -{ \ - unsigned type value = in##bwl##_local(port); \ - slow_down_io(); \ - return value; \ -} \ - \ -__BUILDIO(bwl, bw, type) \ - \ -static inline void out##bwl##_p(unsigned type value, int port) \ -{ \ - out##bwl(value, port); \ - slow_down_io(); \ -} \ - \ -static inline unsigned type in##bwl##_p(int port) \ -{ \ - unsigned type value = in##bwl(port); \ - slow_down_io(); \ - return value; \ -} \ - \ -static inline void outs##bwl(int port, const void *addr, unsigned long count) \ -{ \ - asm volatile("rep; outs" #bwl \ - : "+S"(addr), "+c"(count) : "d"(port)); \ -} \ - \ -static inline void ins##bwl(int port, void *addr, unsigned long count) \ -{ \ - asm volatile("rep; ins" #bwl \ - : "+D"(addr), "+c"(count) : "d"(port)); \ -} - -BUILDIO(b, b, char) -BUILDIO(w, w, short) -BUILDIO(l, , int) - -#endif /* _ASM_X86_IO_32_H */ diff --git a/arch/x86/include/asm/io_64.h b/arch/x86/include/asm/io_64.h deleted file mode 100644 index 244067893af..00000000000 --- a/arch/x86/include/asm/io_64.h +++ /dev/null @@ -1,181 +0,0 @@ -#ifndef _ASM_X86_IO_64_H -#define _ASM_X86_IO_64_H - - -/* - * This file contains the definitions for the x86 IO instructions - * inb/inw/inl/outb/outw/outl and the "string versions" of the same - * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing" - * versions of the single-IO instructions (inb_p/inw_p/..). - * - * This file is not meant to be obfuscating: it's just complicated - * to (a) handle it all in a way that makes gcc able to optimize it - * as well as possible and (b) trying to avoid writing the same thing - * over and over again with slight variations and possibly making a - * mistake somewhere. - */ - -/* - * Thanks to James van Artsdalen for a better timing-fix than - * the two short jumps: using outb's to a nonexistent port seems - * to guarantee better timings even on fast machines. - * - * On the other hand, I'd like to be sure of a non-existent port: - * I feel a bit unsafe about using 0x80 (should be safe, though) - * - * Linus - */ - - /* - * Bit simplified and optimized by Jan Hubicka - * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999. - * - * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added, - * isa_read[wl] and isa_write[wl] fixed - * - Arnaldo Carvalho de Melo <acme@conectiva.com.br> - */ - -extern void native_io_delay(void); - -extern int io_delay_type; -extern void io_delay_init(void); - -#if defined(CONFIG_PARAVIRT) -#include <asm/paravirt.h> -#else - -static inline void slow_down_io(void) -{ - native_io_delay(); -#ifdef REALLY_SLOW_IO - native_io_delay(); - native_io_delay(); - native_io_delay(); -#endif -} -#endif - -/* - * Talk about misusing macros.. - */ -#define __OUT1(s, x) \ -static inline void out##s(unsigned x value, unsigned short port) { - -#define __OUT2(s, s1, s2) \ -asm volatile ("out" #s " %" s1 "0,%" s2 "1" - -#ifndef REALLY_SLOW_IO -#define REALLY_SLOW_IO -#define UNSET_REALLY_SLOW_IO -#endif - -#define __OUT(s, s1, x) \ - __OUT1(s, x) __OUT2(s, s1, "w") : : "a" (value), "Nd" (port)); \ - } \ - __OUT1(s##_p, x) __OUT2(s, s1, "w") : : "a" (value), "Nd" (port)); \ - slow_down_io(); \ -} - -#define __IN1(s) \ -static inline RETURN_TYPE in##s(unsigned short port) \ -{ \ - RETURN_TYPE _v; - -#define __IN2(s, s1, s2) \ - asm volatile ("in" #s " %" s2 "1,%" s1 "0" - -#define __IN(s, s1, i...) \ - __IN1(s) __IN2(s, s1, "w") : "=a" (_v) : "Nd" (port), ##i); \ - return _v; \ - } \ - __IN1(s##_p) __IN2(s, s1, "w") : "=a" (_v) : "Nd" (port), ##i); \ - slow_down_io(); \ - return _v; } - -#ifdef UNSET_REALLY_SLOW_IO -#undef REALLY_SLOW_IO -#endif - -#define __INS(s) \ -static inline void ins##s(unsigned short port, void *addr, \ - unsigned long count) \ -{ \ - asm volatile ("rep ; ins" #s \ - : "=D" (addr), "=c" (count) \ - : "d" (port), "0" (addr), "1" (count)); \ -} - -#define __OUTS(s) \ -static inline void outs##s(unsigned short port, const void *addr, \ - unsigned long count) \ -{ \ - asm volatile ("rep ; outs" #s \ - : "=S" (addr), "=c" (count) \ - : "d" (port), "0" (addr), "1" (count)); \ -} - -#define RETURN_TYPE unsigned char -__IN(b, "") -#undef RETURN_TYPE -#define RETURN_TYPE unsigned short -__IN(w, "") -#undef RETURN_TYPE -#define RETURN_TYPE unsigned int -__IN(l, "") -#undef RETURN_TYPE - -__OUT(b, "b", char) -__OUT(w, "w", short) -__OUT(l, , int) - -__INS(b) -__INS(w) -__INS(l) - -__OUTS(b) -__OUTS(w) -__OUTS(l) - -#if defined(__KERNEL__) && defined(__x86_64__) - -#include <linux/vmalloc.h> - -#include <asm-generic/iomap.h> - -void __memcpy_fromio(void *, unsigned long, unsigned); -void __memcpy_toio(unsigned long, const void *, unsigned); - -static inline void memcpy_fromio(void *to, const volatile void __iomem *from, - unsigned len) -{ - __memcpy_fromio(to, (unsigned long)from, len); -} - -static inline void memcpy_toio(volatile void __iomem *to, const void *from, - unsigned len) -{ - __memcpy_toio((unsigned long)to, from, len); -} - -void memset_io(volatile void __iomem *a, int b, size_t c); - -/* - * ISA space is 'always mapped' on a typical x86 system, no need to - * explicitly ioremap() it. The fact that the ISA IO space is mapped - * to PAGE_OFFSET is pure coincidence - it does not mean ISA values - * are physical addresses. The following constant pointer can be - * used as the IO-area pointer (it can be iounmapped as well, so the - * analogy with PCI is quite large): - */ -#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET)) - -#define flush_write_buffers() - -/* - * Convert a virtual cached pointer to an uncached pointer - */ -#define xlate_dev_kmem_ptr(p) p - -#endif /* __KERNEL__ */ - -#endif /* _ASM_X86_IO_64_H */ diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index 950df434763..f46b79f6c16 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -254,6 +254,10 @@ struct kvm_reinject_control { __u8 reserved[31]; }; +/* When set in flags, include corresponding fields on KVM_SET_VCPU_EVENTS */ +#define KVM_VCPUEVENT_VALID_NMI_PENDING 0x00000001 +#define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002 + /* for KVM_GET/SET_VCPU_EVENTS */ struct kvm_vcpu_events { struct { diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 858baa061cf..6c3fdd631ed 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -108,10 +108,11 @@ struct mce_log { #define K8_MCE_THRESHOLD_BANK_5 (MCE_THRESHOLD_BASE + 5 * 9) #define K8_MCE_THRESHOLD_DRAM_ECC (MCE_THRESHOLD_BANK_4 + 0) -extern struct atomic_notifier_head x86_mce_decoder_chain; #ifdef __KERNEL__ +extern struct atomic_notifier_head x86_mce_decoder_chain; + #include <linux/percpu.h> #include <linux/init.h> #include <asm/atomic.h> diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index c24ca9a5645..ef51b501e22 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -12,8 +12,6 @@ struct device; enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND }; struct microcode_ops { - void (*init)(struct device *device); - void (*fini)(void); enum ucode_state (*request_microcode_user) (int cpu, const void __user *buf, size_t size); diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h index a29f48c2a32..288b96f815a 100644 --- a/arch/x86/include/asm/mmzone_64.h +++ b/arch/x86/include/asm/mmzone_64.h @@ -39,11 +39,5 @@ static inline __attribute__((pure)) int phys_to_nid(unsigned long addr) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) (NODE_DATA(nid)->node_start_pfn + \ NODE_DATA(nid)->node_spanned_pages) - -#ifdef CONFIG_NUMA_EMU -#define FAKE_NODE_MIN_SIZE (64 * 1024 * 1024) -#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL)) -#endif - #endif #endif /* _ASM_X86_MMZONE_64_H */ diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 139d4c1a33a..93da9c3f334 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -19,7 +19,6 @@ extern void die_nmi(char *str, struct pt_regs *regs, int do_panic); extern int check_nmi_watchdog(void); extern int nmi_watchdog_enabled; extern int avail_to_resrv_perfctr_nmi_bit(unsigned int); -extern int avail_to_resrv_perfctr_nmi(unsigned int); extern int reserve_perfctr_nmi(unsigned int); extern void release_perfctr_nmi(unsigned int); extern int reserve_evntsel_nmi(unsigned int); diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h index c4ae822e415..823e070e7c2 100644 --- a/arch/x86/include/asm/numa_64.h +++ b/arch/x86/include/asm/numa_64.h @@ -36,6 +36,11 @@ extern void __cpuinit numa_set_node(int cpu, int node); extern void __cpuinit numa_clear_node(int cpu); extern void __cpuinit numa_add_cpu(int cpu); extern void __cpuinit numa_remove_cpu(int cpu); + +#ifdef CONFIG_NUMA_EMU +#define FAKE_NODE_MIN_SIZE ((u64)64 << 20) +#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL)) +#endif /* CONFIG_NUMA_EMU */ #else static inline void init_cpu_to_node(void) { } static inline void numa_set_node(int cpu, int node) { } diff --git a/arch/x86/include/asm/numaq.h b/arch/x86/include/asm/numaq.h index 9f0a5f5d29e..13370b95ea9 100644 --- a/arch/x86/include/asm/numaq.h +++ b/arch/x86/include/asm/numaq.h @@ -33,6 +33,10 @@ extern int get_memcfg_numaq(void); extern void *xquad_portio; +#define XQUAD_PORTIO_BASE 0xfe400000 +#define XQUAD_PORTIO_QUAD 0x40000 /* 256k per quad. */ +#define XQUAD_PORT_ADDR(port, quad) (xquad_portio + (XQUAD_PORTIO_QUAD*quad) + port) + /* * SYS_CFG_DATA_PRIV_ADDR, struct eachquadmem, and struct sys_cfg_data are the */ diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index 642fe34b36a..a667f24c725 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -40,7 +40,6 @@ #ifndef __ASSEMBLY__ -extern int page_is_ram(unsigned long pagenr); extern int devmem_is_allowed(unsigned long pagenr); extern unsigned long max_low_pfn_mapped; diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index b4bf9a942ed..05b58ccb2e8 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -29,6 +29,7 @@ #define PCI_CHECK_ENABLE_AMD_MMCONF 0x20000 #define PCI_HAS_IO_ECS 0x40000 #define PCI_NOASSIGN_ROMS 0x80000 +#define PCI_ROOT_NO_CRS 0x100000 extern unsigned int pci_probe; extern unsigned long pirq_table_addr; diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 8d9f8548a87..befd172c82a 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -19,6 +19,7 @@ #define MSR_ARCH_PERFMON_EVENTSEL1 0x187 #define ARCH_PERFMON_EVENTSEL0_ENABLE (1 << 22) +#define ARCH_PERFMON_EVENTSEL_ANY (1 << 21) #define ARCH_PERFMON_EVENTSEL_INT (1 << 20) #define ARCH_PERFMON_EVENTSEL_OS (1 << 17) #define ARCH_PERFMON_EVENTSEL_USR (1 << 16) @@ -26,7 +27,14 @@ /* * Includes eventsel and unit mask as well: */ -#define ARCH_PERFMON_EVENT_MASK 0xffff + + +#define INTEL_ARCH_EVTSEL_MASK 0x000000FFULL +#define INTEL_ARCH_UNIT_MASK 0x0000FF00ULL +#define INTEL_ARCH_EDGE_MASK 0x00040000ULL +#define INTEL_ARCH_INV_MASK 0x00800000ULL +#define INTEL_ARCH_CNT_MASK 0xFF000000ULL +#define INTEL_ARCH_EVENT_MASK (INTEL_ARCH_UNIT_MASK|INTEL_ARCH_EVTSEL_MASK) /* * filter mask to validate fixed counter events. @@ -37,7 +45,12 @@ * The other filters are supported by fixed counters. * The any-thread option is supported starting with v3. */ -#define ARCH_PERFMON_EVENT_FILTER_MASK 0xff840000 +#define INTEL_ARCH_FIXED_MASK \ + (INTEL_ARCH_CNT_MASK| \ + INTEL_ARCH_INV_MASK| \ + INTEL_ARCH_EDGE_MASK|\ + INTEL_ARCH_UNIT_MASK|\ + INTEL_ARCH_EVTSEL_MASK) #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8) diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index 0e8c2a0fd92..271de94c381 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -23,6 +23,11 @@ static inline void paravirt_release_pud(unsigned long pfn) {} #endif /* + * Flags to use when allocating a user page table page. + */ +extern gfp_t __userpte_alloc_gfp; + +/* * Allocate and free page tables. */ extern pgd_t *pgd_alloc(struct mm_struct *); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index fc801bab1b3..b753ea59703 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -450,6 +450,8 @@ struct thread_struct { struct perf_event *ptrace_bps[HBP_NUM]; /* Debug status used for traps, single steps, etc... */ unsigned long debugreg6; + /* Keep track of the exact dr7 value set by the user */ + unsigned long ptrace_dr7; /* Fault info: */ unsigned long cr2; unsigned long trap_no; diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 9d369f68032..20102808b19 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -274,10 +274,6 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, return 0; } -/* Get Nth argument at function call */ -extern unsigned long regs_get_argument_nth(struct pt_regs *regs, - unsigned int n); - /* * These are defined as per linux/ptrace.h, which see. */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 1e796782cd7..4cfc9082406 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -135,6 +135,8 @@ int native_cpu_disable(void); void native_cpu_die(unsigned int cpu); void native_play_dead(void); void play_dead_common(void); +void wbinvd_on_cpu(int cpu); +int wbinvd_on_all_cpus(void); void native_send_call_func_ipi(const struct cpumask *mask); void native_send_call_func_single_ipi(int cpu); @@ -147,6 +149,13 @@ static inline int num_booting_cpus(void) { return cpumask_weight(cpu_callout_mask); } +#else /* !CONFIG_SMP */ +#define wbinvd_on_cpu(cpu) wbinvd() +static inline int wbinvd_on_all_cpus(void) +{ + wbinvd(); + return 0; +} #endif /* CONFIG_SMP */ extern unsigned disabled_cpus __cpuinitdata; diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 35e89122a42..4dab78edbad 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -3,8 +3,6 @@ extern int kstack_depth_to_print; -int x86_is_stack_id(int id, char *name); - struct thread_info; struct stacktrace_ops; diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 8d33bc5462d..c4a348f7bd4 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -16,6 +16,8 @@ #include <linux/sched.h> #include <linux/err.h> +extern const unsigned long sys_call_table[]; + /* * Only the low 32 bits of orig_ax are meaningful, so we return int. * This importantly ignores the high bits on 64-bit, so comparisons diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index ecb544e6538..e04740f7a0b 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -11,9 +11,9 @@ #include <linux/irqflags.h> /* entries in ARCH_DLINFO: */ -#ifdef CONFIG_IA32_EMULATION +#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64) # define AT_VECTOR_SIZE_ARCH 2 -#else +#else /* else it's non-compat x86-64 */ # define AT_VECTOR_SIZE_ARCH 1 #endif diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 375c917c37d..e0d28901e96 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -87,7 +87,6 @@ struct thread_info { #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* 32bit process */ #define TIF_FORK 18 /* ret_from_fork */ -#define TIF_ABI_PENDING 19 #define TIF_MEMDIE 20 #define TIF_DEBUG 21 /* uses debug registers */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ @@ -112,7 +111,6 @@ struct thread_info { #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) #define _TIF_FORK (1 << TIF_FORK) -#define _TIF_ABI_PENDING (1 << TIF_ABI_PENDING) #define _TIF_DEBUG (1 << TIF_DEBUG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) #define _TIF_FREEZE (1 << TIF_FREEZE) diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 0c9825e97f3..088d09fb161 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -205,14 +205,13 @@ static inline unsigned long __must_check copy_from_user(void *to, unsigned long n) { int sz = __compiletime_object_size(to); - int ret = -EFAULT; if (likely(sz == -1 || sz >= n)) - ret = _copy_from_user(to, from, n); + n = _copy_from_user(to, from, n); else copy_from_user_overflow(); - return ret; + return n; } long __must_check strncpy_from_user(char *dst, const char __user *src, diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index a78c4030544..316708d5af9 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -49,16 +49,15 @@ static inline unsigned long __must_check copy_from_user(void *to, unsigned long n) { int sz = __compiletime_object_size(to); - int ret = -EFAULT; might_fault(); if (likely(sz == -1 || sz >= n)) - ret = _copy_from_user(to, from, n); + n = _copy_from_user(to, from, n); #ifdef CONFIG_DEBUG_VM else WARN(1, "Buffer overflow detected!\n"); #endif - return ret; + return n; } static __always_inline __must_check diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 811bfabc80b..40be813fefb 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -31,20 +31,20 @@ * contiguous (although various IO spaces may punch holes in * it).. * - * N - Number of bits in the node portion of a socket physical - * address. + * N - Number of bits in the node portion of a socket physical + * address. * - * NASID - network ID of a router, Mbrick or Cbrick. Nasid values of - * routers always have low bit of 1, C/MBricks have low bit - * equal to 0. Most addressing macros that target UV hub chips - * right shift the NASID by 1 to exclude the always-zero bit. - * NASIDs contain up to 15 bits. + * NASID - network ID of a router, Mbrick or Cbrick. Nasid values of + * routers always have low bit of 1, C/MBricks have low bit + * equal to 0. Most addressing macros that target UV hub chips + * right shift the NASID by 1 to exclude the always-zero bit. + * NASIDs contain up to 15 bits. * * GNODE - NASID right shifted by 1 bit. Most mmrs contain gnodes instead * of nasids. * - * PNODE - the low N bits of the GNODE. The PNODE is the most useful variant - * of the nasid for socket usage. + * PNODE - the low N bits of the GNODE. The PNODE is the most useful variant + * of the nasid for socket usage. * * * NumaLink Global Physical Address Format: @@ -71,12 +71,12 @@ * * * APICID format - * NOTE!!!!!! This is the current format of the APICID. However, code - * should assume that this will change in the future. Use functions - * in this file for all APICID bit manipulations and conversion. + * NOTE!!!!!! This is the current format of the APICID. However, code + * should assume that this will change in the future. Use functions + * in this file for all APICID bit manipulations and conversion. * - * 1111110000000000 - * 5432109876543210 + * 1111110000000000 + * 5432109876543210 * pppppppppplc0cch * sssssssssss * @@ -89,9 +89,9 @@ * Note: Processor only supports 12 bits in the APICID register. The ACPI * tables hold all 16 bits. Software needs to be aware of this. * - * Unless otherwise specified, all references to APICID refer to - * the FULL value contained in ACPI tables, not the subset in the - * processor APICID register. + * Unless otherwise specified, all references to APICID refer to + * the FULL value contained in ACPI tables, not the subset in the + * processor APICID register. */ @@ -151,16 +151,16 @@ struct uv_hub_info_s { }; DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info); -#define uv_hub_info (&__get_cpu_var(__uv_hub_info)) +#define uv_hub_info (&__get_cpu_var(__uv_hub_info)) #define uv_cpu_hub_info(cpu) (&per_cpu(__uv_hub_info, cpu)) /* * Local & Global MMR space macros. - * Note: macros are intended to be used ONLY by inline functions - * in this file - not by other kernel code. - * n - NASID (full 15-bit global nasid) - * g - GNODE (full 15-bit global nasid, right shifted 1) - * p - PNODE (local part of nsids, right shifted 1) + * Note: macros are intended to be used ONLY by inline functions + * in this file - not by other kernel code. + * n - NASID (full 15-bit global nasid) + * g - GNODE (full 15-bit global nasid, right shifted 1) + * p - PNODE (local part of nsids, right shifted 1) */ #define UV_NASID_TO_PNODE(n) (((n) >> 1) & uv_hub_info->pnode_mask) #define UV_PNODE_TO_GNODE(p) ((p) |uv_hub_info->gnode_extra) @@ -215,8 +215,8 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info); /* * Macros for converting between kernel virtual addresses, socket local physical * addresses, and UV global physical addresses. - * Note: use the standard __pa() & __va() macros for converting - * between socket virtual and socket physical addresses. + * Note: use the standard __pa() & __va() macros for converting + * between socket virtual and socket physical addresses. */ /* socket phys RAM --> UV global physical address */ @@ -287,21 +287,18 @@ static inline int uv_apicid_to_pnode(int apicid) * Access global MMRs using the low memory MMR32 space. This region supports * faster MMR access but not all MMRs are accessible in this space. */ -static inline unsigned long *uv_global_mmr32_address(int pnode, - unsigned long offset) +static inline unsigned long *uv_global_mmr32_address(int pnode, unsigned long offset) { return __va(UV_GLOBAL_MMR32_BASE | UV_GLOBAL_MMR32_PNODE_BITS(pnode) | offset); } -static inline void uv_write_global_mmr32(int pnode, unsigned long offset, - unsigned long val) +static inline void uv_write_global_mmr32(int pnode, unsigned long offset, unsigned long val) { writeq(val, uv_global_mmr32_address(pnode, offset)); } -static inline unsigned long uv_read_global_mmr32(int pnode, - unsigned long offset) +static inline unsigned long uv_read_global_mmr32(int pnode, unsigned long offset) { return readq(uv_global_mmr32_address(pnode, offset)); } @@ -310,21 +307,18 @@ static inline unsigned long uv_read_global_mmr32(int pnode, * Access Global MMR space using the MMR space located at the top of physical * memory. */ -static inline unsigned long *uv_global_mmr64_address(int pnode, - unsigned long offset) +static inline unsigned long *uv_global_mmr64_address(int pnode, unsigned long offset) { return __va(UV_GLOBAL_MMR64_BASE | UV_GLOBAL_MMR64_PNODE_BITS(pnode) | offset); } -static inline void uv_write_global_mmr64(int pnode, unsigned long offset, - unsigned long val) +static inline void uv_write_global_mmr64(int pnode, unsigned long offset, unsigned long val) { writeq(val, uv_global_mmr64_address(pnode, offset)); } -static inline unsigned long uv_read_global_mmr64(int pnode, - unsigned long offset) +static inline unsigned long uv_read_global_mmr64(int pnode, unsigned long offset) { return readq(uv_global_mmr64_address(pnode, offset)); } @@ -338,6 +332,16 @@ static inline unsigned long uv_global_gru_mmr_address(int pnode, unsigned long o return UV_GLOBAL_GRU_MMR_BASE | offset | (pnode << uv_hub_info->m_val); } +static inline void uv_write_global_mmr8(int pnode, unsigned long offset, unsigned char val) +{ + writeb(val, uv_global_mmr64_address(pnode, offset)); +} + +static inline unsigned char uv_read_global_mmr8(int pnode, unsigned long offset) +{ + return readb(uv_global_mmr64_address(pnode, offset)); +} + /* * Access hub local MMRs. Faster than using global space but only local MMRs * are accessible. @@ -457,11 +461,17 @@ static inline void uv_set_scir_bits(unsigned char value) } } +static inline unsigned long uv_scir_offset(int apicid) +{ + return SCIR_LOCAL_MMR_BASE | (apicid & 0x3f); +} + static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value) { if (uv_cpu_hub_info(cpu)->scir.state != value) { + uv_write_global_mmr8(uv_cpu_to_pnode(cpu), + uv_cpu_hub_info(cpu)->scir.offset, value); uv_cpu_hub_info(cpu)->scir.state = value; - uv_write_local_mmr8(uv_cpu_hub_info(cpu)->scir.offset, value); } } @@ -485,5 +495,17 @@ static inline void uv_hub_send_ipi(int pnode, int apicid, int vector) uv_write_global_mmr64(pnode, UVH_IPI_INT, val); } +/* + * Get the minimum revision number of the hub chips within the partition. + * 1 - initial rev 1.0 silicon + * 2 - rev 2.0 production silicon + */ +static inline int uv_get_min_hub_revision_id(void) +{ + extern int uv_min_hub_revision_id; + + return uv_min_hub_revision_id; +} + #endif /* CONFIG_X86_64 */ #endif /* _ASM_X86_UV_UV_HUB_H */ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index fb1035cd9a6..f95703098f8 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -49,6 +49,7 @@ EXPORT_SYMBOL(acpi_disabled); #ifdef CONFIG_X86_64 # include <asm/proto.h> +# include <asm/numa_64.h> #endif /* X86 */ #define BAD_MADT_ENTRY(entry, end) ( \ @@ -482,6 +483,25 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) */ #ifdef CONFIG_ACPI_HOTPLUG_CPU +static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) +{ +#ifdef CONFIG_ACPI_NUMA + int nid; + + nid = acpi_get_node(handle); + if (nid == -1 || !node_online(nid)) + return; +#ifdef CONFIG_X86_64 + apicid_to_node[physid] = nid; + numa_set_node(cpu, nid); +#else /* CONFIG_X86_32 */ + apicid_2_node[physid] = nid; + cpu_to_node_map[cpu] = nid; +#endif + +#endif +} + static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu) { struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; @@ -540,6 +560,7 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu) } cpu = cpumask_first(new_map); + acpi_map_cpu2node(handle, cpu, physid); *pcpu = cpu; retval = 0; @@ -1185,9 +1206,6 @@ static void __init acpi_process_madt(void) if (!error) { acpi_lapic = 1; -#ifdef CONFIG_X86_BIGSMP - generic_bigsmp_probe(); -#endif /* * Parse MADT IO-APIC entries */ @@ -1197,8 +1215,6 @@ static void __init acpi_process_madt(void) acpi_ioapic = 1; smp_found_config = 1; - if (apic->setup_apic_routing) - apic->setup_apic_routing(); } } if (error == -EINVAL) { @@ -1349,14 +1365,6 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = { }, { .callback = force_acpi_ht, - .ident = "ASUS P2B-DS", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), - DMI_MATCH(DMI_BOARD_NAME, "P2B-DS"), - }, - }, - { - .callback = force_acpi_ht, .ident = "ASUS CUR-DLS", .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), @@ -1529,16 +1537,10 @@ static struct dmi_system_id __initdata acpi_dmi_table_late[] = { * if acpi_blacklisted() acpi_disabled = 1; * acpi_irq_model=... * ... - * - * return value: (currently ignored) - * 0: success - * !0: failure */ -int __init acpi_boot_table_init(void) +void __init acpi_boot_table_init(void) { - int error; - dmi_check_system(acpi_dmi_table); /* @@ -1546,15 +1548,14 @@ int __init acpi_boot_table_init(void) * One exception: acpi=ht continues far enough to enumerate LAPICs */ if (acpi_disabled && !acpi_ht) - return 1; + return; /* * Initialize the ACPI boot-time table parser. */ - error = acpi_table_init(); - if (error) { + if (acpi_table_init()) { disable_acpi(); - return error; + return; } acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf); @@ -1562,18 +1563,15 @@ int __init acpi_boot_table_init(void) /* * blacklist may disable ACPI entirely */ - error = acpi_blacklisted(); - if (error) { + if (acpi_blacklisted()) { if (acpi_force) { printk(KERN_WARNING PREFIX "acpi=force override\n"); } else { printk(KERN_WARNING PREFIX "Disabling ACPI support\n"); disable_acpi(); - return error; + return; } } - - return 0; } int __init early_acpi_boot_init(void) diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 82e508677b9..f9961034e55 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -162,6 +162,8 @@ static int __init acpi_sleep_setup(char *str) #endif if (strncmp(str, "old_ordering", 12) == 0) acpi_old_suspend_ordering(); + if (strncmp(str, "sci_force_enable", 16) == 0) + acpi_set_sci_en_on_resume(); str = strchr(str, ','); if (str != NULL) str += strspn(str, ", \t"); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 2589ea4c60c..e6ea0342c8f 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -392,6 +392,24 @@ void alternatives_smp_switch(int smp) mutex_unlock(&smp_alt); } +/* Return 1 if the address range is reserved for smp-alternatives */ +int alternatives_text_reserved(void *start, void *end) +{ + struct smp_alt_module *mod; + u8 **ptr; + u8 *text_start = start; + u8 *text_end = end; + + list_for_each_entry(mod, &smp_alt_modules, next) { + if (mod->text > text_end || mod->text_end < text_start) + continue; + for (ptr = mod->locks; ptr < mod->locks_end; ptr++) + if (text_start <= *ptr && text_end >= *ptr) + return 1; + } + + return 0; +} #endif #ifdef CONFIG_PARAVIRT diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 23824fef789..adb0ba02570 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -980,7 +980,7 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom, { int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT; struct amd_iommu *iommu; - int i; + unsigned long i; #ifdef CONFIG_IOMMU_STRESS populate = false; @@ -1489,11 +1489,14 @@ static void __detach_device(struct device *dev) { struct iommu_dev_data *dev_data = get_dev_data(dev); struct iommu_dev_data *alias_data; + struct protection_domain *domain; unsigned long flags; BUG_ON(!dev_data->domain); - spin_lock_irqsave(&dev_data->domain->lock, flags); + domain = dev_data->domain; + + spin_lock_irqsave(&domain->lock, flags); if (dev_data->alias != dev) { alias_data = get_dev_data(dev_data->alias); @@ -1504,13 +1507,15 @@ static void __detach_device(struct device *dev) if (atomic_dec_and_test(&dev_data->bind)) do_detach(dev); - spin_unlock_irqrestore(&dev_data->domain->lock, flags); + spin_unlock_irqrestore(&domain->lock, flags); /* * If we run in passthrough mode the device must be assigned to the - * passthrough domain if it is detached from any other domain + * passthrough domain if it is detached from any other domain. + * Make sure we can deassign from the pt_domain itself. */ - if (iommu_pass_through && dev_data->domain == NULL) + if (iommu_pass_through && + (dev_data->domain == NULL && domain != pt_domain)) __attach_device(dev, pt_domain); } @@ -2218,6 +2223,12 @@ static struct dma_map_ops amd_iommu_dma_ops = { /* * The function which clues the AMD IOMMU driver into dma_ops. */ + +void __init amd_iommu_init_api(void) +{ + register_iommu(&amd_iommu_ops); +} + int __init amd_iommu_init_dma_ops(void) { struct amd_iommu *iommu; @@ -2253,8 +2264,6 @@ int __init amd_iommu_init_dma_ops(void) /* Make the driver finally visible to the drivers */ dma_ops = &amd_iommu_dma_ops; - register_iommu(&amd_iommu_ops); - amd_iommu_stats_init(); return 0; diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 1dca9c34eae..9dc91b43147 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -138,6 +138,11 @@ int amd_iommus_present; bool amd_iommu_np_cache __read_mostly; /* + * Set to true if ACPI table parsing and hardware intialization went properly + */ +static bool amd_iommu_initialized; + +/* * List of protection domains - used during resume */ LIST_HEAD(amd_iommu_pd_list); @@ -929,6 +934,8 @@ static int __init init_iommu_all(struct acpi_table_header *table) } WARN_ON(p != end); + amd_iommu_initialized = true; + return 0; } @@ -1263,6 +1270,9 @@ static int __init amd_iommu_init(void) if (acpi_table_parse("IVRS", init_iommu_all) != 0) goto free; + if (!amd_iommu_initialized) + goto free; + if (acpi_table_parse("IVRS", init_memory_definitions) != 0) goto free; @@ -1282,9 +1292,12 @@ static int __init amd_iommu_init(void) ret = amd_iommu_init_passthrough(); else ret = amd_iommu_init_dma_ops(); + if (ret) goto free; + amd_iommu_init_api(); + amd_iommu_init_notifier(); enable_iommus(); diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 3704997e8b2..f147a95fd84 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -31,6 +31,7 @@ #include <asm/x86_init.h> int gart_iommu_aperture; +EXPORT_SYMBOL_GPL(gart_iommu_aperture); int gart_iommu_aperture_disabled __initdata; int gart_iommu_aperture_allowed __initdata; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index aa57c079c98..6e29b2a77aa 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -61,12 +61,6 @@ unsigned int boot_cpu_physical_apicid = -1U; /* * The highest APIC ID seen during enumeration. - * - * On AMD, this determines the messaging protocol we can use: if all APIC IDs - * are in the 0 ... 7 range, then we can use logical addressing which - * has some performance advantages (better broadcasting). - * - * If there's an APIC ID above 8, we use physical addressing. */ unsigned int max_physical_apicid; @@ -587,7 +581,7 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc) res = (((u64)(*deltatsc)) * pm_100ms); do_div(res, deltapm); apic_printk(APIC_VERBOSE, "TSC delta adjusted to " - "PM-Timer: %lu (%ld) \n", + "PM-Timer: %lu (%ld)\n", (unsigned long)res, *deltatsc); *deltatsc = (long)res; } @@ -1647,9 +1641,7 @@ int __init APIC_init_uniprocessor(void) #endif enable_IR_x2apic(); -#ifdef CONFIG_X86_64 default_setup_apic_routing(); -#endif verify_local_APIC(); connect_bsp_APIC(); @@ -1897,18 +1889,6 @@ void __cpuinit generic_processor_info(int apicid, int version) if (apicid > max_physical_apicid) max_physical_apicid = apicid; -#ifdef CONFIG_X86_32 - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_INTEL: - if (num_processors > 8) - def_to_bigsmp = 1; - break; - case X86_VENDOR_AMD: - if (max_physical_apicid >= 8) - def_to_bigsmp = 1; - } -#endif - #if defined(CONFIG_SMP) || defined(CONFIG_X86_64) early_per_cpu(x86_cpu_to_apicid, cpu) = apicid; early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid; diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index eacbd2b31d2..e3c3d820c32 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -240,6 +240,11 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id) printk(KERN_DEBUG "system APIC only can use physical flat"); return 1; } + + if (!strncmp(oem_id, "IBM", 3) && !strncmp(oem_table_id, "EXA", 3)) { + printk(KERN_DEBUG "IBM Summit detected, will use apic physical"); + return 1; + } #endif return 0; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index de00c4619a5..6bdd2c7ead7 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1647,7 +1647,7 @@ __apicdebuginit(void) print_IO_APIC(void) printk(KERN_DEBUG ".... IRQ redirection table:\n"); printk(KERN_DEBUG " NR Dst Mask Trig IRR Pol" - " Stat Dmod Deli Vect: \n"); + " Stat Dmod Deli Vect:\n"); for (i = 0; i <= reg_01.bits.entries; i++) { struct IO_APIC_route_entry entry; @@ -2434,6 +2434,13 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) cfg = irq_cfg(irq); raw_spin_lock(&desc->lock); + /* + * Check if the irq migration is in progress. If so, we + * haven't received the cleanup request yet for this irq. + */ + if (cfg->move_in_progress) + goto unlock; + if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) goto unlock; diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index 98c4665f251..47dd856708e 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -225,7 +225,7 @@ static void __init smp_read_mpc_oem(struct mpc_table *mpc) mpc_record = 0; printk(KERN_INFO - "Found an OEM MPC table at %8p - parsing it ... \n", oemtable); + "Found an OEM MPC table at %8p - parsing it...\n", oemtable); if (memcmp(oemtable->signature, MPC_OEM_SIGNATURE, 4)) { printk(KERN_WARNING diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 1a6559f6768..99d2fe01608 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -52,7 +52,32 @@ static int __init print_ipi_mode(void) } late_initcall(print_ipi_mode); -void default_setup_apic_routing(void) +void __init default_setup_apic_routing(void) +{ + int version = apic_version[boot_cpu_physical_apicid]; + + if (num_possible_cpus() > 8) { + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_INTEL: + if (!APIC_XAPIC(version)) { + def_to_bigsmp = 0; + break; + } + /* If P4 and above fall through */ + case X86_VENDOR_AMD: + def_to_bigsmp = 1; + } + } + +#ifdef CONFIG_X86_BIGSMP + generic_bigsmp_probe(); +#endif + + if (apic->setup_apic_routing) + apic->setup_apic_routing(); +} + +static void setup_apic_flat_routing(void) { #ifdef CONFIG_X86_IO_APIC printk(KERN_INFO @@ -103,7 +128,7 @@ struct apic apic_default = { .init_apic_ldr = default_init_apic_ldr, .ioapic_phys_id_map = default_ioapic_phys_id_map, - .setup_apic_routing = default_setup_apic_routing, + .setup_apic_routing = setup_apic_flat_routing, .multi_timer_check = NULL, .apicid_to_node = default_apicid_to_node, .cpu_to_logical_apicid = default_cpu_to_logical_apicid, diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index c4cbd3080c1..83e9be4778e 100644 --- a/arch/x86/kernel/apic/probe_64.c +++ b/arch/x86/kernel/apic/probe_64.c @@ -67,17 +67,8 @@ void __init default_setup_apic_routing(void) } #endif - if (apic == &apic_flat) { - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_INTEL: - if (num_processors > 8) - apic = &apic_physflat; - break; - case X86_VENDOR_AMD: - if (max_physical_apicid >= 8) - apic = &apic_physflat; - } - } + if (apic == &apic_flat && num_possible_cpus() > 8) + apic = &apic_physflat; printk(KERN_INFO "Setting APIC routing to %s\n", apic->name); diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index d56b0efb205..21db3cbea7d 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -36,6 +36,8 @@ DEFINE_PER_CPU(int, x2apic_extra_bits); static enum uv_system_type uv_system_type; static u64 gru_start_paddr, gru_end_paddr; +int uv_min_hub_revision_id; +EXPORT_SYMBOL_GPL(uv_min_hub_revision_id); static inline bool is_GRU_range(u64 start, u64 end) { @@ -55,12 +57,19 @@ static int early_get_nodeid(void) mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_NODE_ID, sizeof(*mmr)); node_id.v = *mmr; early_iounmap(mmr, sizeof(*mmr)); + + /* Currently, all blades have same revision number */ + uv_min_hub_revision_id = node_id.s.revision; + return node_id.s.node_id; } static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { + int nodeid; + if (!strcmp(oem_id, "SGI")) { + nodeid = early_get_nodeid(); x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; if (!strcmp(oem_table_id, "UVL")) uv_system_type = UV_LEGACY_APIC; @@ -68,7 +77,7 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) uv_system_type = UV_X2APIC; else if (!strcmp(oem_table_id, "UVH")) { __get_cpu_var(x2apic_extra_bits) = - early_get_nodeid() << (UV_APIC_PNODE_SHIFT - 1); + nodeid << (UV_APIC_PNODE_SHIFT - 1); uv_system_type = UV_NON_UNIQUE_APIC; return 1; } @@ -374,13 +383,13 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size) enum map_type {map_wb, map_uc}; -static __init void map_high(char *id, unsigned long base, int shift, - int max_pnode, enum map_type map_type) +static __init void map_high(char *id, unsigned long base, int pshift, + int bshift, int max_pnode, enum map_type map_type) { unsigned long bytes, paddr; - paddr = base << shift; - bytes = (1UL << shift) * (max_pnode + 1); + paddr = base << pshift; + bytes = (1UL << bshift) * (max_pnode + 1); printk(KERN_INFO "UV: Map %s_HI 0x%lx - 0x%lx\n", id, paddr, paddr + bytes); if (map_type == map_uc) @@ -396,7 +405,7 @@ static __init void map_gru_high(int max_pnode) gru.v = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR); if (gru.s.enable) { - map_high("GRU", gru.s.base, shift, max_pnode, map_wb); + map_high("GRU", gru.s.base, shift, shift, max_pnode, map_wb); gru_start_paddr = ((u64)gru.s.base << shift); gru_end_paddr = gru_start_paddr + (1UL << shift) * (max_pnode + 1); @@ -410,7 +419,7 @@ static __init void map_mmr_high(int max_pnode) mmr.v = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR); if (mmr.s.enable) - map_high("MMR", mmr.s.base, shift, max_pnode, map_uc); + map_high("MMR", mmr.s.base, shift, shift, max_pnode, map_uc); } static __init void map_mmioh_high(int max_pnode) @@ -420,7 +429,8 @@ static __init void map_mmioh_high(int max_pnode) mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR); if (mmioh.s.enable) - map_high("MMIOH", mmioh.s.base, shift, max_pnode, map_uc); + map_high("MMIOH", mmioh.s.base, shift, mmioh.s.m_io, + max_pnode, map_uc); } static __init void map_low_mmrs(void) @@ -629,8 +639,10 @@ void __init uv_system_init(void) uv_rtc_init(); for_each_present_cpu(cpu) { + int apicid = per_cpu(x86_cpu_to_apicid, cpu); + nid = cpu_to_node(cpu); - pnode = uv_apicid_to_pnode(per_cpu(x86_cpu_to_apicid, cpu)); + pnode = uv_apicid_to_pnode(apicid); blade = boot_pnode_to_blade(pnode); lcpu = uv_blade_info[blade].nr_possible_cpus; uv_blade_info[blade].nr_possible_cpus++; @@ -651,15 +663,13 @@ void __init uv_system_init(void) uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra; uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base; uv_cpu_hub_info(cpu)->coherency_domain_number = sn_coherency_id; - uv_cpu_hub_info(cpu)->scir.offset = SCIR_LOCAL_MMR_BASE + lcpu; + uv_cpu_hub_info(cpu)->scir.offset = uv_scir_offset(apicid); uv_node_to_blade[nid] = blade; uv_cpu_to_blade[cpu] = blade; max_pnode = max(pnode, max_pnode); - printk(KERN_DEBUG "UV: cpu %d, apicid 0x%x, pnode %d, nid %d, " - "lcpu %d, blade %d\n", - cpu, per_cpu(x86_cpu_to_apicid, cpu), pnode, nid, - lcpu, blade); + printk(KERN_DEBUG "UV: cpu %d, apicid 0x%x, pnode %d, nid %d, lcpu %d, blade %d\n", + cpu, apicid, pnode, nid, lcpu, blade); } /* Add blade/pnode info for nodes without cpus */ diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index b5b6b23bce5..031aa887b0e 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1992,8 +1992,8 @@ static int __init apm_is_horked_d850md(const struct dmi_system_id *d) apm_info.disabled = 1; printk(KERN_INFO "%s machine detected. " "Disabling APM.\n", d->ident); - printk(KERN_INFO "This bug is fixed in bios P15 which is available for \n"); - printk(KERN_INFO "download from support.intel.com \n"); + printk(KERN_INFO "This bug is fixed in bios P15 which is available for\n"); + printk(KERN_INFO "download from support.intel.com\n"); } return 0; } diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 1d2cb383410..c202b62f367 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -19,8 +19,6 @@ obj-y += vmware.o hypervisor.o sched.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 diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c index 468489b57aa..97ad79cdf68 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/addon_cpuid_features.c @@ -32,6 +32,10 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006 }, { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006 }, + { X86_FEATURE_NPT, CR_EDX, 0, 0x8000000a }, + { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a }, + { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a }, + { X86_FEATURE_NRIPS, CR_EDX, 3, 0x8000000a }, { 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c deleted file mode 100644 index b368cd86299..00000000000 --- a/arch/x86/kernel/cpu/cpu_debug.c +++ /dev/null @@ -1,688 +0,0 @@ -/* - * 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_REG_ALL_BIT], cpud_arr); -static DEFINE_PER_CPU(struct cpu_private * [MAX_CPU_FILES], cpud_priv_arr); -static DEFINE_PER_CPU(int, cpud_priv_count); - -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 }, -}; - -/* CPU Registers Range */ -static struct cpu_debug_range cpu_reg_range[] = { - { 0x00000000, 0x00000001, CPU_MC, }, - { 0x00000006, 0x00000007, CPU_MONITOR, }, - { 0x00000010, 0x00000010, CPU_TIME, }, - { 0x00000011, 0x00000013, CPU_PMC, }, - { 0x00000017, 0x00000017, CPU_PLATFORM, }, - { 0x0000001B, 0x0000001B, CPU_APIC, }, - { 0x0000002A, 0x0000002B, CPU_POWERON, }, - { 0x0000002C, 0x0000002C, CPU_FREQ, }, - { 0x0000003A, 0x0000003A, CPU_CONTROL, }, - { 0x00000040, 0x00000047, CPU_LBRANCH, }, - { 0x00000060, 0x00000067, CPU_LBRANCH, }, - { 0x00000079, 0x00000079, CPU_BIOS, }, - { 0x00000088, 0x0000008A, CPU_CACHE, }, - { 0x0000008B, 0x0000008B, CPU_BIOS, }, - { 0x0000009B, 0x0000009B, CPU_MONITOR, }, - { 0x000000C1, 0x000000C4, CPU_PMC, }, - { 0x000000CD, 0x000000CD, CPU_FREQ, }, - { 0x000000E7, 0x000000E8, CPU_PERF, }, - { 0x000000FE, 0x000000FE, CPU_MTRR, }, - - { 0x00000116, 0x0000011E, CPU_CACHE, }, - { 0x00000174, 0x00000176, CPU_SYSENTER, }, - { 0x00000179, 0x0000017B, CPU_MC, }, - { 0x00000186, 0x00000189, CPU_PMC, }, - { 0x00000198, 0x00000199, CPU_PERF, }, - { 0x0000019A, 0x0000019A, CPU_TIME, }, - { 0x0000019B, 0x0000019D, CPU_THERM, }, - { 0x000001A0, 0x000001A0, CPU_MISC, }, - { 0x000001C9, 0x000001C9, CPU_LBRANCH, }, - { 0x000001D7, 0x000001D8, CPU_LBRANCH, }, - { 0x000001D9, 0x000001D9, CPU_DEBUG, }, - { 0x000001DA, 0x000001E0, CPU_LBRANCH, }, - - { 0x00000200, 0x0000020F, CPU_MTRR, }, - { 0x00000250, 0x00000250, CPU_MTRR, }, - { 0x00000258, 0x00000259, CPU_MTRR, }, - { 0x00000268, 0x0000026F, CPU_MTRR, }, - { 0x00000277, 0x00000277, CPU_PAT, }, - { 0x000002FF, 0x000002FF, CPU_MTRR, }, - - { 0x00000300, 0x00000311, CPU_PMC, }, - { 0x00000345, 0x00000345, CPU_PMC, }, - { 0x00000360, 0x00000371, CPU_PMC, }, - { 0x0000038D, 0x00000390, CPU_PMC, }, - { 0x000003A0, 0x000003BE, CPU_PMC, }, - { 0x000003C0, 0x000003CD, CPU_PMC, }, - { 0x000003E0, 0x000003E1, CPU_PMC, }, - { 0x000003F0, 0x000003F2, CPU_PMC, }, - - { 0x00000400, 0x00000417, CPU_MC, }, - { 0x00000480, 0x0000048B, CPU_VMX, }, - - { 0x00000600, 0x00000600, CPU_DEBUG, }, - { 0x00000680, 0x0000068F, CPU_LBRANCH, }, - { 0x000006C0, 0x000006CF, CPU_LBRANCH, }, - - { 0x000107CC, 0x000107D3, CPU_PMC, }, - - { 0xC0000080, 0xC0000080, CPU_FEATURES, }, - { 0xC0000081, 0xC0000084, CPU_CALL, }, - { 0xC0000100, 0xC0000102, CPU_BASE, }, - { 0xC0000103, 0xC0000103, CPU_TIME, }, - - { 0xC0010000, 0xC0010007, CPU_PMC, }, - { 0xC0010010, 0xC0010010, CPU_CONF, }, - { 0xC0010015, 0xC0010015, CPU_CONF, }, - { 0xC0010016, 0xC001001A, CPU_MTRR, }, - { 0xC001001D, 0xC001001D, CPU_MTRR, }, - { 0xC001001F, 0xC001001F, CPU_CONF, }, - { 0xC0010030, 0xC0010035, CPU_BIOS, }, - { 0xC0010044, 0xC0010048, CPU_MC, }, - { 0xC0010050, 0xC0010056, CPU_SMM, }, - { 0xC0010058, 0xC0010058, CPU_CONF, }, - { 0xC0010060, 0xC0010060, CPU_CACHE, }, - { 0xC0010061, 0xC0010068, CPU_SMM, }, - { 0xC0010069, 0xC001006B, CPU_SMM, }, - { 0xC0010070, 0xC0010071, CPU_SMM, }, - { 0xC0010111, 0xC0010113, CPU_SMM, }, - { 0xC0010114, 0xC0010118, CPU_SVM, }, - { 0xC0010140, 0xC0010141, CPU_OSVM, }, - { 0xC0011022, 0xC0011023, CPU_CONF, }, -}; - -static int is_typeflag_valid(unsigned cpu, unsigned flag) -{ - int i; - - /* Standard Registers should be always valid */ - if (flag >= CPU_TSS) - return 1; - - for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) { - if (cpu_reg_range[i].flag == flag) - return 1; - } - - /* Invalid */ - return 0; -} - -static unsigned get_cpu_range(unsigned cpu, unsigned *min, unsigned *max, - int index, unsigned flag) -{ - if (cpu_reg_range[index].flag == flag) { - *min = cpu_reg_range[index].min; - *max = cpu_reg_range[index].max; - } else - *max = 0; - - 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; - - 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; - } - } - - for (i = 0; i < ARRAY_SIZE(cpu_reg_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)); - if (boot_cpu_has(X86_FEATURE_EXTAPIC)) { - unsigned int i, v, maxeilvt; - - v = apic_read(APIC_EFEAT); - maxeilvt = (v >> 16) & 0xff; - seq_printf(seq, " EFEAT\t\t: %08x\n", v); - seq_printf(seq, " ECTRL\t\t: %08x\n", apic_read(APIC_ECTRL)); - - for (i = 0; i < maxeilvt; i++) { - v = apic_read(APIC_EILVTn(i)); - seq_printf(seq, " EILVT%d\t\t: %08x\n", i, v); - } - } -#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(cpud_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(cpud_priv_arr[type], cpu) = priv; - per_cpu(cpud_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(cpud_arr[type].dentry, cpu), - (void *)priv, &cpu_fops); - mutex_lock(&cpu_debug_lock); - per_cpu(cpud_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, err = 0; - char reg_dir[12]; - u32 low, high; - - for (i = 0; i < ARRAY_SIZE(cpu_reg_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(cpud_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; - - 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(cpud_priv_count, cpu)); - if (per_cpu(cpud_priv_count, cpu) > MAX_CPU_FILES) { - pr_err("Register files count %d exceeds limit %d\n", - per_cpu(cpud_priv_count, cpu), MAX_CPU_FILES); - per_cpu(cpud_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(cpud_priv_count, cpu); i++) - kfree(per_cpu(cpud_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/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index f125e5c551c..6e44519960c 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -1356,6 +1356,7 @@ static int __devexit powernowk8_cpu_exit(struct cpufreq_policy *pol) kfree(data->powernow_table); kfree(data); + per_cpu(powernow_data, pol->cpu) = NULL; return 0; } @@ -1375,7 +1376,7 @@ static unsigned int powernowk8_get(unsigned int cpu) int err; if (!data) - return -EINVAL; + return 0; smp_call_function_single(cpu, query_values_on_cpu, &err, true); if (err) diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index c2b722d5a72..eddb1bdd1b8 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -18,6 +18,7 @@ #include <asm/processor.h> #include <linux/smp.h> #include <asm/k8.h> +#include <asm/smp.h> #define LVL_1_INST 1 #define LVL_1_DATA 2 @@ -152,7 +153,8 @@ struct _cpuid4_info { union _cpuid4_leaf_ebx ebx; union _cpuid4_leaf_ecx ecx; unsigned long size; - unsigned long can_disable; + bool can_disable; + unsigned int l3_indices; DECLARE_BITMAP(shared_cpu_map, NR_CPUS); }; @@ -162,7 +164,8 @@ struct _cpuid4_info_regs { union _cpuid4_leaf_ebx ebx; union _cpuid4_leaf_ecx ecx; unsigned long size; - unsigned long can_disable; + bool can_disable; + unsigned int l3_indices; }; unsigned short num_cache_leaves; @@ -292,6 +295,36 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, (ebx->split.ways_of_associativity + 1) - 1; } +struct _cache_attr { + struct attribute attr; + ssize_t (*show)(struct _cpuid4_info *, char *); + ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count); +}; + +#ifdef CONFIG_CPU_SUP_AMD +static unsigned int __cpuinit amd_calc_l3_indices(void) +{ + /* + * We're called over smp_call_function_single() and therefore + * are on the correct cpu. + */ + int cpu = smp_processor_id(); + int node = cpu_to_node(cpu); + struct pci_dev *dev = node_to_k8_nb_misc(node); + unsigned int sc0, sc1, sc2, sc3; + u32 val = 0; + + pci_read_config_dword(dev, 0x1C4, &val); + + /* calculate subcache sizes */ + sc0 = !(val & BIT(0)); + sc1 = !(val & BIT(4)); + sc2 = !(val & BIT(8)) + !(val & BIT(9)); + sc3 = !(val & BIT(12)) + !(val & BIT(13)); + + return (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1; +} + static void __cpuinit amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) { @@ -301,12 +334,103 @@ amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) if (boot_cpu_data.x86 == 0x11) return; - /* see erratum #382 */ - if ((boot_cpu_data.x86 == 0x10) && (boot_cpu_data.x86_model < 0x8)) + /* see errata #382 and #388 */ + if ((boot_cpu_data.x86 == 0x10) && + ((boot_cpu_data.x86_model < 0x8) || + (boot_cpu_data.x86_mask < 0x1))) return; - this_leaf->can_disable = 1; + this_leaf->can_disable = true; + this_leaf->l3_indices = amd_calc_l3_indices(); +} + +static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf, + unsigned int index) +{ + int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); + int node = amd_get_nb_id(cpu); + struct pci_dev *dev = node_to_k8_nb_misc(node); + unsigned int reg = 0; + + if (!this_leaf->can_disable) + return -EINVAL; + + if (!dev) + return -EINVAL; + + pci_read_config_dword(dev, 0x1BC + index * 4, ®); + return sprintf(buf, "0x%08x\n", reg); +} + +#define SHOW_CACHE_DISABLE(index) \ +static ssize_t \ +show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf) \ +{ \ + return show_cache_disable(this_leaf, buf, index); \ +} +SHOW_CACHE_DISABLE(0) +SHOW_CACHE_DISABLE(1) + +static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, + const char *buf, size_t count, unsigned int index) +{ + int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); + int node = amd_get_nb_id(cpu); + struct pci_dev *dev = node_to_k8_nb_misc(node); + unsigned long val = 0; + +#define SUBCACHE_MASK (3UL << 20) +#define SUBCACHE_INDEX 0xfff + + if (!this_leaf->can_disable) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!dev) + return -EINVAL; + + if (strict_strtoul(buf, 10, &val) < 0) + return -EINVAL; + + /* do not allow writes outside of allowed bits */ + if ((val & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) || + ((val & SUBCACHE_INDEX) > this_leaf->l3_indices)) + return -EINVAL; + + val |= BIT(30); + pci_write_config_dword(dev, 0x1BC + index * 4, val); + /* + * We need to WBINVD on a core on the node containing the L3 cache which + * indices we disable therefore a simple wbinvd() is not sufficient. + */ + wbinvd_on_cpu(cpu); + pci_write_config_dword(dev, 0x1BC + index * 4, val | BIT(31)); + return count; +} + +#define STORE_CACHE_DISABLE(index) \ +static ssize_t \ +store_cache_disable_##index(struct _cpuid4_info *this_leaf, \ + const char *buf, size_t count) \ +{ \ + return store_cache_disable(this_leaf, buf, count, index); \ } +STORE_CACHE_DISABLE(0) +STORE_CACHE_DISABLE(1) + +static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644, + show_cache_disable_0, store_cache_disable_0); +static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644, + show_cache_disable_1, store_cache_disable_1); + +#else /* CONFIG_CPU_SUP_AMD */ +static void __cpuinit +amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) +{ +}; +#endif /* CONFIG_CPU_SUP_AMD */ static int __cpuinit cpuid4_cache_lookup_regs(int index, @@ -713,82 +837,6 @@ static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf) #define to_object(k) container_of(k, struct _index_kobject, kobj) #define to_attr(a) container_of(a, struct _cache_attr, attr) -static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf, - unsigned int index) -{ - int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); - int node = cpu_to_node(cpu); - struct pci_dev *dev = node_to_k8_nb_misc(node); - unsigned int reg = 0; - - if (!this_leaf->can_disable) - return -EINVAL; - - if (!dev) - return -EINVAL; - - pci_read_config_dword(dev, 0x1BC + index * 4, ®); - return sprintf(buf, "%x\n", reg); -} - -#define SHOW_CACHE_DISABLE(index) \ -static ssize_t \ -show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf) \ -{ \ - return show_cache_disable(this_leaf, buf, index); \ -} -SHOW_CACHE_DISABLE(0) -SHOW_CACHE_DISABLE(1) - -static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, - const char *buf, size_t count, unsigned int index) -{ - int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); - int node = cpu_to_node(cpu); - struct pci_dev *dev = node_to_k8_nb_misc(node); - unsigned long val = 0; - unsigned int scrubber = 0; - - if (!this_leaf->can_disable) - return -EINVAL; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - if (!dev) - return -EINVAL; - - if (strict_strtoul(buf, 10, &val) < 0) - return -EINVAL; - - val |= 0xc0000000; - - pci_read_config_dword(dev, 0x58, &scrubber); - scrubber &= ~0x1f000000; - pci_write_config_dword(dev, 0x58, scrubber); - - pci_write_config_dword(dev, 0x1BC + index * 4, val & ~0x40000000); - wbinvd(); - pci_write_config_dword(dev, 0x1BC + index * 4, val); - return count; -} - -#define STORE_CACHE_DISABLE(index) \ -static ssize_t \ -store_cache_disable_##index(struct _cpuid4_info *this_leaf, \ - const char *buf, size_t count) \ -{ \ - return store_cache_disable(this_leaf, buf, count, index); \ -} -STORE_CACHE_DISABLE(0) -STORE_CACHE_DISABLE(1) - -struct _cache_attr { - struct attribute attr; - ssize_t (*show)(struct _cpuid4_info *, char *); - ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count); -}; - #define define_one_ro(_name) \ static struct _cache_attr _name = \ __ATTR(_name, 0444, show_##_name, NULL) @@ -803,23 +851,28 @@ define_one_ro(size); define_one_ro(shared_cpu_map); define_one_ro(shared_cpu_list); -static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644, - show_cache_disable_0, store_cache_disable_0); -static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644, - show_cache_disable_1, store_cache_disable_1); +#define DEFAULT_SYSFS_CACHE_ATTRS \ + &type.attr, \ + &level.attr, \ + &coherency_line_size.attr, \ + &physical_line_partition.attr, \ + &ways_of_associativity.attr, \ + &number_of_sets.attr, \ + &size.attr, \ + &shared_cpu_map.attr, \ + &shared_cpu_list.attr static struct attribute *default_attrs[] = { - &type.attr, - &level.attr, - &coherency_line_size.attr, - &physical_line_partition.attr, - &ways_of_associativity.attr, - &number_of_sets.attr, - &size.attr, - &shared_cpu_map.attr, - &shared_cpu_list.attr, + DEFAULT_SYSFS_CACHE_ATTRS, + NULL +}; + +static struct attribute *default_l3_attrs[] = { + DEFAULT_SYSFS_CACHE_ATTRS, +#ifdef CONFIG_CPU_SUP_AMD &cache_disable_0.attr, &cache_disable_1.attr, +#endif NULL }; @@ -910,6 +963,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) unsigned int cpu = sys_dev->id; unsigned long i, j; struct _index_kobject *this_object; + struct _cpuid4_info *this_leaf; int retval; retval = cpuid4_cache_sysfs_init(cpu); @@ -928,6 +982,14 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) this_object = INDEX_KOBJECT_PTR(cpu, i); this_object->cpu = cpu; this_object->index = i; + + this_leaf = CPUID4_INFO_IDX(cpu, i); + + if (this_leaf->can_disable) + ktype_cache.default_attrs = default_l3_attrs; + else + ktype_cache.default_attrs = default_attrs; + retval = kobject_init_and_add(&(this_object->kobj), &ktype_cache, per_cpu(ici_cache_kobject, cpu), diff --git a/arch/x86/kernel/cpu/mtrr/Makefile b/arch/x86/kernel/cpu/mtrr/Makefile index f4361b56f8e..ad9e5ed8118 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 cleanup.o +obj-y := main.o if.o generic.o cleanup.o obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o diff --git a/arch/x86/kernel/cpu/mtrr/amd.c b/arch/x86/kernel/cpu/mtrr/amd.c index 33af14110df..92ba9cd31c9 100644 --- a/arch/x86/kernel/cpu/mtrr/amd.c +++ b/arch/x86/kernel/cpu/mtrr/amd.c @@ -108,7 +108,7 @@ amd_validate_add_page(unsigned long base, unsigned long size, unsigned int type) return 0; } -static struct mtrr_ops amd_mtrr_ops = { +static const struct mtrr_ops amd_mtrr_ops = { .vendor = X86_VENDOR_AMD, .set = amd_set_mtrr, .get = amd_get_mtrr, diff --git a/arch/x86/kernel/cpu/mtrr/centaur.c b/arch/x86/kernel/cpu/mtrr/centaur.c index de89f14eff3..316fe3e60a9 100644 --- a/arch/x86/kernel/cpu/mtrr/centaur.c +++ b/arch/x86/kernel/cpu/mtrr/centaur.c @@ -110,7 +110,7 @@ centaur_validate_add_page(unsigned long base, unsigned long size, unsigned int t return 0; } -static struct mtrr_ops centaur_mtrr_ops = { +static const struct mtrr_ops centaur_mtrr_ops = { .vendor = X86_VENDOR_CENTAUR, .set = centaur_set_mcr, .get = centaur_get_mcr, diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index 228d982ce09..68a3343e579 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -265,7 +265,7 @@ static void cyrix_set_all(void) post_set(); } -static struct mtrr_ops cyrix_mtrr_ops = { +static const struct mtrr_ops cyrix_mtrr_ops = { .vendor = X86_VENDOR_CYRIX, .set_all = cyrix_set_all, .set = cyrix_set_arr, diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 55da0c5f68d..9aa5dc76ff4 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -464,7 +464,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, tmp |= ~((1<<(hi - 1)) - 1); if (tmp != mask_lo) { - WARN_ONCE(1, KERN_INFO "mtrr: your BIOS has set up an incorrect mask, fixing it up.\n"); + printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n"); mask_lo = tmp; } } @@ -570,7 +570,7 @@ static unsigned long set_mtrr_state(void) static unsigned long cr4; -static DEFINE_SPINLOCK(set_atomicity_lock); +static DEFINE_RAW_SPINLOCK(set_atomicity_lock); /* * Since we are disabling the cache don't allow any interrupts, @@ -590,7 +590,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) * changes to the way the kernel boots */ - spin_lock(&set_atomicity_lock); + raw_spin_lock(&set_atomicity_lock); /* Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */ cr0 = read_cr0() | X86_CR0_CD; @@ -627,7 +627,7 @@ static void post_set(void) __releases(set_atomicity_lock) /* Restore value of CR4 */ if (cpu_has_pge) write_cr4(cr4); - spin_unlock(&set_atomicity_lock); + raw_spin_unlock(&set_atomicity_lock); } static void generic_set_all(void) @@ -752,7 +752,7 @@ int positive_have_wrcomb(void) /* * Generic structure... */ -struct mtrr_ops generic_mtrr_ops = { +const struct mtrr_ops generic_mtrr_ops = { .use_intel_if = 1, .set_all = generic_set_all, .get = generic_get_mtrr, diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 84e83de5457..fe4622e8c83 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -60,14 +60,14 @@ static DEFINE_MUTEX(mtrr_mutex); u64 size_or_mask, size_and_mask; static bool mtrr_aps_delayed_init; -static struct mtrr_ops *mtrr_ops[X86_VENDOR_NUM]; +static const struct mtrr_ops *mtrr_ops[X86_VENDOR_NUM]; -struct mtrr_ops *mtrr_if; +const struct mtrr_ops *mtrr_if; static void set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type); -void set_mtrr_ops(struct mtrr_ops *ops) +void set_mtrr_ops(const struct mtrr_ops *ops) { if (ops->vendor && ops->vendor < X86_VENDOR_NUM) mtrr_ops[ops->vendor] = ops; diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index a501dee9a87..df5e41f31a2 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -32,7 +32,7 @@ extern int generic_get_free_region(unsigned long base, unsigned long size, extern int generic_validate_add_page(unsigned long base, unsigned long size, unsigned int type); -extern struct mtrr_ops generic_mtrr_ops; +extern const struct mtrr_ops generic_mtrr_ops; extern int positive_have_wrcomb(void); @@ -53,10 +53,10 @@ void fill_mtrr_var_range(unsigned int index, u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi); void get_mtrr_state(void); -extern void set_mtrr_ops(struct mtrr_ops *ops); +extern void set_mtrr_ops(const struct mtrr_ops *ops); extern u64 size_or_mask, size_and_mask; -extern struct mtrr_ops *mtrr_if; +extern const struct mtrr_ops *mtrr_if; #define is_cpu(vnd) (mtrr_if && mtrr_if->vendor == X86_VENDOR_##vnd) #define use_intel() (mtrr_if && mtrr_if->use_intel_if == 1) diff --git a/arch/x86/kernel/cpu/mtrr/state.c b/arch/x86/kernel/cpu/mtrr/state.c deleted file mode 100644 index dfc80b4e6b0..00000000000 --- a/arch/x86/kernel/cpu/mtrr/state.c +++ /dev/null @@ -1,94 +0,0 @@ -#include <linux/init.h> -#include <linux/io.h> -#include <linux/mm.h> - -#include <asm/processor-cyrix.h> -#include <asm/processor-flags.h> -#include <asm/mtrr.h> -#include <asm/msr.h> - -#include "mtrr.h" - -/* Put the processor into a state where MTRRs can be safely set */ -void set_mtrr_prepare_save(struct set_mtrr_context *ctxt) -{ - unsigned int cr0; - - /* Disable interrupts locally */ - local_irq_save(ctxt->flags); - - if (use_intel() || is_cpu(CYRIX)) { - - /* Save value of CR4 and clear Page Global Enable (bit 7) */ - if (cpu_has_pge) { - ctxt->cr4val = read_cr4(); - write_cr4(ctxt->cr4val & ~X86_CR4_PGE); - } - - /* - * Disable and flush caches. Note that wbinvd flushes the TLBs - * as a side-effect - */ - cr0 = read_cr0() | X86_CR0_CD; - wbinvd(); - write_cr0(cr0); - wbinvd(); - - if (use_intel()) { - /* Save MTRR state */ - rdmsr(MSR_MTRRdefType, ctxt->deftype_lo, ctxt->deftype_hi); - } else { - /* - * Cyrix ARRs - - * everything else were excluded at the top - */ - ctxt->ccr3 = getCx86(CX86_CCR3); - } - } -} - -void set_mtrr_cache_disable(struct set_mtrr_context *ctxt) -{ - if (use_intel()) { - /* Disable MTRRs, and set the default type to uncached */ - mtrr_wrmsr(MSR_MTRRdefType, ctxt->deftype_lo & 0xf300UL, - ctxt->deftype_hi); - } else { - if (is_cpu(CYRIX)) { - /* Cyrix ARRs - everything else were excluded at the top */ - setCx86(CX86_CCR3, (ctxt->ccr3 & 0x0f) | 0x10); - } - } -} - -/* Restore the processor after a set_mtrr_prepare */ -void set_mtrr_done(struct set_mtrr_context *ctxt) -{ - if (use_intel() || is_cpu(CYRIX)) { - - /* Flush caches and TLBs */ - wbinvd(); - - /* Restore MTRRdefType */ - if (use_intel()) { - /* Intel (P6) standard MTRRs */ - mtrr_wrmsr(MSR_MTRRdefType, ctxt->deftype_lo, - ctxt->deftype_hi); - } else { - /* - * Cyrix ARRs - - * everything else was excluded at the top - */ - setCx86(CX86_CCR3, ctxt->ccr3); - } - - /* Enable caches */ - write_cr0(read_cr0() & 0xbfffffff); - - /* Restore value of CR4 */ - if (cpu_has_pge) - write_cr4(ctxt->cr4val); - } - /* Re-enable interrupts locally (if enabled previously) */ - local_irq_restore(ctxt->flags); -} diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index c223b7e895d..641ccb9dddb 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -7,6 +7,7 @@ * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> + * Copyright (C) 2009 Google, Inc., Stephane Eranian * * For licencing details see kernel-base/COPYING */ @@ -22,6 +23,7 @@ #include <linux/uaccess.h> #include <linux/highmem.h> #include <linux/cpu.h> +#include <linux/bitops.h> #include <asm/apic.h> #include <asm/stacktrace.h> @@ -68,26 +70,59 @@ struct debug_store { u64 pebs_event_reset[MAX_PEBS_EVENTS]; }; +struct event_constraint { + union { + unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + u64 idxmsk64[1]; + }; + int code; + int cmask; + int weight; +}; + +struct amd_nb { + int nb_id; /* NorthBridge id */ + int refcnt; /* reference count */ + struct perf_event *owners[X86_PMC_IDX_MAX]; + struct event_constraint event_constraints[X86_PMC_IDX_MAX]; +}; + struct cpu_hw_events { - struct perf_event *events[X86_PMC_IDX_MAX]; - unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */ unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; unsigned long interrupts; int enabled; struct debug_store *ds; -}; -struct event_constraint { - unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; - int code; + int n_events; + int n_added; + int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ + u64 tags[X86_PMC_IDX_MAX]; + struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */ + struct amd_nb *amd_nb; }; -#define EVENT_CONSTRAINT(c, m) { .code = (c), .idxmsk[0] = (m) } -#define EVENT_CONSTRAINT_END { .code = 0, .idxmsk[0] = 0 } +#define __EVENT_CONSTRAINT(c, n, m, w) {\ + { .idxmsk64[0] = (n) }, \ + .code = (c), \ + .cmask = (m), \ + .weight = (w), \ +} + +#define EVENT_CONSTRAINT(c, n, m) \ + __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n)) -#define for_each_event_constraint(e, c) \ - for ((e) = (c); (e)->idxmsk[0]; (e)++) +#define INTEL_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVTSEL_MASK) +#define FIXED_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, INTEL_ARCH_FIXED_MASK) + +#define EVENT_CONSTRAINT_END \ + EVENT_CONSTRAINT(0, 0, 0) + +#define for_each_event_constraint(e, c) \ + for ((e) = (c); (e)->cmask; (e)++) /* * struct x86_pmu - generic x86 pmu @@ -114,8 +149,14 @@ struct x86_pmu { u64 intel_ctrl; void (*enable_bts)(u64 config); void (*disable_bts)(void); - int (*get_event_idx)(struct cpu_hw_events *cpuc, - struct hw_perf_event *hwc); + + struct event_constraint * + (*get_event_constraints)(struct cpu_hw_events *cpuc, + struct perf_event *event); + + void (*put_event_constraints)(struct cpu_hw_events *cpuc, + struct perf_event *event); + struct event_constraint *event_constraints; }; static struct x86_pmu x86_pmu __read_mostly; @@ -124,111 +165,8 @@ static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, }; -static const struct event_constraint *event_constraints; - -/* - * Not sure about some of these - */ -static const u64 p6_perfmon_event_map[] = -{ - [PERF_COUNT_HW_CPU_CYCLES] = 0x0079, - [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, - [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0f2e, - [PERF_COUNT_HW_CACHE_MISSES] = 0x012e, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, - [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, - [PERF_COUNT_HW_BUS_CYCLES] = 0x0062, -}; - -static u64 p6_pmu_event_map(int hw_event) -{ - return p6_perfmon_event_map[hw_event]; -} - -/* - * Event setting that is specified not to count anything. - * We use this to effectively disable a counter. - * - * L2_RQSTS with 0 MESI unit mask. - */ -#define P6_NOP_EVENT 0x0000002EULL - -static u64 p6_pmu_raw_event(u64 hw_event) -{ -#define P6_EVNTSEL_EVENT_MASK 0x000000FFULL -#define P6_EVNTSEL_UNIT_MASK 0x0000FF00ULL -#define P6_EVNTSEL_EDGE_MASK 0x00040000ULL -#define P6_EVNTSEL_INV_MASK 0x00800000ULL -#define P6_EVNTSEL_REG_MASK 0xFF000000ULL - -#define P6_EVNTSEL_MASK \ - (P6_EVNTSEL_EVENT_MASK | \ - P6_EVNTSEL_UNIT_MASK | \ - P6_EVNTSEL_EDGE_MASK | \ - P6_EVNTSEL_INV_MASK | \ - P6_EVNTSEL_REG_MASK) - - return hw_event & P6_EVNTSEL_MASK; -} - -static const struct event_constraint intel_p6_event_constraints[] = -{ - EVENT_CONSTRAINT(0xc1, 0x1), /* FLOPS */ - EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */ - EVENT_CONSTRAINT(0x11, 0x1), /* FP_ASSIST */ - EVENT_CONSTRAINT(0x12, 0x2), /* MUL */ - EVENT_CONSTRAINT(0x13, 0x2), /* DIV */ - EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */ - EVENT_CONSTRAINT_END -}; - -/* - * Intel PerfMon v3. Used on Core2 and later. - */ -static const u64 intel_perfmon_event_map[] = -{ - [PERF_COUNT_HW_CPU_CYCLES] = 0x003c, - [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, - [PERF_COUNT_HW_CACHE_REFERENCES] = 0x4f2e, - [PERF_COUNT_HW_CACHE_MISSES] = 0x412e, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, - [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, - [PERF_COUNT_HW_BUS_CYCLES] = 0x013c, -}; - -static const struct event_constraint intel_core_event_constraints[] = -{ - EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */ - EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */ - EVENT_CONSTRAINT(0x12, 0x2), /* MUL */ - EVENT_CONSTRAINT(0x13, 0x2), /* DIV */ - EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */ - EVENT_CONSTRAINT(0x18, 0x1), /* IDLE_DURING_DIV */ - EVENT_CONSTRAINT(0x19, 0x2), /* DELAYED_BYPASS */ - EVENT_CONSTRAINT(0xa1, 0x1), /* RS_UOPS_DISPATCH_CYCLES */ - EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED */ - EVENT_CONSTRAINT_END -}; - -static const struct event_constraint intel_nehalem_event_constraints[] = -{ - EVENT_CONSTRAINT(0x40, 0x3), /* L1D_CACHE_LD */ - EVENT_CONSTRAINT(0x41, 0x3), /* L1D_CACHE_ST */ - EVENT_CONSTRAINT(0x42, 0x3), /* L1D_CACHE_LOCK */ - EVENT_CONSTRAINT(0x43, 0x3), /* L1D_ALL_REF */ - EVENT_CONSTRAINT(0x4e, 0x3), /* L1D_PREFETCH */ - EVENT_CONSTRAINT(0x4c, 0x3), /* LOAD_HIT_PRE */ - EVENT_CONSTRAINT(0x51, 0x3), /* L1D */ - EVENT_CONSTRAINT(0x52, 0x3), /* L1D_CACHE_PREFETCH_LOCK_FB_HIT */ - EVENT_CONSTRAINT(0x53, 0x3), /* L1D_CACHE_LOCK_FB_HIT */ - EVENT_CONSTRAINT(0xc5, 0x3), /* CACHE_LOCK_CYCLES */ - EVENT_CONSTRAINT_END -}; - -static u64 intel_pmu_event_map(int hw_event) -{ - return intel_perfmon_event_map[hw_event]; -} +static int x86_perf_event_set_period(struct perf_event *event, + struct hw_perf_event *hwc, int idx); /* * Generalized hw caching related hw_event table, filled @@ -245,424 +183,6 @@ static u64 __read_mostly hw_cache_event_ids [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; -static __initconst u64 nehalem_hw_cache_event_ids - [PERF_COUNT_HW_CACHE_MAX] - [PERF_COUNT_HW_CACHE_OP_MAX] - [PERF_COUNT_HW_CACHE_RESULT_MAX] = -{ - [ C(L1D) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI */ - [ C(RESULT_MISS) ] = 0x0140, /* L1D_CACHE_LD.I_STATE */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI */ - [ C(RESULT_MISS) ] = 0x0141, /* L1D_CACHE_ST.I_STATE */ - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS */ - [ C(RESULT_MISS) ] = 0x024e, /* L1D_PREFETCH.MISS */ - }, - }, - [ C(L1I ) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS */ - [ C(RESULT_MISS) ] = 0x0280, /* L1I.MISSES */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0x0, - [ C(RESULT_MISS) ] = 0x0, - }, - }, - [ C(LL ) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */ - [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */ - [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */ - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */ - [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */ - }, - }, - [ C(DTLB) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI (alias) */ - [ C(RESULT_MISS) ] = 0x0108, /* DTLB_LOAD_MISSES.ANY */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI (alias) */ - [ C(RESULT_MISS) ] = 0x010c, /* MEM_STORE_RETIRED.DTLB_MISS */ - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0x0, - [ C(RESULT_MISS) ] = 0x0, - }, - }, - [ C(ITLB) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x01c0, /* INST_RETIRED.ANY_P */ - [ C(RESULT_MISS) ] = 0x20c8, /* ITLB_MISS_RETIRED */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - }, - [ C(BPU ) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */ - [ C(RESULT_MISS) ] = 0x03e8, /* BPU_CLEARS.ANY */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - }, -}; - -static __initconst u64 core2_hw_cache_event_ids - [PERF_COUNT_HW_CACHE_MAX] - [PERF_COUNT_HW_CACHE_OP_MAX] - [PERF_COUNT_HW_CACHE_RESULT_MAX] = -{ - [ C(L1D) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI */ - [ C(RESULT_MISS) ] = 0x0140, /* L1D_CACHE_LD.I_STATE */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI */ - [ C(RESULT_MISS) ] = 0x0141, /* L1D_CACHE_ST.I_STATE */ - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0x104e, /* L1D_PREFETCH.REQUESTS */ - [ C(RESULT_MISS) ] = 0, - }, - }, - [ C(L1I ) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0080, /* L1I.READS */ - [ C(RESULT_MISS) ] = 0x0081, /* L1I.MISSES */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0, - [ C(RESULT_MISS) ] = 0, - }, - }, - [ C(LL ) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI */ - [ C(RESULT_MISS) ] = 0x4129, /* L2_LD.ISTATE */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI */ - [ C(RESULT_MISS) ] = 0x412A, /* L2_ST.ISTATE */ - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0, - [ C(RESULT_MISS) ] = 0, - }, - }, - [ C(DTLB) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI (alias) */ - [ C(RESULT_MISS) ] = 0x0208, /* DTLB_MISSES.MISS_LD */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI (alias) */ - [ C(RESULT_MISS) ] = 0x0808, /* DTLB_MISSES.MISS_ST */ - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0, - [ C(RESULT_MISS) ] = 0, - }, - }, - [ C(ITLB) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */ - [ C(RESULT_MISS) ] = 0x1282, /* ITLBMISSES */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - }, - [ C(BPU ) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY */ - [ C(RESULT_MISS) ] = 0x00c5, /* BP_INST_RETIRED.MISPRED */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - }, -}; - -static __initconst u64 atom_hw_cache_event_ids - [PERF_COUNT_HW_CACHE_MAX] - [PERF_COUNT_HW_CACHE_OP_MAX] - [PERF_COUNT_HW_CACHE_RESULT_MAX] = -{ - [ C(L1D) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE.LD */ - [ C(RESULT_MISS) ] = 0, - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE.ST */ - [ C(RESULT_MISS) ] = 0, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0x0, - [ C(RESULT_MISS) ] = 0, - }, - }, - [ C(L1I ) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS */ - [ C(RESULT_MISS) ] = 0x0280, /* L1I.MISSES */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0, - [ C(RESULT_MISS) ] = 0, - }, - }, - [ C(LL ) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI */ - [ C(RESULT_MISS) ] = 0x4129, /* L2_LD.ISTATE */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI */ - [ C(RESULT_MISS) ] = 0x412A, /* L2_ST.ISTATE */ - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0, - [ C(RESULT_MISS) ] = 0, - }, - }, - [ C(DTLB) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE_LD.MESI (alias) */ - [ C(RESULT_MISS) ] = 0x0508, /* DTLB_MISSES.MISS_LD */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE_ST.MESI (alias) */ - [ C(RESULT_MISS) ] = 0x0608, /* DTLB_MISSES.MISS_ST */ - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0, - [ C(RESULT_MISS) ] = 0, - }, - }, - [ C(ITLB) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */ - [ C(RESULT_MISS) ] = 0x0282, /* ITLB.MISSES */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - }, - [ C(BPU ) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY */ - [ C(RESULT_MISS) ] = 0x00c5, /* BP_INST_RETIRED.MISPRED */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - }, -}; - -static u64 intel_pmu_raw_event(u64 hw_event) -{ -#define CORE_EVNTSEL_EVENT_MASK 0x000000FFULL -#define CORE_EVNTSEL_UNIT_MASK 0x0000FF00ULL -#define CORE_EVNTSEL_EDGE_MASK 0x00040000ULL -#define CORE_EVNTSEL_INV_MASK 0x00800000ULL -#define CORE_EVNTSEL_REG_MASK 0xFF000000ULL - -#define CORE_EVNTSEL_MASK \ - (CORE_EVNTSEL_EVENT_MASK | \ - CORE_EVNTSEL_UNIT_MASK | \ - CORE_EVNTSEL_EDGE_MASK | \ - CORE_EVNTSEL_INV_MASK | \ - CORE_EVNTSEL_REG_MASK) - - return hw_event & CORE_EVNTSEL_MASK; -} - -static __initconst u64 amd_hw_cache_event_ids - [PERF_COUNT_HW_CACHE_MAX] - [PERF_COUNT_HW_CACHE_OP_MAX] - [PERF_COUNT_HW_CACHE_RESULT_MAX] = -{ - [ C(L1D) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses */ - [ C(RESULT_MISS) ] = 0x0041, /* Data Cache Misses */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */ - [ C(RESULT_MISS) ] = 0, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0x0267, /* Data Prefetcher :attempts */ - [ C(RESULT_MISS) ] = 0x0167, /* Data Prefetcher :cancelled */ - }, - }, - [ C(L1I ) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0080, /* Instruction cache fetches */ - [ C(RESULT_MISS) ] = 0x0081, /* Instruction cache misses */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0x014B, /* Prefetch Instructions :Load */ - [ C(RESULT_MISS) ] = 0, - }, - }, - [ C(LL ) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x037D, /* Requests to L2 Cache :IC+DC */ - [ C(RESULT_MISS) ] = 0x037E, /* L2 Cache Misses : IC+DC */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x017F, /* L2 Fill/Writeback */ - [ C(RESULT_MISS) ] = 0, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0, - [ C(RESULT_MISS) ] = 0, - }, - }, - [ C(DTLB) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses */ - [ C(RESULT_MISS) ] = 0x0046, /* L1 DTLB and L2 DLTB Miss */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0, - [ C(RESULT_MISS) ] = 0, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0, - [ C(RESULT_MISS) ] = 0, - }, - }, - [ C(ITLB) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0080, /* Instruction fecthes */ - [ C(RESULT_MISS) ] = 0x0085, /* Instr. fetch ITLB misses */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - }, - [ C(BPU ) ] = { - [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x00c2, /* Retired Branch Instr. */ - [ C(RESULT_MISS) ] = 0x00c3, /* Retired Mispredicted BI */ - }, - [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = -1, - [ C(RESULT_MISS) ] = -1, - }, - }, -}; - -/* - * AMD Performance Monitor K7 and later. - */ -static const u64 amd_perfmon_event_map[] = -{ - [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, - [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, - [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0080, - [PERF_COUNT_HW_CACHE_MISSES] = 0x0081, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, - [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, -}; - -static u64 amd_pmu_event_map(int hw_event) -{ - return amd_perfmon_event_map[hw_event]; -} - -static u64 amd_pmu_raw_event(u64 hw_event) -{ -#define K7_EVNTSEL_EVENT_MASK 0x7000000FFULL -#define K7_EVNTSEL_UNIT_MASK 0x00000FF00ULL -#define K7_EVNTSEL_EDGE_MASK 0x000040000ULL -#define K7_EVNTSEL_INV_MASK 0x000800000ULL -#define K7_EVNTSEL_REG_MASK 0x0FF000000ULL - -#define K7_EVNTSEL_MASK \ - (K7_EVNTSEL_EVENT_MASK | \ - K7_EVNTSEL_UNIT_MASK | \ - K7_EVNTSEL_EDGE_MASK | \ - K7_EVNTSEL_INV_MASK | \ - K7_EVNTSEL_REG_MASK) - - return hw_event & K7_EVNTSEL_MASK; -} - /* * Propagate event elapsed time into the generic event. * Can only be executed on the CPU where the event is active. @@ -914,42 +434,6 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr) return 0; } -static void intel_pmu_enable_bts(u64 config) -{ - unsigned long debugctlmsr; - - debugctlmsr = get_debugctlmsr(); - - debugctlmsr |= X86_DEBUGCTL_TR; - debugctlmsr |= X86_DEBUGCTL_BTS; - debugctlmsr |= X86_DEBUGCTL_BTINT; - - if (!(config & ARCH_PERFMON_EVENTSEL_OS)) - debugctlmsr |= X86_DEBUGCTL_BTS_OFF_OS; - - if (!(config & ARCH_PERFMON_EVENTSEL_USR)) - debugctlmsr |= X86_DEBUGCTL_BTS_OFF_USR; - - update_debugctlmsr(debugctlmsr); -} - -static void intel_pmu_disable_bts(void) -{ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - unsigned long debugctlmsr; - - if (!cpuc->ds) - return; - - debugctlmsr = get_debugctlmsr(); - - debugctlmsr &= - ~(X86_DEBUGCTL_TR | X86_DEBUGCTL_BTS | X86_DEBUGCTL_BTINT | - X86_DEBUGCTL_BTS_OFF_OS | X86_DEBUGCTL_BTS_OFF_USR); - - update_debugctlmsr(debugctlmsr); -} - /* * Setup the hardware configuration for a given attr_type */ @@ -988,6 +472,8 @@ static int __hw_perf_event_init(struct perf_event *event) hwc->config = ARCH_PERFMON_EVENTSEL_INT; hwc->idx = -1; + hwc->last_cpu = -1; + hwc->last_tag = ~0ULL; /* * Count user and OS events unless requested not to. @@ -1056,216 +542,323 @@ static int __hw_perf_event_init(struct perf_event *event) return 0; } -static void p6_pmu_disable_all(void) +static void x86_pmu_disable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - u64 val; - - if (!cpuc->enabled) - return; + int idx; - cpuc->enabled = 0; - barrier(); + for (idx = 0; idx < x86_pmu.num_events; idx++) { + u64 val; - /* p6 only has one enable register */ - rdmsrl(MSR_P6_EVNTSEL0, val); - val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE; - wrmsrl(MSR_P6_EVNTSEL0, val); + if (!test_bit(idx, cpuc->active_mask)) + continue; + rdmsrl(x86_pmu.eventsel + idx, val); + if (!(val & ARCH_PERFMON_EVENTSEL0_ENABLE)) + continue; + val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE; + wrmsrl(x86_pmu.eventsel + idx, val); + } } -static void intel_pmu_disable_all(void) +void hw_perf_disable(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + if (!x86_pmu_initialized()) + return; + if (!cpuc->enabled) return; + cpuc->n_added = 0; cpuc->enabled = 0; barrier(); - wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0); - - if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) - intel_pmu_disable_bts(); + x86_pmu.disable_all(); } -static void amd_pmu_disable_all(void) +static void x86_pmu_enable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int idx; - if (!cpuc->enabled) - return; - - cpuc->enabled = 0; - /* - * ensure we write the disable before we start disabling the - * events proper, so that amd_pmu_enable_event() does the - * right thing. - */ - barrier(); - for (idx = 0; idx < x86_pmu.num_events; idx++) { + struct perf_event *event = cpuc->events[idx]; u64 val; if (!test_bit(idx, cpuc->active_mask)) continue; - rdmsrl(MSR_K7_EVNTSEL0 + idx, val); - if (!(val & ARCH_PERFMON_EVENTSEL0_ENABLE)) - continue; - val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE; - wrmsrl(MSR_K7_EVNTSEL0 + idx, val); + + val = event->hw.config; + val |= ARCH_PERFMON_EVENTSEL0_ENABLE; + wrmsrl(x86_pmu.eventsel + idx, val); } } -void hw_perf_disable(void) +static const struct pmu pmu; + +static inline int is_x86_event(struct perf_event *event) { - if (!x86_pmu_initialized()) - return; - return x86_pmu.disable_all(); + return event->pmu == &pmu; } -static void p6_pmu_enable_all(void) +static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - unsigned long val; + struct event_constraint *c, *constraints[X86_PMC_IDX_MAX]; + unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + int i, j, w, wmax, num = 0; + struct hw_perf_event *hwc; - if (cpuc->enabled) - return; + bitmap_zero(used_mask, X86_PMC_IDX_MAX); - cpuc->enabled = 1; - barrier(); + for (i = 0; i < n; i++) { + constraints[i] = + x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]); + } - /* p6 only has one enable register */ - rdmsrl(MSR_P6_EVNTSEL0, val); - val |= ARCH_PERFMON_EVENTSEL0_ENABLE; - wrmsrl(MSR_P6_EVNTSEL0, val); -} + /* + * fastpath, try to reuse previous register + */ + for (i = 0; i < n; i++) { + hwc = &cpuc->event_list[i]->hw; + c = constraints[i]; -static void intel_pmu_enable_all(void) -{ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + /* never assigned */ + if (hwc->idx == -1) + break; - if (cpuc->enabled) - return; + /* constraint still honored */ + if (!test_bit(hwc->idx, c->idxmsk)) + break; - cpuc->enabled = 1; - barrier(); + /* not already used */ + if (test_bit(hwc->idx, used_mask)) + break; + + set_bit(hwc->idx, used_mask); + if (assign) + assign[i] = hwc->idx; + } + if (i == n) + goto done; - wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl); + /* + * begin slow path + */ + + bitmap_zero(used_mask, X86_PMC_IDX_MAX); + + /* + * weight = number of possible counters + * + * 1 = most constrained, only works on one counter + * wmax = least constrained, works on any counter + * + * assign events to counters starting with most + * constrained events. + */ + wmax = x86_pmu.num_events; + + /* + * when fixed event counters are present, + * wmax is incremented by 1 to account + * for one more choice + */ + if (x86_pmu.num_events_fixed) + wmax++; - if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) { - struct perf_event *event = - cpuc->events[X86_PMC_IDX_FIXED_BTS]; + for (w = 1, num = n; num && w <= wmax; w++) { + /* for each event */ + for (i = 0; num && i < n; i++) { + c = constraints[i]; + hwc = &cpuc->event_list[i]->hw; - if (WARN_ON_ONCE(!event)) - return; + if (c->weight != w) + continue; - intel_pmu_enable_bts(event->hw.config); + for_each_bit(j, c->idxmsk, X86_PMC_IDX_MAX) { + if (!test_bit(j, used_mask)) + break; + } + + if (j == X86_PMC_IDX_MAX) + break; + + set_bit(j, used_mask); + + if (assign) + assign[i] = j; + num--; + } + } +done: + /* + * scheduling failed or is just a simulation, + * free resources if necessary + */ + if (!assign || num) { + for (i = 0; i < n; i++) { + if (x86_pmu.put_event_constraints) + x86_pmu.put_event_constraints(cpuc, cpuc->event_list[i]); + } } + return num ? -ENOSPC : 0; } -static void amd_pmu_enable_all(void) +/* + * dogrp: true if must collect siblings events (group) + * returns total number of events and error code + */ +static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, bool dogrp) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - int idx; + struct perf_event *event; + int n, max_count; - if (cpuc->enabled) - return; + max_count = x86_pmu.num_events + x86_pmu.num_events_fixed; - cpuc->enabled = 1; - barrier(); + /* current number of events already accepted */ + n = cpuc->n_events; - for (idx = 0; idx < x86_pmu.num_events; idx++) { - struct perf_event *event = cpuc->events[idx]; - u64 val; + if (is_x86_event(leader)) { + if (n >= max_count) + return -ENOSPC; + cpuc->event_list[n] = leader; + n++; + } + if (!dogrp) + return n; - if (!test_bit(idx, cpuc->active_mask)) + list_for_each_entry(event, &leader->sibling_list, group_entry) { + if (!is_x86_event(event) || + event->state <= PERF_EVENT_STATE_OFF) continue; - val = event->hw.config; - val |= ARCH_PERFMON_EVENTSEL0_ENABLE; - wrmsrl(MSR_K7_EVNTSEL0 + idx, val); - } -} + if (n >= max_count) + return -ENOSPC; -void hw_perf_enable(void) -{ - if (!x86_pmu_initialized()) - return; - x86_pmu.enable_all(); + cpuc->event_list[n] = event; + n++; + } + return n; } -static inline u64 intel_pmu_get_status(void) +static inline void x86_assign_hw_event(struct perf_event *event, + struct cpu_hw_events *cpuc, int i) { - u64 status; + struct hw_perf_event *hwc = &event->hw; - rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status); + hwc->idx = cpuc->assign[i]; + hwc->last_cpu = smp_processor_id(); + hwc->last_tag = ++cpuc->tags[i]; - return status; + if (hwc->idx == X86_PMC_IDX_FIXED_BTS) { + hwc->config_base = 0; + hwc->event_base = 0; + } else if (hwc->idx >= X86_PMC_IDX_FIXED) { + hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL; + /* + * We set it so that event_base + idx in wrmsr/rdmsr maps to + * MSR_ARCH_PERFMON_FIXED_CTR0 ... CTR2: + */ + hwc->event_base = + MSR_ARCH_PERFMON_FIXED_CTR0 - X86_PMC_IDX_FIXED; + } else { + hwc->config_base = x86_pmu.eventsel; + hwc->event_base = x86_pmu.perfctr; + } } -static inline void intel_pmu_ack_status(u64 ack) +static inline int match_prev_assignment(struct hw_perf_event *hwc, + struct cpu_hw_events *cpuc, + int i) { - wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack); + return hwc->idx == cpuc->assign[i] && + hwc->last_cpu == smp_processor_id() && + hwc->last_tag == cpuc->tags[i]; } -static inline void x86_pmu_enable_event(struct hw_perf_event *hwc, int idx) -{ - (void)checking_wrmsrl(hwc->config_base + idx, - hwc->config | ARCH_PERFMON_EVENTSEL0_ENABLE); -} +static void x86_pmu_stop(struct perf_event *event); -static inline void x86_pmu_disable_event(struct hw_perf_event *hwc, int idx) +void hw_perf_enable(void) { - (void)checking_wrmsrl(hwc->config_base + idx, hwc->config); -} + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct perf_event *event; + struct hw_perf_event *hwc; + int i; -static inline void -intel_pmu_disable_fixed(struct hw_perf_event *hwc, int __idx) -{ - int idx = __idx - X86_PMC_IDX_FIXED; - u64 ctrl_val, mask; + if (!x86_pmu_initialized()) + return; - mask = 0xfULL << (idx * 4); + if (cpuc->enabled) + return; - rdmsrl(hwc->config_base, ctrl_val); - ctrl_val &= ~mask; - (void)checking_wrmsrl(hwc->config_base, ctrl_val); -} + if (cpuc->n_added) { + /* + * apply assignment obtained either from + * hw_perf_group_sched_in() or x86_pmu_enable() + * + * step1: save events moving to new counters + * step2: reprogram moved events into new counters + */ + for (i = 0; i < cpuc->n_events; i++) { -static inline void -p6_pmu_disable_event(struct hw_perf_event *hwc, int idx) -{ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - u64 val = P6_NOP_EVENT; + event = cpuc->event_list[i]; + hwc = &event->hw; - if (cpuc->enabled) - val |= ARCH_PERFMON_EVENTSEL0_ENABLE; + /* + * we can avoid reprogramming counter if: + * - assigned same counter as last time + * - running on same CPU as last time + * - no other event has used the counter since + */ + if (hwc->idx == -1 || + match_prev_assignment(hwc, cpuc, i)) + continue; - (void)checking_wrmsrl(hwc->config_base + idx, val); -} + x86_pmu_stop(event); -static inline void -intel_pmu_disable_event(struct hw_perf_event *hwc, int idx) -{ - if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) { - intel_pmu_disable_bts(); - return; - } + hwc->idx = -1; + } - if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { - intel_pmu_disable_fixed(hwc, idx); - return; + for (i = 0; i < cpuc->n_events; i++) { + + event = cpuc->event_list[i]; + hwc = &event->hw; + + if (hwc->idx == -1) { + x86_assign_hw_event(event, cpuc, i); + x86_perf_event_set_period(event, hwc, hwc->idx); + } + /* + * need to mark as active because x86_pmu_disable() + * clear active_mask and events[] yet it preserves + * idx + */ + set_bit(hwc->idx, cpuc->active_mask); + cpuc->events[hwc->idx] = event; + + x86_pmu.enable(hwc, hwc->idx); + perf_event_update_userpage(event); + } + cpuc->n_added = 0; + perf_events_lapic_init(); } - x86_pmu_disable_event(hwc, idx); + cpuc->enabled = 1; + barrier(); + + x86_pmu.enable_all(); } -static inline void -amd_pmu_disable_event(struct hw_perf_event *hwc, int idx) +static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, int idx) { - x86_pmu_disable_event(hwc, idx); + (void)checking_wrmsrl(hwc->config_base + idx, + hwc->config | ARCH_PERFMON_EVENTSEL0_ENABLE); +} + +static inline void x86_pmu_disable_event(struct hw_perf_event *hwc, int idx) +{ + (void)checking_wrmsrl(hwc->config_base + idx, hwc->config); } static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); @@ -1326,213 +919,60 @@ x86_perf_event_set_period(struct perf_event *event, return ret; } -static inline void -intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx) -{ - int idx = __idx - X86_PMC_IDX_FIXED; - u64 ctrl_val, bits, mask; - int err; - - /* - * Enable IRQ generation (0x8), - * and enable ring-3 counting (0x2) and ring-0 counting (0x1) - * if requested: - */ - bits = 0x8ULL; - if (hwc->config & ARCH_PERFMON_EVENTSEL_USR) - bits |= 0x2; - if (hwc->config & ARCH_PERFMON_EVENTSEL_OS) - bits |= 0x1; - bits <<= (idx * 4); - mask = 0xfULL << (idx * 4); - - rdmsrl(hwc->config_base, ctrl_val); - ctrl_val &= ~mask; - ctrl_val |= bits; - err = checking_wrmsrl(hwc->config_base, ctrl_val); -} - -static void p6_pmu_enable_event(struct hw_perf_event *hwc, int idx) +static void x86_pmu_enable_event(struct hw_perf_event *hwc, int idx) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - u64 val; - - val = hwc->config; if (cpuc->enabled) - val |= ARCH_PERFMON_EVENTSEL0_ENABLE; - - (void)checking_wrmsrl(hwc->config_base + idx, val); + __x86_pmu_enable_event(hwc, idx); } - -static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx) -{ - if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) { - if (!__get_cpu_var(cpu_hw_events).enabled) - return; - - intel_pmu_enable_bts(hwc->config); - return; - } - - if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { - intel_pmu_enable_fixed(hwc, idx); - return; - } - - x86_pmu_enable_event(hwc, idx); -} - -static void amd_pmu_enable_event(struct hw_perf_event *hwc, int idx) +/* + * activate a single event + * + * The event is added to the group of enabled events + * but only if it can be scehduled with existing events. + * + * Called with PMU disabled. If successful and return value 1, + * then guaranteed to call perf_enable() and hw_perf_enable() + */ +static int x86_pmu_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc; + int assign[X86_PMC_IDX_MAX]; + int n, n0, ret; - if (cpuc->enabled) - x86_pmu_enable_event(hwc, idx); -} - -static int fixed_mode_idx(struct hw_perf_event *hwc) -{ - unsigned int hw_event; - - hw_event = hwc->config & ARCH_PERFMON_EVENT_MASK; - - if (unlikely((hw_event == - x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)) && - (hwc->sample_period == 1))) - return X86_PMC_IDX_FIXED_BTS; + hwc = &event->hw; - if (!x86_pmu.num_events_fixed) - return -1; + n0 = cpuc->n_events; + n = collect_events(cpuc, event, false); + if (n < 0) + return n; + ret = x86_schedule_events(cpuc, n, assign); + if (ret) + return ret; /* - * fixed counters do not take all possible filters + * copy new assignment, now we know it is possible + * will be used by hw_perf_enable() */ - if (hwc->config & ARCH_PERFMON_EVENT_FILTER_MASK) - return -1; - - if (unlikely(hw_event == x86_pmu.event_map(PERF_COUNT_HW_INSTRUCTIONS))) - return X86_PMC_IDX_FIXED_INSTRUCTIONS; - if (unlikely(hw_event == x86_pmu.event_map(PERF_COUNT_HW_CPU_CYCLES))) - return X86_PMC_IDX_FIXED_CPU_CYCLES; - if (unlikely(hw_event == x86_pmu.event_map(PERF_COUNT_HW_BUS_CYCLES))) - return X86_PMC_IDX_FIXED_BUS_CYCLES; + memcpy(cpuc->assign, assign, n*sizeof(int)); - return -1; -} + cpuc->n_events = n; + cpuc->n_added = n - n0; -/* - * generic counter allocator: get next free counter - */ -static int -gen_get_event_idx(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc) -{ - int idx; - - idx = find_first_zero_bit(cpuc->used_mask, x86_pmu.num_events); - return idx == x86_pmu.num_events ? -1 : idx; -} - -/* - * intel-specific counter allocator: check event constraints - */ -static int -intel_get_event_idx(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc) -{ - const struct event_constraint *event_constraint; - int i, code; - - if (!event_constraints) - goto skip; - - code = hwc->config & CORE_EVNTSEL_EVENT_MASK; - - for_each_event_constraint(event_constraint, event_constraints) { - if (code == event_constraint->code) { - for_each_bit(i, event_constraint->idxmsk, X86_PMC_IDX_MAX) { - if (!test_and_set_bit(i, cpuc->used_mask)) - return i; - } - return -1; - } - } -skip: - return gen_get_event_idx(cpuc, hwc); -} - -static int -x86_schedule_event(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc) -{ - int idx; - - idx = fixed_mode_idx(hwc); - if (idx == X86_PMC_IDX_FIXED_BTS) { - /* BTS is already occupied. */ - if (test_and_set_bit(idx, cpuc->used_mask)) - return -EAGAIN; - - hwc->config_base = 0; - hwc->event_base = 0; - hwc->idx = idx; - } else if (idx >= 0) { - /* - * Try to get the fixed event, if that is already taken - * then try to get a generic event: - */ - if (test_and_set_bit(idx, cpuc->used_mask)) - goto try_generic; - - hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL; - /* - * We set it so that event_base + idx in wrmsr/rdmsr maps to - * MSR_ARCH_PERFMON_FIXED_CTR0 ... CTR2: - */ - hwc->event_base = - MSR_ARCH_PERFMON_FIXED_CTR0 - X86_PMC_IDX_FIXED; - hwc->idx = idx; - } else { - idx = hwc->idx; - /* Try to get the previous generic event again */ - if (idx == -1 || test_and_set_bit(idx, cpuc->used_mask)) { -try_generic: - idx = x86_pmu.get_event_idx(cpuc, hwc); - if (idx == -1) - return -EAGAIN; - - set_bit(idx, cpuc->used_mask); - hwc->idx = idx; - } - hwc->config_base = x86_pmu.eventsel; - hwc->event_base = x86_pmu.perfctr; - } - - return idx; + return 0; } -/* - * Find a PMC slot for the freshly enabled / scheduled in event: - */ -static int x86_pmu_enable(struct perf_event *event) +static int x86_pmu_start(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - int idx; - idx = x86_schedule_event(cpuc, hwc); - if (idx < 0) - return idx; + if (hwc->idx == -1) + return -EAGAIN; - perf_events_lapic_init(); - - x86_pmu.disable(hwc, idx); - - cpuc->events[idx] = event; - set_bit(idx, cpuc->active_mask); - - x86_perf_event_set_period(event, hwc, idx); - x86_pmu.enable(hwc, idx); - - perf_event_update_userpage(event); + x86_perf_event_set_period(event, hwc, hwc->idx); + x86_pmu.enable(hwc, hwc->idx); return 0; } @@ -1576,7 +1016,7 @@ void perf_event_print_debug(void) pr_info("CPU#%d: overflow: %016llx\n", cpu, overflow); pr_info("CPU#%d: fixed: %016llx\n", cpu, fixed); } - pr_info("CPU#%d: used: %016llx\n", cpu, *(u64 *)cpuc->used_mask); + pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask); for (idx = 0; idx < x86_pmu.num_events; idx++) { rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl); @@ -1600,67 +1040,7 @@ void perf_event_print_debug(void) local_irq_restore(flags); } -static void intel_pmu_drain_bts_buffer(struct cpu_hw_events *cpuc) -{ - struct debug_store *ds = cpuc->ds; - struct bts_record { - u64 from; - u64 to; - u64 flags; - }; - struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS]; - struct bts_record *at, *top; - struct perf_output_handle handle; - struct perf_event_header header; - struct perf_sample_data data; - struct pt_regs regs; - - if (!event) - return; - - if (!ds) - return; - - at = (struct bts_record *)(unsigned long)ds->bts_buffer_base; - top = (struct bts_record *)(unsigned long)ds->bts_index; - - if (top <= at) - return; - - ds->bts_index = ds->bts_buffer_base; - - - data.period = event->hw.last_period; - data.addr = 0; - data.raw = NULL; - regs.ip = 0; - - /* - * Prepare a generic sample, i.e. fill in the invariant fields. - * We will overwrite the from and to address before we output - * the sample. - */ - perf_prepare_sample(&header, &data, event, ®s); - - if (perf_output_begin(&handle, event, - header.size * (top - at), 1, 1)) - return; - - for (; at < top; at++) { - data.ip = at->from; - data.addr = at->to; - - perf_output_sample(&handle, &header, &data, event); - } - - perf_output_end(&handle); - - /* There's new data available. */ - event->hw.interrupts++; - event->pending_kill = POLL_IN; -} - -static void x86_pmu_disable(struct perf_event *event) +static void x86_pmu_stop(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; @@ -1674,183 +1054,38 @@ static void x86_pmu_disable(struct perf_event *event) x86_pmu.disable(hwc, idx); /* - * Make sure the cleared pointer becomes visible before we - * (potentially) free the event: - */ - barrier(); - - /* * Drain the remaining delta count out of a event * that we are disabling: */ x86_perf_event_update(event, hwc, idx); - /* Drain the remaining BTS records. */ - if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) - intel_pmu_drain_bts_buffer(cpuc); - cpuc->events[idx] = NULL; - clear_bit(idx, cpuc->used_mask); - - perf_event_update_userpage(event); -} - -/* - * Save and restart an expired event. Called by NMI contexts, - * so it has to be careful about preempting normal event ops: - */ -static int intel_pmu_save_and_restart(struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - int idx = hwc->idx; - int ret; - - x86_perf_event_update(event, hwc, idx); - ret = x86_perf_event_set_period(event, hwc, idx); - - if (event->state == PERF_EVENT_STATE_ACTIVE) - intel_pmu_enable_event(hwc, idx); - - return ret; -} - -static void intel_pmu_reset(void) -{ - struct debug_store *ds = __get_cpu_var(cpu_hw_events).ds; - unsigned long flags; - int idx; - - if (!x86_pmu.num_events) - return; - - local_irq_save(flags); - - printk("clearing PMU state on CPU#%d\n", smp_processor_id()); - - for (idx = 0; idx < x86_pmu.num_events; idx++) { - checking_wrmsrl(x86_pmu.eventsel + idx, 0ull); - checking_wrmsrl(x86_pmu.perfctr + idx, 0ull); - } - for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) { - checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull); - } - if (ds) - ds->bts_index = ds->bts_buffer_base; - - local_irq_restore(flags); -} - -static int p6_pmu_handle_irq(struct pt_regs *regs) -{ - struct perf_sample_data data; - struct cpu_hw_events *cpuc; - struct perf_event *event; - struct hw_perf_event *hwc; - int idx, handled = 0; - u64 val; - - data.addr = 0; - data.raw = NULL; - - cpuc = &__get_cpu_var(cpu_hw_events); - - for (idx = 0; idx < x86_pmu.num_events; idx++) { - if (!test_bit(idx, cpuc->active_mask)) - continue; - - event = cpuc->events[idx]; - hwc = &event->hw; - - val = x86_perf_event_update(event, hwc, idx); - if (val & (1ULL << (x86_pmu.event_bits - 1))) - continue; - - /* - * event overflow - */ - handled = 1; - data.period = event->hw.last_period; - - if (!x86_perf_event_set_period(event, hwc, idx)) - continue; - - if (perf_event_overflow(event, 1, &data, regs)) - p6_pmu_disable_event(hwc, idx); - } - - if (handled) - inc_irq_stat(apic_perf_irqs); - - return handled; } -/* - * This handler is triggered by the local APIC, so the APIC IRQ handling - * rules apply: - */ -static int intel_pmu_handle_irq(struct pt_regs *regs) +static void x86_pmu_disable(struct perf_event *event) { - struct perf_sample_data data; - struct cpu_hw_events *cpuc; - int bit, loops; - u64 ack, status; - - data.addr = 0; - data.raw = NULL; - - cpuc = &__get_cpu_var(cpu_hw_events); - - perf_disable(); - intel_pmu_drain_bts_buffer(cpuc); - status = intel_pmu_get_status(); - if (!status) { - perf_enable(); - return 0; - } - - loops = 0; -again: - if (++loops > 100) { - WARN_ONCE(1, "perfevents: irq loop stuck!\n"); - perf_event_print_debug(); - intel_pmu_reset(); - perf_enable(); - return 1; - } + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int i; - inc_irq_stat(apic_perf_irqs); - ack = status; - for_each_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) { - struct perf_event *event = cpuc->events[bit]; + x86_pmu_stop(event); - clear_bit(bit, (unsigned long *) &status); - if (!test_bit(bit, cpuc->active_mask)) - continue; + for (i = 0; i < cpuc->n_events; i++) { + if (event == cpuc->event_list[i]) { - if (!intel_pmu_save_and_restart(event)) - continue; + if (x86_pmu.put_event_constraints) + x86_pmu.put_event_constraints(cpuc, event); - data.period = event->hw.last_period; + while (++i < cpuc->n_events) + cpuc->event_list[i-1] = cpuc->event_list[i]; - if (perf_event_overflow(event, 1, &data, regs)) - intel_pmu_disable_event(&event->hw, bit); + --cpuc->n_events; + break; + } } - - intel_pmu_ack_status(ack); - - /* - * Repeat if there is more work to be done: - */ - status = intel_pmu_get_status(); - if (status) - goto again; - - perf_enable(); - - return 1; + perf_event_update_userpage(event); } -static int amd_pmu_handle_irq(struct pt_regs *regs) +static int x86_pmu_handle_irq(struct pt_regs *regs) { struct perf_sample_data data; struct cpu_hw_events *cpuc; @@ -1885,7 +1120,7 @@ static int amd_pmu_handle_irq(struct pt_regs *regs) continue; if (perf_event_overflow(event, 1, &data, regs)) - amd_pmu_disable_event(hwc, idx); + x86_pmu.disable(hwc, idx); } if (handled) @@ -1968,194 +1203,137 @@ static __read_mostly struct notifier_block perf_event_nmi_notifier = { .priority = 1 }; -static __initconst struct x86_pmu p6_pmu = { - .name = "p6", - .handle_irq = p6_pmu_handle_irq, - .disable_all = p6_pmu_disable_all, - .enable_all = p6_pmu_enable_all, - .enable = p6_pmu_enable_event, - .disable = p6_pmu_disable_event, - .eventsel = MSR_P6_EVNTSEL0, - .perfctr = MSR_P6_PERFCTR0, - .event_map = p6_pmu_event_map, - .raw_event = p6_pmu_raw_event, - .max_events = ARRAY_SIZE(p6_perfmon_event_map), - .apic = 1, - .max_period = (1ULL << 31) - 1, - .version = 0, - .num_events = 2, - /* - * Events have 40 bits implemented. However they are designed such - * that bits [32-39] are sign extensions of bit 31. As such the - * effective width of a event for P6-like PMU is 32 bits only. - * - * See IA-32 Intel Architecture Software developer manual Vol 3B - */ - .event_bits = 32, - .event_mask = (1ULL << 32) - 1, - .get_event_idx = intel_get_event_idx, -}; +static struct event_constraint unconstrained; +static struct event_constraint emptyconstraint; -static __initconst struct x86_pmu intel_pmu = { - .name = "Intel", - .handle_irq = intel_pmu_handle_irq, - .disable_all = intel_pmu_disable_all, - .enable_all = intel_pmu_enable_all, - .enable = intel_pmu_enable_event, - .disable = intel_pmu_disable_event, - .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, - .perfctr = MSR_ARCH_PERFMON_PERFCTR0, - .event_map = intel_pmu_event_map, - .raw_event = intel_pmu_raw_event, - .max_events = ARRAY_SIZE(intel_perfmon_event_map), - .apic = 1, - /* - * Intel PMCs cannot be accessed sanely above 32 bit width, - * so we install an artificial 1<<31 period regardless of - * the generic event period: - */ - .max_period = (1ULL << 31) - 1, - .enable_bts = intel_pmu_enable_bts, - .disable_bts = intel_pmu_disable_bts, - .get_event_idx = intel_get_event_idx, -}; +static struct event_constraint * +x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + struct event_constraint *c; -static __initconst struct x86_pmu amd_pmu = { - .name = "AMD", - .handle_irq = amd_pmu_handle_irq, - .disable_all = amd_pmu_disable_all, - .enable_all = amd_pmu_enable_all, - .enable = amd_pmu_enable_event, - .disable = amd_pmu_disable_event, - .eventsel = MSR_K7_EVNTSEL0, - .perfctr = MSR_K7_PERFCTR0, - .event_map = amd_pmu_event_map, - .raw_event = amd_pmu_raw_event, - .max_events = ARRAY_SIZE(amd_perfmon_event_map), - .num_events = 4, - .event_bits = 48, - .event_mask = (1ULL << 48) - 1, - .apic = 1, - /* use highest bit to detect overflow */ - .max_period = (1ULL << 47) - 1, - .get_event_idx = gen_get_event_idx, -}; + if (x86_pmu.event_constraints) { + for_each_event_constraint(c, x86_pmu.event_constraints) { + if ((event->hw.config & c->cmask) == c->code) + return c; + } + } + + return &unconstrained; +} -static __init int p6_pmu_init(void) +static int x86_event_sched_in(struct perf_event *event, + struct perf_cpu_context *cpuctx) { - switch (boot_cpu_data.x86_model) { - case 1: - case 3: /* Pentium Pro */ - case 5: - case 6: /* Pentium II */ - case 7: - case 8: - case 11: /* Pentium III */ - event_constraints = intel_p6_event_constraints; - break; - case 9: - case 13: - /* Pentium M */ - event_constraints = intel_p6_event_constraints; - break; - default: - pr_cont("unsupported p6 CPU model %d ", - boot_cpu_data.x86_model); - return -ENODEV; - } + int ret = 0; - x86_pmu = p6_pmu; + event->state = PERF_EVENT_STATE_ACTIVE; + event->oncpu = smp_processor_id(); + event->tstamp_running += event->ctx->time - event->tstamp_stopped; - return 0; + if (!is_x86_event(event)) + ret = event->pmu->enable(event); + + if (!ret && !is_software_event(event)) + cpuctx->active_oncpu++; + + if (!ret && event->attr.exclusive) + cpuctx->exclusive = 1; + + return ret; } -static __init int intel_pmu_init(void) +static void x86_event_sched_out(struct perf_event *event, + struct perf_cpu_context *cpuctx) { - union cpuid10_edx edx; - union cpuid10_eax eax; - unsigned int unused; - unsigned int ebx; - int version; - - if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { - /* check for P6 processor family */ - if (boot_cpu_data.x86 == 6) { - return p6_pmu_init(); - } else { - return -ENODEV; - } - } + event->state = PERF_EVENT_STATE_INACTIVE; + event->oncpu = -1; - /* - * Check whether the Architectural PerfMon supports - * Branch Misses Retired hw_event or not. - */ - cpuid(10, &eax.full, &ebx, &unused, &edx.full); - if (eax.split.mask_length <= ARCH_PERFMON_BRANCH_MISSES_RETIRED) - return -ENODEV; + if (!is_x86_event(event)) + event->pmu->disable(event); - version = eax.split.version_id; - if (version < 2) - return -ENODEV; + event->tstamp_running -= event->ctx->time - event->tstamp_stopped; - x86_pmu = intel_pmu; - x86_pmu.version = version; - x86_pmu.num_events = eax.split.num_events; - x86_pmu.event_bits = eax.split.bit_width; - x86_pmu.event_mask = (1ULL << eax.split.bit_width) - 1; + if (!is_software_event(event)) + cpuctx->active_oncpu--; - /* - * Quirk: v2 perfmon does not report fixed-purpose events, so - * assume at least 3 events: - */ - x86_pmu.num_events_fixed = max((int)edx.split.num_events_fixed, 3); + if (event->attr.exclusive || !cpuctx->active_oncpu) + cpuctx->exclusive = 0; +} +/* + * Called to enable a whole group of events. + * Returns 1 if the group was enabled, or -EAGAIN if it could not be. + * Assumes the caller has disabled interrupts and has + * frozen the PMU with hw_perf_save_disable. + * + * called with PMU disabled. If successful and return value 1, + * then guaranteed to call perf_enable() and hw_perf_enable() + */ +int hw_perf_group_sched_in(struct perf_event *leader, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct perf_event *sub; + int assign[X86_PMC_IDX_MAX]; + int n0, n1, ret; + + /* n0 = total number of events */ + n0 = collect_events(cpuc, leader, true); + if (n0 < 0) + return n0; + + ret = x86_schedule_events(cpuc, n0, assign); + if (ret) + return ret; + + ret = x86_event_sched_in(leader, cpuctx); + if (ret) + return ret; + + n1 = 1; + list_for_each_entry(sub, &leader->sibling_list, group_entry) { + if (sub->state > PERF_EVENT_STATE_OFF) { + ret = x86_event_sched_in(sub, cpuctx); + if (ret) + goto undo; + ++n1; + } + } /* - * Install the hw-cache-events table: + * copy new assignment, now we know it is possible + * will be used by hw_perf_enable() */ - switch (boot_cpu_data.x86_model) { - case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ - case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ - case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */ - case 29: /* six-core 45 nm xeon "Dunnington" */ - memcpy(hw_cache_event_ids, core2_hw_cache_event_ids, - sizeof(hw_cache_event_ids)); - - pr_cont("Core2 events, "); - event_constraints = intel_core_event_constraints; - break; - default: - case 26: - memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids, - sizeof(hw_cache_event_ids)); + memcpy(cpuc->assign, assign, n0*sizeof(int)); - event_constraints = intel_nehalem_event_constraints; - pr_cont("Nehalem/Corei7 events, "); - break; - case 28: - memcpy(hw_cache_event_ids, atom_hw_cache_event_ids, - sizeof(hw_cache_event_ids)); + cpuc->n_events = n0; + cpuc->n_added = n1; + ctx->nr_active += n1; - pr_cont("Atom events, "); - break; + /* + * 1 means successful and events are active + * This is not quite true because we defer + * actual activation until hw_perf_enable() but + * this way we* ensure caller won't try to enable + * individual events + */ + return 1; +undo: + x86_event_sched_out(leader, cpuctx); + n0 = 1; + list_for_each_entry(sub, &leader->sibling_list, group_entry) { + if (sub->state == PERF_EVENT_STATE_ACTIVE) { + x86_event_sched_out(sub, cpuctx); + if (++n0 == n1) + break; + } } - return 0; + return ret; } -static __init int amd_pmu_init(void) -{ - /* Performance-monitoring supported from K7 and later: */ - if (boot_cpu_data.x86 < 6) - return -ENODEV; - - x86_pmu = amd_pmu; - - /* Events are common for all AMDs */ - memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, - sizeof(hw_cache_event_ids)); - - return 0; -} +#include "perf_event_amd.c" +#include "perf_event_p6.c" +#include "perf_event_intel.c" static void __init pmu_check_apic(void) { @@ -2213,6 +1391,10 @@ void __init init_hw_perf_events(void) perf_events_lapic_init(); register_die_notifier(&perf_event_nmi_notifier); + unconstrained = (struct event_constraint) + __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_events) - 1, + 0, x86_pmu.num_events); + pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.event_bits); pr_info("... generic registers: %d\n", x86_pmu.num_events); @@ -2230,50 +1412,79 @@ static inline void x86_pmu_read(struct perf_event *event) static const struct pmu pmu = { .enable = x86_pmu_enable, .disable = x86_pmu_disable, + .start = x86_pmu_start, + .stop = x86_pmu_stop, .read = x86_pmu_read, .unthrottle = x86_pmu_unthrottle, }; -static int -validate_event(struct cpu_hw_events *cpuc, struct perf_event *event) -{ - struct hw_perf_event fake_event = event->hw; - - if (event->pmu && event->pmu != &pmu) - return 0; - - return x86_schedule_event(cpuc, &fake_event) >= 0; -} - +/* + * validate a single event group + * + * validation include: + * - check events are compatible which each other + * - events do not compete for the same counter + * - number of events <= number of counters + * + * validation ensures the group can be loaded onto the + * PMU if it was the only group available. + */ static int validate_group(struct perf_event *event) { - struct perf_event *sibling, *leader = event->group_leader; - struct cpu_hw_events fake_pmu; + struct perf_event *leader = event->group_leader; + struct cpu_hw_events *fake_cpuc; + int ret, n; - memset(&fake_pmu, 0, sizeof(fake_pmu)); + ret = -ENOMEM; + fake_cpuc = kmalloc(sizeof(*fake_cpuc), GFP_KERNEL | __GFP_ZERO); + if (!fake_cpuc) + goto out; + + /* + * the event is not yet connected with its + * siblings therefore we must first collect + * existing siblings, then add the new event + * before we can simulate the scheduling + */ + ret = -ENOSPC; + n = collect_events(fake_cpuc, leader, true); + if (n < 0) + goto out_free; - if (!validate_event(&fake_pmu, leader)) - return -ENOSPC; + fake_cpuc->n_events = n; + n = collect_events(fake_cpuc, event, false); + if (n < 0) + goto out_free; - list_for_each_entry(sibling, &leader->sibling_list, group_entry) { - if (!validate_event(&fake_pmu, sibling)) - return -ENOSPC; - } + fake_cpuc->n_events = n; - if (!validate_event(&fake_pmu, event)) - return -ENOSPC; + ret = x86_schedule_events(fake_cpuc, n, NULL); - return 0; +out_free: + kfree(fake_cpuc); +out: + return ret; } const struct pmu *hw_perf_event_init(struct perf_event *event) { + const struct pmu *tmp; int err; err = __hw_perf_event_init(event); if (!err) { + /* + * we temporarily connect event to its pmu + * such that validate_group() can classify + * it as an x86 event using is_x86_event() + */ + tmp = event->pmu; + event->pmu = &pmu; + if (event->group_leader != event) err = validate_group(event); + + event->pmu = tmp; } if (err) { if (event->destroy) @@ -2297,7 +1508,6 @@ void callchain_store(struct perf_callchain_entry *entry, u64 ip) static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry); static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry); -static DEFINE_PER_CPU(int, in_ignored_frame); static void @@ -2313,10 +1523,6 @@ static void backtrace_warning(void *data, char *msg) static int backtrace_stack(void *data, char *name) { - per_cpu(in_ignored_frame, smp_processor_id()) = - x86_is_stack_id(NMI_STACK, name) || - x86_is_stack_id(DEBUG_STACK, name); - return 0; } @@ -2324,9 +1530,6 @@ static void backtrace_address(void *data, unsigned long addr, int reliable) { struct perf_callchain_entry *entry = data; - if (per_cpu(in_ignored_frame, smp_processor_id())) - return; - if (reliable) callchain_store(entry, addr); } @@ -2347,7 +1550,7 @@ perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry) callchain_store(entry, PERF_CONTEXT_KERNEL); callchain_store(entry, regs->ip); - dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry); + dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry); } /* @@ -2433,9 +1636,6 @@ perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry) is_user = user_mode(regs); - if (!current || current->pid == 0) - return; - if (is_user && current->state != TASK_RUNNING) return; @@ -2465,4 +1665,25 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) void hw_perf_event_setup_online(int cpu) { init_debug_store_on_cpu(cpu); + + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + amd_pmu_cpu_online(cpu); + break; + default: + return; + } +} + +void hw_perf_event_setup_offline(int cpu) +{ + init_debug_store_on_cpu(cpu); + + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + amd_pmu_cpu_offline(cpu); + break; + default: + return; + } } diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c new file mode 100644 index 00000000000..8f3dbfda3c4 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -0,0 +1,416 @@ +#ifdef CONFIG_CPU_SUP_AMD + +static DEFINE_RAW_SPINLOCK(amd_nb_lock); + +static __initconst u64 amd_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses */ + [ C(RESULT_MISS) ] = 0x0041, /* Data Cache Misses */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */ + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0267, /* Data Prefetcher :attempts */ + [ C(RESULT_MISS) ] = 0x0167, /* Data Prefetcher :cancelled */ + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0080, /* Instruction cache fetches */ + [ C(RESULT_MISS) ] = 0x0081, /* Instruction cache misses */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x014B, /* Prefetch Instructions :Load */ + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x037D, /* Requests to L2 Cache :IC+DC */ + [ C(RESULT_MISS) ] = 0x037E, /* L2 Cache Misses : IC+DC */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x017F, /* L2 Fill/Writeback */ + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses */ + [ C(RESULT_MISS) ] = 0x0046, /* L1 DTLB and L2 DLTB Miss */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0080, /* Instruction fecthes */ + [ C(RESULT_MISS) ] = 0x0085, /* Instr. fetch ITLB misses */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c2, /* Retired Branch Instr. */ + [ C(RESULT_MISS) ] = 0x00c3, /* Retired Mispredicted BI */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + +/* + * AMD Performance Monitor K7 and later. + */ +static const u64 amd_perfmon_event_map[] = +{ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0080, + [PERF_COUNT_HW_CACHE_MISSES] = 0x0081, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, +}; + +static u64 amd_pmu_event_map(int hw_event) +{ + return amd_perfmon_event_map[hw_event]; +} + +static u64 amd_pmu_raw_event(u64 hw_event) +{ +#define K7_EVNTSEL_EVENT_MASK 0xF000000FFULL +#define K7_EVNTSEL_UNIT_MASK 0x00000FF00ULL +#define K7_EVNTSEL_EDGE_MASK 0x000040000ULL +#define K7_EVNTSEL_INV_MASK 0x000800000ULL +#define K7_EVNTSEL_REG_MASK 0x0FF000000ULL + +#define K7_EVNTSEL_MASK \ + (K7_EVNTSEL_EVENT_MASK | \ + K7_EVNTSEL_UNIT_MASK | \ + K7_EVNTSEL_EDGE_MASK | \ + K7_EVNTSEL_INV_MASK | \ + K7_EVNTSEL_REG_MASK) + + return hw_event & K7_EVNTSEL_MASK; +} + +/* + * AMD64 events are detected based on their event codes. + */ +static inline int amd_is_nb_event(struct hw_perf_event *hwc) +{ + return (hwc->config & 0xe0) == 0xe0; +} + +static void amd_put_event_constraints(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct amd_nb *nb = cpuc->amd_nb; + int i; + + /* + * only care about NB events + */ + if (!(nb && amd_is_nb_event(hwc))) + return; + + /* + * need to scan whole list because event may not have + * been assigned during scheduling + * + * no race condition possible because event can only + * be removed on one CPU at a time AND PMU is disabled + * when we come here + */ + for (i = 0; i < x86_pmu.num_events; i++) { + if (nb->owners[i] == event) { + cmpxchg(nb->owners+i, event, NULL); + break; + } + } +} + + /* + * AMD64 NorthBridge events need special treatment because + * counter access needs to be synchronized across all cores + * of a package. Refer to BKDG section 3.12 + * + * NB events are events measuring L3 cache, Hypertransport + * traffic. They are identified by an event code >= 0xe00. + * They measure events on the NorthBride which is shared + * by all cores on a package. NB events are counted on a + * shared set of counters. When a NB event is programmed + * in a counter, the data actually comes from a shared + * counter. Thus, access to those counters needs to be + * synchronized. + * + * We implement the synchronization such that no two cores + * can be measuring NB events using the same counters. Thus, + * we maintain a per-NB allocation table. The available slot + * is propagated using the event_constraint structure. + * + * We provide only one choice for each NB event based on + * the fact that only NB events have restrictions. Consequently, + * if a counter is available, there is a guarantee the NB event + * will be assigned to it. If no slot is available, an empty + * constraint is returned and scheduling will eventually fail + * for this event. + * + * Note that all cores attached the same NB compete for the same + * counters to host NB events, this is why we use atomic ops. Some + * multi-chip CPUs may have more than one NB. + * + * Given that resources are allocated (cmpxchg), they must be + * eventually freed for others to use. This is accomplished by + * calling amd_put_event_constraints(). + * + * Non NB events are not impacted by this restriction. + */ +static struct event_constraint * +amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct amd_nb *nb = cpuc->amd_nb; + struct perf_event *old = NULL; + int max = x86_pmu.num_events; + int i, j, k = -1; + + /* + * if not NB event or no NB, then no constraints + */ + if (!(nb && amd_is_nb_event(hwc))) + return &unconstrained; + + /* + * detect if already present, if so reuse + * + * cannot merge with actual allocation + * because of possible holes + * + * event can already be present yet not assigned (in hwc->idx) + * because of successive calls to x86_schedule_events() from + * hw_perf_group_sched_in() without hw_perf_enable() + */ + for (i = 0; i < max; i++) { + /* + * keep track of first free slot + */ + if (k == -1 && !nb->owners[i]) + k = i; + + /* already present, reuse */ + if (nb->owners[i] == event) + goto done; + } + /* + * not present, so grab a new slot + * starting either at: + */ + if (hwc->idx != -1) { + /* previous assignment */ + i = hwc->idx; + } else if (k != -1) { + /* start from free slot found */ + i = k; + } else { + /* + * event not found, no slot found in + * first pass, try again from the + * beginning + */ + i = 0; + } + j = i; + do { + old = cmpxchg(nb->owners+i, NULL, event); + if (!old) + break; + if (++i == max) + i = 0; + } while (i != j); +done: + if (!old) + return &nb->event_constraints[i]; + + return &emptyconstraint; +} + +static __initconst struct x86_pmu amd_pmu = { + .name = "AMD", + .handle_irq = x86_pmu_handle_irq, + .disable_all = x86_pmu_disable_all, + .enable_all = x86_pmu_enable_all, + .enable = x86_pmu_enable_event, + .disable = x86_pmu_disable_event, + .eventsel = MSR_K7_EVNTSEL0, + .perfctr = MSR_K7_PERFCTR0, + .event_map = amd_pmu_event_map, + .raw_event = amd_pmu_raw_event, + .max_events = ARRAY_SIZE(amd_perfmon_event_map), + .num_events = 4, + .event_bits = 48, + .event_mask = (1ULL << 48) - 1, + .apic = 1, + /* use highest bit to detect overflow */ + .max_period = (1ULL << 47) - 1, + .get_event_constraints = amd_get_event_constraints, + .put_event_constraints = amd_put_event_constraints +}; + +static struct amd_nb *amd_alloc_nb(int cpu, int nb_id) +{ + struct amd_nb *nb; + int i; + + nb = kmalloc(sizeof(struct amd_nb), GFP_KERNEL); + if (!nb) + return NULL; + + memset(nb, 0, sizeof(*nb)); + nb->nb_id = nb_id; + + /* + * initialize all possible NB constraints + */ + for (i = 0; i < x86_pmu.num_events; i++) { + set_bit(i, nb->event_constraints[i].idxmsk); + nb->event_constraints[i].weight = 1; + } + return nb; +} + +static void amd_pmu_cpu_online(int cpu) +{ + struct cpu_hw_events *cpu1, *cpu2; + struct amd_nb *nb = NULL; + int i, nb_id; + + if (boot_cpu_data.x86_max_cores < 2) + return; + + /* + * function may be called too early in the + * boot process, in which case nb_id is bogus + */ + nb_id = amd_get_nb_id(cpu); + if (nb_id == BAD_APICID) + return; + + cpu1 = &per_cpu(cpu_hw_events, cpu); + cpu1->amd_nb = NULL; + + raw_spin_lock(&amd_nb_lock); + + for_each_online_cpu(i) { + cpu2 = &per_cpu(cpu_hw_events, i); + nb = cpu2->amd_nb; + if (!nb) + continue; + if (nb->nb_id == nb_id) + goto found; + } + + nb = amd_alloc_nb(cpu, nb_id); + if (!nb) { + pr_err("perf_events: failed NB allocation for CPU%d\n", cpu); + raw_spin_unlock(&amd_nb_lock); + return; + } +found: + nb->refcnt++; + cpu1->amd_nb = nb; + + raw_spin_unlock(&amd_nb_lock); +} + +static void amd_pmu_cpu_offline(int cpu) +{ + struct cpu_hw_events *cpuhw; + + if (boot_cpu_data.x86_max_cores < 2) + return; + + cpuhw = &per_cpu(cpu_hw_events, cpu); + + raw_spin_lock(&amd_nb_lock); + + if (--cpuhw->amd_nb->refcnt == 0) + kfree(cpuhw->amd_nb); + + cpuhw->amd_nb = NULL; + + raw_spin_unlock(&amd_nb_lock); +} + +static __init int amd_pmu_init(void) +{ + /* Performance-monitoring supported from K7 and later: */ + if (boot_cpu_data.x86 < 6) + return -ENODEV; + + x86_pmu = amd_pmu; + + /* Events are common for all AMDs */ + memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + + /* + * explicitly initialize the boot cpu, other cpus will get + * the cpu hotplug callbacks from smp_init() + */ + amd_pmu_cpu_online(smp_processor_id()); + return 0; +} + +#else /* CONFIG_CPU_SUP_AMD */ + +static int amd_pmu_init(void) +{ + return 0; +} + +static void amd_pmu_cpu_online(int cpu) +{ +} + +static void amd_pmu_cpu_offline(int cpu) +{ +} + +#endif diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c new file mode 100644 index 00000000000..cf6590cf4a5 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -0,0 +1,971 @@ +#ifdef CONFIG_CPU_SUP_INTEL + +/* + * Intel PerfMon v3. Used on Core2 and later. + */ +static const u64 intel_perfmon_event_map[] = +{ + [PERF_COUNT_HW_CPU_CYCLES] = 0x003c, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x4f2e, + [PERF_COUNT_HW_CACHE_MISSES] = 0x412e, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, + [PERF_COUNT_HW_BUS_CYCLES] = 0x013c, +}; + +static struct event_constraint intel_core_event_constraints[] = +{ + INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */ + INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */ + INTEL_EVENT_CONSTRAINT(0x13, 0x2), /* DIV */ + INTEL_EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */ + INTEL_EVENT_CONSTRAINT(0x19, 0x2), /* DELAYED_BYPASS */ + INTEL_EVENT_CONSTRAINT(0xc1, 0x1), /* FP_COMP_INSTR_RET */ + EVENT_CONSTRAINT_END +}; + +static struct event_constraint intel_core2_event_constraints[] = +{ + FIXED_EVENT_CONSTRAINT(0xc0, (0x3|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */ + FIXED_EVENT_CONSTRAINT(0x3c, (0x3|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */ + INTEL_EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */ + INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */ + INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */ + INTEL_EVENT_CONSTRAINT(0x13, 0x2), /* DIV */ + INTEL_EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */ + INTEL_EVENT_CONSTRAINT(0x18, 0x1), /* IDLE_DURING_DIV */ + INTEL_EVENT_CONSTRAINT(0x19, 0x2), /* DELAYED_BYPASS */ + INTEL_EVENT_CONSTRAINT(0xa1, 0x1), /* RS_UOPS_DISPATCH_CYCLES */ + INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED */ + EVENT_CONSTRAINT_END +}; + +static struct event_constraint intel_nehalem_event_constraints[] = +{ + FIXED_EVENT_CONSTRAINT(0xc0, (0xf|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */ + FIXED_EVENT_CONSTRAINT(0x3c, (0xf|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */ + INTEL_EVENT_CONSTRAINT(0x40, 0x3), /* L1D_CACHE_LD */ + INTEL_EVENT_CONSTRAINT(0x41, 0x3), /* L1D_CACHE_ST */ + INTEL_EVENT_CONSTRAINT(0x42, 0x3), /* L1D_CACHE_LOCK */ + INTEL_EVENT_CONSTRAINT(0x43, 0x3), /* L1D_ALL_REF */ + INTEL_EVENT_CONSTRAINT(0x48, 0x3), /* L1D_PEND_MISS */ + INTEL_EVENT_CONSTRAINT(0x4e, 0x3), /* L1D_PREFETCH */ + INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */ + INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */ + EVENT_CONSTRAINT_END +}; + +static struct event_constraint intel_westmere_event_constraints[] = +{ + FIXED_EVENT_CONSTRAINT(0xc0, (0xf|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */ + FIXED_EVENT_CONSTRAINT(0x3c, (0xf|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */ + INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */ + INTEL_EVENT_CONSTRAINT(0x60, 0x1), /* OFFCORE_REQUESTS_OUTSTANDING */ + INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */ + EVENT_CONSTRAINT_END +}; + +static struct event_constraint intel_gen_event_constraints[] = +{ + FIXED_EVENT_CONSTRAINT(0xc0, (0x3|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */ + FIXED_EVENT_CONSTRAINT(0x3c, (0x3|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */ + EVENT_CONSTRAINT_END +}; + +static u64 intel_pmu_event_map(int hw_event) +{ + return intel_perfmon_event_map[hw_event]; +} + +static __initconst u64 westmere_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS */ + [ C(RESULT_MISS) ] = 0x0151, /* L1D.REPL */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES */ + [ C(RESULT_MISS) ] = 0x0251, /* L1D.M_REPL */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS */ + [ C(RESULT_MISS) ] = 0x024e, /* L1D_PREFETCH.MISS */ + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS */ + [ C(RESULT_MISS) ] = 0x0280, /* L1I.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */ + [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */ + [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */ + [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */ + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS */ + [ C(RESULT_MISS) ] = 0x0108, /* DTLB_LOAD_MISSES.ANY */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES */ + [ C(RESULT_MISS) ] = 0x010c, /* MEM_STORE_RETIRED.DTLB_MISS */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x01c0, /* INST_RETIRED.ANY_P */ + [ C(RESULT_MISS) ] = 0x0185, /* ITLB_MISSES.ANY */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */ + [ C(RESULT_MISS) ] = 0x03e8, /* BPU_CLEARS.ANY */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + +static __initconst u64 nehalem_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI */ + [ C(RESULT_MISS) ] = 0x0140, /* L1D_CACHE_LD.I_STATE */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI */ + [ C(RESULT_MISS) ] = 0x0141, /* L1D_CACHE_ST.I_STATE */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS */ + [ C(RESULT_MISS) ] = 0x024e, /* L1D_PREFETCH.MISS */ + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS */ + [ C(RESULT_MISS) ] = 0x0280, /* L1I.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */ + [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */ + [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */ + [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */ + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI (alias) */ + [ C(RESULT_MISS) ] = 0x0108, /* DTLB_LOAD_MISSES.ANY */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI (alias) */ + [ C(RESULT_MISS) ] = 0x010c, /* MEM_STORE_RETIRED.DTLB_MISS */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x01c0, /* INST_RETIRED.ANY_P */ + [ C(RESULT_MISS) ] = 0x20c8, /* ITLB_MISS_RETIRED */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */ + [ C(RESULT_MISS) ] = 0x03e8, /* BPU_CLEARS.ANY */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + +static __initconst u64 core2_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI */ + [ C(RESULT_MISS) ] = 0x0140, /* L1D_CACHE_LD.I_STATE */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI */ + [ C(RESULT_MISS) ] = 0x0141, /* L1D_CACHE_ST.I_STATE */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x104e, /* L1D_PREFETCH.REQUESTS */ + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0080, /* L1I.READS */ + [ C(RESULT_MISS) ] = 0x0081, /* L1I.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI */ + [ C(RESULT_MISS) ] = 0x4129, /* L2_LD.ISTATE */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI */ + [ C(RESULT_MISS) ] = 0x412A, /* L2_ST.ISTATE */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI (alias) */ + [ C(RESULT_MISS) ] = 0x0208, /* DTLB_MISSES.MISS_LD */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI (alias) */ + [ C(RESULT_MISS) ] = 0x0808, /* DTLB_MISSES.MISS_ST */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */ + [ C(RESULT_MISS) ] = 0x1282, /* ITLBMISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY */ + [ C(RESULT_MISS) ] = 0x00c5, /* BP_INST_RETIRED.MISPRED */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + +static __initconst u64 atom_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE.LD */ + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE.ST */ + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS */ + [ C(RESULT_MISS) ] = 0x0280, /* L1I.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI */ + [ C(RESULT_MISS) ] = 0x4129, /* L2_LD.ISTATE */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI */ + [ C(RESULT_MISS) ] = 0x412A, /* L2_ST.ISTATE */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE_LD.MESI (alias) */ + [ C(RESULT_MISS) ] = 0x0508, /* DTLB_MISSES.MISS_LD */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE_ST.MESI (alias) */ + [ C(RESULT_MISS) ] = 0x0608, /* DTLB_MISSES.MISS_ST */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */ + [ C(RESULT_MISS) ] = 0x0282, /* ITLB.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY */ + [ C(RESULT_MISS) ] = 0x00c5, /* BP_INST_RETIRED.MISPRED */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + +static u64 intel_pmu_raw_event(u64 hw_event) +{ +#define CORE_EVNTSEL_EVENT_MASK 0x000000FFULL +#define CORE_EVNTSEL_UNIT_MASK 0x0000FF00ULL +#define CORE_EVNTSEL_EDGE_MASK 0x00040000ULL +#define CORE_EVNTSEL_INV_MASK 0x00800000ULL +#define CORE_EVNTSEL_REG_MASK 0xFF000000ULL + +#define CORE_EVNTSEL_MASK \ + (INTEL_ARCH_EVTSEL_MASK | \ + INTEL_ARCH_UNIT_MASK | \ + INTEL_ARCH_EDGE_MASK | \ + INTEL_ARCH_INV_MASK | \ + INTEL_ARCH_CNT_MASK) + + return hw_event & CORE_EVNTSEL_MASK; +} + +static void intel_pmu_enable_bts(u64 config) +{ + unsigned long debugctlmsr; + + debugctlmsr = get_debugctlmsr(); + + debugctlmsr |= X86_DEBUGCTL_TR; + debugctlmsr |= X86_DEBUGCTL_BTS; + debugctlmsr |= X86_DEBUGCTL_BTINT; + + if (!(config & ARCH_PERFMON_EVENTSEL_OS)) + debugctlmsr |= X86_DEBUGCTL_BTS_OFF_OS; + + if (!(config & ARCH_PERFMON_EVENTSEL_USR)) + debugctlmsr |= X86_DEBUGCTL_BTS_OFF_USR; + + update_debugctlmsr(debugctlmsr); +} + +static void intel_pmu_disable_bts(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + unsigned long debugctlmsr; + + if (!cpuc->ds) + return; + + debugctlmsr = get_debugctlmsr(); + + debugctlmsr &= + ~(X86_DEBUGCTL_TR | X86_DEBUGCTL_BTS | X86_DEBUGCTL_BTINT | + X86_DEBUGCTL_BTS_OFF_OS | X86_DEBUGCTL_BTS_OFF_USR); + + update_debugctlmsr(debugctlmsr); +} + +static void intel_pmu_disable_all(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0); + + if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) + intel_pmu_disable_bts(); +} + +static void intel_pmu_enable_all(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl); + + if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) { + struct perf_event *event = + cpuc->events[X86_PMC_IDX_FIXED_BTS]; + + if (WARN_ON_ONCE(!event)) + return; + + intel_pmu_enable_bts(event->hw.config); + } +} + +static inline u64 intel_pmu_get_status(void) +{ + u64 status; + + rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status); + + return status; +} + +static inline void intel_pmu_ack_status(u64 ack) +{ + wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack); +} + +static inline void +intel_pmu_disable_fixed(struct hw_perf_event *hwc, int __idx) +{ + int idx = __idx - X86_PMC_IDX_FIXED; + u64 ctrl_val, mask; + + mask = 0xfULL << (idx * 4); + + rdmsrl(hwc->config_base, ctrl_val); + ctrl_val &= ~mask; + (void)checking_wrmsrl(hwc->config_base, ctrl_val); +} + +static void intel_pmu_drain_bts_buffer(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct debug_store *ds = cpuc->ds; + struct bts_record { + u64 from; + u64 to; + u64 flags; + }; + struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS]; + struct bts_record *at, *top; + struct perf_output_handle handle; + struct perf_event_header header; + struct perf_sample_data data; + struct pt_regs regs; + + if (!event) + return; + + if (!ds) + return; + + at = (struct bts_record *)(unsigned long)ds->bts_buffer_base; + top = (struct bts_record *)(unsigned long)ds->bts_index; + + if (top <= at) + return; + + ds->bts_index = ds->bts_buffer_base; + + + data.period = event->hw.last_period; + data.addr = 0; + data.raw = NULL; + regs.ip = 0; + + /* + * Prepare a generic sample, i.e. fill in the invariant fields. + * We will overwrite the from and to address before we output + * the sample. + */ + perf_prepare_sample(&header, &data, event, ®s); + + if (perf_output_begin(&handle, event, + header.size * (top - at), 1, 1)) + return; + + for (; at < top; at++) { + data.ip = at->from; + data.addr = at->to; + + perf_output_sample(&handle, &header, &data, event); + } + + perf_output_end(&handle); + + /* There's new data available. */ + event->hw.interrupts++; + event->pending_kill = POLL_IN; +} + +static inline void +intel_pmu_disable_event(struct hw_perf_event *hwc, int idx) +{ + if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) { + intel_pmu_disable_bts(); + intel_pmu_drain_bts_buffer(); + return; + } + + if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { + intel_pmu_disable_fixed(hwc, idx); + return; + } + + x86_pmu_disable_event(hwc, idx); +} + +static inline void +intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx) +{ + int idx = __idx - X86_PMC_IDX_FIXED; + u64 ctrl_val, bits, mask; + int err; + + /* + * Enable IRQ generation (0x8), + * and enable ring-3 counting (0x2) and ring-0 counting (0x1) + * if requested: + */ + bits = 0x8ULL; + if (hwc->config & ARCH_PERFMON_EVENTSEL_USR) + bits |= 0x2; + if (hwc->config & ARCH_PERFMON_EVENTSEL_OS) + bits |= 0x1; + + /* + * ANY bit is supported in v3 and up + */ + if (x86_pmu.version > 2 && hwc->config & ARCH_PERFMON_EVENTSEL_ANY) + bits |= 0x4; + + bits <<= (idx * 4); + mask = 0xfULL << (idx * 4); + + rdmsrl(hwc->config_base, ctrl_val); + ctrl_val &= ~mask; + ctrl_val |= bits; + err = checking_wrmsrl(hwc->config_base, ctrl_val); +} + +static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx) +{ + if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) { + if (!__get_cpu_var(cpu_hw_events).enabled) + return; + + intel_pmu_enable_bts(hwc->config); + return; + } + + if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { + intel_pmu_enable_fixed(hwc, idx); + return; + } + + __x86_pmu_enable_event(hwc, idx); +} + +/* + * Save and restart an expired event. Called by NMI contexts, + * so it has to be careful about preempting normal event ops: + */ +static int intel_pmu_save_and_restart(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + int ret; + + x86_perf_event_update(event, hwc, idx); + ret = x86_perf_event_set_period(event, hwc, idx); + + return ret; +} + +static void intel_pmu_reset(void) +{ + struct debug_store *ds = __get_cpu_var(cpu_hw_events).ds; + unsigned long flags; + int idx; + + if (!x86_pmu.num_events) + return; + + local_irq_save(flags); + + printk("clearing PMU state on CPU#%d\n", smp_processor_id()); + + for (idx = 0; idx < x86_pmu.num_events; idx++) { + checking_wrmsrl(x86_pmu.eventsel + idx, 0ull); + checking_wrmsrl(x86_pmu.perfctr + idx, 0ull); + } + for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) { + checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull); + } + if (ds) + ds->bts_index = ds->bts_buffer_base; + + local_irq_restore(flags); +} + +/* + * This handler is triggered by the local APIC, so the APIC IRQ handling + * rules apply: + */ +static int intel_pmu_handle_irq(struct pt_regs *regs) +{ + struct perf_sample_data data; + struct cpu_hw_events *cpuc; + int bit, loops; + u64 ack, status; + + data.addr = 0; + data.raw = NULL; + + cpuc = &__get_cpu_var(cpu_hw_events); + + perf_disable(); + intel_pmu_drain_bts_buffer(); + status = intel_pmu_get_status(); + if (!status) { + perf_enable(); + return 0; + } + + loops = 0; +again: + if (++loops > 100) { + WARN_ONCE(1, "perfevents: irq loop stuck!\n"); + perf_event_print_debug(); + intel_pmu_reset(); + perf_enable(); + return 1; + } + + inc_irq_stat(apic_perf_irqs); + ack = status; + for_each_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) { + struct perf_event *event = cpuc->events[bit]; + + clear_bit(bit, (unsigned long *) &status); + if (!test_bit(bit, cpuc->active_mask)) + continue; + + if (!intel_pmu_save_and_restart(event)) + continue; + + data.period = event->hw.last_period; + + if (perf_event_overflow(event, 1, &data, regs)) + intel_pmu_disable_event(&event->hw, bit); + } + + intel_pmu_ack_status(ack); + + /* + * Repeat if there is more work to be done: + */ + status = intel_pmu_get_status(); + if (status) + goto again; + + perf_enable(); + + return 1; +} + +static struct event_constraint bts_constraint = + EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0); + +static struct event_constraint * +intel_special_constraints(struct perf_event *event) +{ + unsigned int hw_event; + + hw_event = event->hw.config & INTEL_ARCH_EVENT_MASK; + + if (unlikely((hw_event == + x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)) && + (event->hw.sample_period == 1))) { + + return &bts_constraint; + } + return NULL; +} + +static struct event_constraint * +intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + struct event_constraint *c; + + c = intel_special_constraints(event); + if (c) + return c; + + return x86_get_event_constraints(cpuc, event); +} + +static __initconst struct x86_pmu core_pmu = { + .name = "core", + .handle_irq = x86_pmu_handle_irq, + .disable_all = x86_pmu_disable_all, + .enable_all = x86_pmu_enable_all, + .enable = x86_pmu_enable_event, + .disable = x86_pmu_disable_event, + .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, + .perfctr = MSR_ARCH_PERFMON_PERFCTR0, + .event_map = intel_pmu_event_map, + .raw_event = intel_pmu_raw_event, + .max_events = ARRAY_SIZE(intel_perfmon_event_map), + .apic = 1, + /* + * Intel PMCs cannot be accessed sanely above 32 bit width, + * so we install an artificial 1<<31 period regardless of + * the generic event period: + */ + .max_period = (1ULL << 31) - 1, + .get_event_constraints = intel_get_event_constraints, + .event_constraints = intel_core_event_constraints, +}; + +static __initconst struct x86_pmu intel_pmu = { + .name = "Intel", + .handle_irq = intel_pmu_handle_irq, + .disable_all = intel_pmu_disable_all, + .enable_all = intel_pmu_enable_all, + .enable = intel_pmu_enable_event, + .disable = intel_pmu_disable_event, + .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, + .perfctr = MSR_ARCH_PERFMON_PERFCTR0, + .event_map = intel_pmu_event_map, + .raw_event = intel_pmu_raw_event, + .max_events = ARRAY_SIZE(intel_perfmon_event_map), + .apic = 1, + /* + * Intel PMCs cannot be accessed sanely above 32 bit width, + * so we install an artificial 1<<31 period regardless of + * the generic event period: + */ + .max_period = (1ULL << 31) - 1, + .enable_bts = intel_pmu_enable_bts, + .disable_bts = intel_pmu_disable_bts, + .get_event_constraints = intel_get_event_constraints +}; + +static __init int intel_pmu_init(void) +{ + union cpuid10_edx edx; + union cpuid10_eax eax; + unsigned int unused; + unsigned int ebx; + int version; + + if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { + /* check for P6 processor family */ + if (boot_cpu_data.x86 == 6) { + return p6_pmu_init(); + } else { + return -ENODEV; + } + } + + /* + * Check whether the Architectural PerfMon supports + * Branch Misses Retired hw_event or not. + */ + cpuid(10, &eax.full, &ebx, &unused, &edx.full); + if (eax.split.mask_length <= ARCH_PERFMON_BRANCH_MISSES_RETIRED) + return -ENODEV; + + version = eax.split.version_id; + if (version < 2) + x86_pmu = core_pmu; + else + x86_pmu = intel_pmu; + + x86_pmu.version = version; + x86_pmu.num_events = eax.split.num_events; + x86_pmu.event_bits = eax.split.bit_width; + x86_pmu.event_mask = (1ULL << eax.split.bit_width) - 1; + + /* + * Quirk: v2 perfmon does not report fixed-purpose events, so + * assume at least 3 events: + */ + if (version > 1) + x86_pmu.num_events_fixed = max((int)edx.split.num_events_fixed, 3); + + /* + * Install the hw-cache-events table: + */ + switch (boot_cpu_data.x86_model) { + case 14: /* 65 nm core solo/duo, "Yonah" */ + pr_cont("Core events, "); + break; + + case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ + case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ + case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */ + case 29: /* six-core 45 nm xeon "Dunnington" */ + memcpy(hw_cache_event_ids, core2_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + + x86_pmu.event_constraints = intel_core2_event_constraints; + pr_cont("Core2 events, "); + break; + + case 26: /* 45 nm nehalem, "Bloomfield" */ + case 30: /* 45 nm nehalem, "Lynnfield" */ + memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + + x86_pmu.event_constraints = intel_nehalem_event_constraints; + pr_cont("Nehalem/Corei7 events, "); + break; + case 28: + memcpy(hw_cache_event_ids, atom_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + + x86_pmu.event_constraints = intel_gen_event_constraints; + pr_cont("Atom events, "); + break; + + case 37: /* 32 nm nehalem, "Clarkdale" */ + case 44: /* 32 nm nehalem, "Gulftown" */ + memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + + x86_pmu.event_constraints = intel_westmere_event_constraints; + pr_cont("Westmere events, "); + break; + default: + /* + * default constraints for v2 and up + */ + x86_pmu.event_constraints = intel_gen_event_constraints; + pr_cont("generic architected perfmon, "); + } + return 0; +} + +#else /* CONFIG_CPU_SUP_INTEL */ + +static int intel_pmu_init(void) +{ + return 0; +} + +#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c new file mode 100644 index 00000000000..1ca5ba078af --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -0,0 +1,157 @@ +#ifdef CONFIG_CPU_SUP_INTEL + +/* + * Not sure about some of these + */ +static const u64 p6_perfmon_event_map[] = +{ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0079, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0f2e, + [PERF_COUNT_HW_CACHE_MISSES] = 0x012e, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, + [PERF_COUNT_HW_BUS_CYCLES] = 0x0062, +}; + +static u64 p6_pmu_event_map(int hw_event) +{ + return p6_perfmon_event_map[hw_event]; +} + +/* + * Event setting that is specified not to count anything. + * We use this to effectively disable a counter. + * + * L2_RQSTS with 0 MESI unit mask. + */ +#define P6_NOP_EVENT 0x0000002EULL + +static u64 p6_pmu_raw_event(u64 hw_event) +{ +#define P6_EVNTSEL_EVENT_MASK 0x000000FFULL +#define P6_EVNTSEL_UNIT_MASK 0x0000FF00ULL +#define P6_EVNTSEL_EDGE_MASK 0x00040000ULL +#define P6_EVNTSEL_INV_MASK 0x00800000ULL +#define P6_EVNTSEL_REG_MASK 0xFF000000ULL + +#define P6_EVNTSEL_MASK \ + (P6_EVNTSEL_EVENT_MASK | \ + P6_EVNTSEL_UNIT_MASK | \ + P6_EVNTSEL_EDGE_MASK | \ + P6_EVNTSEL_INV_MASK | \ + P6_EVNTSEL_REG_MASK) + + return hw_event & P6_EVNTSEL_MASK; +} + +static struct event_constraint p6_event_constraints[] = +{ + INTEL_EVENT_CONSTRAINT(0xc1, 0x1), /* FLOPS */ + INTEL_EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */ + INTEL_EVENT_CONSTRAINT(0x11, 0x1), /* FP_ASSIST */ + INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */ + INTEL_EVENT_CONSTRAINT(0x13, 0x2), /* DIV */ + INTEL_EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */ + EVENT_CONSTRAINT_END +}; + +static void p6_pmu_disable_all(void) +{ + u64 val; + + /* p6 only has one enable register */ + rdmsrl(MSR_P6_EVNTSEL0, val); + val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE; + wrmsrl(MSR_P6_EVNTSEL0, val); +} + +static void p6_pmu_enable_all(void) +{ + unsigned long val; + + /* p6 only has one enable register */ + rdmsrl(MSR_P6_EVNTSEL0, val); + val |= ARCH_PERFMON_EVENTSEL0_ENABLE; + wrmsrl(MSR_P6_EVNTSEL0, val); +} + +static inline void +p6_pmu_disable_event(struct hw_perf_event *hwc, int idx) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + u64 val = P6_NOP_EVENT; + + if (cpuc->enabled) + val |= ARCH_PERFMON_EVENTSEL0_ENABLE; + + (void)checking_wrmsrl(hwc->config_base + idx, val); +} + +static void p6_pmu_enable_event(struct hw_perf_event *hwc, int idx) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + u64 val; + + val = hwc->config; + if (cpuc->enabled) + val |= ARCH_PERFMON_EVENTSEL0_ENABLE; + + (void)checking_wrmsrl(hwc->config_base + idx, val); +} + +static __initconst struct x86_pmu p6_pmu = { + .name = "p6", + .handle_irq = x86_pmu_handle_irq, + .disable_all = p6_pmu_disable_all, + .enable_all = p6_pmu_enable_all, + .enable = p6_pmu_enable_event, + .disable = p6_pmu_disable_event, + .eventsel = MSR_P6_EVNTSEL0, + .perfctr = MSR_P6_PERFCTR0, + .event_map = p6_pmu_event_map, + .raw_event = p6_pmu_raw_event, + .max_events = ARRAY_SIZE(p6_perfmon_event_map), + .apic = 1, + .max_period = (1ULL << 31) - 1, + .version = 0, + .num_events = 2, + /* + * Events have 40 bits implemented. However they are designed such + * that bits [32-39] are sign extensions of bit 31. As such the + * effective width of a event for P6-like PMU is 32 bits only. + * + * See IA-32 Intel Architecture Software developer manual Vol 3B + */ + .event_bits = 32, + .event_mask = (1ULL << 32) - 1, + .get_event_constraints = x86_get_event_constraints, + .event_constraints = p6_event_constraints, +}; + +static __init int p6_pmu_init(void) +{ + switch (boot_cpu_data.x86_model) { + case 1: + case 3: /* Pentium Pro */ + case 5: + case 6: /* Pentium II */ + case 7: + case 8: + case 11: /* Pentium III */ + case 9: + case 13: + /* Pentium M */ + break; + default: + pr_cont("unsupported p6 CPU model %d ", + boot_cpu_data.x86_model); + return -ENODEV; + } + + x86_pmu = p6_pmu; + + return 0; +} + +#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index 898df9719af..74f4e85a572 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -115,17 +115,6 @@ int avail_to_resrv_perfctr_nmi_bit(unsigned int counter) return !test_bit(counter, perfctr_nmi_owner); } - -/* checks the an msr for availability */ -int avail_to_resrv_perfctr_nmi(unsigned int msr) -{ - unsigned int counter; - - counter = nmi_perfctr_msr_to_bit(msr); - BUG_ON(counter > NMI_MAX_COUNTER_BITS); - - return !test_bit(counter, perfctr_nmi_owner); -} EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit); int reserve_perfctr_nmi(unsigned int msr) diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index cb27fd6136c..83e5e628de7 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -229,7 +229,7 @@ static void __exit cpuid_exit(void) for_each_online_cpu(cpu) cpuid_device_destroy(cpu); class_destroy(cpuid_class); - unregister_chrdev(CPUID_MAJOR, "cpu/cpuid"); + __unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid"); unregister_hotcpu_notifier(&cpuid_class_cpu_notifier); } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index c56bc287303..6d817554780 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -123,13 +123,15 @@ print_context_stack_bp(struct thread_info *tinfo, while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) { unsigned long addr = *ret_addr; - if (__kernel_text_address(addr)) { - ops->address(data, addr, 1); - frame = frame->next_frame; - ret_addr = &frame->return_address; - print_ftrace_graph_addr(addr, data, ops, tinfo, graph); - } + if (!__kernel_text_address(addr)) + break; + + ops->address(data, addr, 1); + frame = frame->next_frame; + ret_addr = &frame->return_address; + print_ftrace_graph_addr(addr, data, ops, tinfo, graph); } + return (unsigned long)frame; } EXPORT_SYMBOL_GPL(print_context_stack_bp); diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index ae775ca47b2..11540a189d9 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -18,11 +18,6 @@ #include "dumpstack.h" -/* Just a stub for now */ -int x86_is_stack_id(int id, char *name) -{ - return 0; -} void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 0ad9597073f..dce99abb449 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -33,11 +33,6 @@ static char x86_stack_ids[][8] = { #endif }; -int x86_is_stack_id(int id, char *name) -{ - return x86_stack_ids[id - 1] == name; -} - static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, unsigned *usedp, char **idp) { @@ -291,6 +286,7 @@ void show_registers(struct pt_regs *regs) sp = regs->sp; printk("CPU %d ", cpu); + print_modules(); __show_regs(regs, 1); printk("Process %s (pid: %d, threadinfo %p, task %p)\n", cur->comm, cur->pid, task_thread_info(cur), cur); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 05ed7ab2ca4..a966b753e49 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -517,11 +517,19 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, int checktype) { int i; + u64 end; u64 real_removed_size = 0; if (size > (ULLONG_MAX - start)) size = ULLONG_MAX - start; + end = start + size; + printk(KERN_DEBUG "e820 remove range: %016Lx - %016Lx ", + (unsigned long long) start, + (unsigned long long) end); + e820_print_type(old_type); + printk(KERN_CONT "\n"); + for (i = 0; i < e820.nr_map; i++) { struct e820entry *ei = &e820.map[i]; u64 final_start, final_end; @@ -733,13 +741,13 @@ struct early_res { }; static struct early_res early_res[MAX_EARLY_RES] __initdata = { { 0, PAGE_SIZE, "BIOS data page", 1 }, /* BIOS data page */ -#ifdef CONFIG_X86_32 +#if defined(CONFIG_X86_32) && defined(CONFIG_X86_TRAMPOLINE) /* * But first pinch a few for the stack/trampoline stuff * FIXME: Don't need the extra page at 4K, but need to fix * trampoline before removing it. (see the GDT stuff) */ - { PAGE_SIZE, PAGE_SIZE, "EX TRAMPOLINE", 1 }, + { PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE", 1 }, #endif {} diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c index cdcfb122f25..c2fa9b8b497 100644 --- a/arch/x86/kernel/efi.c +++ b/arch/x86/kernel/efi.c @@ -362,7 +362,7 @@ void __init efi_init(void) printk(KERN_ERR PFX "Could not map the firmware vendor!\n"); early_iounmap(tmp, 2); - printk(KERN_INFO "EFI v%u.%.02u by %s \n", + printk(KERN_INFO "EFI v%u.%.02u by %s\n", efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff, vendor); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 30968924543..cd37469b54e 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -30,14 +30,32 @@ #ifdef CONFIG_DYNAMIC_FTRACE +/* + * modifying_code is set to notify NMIs that they need to use + * memory barriers when entering or exiting. But we don't want + * to burden NMIs with unnecessary memory barriers when code + * modification is not being done (which is most of the time). + * + * A mutex is already held when ftrace_arch_code_modify_prepare + * and post_process are called. No locks need to be taken here. + * + * Stop machine will make sure currently running NMIs are done + * and new NMIs will see the updated variable before we need + * to worry about NMIs doing memory barriers. + */ +static int modifying_code __read_mostly; +static DEFINE_PER_CPU(int, save_modifying_code); + int ftrace_arch_code_modify_prepare(void) { set_kernel_text_rw(); + modifying_code = 1; return 0; } int ftrace_arch_code_modify_post_process(void) { + modifying_code = 0; set_kernel_text_ro(); return 0; } @@ -149,6 +167,11 @@ static void ftrace_mod_code(void) void ftrace_nmi_enter(void) { + __get_cpu_var(save_modifying_code) = modifying_code; + + if (!__get_cpu_var(save_modifying_code)) + return; + if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) { smp_rmb(); ftrace_mod_code(); @@ -160,6 +183,9 @@ void ftrace_nmi_enter(void) void ftrace_nmi_exit(void) { + if (!__get_cpu_var(save_modifying_code)) + return; + /* Finish all executions before clearing nmi_running */ smp_mb(); atomic_dec(&nmi_running); @@ -484,13 +510,3 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, } } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ - -#ifdef CONFIG_FTRACE_SYSCALLS - -extern unsigned long *sys_call_table; - -unsigned long __init arch_syscall_addr(int nr) -{ - return (unsigned long)(&sys_call_table)[nr]; -} -#endif diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index ba6e6588460..ad80a1c718c 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -34,6 +34,8 @@ */ unsigned long hpet_address; u8 hpet_blockid; /* OS timer block num */ +u8 hpet_msi_disable; + #ifdef CONFIG_PCI_MSI static unsigned long hpet_num_timers; #endif @@ -596,6 +598,9 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) unsigned int num_timers_used = 0; int i; + if (hpet_msi_disable) + return; + if (boot_cpu_has(X86_FEATURE_ARAT)) return; id = hpet_readl(HPET_ID); @@ -928,6 +933,9 @@ static __init int hpet_late_init(void) hpet_reserve_platform_timers(hpet_readl(HPET_ID)); hpet_print_config(); + if (hpet_msi_disable) + return 0; + if (boot_cpu_has(X86_FEATURE_ARAT)) return 0; diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 05d5fec64a9..dca2802c666 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -212,25 +212,6 @@ static int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len) return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } -/* - * Store a breakpoint's encoded address, length, and type. - */ -static int arch_store_info(struct perf_event *bp) -{ - struct arch_hw_breakpoint *info = counter_arch_bp(bp); - /* - * For kernel-addresses, either the address or symbol name can be - * specified. - */ - if (info->name) - info->address = (unsigned long) - kallsyms_lookup_name(info->name); - if (info->address) - return 0; - - return -EINVAL; -} - int arch_bp_generic_fields(int x86_len, int x86_type, int *gen_len, int *gen_type) { @@ -362,10 +343,13 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp, return ret; } - ret = arch_store_info(bp); - - if (ret < 0) - return ret; + /* + * For kernel-addresses, either the address or symbol name can be + * specified. + */ + if (info->name) + info->address = (unsigned long) + kallsyms_lookup_name(info->name); /* * Check that the low-order bits of the address are appropriate * for the alignment implied by len. @@ -502,8 +486,6 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args) rcu_read_lock(); bp = per_cpu(bp_per_reg[i], cpu); - if (bp) - rc = NOTIFY_DONE; /* * Reset the 'i'th TRAP bit in dr6 to denote completion of * exception handling @@ -522,7 +504,13 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args) rcu_read_unlock(); } - if (dr6 & (~DR_TRAP_BITS)) + /* + * Further processing in do_debug() is needed for a) user-space + * breakpoints (to generate signals) and b) when the system has + * taken exception due to multiple causes + */ + if ((current->thread.debugreg6 & DR_TRAP_BITS) || + (dr6 & (~DR_TRAP_BITS))) rc = NOTIFY_DONE; set_debugreg(dr7, 7); diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index dd74fe7273b..bfba6019d76 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -42,6 +42,7 @@ #include <linux/init.h> #include <linux/smp.h> #include <linux/nmi.h> +#include <linux/hw_breakpoint.h> #include <asm/debugreg.h> #include <asm/apicdef.h> @@ -204,40 +205,81 @@ void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs) static struct hw_breakpoint { unsigned enabled; - unsigned type; - unsigned len; unsigned long addr; + int len; + int type; + struct perf_event **pev; } breakinfo[4]; static void kgdb_correct_hw_break(void) { - unsigned long dr7; - int correctit = 0; - int breakbit; int breakno; - get_debugreg(dr7, 7); for (breakno = 0; breakno < 4; breakno++) { - breakbit = 2 << (breakno << 1); - if (!(dr7 & breakbit) && breakinfo[breakno].enabled) { - correctit = 1; - dr7 |= breakbit; - dr7 &= ~(0xf0000 << (breakno << 2)); - dr7 |= ((breakinfo[breakno].len << 2) | - breakinfo[breakno].type) << - ((breakno << 2) + 16); - set_debugreg(breakinfo[breakno].addr, breakno); - - } else { - if ((dr7 & breakbit) && !breakinfo[breakno].enabled) { - correctit = 1; - dr7 &= ~breakbit; - dr7 &= ~(0xf0000 << (breakno << 2)); - } - } + struct perf_event *bp; + struct arch_hw_breakpoint *info; + int val; + int cpu = raw_smp_processor_id(); + if (!breakinfo[breakno].enabled) + continue; + bp = *per_cpu_ptr(breakinfo[breakno].pev, cpu); + info = counter_arch_bp(bp); + if (bp->attr.disabled != 1) + continue; + bp->attr.bp_addr = breakinfo[breakno].addr; + bp->attr.bp_len = breakinfo[breakno].len; + bp->attr.bp_type = breakinfo[breakno].type; + info->address = breakinfo[breakno].addr; + info->len = breakinfo[breakno].len; + info->type = breakinfo[breakno].type; + val = arch_install_hw_breakpoint(bp); + if (!val) + bp->attr.disabled = 0; + } + hw_breakpoint_restore(); +} + +static int hw_break_reserve_slot(int breakno) +{ + int cpu; + int cnt = 0; + struct perf_event **pevent; + + for_each_online_cpu(cpu) { + cnt++; + pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu); + if (dbg_reserve_bp_slot(*pevent)) + goto fail; + } + + return 0; + +fail: + for_each_online_cpu(cpu) { + cnt--; + if (!cnt) + break; + pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu); + dbg_release_bp_slot(*pevent); } - if (correctit) - set_debugreg(dr7, 7); + return -1; +} + +static int hw_break_release_slot(int breakno) +{ + struct perf_event **pevent; + int cpu; + + for_each_online_cpu(cpu) { + pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu); + if (dbg_release_bp_slot(*pevent)) + /* + * The debugger is responisble for handing the retry on + * remove failure. + */ + return -1; + } + return 0; } static int @@ -251,6 +293,10 @@ kgdb_remove_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) if (i == 4) return -1; + if (hw_break_release_slot(i)) { + printk(KERN_ERR "Cannot remove hw breakpoint at %lx\n", addr); + return -1; + } breakinfo[i].enabled = 0; return 0; @@ -259,15 +305,23 @@ kgdb_remove_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) static void kgdb_remove_all_hw_break(void) { int i; + int cpu = raw_smp_processor_id(); + struct perf_event *bp; - for (i = 0; i < 4; i++) - memset(&breakinfo[i], 0, sizeof(struct hw_breakpoint)); + for (i = 0; i < 4; i++) { + if (!breakinfo[i].enabled) + continue; + bp = *per_cpu_ptr(breakinfo[i].pev, cpu); + if (bp->attr.disabled == 1) + continue; + arch_uninstall_hw_breakpoint(bp); + bp->attr.disabled = 1; + } } static int kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) { - unsigned type; int i; for (i = 0; i < 4; i++) @@ -278,27 +332,42 @@ kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) switch (bptype) { case BP_HARDWARE_BREAKPOINT: - type = 0; - len = 1; + len = 1; + breakinfo[i].type = X86_BREAKPOINT_EXECUTE; break; case BP_WRITE_WATCHPOINT: - type = 1; + breakinfo[i].type = X86_BREAKPOINT_WRITE; break; case BP_ACCESS_WATCHPOINT: - type = 3; + breakinfo[i].type = X86_BREAKPOINT_RW; break; default: return -1; } - - if (len == 1 || len == 2 || len == 4) - breakinfo[i].len = len - 1; - else + switch (len) { + case 1: + breakinfo[i].len = X86_BREAKPOINT_LEN_1; + break; + case 2: + breakinfo[i].len = X86_BREAKPOINT_LEN_2; + break; + case 4: + breakinfo[i].len = X86_BREAKPOINT_LEN_4; + break; +#ifdef CONFIG_X86_64 + case 8: + breakinfo[i].len = X86_BREAKPOINT_LEN_8; + break; +#endif + default: return -1; - - breakinfo[i].enabled = 1; + } breakinfo[i].addr = addr; - breakinfo[i].type = type; + if (hw_break_reserve_slot(i)) { + breakinfo[i].addr = 0; + return -1; + } + breakinfo[i].enabled = 1; return 0; } @@ -313,8 +382,21 @@ kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) */ void kgdb_disable_hw_debug(struct pt_regs *regs) { + int i; + int cpu = raw_smp_processor_id(); + struct perf_event *bp; + /* Disable hardware debugging while we are in kgdb: */ set_debugreg(0UL, 7); + for (i = 0; i < 4; i++) { + if (!breakinfo[i].enabled) + continue; + bp = *per_cpu_ptr(breakinfo[i].pev, cpu); + if (bp->attr.disabled == 1) + continue; + arch_uninstall_hw_breakpoint(bp); + bp->attr.disabled = 1; + } } /** @@ -378,7 +460,6 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, struct pt_regs *linux_regs) { unsigned long addr; - unsigned long dr6; char *ptr; int newPC; @@ -404,20 +485,6 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, raw_smp_processor_id()); } - get_debugreg(dr6, 6); - if (!(dr6 & 0x4000)) { - int breakno; - - for (breakno = 0; breakno < 4; breakno++) { - if (dr6 & (1 << breakno) && - breakinfo[breakno].type == 0) { - /* Set restore flag: */ - linux_regs->flags |= X86_EFLAGS_RF; - break; - } - } - } - set_debugreg(0UL, 6); kgdb_correct_hw_break(); return 0; @@ -485,8 +552,7 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd) break; case DIE_DEBUG: - if (atomic_read(&kgdb_cpu_doing_single_step) == - raw_smp_processor_id()) { + if (atomic_read(&kgdb_cpu_doing_single_step) != -1) { if (user_mode(regs)) return single_step_cont(regs, args); break; @@ -539,7 +605,42 @@ static struct notifier_block kgdb_notifier = { */ int kgdb_arch_init(void) { - return register_die_notifier(&kgdb_notifier); + int i, cpu; + int ret; + struct perf_event_attr attr; + struct perf_event **pevent; + + ret = register_die_notifier(&kgdb_notifier); + if (ret != 0) + return ret; + /* + * Pre-allocate the hw breakpoint structions in the non-atomic + * portion of kgdb because this operation requires mutexs to + * complete. + */ + attr.bp_addr = (unsigned long)kgdb_arch_init; + attr.type = PERF_TYPE_BREAKPOINT; + attr.bp_len = HW_BREAKPOINT_LEN_1; + attr.bp_type = HW_BREAKPOINT_W; + attr.disabled = 1; + for (i = 0; i < 4; i++) { + breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL); + if (IS_ERR(breakinfo[i].pev)) { + printk(KERN_ERR "kgdb: Could not allocate hw breakpoints\n"); + breakinfo[i].pev = NULL; + kgdb_arch_exit(); + return -1; + } + for_each_online_cpu(cpu) { + pevent = per_cpu_ptr(breakinfo[i].pev, cpu); + pevent[0]->hw.sample_period = 1; + if (pevent[0]->destroy != NULL) { + pevent[0]->destroy = NULL; + release_bp_slot(*pevent); + } + } + } + return ret; } /** @@ -550,6 +651,13 @@ int kgdb_arch_init(void) */ void kgdb_arch_exit(void) { + int i; + for (i = 0; i < 4; i++) { + if (breakinfo[i].pev) { + unregister_wide_hw_breakpoint(breakinfo[i].pev); + breakinfo[i].pev = NULL; + } + } unregister_die_notifier(&kgdb_notifier); } diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 5b8c7505b3b..5de9f4a9c3f 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -337,6 +337,9 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p) int __kprobes arch_prepare_kprobe(struct kprobe *p) { + if (alternatives_text_reserved(p->addr, p->addr)) + return -EINVAL; + if (!can_probe((unsigned long)p->addr)) return -EILSEQ; /* insn: must be on special executable page on x86. */ @@ -429,7 +432,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { -#if !defined(CONFIG_PREEMPT) || defined(CONFIG_FREEZER) +#if !defined(CONFIG_PREEMPT) if (p->ainsn.boostable == 1 && !p->post_handler) { /* Boost up -- we can execute copied instructions directly */ reset_current_kprobe(); diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 37542b67c57..e1af7c055c7 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -36,9 +36,6 @@ MODULE_LICENSE("GPL v2"); #define UCODE_EQUIV_CPU_TABLE_TYPE 0x00000000 #define UCODE_UCODE_TYPE 0x00000001 -const struct firmware *firmware; -static int supported_cpu; - struct equiv_cpu_entry { u32 installed_cpu; u32 fixed_errata_mask; @@ -77,12 +74,15 @@ static struct equiv_cpu_entry *equiv_cpu_table; static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig) { + struct cpuinfo_x86 *c = &cpu_data(cpu); u32 dummy; - if (!supported_cpu) - return -1; - memset(csig, 0, sizeof(*csig)); + if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) { + pr_warning("microcode: CPU%d: AMD CPU family 0x%x not " + "supported\n", cpu, c->x86); + return -1; + } rdmsr(MSR_AMD64_PATCH_LEVEL, csig->rev, dummy); pr_info("CPU%d: patch_level=0x%x\n", cpu, csig->rev); return 0; @@ -294,10 +294,14 @@ generic_load_microcode(int cpu, const u8 *data, size_t size) static enum ucode_state request_microcode_fw(int cpu, struct device *device) { + const char *fw_name = "amd-ucode/microcode_amd.bin"; + const struct firmware *firmware; enum ucode_state ret; - if (firmware == NULL) + if (request_firmware(&firmware, fw_name, device)) { + printk(KERN_ERR "microcode: failed to load file %s\n", fw_name); return UCODE_NFOUND; + } if (*(u32 *)firmware->data != UCODE_MAGIC) { pr_err("invalid UCODE_MAGIC (0x%08x)\n", @@ -307,6 +311,8 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device) ret = generic_load_microcode(cpu, firmware->data, firmware->size); + release_firmware(firmware); + return ret; } @@ -325,31 +331,7 @@ static void microcode_fini_cpu_amd(int cpu) uci->mc = NULL; } -void init_microcode_amd(struct device *device) -{ - const char *fw_name = "amd-ucode/microcode_amd.bin"; - struct cpuinfo_x86 *c = &boot_cpu_data; - - WARN_ON(c->x86_vendor != X86_VENDOR_AMD); - - if (c->x86 < 0x10) { - pr_warning("AMD CPU family 0x%x not supported\n", c->x86); - return; - } - supported_cpu = 1; - - if (request_firmware(&firmware, fw_name, device)) - pr_err("failed to load file %s\n", fw_name); -} - -void fini_microcode_amd(void) -{ - release_firmware(firmware); -} - static struct microcode_ops microcode_amd_ops = { - .init = init_microcode_amd, - .fini = fini_microcode_amd, .request_microcode_user = request_microcode_user, .request_microcode_fw = request_microcode_fw, .collect_cpu_info = collect_cpu_info_amd, diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index 0c863243309..cceb5bc3c3c 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -521,9 +521,6 @@ static int __init microcode_init(void) return PTR_ERR(microcode_pdev); } - if (microcode_ops->init) - microcode_ops->init(µcode_pdev->dev); - get_online_cpus(); mutex_lock(µcode_mutex); @@ -566,9 +563,6 @@ static void __exit microcode_exit(void) platform_device_unregister(microcode_pdev); - if (microcode_ops->fini) - microcode_ops->fini(); - microcode_ops = NULL; pr_info("Microcode Update Driver: v" MICROCODE_VERSION " removed.\n"); diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c index ebd193e476c..85a343e2893 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/microcode_intel.c @@ -328,7 +328,7 @@ static int apply_microcode(int cpu) cpu_num, mc_intel->hdr.rev); return -1; } - pr_info("CPU%d updated to revision 0x%x, date = %04x-%02x-%02x \n", + pr_info("CPU%d updated to revision 0x%x, date = %04x-%02x-%02x\n", cpu_num, val[1], mc_intel->hdr.date & 0xffff, mc_intel->hdr.date >> 24, diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 40b54ceb68b..a2c1edd2d3a 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -359,13 +359,6 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) x86_init.mpparse.mpc_record(1); } -#ifdef CONFIG_X86_BIGSMP - generic_bigsmp_probe(); -#endif - - if (apic->setup_apic_routing) - apic->setup_apic_routing(); - if (!num_processors) printk(KERN_ERR "MPTABLE: no processors registered!\n"); return num_processors; diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 4bd93c9b2b2..206735ac8cb 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -285,7 +285,7 @@ static void __exit msr_exit(void) for_each_online_cpu(cpu) msr_device_destroy(cpu); class_destroy(msr_class); - unregister_chrdev(MSR_MAJOR, "cpu/msr"); + __unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr"); unregister_hotcpu_notifier(&msr_class_cpu_notifier); } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index cf1e04b2ad6..02d678065d7 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -110,8 +110,8 @@ void show_regs_common(void) if (!product) product = ""; - printk("\n"); - printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s %s/%s\n", + printk(KERN_CONT "\n"); + printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s %s/%s\n", current->pid, current->comm, print_tainted(), init_utsname()->release, (int)strcspn(init_utsname()->version, " "), @@ -122,18 +122,6 @@ 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 - flush_ptrace_hw_breakpoint(tsk); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); /* @@ -295,6 +283,8 @@ int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) regs.es = __USER_DS; regs.fs = __KERNEL_PERCPU; regs.gs = __KERNEL_STACK_CANARY; +#else + regs.ss = __KERNEL_DS; #endif regs.orig_ax = -1; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index fe6a34e42bd..f6c62667e30 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -139,16 +139,16 @@ void __show_regs(struct pt_regs *regs, int all) show_regs_common(); - printk("EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n", + printk(KERN_DEFAULT "EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n", (u16)regs->cs, regs->ip, regs->flags, smp_processor_id()); print_symbol("EIP is at %s\n", regs->ip); - printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", + printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", regs->ax, regs->bx, regs->cx, regs->dx); - printk("ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n", + printk(KERN_DEFAULT "ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n", regs->si, regs->di, regs->bp, sp); - printk(" DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n", + printk(KERN_DEFAULT " DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n", (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss); if (!all) @@ -158,19 +158,19 @@ void __show_regs(struct pt_regs *regs, int all) cr2 = read_cr2(); cr3 = read_cr3(); cr4 = read_cr4_safe(); - printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", + printk(KERN_DEFAULT "CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4); get_debugreg(d0, 0); get_debugreg(d1, 1); get_debugreg(d2, 2); get_debugreg(d3, 3); - printk("DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n", + printk(KERN_DEFAULT "DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n", d0, d1, d2, d3); get_debugreg(d6, 6); get_debugreg(d7, 7); - printk("DR6: %08lx DR7: %08lx\n", + printk(KERN_DEFAULT "DR6: %08lx DR7: %08lx\n", d6, d7); } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 418f860880a..dc9690b4c4c 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -161,19 +161,19 @@ void __show_regs(struct pt_regs *regs, int all) unsigned int ds, cs, es; show_regs_common(); - printk(KERN_INFO "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip); + printk(KERN_DEFAULT "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip); printk_address(regs->ip, 1); - printk(KERN_INFO "RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, + printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, regs->sp, regs->flags); - printk(KERN_INFO "RAX: %016lx RBX: %016lx RCX: %016lx\n", + printk(KERN_DEFAULT "RAX: %016lx RBX: %016lx RCX: %016lx\n", regs->ax, regs->bx, regs->cx); - printk(KERN_INFO "RDX: %016lx RSI: %016lx RDI: %016lx\n", + printk(KERN_DEFAULT "RDX: %016lx RSI: %016lx RDI: %016lx\n", regs->dx, regs->si, regs->di); - printk(KERN_INFO "RBP: %016lx R08: %016lx R09: %016lx\n", + printk(KERN_DEFAULT "RBP: %016lx R08: %016lx R09: %016lx\n", regs->bp, regs->r8, regs->r9); - printk(KERN_INFO "R10: %016lx R11: %016lx R12: %016lx\n", + printk(KERN_DEFAULT "R10: %016lx R11: %016lx R12: %016lx\n", regs->r10, regs->r11, regs->r12); - printk(KERN_INFO "R13: %016lx R14: %016lx R15: %016lx\n", + printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n", regs->r13, regs->r14, regs->r15); asm("movl %%ds,%0" : "=r" (ds)); @@ -194,21 +194,21 @@ void __show_regs(struct pt_regs *regs, int all) cr3 = read_cr3(); cr4 = read_cr4(); - printk(KERN_INFO "FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", + printk(KERN_DEFAULT "FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", fs, fsindex, gs, gsindex, shadowgs); - printk(KERN_INFO "CS: %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds, + printk(KERN_DEFAULT "CS: %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds, es, cr0); - printk(KERN_INFO "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3, + printk(KERN_DEFAULT "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3, cr4); get_debugreg(d0, 0); get_debugreg(d1, 1); get_debugreg(d2, 2); - printk(KERN_INFO "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2); + printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2); get_debugreg(d3, 3); get_debugreg(d6, 6); get_debugreg(d7, 7); - printk(KERN_INFO "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7); + printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7); } void release_thread(struct task_struct *dead_task) @@ -515,6 +515,18 @@ void set_personality_64bit(void) current->personality &= ~READ_IMPLIES_EXEC; } +void set_personality_ia32(void) +{ + /* inherit personality from parent */ + + /* Make sure to be in 32bit mode */ + set_thread_flag(TIF_IA32); + current->personality |= force_personality32; + + /* Prepare the first "return" to user space */ + current_thread_info()->status |= TS_COMPAT; +} + 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 017d937639f..d03146f71b2 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -140,30 +140,6 @@ static const int arg_offs_table[] = { #endif }; -/** - * regs_get_argument_nth() - get Nth argument at function call - * @regs: pt_regs which contains registers at function entry. - * @n: argument number. - * - * regs_get_argument_nth() returns @n th argument of a function call. - * Since usually the kernel stack will be changed right after function entry, - * you must use this at function entry. If the @n th entry is NOT in the - * kernel stack or pt_regs, this returns 0. - */ -unsigned long regs_get_argument_nth(struct pt_regs *regs, unsigned int n) -{ - if (n < ARRAY_SIZE(arg_offs_table)) - return *(unsigned long *)((char *)regs + arg_offs_table[n]); - else { - /* - * The typical case: arg n is on the stack. - * (Note: stack[0] = return address, so skip it) - */ - n -= ARRAY_SIZE(arg_offs_table); - return regs_get_kernel_stack_nth(regs, 1 + n); - } -} - /* * does not yet catch signals sent when the child dies. * in exit.c or in signal.c. @@ -702,7 +678,7 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n) } else if (n == 6) { val = thread->debugreg6; } else if (n == 7) { - val = ptrace_get_dr7(thread->ptrace_bps); + val = thread->ptrace_dr7; } return val; } @@ -778,8 +754,11 @@ int ptrace_set_debugreg(struct task_struct *tsk, int n, unsigned long val) return rc; } /* All that's left is DR7 */ - if (n == 7) + if (n == 7) { rc = ptrace_write_dr7(tsk, val); + if (!rc) + thread->ptrace_dr7 = val; + } ret_path: return rc; diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 18093d7498f..12e9feaa2f7 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -491,6 +491,19 @@ void force_hpet_resume(void) break; } } + +/* + * HPET MSI on some boards (ATI SB700/SB800) has side effect on + * floppy DMA. Disable HPET MSI on such platforms. + */ +static void force_disable_hpet_msi(struct pci_dev *unused) +{ + hpet_msi_disable = 1; +} + +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, + force_disable_hpet_msi); + #endif #if defined(CONFIG_PCI) && defined(CONFIG_NUMA) diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 1545bc0c984..704bddcdf64 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -203,6 +203,15 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "0T656F"), }, }, + { /* Handle problems with rebooting on Dell OptiPlex 760 with 0G919G*/ + .callback = set_bios_reboot, + .ident = "Dell OptiPlex 760", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 760"), + DMI_MATCH(DMI_BOARD_NAME, "0G919G"), + }, + }, { /* Handle problems with rebooting on Dell 2400's */ .callback = set_bios_reboot, .ident = "Dell PowerEdge 2400", diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f7b8b9894b2..cb42109a55b 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -121,7 +121,9 @@ unsigned long max_low_pfn_mapped; unsigned long max_pfn_mapped; +#ifdef CONFIG_DMI RESERVE_BRK(dmi_alloc, 65536); +#endif unsigned int boot_cpu_id __read_mostly; @@ -642,23 +644,48 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix/MSC"), }, }, - { /* - * AMI BIOS with low memory corruption was found on Intel DG45ID board. - * It hase different DMI_BIOS_VENDOR = "Intel Corp.", for now we will + * AMI BIOS with low memory corruption was found on Intel DG45ID and + * DG45FC boards. + * It has a different DMI_BIOS_VENDOR = "Intel Corp.", for now we will * match only DMI_BOARD_NAME and see if there is more bad products * with this vendor. */ + { .callback = dmi_low_memory_corruption, .ident = "AMI BIOS", .matches = { DMI_MATCH(DMI_BOARD_NAME, "DG45ID"), }, }, + { + .callback = dmi_low_memory_corruption, + .ident = "AMI BIOS", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "DG45FC"), + }, + }, #endif {} }; +static void __init trim_bios_range(void) +{ + /* + * A special case is the first 4Kb of memory; + * This is a BIOS owned area, not kernel ram, but generally + * not listed as such in the E820 table. + */ + e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED); + /* + * special case: Some BIOSen report the PC BIOS + * area (640->1Mb) as ram even though it is not. + * take them out. + */ + e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1); + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); +} + /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -822,7 +849,7 @@ void __init setup_arch(char **cmdline_p) insert_resource(&iomem_resource, &data_resource); insert_resource(&iomem_resource, &bss_resource); - + trim_bios_range(); #ifdef CONFIG_X86_32 if (ppro_with_ram_bug()) { e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM, diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 678d0b8c26f..b4e870cbdc6 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1083,9 +1083,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_cpu_sibling_map(0); enable_IR_x2apic(); -#ifdef CONFIG_X86_64 default_setup_apic_routing(); -#endif if (smp_sanity_check(max_cpus) < 0) { printk(KERN_INFO "SMP disabled\n"); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 33399176512..1168e445418 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -534,6 +534,9 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) get_debugreg(dr6, 6); + /* Filter out all the reserved bits which are preset to 1 */ + dr6 &= ~DR6_RESERVED; + /* Catch kmemcheck conditions first of all! */ if ((dr6 & DR_STEP) && kmemcheck_trap(regs)) return; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 597683aa5ba..23066ecf12f 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -806,7 +806,7 @@ static void __init check_system_tsc_reliable(void) unsigned long res_low, res_high; rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high); - /* Geode_LX - the OLPC CPU has a possibly a very reliable TSC */ + /* Geode_LX - the OLPC CPU has a very reliable TSC */ if (res_low & RTSC_SUSP) tsc_clocksource_reliable = 1; #endif diff --git a/arch/x86/kernel/uv_sysfs.c b/arch/x86/kernel/uv_sysfs.c index 36afb98675a..309c70fb775 100644 --- a/arch/x86/kernel/uv_sysfs.c +++ b/arch/x86/kernel/uv_sysfs.c @@ -54,19 +54,19 @@ static int __init sgi_uv_sysfs_init(void) if (!sgi_uv_kobj) sgi_uv_kobj = kobject_create_and_add("sgi_uv", firmware_kobj); if (!sgi_uv_kobj) { - printk(KERN_WARNING "kobject_create_and_add sgi_uv failed \n"); + printk(KERN_WARNING "kobject_create_and_add sgi_uv failed\n"); return -EINVAL; } ret = sysfs_create_file(sgi_uv_kobj, &partition_id_attr.attr); if (ret) { - printk(KERN_WARNING "sysfs_create_file partition_id failed \n"); + printk(KERN_WARNING "sysfs_create_file partition_id failed\n"); return ret; } ret = sysfs_create_file(sgi_uv_kobj, &coherence_id_attr.attr); if (ret) { - printk(KERN_WARNING "sysfs_create_file coherence_id failed \n"); + printk(KERN_WARNING "sysfs_create_file coherence_id failed\n"); return ret; } diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c index 3c84aa001c1..2b75ef638db 100644 --- a/arch/x86/kernel/uv_time.c +++ b/arch/x86/kernel/uv_time.c @@ -282,10 +282,21 @@ static int uv_rtc_unset_timer(int cpu, int force) /* * Read the RTC. + * + * Starting with HUB rev 2.0, the UV RTC register is replicated across all + * cachelines of it's own page. This allows faster simultaneous reads + * from a given socket. */ static cycle_t uv_read_rtc(struct clocksource *cs) { - return (cycle_t)uv_read_local_mmr(UVH_RTC); + unsigned long offset; + + if (uv_get_min_hub_revision_id() == 1) + offset = 0; + else + offset = (uv_blade_processor_id() * L1_CACHE_BYTES) % PAGE_SIZE; + + return (cycle_t)uv_read_local_mmr(UVH_RTC | offset); } /* diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 296aba49472..15578f180e5 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -467,6 +467,9 @@ static int pit_ioport_read(struct kvm_io_device *this, return -EOPNOTSUPP; addr &= KVM_PIT_CHANNEL_MASK; + if (addr == 3) + return 0; + s = &pit_state->channels[addr]; mutex_lock(&pit_state->lock); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index cd60c0bd1b3..ba8c045da78 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -373,6 +373,12 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, if (unlikely(!apic_enabled(apic))) break; + if (trig_mode) { + apic_debug("level trig mode for vector %d", vector); + apic_set_vector(vector, apic->regs + APIC_TMR); + } else + apic_clear_vector(vector, apic->regs + APIC_TMR); + result = !apic_test_and_set_irr(vector, apic); trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode, trig_mode, vector, !result); @@ -383,11 +389,6 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, break; } - if (trig_mode) { - apic_debug("level trig mode for vector %d", vector); - apic_set_vector(vector, apic->regs + APIC_TMR); - } else - apic_clear_vector(vector, apic->regs + APIC_TMR); kvm_vcpu_kick(vcpu); break; @@ -1150,6 +1151,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu) hrtimer_cancel(&apic->lapic_timer.timer); update_divide_count(apic); start_apic_timer(apic); + apic->irr_pending = true; } void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 4c3e5b2314c..89a49fb46a2 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -477,7 +477,7 @@ static int host_mapping_level(struct kvm *kvm, gfn_t gfn) addr = gfn_to_hva(kvm, gfn); if (kvm_is_error_hva(addr)) - return page_size; + return PT_PAGE_TABLE_LEVEL; down_read(¤t->mm->mmap_sem); vma = find_vma(current->mm, addr); @@ -515,11 +515,9 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) if (host_level == PT_PAGE_TABLE_LEVEL) return host_level; - for (level = PT_DIRECTORY_LEVEL; level <= host_level; ++level) { - + for (level = PT_DIRECTORY_LEVEL; level <= host_level; ++level) if (has_wrprotected_page(vcpu->kvm, large_gfn, level)) break; - } return level - 1; } diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index a6017132fba..ede2131a922 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -150,7 +150,9 @@ walk: walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; - kvm_read_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte)); + if (kvm_read_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte))) + goto not_present; + trace_kvm_mmu_paging_element(pte, walker->level); if (!is_present_gpte(pte)) @@ -455,8 +457,6 @@ out_unlock: static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) { struct kvm_shadow_walk_iterator iterator; - pt_element_t gpte; - gpa_t pte_gpa = -1; int level; u64 *sptep; int need_flush = 0; @@ -470,10 +470,6 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) if (level == PT_PAGE_TABLE_LEVEL || ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) || ((level == PT_PDPE_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); @@ -492,18 +488,6 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) if (need_flush) kvm_flush_remote_tlbs(vcpu->kvm); spin_unlock(&vcpu->kvm->mmu_lock); - - if (pte_gpa == -1) - return; - if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte, - sizeof(pt_element_t))) - return; - if (is_present_gpte(gpte) && (gpte & PT_ACCESSED_MASK)) { - if (mmu_topup_memory_caches(vcpu)) - return; - kvm_mmu_pte_write(vcpu, pte_gpa, (const u8 *)&gpte, - sizeof(pt_element_t), 0); - } } static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9d068966fb2..a1e1bc9d412 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -670,7 +670,7 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) { static int version; struct pvclock_wall_clock wc; - struct timespec now, sys, boot; + struct timespec boot; if (!wall_clock) return; @@ -685,9 +685,7 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) * wall clock specified here. guest system time equals host * system time for us, thus we must fill in host boot time here. */ - now = current_kernel_time(); - ktime_get_ts(&sys); - boot = ns_to_timespec(timespec_to_ns(&now) - timespec_to_ns(&sys)); + getboottime(&boot); wc.sec = boot.tv_sec; wc.nsec = boot.tv_nsec; @@ -762,6 +760,7 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) local_irq_save(flags); kvm_get_msr(v, MSR_IA32_TSC, &vcpu->hv_clock.tsc_timestamp); ktime_get_ts(&ts); + monotonic_to_bootbased(&ts); local_irq_restore(flags); /* With all the info we got, fill in the values */ @@ -1913,7 +1912,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->sipi_vector = vcpu->arch.sipi_vector; - events->flags = 0; + events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING + | KVM_VCPUEVENT_VALID_SIPI_VECTOR); vcpu_put(vcpu); } @@ -1921,7 +1921,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { - if (events->flags) + if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING + | KVM_VCPUEVENT_VALID_SIPI_VECTOR)) return -EINVAL; vcpu_load(vcpu); @@ -1938,10 +1939,12 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, kvm_pic_clear_isr_ack(vcpu->kvm); vcpu->arch.nmi_injected = events->nmi.injected; - vcpu->arch.nmi_pending = events->nmi.pending; + if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) + vcpu->arch.nmi_pending = events->nmi.pending; kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked); - vcpu->arch.sipi_vector = events->sipi_vector; + if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR) + vcpu->arch.sipi_vector = events->sipi_vector; vcpu_put(vcpu); @@ -5068,12 +5071,13 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) GFP_KERNEL); if (!vcpu->arch.mce_banks) { r = -ENOMEM; - goto fail_mmu_destroy; + goto fail_free_lapic; } vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; return 0; - +fail_free_lapic: + kvm_free_lapic(vcpu); fail_mmu_destroy: kvm_mmu_destroy(vcpu); fail_free_pio_data: @@ -5084,6 +5088,7 @@ fail: void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) { + kfree(vcpu->arch.mce_banks); kvm_free_lapic(vcpu); down_read(&vcpu->kvm->slots_lock); kvm_mmu_destroy(vcpu); diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index c80245131fd..419386c24b8 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -14,7 +14,7 @@ $(obj)/inat.o: $(obj)/inat-tables.c clean-files := inat-tables.c -obj-$(CONFIG_SMP) += msr-smp.o +obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o lib-y := delay.o lib-y += thunk_$(BITS).o @@ -34,7 +34,7 @@ ifneq ($(CONFIG_X86_CMPXCHG64),y) endif lib-$(CONFIG_X86_USE_3DNOW) += mmx_32.o else - obj-y += io_64.o iomap_copy_64.o + obj-y += iomap_copy_64.o lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o lib-y += thunk_64.o clear_page_64.o copy_page_64.o lib-y += memmove_64.o memset_64.o diff --git a/arch/x86/lib/cache-smp.c b/arch/x86/lib/cache-smp.c new file mode 100644 index 00000000000..a3c66887503 --- /dev/null +++ b/arch/x86/lib/cache-smp.c @@ -0,0 +1,19 @@ +#include <linux/smp.h> +#include <linux/module.h> + +static void __wbinvd(void *dummy) +{ + wbinvd(); +} + +void wbinvd_on_cpu(int cpu) +{ + smp_call_function_single(cpu, __wbinvd, NULL, 1); +} +EXPORT_SYMBOL(wbinvd_on_cpu); + +int wbinvd_on_all_cpus(void) +{ + return on_each_cpu(__wbinvd, NULL, 1); +} +EXPORT_SYMBOL(wbinvd_on_all_cpus); diff --git a/arch/x86/lib/io_64.c b/arch/x86/lib/io_64.c deleted file mode 100644 index 3f1eb59b5f0..00000000000 --- a/arch/x86/lib/io_64.c +++ /dev/null @@ -1,25 +0,0 @@ -#include <linux/string.h> -#include <linux/module.h> -#include <asm/io.h> - -void __memcpy_toio(unsigned long dst, const void *src, unsigned len) -{ - __inline_memcpy((void *)dst, src, len); -} -EXPORT_SYMBOL(__memcpy_toio); - -void __memcpy_fromio(void *dst, unsigned long src, unsigned len) -{ - __inline_memcpy(dst, (const void *)src, len); -} -EXPORT_SYMBOL(__memcpy_fromio); - -void memset_io(volatile void __iomem *a, int b, size_t c) -{ - /* - * TODO: memset can mangle the IO patterns quite a bit. - * perhaps it would be better to use a dumb one: - */ - memset((void *)a, b, c); -} -EXPORT_SYMBOL(memset_io); diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 71da1bca13c..738e6593799 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -18,7 +18,7 @@ static inline pte_t gup_get_pte(pte_t *ptep) #else /* * With get_user_pages_fast, we walk down the pagetables without taking - * any locks. For this we would like to load the pointers atoimcally, + * any locks. For this we would like to load the pointers atomically, * but that is not possible (without expensive cmpxchg8b) on PAE. What * we do have is the guarantee that a pte will only either go from not * present to present, or present to not present or both -- it will not diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index d406c523901..e71c5cbc8f3 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -266,16 +266,9 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, 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(); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index c973f8e2a6c..2226f2c70ea 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -241,6 +241,7 @@ kernel_physical_mapping_init(unsigned long start, unsigned long page_size_mask) { int use_pse = page_size_mask == (1<<PG_LEVEL_2M); + unsigned long last_map_addr = end; unsigned long start_pfn, end_pfn; pgd_t *pgd_base = swapper_pg_dir; int pgd_idx, pmd_idx, pte_ofs; @@ -341,9 +342,10 @@ repeat: prot = PAGE_KERNEL_EXEC; pages_4k++; - if (mapping_iter == 1) + if (mapping_iter == 1) { set_pte(pte, pfn_pte(pfn, init_prot)); - else + last_map_addr = (pfn << PAGE_SHIFT) + PAGE_SIZE; + } else set_pte(pte, pfn_pte(pfn, prot)); } } @@ -368,7 +370,7 @@ repeat: mapping_iter = 2; goto repeat; } - return 0; + return last_map_addr; } pte_t *kmap_pte; @@ -892,8 +894,7 @@ void __init mem_init(void) reservedpages << (PAGE_SHIFT-10), datasize >> 10, initsize >> 10, - (unsigned long) (totalhigh_pages << (PAGE_SHIFT-10)) - ); + totalhigh_pages << (PAGE_SHIFT-10)); printk(KERN_INFO "virtual kernel memory layout:\n" " fixmap : 0x%08lx - 0x%08lx (%4ld kB)\n" diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 5198b9bb34e..69ddfbd9113 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -49,6 +49,7 @@ #include <asm/numa.h> #include <asm/cacheflush.h> #include <asm/init.h> +#include <linux/bootmem.h> static unsigned long dma_reserve __initdata; @@ -616,6 +617,21 @@ void __init paging_init(void) */ #ifdef CONFIG_MEMORY_HOTPLUG /* + * After memory hotplug the variables max_pfn, max_low_pfn and high_memory need + * updating. + */ +static void update_end_of_memory_vars(u64 start, u64 size) +{ + unsigned long end_pfn = PFN_UP(start + size); + + if (end_pfn > max_pfn) { + max_pfn = end_pfn; + max_low_pfn = end_pfn; + high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1; + } +} + +/* * Memory is added always to NORMAL zone. This means you will never get * additional DMA/DMA32 memory. */ @@ -634,6 +650,9 @@ int arch_add_memory(int nid, u64 start, u64 size) ret = __add_pages(nid, zone, start_pfn, nr_pages); WARN_ON_ONCE(ret); + /* update max_pfn, max_low_pfn and high_memory */ + update_end_of_memory_vars(start, size); + return ret; } EXPORT_SYMBOL_GPL(arch_add_memory); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 03c75ffd5c2..5eb1ba74a3a 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -24,43 +24,6 @@ #include "physaddr.h" -int page_is_ram(unsigned long pagenr) -{ - resource_size_t addr, end; - int i; - - /* - * A special case is the first 4Kb of memory; - * This is a BIOS owned area, not kernel ram, but generally - * not listed as such in the E820 table. - */ - if (pagenr == 0) - return 0; - - /* - * Second special case: Some BIOSen report the PC BIOS - * area (640->1Mb) as ram even though it is not. - */ - if (pagenr >= (BIOS_BEGIN >> PAGE_SHIFT) && - pagenr < (BIOS_END >> PAGE_SHIFT)) - return 0; - - for (i = 0; i < e820.nr_map; i++) { - /* - * Not usable memory: - */ - if (e820.map[i].type != E820_RAM) - continue; - addr = (e820.map[i].addr + PAGE_SIZE-1) >> PAGE_SHIFT; - end = (e820.map[i].addr + e820.map[i].size) >> PAGE_SHIFT; - - - if ((pagenr >= addr) && (pagenr < end)) - return 1; - } - return 0; -} - /* * Fix up the linear direct mapping of the kernel to avoid cache attribute * conflicts. diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c index 4901d0dafda..af3b6c8a436 100644 --- a/arch/x86/mm/kmemcheck/error.c +++ b/arch/x86/mm/kmemcheck/error.c @@ -106,26 +106,25 @@ void kmemcheck_error_recall(void) switch (e->type) { case KMEMCHECK_ERROR_INVALID_ACCESS: - printk(KERN_ERR "WARNING: kmemcheck: Caught %d-bit read " - "from %s memory (%p)\n", + printk(KERN_WARNING "WARNING: kmemcheck: Caught %d-bit read from %s memory (%p)\n", 8 * e->size, e->state < ARRAY_SIZE(desc) ? desc[e->state] : "(invalid shadow state)", (void *) e->address); - printk(KERN_INFO); + printk(KERN_WARNING); for (i = 0; i < SHADOW_COPY_SIZE; ++i) - printk("%02x", e->memory_copy[i]); - printk("\n"); + printk(KERN_CONT "%02x", e->memory_copy[i]); + printk(KERN_CONT "\n"); - printk(KERN_INFO); + printk(KERN_WARNING); for (i = 0; i < SHADOW_COPY_SIZE; ++i) { if (e->shadow_copy[i] < ARRAY_SIZE(short_desc)) - printk(" %c", short_desc[e->shadow_copy[i]]); + printk(KERN_CONT " %c", short_desc[e->shadow_copy[i]]); else - printk(" ?"); + printk(KERN_CONT " ?"); } - printk("\n"); - printk(KERN_INFO "%*c\n", 2 + 2 + printk(KERN_CONT "\n"); + printk(KERN_WARNING "%*c\n", 2 + 2 * (int) (e->address & (SHADOW_COPY_SIZE - 1)), '^'); break; case KMEMCHECK_ERROR_BUG: diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c index 8cc18334414..b3b531a4f8e 100644 --- a/arch/x86/mm/kmemcheck/kmemcheck.c +++ b/arch/x86/mm/kmemcheck/kmemcheck.c @@ -337,7 +337,7 @@ bool kmemcheck_is_obj_initialized(unsigned long addr, size_t size) if (!shadow) return true; - status = kmemcheck_shadow_test(shadow, size); + status = kmemcheck_shadow_test_all(shadow, size); return status == KMEMCHECK_SHADOW_INITIALIZED; } diff --git a/arch/x86/mm/kmemcheck/shadow.c b/arch/x86/mm/kmemcheck/shadow.c index 3f66b82076a..aec124214d9 100644 --- a/arch/x86/mm/kmemcheck/shadow.c +++ b/arch/x86/mm/kmemcheck/shadow.c @@ -125,12 +125,12 @@ void kmemcheck_mark_initialized_pages(struct page *p, unsigned int n) enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size) { +#ifdef CONFIG_KMEMCHECK_PARTIAL_OK uint8_t *x; unsigned int i; x = shadow; -#ifdef CONFIG_KMEMCHECK_PARTIAL_OK /* * Make sure _some_ bytes are initialized. Gcc frequently generates * code to access neighboring bytes. @@ -139,13 +139,25 @@ enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size) if (x[i] == KMEMCHECK_SHADOW_INITIALIZED) return x[i]; } + + return x[0]; #else + return kmemcheck_shadow_test_all(shadow, size); +#endif +} + +enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow, unsigned int size) +{ + uint8_t *x; + unsigned int i; + + x = shadow; + /* All bytes must be initialized. */ for (i = 0; i < size; ++i) { if (x[i] != KMEMCHECK_SHADOW_INITIALIZED) return x[i]; } -#endif return x[0]; } diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h index af46d9ab9d8..ff0b2f70fbc 100644 --- a/arch/x86/mm/kmemcheck/shadow.h +++ b/arch/x86/mm/kmemcheck/shadow.h @@ -11,6 +11,8 @@ enum kmemcheck_shadow { void *kmemcheck_shadow_lookup(unsigned long address); enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size); +enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow, + unsigned int size); void kmemcheck_shadow_set(void *shadow, unsigned int size); #endif diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index c0f6198565e..536fb682336 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -538,14 +538,15 @@ static int kmmio_die_notifier(struct notifier_block *nb, unsigned long val, void *args) { struct die_args *arg = args; + unsigned long* dr6_p = (unsigned long *)ERR_PTR(arg->err); - if (val == DIE_DEBUG && (arg->err & DR_STEP)) - if (post_kmmio_handler(arg->err, arg->regs) == 1) { + if (val == DIE_DEBUG && (*dr6_p & DR_STEP)) + if (post_kmmio_handler(*dr6_p, arg->regs) == 1) { /* * Reset the BS bit in dr6 (pointed by args->err) to * denote completion of processing */ - (*(unsigned long *)ERR_PTR(arg->err)) &= ~DR_STEP; + *dr6_p &= ~DR_STEP; return NOTIFY_STOP; } diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index c8191defc38..1dab5194fd9 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -71,7 +71,7 @@ static int mmap_is_legacy(void) if (current->personality & ADDR_COMPAT_LAYOUT) return 1; - if (current->signal->rlim[RLIMIT_STACK].rlim_cur == RLIM_INFINITY) + if (rlimit(RLIMIT_STACK) == RLIM_INFINITY) return 1; return sysctl_legacy_va_layout; @@ -96,7 +96,7 @@ static unsigned long mmap_rnd(void) static unsigned long mmap_base(void) { - unsigned long gap = current->signal->rlim[RLIMIT_STACK].rlim_cur; + unsigned long gap = rlimit(RLIMIT_STACK); if (gap < MIN_GAP) gap = MIN_GAP; diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 83bbc70d11b..3307ea8bd43 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -427,7 +427,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr, * Calculate the number of big nodes that can be allocated as a result * of consolidating the remainder. */ - big = ((size & ~FAKE_NODE_MIN_HASH_MASK) & nr_nodes) / + big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * nr_nodes) / FAKE_NODE_MIN_SIZE; size &= FAKE_NODE_MIN_HASH_MASK; @@ -502,77 +502,99 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr, } /* - * Splits num_nodes nodes up equally starting at node_start. The return value - * is the number of nodes split up and addr is adjusted to be at the end of the - * last node allocated. + * Returns the end address of a node so that there is at least `size' amount of + * non-reserved memory or `max_addr' is reached. */ -static int __init split_nodes_equally(u64 *addr, u64 max_addr, int node_start, - int num_nodes) +static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size) { - unsigned int big; - u64 size; - int i; - - if (num_nodes <= 0) - return -1; - if (num_nodes > MAX_NUMNODES) - num_nodes = MAX_NUMNODES; - size = (max_addr - *addr - e820_hole_size(*addr, max_addr)) / - num_nodes; - /* - * Calculate the number of big nodes that can be allocated as a result - * of consolidating the leftovers. - */ - big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * num_nodes) / - FAKE_NODE_MIN_SIZE; - - /* Round down to nearest FAKE_NODE_MIN_SIZE. */ - size &= FAKE_NODE_MIN_HASH_MASK; - if (!size) { - printk(KERN_ERR "Not enough memory for each node. " - "NUMA emulation disabled.\n"); - return -1; - } - - for (i = node_start; i < num_nodes + node_start; i++) { - u64 end = *addr + size; + u64 end = start + size; - if (i < big) - end += FAKE_NODE_MIN_SIZE; - /* - * The final node can have the remaining system RAM. Other - * nodes receive roughly the same amount of available pages. - */ - if (i == num_nodes + node_start - 1) + while (end - start - e820_hole_size(start, end) < size) { + end += FAKE_NODE_MIN_SIZE; + if (end > max_addr) { end = max_addr; - else - while (end - *addr - e820_hole_size(*addr, end) < - size) { - end += FAKE_NODE_MIN_SIZE; - if (end > max_addr) { - end = max_addr; - break; - } - } - if (setup_node_range(i, addr, end - *addr, max_addr) < 0) break; + } } - return i - node_start + 1; + return end; } /* - * Splits the remaining system RAM into chunks of size. The remaining memory is - * always assigned to a final node and can be asymmetric. Returns the number of - * nodes split. + * Sets up fake nodes of `size' interleaved over physical nodes ranging from + * `addr' to `max_addr'. The return value is the number of nodes allocated. */ -static int __init split_nodes_by_size(u64 *addr, u64 max_addr, int node_start, - u64 size) +static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size) { - int i = node_start; - size = (size << 20) & FAKE_NODE_MIN_HASH_MASK; - while (!setup_node_range(i++, addr, size, max_addr)) - ; - return i - node_start; + nodemask_t physnode_mask = NODE_MASK_NONE; + u64 min_size; + int ret = 0; + int i; + + if (!size) + return -1; + /* + * The limit on emulated nodes is MAX_NUMNODES, so the size per node is + * increased accordingly if the requested size is too small. This + * creates a uniform distribution of node sizes across the entire + * machine (but not necessarily over physical nodes). + */ + min_size = (max_addr - addr - e820_hole_size(addr, max_addr)) / + MAX_NUMNODES; + min_size = max(min_size, FAKE_NODE_MIN_SIZE); + if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size) + min_size = (min_size + FAKE_NODE_MIN_SIZE) & + FAKE_NODE_MIN_HASH_MASK; + if (size < min_size) { + pr_err("Fake node size %LuMB too small, increasing to %LuMB\n", + size >> 20, min_size >> 20); + size = min_size; + } + size &= FAKE_NODE_MIN_HASH_MASK; + + for (i = 0; i < MAX_NUMNODES; i++) + if (physnodes[i].start != physnodes[i].end) + node_set(i, physnode_mask); + /* + * Fill physical nodes with fake nodes of size until there is no memory + * left on any of them. + */ + while (nodes_weight(physnode_mask)) { + for_each_node_mask(i, physnode_mask) { + u64 dma32_end = MAX_DMA32_PFN << PAGE_SHIFT; + u64 end; + + end = find_end_of_node(physnodes[i].start, + physnodes[i].end, size); + /* + * If there won't be at least FAKE_NODE_MIN_SIZE of + * non-reserved memory in ZONE_DMA32 for the next node, + * this one must extend to the boundary. + */ + if (end < dma32_end && dma32_end - end - + e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) + end = dma32_end; + + /* + * If there won't be enough non-reserved memory for the + * next node, this one must extend to the end of the + * physical node. + */ + if (physnodes[i].end - end - + e820_hole_size(end, physnodes[i].end) < size) + end = physnodes[i].end; + + /* + * Setup the fake node that will be allocated as bootmem + * later. If setup_node_range() returns non-zero, there + * is no more memory available on this physical node. + */ + if (setup_node_range(ret++, &physnodes[i].start, + end - physnodes[i].start, + physnodes[i].end) < 0) + node_clear(i, physnode_mask); + } + } + return ret; } /* @@ -582,87 +604,32 @@ static int __init split_nodes_by_size(u64 *addr, u64 max_addr, int node_start, static int __init numa_emulation(unsigned long start_pfn, unsigned long last_pfn, int acpi, int k8) { - u64 size, addr = start_pfn << PAGE_SHIFT; + u64 addr = start_pfn << PAGE_SHIFT; u64 max_addr = last_pfn << PAGE_SHIFT; - int num_nodes = 0, num = 0, coeff_flag, coeff = -1, i; int num_phys_nodes; + int num_nodes; + int i; num_phys_nodes = setup_physnodes(addr, max_addr, acpi, k8); /* - * If the numa=fake command-line is just a single number N, split the - * system RAM into N fake nodes. + * If the numa=fake command-line contains a 'M' or 'G', it represents + * the fixed node size. Otherwise, if it is just a single number N, + * split the system RAM into N fake nodes. */ - if (!strchr(cmdline, '*') && !strchr(cmdline, ',')) { - long n = simple_strtol(cmdline, NULL, 0); - - num_nodes = split_nodes_interleave(addr, max_addr, - num_phys_nodes, n); - if (num_nodes < 0) - return num_nodes; - goto out; - } + if (strchr(cmdline, 'M') || strchr(cmdline, 'G')) { + u64 size; - /* Parse the command line. */ - for (coeff_flag = 0; ; cmdline++) { - if (*cmdline && isdigit(*cmdline)) { - num = num * 10 + *cmdline - '0'; - continue; - } - if (*cmdline == '*') { - if (num > 0) - coeff = num; - coeff_flag = 1; - } - if (!*cmdline || *cmdline == ',') { - if (!coeff_flag) - coeff = 1; - /* - * Round down to the nearest FAKE_NODE_MIN_SIZE. - * Command-line coefficients are in megabytes. - */ - size = ((u64)num << 20) & FAKE_NODE_MIN_HASH_MASK; - if (size) - for (i = 0; i < coeff; i++, num_nodes++) - if (setup_node_range(num_nodes, &addr, - size, max_addr) < 0) - goto done; - if (!*cmdline) - break; - coeff_flag = 0; - coeff = -1; - } - num = 0; - } -done: - if (!num_nodes) - return -1; - /* Fill remainder of system RAM, if appropriate. */ - if (addr < max_addr) { - if (coeff_flag && coeff < 0) { - /* Split remaining nodes into num-sized chunks */ - num_nodes += split_nodes_by_size(&addr, max_addr, - num_nodes, num); - goto out; - } - switch (*(cmdline - 1)) { - case '*': - /* Split remaining nodes into coeff chunks */ - if (coeff <= 0) - break; - num_nodes += split_nodes_equally(&addr, max_addr, - num_nodes, coeff); - break; - case ',': - /* Do not allocate remaining system RAM */ - break; - default: - /* Give one final node */ - setup_node_range(num_nodes, &addr, max_addr - addr, - max_addr); - num_nodes++; - } + size = memparse(cmdline, &cmdline); + num_nodes = split_nodes_size_interleave(addr, max_addr, size); + } else { + unsigned long n; + + n = simple_strtoul(cmdline, NULL, 0); + num_nodes = split_nodes_interleave(addr, max_addr, num_phys_nodes, n); } -out: + + if (num_nodes < 0) + return num_nodes; memnode_shift = compute_hash_shift(nodes, num_nodes, NULL); if (memnode_shift < 0) { memnode_shift = 0; diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index ed34f5e3599..c9ba9deafe8 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -6,6 +6,14 @@ #define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO +#ifdef CONFIG_HIGHPTE +#define PGALLOC_USER_GFP __GFP_HIGHMEM +#else +#define PGALLOC_USER_GFP 0 +#endif + +gfp_t __userpte_alloc_gfp = PGALLOC_GFP | PGALLOC_USER_GFP; + pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { return (pte_t *)__get_free_page(PGALLOC_GFP); @@ -15,16 +23,29 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { struct page *pte; -#ifdef CONFIG_HIGHPTE - pte = alloc_pages(PGALLOC_GFP | __GFP_HIGHMEM, 0); -#else - pte = alloc_pages(PGALLOC_GFP, 0); -#endif + pte = alloc_pages(__userpte_alloc_gfp, 0); if (pte) pgtable_page_ctor(pte); return pte; } +static int __init setup_userpte(char *arg) +{ + if (!arg) + return -EINVAL; + + /* + * "userpte=nohigh" disables allocation of user pagetables in + * high memory. + */ + if (strcmp(arg, "nohigh") == 0) + __userpte_alloc_gfp &= ~__GFP_HIGHMEM; + else + return -EINVAL; + return 0; +} +early_param("userpte", setup_userpte); + void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) { pgtable_page_dtor(pte); diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index a27124185fc..28c68762648 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -229,9 +229,11 @@ update_nodes_add(int node, unsigned long start, unsigned long end) printk(KERN_ERR "SRAT: Hotplug zone not continuous. Partly ignored\n"); } - if (changed) + if (changed) { + node_set(node, cpu_nodes_parsed); printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n", nd->start, nd->end); + } } /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */ diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 65b58e4b0b8..426f3a1a64d 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -41,7 +41,7 @@ union smp_flush_state { struct { struct mm_struct *flush_mm; unsigned long flush_va; - spinlock_t tlbstate_lock; + raw_spinlock_t tlbstate_lock; DECLARE_BITMAP(flush_cpumask, NR_CPUS); }; char pad[INTERNODE_CACHE_BYTES]; @@ -181,7 +181,7 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask, * num_online_cpus() <= NUM_INVALIDATE_TLB_VECTORS, but it is * probably not worth checking this for a cache-hot lock. */ - spin_lock(&f->tlbstate_lock); + raw_spin_lock(&f->tlbstate_lock); f->flush_mm = mm; f->flush_va = va; @@ -199,7 +199,7 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask, f->flush_mm = NULL; f->flush_va = 0; - spin_unlock(&f->tlbstate_lock); + raw_spin_unlock(&f->tlbstate_lock); } void native_flush_tlb_others(const struct cpumask *cpumask, @@ -223,7 +223,7 @@ static int __cpuinit init_smp_flush(void) int i; for (i = 0; i < ARRAY_SIZE(flush_state); i++) - spin_lock_init(&flush_state[i].tlbstate_lock); + raw_spin_lock_init(&flush_state[i].tlbstate_lock); return 0; } diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index cb88b1a0bd5..2c505ee7101 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -159,7 +159,7 @@ static int nmi_setup_mux(void) for_each_possible_cpu(i) { per_cpu(cpu_msrs, i).multiplex = - kmalloc(multiplex_size, GFP_KERNEL); + kzalloc(multiplex_size, GFP_KERNEL); if (!per_cpu(cpu_msrs, i).multiplex) return 0; } @@ -179,7 +179,6 @@ static void nmi_cpu_setup_mux(int cpu, struct op_msrs const * const msrs) if (counter_config[i].enabled) { multiplex[i].saved = -(u64)counter_config[i].count; } else { - multiplex[i].addr = 0; multiplex[i].saved = 0; } } @@ -189,25 +188,27 @@ static void nmi_cpu_setup_mux(int cpu, struct op_msrs const * const msrs) static void nmi_cpu_save_mpx_registers(struct op_msrs *msrs) { + struct op_msr *counters = msrs->counters; struct op_msr *multiplex = msrs->multiplex; int i; for (i = 0; i < model->num_counters; ++i) { int virt = op_x86_phys_to_virt(i); - if (multiplex[virt].addr) - rdmsrl(multiplex[virt].addr, multiplex[virt].saved); + if (counters[i].addr) + rdmsrl(counters[i].addr, multiplex[virt].saved); } } static void nmi_cpu_restore_mpx_registers(struct op_msrs *msrs) { + struct op_msr *counters = msrs->counters; struct op_msr *multiplex = msrs->multiplex; int i; for (i = 0; i < model->num_counters; ++i) { int virt = op_x86_phys_to_virt(i); - if (multiplex[virt].addr) - wrmsrl(multiplex[virt].addr, multiplex[virt].saved); + if (counters[i].addr) + wrmsrl(counters[i].addr, multiplex[virt].saved); } } @@ -222,7 +223,7 @@ static void nmi_cpu_switch(void *dummy) /* move to next set */ si += model->num_counters; - if ((si > model->num_virt_counters) || (counter_config[si].count == 0)) + if ((si >= model->num_virt_counters) || (counter_config[si].count == 0)) per_cpu(switch_index, cpu) = 0; else per_cpu(switch_index, cpu) = si; @@ -303,11 +304,11 @@ static int allocate_msrs(void) int i; for_each_possible_cpu(i) { - per_cpu(cpu_msrs, i).counters = kmalloc(counters_size, + per_cpu(cpu_msrs, i).counters = kzalloc(counters_size, GFP_KERNEL); if (!per_cpu(cpu_msrs, i).counters) return 0; - per_cpu(cpu_msrs, i).controls = kmalloc(controls_size, + per_cpu(cpu_msrs, i).controls = kzalloc(controls_size, GFP_KERNEL); if (!per_cpu(cpu_msrs, i).controls) return 0; @@ -598,6 +599,7 @@ static int __init ppro_init(char **cpu_type) case 15: case 23: *cpu_type = "i386/core_2"; break; + case 0x2e: case 26: spec = &op_arch_perfmon_spec; *cpu_type = "i386/core_i7"; diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index 39686c29f03..6a58256dce9 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -22,6 +22,9 @@ #include <asm/ptrace.h> #include <asm/msr.h> #include <asm/nmi.h> +#include <asm/apic.h> +#include <asm/processor.h> +#include <asm/cpufeature.h> #include "op_x86_model.h" #include "op_counter.h" @@ -43,15 +46,13 @@ static unsigned long reset_value[NUM_VIRT_COUNTERS]; -#ifdef CONFIG_OPROFILE_IBS - /* IbsFetchCtl bits/masks */ #define IBS_FETCH_RAND_EN (1ULL<<57) #define IBS_FETCH_VAL (1ULL<<49) #define IBS_FETCH_ENABLE (1ULL<<48) #define IBS_FETCH_CNT_MASK 0xFFFF0000ULL -/*IbsOpCtl bits */ +/* IbsOpCtl bits */ #define IBS_OP_CNT_CTL (1ULL<<19) #define IBS_OP_VAL (1ULL<<18) #define IBS_OP_ENABLE (1ULL<<17) @@ -59,7 +60,7 @@ static unsigned long reset_value[NUM_VIRT_COUNTERS]; #define IBS_FETCH_SIZE 6 #define IBS_OP_SIZE 12 -static int has_ibs; /* AMD Family10h and later */ +static u32 ibs_caps; struct op_ibs_config { unsigned long op_enabled; @@ -71,24 +72,52 @@ struct op_ibs_config { }; static struct op_ibs_config ibs_config; +static u64 ibs_op_ctl; -#endif +/* + * IBS cpuid feature detection + */ -#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX +#define IBS_CPUID_FEATURES 0x8000001b + +/* + * Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but + * bit 0 is used to indicate the existence of IBS. + */ +#define IBS_CAPS_AVAIL (1LL<<0) +#define IBS_CAPS_RDWROPCNT (1LL<<3) +#define IBS_CAPS_OPCNT (1LL<<4) + +/* + * IBS randomization macros + */ +#define IBS_RANDOM_BITS 12 +#define IBS_RANDOM_MASK ((1ULL << IBS_RANDOM_BITS) - 1) +#define IBS_RANDOM_MAXCNT_OFFSET (1ULL << (IBS_RANDOM_BITS - 5)) -static void op_mux_fill_in_addresses(struct op_msrs * const msrs) +static u32 get_ibs_caps(void) { - int i; + u32 ibs_caps; + unsigned int max_level; - for (i = 0; i < NUM_VIRT_COUNTERS; i++) { - int hw_counter = op_x86_virt_to_phys(i); - if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i)) - msrs->multiplex[i].addr = MSR_K7_PERFCTR0 + hw_counter; - else - msrs->multiplex[i].addr = 0; - } + if (!boot_cpu_has(X86_FEATURE_IBS)) + return 0; + + /* check IBS cpuid feature flags */ + max_level = cpuid_eax(0x80000000); + if (max_level < IBS_CPUID_FEATURES) + return IBS_CAPS_AVAIL; + + ibs_caps = cpuid_eax(IBS_CPUID_FEATURES); + if (!(ibs_caps & IBS_CAPS_AVAIL)) + /* cpuid flags not valid */ + return IBS_CAPS_AVAIL; + + return ibs_caps; } +#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX + static void op_mux_switch_ctrl(struct op_x86_model_spec const *model, struct op_msrs const * const msrs) { @@ -98,7 +127,7 @@ static void op_mux_switch_ctrl(struct op_x86_model_spec const *model, /* enable active counters */ for (i = 0; i < NUM_COUNTERS; ++i) { int virt = op_x86_phys_to_virt(i); - if (!counter_config[virt].enabled) + if (!reset_value[virt]) continue; rdmsrl(msrs->controls[i].addr, val); val &= model->reserved; @@ -107,10 +136,6 @@ static void op_mux_switch_ctrl(struct op_x86_model_spec const *model, } } -#else - -static inline void op_mux_fill_in_addresses(struct op_msrs * const msrs) { } - #endif /* functions for op_amd_spec */ @@ -122,18 +147,12 @@ static void op_amd_fill_in_addresses(struct op_msrs * const msrs) for (i = 0; i < NUM_COUNTERS; i++) { if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i)) msrs->counters[i].addr = MSR_K7_PERFCTR0 + i; - else - msrs->counters[i].addr = 0; } for (i = 0; i < NUM_CONTROLS; i++) { if (reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i; - else - msrs->controls[i].addr = 0; } - - op_mux_fill_in_addresses(msrs); } static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, @@ -144,7 +163,8 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, /* setup reset_value */ for (i = 0; i < NUM_VIRT_COUNTERS; ++i) { - if (counter_config[i].enabled) + if (counter_config[i].enabled + && msrs->counters[op_x86_virt_to_phys(i)].addr) reset_value[i] = counter_config[i].count; else reset_value[i] = 0; @@ -152,9 +172,18 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, /* clear all counters */ for (i = 0; i < NUM_CONTROLS; ++i) { - if (unlikely(!msrs->controls[i].addr)) + if (unlikely(!msrs->controls[i].addr)) { + if (counter_config[i].enabled && !smp_processor_id()) + /* + * counter is reserved, this is on all + * cpus, so report only for cpu #0 + */ + op_x86_warn_reserved(i); continue; + } rdmsrl(msrs->controls[i].addr, val); + if (val & ARCH_PERFMON_EVENTSEL0_ENABLE) + op_x86_warn_in_use(i); val &= model->reserved; wrmsrl(msrs->controls[i].addr, val); } @@ -169,9 +198,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, /* enable active counters */ for (i = 0; i < NUM_COUNTERS; ++i) { int virt = op_x86_phys_to_virt(i); - if (!counter_config[virt].enabled) - continue; - if (!msrs->counters[i].addr) + if (!reset_value[virt]) continue; /* setup counter registers */ @@ -185,7 +212,60 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, } } -#ifdef CONFIG_OPROFILE_IBS +/* + * 16-bit Linear Feedback Shift Register (LFSR) + * + * 16 14 13 11 + * Feedback polynomial = X + X + X + X + 1 + */ +static unsigned int lfsr_random(void) +{ + static unsigned int lfsr_value = 0xF00D; + unsigned int bit; + + /* Compute next bit to shift in */ + bit = ((lfsr_value >> 0) ^ + (lfsr_value >> 2) ^ + (lfsr_value >> 3) ^ + (lfsr_value >> 5)) & 0x0001; + + /* Advance to next register value */ + lfsr_value = (lfsr_value >> 1) | (bit << 15); + + return lfsr_value; +} + +/* + * IBS software randomization + * + * The IBS periodic op counter is randomized in software. The lower 12 + * bits of the 20 bit counter are randomized. IbsOpCurCnt is + * initialized with a 12 bit random value. + */ +static inline u64 op_amd_randomize_ibs_op(u64 val) +{ + unsigned int random = lfsr_random(); + + if (!(ibs_caps & IBS_CAPS_RDWROPCNT)) + /* + * Work around if the hw can not write to IbsOpCurCnt + * + * Randomize the lower 8 bits of the 16 bit + * IbsOpMaxCnt [15:0] value in the range of -128 to + * +127 by adding/subtracting an offset to the + * maximum count (IbsOpMaxCnt). + * + * To avoid over or underflows and protect upper bits + * starting at bit 16, the initial value for + * IbsOpMaxCnt must fit in the range from 0x0081 to + * 0xff80. + */ + val += (s8)(random >> 4); + else + val |= (u64)(random & IBS_RANDOM_MASK) << 32; + + return val; +} static inline void op_amd_handle_ibs(struct pt_regs * const regs, @@ -194,7 +274,7 @@ op_amd_handle_ibs(struct pt_regs * const regs, u64 val, ctl; struct op_entry entry; - if (!has_ibs) + if (!ibs_caps) return; if (ibs_config.fetch_enabled) { @@ -236,8 +316,7 @@ op_amd_handle_ibs(struct pt_regs * const regs, oprofile_write_commit(&entry); /* reenable the IRQ */ - ctl &= ~IBS_OP_VAL & 0xFFFFFFFF; - ctl |= IBS_OP_ENABLE; + ctl = op_amd_randomize_ibs_op(ibs_op_ctl); wrmsrl(MSR_AMD64_IBSOPCTL, ctl); } } @@ -246,41 +325,57 @@ op_amd_handle_ibs(struct pt_regs * const regs, static inline void op_amd_start_ibs(void) { u64 val; - if (has_ibs && ibs_config.fetch_enabled) { + + if (!ibs_caps) + return; + + if (ibs_config.fetch_enabled) { val = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF; val |= ibs_config.rand_en ? IBS_FETCH_RAND_EN : 0; val |= IBS_FETCH_ENABLE; wrmsrl(MSR_AMD64_IBSFETCHCTL, val); } - if (has_ibs && ibs_config.op_enabled) { - val = (ibs_config.max_cnt_op >> 4) & 0xFFFF; - val |= ibs_config.dispatched_ops ? IBS_OP_CNT_CTL : 0; - val |= IBS_OP_ENABLE; + if (ibs_config.op_enabled) { + ibs_op_ctl = ibs_config.max_cnt_op >> 4; + if (!(ibs_caps & IBS_CAPS_RDWROPCNT)) { + /* + * IbsOpCurCnt not supported. See + * op_amd_randomize_ibs_op() for details. + */ + ibs_op_ctl = clamp(ibs_op_ctl, 0x0081ULL, 0xFF80ULL); + } else { + /* + * The start value is randomized with a + * positive offset, we need to compensate it + * with the half of the randomized range. Also + * avoid underflows. + */ + ibs_op_ctl = min(ibs_op_ctl + IBS_RANDOM_MAXCNT_OFFSET, + 0xFFFFULL); + } + if (ibs_caps & IBS_CAPS_OPCNT && ibs_config.dispatched_ops) + ibs_op_ctl |= IBS_OP_CNT_CTL; + ibs_op_ctl |= IBS_OP_ENABLE; + val = op_amd_randomize_ibs_op(ibs_op_ctl); wrmsrl(MSR_AMD64_IBSOPCTL, val); } } static void op_amd_stop_ibs(void) { - if (has_ibs && ibs_config.fetch_enabled) + if (!ibs_caps) + return; + + if (ibs_config.fetch_enabled) /* clear max count and enable */ wrmsrl(MSR_AMD64_IBSFETCHCTL, 0); - if (has_ibs && ibs_config.op_enabled) + if (ibs_config.op_enabled) /* clear max count and enable */ wrmsrl(MSR_AMD64_IBSOPCTL, 0); } -#else - -static inline void op_amd_handle_ibs(struct pt_regs * const regs, - struct op_msrs const * const msrs) { } -static inline void op_amd_start_ibs(void) { } -static inline void op_amd_stop_ibs(void) { } - -#endif - static int op_amd_check_ctrs(struct pt_regs * const regs, struct op_msrs const * const msrs) { @@ -355,8 +450,6 @@ static void op_amd_shutdown(struct op_msrs const * const msrs) } } -#ifdef CONFIG_OPROFILE_IBS - static u8 ibs_eilvt_off; static inline void apic_init_ibs_nmi_per_cpu(void *arg) @@ -405,45 +498,36 @@ static int init_ibs_nmi(void) return 1; } -#ifdef CONFIG_NUMA - /* Sanity check */ - /* Works only for 64bit with proper numa implementation. */ - if (nodes != num_possible_nodes()) { - printk(KERN_DEBUG "Failed to setup CPU node(s) for IBS, " - "found: %d, expected %d", - nodes, num_possible_nodes()); - return 1; - } -#endif return 0; } /* uninitialize the APIC for the IBS interrupts if needed */ static void clear_ibs_nmi(void) { - if (has_ibs) + if (ibs_caps) on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1); } /* initialize the APIC for the IBS interrupts if available */ static void ibs_init(void) { - has_ibs = boot_cpu_has(X86_FEATURE_IBS); + ibs_caps = get_ibs_caps(); - if (!has_ibs) + if (!ibs_caps) return; if (init_ibs_nmi()) { - has_ibs = 0; + ibs_caps = 0; return; } - printk(KERN_INFO "oprofile: AMD IBS detected\n"); + printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", + (unsigned)ibs_caps); } static void ibs_exit(void) { - if (!has_ibs) + if (!ibs_caps) return; clear_ibs_nmi(); @@ -463,7 +547,7 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root) if (ret) return ret; - if (!has_ibs) + if (!ibs_caps) return ret; /* model specific files */ @@ -473,7 +557,7 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root) ibs_config.fetch_enabled = 0; ibs_config.max_cnt_op = 250000; ibs_config.op_enabled = 0; - ibs_config.dispatched_ops = 1; + ibs_config.dispatched_ops = 0; dir = oprofilefs_mkdir(sb, root, "ibs_fetch"); oprofilefs_create_ulong(sb, dir, "enable", @@ -488,8 +572,9 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root) &ibs_config.op_enabled); oprofilefs_create_ulong(sb, dir, "max_count", &ibs_config.max_cnt_op); - oprofilefs_create_ulong(sb, dir, "dispatched_ops", - &ibs_config.dispatched_ops); + if (ibs_caps & IBS_CAPS_OPCNT) + oprofilefs_create_ulong(sb, dir, "dispatched_ops", + &ibs_config.dispatched_ops); return 0; } @@ -507,19 +592,6 @@ static void op_amd_exit(void) ibs_exit(); } -#else - -/* no IBS support */ - -static int op_amd_init(struct oprofile_operations *ops) -{ - return 0; -} - -static void op_amd_exit(void) {} - -#endif /* CONFIG_OPROFILE_IBS */ - struct op_x86_model_spec op_amd_spec = { .num_counters = NUM_COUNTERS, .num_controls = NUM_CONTROLS, diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c index ac6b354becd..e6a160a4684 100644 --- a/arch/x86/oprofile/op_model_p4.c +++ b/arch/x86/oprofile/op_model_p4.c @@ -394,12 +394,6 @@ static void p4_fill_in_addresses(struct op_msrs * const msrs) setup_num_counters(); stag = get_stagger(); - /* initialize some registers */ - for (i = 0; i < num_counters; ++i) - msrs->counters[i].addr = 0; - for (i = 0; i < num_controls; ++i) - msrs->controls[i].addr = 0; - /* the counter & cccr registers we pay attention to */ for (i = 0; i < num_counters; ++i) { addr = p4_counters[VIRT_CTR(stag, i)].counter_address; diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index 8eb05878554..5d1727ba409 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -37,15 +37,11 @@ static void ppro_fill_in_addresses(struct op_msrs * const msrs) for (i = 0; i < num_counters; i++) { if (reserve_perfctr_nmi(MSR_P6_PERFCTR0 + i)) msrs->counters[i].addr = MSR_P6_PERFCTR0 + i; - else - msrs->counters[i].addr = 0; } for (i = 0; i < num_counters; i++) { if (reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i)) msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i; - else - msrs->controls[i].addr = 0; } } @@ -57,7 +53,7 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model, int i; if (!reset_value) { - reset_value = kmalloc(sizeof(reset_value[0]) * num_counters, + reset_value = kzalloc(sizeof(reset_value[0]) * num_counters, GFP_ATOMIC); if (!reset_value) return; @@ -82,9 +78,18 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model, /* clear all counters */ for (i = 0; i < num_counters; ++i) { - if (unlikely(!msrs->controls[i].addr)) + if (unlikely(!msrs->controls[i].addr)) { + if (counter_config[i].enabled && !smp_processor_id()) + /* + * counter is reserved, this is on all + * cpus, so report only for cpu #0 + */ + op_x86_warn_reserved(i); continue; + } rdmsrl(msrs->controls[i].addr, val); + if (val & ARCH_PERFMON_EVENTSEL0_ENABLE) + op_x86_warn_in_use(i); val &= model->reserved; wrmsrl(msrs->controls[i].addr, val); } diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h index 7b8e75d1608..ff82a755edd 100644 --- a/arch/x86/oprofile/op_x86_model.h +++ b/arch/x86/oprofile/op_x86_model.h @@ -57,6 +57,26 @@ struct op_x86_model_spec { struct op_counter_config; +static inline void op_x86_warn_in_use(int counter) +{ + /* + * The warning indicates an already running counter. If + * oprofile doesn't collect data, then try using a different + * performance counter on your platform to monitor the desired + * event. Delete counter #%d from the desired event by editing + * the /usr/share/oprofile/%s/<cpu>/events file. If the event + * cannot be monitored by any other counter, contact your + * hardware or BIOS vendor. + */ + pr_warning("oprofile: counter #%d on cpu #%d may already be used\n", + counter, smp_processor_id()); +} + +static inline void op_x86_warn_reserved(int counter) +{ + pr_warning("oprofile: counter #%d is already reserved\n", counter); +} + extern u64 op_x86_get_ctrl(struct op_x86_model_spec const *model, struct op_counter_config *counter_config); extern int op_x86_phys_to_virt(int phys); diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile index 564b008a51c..39fba37f702 100644 --- a/arch/x86/pci/Makefile +++ b/arch/x86/pci/Makefile @@ -15,7 +15,7 @@ obj-$(CONFIG_X86_NUMAQ) += numaq_32.o obj-y += common.o early.o obj-y += amd_bus.o -obj-$(CONFIG_X86_64) += bus_numa.o intel_bus.o +obj-$(CONFIG_X86_64) += bus_numa.o ifeq ($(CONFIG_PCI_DEBUG),y) EXTRA_CFLAGS += -DDEBUG diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 959e548a703..5f11ff6f538 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -15,6 +15,51 @@ struct pci_root_info { int busnum; }; +static bool pci_use_crs = true; + +static int __init set_use_crs(const struct dmi_system_id *id) +{ + pci_use_crs = true; + return 0; +} + +static const struct dmi_system_id pci_use_crs_table[] __initconst = { + /* http://bugzilla.kernel.org/show_bug.cgi?id=14183 */ + { + .callback = set_use_crs, + .ident = "IBM System x3800", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "IBM"), + DMI_MATCH(DMI_PRODUCT_NAME, "x3800"), + }, + }, + {} +}; + +void __init pci_acpi_crs_quirks(void) +{ + int year; + + if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008) + pci_use_crs = false; + + dmi_check_system(pci_use_crs_table); + + /* + * If the user specifies "pci=use_crs" or "pci=nocrs" explicitly, that + * takes precedence over anything we figured out above. + */ + if (pci_probe & PCI_ROOT_NO_CRS) + pci_use_crs = false; + else if (pci_probe & PCI_USE__CRS) + pci_use_crs = true; + + printk(KERN_INFO "PCI: %s host bridge windows from ACPI; " + "if necessary, use \"pci=%s\" and report a bug\n", + pci_use_crs ? "Using" : "Ignoring", + pci_use_crs ? "nocrs" : "use_crs"); +} + static acpi_status resource_to_addr(struct acpi_resource *resource, struct acpi_resource_address64 *addr) @@ -45,20 +90,6 @@ count_resource(struct acpi_resource *acpi_res, void *data) return AE_OK; } -static int -bus_has_transparent_bridge(struct pci_bus *bus) -{ - struct pci_dev *dev; - - list_for_each_entry(dev, &bus->devices, bus_list) { - u16 class = dev->class >> 8; - - if (class == PCI_CLASS_BRIDGE_PCI && dev->transparent) - return true; - } - return false; -} - static void align_resource(struct acpi_device *bridge, struct resource *res) { @@ -92,12 +123,8 @@ setup_resource(struct acpi_resource *acpi_res, void *data) acpi_status status; unsigned long flags; struct resource *root; - int max_root_bus_resources = PCI_BUS_NUM_RESOURCES; u64 start, end; - if (bus_has_transparent_bridge(info->bus)) - max_root_bus_resources -= 3; - status = resource_to_addr(acpi_res, &addr); if (!ACPI_SUCCESS(status)) return AE_OK; @@ -115,15 +142,6 @@ setup_resource(struct acpi_resource *acpi_res, void *data) start = addr.minimum + addr.translation_offset; end = start + addr.address_length - 1; - if (info->res_num >= max_root_bus_resources) { - if (pci_probe & PCI_USE__CRS) - printk(KERN_WARNING "PCI: Failed to allocate " - "0x%lx-0x%lx from %s for %s due to _CRS " - "returning more than %d resource descriptors\n", - (unsigned long) start, (unsigned long) end, - root->name, info->name, max_root_bus_resources); - return AE_OK; - } res = &info->res[info->res_num]; res->name = info->name; @@ -133,7 +151,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data) res->child = NULL; align_resource(info->bridge, res); - if (!(pci_probe & PCI_USE__CRS)) { + if (!pci_use_crs) { dev_printk(KERN_DEBUG, &info->bridge->dev, "host bridge window %pR (ignored)\n", res); return AE_OK; @@ -143,7 +161,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data) dev_err(&info->bridge->dev, "can't allocate host bridge window %pR\n", res); } else { - info->bus->resource[info->res_num] = res; + pci_bus_add_resource(info->bus, res, 0); info->res_num++; if (addr.translation_offset) dev_info(&info->bridge->dev, "host bridge window %pR " @@ -164,10 +182,8 @@ get_current_resources(struct acpi_device *device, int busnum, struct pci_root_info info; size_t size; - if (!(pci_probe & PCI_USE__CRS)) - dev_info(&device->dev, - "ignoring host bridge windows from ACPI; " - "boot with \"pci=use_crs\" to use them\n"); + if (pci_use_crs) + pci_bus_remove_resources(bus); info.bridge = device; info.bus = bus; diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c index 145df00e038..12d54ff3654 100644 --- a/arch/x86/pci/bus_numa.c +++ b/arch/x86/pci/bus_numa.c @@ -36,13 +36,14 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b) printk(KERN_DEBUG "PCI: peer root bus %02x res updated from pci conf\n", b->number); + pci_bus_remove_resources(b); info = &pci_root_info[i]; for (j = 0; j < info->res_num; j++) { struct resource *res; struct resource *root; res = &info->res[j]; - b->resource[j] = res; + pci_bus_add_resource(b, res, 0); if (res->flags & IORESOURCE_IO) root = &ioport_resource; else @@ -51,7 +52,7 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b) } } -void __init update_res(struct pci_root_info *info, size_t start, +void __devinit update_res(struct pci_root_info *info, size_t start, size_t end, unsigned long flags, int merge) { int i; diff --git a/arch/x86/pci/bus_numa.h b/arch/x86/pci/bus_numa.h index adbc23fe82a..731b64ee8d8 100644 --- a/arch/x86/pci/bus_numa.h +++ b/arch/x86/pci/bus_numa.h @@ -2,8 +2,7 @@ /* * sub bus (transparent) will use entres from 3 to store extra from - * root, so need to make sure we have enough slot there, Should we - * increase PCI_BUS_NUM_RESOURCES? + * root, so need to make sure we have enough slot there. */ #define RES_NUM 16 struct pci_root_info { diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index d2552c68e94..3736176acaa 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -520,6 +520,9 @@ char * __devinit pcibios_setup(char *str) } else if (!strcmp(str, "use_crs")) { pci_probe |= PCI_USE__CRS; return NULL; + } else if (!strcmp(str, "nocrs")) { + pci_probe |= PCI_ROOT_NO_CRS; + return NULL; } else if (!strcmp(str, "earlydump")) { pci_early_dump_regs = 1; return NULL; diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 5dc9e8c63fc..5a8fbf8d4ca 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -60,22 +60,20 @@ skip_isa_ioresource_align(struct pci_dev *dev) { * but we want to try to avoid allocating at 0x2900-0x2bff * which might have be mirrored at 0x0100-0x03ff.. */ -void -pcibios_align_resource(void *data, struct resource *res, +resource_size_t +pcibios_align_resource(void *data, const struct resource *res, resource_size_t size, resource_size_t align) { struct pci_dev *dev = data; + resource_size_t start = res->start; if (res->flags & IORESOURCE_IO) { - resource_size_t start = res->start; - if (skip_isa_ioresource_align(dev)) - return; - if (start & 0x300) { + return start; + if (start & 0x300) start = (start + 0x3ff) & ~0x3ff; - res->start = start; - } } + return start; } EXPORT_SYMBOL(pcibios_align_resource); diff --git a/arch/x86/pci/intel_bus.c b/arch/x86/pci/intel_bus.c deleted file mode 100644 index b7a55dc55d1..00000000000 --- a/arch/x86/pci/intel_bus.c +++ /dev/null @@ -1,90 +0,0 @@ -/* - * to read io range from IOH pci conf, need to do it after mmconfig is there - */ - -#include <linux/delay.h> -#include <linux/dmi.h> -#include <linux/pci.h> -#include <linux/init.h> -#include <asm/pci_x86.h> - -#include "bus_numa.h" - -static inline void print_ioh_resources(struct pci_root_info *info) -{ - int res_num; - int busnum; - int i; - - printk(KERN_DEBUG "IOH bus: [%02x, %02x]\n", - info->bus_min, info->bus_max); - res_num = info->res_num; - busnum = info->bus_min; - for (i = 0; i < res_num; i++) { - struct resource *res; - - res = &info->res[i]; - printk(KERN_DEBUG "IOH bus: %02x index %x %s: [%llx, %llx]\n", - busnum, i, - (res->flags & IORESOURCE_IO) ? "io port" : - "mmio", - res->start, res->end); - } -} - -#define IOH_LIO 0x108 -#define IOH_LMMIOL 0x10c -#define IOH_LMMIOH 0x110 -#define IOH_LMMIOH_BASEU 0x114 -#define IOH_LMMIOH_LIMITU 0x118 -#define IOH_LCFGBUS 0x11c - -static void __devinit pci_root_bus_res(struct pci_dev *dev) -{ - u16 word; - u32 dword; - struct pci_root_info *info; - u16 io_base, io_end; - u32 mmiol_base, mmiol_end; - u64 mmioh_base, mmioh_end; - int bus_base, bus_end; - - if (pci_root_num >= PCI_ROOT_NR) { - printk(KERN_DEBUG "intel_bus.c: PCI_ROOT_NR is too small\n"); - return; - } - - info = &pci_root_info[pci_root_num]; - pci_root_num++; - - pci_read_config_word(dev, IOH_LCFGBUS, &word); - bus_base = (word & 0xff); - bus_end = (word & 0xff00) >> 8; - sprintf(info->name, "PCI Bus #%02x", bus_base); - info->bus_min = bus_base; - info->bus_max = bus_end; - - pci_read_config_word(dev, IOH_LIO, &word); - io_base = (word & 0xf0) << (12 - 4); - io_end = (word & 0xf000) | 0xfff; - update_res(info, io_base, io_end, IORESOURCE_IO, 0); - - pci_read_config_dword(dev, IOH_LMMIOL, &dword); - mmiol_base = (dword & 0xff00) << (24 - 8); - mmiol_end = (dword & 0xff000000) | 0xffffff; - update_res(info, mmiol_base, mmiol_end, IORESOURCE_MEM, 0); - - pci_read_config_dword(dev, IOH_LMMIOH, &dword); - mmioh_base = ((u64)(dword & 0xfc00)) << (26 - 10); - mmioh_end = ((u64)(dword & 0xfc000000) | 0x3ffffff); - pci_read_config_dword(dev, IOH_LMMIOH_BASEU, &dword); - mmioh_base |= ((u64)(dword & 0x7ffff)) << 32; - pci_read_config_dword(dev, IOH_LMMIOH_LIMITU, &dword); - mmioh_end |= ((u64)(dword & 0x7ffff)) << 32; - update_res(info, mmioh_base, mmioh_end, IORESOURCE_MEM, 0); - - print_ioh_resources(info); -} - -/* intel IOH */ -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x342e, pci_root_bus_res); diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 0696d506c4a..b02f6d8ac92 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -590,6 +590,8 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route case PCI_DEVICE_ID_INTEL_ICH10_1: case PCI_DEVICE_ID_INTEL_ICH10_2: case PCI_DEVICE_ID_INTEL_ICH10_3: + case PCI_DEVICE_ID_INTEL_CPT_LPC1: + case PCI_DEVICE_ID_INTEL_CPT_LPC2: r->name = "PIIX/ICH"; r->get = pirq_piix_get; r->set = pirq_piix_set; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index b19d1e54201..8f3f9a50b1e 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -303,22 +303,17 @@ static void __init pci_mmcfg_check_end_bus_number(void) { struct pci_mmcfg_region *cfg, *cfgx; - /* last one*/ - cfg = list_entry(pci_mmcfg_list.prev, typeof(*cfg), list); - if (cfg) - if (cfg->end_bus < cfg->start_bus) - cfg->end_bus = 255; - - if (list_is_singular(&pci_mmcfg_list)) - return; - - /* don't overlap please */ + /* Fixup overlaps */ list_for_each_entry(cfg, &pci_mmcfg_list, list) { if (cfg->end_bus < cfg->start_bus) cfg->end_bus = 255; + /* Don't access the list head ! */ + if (cfg->list.next == &pci_mmcfg_list) + break; + cfgx = list_entry(cfg->list.next, typeof(*cfg), list); - if (cfg != cfgx && cfg->end_bus >= cfgx->start_bus) + if (cfg->end_bus >= cfgx->start_bus) cfg->end_bus = cfgx->start_bus - 1; } } diff --git a/arch/x86/pci/numaq_32.c b/arch/x86/pci/numaq_32.c index 8eb295e116f..8884a1c1ada 100644 --- a/arch/x86/pci/numaq_32.c +++ b/arch/x86/pci/numaq_32.c @@ -8,9 +8,7 @@ #include <asm/apic.h> #include <asm/mpspec.h> #include <asm/pci_x86.h> - -#define XQUAD_PORTIO_BASE 0xfe400000 -#define XQUAD_PORTIO_QUAD 0x40000 /* 256k per quad. */ +#include <asm/numaq.h> #define BUS2QUAD(global) (mp_bus_id_to_node[global]) @@ -18,8 +16,6 @@ #define QUADLOCAL2BUS(quad,local) (quad_local_to_mp_bus_id[quad][local]) -#define XQUAD_PORT_ADDR(port, quad) (xquad_portio + (XQUAD_PORTIO_QUAD*quad) + port) - #define PCI_CONF1_MQ_ADDRESS(bus, devfn, reg) \ (0x80000000 | (BUS2LOCAL(bus) << 16) | (devfn << 8) | (reg & ~3)) diff --git a/arch/x86/tools/chkobjdump.awk b/arch/x86/tools/chkobjdump.awk index 5bbb5a33f22..fd1ab80be0d 100644 --- a/arch/x86/tools/chkobjdump.awk +++ b/arch/x86/tools/chkobjdump.awk @@ -8,14 +8,24 @@ BEGIN { od_sver = 19; } -/^GNU/ { - split($3, ver, "."); +/^GNU objdump/ { + verstr = "" + for (i = 3; i <= NF; i++) + if (match($(i), "^[0-9]")) { + verstr = $(i); + break; + } + if (verstr == "") { + printf("Warning: Failed to find objdump version number.\n"); + exit 0; + } + split(verstr, ver, "."); if (ver[1] > od_ver || (ver[1] == od_ver && ver[2] >= od_sver)) { exit 1; } else { printf("Warning: objdump version %s is older than %d.%d\n", - $4, od_ver, od_sver); + verstr, od_ver, od_sver); print("Warning: Skipping posttest."); # Logic is inverted, because we just skip test without error. exit 0; diff --git a/arch/x86/tools/test_get_len.c b/arch/x86/tools/test_get_len.c index bee8d6ac269..13403fc95a9 100644 --- a/arch/x86/tools/test_get_len.c +++ b/arch/x86/tools/test_get_len.c @@ -43,7 +43,7 @@ static int x86_64; static void usage(void) { fprintf(stderr, "Usage: objdump -d a.out | awk -f distill.awk |" - " %s [-y|-n] [-v] \n", prog); + " %s [-y|-n] [-v]\n", prog); fprintf(stderr, "\t-y 64bit mode\n"); fprintf(stderr, "\t-n 32bit mode\n"); fprintf(stderr, "\t-v verbose mode\n"); @@ -69,7 +69,7 @@ static void dump_field(FILE *fp, const char *name, const char *indent, static void dump_insn(FILE *fp, struct insn *insn) { - fprintf(fp, "Instruction = { \n"); + fprintf(fp, "Instruction = {\n"); dump_field(fp, "prefixes", "\t", &insn->prefixes); dump_field(fp, "rex_prefix", "\t", &insn->rex_prefix); dump_field(fp, "vex_prefix", "\t", &insn->vex_prefix); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 2b26dd5930c..36daccb6864 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1151,9 +1151,13 @@ asmlinkage void __init xen_start_kernel(void) /* keep using Xen gdt for now; no urgent need to change it */ +#ifdef CONFIG_X86_32 pv_info.kernel_rpl = 1; if (xen_feature(XENFEAT_supervisor_mode_kernel)) pv_info.kernel_rpl = 0; +#else + pv_info.kernel_rpl = 0; +#endif /* set the limit of our address space */ xen_reserve_top(); |