diff options
Diffstat (limited to 'arch/x86')
114 files changed, 1227 insertions, 2042 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3b2a5ac..eb40925 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -49,7 +49,10 @@ config X86 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 select HAVE_ARCH_KMEMCHECK select HAVE_USER_RETURN_NOTIFIER @@ -986,12 +989,6 @@ 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 @@ -1244,6 +1241,11 @@ 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 08e442b..f20ddf8 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/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index f8ed065..fbb47da 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 $@ ; false ) diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 842b2a3..3b22fe8 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -162,6 +162,10 @@ static int lines, cols; #include "../../../../lib/decompress_unlzma.c" #endif +#ifdef CONFIG_KERNEL_LZO +#include "../../../../lib/decompress_unlzo.c" +#endif + static void scroll(void) { int i; diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c index bbeb0c3..89bbf4e 100644 --- a/arch/x86/boot/compressed/relocs.c +++ b/arch/x86/boot/compressed/relocs.c @@ -9,6 +9,9 @@ #include <byteswap.h> #define USE_BSD #include <endian.h> +#include <regex.h> + +static void die(char *fmt, ...); #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) static Elf32_Ehdr ehdr; @@ -30,25 +33,47 @@ static struct section *secs; * the address for which it has been compiled. Don't warn user about * absolute relocations present w.r.t these symbols. */ -static const char* safe_abs_relocs[] = { - "xen_irq_disable_direct_reloc", - "xen_save_fl_direct_reloc", -}; +static const char abs_sym_regex[] = + "^(xen_irq_disable_direct_reloc$|" + "xen_save_fl_direct_reloc$|" + "VDSO|" + "__crc_)"; +static regex_t abs_sym_regex_c; +static int is_abs_reloc(const char *sym_name) +{ + return !regexec(&abs_sym_regex_c, sym_name, 0, NULL, 0); +} -static int is_safe_abs_reloc(const char* sym_name) +/* + * These symbols are known to be relative, even if the linker marks them + * as absolute (typically defined outside any section in the linker script.) + */ +static const char rel_sym_regex[] = + "^_end$"; +static regex_t rel_sym_regex_c; +static int is_rel_reloc(const char *sym_name) { - int i; + return !regexec(&rel_sym_regex_c, sym_name, 0, NULL, 0); +} - for (i = 0; i < ARRAY_SIZE(safe_abs_relocs); i++) { - if (!strcmp(sym_name, safe_abs_relocs[i])) - /* Match found */ - return 1; - } - if (strncmp(sym_name, "VDSO", 4) == 0) - return 1; - if (strncmp(sym_name, "__crc_", 6) == 0) - return 1; - return 0; +static void regex_init(void) +{ + char errbuf[128]; + int err; + + err = regcomp(&abs_sym_regex_c, abs_sym_regex, + REG_EXTENDED|REG_NOSUB); + if (err) { + regerror(err, &abs_sym_regex_c, errbuf, sizeof errbuf); + die("%s", errbuf); + } + + err = regcomp(&rel_sym_regex_c, rel_sym_regex, + REG_EXTENDED|REG_NOSUB); + if (err) { + regerror(err, &rel_sym_regex_c, errbuf, sizeof errbuf); + die("%s", errbuf); + } } static void die(char *fmt, ...) @@ -131,7 +156,7 @@ static const char *rel_type(unsigned type) #undef REL_TYPE }; const char *name = "unknown type rel type name"; - if (type < ARRAY_SIZE(type_name)) { + if (type < ARRAY_SIZE(type_name) && type_name[type]) { name = type_name[type]; } return name; @@ -448,7 +473,7 @@ static void print_absolute_relocs(void) * Before warning check if this absolute symbol * relocation is harmless. */ - if (is_safe_abs_reloc(name)) + if (is_abs_reloc(name) || is_rel_reloc(name)) continue; if (!printed) { @@ -501,21 +526,26 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym)) sym = &sh_symtab[ELF32_R_SYM(rel->r_info)]; r_type = ELF32_R_TYPE(rel->r_info); /* Don't visit relocations to absolute symbols */ - if (sym->st_shndx == SHN_ABS) { + if (sym->st_shndx == SHN_ABS && + !is_rel_reloc(sym_name(sym_strtab, sym))) { continue; } - if (r_type == R_386_NONE || r_type == R_386_PC32) { + switch (r_type) { + case R_386_NONE: + case R_386_PC32: /* * NONE can be ignored and and PC relative * relocations don't need to be adjusted. */ - } - else if (r_type == R_386_32) { + break; + case R_386_32: /* Visit relocations that need to be adjusted */ visit(rel, sym); - } - else { - die("Unsupported relocation type: %d\n", r_type); + break; + default: + die("Unsupported relocation type: %s (%d)\n", + rel_type(r_type), r_type); + break; } } } @@ -571,16 +601,15 @@ static void emit_relocs(int as_text) } else { unsigned char buf[4]; - buf[0] = buf[1] = buf[2] = buf[3] = 0; /* Print a stop */ - printf("%c%c%c%c", buf[0], buf[1], buf[2], buf[3]); + fwrite("\0\0\0\0", 4, 1, stdout); /* Now print each relocation */ for (i = 0; i < reloc_count; i++) { buf[0] = (relocs[i] >> 0) & 0xff; buf[1] = (relocs[i] >> 8) & 0xff; buf[2] = (relocs[i] >> 16) & 0xff; buf[3] = (relocs[i] >> 24) & 0xff; - printf("%c%c%c%c", buf[0], buf[1], buf[2], buf[3]); + fwrite(buf, 4, 1, stdout); } } } @@ -598,6 +627,8 @@ int main(int argc, char **argv) FILE *fp; int i; + regex_init(); + show_absolute_syms = 0; show_absolute_relocs = 0; as_text = 0; diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index b31cc54..93e689f4 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -16,7 +16,7 @@ */ #include <asm/segment.h> -#include <linux/utsrelease.h> +#include <generated/utsrelease.h> #include <asm/boot.h> #include <asm/e820.h> #include <asm/page_types.h> diff --git a/arch/x86/boot/version.c b/arch/x86/boot/version.c index 2723d9b..2b15aa4 100644 --- a/arch/x86/boot/version.c +++ b/arch/x86/boot/version.c @@ -13,8 +13,8 @@ */ #include "boot.h" -#include <linux/utsrelease.h> -#include <linux/compile.h> +#include <generated/utsrelease.h> +#include <generated/compile.h> const char kernel_version[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ") " diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 2a4d073..f9f4724 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -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/acpi.h b/arch/x86/include/asm/acpi.h index 60d2b2d..56f462c 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -142,6 +142,32 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate) return max_cstate; } +static inline bool arch_has_acpi_pdc(void) +{ + struct cpuinfo_x86 *c = &cpu_data(0); + return (c->x86_vendor == X86_VENDOR_INTEL || + c->x86_vendor == X86_VENDOR_CENTAUR); +} + +static inline void arch_acpi_set_pdc_bits(u32 *buf) +{ + struct cpuinfo_x86 *c = &cpu_data(0); + + buf[2] |= ACPI_PDC_C_CAPABILITY_SMP; + + if (cpu_has(c, X86_FEATURE_EST)) + buf[2] |= ACPI_PDC_EST_CAPABILITY_SWSMP; + + if (cpu_has(c, X86_FEATURE_ACPI)) + buf[2] |= ACPI_PDC_T_FFH; + + /* + * If mwait/monitor is unsupported, C2/C3_FFH will be disabled + */ + if (!cpu_has(c, X86_FEATURE_MWAIT)) + buf[2] &= ~(ACPI_PDC_C_C2C3_FFH); +} + #else /* !CONFIG_ACPI */ #define acpi_lapic 0 diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h index 4d817f9..d2544f1 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/asm-offsets.h b/arch/x86/include/asm/asm-offsets.h new file mode 100644 index 0000000..d370ee3 --- /dev/null +++ b/arch/x86/include/asm/asm-offsets.h @@ -0,0 +1 @@ +#include <generated/asm-offsets.h> diff --git a/arch/x86/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h deleted file mode 100644 index d96c1ee..0000000 --- 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 613700f..637e1ec 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -153,6 +153,7 @@ #define X86_FEATURE_SSE5 (6*32+11) /* SSE-5 */ #define X86_FEATURE_SKINIT (6*32+12) /* SKINIT/STGI instructions */ #define X86_FEATURE_WDT (6*32+13) /* Watchdog timer */ +#define X86_FEATURE_NODEID_MSR (6*32+19) /* NodeId MSR */ /* * Auxiliary flags: Linux defined - For features scattered in various diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index b4501ee..f2ad216 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/hpet.h b/arch/x86/include/asm/hpet.h index 5d89fd2..1d5c08a 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/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 08c48a8..eeac829 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -103,7 +103,8 @@ extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *); extern void send_cleanup_vector(struct irq_cfg *); struct irq_desc; -extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *); +extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *, + unsigned int *dest_id); extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin, struct io_apic_irq_attr *irq_attr); extern void setup_ioapic_dest(void); diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index 950df43..f46b79f 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 858baa0..6c3fdd6 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 c24ca9a..ef51b50 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/msr-index.h b/arch/x86/include/asm/msr-index.h index 4ffe09b..1cd58cd 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -12,6 +12,7 @@ #define MSR_FS_BASE 0xc0000100 /* 64bit FS base */ #define MSR_GS_BASE 0xc0000101 /* 64bit GS base */ #define MSR_KERNEL_GS_BASE 0xc0000102 /* SwapGS GS shadow */ +#define MSR_TSC_AUX 0xc0000103 /* Auxiliary TSC */ /* EFER bits: */ #define _EFER_SCE 0 /* SYSCALL/SYSRET */ @@ -123,6 +124,7 @@ #define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2 #define FAM10H_MMIO_CONF_BASE_MASK 0xfffffff #define FAM10H_MMIO_CONF_BASE_SHIFT 20 +#define MSR_FAM10H_NODE_ID 0xc001100c /* K8 MSRs */ #define MSR_K8_TOP_MEM1 0xc001001a diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 2d228fc..c5bc4c2 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -27,6 +27,18 @@ struct msr { }; }; +struct msr_info { + u32 msr_no; + struct msr reg; + struct msr *msrs; + int err; +}; + +struct msr_regs_info { + u32 *regs; + int err; +}; + static inline unsigned long long native_read_tscp(unsigned int *aux) { unsigned long low, high; @@ -240,9 +252,9 @@ do { \ #define checking_wrmsrl(msr, val) wrmsr_safe((msr), (u32)(val), \ (u32)((val) >> 32)) -#define write_tsc(val1, val2) wrmsr(0x10, (val1), (val2)) +#define write_tsc(val1, val2) wrmsr(MSR_IA32_TSC, (val1), (val2)) -#define write_rdtscp_aux(val) wrmsr(0xc0000103, (val), 0) +#define write_rdtscp_aux(val) wrmsr(MSR_TSC_AUX, (val), 0) struct msr *msrs_alloc(void); void msrs_free(struct msr *msrs); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 8d9f854..1380367 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) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 6f8ec1c..b753ea5 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -181,7 +181,7 @@ static inline void native_cpuid(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx) { /* ecx is often an input as well as an output. */ - asm("cpuid" + asm volatile("cpuid" : "=a" (*eax), "=b" (*ebx), "=c" (*ecx), @@ -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/stacktrace.h b/arch/x86/include/asm/stacktrace.h index cf86a5e..35e8912 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -5,6 +5,29 @@ extern int kstack_depth_to_print; int x86_is_stack_id(int id, char *name); +struct thread_info; +struct stacktrace_ops; + +typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo, + unsigned long *stack, + unsigned long bp, + const struct stacktrace_ops *ops, + void *data, + unsigned long *end, + int *graph); + +extern unsigned long +print_context_stack(struct thread_info *tinfo, + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data, + unsigned long *end, int *graph); + +extern unsigned long +print_context_stack_bp(struct thread_info *tinfo, + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data, + unsigned long *end, int *graph); + /* Generic stack tracer with callbacks */ struct stacktrace_ops { @@ -14,6 +37,7 @@ struct stacktrace_ops { void (*address)(void *data, unsigned long address, int reliable); /* On negative return stop dumping */ int (*stack)(void *data, char *name); + walk_stack_t walk_stack; }; void dump_trace(struct task_struct *tsk, struct pt_regs *regs, diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h index 87ffcb1..8085277 100644 --- a/arch/x86/include/asm/swiotlb.h +++ b/arch/x86/include/asm/swiotlb.h @@ -5,13 +5,17 @@ #ifdef CONFIG_SWIOTLB extern int swiotlb; -extern int pci_swiotlb_init(void); +extern int __init pci_swiotlb_detect(void); +extern void __init pci_swiotlb_init(void); #else #define swiotlb 0 -static inline int pci_swiotlb_init(void) +static inline int pci_swiotlb_detect(void) { return 0; } +static inline void pci_swiotlb_init(void) +{ +} #endif static inline void dma_mark_clean(void *addr, size_t size) {} diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 4a5a089e..d5f6904 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -30,7 +30,6 @@ struct mmap_arg_struct; asmlinkage long sys32_mmap(struct mmap_arg_struct __user *); asmlinkage long sys32_mprotect(unsigned long, size_t, unsigned long); -asmlinkage long sys32_pipe(int __user *); struct sigaction32; struct old_sigaction32; asmlinkage long sys32_rt_sigaction(int, struct sigaction32 __user *, diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 1bb6e39..8868b94 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -18,16 +18,24 @@ /* Common in X86_32 and X86_64 */ /* kernel/ioport.c */ asmlinkage long sys_ioperm(unsigned long, unsigned long, int); +long sys_iopl(unsigned int, struct pt_regs *); /* kernel/process.c */ int sys_fork(struct pt_regs *); int sys_vfork(struct pt_regs *); +long sys_execve(char __user *, char __user * __user *, + char __user * __user *, struct pt_regs *); +long sys_clone(unsigned long, unsigned long, void __user *, + void __user *, struct pt_regs *); /* kernel/ldt.c */ asmlinkage int sys_modify_ldt(int, void __user *, unsigned long); /* kernel/signal.c */ long sys_rt_sigreturn(struct pt_regs *); +long sys_sigaltstack(const stack_t __user *, stack_t __user *, + struct pt_regs *); + /* kernel/tls.c */ asmlinkage int sys_set_thread_area(struct user_desc __user *); @@ -35,18 +43,11 @@ asmlinkage int sys_get_thread_area(struct user_desc __user *); /* X86_32 only */ #ifdef CONFIG_X86_32 -/* kernel/ioport.c */ -long sys_iopl(struct pt_regs *); - -/* kernel/process_32.c */ -int sys_clone(struct pt_regs *); -int sys_execve(struct pt_regs *); /* kernel/signal.c */ asmlinkage int sys_sigsuspend(int, int, old_sigset_t); asmlinkage int sys_sigaction(int, const struct old_sigaction __user *, struct old_sigaction __user *); -int sys_sigaltstack(struct pt_regs *); unsigned long sys_sigreturn(struct pt_regs *); /* kernel/sys_i386_32.c */ @@ -62,28 +63,15 @@ asmlinkage int sys_uname(struct old_utsname __user *); asmlinkage int sys_olduname(struct oldold_utsname __user *); /* kernel/vm86_32.c */ -int sys_vm86old(struct pt_regs *); -int sys_vm86(struct pt_regs *); +int sys_vm86old(struct vm86_struct __user *, struct pt_regs *); +int sys_vm86(unsigned long, unsigned long, struct pt_regs *); #else /* CONFIG_X86_32 */ /* X86_64 only */ -/* kernel/ioport.c */ -asmlinkage long sys_iopl(unsigned int, struct pt_regs *); - /* kernel/process_64.c */ -asmlinkage long sys_clone(unsigned long, unsigned long, - void __user *, void __user *, - struct pt_regs *); -asmlinkage long sys_execve(char __user *, char __user * __user *, - char __user * __user *, - struct pt_regs *); long sys_arch_prctl(int, unsigned long); -/* kernel/signal.c */ -asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *, - struct pt_regs *); - /* kernel/sys_x86_64.c */ struct new_utsname; diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index ecb544e..e04740f 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 375c917..e0d2890 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 0c9825e..088d09f 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 46324c6..535e4214 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -30,16 +30,15 @@ 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 811bfab..40be813 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/Makefile b/arch/x86/kernel/acpi/Makefile index fd5ca97..6f35260 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -4,7 +4,7 @@ obj-$(CONFIG_ACPI) += boot.o obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_rm.o wakeup_$(BITS).o ifneq ($(CONFIG_ACPI_PROCESSOR),) -obj-y += cstate.o processor.o +obj-y += cstate.o endif $(obj)/wakeup_rm.o: $(obj)/realmode/wakeup.bin diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index fb1035c..af1c583 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1185,9 +1185,6 @@ 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 +1194,6 @@ 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 +1344,6 @@ 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 +1516,10 @@ 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 +1527,14 @@ 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 +1542,15 @@ 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/cstate.c b/arch/x86/kernel/acpi/cstate.c index 59cdfa4..2e837f5 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -48,7 +48,7 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags, * P4, Core and beyond CPUs */ if (c->x86_vendor == X86_VENDOR_INTEL && - (c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 14))) + (c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 0x0f))) flags->bm_control = 0; } EXPORT_SYMBOL(acpi_processor_power_init_bm_check); diff --git a/arch/x86/kernel/acpi/processor.c b/arch/x86/kernel/acpi/processor.c deleted file mode 100644 index d85d1b2..0000000 --- a/arch/x86/kernel/acpi/processor.c +++ /dev/null @@ -1,101 +0,0 @@ -/* - * Copyright (C) 2005 Intel Corporation - * Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> - * - Added _PDC for platforms with Intel CPUs - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/acpi.h> - -#include <acpi/processor.h> -#include <asm/acpi.h> - -static void init_intel_pdc(struct acpi_processor *pr, struct cpuinfo_x86 *c) -{ - struct acpi_object_list *obj_list; - union acpi_object *obj; - u32 *buf; - - /* allocate and initialize pdc. It will be used later. */ - obj_list = kmalloc(sizeof(struct acpi_object_list), GFP_KERNEL); - if (!obj_list) { - printk(KERN_ERR "Memory allocation error\n"); - return; - } - - obj = kmalloc(sizeof(union acpi_object), GFP_KERNEL); - if (!obj) { - printk(KERN_ERR "Memory allocation error\n"); - kfree(obj_list); - return; - } - - buf = kmalloc(12, GFP_KERNEL); - if (!buf) { - printk(KERN_ERR "Memory allocation error\n"); - kfree(obj); - kfree(obj_list); - return; - } - - buf[0] = ACPI_PDC_REVISION_ID; - buf[1] = 1; - buf[2] = ACPI_PDC_C_CAPABILITY_SMP; - - /* - * The default of PDC_SMP_T_SWCOORD bit is set for intel x86 cpu so - * that OSPM is capable of native ACPI throttling software - * coordination using BIOS supplied _TSD info. - */ - buf[2] |= ACPI_PDC_SMP_T_SWCOORD; - if (cpu_has(c, X86_FEATURE_EST)) - buf[2] |= ACPI_PDC_EST_CAPABILITY_SWSMP; - - if (cpu_has(c, X86_FEATURE_ACPI)) - buf[2] |= ACPI_PDC_T_FFH; - - /* - * If mwait/monitor is unsupported, C2/C3_FFH will be disabled - */ - if (!cpu_has(c, X86_FEATURE_MWAIT)) - buf[2] &= ~(ACPI_PDC_C_C2C3_FFH); - - obj->type = ACPI_TYPE_BUFFER; - obj->buffer.length = 12; - obj->buffer.pointer = (u8 *) buf; - obj_list->count = 1; - obj_list->pointer = obj; - pr->pdc = obj_list; - - return; -} - - -/* Initialize _PDC data based on the CPU vendor */ -void arch_acpi_processor_init_pdc(struct acpi_processor *pr) -{ - struct cpuinfo_x86 *c = &cpu_data(pr->id); - - pr->pdc = NULL; - if (c->x86_vendor == X86_VENDOR_INTEL || - c->x86_vendor == X86_VENDOR_CENTAUR) - init_intel_pdc(pr, c); - - return; -} - -EXPORT_SYMBOL(arch_acpi_processor_init_pdc); - -void arch_acpi_processor_cleanup_pdc(struct acpi_processor *pr) -{ - if (pr->pdc) { - kfree(pr->pdc->pointer->buffer.pointer); - kfree(pr->pdc->pointer); - kfree(pr->pdc); - pr->pdc = NULL; - } -} - -EXPORT_SYMBOL(arch_acpi_processor_cleanup_pdc); diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 82e5086..f996103 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/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 23824fe..adb0ba0 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 1dca9c3..9dc91b4 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 3704997..f147a95 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 aa57c07..dfca210 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; @@ -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 d0c99ab..e3c3d82 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; @@ -306,10 +311,7 @@ physflat_cpu_mask_to_apicid_and(const struct cpumask *cpumask, if (cpumask_test_cpu(cpu, cpu_online_mask)) break; } - if (cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_apicid, cpu); - - return BAD_APICID; + return per_cpu(x86_cpu_to_apicid, cpu); } struct apic apic_physflat = { diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 38dcecf..cb804c5 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -131,10 +131,7 @@ static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask, if (cpumask_test_cpu(cpu, cpu_online_mask)) break; } - if (cpu < nr_cpu_ids) - return bigsmp_cpu_to_logical_apicid(cpu); - - return BAD_APICID; + return bigsmp_cpu_to_logical_apicid(cpu); } static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 11a5851..53243ca 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2276,26 +2276,28 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq /* * Either sets desc->affinity to a valid value, and returns - * ->cpu_mask_to_apicid of that, or returns BAD_APICID and + * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and * leaves desc->affinity untouched. */ unsigned int -set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask) +set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask, + unsigned int *dest_id) { struct irq_cfg *cfg; unsigned int irq; if (!cpumask_intersects(mask, cpu_online_mask)) - return BAD_APICID; + return -1; irq = desc->irq; cfg = desc->chip_data; if (assign_irq_vector(irq, cfg, mask)) - return BAD_APICID; + return -1; cpumask_copy(desc->affinity, mask); - return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain); + *dest_id = apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain); + return 0; } static int @@ -2311,12 +2313,11 @@ set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask) cfg = desc->chip_data; spin_lock_irqsave(&ioapic_lock, flags); - dest = set_desc_affinity(desc, mask); - if (dest != BAD_APICID) { + ret = set_desc_affinity(desc, mask, &dest); + if (!ret) { /* Only the high 8 bits are valid. */ dest = SET_APIC_LOGICAL_ID(dest); __target_IO_APIC_irq(irq, dest, cfg); - ret = 0; } spin_unlock_irqrestore(&ioapic_lock, flags); @@ -2433,6 +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; @@ -3351,8 +3359,7 @@ static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask) struct msi_msg msg; unsigned int dest; - dest = set_desc_affinity(desc, mask); - if (dest == BAD_APICID) + if (set_desc_affinity(desc, mask, &dest)) return -1; cfg = desc->chip_data; @@ -3384,8 +3391,7 @@ ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask) if (get_irte(irq, &irte)) return -1; - dest = set_desc_affinity(desc, mask); - if (dest == BAD_APICID) + if (set_desc_affinity(desc, mask, &dest)) return -1; irte.vector = cfg->vector; @@ -3567,8 +3573,7 @@ static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask) struct msi_msg msg; unsigned int dest; - dest = set_desc_affinity(desc, mask); - if (dest == BAD_APICID) + if (set_desc_affinity(desc, mask, &dest)) return -1; cfg = desc->chip_data; @@ -3623,8 +3628,7 @@ static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask) struct msi_msg msg; unsigned int dest; - dest = set_desc_affinity(desc, mask); - if (dest == BAD_APICID) + if (set_desc_affinity(desc, mask, &dest)) return -1; cfg = desc->chip_data; @@ -3730,8 +3734,7 @@ static int set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask) struct irq_cfg *cfg; unsigned int dest; - dest = set_desc_affinity(desc, mask); - if (dest == BAD_APICID) + if (set_desc_affinity(desc, mask, &dest)) return -1; cfg = desc->chip_data; diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 1a6559f..99d2fe0 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 c4cbd30..83e9be4 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_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index a5371ec..cf69c59 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -148,10 +148,7 @@ x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, break; } - if (cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_logical_apicid, cpu); - - return BAD_APICID; + return per_cpu(x86_cpu_to_logical_apicid, cpu); } static unsigned int x2apic_cluster_phys_get_apic_id(unsigned long x) diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index a8989aa..8972f38 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -146,10 +146,7 @@ x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, break; } - if (cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_apicid, cpu); - - return BAD_APICID; + return per_cpu(x86_cpu_to_apicid, cpu); } static unsigned int x2apic_phys_get_apic_id(unsigned long x) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index b684bb3..21db3cb 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; } @@ -225,10 +234,7 @@ uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask, if (cpumask_test_cpu(cpu, cpu_online_mask)) break; } - if (cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_apicid, cpu); - - return BAD_APICID; + return per_cpu(x86_cpu_to_apicid, cpu); } static unsigned int x2apic_get_apic_id(unsigned long x) @@ -377,13 +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) @@ -399,7 +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); @@ -413,7 +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) @@ -423,7 +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) @@ -632,8 +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++; @@ -654,15 +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/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 1d2cb38..c202b62 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/amd.c b/arch/x86/kernel/cpu/amd.c index 8dc3ea1..e485825 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -254,59 +254,36 @@ static int __cpuinit nearby_node(int apicid) /* * Fixup core topology information for AMD multi-node processors. - * Assumption 1: Number of cores in each internal node is the same. - * Assumption 2: Mixed systems with both single-node and dual-node - * processors are not supported. + * Assumption: Number of cores in each internal node is the same. */ #ifdef CONFIG_X86_HT static void __cpuinit amd_fixup_dcm(struct cpuinfo_x86 *c) { -#ifdef CONFIG_PCI - u32 t, cpn; - u8 n, n_id; + unsigned long long value; + u32 nodes, cores_per_node; int cpu = smp_processor_id(); + if (!cpu_has(c, X86_FEATURE_NODEID_MSR)) + return; + /* fixup topology information only once for a core */ if (cpu_has(c, X86_FEATURE_AMD_DCM)) return; - /* check for multi-node processor on boot cpu */ - t = read_pci_config(0, 24, 3, 0xe8); - if (!(t & (1 << 29))) + rdmsrl(MSR_FAM10H_NODE_ID, value); + + nodes = ((value >> 3) & 7) + 1; + if (nodes == 1) return; set_cpu_cap(c, X86_FEATURE_AMD_DCM); + cores_per_node = c->x86_max_cores / nodes; - /* cores per node: each internal node has half the number of cores */ - cpn = c->x86_max_cores >> 1; + /* store NodeID, use llc_shared_map to store sibling info */ + per_cpu(cpu_llc_id, cpu) = value & 7; - /* even-numbered NB_id of this dual-node processor */ - n = c->phys_proc_id << 1; - - /* - * determine internal node id and assign cores fifty-fifty to - * each node of the dual-node processor - */ - t = read_pci_config(0, 24 + n, 3, 0xe8); - n = (t>>30) & 0x3; - if (n == 0) { - if (c->cpu_core_id < cpn) - n_id = 0; - else - n_id = 1; - } else { - if (c->cpu_core_id < cpn) - n_id = 1; - else - n_id = 0; - } - - /* compute entire NodeID, use llc_shared_map to store sibling info */ - per_cpu(cpu_llc_id, cpu) = (c->phys_proc_id << 1) + n_id; - - /* fixup core id to be in range from 0 to cpn */ - c->cpu_core_id = c->cpu_core_id % cpn; -#endif + /* fixup core id to be in range from 0 to (cores_per_node - 1) */ + c->cpu_core_id = c->cpu_core_id % cores_per_node; } #endif diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c deleted file mode 100644 index b368cd8..0000000 --- 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/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index f28decf..1b1920f 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -190,9 +190,11 @@ static void do_drv_write(void *_cmd) static void drv_read(struct drv_cmd *cmd) { + int err; cmd->val = 0; - smp_call_function_single(cpumask_any(cmd->mask), do_drv_read, cmd, 1); + err = smp_call_function_any(cmd->mask, do_drv_read, cmd, 1); + WARN_ON_ONCE(err); /* smp_call_function_any() was buggy? */ } static void drv_write(struct drv_cmd *cmd) diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index a9df944..6e44519 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -1136,7 +1136,7 @@ static int powernowk8_target(struct cpufreq_policy *pol, if (!alloc_cpumask_var(&oldmask, GFP_KERNEL)) return -ENOMEM; - cpumask_copy(oldmask, tsk_cpumask(current)); + cpumask_copy(oldmask, tsk_cpus_allowed(current)); set_cpus_allowed_ptr(current, cpumask_of(pol->cpu)); if (smp_processor_id() != pol->cpu) { @@ -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.c b/arch/x86/kernel/cpu/intel.c index 9c31e8b..879666f 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -70,7 +70,6 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE); sched_clock_stable = 1; } diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 472763d..73734ba 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -74,7 +74,7 @@ static void raise_exception(struct mce *m, struct pt_regs *pregs) m->finished = 0; } -static cpumask_t mce_inject_cpumask; +static cpumask_var_t mce_inject_cpumask; static int mce_raise_notify(struct notifier_block *self, unsigned long val, void *data) @@ -82,9 +82,9 @@ static int mce_raise_notify(struct notifier_block *self, struct die_args *args = (struct die_args *)data; int cpu = smp_processor_id(); struct mce *m = &__get_cpu_var(injectm); - if (val != DIE_NMI_IPI || !cpu_isset(cpu, mce_inject_cpumask)) + if (val != DIE_NMI_IPI || !cpumask_test_cpu(cpu, mce_inject_cpumask)) return NOTIFY_DONE; - cpu_clear(cpu, mce_inject_cpumask); + cpumask_clear_cpu(cpu, mce_inject_cpumask); if (m->inject_flags & MCJ_EXCEPTION) raise_exception(m, args->regs); else if (m->status) @@ -148,22 +148,22 @@ static void raise_mce(struct mce *m) unsigned long start; int cpu; get_online_cpus(); - mce_inject_cpumask = cpu_online_map; - cpu_clear(get_cpu(), mce_inject_cpumask); + cpumask_copy(mce_inject_cpumask, cpu_online_mask); + cpumask_clear_cpu(get_cpu(), mce_inject_cpumask); for_each_online_cpu(cpu) { struct mce *mcpu = &per_cpu(injectm, cpu); if (!mcpu->finished || MCJ_CTX(mcpu->inject_flags) != MCJ_CTX_RANDOM) - cpu_clear(cpu, mce_inject_cpumask); + cpumask_clear_cpu(cpu, mce_inject_cpumask); } - if (!cpus_empty(mce_inject_cpumask)) - apic->send_IPI_mask(&mce_inject_cpumask, NMI_VECTOR); + if (!cpumask_empty(mce_inject_cpumask)) + apic->send_IPI_mask(mce_inject_cpumask, NMI_VECTOR); start = jiffies; - while (!cpus_empty(mce_inject_cpumask)) { + while (!cpumask_empty(mce_inject_cpumask)) { if (!time_before(jiffies, start + 2*HZ)) { printk(KERN_ERR "Timeout waiting for mce inject NMI %lx\n", - *cpus_addr(mce_inject_cpumask)); + *cpumask_bits(mce_inject_cpumask)); break; } cpu_relax(); @@ -210,6 +210,8 @@ static ssize_t mce_write(struct file *filp, const char __user *ubuf, static int inject_init(void) { + if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL)) + return -ENOMEM; printk(KERN_INFO "Machine check injector initialized\n"); mce_chrdev_ops.write = mce_write; register_die_notifier(&mce_raise_nb); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 45506d5..8c1c070 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1343,6 +1343,13 @@ intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx) 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); @@ -2336,6 +2343,7 @@ static const struct stacktrace_ops backtrace_ops = { .warning_symbol = backtrace_warning_symbol, .stack = backtrace_stack, .address = backtrace_address, + .walk_stack = print_context_stack_bp, }; #include "../dumpstack.h" @@ -2346,7 +2354,7 @@ 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); } /* diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 7ef24a7..83e5e62 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -187,7 +187,8 @@ static int __init cpuid_init(void) int i, err = 0; i = 0; - if (register_chrdev(CPUID_MAJOR, "cpu/cpuid", &cpuid_fops)) { + if (__register_chrdev(CPUID_MAJOR, 0, NR_CPUS, + "cpu/cpuid", &cpuid_fops)) { printk(KERN_ERR "cpuid: unable to get major %d for cpuid\n", CPUID_MAJOR); err = -EBUSY; @@ -216,7 +217,7 @@ out_class: } class_destroy(cpuid_class); out_chrdev: - unregister_chrdev(CPUID_MAJOR, "cpu/cpuid"); + __unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid"); out: return err; } @@ -228,7 +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 0a0aa1c..6d81755 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -109,6 +109,32 @@ print_context_stack(struct thread_info *tinfo, } return bp; } +EXPORT_SYMBOL_GPL(print_context_stack); + +unsigned long +print_context_stack_bp(struct thread_info *tinfo, + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data, + unsigned long *end, int *graph) +{ + struct stack_frame *frame = (struct stack_frame *)bp; + unsigned long *ret_addr = &frame->return_address; + + while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) { + unsigned long addr = *ret_addr; + + 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); static void @@ -141,10 +167,11 @@ static void print_trace_address(void *data, unsigned long addr, int reliable) } static const struct stacktrace_ops print_trace_ops = { - .warning = print_trace_warning, - .warning_symbol = print_trace_warning_symbol, - .stack = print_trace_stack, - .address = print_trace_address, + .warning = print_trace_warning, + .warning_symbol = print_trace_warning_symbol, + .stack = print_trace_stack, + .address = print_trace_address, + .walk_stack = print_context_stack, }; void diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h index 81086c2..4fd1420 100644 --- a/arch/x86/kernel/dumpstack.h +++ b/arch/x86/kernel/dumpstack.h @@ -14,12 +14,6 @@ #define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) #endif -extern unsigned long -print_context_stack(struct thread_info *tinfo, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data, - unsigned long *end, int *graph); - extern void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, char *log_lvl); diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index e0ed4c7..ae775ca 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -58,7 +58,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, context = (struct thread_info *) ((unsigned long)stack & (~(THREAD_SIZE - 1))); - bp = print_context_stack(context, stack, bp, ops, data, NULL, &graph); + bp = ops->walk_stack(context, stack, bp, ops, data, NULL, &graph); stack = (unsigned long *)context->previous_esp; if (!stack) diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index b13af53..0ad9597 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -188,8 +188,8 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (ops->stack(data, id) < 0) break; - bp = print_context_stack(tinfo, stack, bp, ops, - data, estack_end, &graph); + bp = ops->walk_stack(tinfo, stack, bp, ops, + data, estack_end, &graph); ops->stack(data, "<EOE>"); /* * We link to the next stack via the diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index f50447d..a1a7876 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -724,7 +724,7 @@ core_initcall(e820_mark_nvs_memory); /* * Early reserved memory areas. */ -#define MAX_EARLY_RES 20 +#define MAX_EARLY_RES 32 struct early_res { u64 start, end; @@ -733,13 +733,13 @@ 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/entry_32.S b/arch/x86/kernel/entry_32.S index 50b9c22..44a8e0d 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -725,22 +725,61 @@ END(syscall_badsys) /* * System calls that need a pt_regs pointer. */ -#define PTREGSCALL(name) \ +#define PTREGSCALL0(name) \ ALIGN; \ ptregs_##name: \ leal 4(%esp),%eax; \ jmp sys_##name; -PTREGSCALL(iopl) -PTREGSCALL(fork) -PTREGSCALL(clone) -PTREGSCALL(vfork) -PTREGSCALL(execve) -PTREGSCALL(sigaltstack) -PTREGSCALL(sigreturn) -PTREGSCALL(rt_sigreturn) -PTREGSCALL(vm86) -PTREGSCALL(vm86old) +#define PTREGSCALL1(name) \ + ALIGN; \ +ptregs_##name: \ + leal 4(%esp),%edx; \ + movl (PT_EBX+4)(%esp),%eax; \ + jmp sys_##name; + +#define PTREGSCALL2(name) \ + ALIGN; \ +ptregs_##name: \ + leal 4(%esp),%ecx; \ + movl (PT_ECX+4)(%esp),%edx; \ + movl (PT_EBX+4)(%esp),%eax; \ + jmp sys_##name; + +#define PTREGSCALL3(name) \ + ALIGN; \ +ptregs_##name: \ + leal 4(%esp),%eax; \ + pushl %eax; \ + movl PT_EDX(%eax),%ecx; \ + movl PT_ECX(%eax),%edx; \ + movl PT_EBX(%eax),%eax; \ + call sys_##name; \ + addl $4,%esp; \ + ret + +PTREGSCALL1(iopl) +PTREGSCALL0(fork) +PTREGSCALL0(vfork) +PTREGSCALL3(execve) +PTREGSCALL2(sigaltstack) +PTREGSCALL0(sigreturn) +PTREGSCALL0(rt_sigreturn) +PTREGSCALL2(vm86) +PTREGSCALL1(vm86old) + +/* Clone is an oddball. The 4th arg is in %edi */ + ALIGN; +ptregs_clone: + leal 4(%esp),%eax + pushl %eax + pushl PT_EDI(%eax) + movl PT_EDX(%eax),%ecx + movl PT_ECX(%eax),%edx + movl PT_EBX(%eax),%eax + call sys_clone + addl $8,%esp + ret .macro FIXUP_ESPFIX_STACK /* @@ -1008,12 +1047,8 @@ END(spurious_interrupt_bug) ENTRY(kernel_thread_helper) pushl $0 # fake return address for unwinder CFI_STARTPROC - movl %edx,%eax - push %edx - CFI_ADJUST_CFA_OFFSET 4 - call *%ebx - push %eax - CFI_ADJUST_CFA_OFFSET 4 + movl %edi,%eax + call *%esi call do_exit ud2 # padding for call trace CFI_ENDPROC diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 673f693..0697ff1 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1166,63 +1166,20 @@ bad_gs: jmp 2b .previous -/* - * Create a kernel thread. - * - * C extern interface: - * extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) - * - * asm input arguments: - * rdi: fn, rsi: arg, rdx: flags - */ -ENTRY(kernel_thread) - CFI_STARTPROC - FAKE_STACK_FRAME $child_rip - SAVE_ALL - - # rdi: flags, rsi: usp, rdx: will be &pt_regs - movq %rdx,%rdi - orq kernel_thread_flags(%rip),%rdi - movq $-1, %rsi - movq %rsp, %rdx - - xorl %r8d,%r8d - xorl %r9d,%r9d - - # clone now - call do_fork - movq %rax,RAX(%rsp) - xorl %edi,%edi - - /* - * It isn't worth to check for reschedule here, - * so internally to the x86_64 port you can rely on kernel_thread() - * not to reschedule the child before returning, this avoids the need - * of hacks for example to fork off the per-CPU idle tasks. - * [Hopefully no generic code relies on the reschedule -AK] - */ - RESTORE_ALL - UNFAKE_STACK_FRAME - ret - CFI_ENDPROC -END(kernel_thread) - -ENTRY(child_rip) +ENTRY(kernel_thread_helper) pushq $0 # fake return address CFI_STARTPROC /* * Here we are in the child and the registers are set as they were * at kernel_thread() invocation in the parent. */ - movq %rdi, %rax - movq %rsi, %rdi - call *%rax + call *%rsi # exit mov %eax, %edi call do_exit ud2 # padding for call trace CFI_ENDPROC -END(child_rip) +END(kernel_thread_helper) /* * execve(). This function needs to use IRET, not SYSRET, to set up all state properly. diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index ba6e658..ad80a1c 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 05d5fec..bb6006e 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. diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 99c4d30..8eec0ec 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -103,9 +103,10 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) * on system-call entry - see also fork() and the signal handling * code. */ -static int do_iopl(unsigned int level, struct pt_regs *regs) +long sys_iopl(unsigned int level, struct pt_regs *regs) { unsigned int old = (regs->flags >> 12) & 3; + struct thread_struct *t = ¤t->thread; if (level > 3) return -EINVAL; @@ -115,29 +116,8 @@ static int do_iopl(unsigned int level, struct pt_regs *regs) return -EPERM; } regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | (level << 12); - - return 0; -} - -#ifdef CONFIG_X86_32 -long sys_iopl(struct pt_regs *regs) -{ - unsigned int level = regs->bx; - struct thread_struct *t = ¤t->thread; - int rc; - - rc = do_iopl(level, regs); - if (rc < 0) - goto out; - t->iopl = level << 12; set_iopl_mask(t->iopl); -out: - return rc; -} -#else -asmlinkage long sys_iopl(unsigned int level, struct pt_regs *regs) -{ - return do_iopl(level, regs); + + return 0; } -#endif diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index dd74fe72..bfba601 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/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 37542b67..e1af7c0 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 844c02c..cceb5bc 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -394,7 +394,7 @@ static enum ucode_state microcode_update_cpu(int cpu) struct ucode_cpu_info *uci = ucode_cpu_info + cpu; enum ucode_state ustate; - if (uci->valid && uci->mc) + if (uci->valid) ustate = microcode_resume_cpu(cpu); else ustate = microcode_init_cpu(cpu); @@ -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/mpparse.c b/arch/x86/kernel/mpparse.c index 40b54ce..a2c1edd 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 5534499..206735a 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -172,11 +172,10 @@ static long msr_ioctl(struct file *file, unsigned int ioc, unsigned long arg) static int msr_open(struct inode *inode, struct file *file) { - unsigned int cpu = iminor(file->f_path.dentry->d_inode); - struct cpuinfo_x86 *c = &cpu_data(cpu); + unsigned int cpu; + struct cpuinfo_x86 *c; cpu = iminor(file->f_path.dentry->d_inode); - if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; /* No such CPU */ @@ -247,7 +246,7 @@ static int __init msr_init(void) int i, err = 0; i = 0; - if (register_chrdev(MSR_MAJOR, "cpu/msr", &msr_fops)) { + if (__register_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr", &msr_fops)) { printk(KERN_ERR "msr: unable to get major %d for msr\n", MSR_MAJOR); err = -EBUSY; @@ -275,7 +274,7 @@ out_class: msr_device_destroy(i); class_destroy(msr_class); out_chrdev: - unregister_chrdev(MSR_MAJOR, "cpu/msr"); + __unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr"); out: return err; } @@ -286,7 +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/pci-dma.c b/arch/x86/kernel/pci-dma.c index fcc2f2b..75e14e2 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -120,15 +120,12 @@ static void __init dma32_free_bootmem(void) void __init pci_iommu_alloc(void) { - int use_swiotlb; - - use_swiotlb = pci_swiotlb_init(); #ifdef CONFIG_X86_64 /* free the range so iommu could get some range less than 4G */ dma32_free_bootmem(); #endif - if (use_swiotlb) - return; + if (pci_swiotlb_detect()) + goto out; gart_iommu_hole_init(); @@ -138,6 +135,8 @@ void __init pci_iommu_alloc(void) /* needs to be called after gart_iommu_hole_init */ amd_iommu_detect(); +out: + pci_swiotlb_init(); } void *dma_generic_alloc_coherent(struct device *dev, size_t size, diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index e3c0a66..7d2829d 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -43,12 +43,12 @@ static struct dma_map_ops swiotlb_dma_ops = { }; /* - * pci_swiotlb_init - initialize swiotlb if necessary + * pci_swiotlb_detect - set swiotlb to 1 if necessary * * This returns non-zero if we are forced to use swiotlb (by the boot * option). */ -int __init pci_swiotlb_init(void) +int __init pci_swiotlb_detect(void) { int use_swiotlb = swiotlb | swiotlb_force; @@ -60,10 +60,13 @@ int __init pci_swiotlb_init(void) if (swiotlb_force) swiotlb = 1; + return use_swiotlb; +} + +void __init pci_swiotlb_init(void) +{ if (swiotlb) { swiotlb_init(0); dma_ops = &swiotlb_dma_ops; } - - return use_swiotlb; } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 7a7bd4e..c9b3522 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -103,8 +103,8 @@ 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, " "), @@ -115,18 +115,6 @@ 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)); /* @@ -255,6 +243,78 @@ int sys_vfork(struct pt_regs *regs) NULL, NULL); } +long +sys_clone(unsigned long clone_flags, unsigned long newsp, + void __user *parent_tid, void __user *child_tid, struct pt_regs *regs) +{ + if (!newsp) + newsp = regs->sp; + return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); +} + +/* + * This gets run with %si containing the + * function to call, and %di containing + * the "args". + */ +extern void kernel_thread_helper(void); + +/* + * Create a kernel thread + */ +int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) +{ + struct pt_regs regs; + + memset(®s, 0, sizeof(regs)); + + regs.si = (unsigned long) fn; + regs.di = (unsigned long) arg; + +#ifdef CONFIG_X86_32 + regs.ds = __USER_DS; + regs.es = __USER_DS; + regs.fs = __KERNEL_PERCPU; + regs.gs = __KERNEL_STACK_CANARY; +#else + regs.ss = __KERNEL_DS; +#endif + + regs.orig_ax = -1; + regs.ip = (unsigned long) kernel_thread_helper; + regs.cs = __KERNEL_CS | get_kernel_rpl(); + regs.flags = X86_EFLAGS_IF | 0x2; + + /* Ok, create the new process.. */ + return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, 0, NULL, NULL); +} +EXPORT_SYMBOL(kernel_thread); + +/* + * sys_execve() executes a new program. + */ +long sys_execve(char __user *name, char __user * __user *argv, + char __user * __user *envp, struct pt_regs *regs) +{ + long error; + char *filename; + + filename = getname(name); + error = PTR_ERR(filename); + if (IS_ERR(filename)) + return error; + error = do_execve(filename, argv, envp, regs); + +#ifdef CONFIG_X86_32 + if (error == 0) { + /* Make sure we don't return using sysenter.. */ + set_thread_flag(TIF_IRET); + } +#endif + + putname(filename); + return error; +} /* * Idle related variables and functions diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 120b887..37ad1e0 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); } @@ -180,39 +180,6 @@ void show_regs(struct pt_regs *regs) show_trace(NULL, regs, ®s->sp, regs->bp); } -/* - * This gets run with %bx containing the - * function to call, and %dx containing - * the "args". - */ -extern void kernel_thread_helper(void); - -/* - * Create a kernel thread - */ -int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) -{ - struct pt_regs regs; - - memset(®s, 0, sizeof(regs)); - - regs.bx = (unsigned long) fn; - regs.dx = (unsigned long) arg; - - regs.ds = __USER_DS; - regs.es = __USER_DS; - regs.fs = __KERNEL_PERCPU; - regs.gs = __KERNEL_STACK_CANARY; - regs.orig_ax = -1; - regs.ip = (unsigned long) kernel_thread_helper; - regs.cs = __KERNEL_CS | get_kernel_rpl(); - regs.flags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2; - - /* Ok, create the new process.. */ - return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, 0, NULL, NULL); -} -EXPORT_SYMBOL(kernel_thread); - void release_thread(struct task_struct *dead_task) { BUG_ON(dead_task->mm); @@ -424,46 +391,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } -int sys_clone(struct pt_regs *regs) -{ - unsigned long clone_flags; - unsigned long newsp; - int __user *parent_tidptr, *child_tidptr; - - clone_flags = regs->bx; - newsp = regs->cx; - parent_tidptr = (int __user *)regs->dx; - child_tidptr = (int __user *)regs->di; - if (!newsp) - newsp = regs->sp; - return do_fork(clone_flags, newsp, regs, 0, parent_tidptr, child_tidptr); -} - -/* - * sys_execve() executes a new program. - */ -int sys_execve(struct pt_regs *regs) -{ - int error; - char *filename; - - filename = getname((char __user *) regs->bx); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - goto out; - error = do_execve(filename, - (char __user * __user *) regs->cx, - (char __user * __user *) regs->dx, - regs); - if (error == 0) { - /* Make sure we don't return using sysenter.. */ - set_thread_flag(TIF_IRET); - } - putname(filename); -out: - return error; -} - #define top_esp (THREAD_SIZE - sizeof(unsigned long)) #define top_ebp (THREAD_SIZE - 2*sizeof(unsigned long)) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e5ab0cd..126f0b4 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -57,8 +57,6 @@ asmlinkage extern void ret_from_fork(void); DEFINE_PER_CPU(unsigned long, old_rsp); static DEFINE_PER_CPU(unsigned char, is_idle); -unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED; - static ATOMIC_NOTIFIER_HEAD(idle_notifier); void idle_notifier_register(struct notifier_block *n) @@ -163,19 +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)); @@ -196,21 +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 show_regs(struct pt_regs *regs) @@ -273,8 +271,9 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, *childregs = *regs; childregs->ax = 0; - childregs->sp = sp; - if (sp == ~0UL) + if (user_mode(regs)) + childregs->sp = sp; + else childregs->sp = (unsigned long)childregs; p->thread.sp = (unsigned long) childregs; @@ -508,25 +507,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } -/* - * sys_execve() executes a new program. - */ -asmlinkage -long sys_execve(char __user *name, char __user * __user *argv, - char __user * __user *envp, struct pt_regs *regs) -{ - long error; - char *filename; - - filename = getname(name); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - return error; - error = do_execve(filename, argv, envp, regs); - putname(filename); - return error; -} - void set_personality_64bit(void) { /* inherit personality from parent */ @@ -541,13 +521,16 @@ void set_personality_64bit(void) current->personality &= ~READ_IMPLIES_EXEC; } -asmlinkage long -sys_clone(unsigned long clone_flags, unsigned long newsp, - void __user *parent_tid, void __user *child_tid, struct pt_regs *regs) +void set_personality_ia32(void) { - if (!newsp) - newsp = regs->sp; - return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); + /* 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) diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 2779321..0c1033d 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -509,14 +509,14 @@ static int genregs_get(struct task_struct *target, { if (kbuf) { unsigned long *k = kbuf; - while (count > 0) { + while (count >= sizeof(*k)) { *k++ = getreg(target, pos); count -= sizeof(*k); pos += sizeof(*k); } } else { unsigned long __user *u = ubuf; - while (count > 0) { + while (count >= sizeof(*u)) { if (__put_user(getreg(target, pos), u++)) return -EFAULT; count -= sizeof(*u); @@ -535,14 +535,14 @@ static int genregs_set(struct task_struct *target, int ret = 0; if (kbuf) { const unsigned long *k = kbuf; - while (count > 0 && !ret) { + while (count >= sizeof(*k) && !ret) { ret = putreg(target, pos, *k++); count -= sizeof(*k); pos += sizeof(*k); } } else { const unsigned long __user *u = ubuf; - while (count > 0 && !ret) { + while (count >= sizeof(*u) && !ret) { unsigned long word; ret = __get_user(word, u++); if (ret) @@ -702,7 +702,7 @@ 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 +778,11 @@ 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; @@ -1458,14 +1461,14 @@ static int genregs32_get(struct task_struct *target, { if (kbuf) { compat_ulong_t *k = kbuf; - while (count > 0) { + while (count >= sizeof(*k)) { getreg32(target, pos, k++); count -= sizeof(*k); pos += sizeof(*k); } } else { compat_ulong_t __user *u = ubuf; - while (count > 0) { + while (count >= sizeof(*u)) { compat_ulong_t word; getreg32(target, pos, &word); if (__put_user(word, u++)) @@ -1486,14 +1489,14 @@ static int genregs32_set(struct task_struct *target, int ret = 0; if (kbuf) { const compat_ulong_t *k = kbuf; - while (count > 0 && !ret) { + while (count >= sizeof(*k) && !ret) { ret = putreg32(target, pos, *k++); count -= sizeof(*k); pos += sizeof(*k); } } else { const compat_ulong_t __user *u = ubuf; - while (count > 0 && !ret) { + while (count >= sizeof(*u) && !ret) { compat_ulong_t word; ret = __get_user(word, u++); if (ret) diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 18093d7..12e9fea 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 1545bc0..704bddc 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 f7b8b98..5d9e40c 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -642,19 +642,27 @@ 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 {} }; diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 74fe6d8..4fd173c 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -545,22 +545,12 @@ sys_sigaction(int sig, const struct old_sigaction __user *act, } #endif /* CONFIG_X86_32 */ -#ifdef CONFIG_X86_32 -int sys_sigaltstack(struct pt_regs *regs) -{ - const stack_t __user *uss = (const stack_t __user *)regs->bx; - stack_t __user *uoss = (stack_t __user *)regs->cx; - - return do_sigaltstack(uss, uoss, regs->sp); -} -#else /* !CONFIG_X86_32 */ -asmlinkage long +long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, struct pt_regs *regs) { return do_sigaltstack(uss, uoss, regs->sp); } -#endif /* CONFIG_X86_32 */ /* * Do a signal return; undo the signal stack. diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 678d0b8..b4e870c 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/stacktrace.c b/arch/x86/kernel/stacktrace.c index c3eb207..922eefb 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -53,17 +53,19 @@ save_stack_address_nosched(void *data, unsigned long addr, int reliable) } static const struct stacktrace_ops save_stack_ops = { - .warning = save_stack_warning, - .warning_symbol = save_stack_warning_symbol, - .stack = save_stack_stack, - .address = save_stack_address, + .warning = save_stack_warning, + .warning_symbol = save_stack_warning_symbol, + .stack = save_stack_stack, + .address = save_stack_address, + .walk_stack = print_context_stack, }; static const struct stacktrace_ops save_stack_ops_nosched = { - .warning = save_stack_warning, - .warning_symbol = save_stack_warning_symbol, - .stack = save_stack_stack, - .address = save_stack_address_nosched, + .warning = save_stack_warning, + .warning_symbol = save_stack_warning_symbol, + .stack = save_stack_stack, + .address = save_stack_address_nosched, + .walk_stack = print_context_stack, }; /* diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index cd982f4..597683a 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -763,6 +763,7 @@ void mark_tsc_unstable(char *reason) { if (!tsc_unstable) { tsc_unstable = 1; + sched_clock_stable = 0; printk(KERN_INFO "Marking TSC unstable due to %s\n", reason); /* Change only the rating, when not registered */ if (clocksource_tsc.mult) diff --git a/arch/x86/kernel/uv_irq.c b/arch/x86/kernel/uv_irq.c index 61d805d..ece73d8 100644 --- a/arch/x86/kernel/uv_irq.c +++ b/arch/x86/kernel/uv_irq.c @@ -215,8 +215,7 @@ static int uv_set_irq_affinity(unsigned int irq, const struct cpumask *mask) unsigned long mmr_offset; unsigned mmr_pnode; - dest = set_desc_affinity(desc, mask); - if (dest == BAD_APICID) + if (set_desc_affinity(desc, mask, &dest)) return -1; mmr_value = 0; diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c index 3c84aa0..2b75ef63 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/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 9c4e625..5ffb5622 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -197,9 +197,8 @@ out: static int do_vm86_irq_handling(int subfunction, int irqnumber); static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk); -int sys_vm86old(struct pt_regs *regs) +int sys_vm86old(struct vm86_struct __user *v86, struct pt_regs *regs) { - struct vm86_struct __user *v86 = (struct vm86_struct __user *)regs->bx; struct kernel_vm86_struct info; /* declare this _on top_, * this avoids wasting of stack space. * This remains on the stack until we @@ -227,7 +226,7 @@ out: } -int sys_vm86(struct pt_regs *regs) +int sys_vm86(unsigned long cmd, unsigned long arg, struct pt_regs *regs) { struct kernel_vm86_struct info; /* declare this _on top_, * this avoids wasting of stack space. @@ -239,12 +238,12 @@ int sys_vm86(struct pt_regs *regs) struct vm86plus_struct __user *v86; tsk = current; - switch (regs->bx) { + switch (cmd) { case VM86_REQUEST_IRQ: case VM86_FREE_IRQ: case VM86_GET_IRQ_BITS: case VM86_GET_AND_RESET_IRQ: - ret = do_vm86_irq_handling(regs->bx, (int)regs->cx); + ret = do_vm86_irq_handling(cmd, (int)arg); goto out; case VM86_PLUS_INSTALL_CHECK: /* @@ -261,7 +260,7 @@ int sys_vm86(struct pt_regs *regs) ret = -EPERM; if (tsk->thread.saved_sp0) goto out; - v86 = (struct vm86plus_struct __user *)regs->cx; + v86 = (struct vm86plus_struct __user *)arg; tmp = copy_vm86_regs_from_user(&info.regs, &v86->regs, offsetof(struct kernel_vm86_struct, regs32) - sizeof(info.regs)); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index f3f2104..f92a0da 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -319,9 +319,7 @@ SECTIONS __brk_limit = .; } - .end : AT(ADDR(.end) - LOAD_OFFSET) { - _end = .; - } + _end = .; STABS_DEBUG DWARF_DEBUG diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index a102976..619f7f8 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -17,8 +17,6 @@ EXPORT_SYMBOL(mcount); #endif -EXPORT_SYMBOL(kernel_thread); - EXPORT_SYMBOL(__get_user_1); EXPORT_SYMBOL(__get_user_2); EXPORT_SYMBOL(__get_user_4); @@ -56,4 +54,6 @@ EXPORT_SYMBOL(__memcpy); EXPORT_SYMBOL(empty_zero_page); EXPORT_SYMBOL(init_level4_pgt); -EXPORT_SYMBOL(load_gs_index); +#ifndef CONFIG_PARAVIRT +EXPORT_SYMBOL(native_load_gs_index); +#endif diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 296aba4..15578f1 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 cd60c0b..ba8c045 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 4c3e5b2..89a49fb 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 a601713..ede2131 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 9d06896..a1e1bc9 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 45b20e4..cffd754f 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.o +obj-$(CONFIG_SMP) += msr-smp.o lib-y := delay.o lib-y += thunk_$(BITS).o @@ -22,7 +22,7 @@ lib-y += usercopy_$(BITS).o getuser.o putuser.o lib-y += memcpy_$(BITS).o lib-$(CONFIG_KPROBES) += insn.o inat.o -obj-y += msr-reg.o msr-reg-export.o +obj-y += msr.o msr-reg.o msr-reg-export.o ifeq ($(CONFIG_X86_32),y) obj-y += atomic64_32.o diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c new file mode 100644 index 0000000..a6b1b86 --- /dev/null +++ b/arch/x86/lib/msr-smp.c @@ -0,0 +1,204 @@ +#include <linux/module.h> +#include <linux/preempt.h> +#include <linux/smp.h> +#include <asm/msr.h> + +static void __rdmsr_on_cpu(void *info) +{ + struct msr_info *rv = info; + struct msr *reg; + int this_cpu = raw_smp_processor_id(); + + if (rv->msrs) + reg = per_cpu_ptr(rv->msrs, this_cpu); + else + reg = &rv->reg; + + rdmsr(rv->msr_no, reg->l, reg->h); +} + +static void __wrmsr_on_cpu(void *info) +{ + struct msr_info *rv = info; + struct msr *reg; + int this_cpu = raw_smp_processor_id(); + + if (rv->msrs) + reg = per_cpu_ptr(rv->msrs, this_cpu); + else + reg = &rv->reg; + + wrmsr(rv->msr_no, reg->l, reg->h); +} + +int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1); + *l = rv.reg.l; + *h = rv.reg.h; + + return err; +} +EXPORT_SYMBOL(rdmsr_on_cpu); + +int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + rv.reg.l = l; + rv.reg.h = h; + err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1); + + return err; +} +EXPORT_SYMBOL(wrmsr_on_cpu); + +static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no, + struct msr *msrs, + void (*msr_func) (void *info)) +{ + struct msr_info rv; + int this_cpu; + + memset(&rv, 0, sizeof(rv)); + + rv.msrs = msrs; + rv.msr_no = msr_no; + + this_cpu = get_cpu(); + + if (cpumask_test_cpu(this_cpu, mask)) + msr_func(&rv); + + smp_call_function_many(mask, msr_func, &rv, 1); + put_cpu(); +} + +/* rdmsr on a bunch of CPUs + * + * @mask: which CPUs + * @msr_no: which MSR + * @msrs: array of MSR values + * + */ +void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) +{ + __rwmsr_on_cpus(mask, msr_no, msrs, __rdmsr_on_cpu); +} +EXPORT_SYMBOL(rdmsr_on_cpus); + +/* + * wrmsr on a bunch of CPUs + * + * @mask: which CPUs + * @msr_no: which MSR + * @msrs: array of MSR values + * + */ +void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) +{ + __rwmsr_on_cpus(mask, msr_no, msrs, __wrmsr_on_cpu); +} +EXPORT_SYMBOL(wrmsr_on_cpus); + +/* These "safe" variants are slower and should be used when the target MSR + may not actually exist. */ +static void __rdmsr_safe_on_cpu(void *info) +{ + struct msr_info *rv = info; + + rv->err = rdmsr_safe(rv->msr_no, &rv->reg.l, &rv->reg.h); +} + +static void __wrmsr_safe_on_cpu(void *info) +{ + struct msr_info *rv = info; + + rv->err = wrmsr_safe(rv->msr_no, rv->reg.l, rv->reg.h); +} + +int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1); + *l = rv.reg.l; + *h = rv.reg.h; + + return err ? err : rv.err; +} +EXPORT_SYMBOL(rdmsr_safe_on_cpu); + +int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + rv.reg.l = l; + rv.reg.h = h; + err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1); + + return err ? err : rv.err; +} +EXPORT_SYMBOL(wrmsr_safe_on_cpu); + +/* + * These variants are significantly slower, but allows control over + * the entire 32-bit GPR set. + */ +static void __rdmsr_safe_regs_on_cpu(void *info) +{ + struct msr_regs_info *rv = info; + + rv->err = rdmsr_safe_regs(rv->regs); +} + +static void __wrmsr_safe_regs_on_cpu(void *info) +{ + struct msr_regs_info *rv = info; + + rv->err = wrmsr_safe_regs(rv->regs); +} + +int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs) +{ + int err; + struct msr_regs_info rv; + + rv.regs = regs; + rv.err = -EIO; + err = smp_call_function_single(cpu, __rdmsr_safe_regs_on_cpu, &rv, 1); + + return err ? err : rv.err; +} +EXPORT_SYMBOL(rdmsr_safe_regs_on_cpu); + +int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs) +{ + int err; + struct msr_regs_info rv; + + rv.regs = regs; + rv.err = -EIO; + err = smp_call_function_single(cpu, __wrmsr_safe_regs_on_cpu, &rv, 1); + + return err ? err : rv.err; +} +EXPORT_SYMBOL(wrmsr_safe_regs_on_cpu); diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 8728341..8f8eebd 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -1,123 +1,7 @@ #include <linux/module.h> #include <linux/preempt.h> -#include <linux/smp.h> #include <asm/msr.h> -struct msr_info { - u32 msr_no; - struct msr reg; - struct msr *msrs; - int err; -}; - -static void __rdmsr_on_cpu(void *info) -{ - struct msr_info *rv = info; - struct msr *reg; - int this_cpu = raw_smp_processor_id(); - - if (rv->msrs) - reg = per_cpu_ptr(rv->msrs, this_cpu); - else - reg = &rv->reg; - - rdmsr(rv->msr_no, reg->l, reg->h); -} - -static void __wrmsr_on_cpu(void *info) -{ - struct msr_info *rv = info; - struct msr *reg; - int this_cpu = raw_smp_processor_id(); - - if (rv->msrs) - reg = per_cpu_ptr(rv->msrs, this_cpu); - else - reg = &rv->reg; - - wrmsr(rv->msr_no, reg->l, reg->h); -} - -int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) -{ - int err; - struct msr_info rv; - - memset(&rv, 0, sizeof(rv)); - - rv.msr_no = msr_no; - err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1); - *l = rv.reg.l; - *h = rv.reg.h; - - return err; -} -EXPORT_SYMBOL(rdmsr_on_cpu); - -int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) -{ - int err; - struct msr_info rv; - - memset(&rv, 0, sizeof(rv)); - - rv.msr_no = msr_no; - rv.reg.l = l; - rv.reg.h = h; - err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1); - - return err; -} -EXPORT_SYMBOL(wrmsr_on_cpu); - -static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no, - struct msr *msrs, - void (*msr_func) (void *info)) -{ - struct msr_info rv; - int this_cpu; - - memset(&rv, 0, sizeof(rv)); - - rv.msrs = msrs; - rv.msr_no = msr_no; - - this_cpu = get_cpu(); - - if (cpumask_test_cpu(this_cpu, mask)) - msr_func(&rv); - - smp_call_function_many(mask, msr_func, &rv, 1); - put_cpu(); -} - -/* rdmsr on a bunch of CPUs - * - * @mask: which CPUs - * @msr_no: which MSR - * @msrs: array of MSR values - * - */ -void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) -{ - __rwmsr_on_cpus(mask, msr_no, msrs, __rdmsr_on_cpu); -} -EXPORT_SYMBOL(rdmsr_on_cpus); - -/* - * wrmsr on a bunch of CPUs - * - * @mask: which CPUs - * @msr_no: which MSR - * @msrs: array of MSR values - * - */ -void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) -{ - __rwmsr_on_cpus(mask, msr_no, msrs, __wrmsr_on_cpu); -} -EXPORT_SYMBOL(wrmsr_on_cpus); - struct msr *msrs_alloc(void) { struct msr *msrs = NULL; @@ -137,100 +21,3 @@ void msrs_free(struct msr *msrs) free_percpu(msrs); } EXPORT_SYMBOL(msrs_free); - -/* These "safe" variants are slower and should be used when the target MSR - may not actually exist. */ -static void __rdmsr_safe_on_cpu(void *info) -{ - struct msr_info *rv = info; - - rv->err = rdmsr_safe(rv->msr_no, &rv->reg.l, &rv->reg.h); -} - -static void __wrmsr_safe_on_cpu(void *info) -{ - struct msr_info *rv = info; - - rv->err = wrmsr_safe(rv->msr_no, rv->reg.l, rv->reg.h); -} - -int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) -{ - int err; - struct msr_info rv; - - memset(&rv, 0, sizeof(rv)); - - rv.msr_no = msr_no; - err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1); - *l = rv.reg.l; - *h = rv.reg.h; - - return err ? err : rv.err; -} -EXPORT_SYMBOL(rdmsr_safe_on_cpu); - -int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) -{ - int err; - struct msr_info rv; - - memset(&rv, 0, sizeof(rv)); - - rv.msr_no = msr_no; - rv.reg.l = l; - rv.reg.h = h; - err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1); - - return err ? err : rv.err; -} -EXPORT_SYMBOL(wrmsr_safe_on_cpu); - -/* - * These variants are significantly slower, but allows control over - * the entire 32-bit GPR set. - */ -struct msr_regs_info { - u32 *regs; - int err; -}; - -static void __rdmsr_safe_regs_on_cpu(void *info) -{ - struct msr_regs_info *rv = info; - - rv->err = rdmsr_safe_regs(rv->regs); -} - -static void __wrmsr_safe_regs_on_cpu(void *info) -{ - struct msr_regs_info *rv = info; - - rv->err = wrmsr_safe_regs(rv->regs); -} - -int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs) -{ - int err; - struct msr_regs_info rv; - - rv.regs = regs; - rv.err = -EIO; - err = smp_call_function_single(cpu, __rdmsr_safe_regs_on_cpu, &rv, 1); - - return err ? err : rv.err; -} -EXPORT_SYMBOL(rdmsr_safe_regs_on_cpu); - -int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs) -{ - int err; - struct msr_regs_info rv; - - rv.regs = regs; - rv.err = -EIO; - err = smp_call_function_single(cpu, __wrmsr_safe_regs_on_cpu, &rv, 1); - - return err ? err : rv.err; -} -EXPORT_SYMBOL(wrmsr_safe_regs_on_cpu); diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 71da1bc..738e659 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_32.c b/arch/x86/mm/init_32.c index c973f8e..9a0c258 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -892,8 +892,7 @@ 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 5198b9b..69ddfbd 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/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c index 4901d0d..af3b6c8 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/kmmio.c b/arch/x86/mm/kmmio.c index c0f6198..536fb68 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/srat_32.c b/arch/x86/mm/srat_32.c index 6f8aa33..9324f13 100644 --- a/arch/x86/mm/srat_32.c +++ b/arch/x86/mm/srat_32.c @@ -267,6 +267,8 @@ int __init get_memcfg_from_srat(void) e820_register_active_regions(chunk->nid, chunk->start_pfn, min(chunk->end_pfn, max_pfn)); } + /* for out of order entries in SRAT */ + sort_node_map(); for_each_online_node(nid) { unsigned long start = node_start_pfn[nid]; diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index d890754..28c6876 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 */ @@ -317,7 +319,7 @@ static int __init nodes_cover_memory(const struct bootnode *nodes) unsigned long s = nodes[i].start >> PAGE_SHIFT; unsigned long e = nodes[i].end >> PAGE_SHIFT; pxmram += e - s; - pxmram -= absent_pages_in_range(s, e); + pxmram -= __absent_pages_in_range(i, s, e); if ((long)pxmram < 0) pxmram = 0; } @@ -373,6 +375,8 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) for_each_node_mask(i, nodes_parsed) e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT, nodes[i].end >> PAGE_SHIFT); + /* for out of order entries in SRAT */ + sort_node_map(); if (!nodes_cover_memory(nodes)) { bad_srat(); return -1; diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index 044897b..3855096 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -41,10 +41,11 @@ static void backtrace_address(void *data, unsigned long addr, int reliable) } static struct stacktrace_ops backtrace_ops = { - .warning = backtrace_warning, - .warning_symbol = backtrace_warning_symbol, - .stack = backtrace_stack, - .address = backtrace_address, + .warning = backtrace_warning, + .warning_symbol = backtrace_warning_symbol, + .stack = backtrace_stack, + .address = backtrace_address, + .walk_stack = print_context_stack, }; struct frame_head { diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index cb88b1a..3347f69 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -222,7 +222,7 @@ 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; @@ -598,6 +598,7 @@ 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/pci/Makefile b/arch/x86/pci/Makefile index 564b008..39fba37 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/bus_numa.c b/arch/x86/pci/bus_numa.c index 145df00..f939d60 100644 --- a/arch/x86/pci/bus_numa.c +++ b/arch/x86/pci/bus_numa.c @@ -51,7 +51,7 @@ 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/intel_bus.c b/arch/x86/pci/intel_bus.c deleted file mode 100644 index b7a55dc..0000000 --- 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/tools/chkobjdump.awk b/arch/x86/tools/chkobjdump.awk index 0d13cd9..fd1ab80 100644 --- a/arch/x86/tools/chkobjdump.awk +++ b/arch/x86/tools/chkobjdump.awk @@ -8,14 +8,24 @@ BEGIN { od_sver = 19; } -/^GNU/ { - split($4, ver, "."); +/^GNU objdump/ { + verstr = "" + for (i = 3; i <= NF; i++) + if (match($(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", - $4, od_ver, od_sver); + verstr, od_ver, od_sver); print("Warning: Skipping posttest."); # Logic is inverted, because we just skip test without error. exit 0; diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk index e34e92a..eaf11f5 100644 --- a/arch/x86/tools/gen-insn-attr-x86.awk +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -6,8 +6,6 @@ # Awk implementation sanity check function check_awk_implement() { - if (!match("abc", "[[:lower:]]+")) - return "Your awk doesn't support charactor-class." if (sprintf("%x", 0) != "0") return "Your awk has a printf-format problem." return "" @@ -44,12 +42,12 @@ BEGIN { delete gtable delete atable - opnd_expr = "^[[:alpha:]/]" + opnd_expr = "^[A-Za-z/]" ext_expr = "^\\(" sep_expr = "^\\|$" - group_expr = "^Grp[[:alnum:]]+" + group_expr = "^Grp[0-9A-Za-z]+" - imm_expr = "^[IJAO][[:lower:]]" + imm_expr = "^[IJAO][a-z]" imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)" imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)" imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)" @@ -62,7 +60,7 @@ BEGIN { imm_flag["Ob"] = "INAT_MOFFSET" imm_flag["Ov"] = "INAT_MOFFSET" - modrm_expr = "^([CDEGMNPQRSUVW/][[:lower:]]+|NTA|T[012])" + modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])" force64_expr = "\\([df]64\\)" rex_expr = "^REX(\\.[XRWB]+)*" fpu_expr = "^ESC" # TODO @@ -226,12 +224,12 @@ function add_flags(old,new) { } # convert operands to flags. -function convert_operands(opnd, i,imm,mod) +function convert_operands(count,opnd, i,j,imm,mod) { imm = null mod = null - for (i in opnd) { - i = opnd[i] + for (j = 1; j <= count; j++) { + i = opnd[j] if (match(i, imm_expr) == 1) { if (!imm_flag[i]) semantic_error("Unknown imm opnd: " i) @@ -282,8 +280,8 @@ function convert_operands(opnd, i,imm,mod) # parse one opcode if (match($i, opnd_expr)) { opnd = $i - split($(i++), opnds, ",") - flags = convert_operands(opnds) + count = split($(i++), opnds, ",") + flags = convert_operands(count, opnds) } if (match($i, ext_expr)) ext = $(i++) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 2b26dd5..36daccb 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(); |