diff options
Diffstat (limited to 'arch/x86')
42 files changed, 228 insertions, 128 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index df9e885eee14..a6efe0a2e9ae 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -498,6 +498,19 @@ config PARAVIRT over full virtualization. However, when run without a hypervisor the kernel is theoretically slower and slightly larger. +config PARAVIRT_SPINLOCKS + bool "Paravirtualization layer for spinlocks" + depends on PARAVIRT && SMP && EXPERIMENTAL + ---help--- + Paravirtualized spinlocks allow a pvops backend to replace the + spinlock implementation with something virtualization-friendly + (for example, block the virtual CPU rather than spinning). + + Unfortunately the downside is an up to 5% performance hit on + native kernels, with various workloads. + + If you are unsure how to answer this question, answer N. + config PARAVIRT_CLOCK bool default n diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c index 857e492c571e..bbeb0c3fbd90 100644 --- a/arch/x86/boot/compressed/relocs.c +++ b/arch/x86/boot/compressed/relocs.c @@ -504,8 +504,11 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym)) if (sym->st_shndx == SHN_ABS) { continue; } - if (r_type == R_386_PC32) { - /* PC relative relocations don't need to be adjusted */ + if (r_type == R_386_NONE || r_type == 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) { /* Visit relocations that need to be adjusted */ diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c index 5054c2ddd1a0..74b3d2ba84e9 100644 --- a/arch/x86/boot/memory.c +++ b/arch/x86/boot/memory.c @@ -17,11 +17,6 @@ #define SMAP 0x534d4150 /* ASCII "SMAP" */ -struct e820_ext_entry { - struct e820entry std; - u32 ext_flags; -} __attribute__((packed)); - static int detect_memory_e820(void) { int count = 0; @@ -29,13 +24,21 @@ static int detect_memory_e820(void) u32 size, id, edi; u8 err; struct e820entry *desc = boot_params.e820_map; - static struct e820_ext_entry buf; /* static so it is zeroed */ + static struct e820entry buf; /* static so it is zeroed */ /* - * Set this here so that if the BIOS doesn't change this field - * but still doesn't change %ecx, we're still okay... + * Note: at least one BIOS is known which assumes that the + * buffer pointed to by one e820 call is the same one as + * the previous call, and only changes modified fields. Therefore, + * we use a temporary buffer and copy the results entry by entry. + * + * This routine deliberately does not try to account for + * ACPI 3+ extended attributes. This is because there are + * BIOSes in the field which report zero for the valid bit for + * all ranges, and we don't currently make any use of the + * other attribute bits. Revisit this if we see the extended + * attribute bits deployed in a meaningful way in the future. */ - buf.ext_flags = 1; do { size = sizeof buf; @@ -66,13 +69,7 @@ static int detect_memory_e820(void) break; } - /* ACPI 3.0 added the extended flags support. If bit 0 - in the extended flags is zero, we're supposed to simply - ignore the entry -- a backwards incompatible change! */ - if (size > 20 && !(buf.ext_flags & 1)) - continue; - - *desc++ = buf.std; + *desc++ = buf; count++; } while (next && count < ARRAY_SIZE(boot_params.e820_map)); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 563933e06a35..4f8c199584e7 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -137,6 +137,7 @@ DECLARE_PER_CPU(mce_banks_t, mce_poll_banks); enum mcp_flags { MCP_TIMESTAMP = (1 << 0), /* log time stamp */ MCP_UC = (1 << 1), /* log uncorrected errors */ + MCP_DONTLOG = (1 << 2), /* only clear, don't log */ }; extern void machine_check_poll(enum mcp_flags flags, mce_banks_t *b); diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 378e3691c08c..a53da004e08e 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -1443,7 +1443,7 @@ u64 _paravirt_ident_64(u64); #define paravirt_nop ((void *)_paravirt_nop) -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS) static inline int __raw_spin_is_locked(struct raw_spinlock *lock) { diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index aee103b26d01..02ecb30982a3 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -82,22 +82,22 @@ do { \ case 1: \ asm(op "b %1,"__percpu_arg(0) \ : "+m" (var) \ - : "ri" ((T__)val)); \ + : "qi" ((T__)(val))); \ break; \ case 2: \ asm(op "w %1,"__percpu_arg(0) \ : "+m" (var) \ - : "ri" ((T__)val)); \ + : "ri" ((T__)(val))); \ break; \ case 4: \ asm(op "l %1,"__percpu_arg(0) \ : "+m" (var) \ - : "ri" ((T__)val)); \ + : "ri" ((T__)(val))); \ break; \ case 8: \ asm(op "q %1,"__percpu_arg(0) \ : "+m" (var) \ - : "re" ((T__)val)); \ + : "re" ((T__)(val))); \ break; \ default: __bad_percpu_size(); \ } \ @@ -109,7 +109,7 @@ do { \ switch (sizeof(var)) { \ case 1: \ asm(op "b "__percpu_arg(1)",%0" \ - : "=r" (ret__) \ + : "=q" (ret__) \ : "m" (var)); \ break; \ case 2: \ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index e304b66abeea..624f133943ed 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -187,14 +187,15 @@ static inline int v8086_mode(struct pt_regs *regs) /* * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode - * when it traps. So regs will be the current sp. + * when it traps. The previous stack will be directly underneath the saved + * registers, and 'sp/ss' won't even have been saved. Thus the '®s->sp'. * * This is valid only for kernel mode traps. */ -static inline unsigned long kernel_trap_sp(struct pt_regs *regs) +static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { #ifdef CONFIG_X86_32 - return (unsigned long)regs; + return (unsigned long)(®s->sp); #else return regs->sp; #endif diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index e5e6caffec87..b7e5db876399 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -172,7 +172,7 @@ static inline int __ticket_spin_is_contended(raw_spinlock_t *lock) return (((tmp >> TICKET_SHIFT) - tmp) & ((1 << TICKET_SHIFT) - 1)) > 1; } -#ifndef CONFIG_PARAVIRT +#ifndef CONFIG_PARAVIRT_SPINLOCKS static inline int __raw_spin_is_locked(raw_spinlock_t *lock) { @@ -206,7 +206,7 @@ static __always_inline void __raw_spin_lock_flags(raw_spinlock_t *lock, __raw_spin_lock(lock); } -#endif +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock) { diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 145cce75cda7..88d1bfc847d3 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -89,7 +89,8 @@ obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o obj-$(CONFIG_VMI) += vmi_32.o vmiclock_32.o obj-$(CONFIG_KVM_GUEST) += kvm.o obj-$(CONFIG_KVM_CLOCK) += kvmclock.o -obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o paravirt-spinlocks.o +obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o +obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 42c33cebf00f..8c0be0902dac 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -49,10 +49,10 @@ #define IVHD_DEV_EXT_SELECT 0x46 #define IVHD_DEV_EXT_SELECT_RANGE 0x47 -#define IVHD_FLAG_HT_TUN_EN 0x00 -#define IVHD_FLAG_PASSPW_EN 0x01 -#define IVHD_FLAG_RESPASSPW_EN 0x02 -#define IVHD_FLAG_ISOC_EN 0x03 +#define IVHD_FLAG_HT_TUN_EN_MASK 0x01 +#define IVHD_FLAG_PASSPW_EN_MASK 0x02 +#define IVHD_FLAG_RESPASSPW_EN_MASK 0x04 +#define IVHD_FLAG_ISOC_EN_MASK 0x08 #define IVMD_FLAG_EXCL_RANGE 0x08 #define IVMD_FLAG_UNITY_MAP 0x01 @@ -569,19 +569,19 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu, * First set the recommended feature enable bits from ACPI * into the IOMMU control registers */ - h->flags & IVHD_FLAG_HT_TUN_EN ? + h->flags & IVHD_FLAG_HT_TUN_EN_MASK ? iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) : iommu_feature_disable(iommu, CONTROL_HT_TUN_EN); - h->flags & IVHD_FLAG_PASSPW_EN ? + h->flags & IVHD_FLAG_PASSPW_EN_MASK ? iommu_feature_enable(iommu, CONTROL_PASSPW_EN) : iommu_feature_disable(iommu, CONTROL_PASSPW_EN); - h->flags & IVHD_FLAG_RESPASSPW_EN ? + h->flags & IVHD_FLAG_RESPASSPW_EN_MASK ? iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) : iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN); - h->flags & IVHD_FLAG_ISOC_EN ? + h->flags & IVHD_FLAG_ISOC_EN_MASK ? iommu_feature_enable(iommu, CONTROL_ISOC_EN) : iommu_feature_disable(iommu, CONTROL_ISOC_EN); diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 1c11b819f245..302947775575 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -254,7 +254,7 @@ static int parse_unisys_oem(char *oemptr) } #ifdef CONFIG_ACPI -static int find_unisys_acpi_oem_table(unsigned long *oem_addr) +static int __init find_unisys_acpi_oem_table(unsigned long *oem_addr) { struct acpi_table_header *header = NULL; struct es7000_oem_table *table; @@ -285,7 +285,7 @@ static int find_unisys_acpi_oem_table(unsigned long *oem_addr) return 0; } -static void unmap_unisys_acpi_oem_table(unsigned long oem_addr) +static void __init unmap_unisys_acpi_oem_table(unsigned long oem_addr) { if (!oem_addr) return; @@ -306,7 +306,7 @@ static int es7000_check_dsdt(void) static int es7000_acpi_ret; /* Hook from generic ACPI tables.c */ -static int es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { unsigned long oem_addr = 0; int check_dsdt; @@ -717,7 +717,7 @@ struct apic apic_es7000_cluster = { .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, }; -struct apic apic_es7000 = { +struct apic __refdata apic_es7000 = { .name = "es7000", .probe = probe_es7000, diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c4f667896c28..77848d9fca68 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -114,6 +114,13 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { } }; EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); +static int __init x86_xsave_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_XSAVE); + return 1; +} +__setup("noxsave", x86_xsave_setup); + #ifdef CONFIG_X86_32 static int cachesize_override __cpuinitdata = -1; static int disable_x86_serial_nr __cpuinitdata = 1; @@ -1203,6 +1210,8 @@ void __cpuinit cpu_init(void) load_TR_desc(); load_LDT(&init_mm.context); + t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); + #ifdef CONFIG_DOUBLEFAULT /* Set up doublefault TSS pointer in the GDT */ __set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss); diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 208ecf6643df..54b6de2cd947 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -693,8 +693,8 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE && policy->cpuinfo.transition_latency > 20 * 1000) { policy->cpuinfo.transition_latency = 20 * 1000; - printk_once(KERN_INFO "Capping off P-state tranision" - " latency at 20 uS\n"); + printk_once(KERN_INFO + "P-state transition latency capped at 20 uS\n"); } /* table init */ diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index 6ac55bd341ae..869615193720 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -168,6 +168,7 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c) case 0x0E: /* Core */ case 0x0F: /* Core Duo */ case 0x16: /* Celeron Core */ + case 0x1C: /* Atom */ p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; return speedstep_get_frequency(SPEEDSTEP_CPU_PCORE); case 0x0D: /* Pentium M (Dothan) */ diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c index 3c28ccd49742..a8363e5be4ef 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c @@ -168,10 +168,12 @@ static int check_powernow(void) return 1; } +#ifdef CONFIG_X86_POWERNOW_K7_ACPI static void invalidate_entry(unsigned int entry) { powernow_table[entry].frequency = CPUFREQ_ENTRY_INVALID; } +#endif static int get_ranges(unsigned char *pst) { diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 4709ead2db52..f6b32d112357 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -649,6 +649,20 @@ static void print_basics(struct powernow_k8_data *data) data->batps); } +static u32 freq_from_fid_did(u32 fid, u32 did) +{ + u32 mhz = 0; + + if (boot_cpu_data.x86 == 0x10) + mhz = (100 * (fid + 0x10)) >> did; + else if (boot_cpu_data.x86 == 0x11) + mhz = (100 * (fid + 8)) >> did; + else + BUG(); + + return mhz * 1000; +} + static int fill_powernow_table(struct powernow_k8_data *data, struct pst_s *pst, u8 maxvid) { @@ -923,8 +937,13 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, powernow_table[i].index = index; - powernow_table[i].frequency = - data->acpi_data.states[i].core_frequency * 1000; + /* Frequency may be rounded for these */ + if (boot_cpu_data.x86 == 0x10 || boot_cpu_data.x86 == 0x11) { + powernow_table[i].frequency = + freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7); + } else + powernow_table[i].frequency = + data->acpi_data.states[i].core_frequency * 1000; } return 0; } @@ -1215,13 +1234,16 @@ static int powernowk8_verify(struct cpufreq_policy *pol) return cpufreq_frequency_table_verify(pol, data->powernow_table); } +static const char ACPI_PSS_BIOS_BUG_MSG[] = + KERN_ERR FW_BUG PFX "No compatible ACPI _PSS objects found.\n" + KERN_ERR FW_BUG PFX "Try again with latest BIOS.\n"; + /* per CPU init entry point to the driver */ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) { struct powernow_k8_data *data; cpumask_t oldmask; int rc; - static int print_once; if (!cpu_online(pol->cpu)) return -ENODEV; @@ -1244,19 +1266,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) * an UP version, and is deprecated by AMD. */ if (num_online_cpus() != 1) { - /* - * Replace this one with print_once as soon as such a - * thing gets introduced - */ - if (!print_once) { - WARN_ONCE(1, KERN_ERR FW_BUG PFX "Your BIOS " - "does not provide ACPI _PSS objects " - "in a way that Linux understands. " - "Please report this to the Linux ACPI" - " maintainers and complain to your " - "BIOS vendor.\n"); - print_once++; - } + printk_once(ACPI_PSS_BIOS_BUG_MSG); goto err_out; } if (pol->cpu != 0) { diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c index 863f89568b1a..6fb0b359d2a5 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c @@ -239,9 +239,10 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - - mce_log(&m); - add_taint(TAINT_MACHINE_CHECK); + if (!(flags & MCP_DONTLOG)) { + mce_log(&m); + add_taint(TAINT_MACHINE_CHECK); + } /* * Clear state for this bank. @@ -452,13 +453,14 @@ void mce_log_therm_throt_event(__u64 status) */ static int check_interval = 5 * 60; /* 5 minutes */ -static int next_interval; /* in jiffies */ +static DEFINE_PER_CPU(int, next_interval); /* in jiffies */ static void mcheck_timer(unsigned long); static DEFINE_PER_CPU(struct timer_list, mce_timer); static void mcheck_timer(unsigned long data) { struct timer_list *t = &per_cpu(mce_timer, data); + int *n; WARN_ON(smp_processor_id() != data); @@ -470,14 +472,14 @@ static void mcheck_timer(unsigned long data) * Alert userspace if needed. If we logged an MCE, reduce the * polling interval, otherwise increase the polling interval. */ + n = &__get_cpu_var(next_interval); if (mce_notify_user()) { - next_interval = max(next_interval/2, HZ/100); + *n = max(*n/2, HZ/100); } else { - next_interval = min(next_interval * 2, - (int)round_jiffies_relative(check_interval*HZ)); + *n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ)); } - t->expires = jiffies + next_interval; + t->expires = jiffies + *n; add_timer(t); } @@ -584,7 +586,7 @@ static void mce_init(void *dummy) * Log the machine checks left over from the previous reset. */ bitmap_fill(all_banks, MAX_NR_BANKS); - machine_check_poll(MCP_UC, &all_banks); + machine_check_poll(MCP_UC|(!mce_bootlog ? MCP_DONTLOG : 0), &all_banks); set_in_cr4(X86_CR4_MCE); @@ -632,14 +634,13 @@ static void mce_cpu_features(struct cpuinfo_x86 *c) static void mce_init_timer(void) { struct timer_list *t = &__get_cpu_var(mce_timer); + int *n = &__get_cpu_var(next_interval); - /* data race harmless because everyone sets to the same value */ - if (!next_interval) - next_interval = check_interval * HZ; - if (!next_interval) + *n = check_interval * HZ; + if (!*n) return; setup_timer(t, mcheck_timer, smp_processor_id()); - t->expires = round_jiffies(jiffies + next_interval); + t->expires = round_jiffies(jiffies + *n); add_timer(t); } @@ -907,7 +908,6 @@ static void mce_cpu_restart(void *data) /* Reinit MCEs after user configuration changes */ static void mce_restart(void) { - next_interval = check_interval * HZ; on_each_cpu(mce_cpu_restart, NULL, 1); } @@ -1110,7 +1110,8 @@ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb, break; case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: - t->expires = round_jiffies(jiffies + next_interval); + t->expires = round_jiffies(jiffies + + __get_cpu_var(next_interval)); add_timer_on(t, cpu); smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); break; diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c index d6b72df89d69..cef3ee30744b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c @@ -151,10 +151,11 @@ static void print_update(char *type, int *hdr, int num) static void cmci_discover(int banks, int boot) { unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned); + unsigned long flags; int hdr = 0; int i; - spin_lock(&cmci_discover_lock); + spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { u64 val; @@ -184,7 +185,7 @@ static void cmci_discover(int banks, int boot) WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks))); } } - spin_unlock(&cmci_discover_lock); + spin_unlock_irqrestore(&cmci_discover_lock, flags); if (hdr) printk(KERN_CONT "\n"); } @@ -211,13 +212,14 @@ void cmci_recheck(void) */ void cmci_clear(void) { + unsigned long flags; int i; int banks; u64 val; if (!cmci_supported(&banks)) return; - spin_lock(&cmci_discover_lock); + spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { if (!test_bit(i, __get_cpu_var(mce_banks_owned))) continue; @@ -227,7 +229,7 @@ void cmci_clear(void) wrmsrl(MSR_IA32_MC0_CTL2 + i, val); __clear_bit(i, __get_cpu_var(mce_banks_owned)); } - spin_unlock(&cmci_discover_lock); + spin_unlock_irqrestore(&cmci_discover_lock, flags); } /* diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 0b776c09aff3..d21d4fb161f7 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -275,7 +275,11 @@ static void __init print_mtrr_state(void) } printk(KERN_DEBUG "MTRR variable ranges %sabled:\n", mtrr_state.enabled & 2 ? "en" : "dis"); - high_width = ((size_or_mask ? ffs(size_or_mask) - 1 : 32) - (32 - PAGE_SHIFT) + 3) / 4; + if (size_or_mask & 0xffffffffUL) + high_width = ffs(size_or_mask & 0xffffffffUL) - 1; + else + high_width = ffs(size_or_mask>>32) + 32 - 1; + high_width = (high_width - (32 - PAGE_SHIFT) + 3) / 4; for (i = 0; i < num_var_ranges; ++i) { if (mtrr_state.var_ranges[i].mask_lo & (1 << 11)) printk(KERN_DEBUG " %u base %0*X%05X000 mask %0*X%05X000 %s\n", diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index f93047fed791..d5e30397246b 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, if (c->x86_max_cores * smp_num_siblings > 1) { seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); seq_printf(m, "siblings\t: %d\n", - cpumask_weight(cpu_sibling_mask(cpu))); + cpumask_weight(cpu_core_mask(cpu))); seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); seq_printf(m, "apicid\t\t: %d\n", c->apicid); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index ef2c3563357d..006281302925 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1074,12 +1074,13 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) u64 addr; u64 start; - start = startt; - while (size < sizet && (start + 1)) + for (start = startt; ; start += size) { start = find_e820_area_size(start, &size, align); - - if (size < sizet) - return 0; + if (!(start + 1)) + return 0; + if (size >= sizet) + break; + } #ifdef CONFIG_X86_32 if (start >= MAXMEM) diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 18dfa30795c9..b79c5533c421 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -442,7 +442,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) _ASM_EXTABLE(1b, 4b) _ASM_EXTABLE(2b, 4b) - : [old] "=r" (old), [faulted] "=r" (faulted) + : [old] "=&r" (old), [faulted] "=r" (faulted) : [parent] "r" (parent), [return_hooker] "r" (return_hooker) : "memory" ); diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index eedfaebe1063..b1f4dffb919e 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -88,6 +88,7 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) gdb_regs[GDB_SS] = __KERNEL_DS; gdb_regs[GDB_FS] = 0xFFFF; gdb_regs[GDB_GS] = 0xFFFF; + gdb_regs[GDB_SP] = (int)®s->sp; #else gdb_regs[GDB_R8] = regs->r8; gdb_regs[GDB_R9] = regs->r9; @@ -100,8 +101,8 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) gdb_regs32[GDB_PS] = regs->flags; gdb_regs32[GDB_CS] = regs->cs; gdb_regs32[GDB_SS] = regs->ss; -#endif gdb_regs[GDB_SP] = regs->sp; +#endif } /** diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index e7368c1da01d..c1c429d00130 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -194,7 +194,7 @@ void machine_kexec(struct kimage *image) unsigned int preserve_context); #ifdef CONFIG_KEXEC_JUMP - if (kexec_image->preserve_context) + if (image->preserve_context) save_processor_state(); #endif @@ -253,7 +253,7 @@ void machine_kexec(struct kimage *image) image->preserve_context); #ifdef CONFIG_KEXEC_JUMP - if (kexec_image->preserve_context) + if (image->preserve_context) restore_processor_state(); #endif diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 89cea4d44679..84c3bf209e98 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -274,7 +274,7 @@ void machine_kexec(struct kimage *image) int save_ftrace_enabled; #ifdef CONFIG_KEXEC_JUMP - if (kexec_image->preserve_context) + if (image->preserve_context) save_processor_state(); #endif @@ -333,7 +333,7 @@ void machine_kexec(struct kimage *image) image->preserve_context); #ifdef CONFIG_KEXEC_JUMP - if (kexec_image->preserve_context) + if (image->preserve_context) restore_processor_state(); #endif diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 8e45f4464880..9faf43bea336 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -134,7 +134,9 @@ static void *get_call_destination(u8 type) .pv_irq_ops = pv_irq_ops, .pv_apic_ops = pv_apic_ops, .pv_mmu_ops = pv_mmu_ops, +#ifdef CONFIG_PARAVIRT_SPINLOCKS .pv_lock_ops = pv_lock_ops, +#endif }; return *((void **)&tmpl + type); } diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 1340dad417f4..667188e0b5a0 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -232,6 +232,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Dell DXP061"), }, }, + { /* Handle problems with rebooting on Sony VGN-Z540N */ + .callback = set_bios_reboot, + .ident = "Sony VGN-Z540N", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"), + }, + }, { } }; diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 3a97a4cf1872..8f0e13be36b3 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -160,8 +160,10 @@ static ssize_t __init setup_pcpu_remap(size_t static_size) /* * If large page isn't supported, there's no benefit in doing * this. Also, on non-NUMA, embedding is better. + * + * NOTE: disabled for now. */ - if (!cpu_has_pse || !pcpu_need_numa()) + if (true || !cpu_has_pse || !pcpu_need_numa()) return -EINVAL; /* diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index b6caf1329b1b..32cf11e5728a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2897,8 +2897,7 @@ static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu, static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu) { - kvm_x86_ops->tlb_flush(vcpu); - set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests); + kvm_set_cr3(vcpu, vcpu->arch.cr3); return 1; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 1821c2078199..1f8510c51d6e 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -411,7 +411,6 @@ static __init int svm_hardware_setup(void) iopm_va = page_address(iopm_pages); memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER)); - clear_bit(0x80, iopm_va); /* allow direct access to PC debug port */ iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT; if (boot_cpu_has(X86_FEATURE_NX)) @@ -796,6 +795,11 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1; var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1; + /* AMD's VMCB does not have an explicit unusable field, so emulate it + * for cross vendor migration purposes by "not present" + */ + var->unusable = !var->present || (var->type == 0); + switch (seg) { case VCPU_SREG_CS: /* @@ -827,8 +831,6 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, var->type |= 0x1; break; } - - var->unusable = !var->present; } static int svm_get_cpl(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7c1ce5ac6131..3944e917e794 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -338,6 +338,9 @@ EXPORT_SYMBOL_GPL(kvm_lmsw); void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { + unsigned long old_cr4 = vcpu->arch.cr4; + unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE; + if (cr4 & CR4_RESERVED_BITS) { printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n"); kvm_inject_gp(vcpu, 0); @@ -351,7 +354,8 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) kvm_inject_gp(vcpu, 0); return; } - } else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & X86_CR4_PAE) + } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) + && ((cr4 ^ old_cr4) & pdptr_bits) && !load_pdptrs(vcpu, vcpu->arch.cr3)) { printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n"); kvm_inject_gp(vcpu, 0); @@ -1121,9 +1125,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) static int is_efer_nx(void) { - u64 efer; + unsigned long long efer = 0; - rdmsrl(MSR_EFER, efer); + rdmsrl_safe(MSR_EFER, &efer); return efer & EFER_NX; } @@ -1259,7 +1263,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, bit(X86_FEATURE_CMOV) | bit(X86_FEATURE_PSE36) | bit(X86_FEATURE_MMX) | bit(X86_FEATURE_FXSR) | bit(X86_FEATURE_SYSCALL) | - (bit(X86_FEATURE_NX) && is_efer_nx()) | + (is_efer_nx() ? bit(X86_FEATURE_NX) : 0) | #ifdef CONFIG_X86_64 bit(X86_FEATURE_LM) | #endif diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 8f307d914c2e..f46c340727b8 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -26,12 +26,16 @@ static unsigned long page_table_shareable(struct vm_area_struct *svma, unsigned long sbase = saddr & PUD_MASK; unsigned long s_end = sbase + PUD_SIZE; + /* Allow segments to share if only one is marked locked */ + unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED; + unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED; + /* * match the virtual addresses, permission and the alignment of the * page table page. */ if (pmd_index(addr) != pmd_index(saddr) || - vma->vm_flags != svma->vm_flags || + vm_flags != svm_flags || sbase < svma->vm_start || svma->vm_end < s_end) return 0; diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index fd3da1dda1c9..ae4f7b5d7104 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -7,6 +7,7 @@ #include <asm/page.h> #include <asm/page_types.h> #include <asm/sections.h> +#include <asm/setup.h> #include <asm/system.h> #include <asm/tlbflush.h> @@ -304,8 +305,23 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, #endif #ifdef CONFIG_X86_64 - if (!after_bootmem) + if (!after_bootmem && !start) { + pud_t *pud; + pmd_t *pmd; + mmu_cr4_features = read_cr4(); + + /* + * _brk_end cannot change anymore, but it and _end may be + * located on different 2M pages. cleanup_highmap(), however, + * can only consider _end when it runs, so destroy any + * mappings beyond _brk_end here. + */ + pud = pud_offset(pgd_offset_k(_brk_end), _brk_end); + pmd = pmd_offset(pud, _brk_end - 1); + while (++pmd <= pmd_offset(pud, (unsigned long)_end - 1)) + pmd_clear(pmd); + } #endif __flush_tlb_all(); diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 4f115e00486b..50dc802a1c46 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -87,7 +87,7 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr) { struct kmmio_probe *p; list_for_each_entry_rcu(p, &kmmio_probes, list) { - if (addr >= p->addr && addr <= (p->addr + p->len)) + if (addr >= p->addr && addr < (p->addr + p->len)) return p; } return NULL; diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 797f9f107cb6..e17efed088c5 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -153,7 +153,7 @@ static void __cpa_flush_all(void *arg) */ __flush_tlb_all(); - if (cache && boot_cpu_data.x86_model >= 4) + if (cache && boot_cpu_data.x86 >= 4) wbinvd(); } @@ -208,20 +208,15 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache, int in_flags, struct page **pages) { unsigned int i, level; + unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */ BUG_ON(irqs_disabled()); - on_each_cpu(__cpa_flush_range, NULL, 1); + on_each_cpu(__cpa_flush_all, (void *) do_wbinvd, 1); - if (!cache) + if (!cache || do_wbinvd) return; - /* 4M threshold */ - if (numpages >= 1024) { - if (boot_cpu_data.x86_model >= 4) - wbinvd(); - return; - } /* * We only need to flush on one CPU, * clflush is a MESI-coherent instruction that diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c index 16ae70fc57e7..29a0e37114f8 100644 --- a/arch/x86/mm/srat_32.c +++ b/arch/x86/mm/srat_32.c @@ -216,7 +216,7 @@ int __init get_memcfg_from_srat(void) if (num_memory_chunks == 0) { printk(KERN_WARNING - "could not finy any ACPI SRAT memory areas.\n"); + "could not find any ACPI SRAT memory areas.\n"); goto out_fail; } diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 33c5fa57e43d..01765955baaf 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -361,6 +361,7 @@ static void __init unparse_node(int node) { int i; node_clear(node, nodes_parsed); + node_clear(node, cpu_nodes_parsed); for (i = 0; i < MAX_LOCAL_APIC; i++) { if (apicid_to_node[i] == node) apicid_to_node[i] = NUMA_NO_NODE; diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index 04df67f8a7ba..044897be021f 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -76,9 +76,9 @@ void x86_backtrace(struct pt_regs * const regs, unsigned int depth) { struct frame_head *head = (struct frame_head *)frame_pointer(regs); - unsigned long stack = kernel_trap_sp(regs); if (!user_mode_vm(regs)) { + unsigned long stack = kernel_stack_pointer(regs); if (depth) dump_trace(NULL, regs, (unsigned long *)stack, 0, &backtrace_ops, &depth); diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index d9d35824c56f..6a40b78b46aa 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -104,11 +104,13 @@ notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) { long ret; if (likely(gtod->sysctl_enabled && gtod->clock.vread)) { - BUILD_BUG_ON(offsetof(struct timeval, tv_usec) != - offsetof(struct timespec, tv_nsec) || - sizeof(*tv) != sizeof(struct timespec)); - do_realtime((struct timespec *)tv); - tv->tv_usec /= 1000; + if (likely(tv != NULL)) { + BUILD_BUG_ON(offsetof(struct timeval, tv_usec) != + offsetof(struct timespec, tv_nsec) || + sizeof(*tv) != sizeof(struct timespec)); + do_realtime((struct timespec *)tv); + tv->tv_usec /= 1000; + } if (unlikely(tz != NULL)) { /* Avoid memcpy. Some old compilers fail to inline it */ tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest; diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 3b767d03fd6a..172438f86a02 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -9,5 +9,6 @@ obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \ time.o xen-asm.o xen-asm_$(BITS).o \ grant-table.o suspend.o -obj-$(CONFIG_SMP) += smp.o spinlock.o -obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o
\ No newline at end of file +obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o +obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 9842b1212407..fba55b1a4021 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -42,6 +42,7 @@ #include <linux/highmem.h> #include <linux/debugfs.h> #include <linux/bug.h> +#include <linux/module.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -1794,6 +1795,11 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir))); + reserve_early(__pa(xen_start_info->pt_base), + __pa(xen_start_info->pt_base + + xen_start_info->nr_pt_frames * PAGE_SIZE), + "XEN PAGETABLES"); + return swapper_pg_dir; } #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 20139464943c..ca6596b05d53 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -62,15 +62,26 @@ void xen_setup_vcpu_info_placement(void); #ifdef CONFIG_SMP void xen_smp_init(void); -void __init xen_init_spinlocks(void); -__cpuinit void xen_init_lock_cpu(int cpu); -void xen_uninit_lock_cpu(int cpu); - extern cpumask_var_t xen_cpu_initialized_map; #else static inline void xen_smp_init(void) {} #endif +#ifdef CONFIG_PARAVIRT_SPINLOCKS +void __init xen_init_spinlocks(void); +__cpuinit void xen_init_lock_cpu(int cpu); +void xen_uninit_lock_cpu(int cpu); +#else +static inline void xen_init_spinlocks(void) +{ +} +static inline void xen_init_lock_cpu(int cpu) +{ +} +static inline void xen_uninit_lock_cpu(int cpu) +{ +} +#endif /* Declare an asm function, along with symbols needed to make it inlineable */ |