diff options
Diffstat (limited to 'arch/x86')
39 files changed, 334 insertions, 323 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index fe120da25625..787072769a80 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -207,6 +207,12 @@ config ARCH_HIBERNATION_POSSIBLE config ARCH_SUSPEND_POSSIBLE def_bool y +config ARCH_WANT_HUGE_PMD_SHARE + def_bool y + +config ARCH_WANT_GENERAL_HUGETLB + def_bool y + config ZONE_DMA32 bool default X86_64 diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index c205035a6b96..d606463aa6d6 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -992,18 +992,20 @@ static efi_status_t exit_boot(struct boot_params *boot_params, efi_memory_desc_t *mem_map; efi_status_t status; __u32 desc_version; + bool called_exit = false; u8 nr_entries; int i; size = sizeof(*mem_map) * 32; again: - size += sizeof(*mem_map); + size += sizeof(*mem_map) * 2; _size = size; status = low_alloc(size, 1, (unsigned long *)&mem_map); if (status != EFI_SUCCESS) return status; +get_map: status = efi_call_phys5(sys_table->boottime->get_memory_map, &size, mem_map, &key, &desc_size, &desc_version); if (status == EFI_BUFFER_TOO_SMALL) { @@ -1029,8 +1031,20 @@ again: /* Might as well exit boot services now */ status = efi_call_phys2(sys_table->boottime->exit_boot_services, handle, key); - if (status != EFI_SUCCESS) - goto free_mem_map; + if (status != EFI_SUCCESS) { + /* + * ExitBootServices() will fail if any of the event + * handlers change the memory map. In which case, we + * must be prepared to retry, but only once so that + * we're guaranteed to exit on repeated failures instead + * of spinning forever. + */ + if (called_exit) + goto free_mem_map; + + called_exit = true; + goto get_map; + } /* Historic? */ boot_params->alt_mem_k = 32 * 1024; diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index cf1a471a18a2..10adb41f162e 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -459,7 +459,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp); + compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); if (ksig->ka.sa.sa_flags & SA_RESTORER) restorer = ksig->ka.sa.sa_restorer; diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h index 653668d140f9..4a8cb8d7cbd5 100644 --- a/arch/x86/include/asm/bootparam_utils.h +++ b/arch/x86/include/asm/bootparam_utils.h @@ -35,9 +35,9 @@ static void sanitize_boot_params(struct boot_params *boot_params) */ if (boot_params->sentinel) { /* fields in boot_params are left uninitialized, clear them */ - memset(&boot_params->olpc_ofw_header, 0, + memset(&boot_params->ext_ramdisk_image, 0, (char *)&boot_params->efi_info - - (char *)&boot_params->olpc_ofw_header); + (char *)&boot_params->ext_ramdisk_image); memset(&boot_params->kbd_status, 0, (char *)&boot_params->hdr - (char *)&boot_params->kbd_status); diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h index 46fc474fd819..f50de6951738 100644 --- a/arch/x86/include/asm/checksum_32.h +++ b/arch/x86/include/asm/checksum_32.h @@ -49,9 +49,15 @@ static inline __wsum csum_partial_copy_from_user(const void __user *src, int len, __wsum sum, int *err_ptr) { + __wsum ret; + might_sleep(); - return csum_partial_copy_generic((__force void *)src, dst, - len, sum, err_ptr, NULL); + stac(); + ret = csum_partial_copy_generic((__force void *)src, dst, + len, sum, err_ptr, NULL); + clac(); + + return ret; } /* @@ -176,10 +182,16 @@ static inline __wsum csum_and_copy_to_user(const void *src, int len, __wsum sum, int *err_ptr) { + __wsum ret; + might_sleep(); - if (access_ok(VERIFY_WRITE, dst, len)) - return csum_partial_copy_generic(src, (__force void *)dst, - len, sum, NULL, err_ptr); + if (access_ok(VERIFY_WRITE, dst, len)) { + stac(); + ret = csum_partial_copy_generic(src, (__force void *)dst, + len, sum, NULL, err_ptr); + clac(); + return ret; + } if (len) *err_ptr = -EFAULT; diff --git a/arch/x86/include/asm/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h index c09241659971..b4b38bacb404 100644 --- a/arch/x86/include/asm/dma-contiguous.h +++ b/arch/x86/include/asm/dma-contiguous.h @@ -4,7 +4,6 @@ #ifdef __KERNEL__ #include <linux/types.h> -#include <asm-generic/dma-contiguous.h> static inline void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { } diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3741c653767c..5137dca9e9d6 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -79,6 +79,13 @@ #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) +static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) +{ + /* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */ + return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - + (base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); +} + #define SELECTOR_TI_MASK (1 << 2) #define SELECTOR_RPL_MASK 0x03 @@ -96,10 +103,6 @@ #define ASYNC_PF_PER_VCPU 64 -struct kvm_vcpu; -struct kvm; -struct kvm_async_pf; - enum kvm_reg { VCPU_REGS_RAX = 0, VCPU_REGS_RCX = 1, @@ -631,8 +634,8 @@ struct msr_data { struct kvm_x86_ops { int (*cpu_has_kvm_support)(void); /* __init */ int (*disabled_by_bios)(void); /* __init */ - int (*hardware_enable)(void *dummy); - void (*hardware_disable)(void *dummy); + int (*hardware_enable)(void); + void (*hardware_disable)(void); void (*check_processor_compatibility)(void *rtn); int (*hardware_setup)(void); /* __init */ void (*hardware_unsetup)(void); /* __exit */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index fa5f71e021d5..e6833c655e59 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -32,11 +32,20 @@ #define MCI_STATUS_PCC (1ULL<<57) /* processor context corrupt */ #define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */ #define MCI_STATUS_AR (1ULL<<55) /* Action required */ -#define MCACOD 0xffff /* MCA Error Code */ + +/* + * Note that the full MCACOD field of IA32_MCi_STATUS MSR is + * bits 15:0. But bit 12 is the 'F' bit, defined for corrected + * errors to indicate that errors are being filtered by hardware. + * We should mask out bit 12 when looking for specific signatures + * of uncorrected errors - so the F bit is deliberately skipped + * in this #define. + */ +#define MCACOD 0xefff /* MCA Error Code */ /* Architecturally defined codes from SDM Vol. 3B Chapter 15 */ #define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */ -#define MCACOD_SCRUBMSK 0xfff0 +#define MCACOD_SCRUBMSK 0xeff0 /* Skip bit 12 ('F' bit) */ #define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */ #define MCACOD_DATA 0x0134 /* Data Load */ #define MCACOD_INSTR 0x0150 /* Instruction Fetch */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index cdbf36776106..be12c534fd59 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -45,22 +45,28 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, /* Re-load page tables */ load_cr3(next->pgd); - /* stop flush ipis for the previous mm */ + /* Stop flush ipis for the previous mm */ cpumask_clear_cpu(cpu, mm_cpumask(prev)); - /* - * load the LDT, if the LDT is different: - */ + /* Load the LDT, if the LDT is different: */ if (unlikely(prev->context.ldt != next->context.ldt)) load_LDT_nolock(&next->context); } #ifdef CONFIG_SMP - else { + else { this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next); - if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) { - /* We were in lazy tlb mode and leave_mm disabled + if (!cpumask_test_cpu(cpu, mm_cpumask(next))) { + /* + * On established mms, the mm_cpumask is only changed + * from irq context, from ptep_clear_flush() while in + * lazy tlb mode, and here. Irqs are blocked during + * schedule, protecting us from simultaneous changes. + */ + cpumask_set_cpu(cpu, mm_cpumask(next)); + /* + * We were in lazy tlb mode and leave_mm disabled * tlb flush IPI delivery. We must reload CR3 * to make sure to use no freed page tables. */ diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h index 7ea79c5fa1f2..492b29802f57 100644 --- a/arch/x86/include/asm/xor_avx.h +++ b/arch/x86/include/asm/xor_avx.h @@ -167,12 +167,12 @@ static struct xor_block_template xor_block_avx = { #define AVX_XOR_SPEED \ do { \ - if (cpu_has_avx) \ + if (cpu_has_avx && cpu_has_osxsave) \ xor_speed(&xor_block_avx); \ } while (0) #define AVX_SELECT(FASTEST) \ - (cpu_has_avx ? &xor_block_avx : FASTEST) + (cpu_has_avx && cpu_has_osxsave ? &xor_block_avx : FASTEST) #else diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 5d9a3033b3d7..d3a87780c70b 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -211,9 +211,9 @@ struct kvm_cpuid_entry2 { __u32 padding[3]; }; -#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1 -#define KVM_CPUID_FLAG_STATEFUL_FUNC 2 -#define KVM_CPUID_FLAG_STATE_READ_NEXT 4 +#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) +#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) +#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) /* for KVM_SET_CPUID2 */ struct kvm_cpuid2 { diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index b44577bc9744..ec94e11807dc 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -48,9 +48,20 @@ int acpi_suspend_lowlevel(void) #ifndef CONFIG_64BIT native_store_gdt((struct desc_ptr *)&header->pmode_gdt); + /* + * We have to check that we can write back the value, and not + * just read it. At least on 90 nm Pentium M (Family 6, Model + * 13), reading an invalid MSR is not guaranteed to trap, see + * Erratum X4 in "Intel Pentium M Processor on 90 nm Process + * with 2-MB L2 Cache and IntelĀ® Processor A100 and A110 on 90 + * nm process with 512-KB L2 Cache Specification Update". + */ if (!rdmsr_safe(MSR_EFER, &header->pmode_efer_low, - &header->pmode_efer_high)) + &header->pmode_efer_high) && + !wrmsr_safe(MSR_EFER, + header->pmode_efer_low, + header->pmode_efer_high)) header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_EFER); #endif /* !CONFIG_64BIT */ @@ -61,7 +72,10 @@ int acpi_suspend_lowlevel(void) } if (!rdmsr_safe(MSR_IA32_MISC_ENABLE, &header->pmode_misc_en_low, - &header->pmode_misc_en_high)) + &header->pmode_misc_en_high) && + !wrmsr_safe(MSR_IA32_MISC_ENABLE, + header->pmode_misc_en_low, + header->pmode_misc_en_high)) header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE); header->realmode_flags = acpi_realmode_flags; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 3048ded1b598..59554dca96ec 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -20,6 +20,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, {} }; @@ -27,6 +28,7 @@ EXPORT_SYMBOL(amd_nb_misc_ids); static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, {} }; @@ -81,13 +83,20 @@ int amd_cache_northbridges(void) next_northbridge(misc, amd_nb_misc_ids); node_to_amd_nb(i)->link = link = next_northbridge(link, amd_nb_link_ids); - } + } + /* GART present only on Fam15h upto model 0fh */ if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || - boot_cpu_data.x86 == 0x15) + (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) amd_northbridges.flags |= AMD_NB_GART; /* + * Check for L3 cache presence. + */ + if (!cpuid_edx(0x80000006)) + return 0; + + /* * Some CPU families support L3 Cache Index Disable. There are some * limitations because of E382 and E388 on family 0x10. */ diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index fa72a39e5d46..3982357de5b0 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -510,8 +510,9 @@ generic_get_free_region(unsigned long base, unsigned long size, int replace_reg) static void generic_get_mtrr(unsigned int reg, unsigned long *base, unsigned long *size, mtrr_type *type) { - unsigned int mask_lo, mask_hi, base_lo, base_hi; - unsigned int tmp, hi; + u32 mask_lo, mask_hi, base_lo, base_hi; + unsigned int hi; + u64 tmp, mask; /* * get_mtrr doesn't need to update mtrr_state, also it could be called @@ -532,18 +533,18 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, rdmsr(MTRRphysBase_MSR(reg), base_lo, base_hi); /* Work out the shifted address mask: */ - tmp = mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT; - mask_lo = size_or_mask | tmp; + tmp = (u64)mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT; + mask = size_or_mask | tmp; /* Expand tmp with high bits to all 1s: */ - hi = fls(tmp); + hi = fls64(tmp); if (hi > 0) { - tmp |= ~((1<<(hi - 1)) - 1); + tmp |= ~((1ULL<<(hi - 1)) - 1); - if (tmp != mask_lo) { + if (tmp != mask) { printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n"); add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); - mask_lo = tmp; + mask = tmp; } } @@ -551,8 +552,8 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, * This works correctly if size is a power of two, i.e. a * contiguous range: */ - *size = -mask_lo; - *base = base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT; + *size = -mask; + *base = (u64)base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT; *type = base_lo & 0xff; out_put_cpu: diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 726bf963c227..ca22b73aaa25 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -305,7 +305,8 @@ int mtrr_add_page(unsigned long base, unsigned long size, return -EINVAL; } - if (base & size_or_mask || size & size_or_mask) { + if ((base | (base + size - 1)) >> + (boot_cpu_data.x86_phys_bits - PAGE_SHIFT)) { pr_warning("mtrr: base or size exceeds the MTRR width\n"); return -EINVAL; } @@ -583,6 +584,7 @@ static struct syscore_ops mtrr_syscore_ops = { int __initdata changed_by_mtrr_cleanup; +#define SIZE_OR_MASK_BITS(n) (~((1ULL << ((n) - PAGE_SHIFT)) - 1)) /** * mtrr_bp_init - initialize mtrrs on the boot CPU * @@ -600,7 +602,7 @@ void __init mtrr_bp_init(void) if (cpu_has_mtrr) { mtrr_if = &generic_mtrr_ops; - size_or_mask = 0xff000000; /* 36 bits */ + size_or_mask = SIZE_OR_MASK_BITS(36); size_and_mask = 0x00f00000; phys_addr = 36; @@ -619,7 +621,7 @@ void __init mtrr_bp_init(void) boot_cpu_data.x86_mask == 0x4)) phys_addr = 36; - size_or_mask = ~((1ULL << (phys_addr - PAGE_SHIFT)) - 1); + size_or_mask = SIZE_OR_MASK_BITS(phys_addr); size_and_mask = ~size_or_mask & 0xfffff00000ULL; } else if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR && boot_cpu_data.x86 == 6) { @@ -627,7 +629,7 @@ void __init mtrr_bp_init(void) * VIA C* family have Intel style MTRRs, * but don't support PAE */ - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; phys_addr = 32; } @@ -637,21 +639,21 @@ void __init mtrr_bp_init(void) if (cpu_has_k6_mtrr) { /* Pre-Athlon (K6) AMD CPU MTRRs */ mtrr_if = mtrr_ops[X86_VENDOR_AMD]; - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; case X86_VENDOR_CENTAUR: if (cpu_has_centaur_mcr) { mtrr_if = mtrr_ops[X86_VENDOR_CENTAUR]; - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; case X86_VENDOR_CYRIX: if (cpu_has_cyrix_arr) { mtrr_if = mtrr_ops[X86_VENDOR_CYRIX]; - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 52441a2af538..8aac56bda7dc 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -314,8 +314,8 @@ static struct uncore_event_desc snbep_uncore_imc_events[] = { static struct uncore_event_desc snbep_uncore_qpi_events[] = { INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"), INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"), - INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x02,umask=0x08"), - INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x03,umask=0x04"), + INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"), + INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"), { /* end: all zeroes */ }, }; diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index b1581527a236..2fbad6b9f23c 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -52,8 +52,7 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) } #ifdef CONFIG_BLK_DEV_INITRD -void __init early_init_dt_setup_initrd_arch(unsigned long start, - unsigned long end) +void __init early_init_dt_setup_initrd_arch(u64 start, u64 end) { initrd_start = (unsigned long)__va(start); initrd_end = (unsigned long)__va(end); diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 94ab6b90dd3f..63bdb29b2549 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -196,15 +196,23 @@ static void __init ati_bugs_contd(int num, int slot, int func) static void __init intel_remapping_check(int num, int slot, int func) { u8 revision; + u16 device; + device = read_pci_config_16(num, slot, func, PCI_DEVICE_ID); revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID); /* - * Revision 0x13 of this chipset supports irq remapping - * but has an erratum that breaks its behavior, flag it as such + * Revision 13 of all triggering devices id in this quirk have + * a problem draining interrupts when irq remapping is enabled, + * and should be flagged as broken. Additionally revisions 0x12 + * and 0x22 of device id 0x3405 has this problem. */ if (revision == 0x13) set_irq_remapping_broken(); + else if ((device == 0x3405) && + ((revision == 0x12) || + (revision == 0x22))) + set_irq_remapping_broken(); } @@ -239,6 +247,8 @@ static struct chipset early_qrk[] __initdata = { PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd }, { PCI_VENDOR_ID_INTEL, 0x3403, PCI_CLASS_BRIDGE_HOST, PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check }, + { PCI_VENDOR_ID_INTEL, 0x3405, PCI_CLASS_BRIDGE_HOST, + PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check }, { PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST, PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check }, {} diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 321d65ebaffe..a8368608ab41 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -513,7 +513,7 @@ ENTRY(phys_base) #include "../../x86/xen/xen-head.S" .section .bss, "aw", @nobits - .align L1_CACHE_BYTES + .align PAGE_SIZE ENTRY(idt_table) .skip IDT_ENTRIES * 16 diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index cb339097b9ea..f7ea30dce238 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -116,7 +116,7 @@ static void __cpuinit mxcsr_feature_mask_init(void) if (cpu_has_fxsr) { memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct)); - asm volatile("fxsave %0" : : "m" (fx_scratch)); + asm volatile("fxsave %0" : "+m" (fx_scratch)); mask = fx_scratch.mxcsr_mask; if (mask == 0) mask = 0x0000ffbf; diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 76fa1e9a2b39..f7703401d6cb 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -36,7 +36,7 @@ void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); static const struct desc_ptr no_idt = {}; -static int reboot_mode; +static enum reboot_mode reboot_mode; enum reboot_type reboot_type = BOOT_ACPI; int reboot_force; @@ -88,11 +88,11 @@ static int __init reboot_setup(char *str) switch (*str) { case 'w': - reboot_mode = 0x1234; + reboot_mode = REBOOT_WARM; break; case 'c': - reboot_mode = 0; + reboot_mode = REBOOT_COLD; break; #ifdef CONFIG_SMP @@ -536,6 +536,7 @@ static void native_machine_emergency_restart(void) int i; int attempt = 0; int orig_reboot_type = reboot_type; + unsigned short mode; if (reboot_emergency) emergency_vmx_disable_all(); @@ -543,7 +544,8 @@ static void native_machine_emergency_restart(void) tboot_shutdown(TB_SHUTDOWN_REBOOT); /* Tell the BIOS if we want cold or warm reboot */ - *((unsigned short *)__va(0x472)) = reboot_mode; + mode = reboot_mode == REBOOT_WARM ? 0x1234 : 0; + *((unsigned short *)__va(0x472)) = mode; for (;;) { /* Could also try the reset bit in the Hammer NB */ @@ -585,7 +587,7 @@ static void native_machine_emergency_restart(void) case BOOT_EFI: if (efi_enabled(EFI_RUNTIME_SERVICES)) - efi.reset_system(reboot_mode ? + efi.reset_system(reboot_mode == REBOOT_WARM ? EFI_RESET_WARM : EFI_RESET_COLD, EFI_SUCCESS, 0, NULL); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 69562992e457..087ab2af381a 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -364,7 +364,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __save_altstack(&frame->uc.uc_stack, regs->sp); + save_altstack_ex(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. */ restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn); @@ -429,7 +429,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __save_altstack(&frame->uc.uc_stack, regs->sp); + save_altstack_ex(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. If provided, use a stub already in userspace. */ @@ -496,7 +496,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp); + compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); put_user_ex(0, &frame->uc.uc__pad0); if (ksig->ka.sa.sa_flags & SA_RESTORER) { diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index dbded5aedb81..30277e27431a 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -101,7 +101,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin, *begin = new_begin; } } else { - *begin = TASK_UNMAPPED_BASE; + *begin = current->mm->mmap_legacy_base; *end = TASK_SIZE; } } diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index a47a3e54b964..bdccfb62aa0d 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -27,6 +27,7 @@ config KVM select MMU_NOTIFIER select ANON_INODES select HAVE_KVM_IRQCHIP + select HAVE_KVM_IRQFD select HAVE_KVM_IRQ_ROUTING select HAVE_KVM_EVENTFD select KVM_APIC_ARCHITECTURE @@ -38,6 +39,7 @@ config KVM select PERF_EVENTS select HAVE_KVM_MSI select HAVE_KVM_CPU_RELAX_INTERCEPT + select KVM_VFIO ---help--- Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index d609e1d84048..25d22b2d6509 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -5,12 +5,13 @@ CFLAGS_x86.o := -I. CFLAGS_svm.o := -I. CFLAGS_vmx.o := -I. -kvm-y += $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ - coalesced_mmio.o irq_comm.o eventfd.o \ - irqchip.o) -kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(addprefix ../../../virt/kvm/, \ - assigned-dev.o iommu.o) -kvm-$(CONFIG_KVM_ASYNC_PF) += $(addprefix ../../../virt/kvm/, async_pf.o) +KVM := ../../../virt/kvm + +kvm-y += $(KVM)/kvm_main.o $(KVM)/ioapic.o \ + $(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o \ + $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o +kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(KVM)/assigned-dev.o $(KVM)/iommu.o +kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ i8254.o cpuid.o pmu.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index a20ecb5b6cbf..89d288237b9c 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -187,8 +187,14 @@ static bool supported_xcr0_bit(unsigned bit) #define F(x) bit(X86_FEATURE_##x) -static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index, int *nent, int maxnent) +static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, + u32 func, u32 index, int *nent, int maxnent) +{ + return 0; +} + +static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, + u32 index, int *nent, int maxnent) { int r; unsigned f_nx = is_efer_nx() ? F(NX) : 0; @@ -480,6 +486,15 @@ out: return r; } +static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func, + u32 idx, int *nent, int maxnent, unsigned int type) +{ + if (type == KVM_GET_EMULATED_CPUID) + return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent); + + return __do_cpuid_ent(entry, func, idx, nent, maxnent); +} + #undef F struct kvm_cpuid_param { @@ -494,8 +509,34 @@ static bool is_centaur_cpu(const struct kvm_cpuid_param *param) return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR; } -int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) +static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries, + __u32 num_entries, unsigned int ioctl_type) +{ + int i; + + if (ioctl_type != KVM_GET_EMULATED_CPUID) + return false; + + /* + * We want to make sure that ->padding is being passed clean from + * userspace in case we want to use it for something in the future. + * + * Sadly, this wasn't enforced for KVM_GET_SUPPORTED_CPUID and so we + * have to give ourselves satisfied only with the emulated side. /me + * sheds a tear. + */ + for (i = 0; i < num_entries; i++) { + if (entries[i].padding[0] || + entries[i].padding[1] || + entries[i].padding[2]) + return true; + } + return false; +} + +int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries, + unsigned int type) { struct kvm_cpuid_entry2 *cpuid_entries; int limit, nent = 0, r = -E2BIG, i; @@ -512,6 +553,10 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, goto out; if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) cpuid->nent = KVM_MAX_CPUID_ENTRIES; + + if (sanity_check_entries(entries, cpuid->nent, type)) + return -EINVAL; + r = -ENOMEM; cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent); if (!cpuid_entries) @@ -525,7 +570,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, continue; r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx, - &nent, cpuid->nent); + &nent, cpuid->nent, type); if (r) goto out_free; @@ -536,7 +581,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, limit = cpuid_entries[nent - 1].eax; for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func) r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx, - &nent, cpuid->nent); + &nent, cpuid->nent, type); if (r) goto out_free; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index b7fd07984888..f1e4895174b2 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -6,8 +6,9 @@ void kvm_update_cpuid(struct kvm_vcpu *vcpu); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, u32 function, u32 index); -int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries); +int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries, + unsigned int type); int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid *cpuid, struct kvm_cpuid_entry __user *entries); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 004cc87b781c..f47d2e11108e 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3232,7 +3232,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) arch.direct_map = vcpu->arch.mmu.direct_map; arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu); - return kvm_setup_async_pf(vcpu, gva, gfn, &arch); + return kvm_setup_async_pf(vcpu, gva, gfn_to_hva(vcpu->kvm, gfn), &arch); } static bool can_do_async_pf(struct kvm_vcpu *vcpu) @@ -4220,7 +4220,7 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) if (nr_to_scan == 0) goto out; - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { int idx; @@ -4256,7 +4256,7 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) break; } - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); out: return percpu_counter_read_positive(&kvm_total_used_mmu_pages); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index da20860b457a..e1af2394a23f 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -69,6 +69,7 @@ struct guest_walker { pt_element_t prefetch_ptes[PTE_PREFETCH_NUM]; gpa_t pte_gpa[PT_MAX_FULL_LEVELS]; pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS]; + bool pte_writable[PT_MAX_FULL_LEVELS]; unsigned pt_access; unsigned pte_access; gfn_t gfn; @@ -130,6 +131,22 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, if (pte == orig_pte) continue; + /* + * If the slot is read-only, simply do not process the accessed + * and dirty bits. This is the correct thing to do if the slot + * is ROM, and page tables in read-as-ROM/write-as-MMIO slots + * are only supported if the accessed and dirty bits are already + * set in the ROM (so that MMIO writes are never needed). + * + * Note that NPT does not allow this at all and faults, since + * it always wants nested page table entries for the guest + * page tables to be writable. And EPT works but will simply + * overwrite the read-only memory to set the accessed and dirty + * bits. + */ + if (unlikely(!walker->pte_writable[level - 1])) + continue; + ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte); if (ret) return ret; @@ -204,7 +221,8 @@ retry_walk: goto error; real_gfn = gpa_to_gfn(real_gfn); - host_addr = gfn_to_hva(vcpu->kvm, real_gfn); + host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn, + &walker->pte_writable[walker->level - 1]); if (unlikely(kvm_is_error_hva(host_addr))) goto error; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index a14a6eaf871d..934befea3e36 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -606,7 +606,7 @@ static int has_svm(void) return 1; } -static void svm_hardware_disable(void *garbage) +static void svm_hardware_disable(void) { /* Make sure we clean up behind us */ if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) @@ -617,7 +617,7 @@ static void svm_hardware_disable(void *garbage) amd_pmu_disable_virt(); } -static int svm_hardware_enable(void *garbage) +static int svm_hardware_enable(void) { struct svm_cpu_data *sd; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 260a91939555..af423252c265 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2566,7 +2566,7 @@ static void kvm_cpu_vmxon(u64 addr) : "memory", "cc"); } -static int hardware_enable(void *garbage) +static int hardware_enable(void) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); @@ -2630,7 +2630,7 @@ static void kvm_cpu_vmxoff(void) asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc"); } -static void hardware_disable(void *garbage) +static void hardware_disable(void) { if (vmm_exclusive) { vmclear_local_loaded_vmcss(); @@ -3399,15 +3399,22 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu, var->limit = vmx_read_guest_seg_limit(vmx, seg); var->selector = vmx_read_guest_seg_selector(vmx, seg); ar = vmx_read_guest_seg_ar(vmx, seg); + var->unusable = (ar >> 16) & 1; var->type = ar & 15; var->s = (ar >> 4) & 1; var->dpl = (ar >> 5) & 3; - var->present = (ar >> 7) & 1; + /* + * Some userspaces do not preserve unusable property. Since usable + * segment has to be present according to VMX spec we can use present + * property to amend userspace bug by making unusable segment always + * nonpresent. vmx_segment_access_rights() already marks nonpresent + * segment as unusable. + */ + var->present = !var->unusable; var->avl = (ar >> 12) & 1; var->l = (ar >> 13) & 1; var->db = (ar >> 14) & 1; var->g = (ar >> 15) & 1; - var->unusable = (ar >> 16) & 1; } static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e8ba99c34180..37d9503b81ea 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -239,7 +239,7 @@ void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) } EXPORT_SYMBOL_GPL(kvm_set_shared_msr); -static void drop_user_return_notifiers(void *ignore) +static void drop_user_return_notifiers(void) { unsigned int cpu = smp_processor_id(); struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); @@ -2500,7 +2500,7 @@ out: return r; } -int kvm_dev_ioctl_check_extension(long ext) +int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { int r; @@ -2510,6 +2510,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_MMU_SHADOW_CACHE_CONTROL: case KVM_CAP_SET_TSS_ADDR: case KVM_CAP_EXT_CPUID: + case KVM_CAP_EXT_EMUL_CPUID: case KVM_CAP_CLOCKSOURCE: case KVM_CAP_PIT: case KVM_CAP_NOP_IO_DELAY: @@ -2619,15 +2620,17 @@ long kvm_arch_dev_ioctl(struct file *filp, r = 0; break; } - case KVM_GET_SUPPORTED_CPUID: { + case KVM_GET_SUPPORTED_CPUID: + case KVM_GET_EMULATED_CPUID: { struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) goto out; - r = kvm_dev_ioctl_get_supported_cpuid(&cpuid, - cpuid_arg->entries); + + r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries, + ioctl); if (r) goto out; @@ -5104,7 +5107,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1); - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->cpu != freq->cpu) @@ -5114,7 +5117,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va send_ipi = 1; } } - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); if (freq->old < freq->new && send_ipi) { /* @@ -5261,12 +5264,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work) struct kvm_vcpu *vcpu; int i; - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_for_each_vcpu(i, vcpu, kvm) set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests); atomic_set(&kvm_guest_has_master_clock, 0); - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); } static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); @@ -5944,7 +5947,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) } if (need_resched()) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - kvm_resched(vcpu); + cond_resched(); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); } } @@ -6600,7 +6603,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector) kvm_rip_write(vcpu, 0); } -int kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; @@ -6611,7 +6614,7 @@ int kvm_arch_hardware_enable(void *garbage) bool stable, backwards_tsc = false; kvm_shared_msr_cpu_online(); - ret = kvm_x86_ops->hardware_enable(garbage); + ret = kvm_x86_ops->hardware_enable(); if (ret != 0) return ret; @@ -6691,10 +6694,10 @@ int kvm_arch_hardware_enable(void *garbage) return 0; } -void kvm_arch_hardware_disable(void *garbage) +void kvm_arch_hardware_disable(void) { - kvm_x86_ops->hardware_disable(garbage); - drop_user_return_notifiers(garbage); + kvm_x86_ops->hardware_disable(); + drop_user_return_notifiers(); } int kvm_arch_hardware_setup(void) @@ -6806,6 +6809,10 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) static_key_slow_dec(&kvm_no_apic_vcpu); } +void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) +{ +} + int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { if (type) @@ -6897,7 +6904,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kfree(rcu_dereference_check(kvm->arch.apic_map, 1)); } -void kvm_arch_free_memslot(struct kvm_memory_slot *free, +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { int i; @@ -6918,7 +6925,8 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free, } } -int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) { int i; @@ -6976,6 +6984,10 @@ out_free: return -ENOMEM; } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem, @@ -7114,7 +7126,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) int r; if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) || - is_error_page(work->page)) + work->wakeup_all) return; r = kvm_mmu_reload(vcpu); @@ -7224,7 +7236,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct x86_exception fault; trace_kvm_async_pf_ready(work->arch.token, work->gva); - if (is_error_page(work->page)) + if (work->wakeup_all) work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c index 25b7ae8d058a..7609e0e421ec 100644 --- a/arch/x86/lib/csum-wrappers_64.c +++ b/arch/x86/lib/csum-wrappers_64.c @@ -6,6 +6,7 @@ */ #include <asm/checksum.h> #include <linux/module.h> +#include <asm/smap.h> /** * csum_partial_copy_from_user - Copy and checksum from user space. @@ -52,8 +53,10 @@ csum_partial_copy_from_user(const void __user *src, void *dst, len -= 2; } } + stac(); isum = csum_partial_copy_generic((__force const void *)src, dst, len, isum, errp, NULL); + clac(); if (unlikely(*errp)) goto out_err; @@ -82,6 +85,8 @@ __wsum csum_partial_copy_to_user(const void *src, void __user *dst, int len, __wsum isum, int *errp) { + __wsum ret; + might_sleep(); if (unlikely(!access_ok(VERIFY_WRITE, dst, len))) { @@ -105,8 +110,11 @@ csum_partial_copy_to_user(const void *src, void __user *dst, } *errp = 0; - return csum_partial_copy_generic(src, (void __force *)dst, - len, isum, NULL, errp); + stac(); + ret = csum_partial_copy_generic(src, (void __force *)dst, + len, isum, NULL, errp); + clac(); + return ret; } EXPORT_SYMBOL(csum_partial_copy_to_user); diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index ae1aa71d0115..7e73e8c69096 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -16,169 +16,6 @@ #include <asm/tlbflush.h> #include <asm/pgalloc.h> -static unsigned long page_table_shareable(struct vm_area_struct *svma, - struct vm_area_struct *vma, - unsigned long addr, pgoff_t idx) -{ - unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) + - svma->vm_start; - 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) || - vm_flags != svm_flags || - sbase < svma->vm_start || svma->vm_end < s_end) - return 0; - - return saddr; -} - -static int vma_shareable(struct vm_area_struct *vma, unsigned long addr) -{ - unsigned long base = addr & PUD_MASK; - unsigned long end = base + PUD_SIZE; - - /* - * check on proper vm_flags and page table alignment - */ - if (vma->vm_flags & VM_MAYSHARE && - vma->vm_start <= base && end <= vma->vm_end) - return 1; - return 0; -} - -/* - * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() - * and returns the corresponding pte. While this is not necessary for the - * !shared pmd case because we can allocate the pmd later as well, it makes the - * code much cleaner. pmd allocation is essential for the shared case because - * pud has to be populated inside the same i_mmap_mutex section - otherwise - * racing tasks could either miss the sharing (see huge_pte_offset) or select a - * bad pmd for sharing. - */ -static pte_t * -huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) -{ - struct vm_area_struct *vma = find_vma(mm, addr); - struct address_space *mapping = vma->vm_file->f_mapping; - pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + - vma->vm_pgoff; - struct vm_area_struct *svma; - unsigned long saddr; - pte_t *spte = NULL; - pte_t *pte; - - if (!vma_shareable(vma, addr)) - return (pte_t *)pmd_alloc(mm, pud, addr); - - mutex_lock(&mapping->i_mmap_mutex); - vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { - if (svma == vma) - continue; - - saddr = page_table_shareable(svma, vma, addr, idx); - if (saddr) { - spte = huge_pte_offset(svma->vm_mm, saddr); - if (spte) { - get_page(virt_to_page(spte)); - break; - } - } - } - - if (!spte) - goto out; - - spin_lock(&mm->page_table_lock); - if (pud_none(*pud)) - pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); - else - put_page(virt_to_page(spte)); - spin_unlock(&mm->page_table_lock); -out: - pte = (pte_t *)pmd_alloc(mm, pud, addr); - mutex_unlock(&mapping->i_mmap_mutex); - return pte; -} - -/* - * unmap huge page backed by shared pte. - * - * Hugetlb pte page is ref counted at the time of mapping. If pte is shared - * indicated by page_count > 1, unmap is achieved by clearing pud and - * decrementing the ref count. If count == 1, the pte page is not shared. - * - * called with vma->vm_mm->page_table_lock held. - * - * returns: 1 successfully unmapped a shared pte page - * 0 the underlying pte page is not shared, or it is the last user - */ -int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) -{ - pgd_t *pgd = pgd_offset(mm, *addr); - pud_t *pud = pud_offset(pgd, *addr); - - BUG_ON(page_count(virt_to_page(ptep)) == 0); - if (page_count(virt_to_page(ptep)) == 1) - return 0; - - pud_clear(pud); - put_page(virt_to_page(ptep)); - *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; - return 1; -} - -pte_t *huge_pte_alloc(struct mm_struct *mm, - unsigned long addr, unsigned long sz) -{ - pgd_t *pgd; - pud_t *pud; - pte_t *pte = NULL; - - pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); - if (pud) { - if (sz == PUD_SIZE) { - pte = (pte_t *)pud; - } else { - BUG_ON(sz != PMD_SIZE); - if (pud_none(*pud)) - pte = huge_pmd_share(mm, addr, pud); - else - pte = (pte_t *)pmd_alloc(mm, pud, addr); - } - } - BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte)); - - return pte; -} - -pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd = NULL; - - pgd = pgd_offset(mm, addr); - if (pgd_present(*pgd)) { - pud = pud_offset(pgd, addr); - if (pud_present(*pud)) { - if (pud_large(*pud)) - return (pte_t *)pud; - pmd = pmd_offset(pud, addr); - } - } - return (pte_t *) pmd; -} - #if 0 /* This is just for testing */ struct page * follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) @@ -240,30 +77,6 @@ int pud_huge(pud_t pud) return !!(pud_val(pud) & _PAGE_PSE); } -struct page * -follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write) -{ - struct page *page; - - page = pte_page(*(pte_t *)pmd); - if (page) - page += ((address & ~PMD_MASK) >> PAGE_SHIFT); - return page; -} - -struct page * -follow_huge_pud(struct mm_struct *mm, unsigned long address, - pud_t *pud, int write) -{ - struct page *page; - - page = pte_page(*(pte_t *)pud); - if (page) - page += ((address & ~PUD_MASK) >> PAGE_SHIFT); - return page; -} - #endif /* x86_64 also uses this file */ diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 1f34e9219775..7a5bf1b76e2f 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -78,8 +78,8 @@ __ref void *alloc_low_pages(unsigned int num) return __va(pfn << PAGE_SHIFT); } -/* need 4 4k for initial PMD_SIZE, 4k for 0-ISA_END_ADDRESS */ -#define INIT_PGT_BUF_SIZE (5 * PAGE_SIZE) +/* need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS */ +#define INIT_PGT_BUF_SIZE (6 * PAGE_SIZE) RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE); void __init early_alloc_pgt_buf(void) { diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 845df6835f9f..5c1ae28825cd 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -112,12 +112,14 @@ static unsigned long mmap_legacy_base(void) */ void arch_pick_mmap_layout(struct mm_struct *mm) { + mm->mmap_legacy_base = mmap_legacy_base(); + mm->mmap_base = mmap_base(); + if (mmap_is_legacy()) { - mm->mmap_base = mmap_legacy_base(); + mm->mmap_base = mm->mmap_legacy_base; mm->get_unmapped_area = arch_get_unmapped_area; mm->unmap_area = arch_unmap_area; } else { - mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; mm->unmap_area = arch_unmap_area_topdown; } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 94eac5c85cdc..0a9fb7a0b452 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -313,6 +313,17 @@ static void xen_align_and_add_e820_region(u64 start, u64 size, int type) e820_add_region(start, end - start, type); } +void xen_ignore_unusable(struct e820entry *list, size_t map_size) +{ + struct e820entry *entry; + unsigned int i; + + for (i = 0, entry = list; i < map_size; i++, entry++) { + if (entry->type == E820_UNUSABLE) + entry->type = E820_RAM; + } +} + /** * machine_specific_memory_setup - Hook for machine specific memory setup. **/ @@ -353,6 +364,17 @@ char * __init xen_memory_setup(void) } BUG_ON(rc); + /* + * Xen won't allow a 1:1 mapping to be created to UNUSABLE + * regions, so if we're using the machine memory map leave the + * region as RAM as it is in the pseudo-physical map. + * + * UNUSABLE regions in domUs are not handled and will need + * a patch in the future. + */ + if (xen_initial_domain()) + xen_ignore_unusable(map, memmap.nr_entries); + /* Make sure the Xen-supplied memory map is well-ordered. */ sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index d99cae8147d1..a1e58e19d0cc 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -667,8 +667,15 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) static int __cpuinit xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle) { int rc; - rc = native_cpu_up(cpu, tidle); - WARN_ON (xen_smp_intr_init(cpu)); + /* + * xen_smp_intr_init() needs to run before native_cpu_up() + * so that IPI vectors are set up on the booting CPU before + * it is marked online in native_cpu_up(). + */ + rc = xen_smp_intr_init(cpu); + WARN_ON(rc); + if (!rc) + rc = native_cpu_up(cpu, tidle); return rc; } diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 3d88bfdf9e1c..13e8935e2eab 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -36,9 +36,8 @@ static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate); /* snapshots of runstate info */ static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot); -/* unused ns of stolen and blocked time */ +/* unused ns of stolen time */ static DEFINE_PER_CPU(u64, xen_residual_stolen); -static DEFINE_PER_CPU(u64, xen_residual_blocked); /* return an consistent snapshot of 64-bit time/counter value */ static u64 get64(const u64 *p) @@ -115,7 +114,7 @@ static void do_stolen_accounting(void) { struct vcpu_runstate_info state; struct vcpu_runstate_info *snap; - s64 blocked, runnable, offline, stolen; + s64 runnable, offline, stolen; cputime_t ticks; get_runstate_snapshot(&state); @@ -125,7 +124,6 @@ static void do_stolen_accounting(void) snap = &__get_cpu_var(xen_runstate_snapshot); /* work out how much time the VCPU has not been runn*ing* */ - blocked = state.time[RUNSTATE_blocked] - snap->time[RUNSTATE_blocked]; runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable]; offline = state.time[RUNSTATE_offline] - snap->time[RUNSTATE_offline]; @@ -141,17 +139,6 @@ static void do_stolen_accounting(void) ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen); __this_cpu_write(xen_residual_stolen, stolen); account_steal_ticks(ticks); - - /* Add the appropriate number of ticks of blocked time, - including any left-overs from last time. */ - blocked += __this_cpu_read(xen_residual_blocked); - - if (blocked < 0) - blocked = 0; - - ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked); - __this_cpu_write(xen_residual_blocked, blocked); - account_idle_ticks(ticks); } /* Get the TSC speed from Xen */ |