diff options
Diffstat (limited to 'arch/x86')
52 files changed, 525 insertions, 355 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7aef2d52daa0..96d058a87100 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1006,7 +1006,7 @@ config X86_THERMAL_VECTOR depends on X86_MCE_INTEL config X86_LEGACY_VM86 - bool "Legacy VM86 support (obsolete)" + bool "Legacy VM86 support" default n depends on X86_32 ---help--- @@ -1018,19 +1018,20 @@ config X86_LEGACY_VM86 available to accelerate real mode DOS programs. However, any recent version of DOSEMU, X, or vbetool should be fully functional even without kernel VM86 support, as they will all - fall back to (pretty well performing) software emulation. + fall back to software emulation. Nevertheless, if you are using + a 16-bit DOS program where 16-bit performance matters, vm86 + mode might be faster than emulation and you might want to + enable this option. - Anything that works on a 64-bit kernel is unlikely to need - this option, as 64-bit kernels don't, and can't, support V8086 - mode. This option is also unrelated to 16-bit protected mode - and is not needed to run most 16-bit programs under Wine. + Note that any app that works on a 64-bit kernel is unlikely to + need this option, as 64-bit kernels don't, and can't, support + V8086 mode. This option is also unrelated to 16-bit protected + mode and is not needed to run most 16-bit programs under Wine. - Enabling this option adds considerable attack surface to the - kernel and slows down system calls and exception handling. + Enabling this option increases the complexity of the kernel + and slows down exception handling a tiny bit. - Unless you use very old userspace or need the last drop of - performance in your real mode DOS games and can't use KVM, - say N here. + If unsure, say N here. config VM86 bool @@ -1307,6 +1308,7 @@ config HIGHMEM config X86_PAE bool "PAE (Physical Address Extension) Support" depends on X86_32 && !HIGHMEM4G + select SWIOTLB ---help--- PAE is required for NX support, and furthermore enables larger swapspace support for non-overcommit purposes. It diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index ee1b6d346b98..db51c1f27446 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -667,6 +667,7 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, bool conout_found = false; void *dummy = NULL; u32 h = handles[i]; + u32 current_fb_base; status = efi_call_early(handle_protocol, h, proto, (void **)&gop32); @@ -678,7 +679,7 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, if (status == EFI_SUCCESS) conout_found = true; - status = __gop_query32(gop32, &info, &size, &fb_base); + status = __gop_query32(gop32, &info, &size, ¤t_fb_base); if (status == EFI_SUCCESS && (!first_gop || conout_found)) { /* * Systems that use the UEFI Console Splitter may @@ -692,6 +693,7 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, pixel_format = info->pixel_format; pixel_info = info->pixel_information; pixels_per_scan_line = info->pixels_per_scan_line; + fb_base = current_fb_base; /* * Once we've found a GOP supporting ConOut, @@ -770,6 +772,7 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, bool conout_found = false; void *dummy = NULL; u64 h = handles[i]; + u32 current_fb_base; status = efi_call_early(handle_protocol, h, proto, (void **)&gop64); @@ -781,7 +784,7 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, if (status == EFI_SUCCESS) conout_found = true; - status = __gop_query64(gop64, &info, &size, &fb_base); + status = __gop_query64(gop64, &info, &size, ¤t_fb_base); if (status == EFI_SUCCESS && (!first_gop || conout_found)) { /* * Systems that use the UEFI Console Splitter may @@ -795,6 +798,7 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, pixel_format = info->pixel_format; pixel_info = info->pixel_information; pixels_per_scan_line = info->pixels_per_scan_line; + fb_base = current_fb_base; /* * Once we've found a GOP supporting ConOut, diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c index 80a0e4389c9a..bacaa13acac5 100644 --- a/arch/x86/crypto/camellia_aesni_avx_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx_glue.c @@ -554,6 +554,11 @@ static int __init camellia_aesni_init(void) { const char *feature_name; + if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) { + pr_info("AVX or AES-NI instructions are not detected.\n"); + return -ENODEV; + } + if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) { pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index d3033183ed70..055a01de7c8d 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1128,7 +1128,18 @@ END(error_exit) /* Runs on exception stack */ ENTRY(nmi) + /* + * Fix up the exception frame if we're on Xen. + * PARAVIRT_ADJUST_EXCEPTION_FRAME is guaranteed to push at most + * one value to the stack on native, so it may clobber the rdx + * scratch slot, but it won't clobber any of the important + * slots past it. + * + * Xen is a different story, because the Xen frame itself overlaps + * the "NMI executing" variable. + */ PARAVIRT_ADJUST_EXCEPTION_FRAME + /* * We allow breakpoints in NMIs. If a breakpoint occurs, then * the iretq it performs will take us out of NMI context. @@ -1179,9 +1190,12 @@ ENTRY(nmi) * we don't want to enable interrupts, because then we'll end * up in an awkward situation in which IRQs are on but NMIs * are off. + * + * We also must not push anything to the stack before switching + * stacks lest we corrupt the "NMI executing" variable. */ - SWAPGS + SWAPGS_UNSAFE_STACK cld movq %rsp, %rdx movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 477fc28050e4..9727b3b48bd1 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -193,7 +193,7 @@ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_HWP ( 7*32+ 10) /* "hwp" Intel HWP */ -#define X86_FEATURE_HWP_NOITFY ( 7*32+ 11) /* Intel HWP_NOTIFY */ +#define X86_FEATURE_HWP_NOTIFY ( 7*32+ 11) /* Intel HWP_NOTIFY */ #define X86_FEATURE_HWP_ACT_WINDOW ( 7*32+ 12) /* Intel HWP_ACT_WINDOW */ #define X86_FEATURE_HWP_EPP ( 7*32+13) /* Intel HWP_EPP */ #define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */ @@ -241,6 +241,7 @@ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ #define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ #define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ +#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */ /* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */ #define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 155162ea0e00..ae68be92f755 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -86,6 +86,18 @@ extern u64 asmlinkage efi_call(void *fp, ...); extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, u32 type, u64 attribute); +#ifdef CONFIG_KASAN +/* + * CONFIG_KASAN may redefine memset to __memset. __memset function is present + * only in kernel binary. Since the EFI stub linked into a separate binary it + * doesn't have __memset(). So we should use standard memset from + * arch/x86/boot/compressed/string.c. The same applies to memcpy and memmove. + */ +#undef memcpy +#undef memset +#undef memmove +#endif + #endif /* CONFIG_X86_32 */ extern struct efi_scratch efi_scratch; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c12e845f59e6..3a36ee704c30 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -40,6 +40,7 @@ #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 +#define KVM_HALT_POLL_NS_DEFAULT 500000 #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS @@ -711,6 +712,7 @@ struct kvm_vcpu_stat { u32 nmi_window_exits; u32 halt_exits; u32 halt_successful_poll; + u32 halt_attempted_poll; u32 halt_wakeup; u32 request_irq_exits; u32 irq_exits; @@ -1224,10 +1226,8 @@ void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); int kvm_is_in_guest(void); -int __x86_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem); -int x86_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem); +int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); +int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu); bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index c1c0a1c14344..b8c14bb7fc8f 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -141,6 +141,8 @@ #define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10) #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11) +#define MSR_PEBS_FRONTEND 0x000003f7 + #define MSR_IA32_POWER_CTL 0x000001fc #define MSR_IA32_MC0_CTL 0x00000400 @@ -331,6 +333,7 @@ /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 #define MSR_K8_TSEG_ADDR 0xc0010112 +#define MSR_K8_TSEG_MASK 0xc0010113 #define K8_MTRRFIXRANGE_DRAM_ENABLE 0x00040000 /* MtrrFixDramEn bit */ #define K8_MTRRFIXRANGE_DRAM_MODIFY 0x00080000 /* MtrrFixDramModEn bit */ #define K8_MTRR_RDMEM_WRMEM_MASK 0x18181818 /* Mask: RdMem|WrMem */ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index ce029e4fa7c6..31247b5bff7c 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -97,7 +97,6 @@ struct pv_lazy_ops { struct pv_time_ops { unsigned long long (*sched_clock)(void); unsigned long long (*steal_clock)(int cpu); - unsigned long (*get_tsc_khz)(void); }; struct pv_cpu_ops { diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h index 655e07a48f6c..67f08230103a 100644 --- a/arch/x86/include/asm/pvclock-abi.h +++ b/arch/x86/include/asm/pvclock-abi.h @@ -41,6 +41,7 @@ struct pvclock_wall_clock { #define PVCLOCK_TSC_STABLE_BIT (1 << 0) #define PVCLOCK_GUEST_STOPPED (1 << 1) +/* PVCLOCK_COUNTS_FROM_ZERO broke ABI and can't be used anymore. */ #define PVCLOCK_COUNTS_FROM_ZERO (1 << 2) #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PVCLOCK_ABI_H */ diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index 9d51fae1cba3..eaba08076030 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -39,18 +39,27 @@ static inline void queued_spin_unlock(struct qspinlock *lock) } #endif -#define virt_queued_spin_lock virt_queued_spin_lock - -static inline bool virt_queued_spin_lock(struct qspinlock *lock) +#ifdef CONFIG_PARAVIRT +#define virt_spin_lock virt_spin_lock +static inline bool virt_spin_lock(struct qspinlock *lock) { if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) return false; - while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0) - cpu_relax(); + /* + * On hypervisors without PARAVIRT_SPINLOCKS support we fall + * back to a Test-and-Set spinlock, because fair locks have + * horrible lock 'holder' preemption issues. + */ + + do { + while (atomic_read(&lock->val) != 0) + cpu_relax(); + } while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0); return true; } +#endif /* CONFIG_PARAVIRT */ #include <asm-generic/qspinlock.h> diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index e4661196994e..ff8b9a17dc4b 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -27,12 +27,11 @@ static __always_inline void *__inline_memcpy(void *to, const void *from, size_t function. */ #define __HAVE_ARCH_MEMCPY 1 +extern void *memcpy(void *to, const void *from, size_t len); extern void *__memcpy(void *to, const void *from, size_t len); #ifndef CONFIG_KMEMCHECK -#if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4 -extern void *memcpy(void *to, const void *from, size_t len); -#else +#if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4 #define memcpy(dst, src, len) \ ({ \ size_t __len = (len); \ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 83aea8055119..4c20dd333412 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -336,10 +336,10 @@ HYPERVISOR_update_descriptor(u64 ma, u64 desc) return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32); } -static inline int +static inline long HYPERVISOR_memory_op(unsigned int cmd, void *arg) { - return _hypercall2(int, memory_op, cmd, arg); + return _hypercall2(long, memory_op, cmd, arg); } static inline int diff --git a/arch/x86/include/uapi/asm/bitsperlong.h b/arch/x86/include/uapi/asm/bitsperlong.h index b0ae1c4dc791..217909b4d6f5 100644 --- a/arch/x86/include/uapi/asm/bitsperlong.h +++ b/arch/x86/include/uapi/asm/bitsperlong.h @@ -1,7 +1,7 @@ #ifndef __ASM_X86_BITSPERLONG_H #define __ASM_X86_BITSPERLONG_H -#ifdef __x86_64__ +#if defined(__x86_64__) && !defined(__ILP32__) # define __BITS_PER_LONG 64 #else # define __BITS_PER_LONG 32 diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index c42827eb86cf..25f909362b7a 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -338,10 +338,15 @@ done: static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr) { + unsigned long flags; + if (instr[0] != 0x90) return; + local_irq_save(flags); add_nops(instr + (a->instrlen - a->padlen), a->padlen); + sync_core(); + local_irq_restore(flags); DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ", instr, a->instrlen - a->padlen, a->padlen); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 3ca3e46aa405..24e94ce454e2 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -336,6 +336,13 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) apic_write(APIC_LVTT, lvtt_value); if (lvtt_value & APIC_LVT_TIMER_TSCDEADLINE) { + /* + * See Intel SDM: TSC-Deadline Mode chapter. In xAPIC mode, + * writing to the APIC LVTT and TSC_DEADLINE MSR isn't serialized. + * According to Intel, MFENCE can do the serialization here. + */ + asm volatile("mfence" : : : "memory"); + printk_once(KERN_DEBUG "TSC deadline timer enabled\n"); return; } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 38a76f826530..bb6bfc01cb82 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2522,6 +2522,7 @@ void __init setup_ioapic_dest(void) int pin, ioapic, irq, irq_entry; const struct cpumask *mask; struct irq_data *idata; + struct irq_chip *chip; if (skip_ioapic_setup == 1) return; @@ -2545,9 +2546,9 @@ void __init setup_ioapic_dest(void) else mask = apic->target_cpus(); - irq_set_affinity(irq, mask); + chip = irq_data_get_irq_chip(idata); + chip->irq_set_affinity(idata, mask, false); } - } #endif @@ -2906,6 +2907,7 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, struct irq_data *irq_data; struct mp_chip_data *data; struct irq_alloc_info *info = arg; + unsigned long flags; if (!info || nr_irqs > 1) return -EINVAL; @@ -2938,11 +2940,14 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, cfg = irqd_cfg(irq_data); add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin); + + local_irq_save(flags); if (info->ioapic_entry) mp_setup_entry(cfg, data, info->ioapic_entry); mp_register_handler(virq, data->trigger); if (virq < nr_legacy_irqs()) legacy_pic->mask(virq); + local_irq_restore(flags); apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i Dest:%d)\n", diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 1bbd0fe2c806..836d11b92811 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -489,10 +489,8 @@ static int apic_set_affinity(struct irq_data *irq_data, err = assign_irq_vector(irq, data, dest); if (err) { - struct irq_data *top = irq_get_irq_data(irq); - if (assign_irq_vector(irq, data, - irq_data_get_affinity_mask(top))) + irq_data_get_affinity_mask(irq_data))) pr_err("Failed to recover vector for irq %d\n", irq); return err; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 07ce52c22ec8..de22ea7ff82f 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1110,10 +1110,10 @@ void print_cpu_info(struct cpuinfo_x86 *c) else printk(KERN_CONT "%d86", c->x86); - printk(KERN_CONT " (fam: %02x, model: %02x", c->x86, c->x86_model); + printk(KERN_CONT " (family: 0x%x, model: 0x%x", c->x86, c->x86_model); if (c->x86_mask || c->cpuid_level >= 0) - printk(KERN_CONT ", stepping: %02x)\n", c->x86_mask); + printk(KERN_CONT ", stepping: 0x%x)\n", c->x86_mask); else printk(KERN_CONT ")\n"); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 381c8b9b3a33..20e242ea1bc4 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -34,11 +34,10 @@ struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); -static void (*hv_kexec_handler)(void); -static void (*hv_crash_handler)(struct pt_regs *regs); - #if IS_ENABLED(CONFIG_HYPERV) static void (*vmbus_handler)(void); +static void (*hv_kexec_handler)(void); +static void (*hv_crash_handler)(struct pt_regs *regs); void hyperv_vector_handler(struct pt_regs *regs) { @@ -96,8 +95,8 @@ void hv_remove_crash_handler(void) hv_crash_handler = NULL; } EXPORT_SYMBOL_GPL(hv_remove_crash_handler); -#endif +#ifdef CONFIG_KEXEC_CORE static void hv_machine_shutdown(void) { if (kexec_in_progress && hv_kexec_handler) @@ -111,7 +110,8 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs) hv_crash_handler(regs); native_machine_crash_shutdown(regs); } - +#endif /* CONFIG_KEXEC_CORE */ +#endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) { @@ -186,8 +186,10 @@ static void __init ms_hyperv_init_platform(void) no_timer_check = 1; #endif +#if IS_ENABLED(CONFIG_HYPERV) && defined(CONFIG_KEXEC_CORE) machine_ops.shutdown = hv_machine_shutdown; machine_ops.crash_shutdown = hv_machine_crash_shutdown; +#endif mark_tsc_unstable("running on Hyper-V"); } diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 5edf6d868fc1..165be83a7fa4 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -47,6 +47,7 @@ enum extra_reg_type { EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ EXTRA_REG_LBR = 2, /* lbr_select */ EXTRA_REG_LDLAT = 3, /* ld_lat_threshold */ + EXTRA_REG_FE = 4, /* fe_* */ EXTRA_REG_MAX /* number of entries needed */ }; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index cd9b6d0b10bf..f63360be2238 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -205,6 +205,11 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = { INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + /* + * Note the low 8 bits eventsel code is not a continuous field, containing + * some #GPing bits. These are masked out. + */ + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), EVENT_EXTRA_END }; @@ -250,7 +255,7 @@ struct event_constraint intel_bdw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ - INTEL_EVENT_CONSTRAINT(0xa3, 0x4), /* CYCLE_ACTIVITY.* */ + INTEL_UEVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ EVENT_CONSTRAINT_END }; @@ -2316,9 +2321,12 @@ static struct event_constraint * intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) { - struct event_constraint *c1 = cpuc->event_constraint[idx]; + struct event_constraint *c1 = NULL; struct event_constraint *c2; + if (idx >= 0) /* fake does < 0 */ + c1 = cpuc->event_constraint[idx]; + /* * first time only * - static constraint: no change across incremental scheduling calls @@ -2888,6 +2896,8 @@ PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); PMU_FORMAT_ATTR(ldlat, "config1:0-15"); +PMU_FORMAT_ATTR(frontend, "config1:0-23"); + static struct attribute *intel_arch3_formats_attr[] = { &format_attr_event.attr, &format_attr_umask.attr, @@ -2904,6 +2914,11 @@ static struct attribute *intel_arch3_formats_attr[] = { NULL, }; +static struct attribute *skl_format_attr[] = { + &format_attr_frontend.attr, + NULL, +}; + static __initconst const struct x86_pmu core_pmu = { .name = "core", .handle_irq = x86_pmu_handle_irq, @@ -3513,7 +3528,8 @@ __init int intel_pmu_init(void) x86_pmu.hw_config = hsw_hw_config; x86_pmu.get_event_constraints = hsw_get_event_constraints; - x86_pmu.cpu_events = hsw_events_attrs; + x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr, + skl_format_attr); WARN_ON(!x86_pmu.format_attrs); x86_pmu.cpu_events = hsw_events_attrs; pr_cont("Skylake events, "); diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c index 54690e885759..d1c0f254afbe 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_bts.c +++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c @@ -222,6 +222,7 @@ static void __bts_event_start(struct perf_event *event) if (!buf || bts_buffer_is_full(buf, bts)) return; + event->hw.itrace_started = 1; event->hw.state = 0; if (!buf->snapshot) diff --git a/arch/x86/kernel/cpu/perf_event_msr.c b/arch/x86/kernel/cpu/perf_event_msr.c index 086b12eae794..f32ac13934f2 100644 --- a/arch/x86/kernel/cpu/perf_event_msr.c +++ b/arch/x86/kernel/cpu/perf_event_msr.c @@ -10,12 +10,12 @@ enum perf_msr_id { PERF_MSR_EVENT_MAX, }; -bool test_aperfmperf(int idx) +static bool test_aperfmperf(int idx) { return boot_cpu_has(X86_FEATURE_APERFMPERF); } -bool test_intel(int idx) +static bool test_intel(int idx) { if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || boot_cpu_data.x86 != 6) diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 3d423a101fae..608fb26c7254 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -37,7 +37,7 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, { X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 }, { X86_FEATURE_HWP, CR_EAX, 7, 0x00000006, 0 }, - { X86_FEATURE_HWP_NOITFY, CR_EAX, 8, 0x00000006, 0 }, + { X86_FEATURE_HWP_NOTIFY, CR_EAX, 8, 0x00000006, 0 }, { X86_FEATURE_HWP_ACT_WINDOW, CR_EAX, 9, 0x00000006, 0 }, { X86_FEATURE_HWP_EPP, CR_EAX,10, 0x00000006, 0 }, { X86_FEATURE_HWP_PKG_REQ, CR_EAX,11, 0x00000006, 0 }, diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index e068d6683dba..74ca2fe7a0b3 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -185,10 +185,9 @@ void native_machine_crash_shutdown(struct pt_regs *regs) } #ifdef CONFIG_KEXEC_FILE -static int get_nr_ram_ranges_callback(unsigned long start_pfn, - unsigned long nr_pfn, void *arg) +static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg) { - int *nr_ranges = arg; + unsigned int *nr_ranges = arg; (*nr_ranges)++; return 0; @@ -214,7 +213,7 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced, ced->image = image; - walk_system_ram_range(0, -1, &nr_ranges, + walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); ced->max_nr_ranges = nr_ranges; diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index c80cf6699678..38da8f29a9c8 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -68,11 +68,10 @@ static inline void *current_stack(void) return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1)); } -static inline int -execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) +static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) { struct irq_stack *curstk, *irqstk; - u32 *isp, *prev_esp, arg1, arg2; + u32 *isp, *prev_esp, arg1; curstk = (struct irq_stack *) current_stack(); irqstk = __this_cpu_read(hardirq_stack); @@ -98,8 +97,8 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) asm volatile("xchgl %%ebx,%%esp \n" "call *%%edi \n" "movl %%ebx,%%esp \n" - : "=a" (arg1), "=d" (arg2), "=b" (isp) - : "0" (irq), "1" (desc), "2" (isp), + : "=a" (arg1), "=b" (isp) + : "0" (desc), "1" (isp), "D" (desc->handle_irq) : "memory", "cc", "ecx"); return 1; @@ -150,19 +149,15 @@ void do_softirq_own_stack(void) bool handle_irq(struct irq_desc *desc, struct pt_regs *regs) { - unsigned int irq; - int overflow; - - overflow = check_stack_overflow(); + int overflow = check_stack_overflow(); if (IS_ERR_OR_NULL(desc)) return false; - irq = irq_desc_get_irq(desc); - if (user_mode(regs) || !execute_on_irq_stack(overflow, desc, irq)) { + if (user_mode(regs) || !execute_on_irq_stack(overflow, desc)) { if (unlikely(overflow)) print_stack_overflow(); - generic_handle_irq_desc(irq, desc); + generic_handle_irq_desc(desc); } return true; diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index ff16ccb918f2..c767cf2bc80a 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -75,6 +75,6 @@ bool handle_irq(struct irq_desc *desc, struct pt_regs *regs) if (unlikely(IS_ERR_OR_NULL(desc))) return false; - generic_handle_irq_desc(irq_desc_get_irq(desc), desc); + generic_handle_irq_desc(desc); return true; } diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 2bcc0525f1c1..6acc9dd91f36 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -58,7 +58,7 @@ static struct ldt_struct *alloc_ldt_struct(int size) if (alloc_size > PAGE_SIZE) new_ldt->entries = vzalloc(alloc_size); else - new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL); + new_ldt->entries = (void *)get_zeroed_page(GFP_KERNEL); if (!new_ldt->entries) { kfree(new_ldt); @@ -95,7 +95,7 @@ static void free_ldt_struct(struct ldt_struct *ldt) if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) vfree(ldt->entries); else - kfree(ldt->entries); + free_page((unsigned long)ldt->entries); kfree(ldt); } diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index f68e48f5f6c2..c2130aef3f9d 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -41,10 +41,18 @@ #include <asm/timer.h> #include <asm/special_insns.h> -/* nop stub */ -void _paravirt_nop(void) -{ -} +/* + * nop stub, which must not clobber anything *including the stack* to + * avoid confusing the entry prologues. + */ +extern void _paravirt_nop(void); +asm (".pushsection .entry.text, \"ax\"\n" + ".global _paravirt_nop\n" + "_paravirt_nop:\n\t" + "ret\n\t" + ".size _paravirt_nop, . - _paravirt_nop\n\t" + ".type _paravirt_nop, @function\n\t" + ".popsection"); /* identity function, which can be inlined */ u32 _paravirt_ident_32(u32 x) diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 84b8ef82a159..1b55de1267cf 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -131,8 +131,8 @@ void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr, bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp) { - *gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp); *gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); + *gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp); if (!*dev) *dev = &x86_dma_fallback_dev; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 6d0e62ae8516..e28db181e4fc 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -506,3 +506,58 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) return randomize_range(mm->brk, range_end, 0) ? : mm->brk; } +/* + * Called from fs/proc with a reference on @p to find the function + * which called into schedule(). This needs to be done carefully + * because the task might wake up and we might look at a stack + * changing under us. + */ +unsigned long get_wchan(struct task_struct *p) +{ + unsigned long start, bottom, top, sp, fp, ip; + int count = 0; + + if (!p || p == current || p->state == TASK_RUNNING) + return 0; + + start = (unsigned long)task_stack_page(p); + if (!start) + return 0; + + /* + * Layout of the stack page: + * + * ----------- topmax = start + THREAD_SIZE - sizeof(unsigned long) + * PADDING + * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING + * stack + * ----------- bottom = start + sizeof(thread_info) + * thread_info + * ----------- start + * + * The tasks stack pointer points at the location where the + * framepointer is stored. The data on the stack is: + * ... IP FP ... IP FP + * + * We need to read FP and IP, so we need to adjust the upper + * bound by another unsigned long. + */ + top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; + top -= 2 * sizeof(unsigned long); + bottom = start + sizeof(struct thread_info); + + sp = READ_ONCE(p->thread.sp); + if (sp < bottom || sp > top) + return 0; + + fp = READ_ONCE_NOCHECK(*(unsigned long *)sp); + do { + if (fp < bottom || fp > top) + return 0; + ip = READ_ONCE_NOCHECK(*(unsigned long *)(fp + sizeof(unsigned long))); + if (!in_sched_functions(ip)) + return ip; + fp = READ_ONCE_NOCHECK(*(unsigned long *)fp); + } while (count++ < 16 && p->state != TASK_RUNNING); + return 0; +} diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index c13df2c735f8..737527b40e5b 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -324,31 +324,3 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } - -#define top_esp (THREAD_SIZE - sizeof(unsigned long)) -#define top_ebp (THREAD_SIZE - 2*sizeof(unsigned long)) - -unsigned long get_wchan(struct task_struct *p) -{ - unsigned long bp, sp, ip; - unsigned long stack_page; - int count = 0; - if (!p || p == current || p->state == TASK_RUNNING) - return 0; - stack_page = (unsigned long)task_stack_page(p); - sp = p->thread.sp; - if (!stack_page || sp < stack_page || sp > top_esp+stack_page) - return 0; - /* include/asm-i386/system.h:switch_to() pushes bp last. */ - bp = *(unsigned long *) sp; - do { - if (bp < stack_page || bp > top_ebp+stack_page) - return 0; - ip = *(unsigned long *) (bp+4); - if (!in_sched_functions(ip)) - return ip; - bp = *(unsigned long *) bp; - } while (count++ < 16); - return 0; -} - diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 3c1bbcf12924..b35921a670b2 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -499,30 +499,6 @@ void set_personality_ia32(bool x32) } EXPORT_SYMBOL_GPL(set_personality_ia32); -unsigned long get_wchan(struct task_struct *p) -{ - unsigned long stack; - u64 fp, ip; - int count = 0; - - if (!p || p == current || p->state == TASK_RUNNING) - return 0; - stack = (unsigned long)task_stack_page(p); - if (p->thread.sp < stack || p->thread.sp >= stack+THREAD_SIZE) - return 0; - fp = *(u64 *)(p->thread.sp); - do { - if (fp < (unsigned long)stack || - fp >= (unsigned long)stack+THREAD_SIZE) - return 0; - ip = *(u64 *)(fp+8); - if (!in_sched_functions(ip)) - return ip; - fp = *(u64 *)fp; - } while (count++ < 16); - return 0; -} - long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) { int ret = 0; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index fdb7f2a2d328..a3cccbfc5f77 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1173,6 +1173,14 @@ void __init setup_arch(char **cmdline_p) clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, swapper_pg_dir + KERNEL_PGD_BOUNDARY, KERNEL_PGD_PTRS); + + /* + * sync back low identity map too. It is used for example + * in the 32-bit EFI stub. + */ + clone_pgd_range(initial_page_table, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + KERNEL_PGD_PTRS); #endif tboot_probe(); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index e0c198e5f920..892ee2e5ecbc 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -509,7 +509,7 @@ void __inquire_remote_apic(int apicid) */ #define UDELAY_10MS_DEFAULT 10000 -static unsigned int init_udelay = UDELAY_10MS_DEFAULT; +static unsigned int init_udelay = INT_MAX; static int __init cpu_init_udelay(char *str) { @@ -522,13 +522,16 @@ early_param("cpu_init_udelay", cpu_init_udelay); static void __init smp_quirk_init_udelay(void) { /* if cmdline changed it from default, leave it alone */ - if (init_udelay != UDELAY_10MS_DEFAULT) + if (init_udelay != INT_MAX) return; /* if modern processor, use no delay */ if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) || ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) init_udelay = 0; + + /* else, use legacy delay */ + init_udelay = UDELAY_10MS_DEFAULT; } /* @@ -657,7 +660,9 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) /* * Give the other CPU some time to accept the IPI. */ - if (init_udelay) + if (init_udelay == 0) + udelay(10); + else udelay(300); pr_debug("Startup point 1\n"); @@ -668,7 +673,9 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) /* * Give the other CPU some time to accept the IPI. */ - if (init_udelay) + if (init_udelay == 0) + udelay(10); + else udelay(200); if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index c8d52cb4cb6e..c3f7602cd038 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -21,6 +21,7 @@ #include <asm/hypervisor.h> #include <asm/nmi.h> #include <asm/x86_init.h> +#include <asm/geode.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -1013,15 +1014,17 @@ EXPORT_SYMBOL_GPL(mark_tsc_unstable); static void __init check_system_tsc_reliable(void) { -#ifdef CONFIG_MGEODE_LX - /* RTSC counts during suspend */ +#if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC) + if (is_geode_lx()) { + /* RTSC counts during suspend */ #define RTSC_SUSP 0x100 - unsigned long res_low, res_high; + unsigned long res_low, res_high; - rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high); - /* Geode_LX - the OLPC CPU has a very reliable TSC */ - if (res_low & RTSC_SUSP) - tsc_clocksource_reliable = 1; + rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high); + /* Geode_LX - the OLPC CPU has a very reliable TSC */ + if (res_low & RTSC_SUSP) + tsc_clocksource_reliable = 1; + } #endif if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) tsc_clocksource_reliable = 1; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index abd8b856bd2b..524619351961 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -45,6 +45,7 @@ #include <linux/audit.h> #include <linux/stddef.h> #include <linux/slab.h> +#include <linux/security.h> #include <asm/uaccess.h> #include <asm/io.h> @@ -232,6 +233,32 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) struct pt_regs *regs = current_pt_regs(); unsigned long err = 0; + err = security_mmap_addr(0); + if (err) { + /* + * vm86 cannot virtualize the address space, so vm86 users + * need to manage the low 1MB themselves using mmap. Given + * that BIOS places important data in the first page, vm86 + * is essentially useless if mmap_min_addr != 0. DOSEMU, + * for example, won't even bother trying to use vm86 if it + * can't map a page at virtual address 0. + * + * To reduce the available kernel attack surface, simply + * disallow vm86(old) for users who cannot mmap at va 0. + * + * The implementation of security_mmap_addr will allow + * suitably privileged users to map va 0 even if + * vm.mmap_min_addr is set above 0, and we want this + * behavior for vm86 as well, as it ensures that legacy + * tools like vbetool will not fail just because of + * vm.mmap_min_addr. + */ + pr_info_once("Denied a call to vm86(old) from %s[%d] (uid: %d). Set the vm.mmap_min_addr sysctl to 0 and/or adjust LSM mmap_min_addr policy to enable vm86 if you are using a vm86-based DOS emulator.\n", + current->comm, task_pid_nr(current), + from_kuid_munged(&init_user_ns, current_uid())); + return -EPERM; + } + if (!vm86) { if (!(vm86 = kzalloc(sizeof(*vm86), GFP_KERNEL))) return -ENOMEM; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index b372a7557c16..9da95b9daf8d 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2418,7 +2418,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) u64 val, cr0, cr4; u32 base3; u16 selector; - int i; + int i, r; for (i = 0; i < 16; i++) *reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8); @@ -2460,13 +2460,17 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) dt.address = GET_SMSTATE(u64, smbase, 0x7e68); ctxt->ops->set_gdt(ctxt, &dt); + r = rsm_enter_protected_mode(ctxt, cr0, cr4); + if (r != X86EMUL_CONTINUE) + return r; + for (i = 0; i < 6; i++) { - int r = rsm_load_seg_64(ctxt, smbase, i); + r = rsm_load_seg_64(ctxt, smbase, i); if (r != X86EMUL_CONTINUE) return r; } - return rsm_enter_protected_mode(ctxt, cr0, cr4); + return X86EMUL_CONTINUE; } static int em_rsm(struct x86_emulate_ctxt *ctxt) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 69088a1ba509..ff606f507913 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3322,7 +3322,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) break; reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte, - leaf); + iterator.level); } walk_shadow_page_lockless_end(vcpu); @@ -3614,7 +3614,7 @@ static void __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, struct rsvd_bits_validate *rsvd_check, int maxphyaddr, int level, bool nx, bool gbpages, - bool pse) + bool pse, bool amd) { u64 exb_bit_rsvd = 0; u64 gbpages_bit_rsvd = 0; @@ -3631,7 +3631,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for * leaf entries) on AMD CPUs only. */ - if (guest_cpuid_is_amd(vcpu)) + if (amd) nonleaf_bit8_rsvd = rsvd_bits(8, 8); switch (level) { @@ -3699,7 +3699,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, __reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check, cpuid_maxphyaddr(vcpu), context->root_level, context->nx, guest_cpuid_has_gbpages(vcpu), - is_pse(vcpu)); + is_pse(vcpu), guest_cpuid_is_amd(vcpu)); } static void @@ -3749,13 +3749,24 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { + /* + * Passing "true" to the last argument is okay; it adds a check + * on bit 8 of the SPTEs which KVM doesn't use anyway. + */ __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, boot_cpu_data.x86_phys_bits, context->shadow_root_level, context->nx, - guest_cpuid_has_gbpages(vcpu), is_pse(vcpu)); + guest_cpuid_has_gbpages(vcpu), is_pse(vcpu), + true); } EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask); +static inline bool boot_cpu_is_amd(void) +{ + WARN_ON_ONCE(!tdp_enabled); + return shadow_x_mask == 0; +} + /* * the direct page table on host, use as much mmu features as * possible, however, kvm currently does not do execution-protection. @@ -3764,11 +3775,11 @@ static void reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { - if (guest_cpuid_is_amd(vcpu)) + if (boot_cpu_is_amd()) __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, boot_cpu_data.x86_phys_bits, context->shadow_root_level, false, - cpu_has_gbpages, true); + cpu_has_gbpages, true, true); else __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, boot_cpu_data.x86_phys_bits, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index fdb8cb63a6c0..2f9ed1ff0632 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -202,6 +202,7 @@ module_param(npt, int, S_IRUGO); static int nested = true; module_param(nested, int, S_IRUGO); +static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); static void svm_flush_tlb(struct kvm_vcpu *vcpu); static void svm_complete_interrupts(struct vcpu_svm *svm); @@ -513,7 +514,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); if (svm->vmcb->control.next_rip != 0) { - WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS)); + WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS)); svm->next_rip = svm->vmcb->control.next_rip; } @@ -865,64 +866,6 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0); } -#define MTRR_TYPE_UC_MINUS 7 -#define MTRR2PROTVAL_INVALID 0xff - -static u8 mtrr2protval[8]; - -static u8 fallback_mtrr_type(int mtrr) -{ - /* - * WT and WP aren't always available in the host PAT. Treat - * them as UC and UC- respectively. Everything else should be - * there. - */ - switch (mtrr) - { - case MTRR_TYPE_WRTHROUGH: - return MTRR_TYPE_UNCACHABLE; - case MTRR_TYPE_WRPROT: - return MTRR_TYPE_UC_MINUS; - default: - BUG(); - } -} - -static void build_mtrr2protval(void) -{ - int i; - u64 pat; - - for (i = 0; i < 8; i++) - mtrr2protval[i] = MTRR2PROTVAL_INVALID; - - /* Ignore the invalid MTRR types. */ - mtrr2protval[2] = 0; - mtrr2protval[3] = 0; - - /* - * Use host PAT value to figure out the mapping from guest MTRR - * values to nested page table PAT/PCD/PWT values. We do not - * want to change the host PAT value every time we enter the - * guest. - */ - rdmsrl(MSR_IA32_CR_PAT, pat); - for (i = 0; i < 8; i++) { - u8 mtrr = pat >> (8 * i); - - if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID) - mtrr2protval[mtrr] = __cm_idx2pte(i); - } - - for (i = 0; i < 8; i++) { - if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) { - u8 fallback = fallback_mtrr_type(i); - mtrr2protval[i] = mtrr2protval[fallback]; - BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID); - } - } -} - static __init int svm_hardware_setup(void) { int cpu; @@ -989,7 +932,6 @@ static __init int svm_hardware_setup(void) } else kvm_disable_tdp(); - build_mtrr2protval(); return 0; err: @@ -1144,43 +1086,6 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) return target_tsc - tsc; } -static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat) -{ - struct kvm_vcpu *vcpu = &svm->vcpu; - - /* Unlike Intel, AMD takes the guest's CR0.CD into account. - * - * AMD does not have IPAT. To emulate it for the case of guests - * with no assigned devices, just set everything to WB. If guests - * have assigned devices, however, we cannot force WB for RAM - * pages only, so use the guest PAT directly. - */ - if (!kvm_arch_has_assigned_device(vcpu->kvm)) - *g_pat = 0x0606060606060606; - else - *g_pat = vcpu->arch.pat; -} - -static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) -{ - u8 mtrr; - - /* - * 1. MMIO: trust guest MTRR, so same as item 3. - * 2. No passthrough: always map as WB, and force guest PAT to WB as well - * 3. Passthrough: can't guarantee the result, try to trust guest. - */ - if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm)) - return 0; - - if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED) && - kvm_read_cr0(vcpu) & X86_CR0_CD) - return _PAGE_NOCACHE; - - mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn); - return mtrr2protval[mtrr]; -} - static void init_vmcb(struct vcpu_svm *svm, bool init_event) { struct vmcb_control_area *control = &svm->vmcb->control; @@ -1263,7 +1168,8 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event) * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0. * It also updates the guest-visible cr0 value. */ - (void)kvm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET); + svm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET); + kvm_mmu_reset_context(&svm->vcpu); save->cr4 = X86_CR4_PAE; /* rdx = ?? */ @@ -1276,7 +1182,6 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event) clr_cr_intercept(svm, INTERCEPT_CR3_READ); clr_cr_intercept(svm, INTERCEPT_CR3_WRITE); save->g_pat = svm->vcpu.arch.pat; - svm_set_guest_pat(svm, &save->g_pat); save->cr3 = 0; save->cr4 = 0; } @@ -1671,10 +1576,13 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!vcpu->fpu_active) cr0 |= X86_CR0_TS; - - /* These are emulated via page tables. */ - cr0 &= ~(X86_CR0_CD | X86_CR0_NW); - + /* + * re-enable caching here because the QEMU bios + * does not do it - this results in some delay at + * reboot + */ + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) + cr0 &= ~(X86_CR0_CD | X86_CR0_NW); svm->vmcb->save.cr0 = cr0; mark_dirty(svm->vmcb, VMCB_CR); update_cr0_intercept(svm); @@ -3349,16 +3257,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_IGNNE: vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; - case MSR_IA32_CR_PAT: - if (npt_enabled) { - if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) - return 1; - vcpu->arch.pat = data; - svm_set_guest_pat(svm, &svm->vmcb->save.g_pat); - mark_dirty(svm->vmcb, VMCB_NPT); - break; - } - /* fall through */ default: return kvm_set_msr_common(vcpu, msr); } @@ -4193,6 +4091,11 @@ static bool svm_has_high_real_mode_segbase(void) return true; } +static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) +{ + return 0; +} + static void svm_cpuid_update(struct kvm_vcpu *vcpu) { } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index d01986832afc..6a8bc64566ab 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4105,17 +4105,13 @@ static void seg_setup(int seg) static int alloc_apic_access_page(struct kvm *kvm) { struct page *page; - struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; mutex_lock(&kvm->slots_lock); if (kvm->arch.apic_access_page_done) goto out; - kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; - kvm_userspace_mem.flags = 0; - kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE; - kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __x86_set_memory_region(kvm, &kvm_userspace_mem); + r = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); if (r) goto out; @@ -4140,17 +4136,12 @@ static int alloc_identity_pagetable(struct kvm *kvm) { /* Called with kvm->slots_lock held. */ - struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; BUG_ON(kvm->arch.ept_identity_pagetable_done); - kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; - kvm_userspace_mem.flags = 0; - kvm_userspace_mem.guest_phys_addr = - kvm->arch.ept_identity_map_addr; - kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __x86_set_memory_region(kvm, &kvm_userspace_mem); + r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, + kvm->arch.ept_identity_map_addr, PAGE_SIZE); return r; } @@ -4949,14 +4940,9 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) { int ret; - struct kvm_userspace_memory_region tss_mem = { - .slot = TSS_PRIVATE_MEMSLOT, - .guest_phys_addr = addr, - .memory_size = PAGE_SIZE * 3, - .flags = 0, - }; - ret = x86_set_memory_region(kvm, &tss_mem); + ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr, + PAGE_SIZE * 3); if (ret) return ret; kvm->arch.tss_addr = addr; @@ -6064,6 +6050,8 @@ static __init int hardware_setup(void) memcpy(vmx_msr_bitmap_longmode_x2apic, vmx_msr_bitmap_longmode, PAGE_SIZE); + set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ + if (enable_apicv) { for (msr = 0x800; msr <= 0x8ff; msr++) vmx_disable_intercept_msr_read_x2apic(msr); @@ -8615,17 +8603,22 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) u64 ipat = 0; /* For VT-d and EPT combination - * 1. MMIO: guest may want to apply WC, trust it. + * 1. MMIO: always map as UC * 2. EPT with VT-d: * a. VT-d without snooping control feature: can't guarantee the - * result, try to trust guest. So the same as item 1. + * result, try to trust guest. * b. VT-d with snooping control feature: snooping control feature of * VT-d engine can guarantee the cache correctness. Just set it * to WB to keep consistent with host. So the same as item 3. * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep * consistent with host MTRR */ - if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) { + if (is_mmio) { + cache = MTRR_TYPE_UNCACHABLE; + goto exit; + } + + if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) { ipat = VMX_EPT_IPAT_BIT; cache = MTRR_TYPE_WRBACK; goto exit; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a60bdbccff51..9a9a19830321 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -149,6 +149,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "nmi_window", VCPU_STAT(nmi_window_exits) }, { "halt_exits", VCPU_STAT(halt_exits) }, { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, + { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) }, { "halt_wakeup", VCPU_STAT(halt_wakeup) }, { "hypercalls", VCPU_STAT(hypercalls) }, { "request_irq", VCPU_STAT(request_irq_exits) }, @@ -1707,8 +1708,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->pvclock_set_guest_stopped_request = false; } - pvclock_flags |= PVCLOCK_COUNTS_FROM_ZERO; - /* If the host uses TSC clocksource, then it is stable */ if (use_master_clock) pvclock_flags |= PVCLOCK_TSC_STABLE_BIT; @@ -2006,8 +2005,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) &vcpu->requests); ka->boot_vcpu_runs_old_kvmclock = tmp; - - ka->kvmclock_offset = -get_kernel_ns(); } vcpu->arch.time = data; @@ -2189,6 +2186,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_LASTINTFROMIP: case MSR_IA32_LASTINTTOIP: case MSR_K8_SYSCFG: + case MSR_K8_TSEG_ADDR: + case MSR_K8_TSEG_MASK: case MSR_K7_HWCR: case MSR_VM_HSAVE_PA: case MSR_K8_INT_PENDING_MSG: @@ -6454,6 +6453,12 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) return 1; } +static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && + !vcpu->arch.apf.halted); +} + static int vcpu_run(struct kvm_vcpu *vcpu) { int r; @@ -6462,8 +6467,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); for (;;) { - if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && - !vcpu->arch.apf.halted) + if (kvm_vcpu_running(vcpu)) r = vcpu_enter_guest(vcpu); else r = vcpu_block(kvm, vcpu); @@ -7475,34 +7479,66 @@ void kvm_arch_sync_events(struct kvm *kvm) kvm_free_pit(kvm); } -int __x86_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem) +int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) { int i, r; + unsigned long hva; + struct kvm_memslots *slots = kvm_memslots(kvm); + struct kvm_memory_slot *slot, old; /* Called with kvm->slots_lock held. */ - BUG_ON(mem->slot >= KVM_MEM_SLOTS_NUM); + if (WARN_ON(id >= KVM_MEM_SLOTS_NUM)) + return -EINVAL; + slot = id_to_memslot(slots, id); + if (size) { + if (WARN_ON(slot->npages)) + return -EEXIST; + + /* + * MAP_SHARED to prevent internal slot pages from being moved + * by fork()/COW. + */ + hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, 0); + if (IS_ERR((void *)hva)) + return PTR_ERR((void *)hva); + } else { + if (!slot->npages) + return 0; + + hva = 0; + } + + old = *slot; for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - struct kvm_userspace_memory_region m = *mem; + struct kvm_userspace_memory_region m; - m.slot |= i << 16; + m.slot = id | (i << 16); + m.flags = 0; + m.guest_phys_addr = gpa; + m.userspace_addr = hva; + m.memory_size = size; r = __kvm_set_memory_region(kvm, &m); if (r < 0) return r; } + if (!size) { + r = vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); + WARN_ON(r < 0); + } + return 0; } EXPORT_SYMBOL_GPL(__x86_set_memory_region); -int x86_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem) +int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) { int r; mutex_lock(&kvm->slots_lock); - r = __x86_set_memory_region(kvm, mem); + r = __x86_set_memory_region(kvm, id, gpa, size); mutex_unlock(&kvm->slots_lock); return r; @@ -7517,16 +7553,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm) * unless the the memory map has changed due to process exit * or fd copying. */ - struct kvm_userspace_memory_region mem; - memset(&mem, 0, sizeof(mem)); - mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; - x86_set_memory_region(kvm, &mem); - - mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; - x86_set_memory_region(kvm, &mem); - - mem.slot = TSS_PRIVATE_MEMSLOT; - x86_set_memory_region(kvm, &mem); + x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0); + x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, 0, 0); + x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); } kvm_iommu_unmap_guest(kvm); kfree(kvm->arch.vpic); @@ -7629,27 +7658,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { - /* - * Only private memory slots need to be mapped here since - * KVM_SET_MEMORY_REGION ioctl is no longer supported. - */ - if ((memslot->id >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_CREATE)) { - unsigned long userspace_addr; - - /* - * MAP_SHARED to prevent internal slot pages from being moved - * by fork()/COW. - */ - userspace_addr = vm_mmap(NULL, 0, memslot->npages * PAGE_SIZE, - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_ANONYMOUS, 0); - - if (IS_ERR((void *)userspace_addr)) - return PTR_ERR((void *)userspace_addr); - - memslot->userspace_addr = userspace_addr; - } - return 0; } @@ -7711,17 +7719,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, { int nr_mmu_pages = 0; - if (change == KVM_MR_DELETE && old->id >= KVM_USER_MEM_SLOTS) { - int ret; - - ret = vm_munmap(old->userspace_addr, - old->npages * PAGE_SIZE); - if (ret < 0) - printk(KERN_WARNING - "kvm_vm_ioctl_set_memory_region: " - "failed to munmap memory\n"); - } - if (!kvm->arch.n_requested_mmu_pages) nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); @@ -7770,19 +7767,36 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, kvm_mmu_invalidate_zap_all_pages(kvm); } +static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) +{ + if (!list_empty_careful(&vcpu->async_pf.done)) + return true; + + if (kvm_apic_has_events(vcpu)) + return true; + + if (vcpu->arch.pv.pv_unhalted) + return true; + + if (atomic_read(&vcpu->arch.nmi_queued)) + return true; + + if (test_bit(KVM_REQ_SMI, &vcpu->requests)) + return true; + + if (kvm_arch_interrupt_allowed(vcpu) && + kvm_cpu_has_interrupt(vcpu)) + return true; + + return false; +} + int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) kvm_x86_ops->check_nested_events(vcpu, false); - return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && - !vcpu->arch.apf.halted) - || !list_empty_careful(&vcpu->async_pf.done) - || kvm_apic_has_events(vcpu) - || vcpu->arch.pv.pv_unhalted - || atomic_read(&vcpu->arch.nmi_queued) || - (kvm_arch_interrupt_allowed(vcpu) && - kvm_cpu_has_interrupt(vcpu)); + return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); } int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 161804de124a..a0d09f6c6533 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1015,7 +1015,7 @@ static struct clock_event_device lguest_clockevent = { * This is the Guest timer interrupt handler (hardware interrupt 0). We just * call the clockevent infrastructure and it does whatever needs doing. */ -static void lguest_time_irq(unsigned int irq, struct irq_desc *desc) +static void lguest_time_irq(struct irq_desc *desc) { unsigned long flags; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 30564e2752d3..df48430c279b 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1132,7 +1132,7 @@ void mark_rodata_ro(void) * has been zapped already via cleanup_highmem(). */ all_end = roundup((unsigned long)_brk_end, PMD_SIZE); - set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT); + set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT); rodata_test(); diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 66338a60aa6e..c2aea63bee20 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -192,10 +192,11 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) node_set(node, numa_nodes_parsed); - pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s\n", + pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s%s\n", node, pxm, (unsigned long long) start, (unsigned long long) end - 1, - hotpluggable ? " hotplug" : ""); + hotpluggable ? " hotplug" : "", + ma->flags & ACPI_SRAT_MEM_NON_VOLATILE ? " non-volatile" : ""); /* Mark hotplug range in memblock. */ if (hotpluggable && memblock_mark_hotplug(start, ma->length)) diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 09d3afc0a181..dc78a4a9a466 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -166,6 +166,7 @@ void pcibios_fixup_bus(struct pci_bus *b) { struct pci_dev *dev; + pci_read_bridge_bases(b); list_for_each_entry(dev, &b->devices, bus_list) pcibios_fixup_device_resources(dev); } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 1db84c0758b7..6a28ded74211 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -705,6 +705,70 @@ out: } /* + * Iterate the EFI memory map in reverse order because the regions + * will be mapped top-down. The end result is the same as if we had + * mapped things forward, but doesn't require us to change the + * existing implementation of efi_map_region(). + */ +static inline void *efi_map_next_entry_reverse(void *entry) +{ + /* Initial call */ + if (!entry) + return memmap.map_end - memmap.desc_size; + + entry -= memmap.desc_size; + if (entry < memmap.map) + return NULL; + + return entry; +} + +/* + * efi_map_next_entry - Return the next EFI memory map descriptor + * @entry: Previous EFI memory map descriptor + * + * This is a helper function to iterate over the EFI memory map, which + * we do in different orders depending on the current configuration. + * + * To begin traversing the memory map @entry must be %NULL. + * + * Returns %NULL when we reach the end of the memory map. + */ +static void *efi_map_next_entry(void *entry) +{ + if (!efi_enabled(EFI_OLD_MEMMAP) && efi_enabled(EFI_64BIT)) { + /* + * Starting in UEFI v2.5 the EFI_PROPERTIES_TABLE + * config table feature requires us to map all entries + * in the same order as they appear in the EFI memory + * map. That is to say, entry N must have a lower + * virtual address than entry N+1. This is because the + * firmware toolchain leaves relative references in + * the code/data sections, which are split and become + * separate EFI memory regions. Mapping things + * out-of-order leads to the firmware accessing + * unmapped addresses. + * + * Since we need to map things this way whether or not + * the kernel actually makes use of + * EFI_PROPERTIES_TABLE, let's just switch to this + * scheme by default for 64-bit. + */ + return efi_map_next_entry_reverse(entry); + } + + /* Initial call */ + if (!entry) + return memmap.map; + + entry += memmap.desc_size; + if (entry >= memmap.map_end) + return NULL; + + return entry; +} + +/* * Map the efi memory ranges of the runtime services and update new_mmap with * virtual addresses. */ @@ -714,7 +778,8 @@ static void * __init efi_map_regions(int *count, int *pg_shift) unsigned long left = 0; efi_memory_desc_t *md; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + p = NULL; + while ((p = efi_map_next_entry(p))) { md = p; if (!(md->attribute & EFI_MEMORY_RUNTIME)) { #ifdef CONFIG_X86_64 diff --git a/arch/x86/um/ldt.c b/arch/x86/um/ldt.c index 9701a4fd7bf2..836a1eb5df43 100644 --- a/arch/x86/um/ldt.c +++ b/arch/x86/um/ldt.c @@ -12,7 +12,10 @@ #include <skas.h> #include <sysdep/tls.h> -extern int modify_ldt(int func, void *ptr, unsigned long bytecount); +static inline int modify_ldt (int func, void *ptr, unsigned long bytecount) +{ + return syscall(__NR_modify_ldt, func, ptr, bytecount); +} static long write_ldt_entry(struct mm_id *mm_idp, int func, struct user_desc *desc, void **addr, int done) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 30d12afe52ed..993b7a71386d 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -33,6 +33,10 @@ #include <linux/memblock.h> #include <linux/edd.h> +#ifdef CONFIG_KEXEC_CORE +#include <linux/kexec.h> +#endif + #include <xen/xen.h> #include <xen/events.h> #include <xen/interface/xen.h> @@ -1077,6 +1081,7 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) /* Fast syscall setup is all done in hypercalls, so these are all ignored. Stub them out here to stop Xen console noise. */ + break; default: if (!pmu_msr_write(msr, low, high, &ret)) @@ -1807,6 +1812,21 @@ static struct notifier_block xen_hvm_cpu_notifier = { .notifier_call = xen_hvm_cpu_notify, }; +#ifdef CONFIG_KEXEC_CORE +static void xen_hvm_shutdown(void) +{ + native_machine_shutdown(); + if (kexec_in_progress) + xen_reboot(SHUTDOWN_soft_reset); +} + +static void xen_hvm_crash_shutdown(struct pt_regs *regs) +{ + native_machine_crash_shutdown(regs); + xen_reboot(SHUTDOWN_soft_reset); +} +#endif + static void __init xen_hvm_guest_init(void) { if (xen_pv_domain()) @@ -1826,6 +1846,10 @@ static void __init xen_hvm_guest_init(void) x86_init.irqs.intr_init = xen_init_IRQ; xen_hvm_init_time_ops(); xen_hvm_init_mmu_ops(); +#ifdef CONFIG_KEXEC_CORE + machine_ops.shutdown = xen_hvm_shutdown; + machine_ops.crash_shutdown = xen_hvm_crash_shutdown; +#endif } #endif diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index bfc08b13044b..660b3cfef234 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -112,6 +112,15 @@ static unsigned long *p2m_identity; static pte_t *p2m_missing_pte; static pte_t *p2m_identity_pte; +/* + * Hint at last populated PFN. + * + * Used to set HYPERVISOR_shared_info->arch.max_pfn so the toolstack + * can avoid scanning the whole P2M (which may be sized to account for + * hotplugged memory). + */ +static unsigned long xen_p2m_last_pfn; + static inline unsigned p2m_top_index(unsigned long pfn) { BUG_ON(pfn >= MAX_P2M_PFN); @@ -270,7 +279,7 @@ void xen_setup_mfn_list_list(void) else HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = virt_to_mfn(p2m_top_mfn); - HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn; + HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn; HYPERVISOR_shared_info->arch.p2m_generation = 0; HYPERVISOR_shared_info->arch.p2m_vaddr = (unsigned long)xen_p2m_addr; HYPERVISOR_shared_info->arch.p2m_cr3 = @@ -406,6 +415,8 @@ void __init xen_vmalloc_p2m_tree(void) static struct vm_struct vm; unsigned long p2m_limit; + xen_p2m_last_pfn = xen_max_p2m_pfn; + p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE; vm.flags = VM_ALLOC; vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit), @@ -608,6 +619,12 @@ static bool alloc_p2m(unsigned long pfn) free_p2m_page(p2m); } + /* Expanded the p2m? */ + if (pfn > xen_p2m_last_pfn) { + xen_p2m_last_pfn = pfn; + HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn; + } + return true; } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index f5ef6746d47a..1c30e4ab1022 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -548,7 +548,7 @@ static unsigned long __init xen_get_max_pages(void) { unsigned long max_pages, limit; domid_t domid = DOMID_SELF; - int ret; + long ret; limit = xen_get_pages_limit(); max_pages = limit; @@ -798,7 +798,7 @@ char * __init xen_memory_setup(void) xen_ignore_unusable(); /* Make sure the Xen-supplied memory map is well-ordered. */ - sanitize_e820_map(xen_e820_map, xen_e820_map_entries, + sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map), &xen_e820_map_entries); max_pages = xen_get_max_pages(); |