diff options
Diffstat (limited to 'arch/x86')
48 files changed, 657 insertions, 236 deletions
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index fcb7604172ce..cd20ca0b4043 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -348,6 +348,7 @@ config X86_DEBUG_FPU config PUNIT_ATOM_DEBUG tristate "ATOM Punit debug driver" + depends on PCI select DEBUG_FS select IOSF_MBI ---help--- diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 0d810fb15eac..d88a2fddba8c 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -73,12 +73,13 @@ UBSAN_SANITIZE := n $(obj)/bzImage: asflags-y := $(SVGA_MODE) quiet_cmd_image = BUILD $@ +silent_redirect_image = >/dev/null cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \ - $(obj)/zoffset.h $@ + $(obj)/zoffset.h $@ $($(quiet)redirect_image) $(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE $(call if_changed,image) - @echo 'Kernel: $@ is ready' ' (#'`cat .version`')' + @$(kecho) 'Kernel: $@ is ready' ' (#'`cat .version`')' OBJCOPYFLAGS_vmlinux.bin := -O binary -R .note -R .comment -S $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 2c860ad4fe06..8a958274b54c 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -34,6 +34,7 @@ KBUILD_CFLAGS += $(cflags-y) KBUILD_CFLAGS += -mno-mmx -mno-sse KBUILD_CFLAGS += $(call cc-option,-ffreestanding) KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector) +KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 630e3664906b..16f49123d747 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -16,6 +16,15 @@ #include "ctype.h" #include "string.h" +/* + * Undef these macros so that the functions that we provide + * here will have the correct names regardless of how string.h + * may have chosen to #define them. + */ +#undef memcpy +#undef memset +#undef memcmp + int memcmp(const void *s1, const void *s2, size_t len) { bool diff; diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 6cf79e1a6830..0eb9f92f3717 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -1,5 +1,4 @@ # CONFIG_64BIT is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -125,7 +124,6 @@ CONFIG_NF_CONNTRACK_IPV4=y CONFIG_IP_NF_IPTABLES=y CONFIG_IP_NF_FILTER=y CONFIG_IP_NF_TARGET_REJECT=y -CONFIG_IP_NF_TARGET_ULOG=y CONFIG_NF_NAT=y CONFIG_IP_NF_TARGET_MASQUERADE=y CONFIG_IP_NF_MANGLE=y @@ -255,7 +253,6 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_UHCI_HCD=y CONFIG_USB_PRINTER=y CONFIG_USB_STORAGE=y -CONFIG_USB_LIBUSUAL=y CONFIG_EDAC=y CONFIG_RTC_CLASS=y # CONFIG_RTC_HCTOSYS is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index de45f57b410d..4a4b16e56d35 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -1,4 +1,3 @@ -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -124,7 +123,6 @@ CONFIG_NF_CONNTRACK_IPV4=y CONFIG_IP_NF_IPTABLES=y CONFIG_IP_NF_FILTER=y CONFIG_IP_NF_TARGET_REJECT=y -CONFIG_IP_NF_TARGET_ULOG=y CONFIG_NF_NAT=y CONFIG_IP_NF_TARGET_MASQUERADE=y CONFIG_IP_NF_MANGLE=y @@ -251,7 +249,6 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_UHCI_HCD=y CONFIG_USB_PRINTER=y CONFIG_USB_STORAGE=y -CONFIG_USB_LIBUSUAL=y CONFIG_EDAC=y CONFIG_RTC_CLASS=y # CONFIG_RTC_HCTOSYS is not set diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index a9a8027a6c0e..d271fb79248f 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -705,6 +705,7 @@ apicinterrupt X86_PLATFORM_IPI_VECTOR x86_platform_ipi smp_x86_platform_ipi #ifdef CONFIG_HAVE_KVM apicinterrupt3 POSTED_INTR_VECTOR kvm_posted_intr_ipi smp_kvm_posted_intr_ipi apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR kvm_posted_intr_wakeup_ipi smp_kvm_posted_intr_wakeup_ipi +apicinterrupt3 POSTED_INTR_NESTED_VECTOR kvm_posted_intr_nested_ipi smp_kvm_posted_intr_nested_ipi #endif #ifdef CONFIG_X86_MCE_THRESHOLD diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index ff1ea2fb9705..8e3db8f642a7 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -191,8 +191,8 @@ static void release_pmc_hardware(void) {} static bool check_hw_exists(void) { - u64 val, val_fail, val_new= ~0; - int i, reg, reg_fail, ret = 0; + u64 val, val_fail = -1, val_new= ~0; + int i, reg, reg_fail = -1, ret = 0; int bios_fail = 0; int reg_safe = -1; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index aa62437d1aa1..98b0f0729527 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -1708,6 +1708,120 @@ static __initconst const u64 glm_hw_cache_extra_regs }, }; +static __initconst const u64 glp_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(L1D)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */ + [C(RESULT_MISS)] = 0x0, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */ + [C(RESULT_MISS)] = 0x0, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, + [C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x0380, /* ICACHE.ACCESSES */ + [C(RESULT_MISS)] = 0x0280, /* ICACHE.MISSES */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */ + [C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */ + [C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, + [C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */ + [C(RESULT_MISS)] = 0xe08, /* DTLB_LOAD_MISSES.WALK_COMPLETED */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */ + [C(RESULT_MISS)] = 0xe49, /* DTLB_STORE_MISSES.WALK_COMPLETED */ + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x00c0, /* INST_RETIRED.ANY_P */ + [C(RESULT_MISS)] = 0x0481, /* ITLB.MISS */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */ + [C(RESULT_MISS)] = 0x00c5, /* BR_MISP_RETIRED.ALL_BRANCHES */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + }, +}; + +static __initconst const u64 glp_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = GLM_DEMAND_READ| + GLM_LLC_ACCESS, + [C(RESULT_MISS)] = GLM_DEMAND_READ| + GLM_LLC_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = GLM_DEMAND_WRITE| + GLM_LLC_ACCESS, + [C(RESULT_MISS)] = GLM_DEMAND_WRITE| + GLM_LLC_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x0, + [C(RESULT_MISS)] = 0x0, + }, + }, +}; + #define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */ #define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */ #define KNL_MCDRAM_LOCAL BIT_ULL(21) @@ -3016,6 +3130,9 @@ static int hsw_hw_config(struct perf_event *event) return 0; } +static struct event_constraint counter0_constraint = + INTEL_ALL_EVENT_CONSTRAINT(0, 0x1); + static struct event_constraint counter2_constraint = EVENT_CONSTRAINT(0, 0x4, 0); @@ -3037,6 +3154,21 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx, return c; } +static struct event_constraint * +glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct event_constraint *c; + + /* :ppp means to do reduced skid PEBS which is PMC0 only. */ + if (event->attr.precise_ip == 3) + return &counter0_constraint; + + c = intel_get_event_constraints(cpuc, idx, event); + + return c; +} + /* * Broadwell: * @@ -3265,10 +3397,8 @@ static void intel_pmu_cpu_dying(int cpu) static void intel_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) { - if (x86_pmu.pebs_active) - intel_pmu_pebs_sched_task(ctx, sched_in); - if (x86_pmu.lbr_nr) - intel_pmu_lbr_sched_task(ctx, sched_in); + intel_pmu_pebs_sched_task(ctx, sched_in); + intel_pmu_lbr_sched_task(ctx, sched_in); } PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); @@ -3838,6 +3968,32 @@ __init int intel_pmu_init(void) pr_cont("Goldmont events, "); break; + case INTEL_FAM6_ATOM_GEMINI_LAKE: + memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + + intel_pmu_lbr_init_skl(); + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_glp_pebs_event_constraints; + x86_pmu.extra_regs = intel_glm_extra_regs; + /* + * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS + * for precise cycles. + */ + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.lbr_pt_coexist = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.get_event_constraints = glp_get_event_constraints; + x86_pmu.cpu_events = glm_events_attrs; + /* Goldmont Plus has 4-wide pipeline */ + event_attr_td_total_slots_scale_glm.event_str = "4"; + pr_cont("Goldmont plus events, "); + break; + case INTEL_FAM6_WESTMERE: case INTEL_FAM6_WESTMERE_EP: case INTEL_FAM6_WESTMERE_EX: diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 238ae3248ba5..4cf100ff2a37 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -40,16 +40,16 @@ * Model specific counters: * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 - * Available model: SLM,AMT + * Available model: SLM,AMT,GLM * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 - * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM * Scope: Core * MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW - * SKL,KNL + * SKL,KNL,GLM * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 @@ -57,16 +57,17 @@ * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 - * Available model: SNB,IVB,HSW,BDW,SKL,KNL + * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL + * GLM * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW - * SKL,KNL + * SKL,KNL,GLM * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 @@ -82,7 +83,7 @@ * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 - * Available model: HSW ULT only + * Available model: HSW ULT, GLM * Scope: Package (physical package) * */ @@ -504,6 +505,17 @@ static const struct cstate_model knl_cstates __initconst = { }; +static const struct cstate_model glm_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C1_RES) | + BIT(PERF_CSTATE_CORE_C3_RES) | + BIT(PERF_CSTATE_CORE_C6_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | + BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES) | + BIT(PERF_CSTATE_PKG_C10_RES), +}; + #define X86_CSTATES_MODEL(model, states) \ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) } @@ -546,6 +558,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates), X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates), + + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index c6d23ffe422d..a322fed5f8ed 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -606,12 +606,6 @@ static inline void intel_pmu_drain_pebs_buffer(void) x86_pmu.drain_pebs(®s); } -void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in) -{ - if (!sched_in) - intel_pmu_drain_pebs_buffer(); -} - /* * PEBS */ @@ -651,6 +645,12 @@ struct event_constraint intel_glm_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_glp_pebs_event_constraints[] = { + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), + EVENT_CONSTRAINT_END +}; + struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ @@ -816,6 +816,14 @@ static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc) return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs); } +void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + if (!sched_in && pebs_needs_sched_cb(cpuc)) + intel_pmu_drain_pebs_buffer(); +} + static inline void pebs_update_threshold(struct cpu_hw_events *cpuc) { struct debug_store *ds = cpuc->ds; @@ -889,6 +897,8 @@ void intel_pmu_pebs_enable(struct perf_event *event) if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { ds->pebs_event_reset[hwc->idx] = (u64)(-hwc->sample_period) & x86_pmu.cntval_mask; + } else { + ds->pebs_event_reset[hwc->idx] = 0; } } diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index eb261656a320..955457a30197 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -380,8 +380,12 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx; + if (!cpuc->lbr_users) + return; + /* * If LBR callstack feature is enabled and the stack was saved when * the task was scheduled out, restore the stack. Otherwise flush diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index dae2fedc1601..4f9127644b80 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -316,7 +316,7 @@ #define SKX_UPI_PCI_PMON_CTL0 0x350 #define SKX_UPI_PCI_PMON_CTR0 0x318 #define SKX_UPI_PCI_PMON_BOX_CTL 0x378 -#define SKX_PMON_CTL_UMASK_EXT 0xff +#define SKX_UPI_CTL_UMASK_EXT 0xffefff /* SKX M2M */ #define SKX_M2M_PCI_PMON_CTL0 0x228 @@ -328,7 +328,7 @@ DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6"); DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); -DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-39"); +DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55"); DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); @@ -351,7 +351,6 @@ DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5"); DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_link3, filter_link, "config1:12"); -DEFINE_UNCORE_FORMAT_ATTR(filter_link4, filter_link, "config1:9-12"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); @@ -3302,7 +3301,6 @@ static struct attribute *skx_uncore_cha_formats_attr[] = { &format_attr_inv.attr, &format_attr_thresh8.attr, &format_attr_filter_tid4.attr, - &format_attr_filter_link4.attr, &format_attr_filter_state5.attr, &format_attr_filter_rem.attr, &format_attr_filter_loc.attr, @@ -3312,7 +3310,6 @@ static struct attribute *skx_uncore_cha_formats_attr[] = { &format_attr_filter_opc_0.attr, &format_attr_filter_opc_1.attr, &format_attr_filter_nc.attr, - &format_attr_filter_c6.attr, &format_attr_filter_isoc.attr, NULL, }; @@ -3333,8 +3330,11 @@ static struct extra_reg skx_uncore_cha_extra_regs[] = { SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x2134, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x8134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x3134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x9134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x8), + EVENT_EXTRA_END }; static u64 skx_cha_filter_mask(int fields) @@ -3347,6 +3347,17 @@ static u64 skx_cha_filter_mask(int fields) mask |= SKX_CHA_MSR_PMON_BOX_FILTER_LINK; if (fields & 0x4) mask |= SKX_CHA_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x8) { + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_REM; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_LOC; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_ALL_OPC; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_NM; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_NOT_NM; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_OPC0; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_OPC1; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_NC; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_ISOC; + } return mask; } @@ -3492,6 +3503,26 @@ static struct intel_uncore_type skx_uncore_irp = { .format_group = &skx_uncore_format_group, }; +static struct attribute *skx_uncore_pcu_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge_det.attr, + &format_attr_filter_band0.attr, + &format_attr_filter_band1.attr, + &format_attr_filter_band2.attr, + &format_attr_filter_band3.attr, + NULL, +}; + +static struct attribute_group skx_uncore_pcu_format_group = { + .name = "format", + .attrs = skx_uncore_pcu_formats_attr, +}; + static struct intel_uncore_ops skx_uncore_pcu_ops = { IVBEP_UNCORE_MSR_OPS_COMMON_INIT(), .hw_config = hswep_pcu_hw_config, @@ -3510,7 +3541,7 @@ static struct intel_uncore_type skx_uncore_pcu = { .box_ctl = HSWEP_PCU_MSR_PMON_BOX_CTL, .num_shared_regs = 1, .ops = &skx_uncore_pcu_ops, - .format_group = &snbep_uncore_pcu_format_group, + .format_group = &skx_uncore_pcu_format_group, }; static struct intel_uncore_type *skx_msr_uncores[] = { @@ -3603,8 +3634,8 @@ static struct intel_uncore_type skx_uncore_upi = { .perf_ctr_bits = 48, .perf_ctr = SKX_UPI_PCI_PMON_CTR0, .event_ctl = SKX_UPI_PCI_PMON_CTL0, - .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, - .event_mask_ext = SKX_PMON_CTL_UMASK_EXT, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .event_mask_ext = SKX_UPI_CTL_UMASK_EXT, .box_ctl = SKX_UPI_PCI_PMON_BOX_CTL, .ops = &skx_upi_uncore_pci_ops, .format_group = &skx_upi_uncore_format_group, diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 53728eea1bed..476aec3a4cab 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -879,6 +879,8 @@ extern struct event_constraint intel_slm_pebs_event_constraints[]; extern struct event_constraint intel_glm_pebs_event_constraints[]; +extern struct event_constraint intel_glp_pebs_event_constraints[]; + extern struct event_constraint intel_nehalem_pebs_event_constraints[]; extern struct event_constraint intel_westmere_pebs_event_constraints[]; diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 39e702d90cdb..aa6b2023d8f8 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -35,7 +35,7 @@ #define _BUG_FLAGS(ins, flags) \ do { \ asm volatile("1:\t" ins "\n" \ - ".pushsection __bug_table,\"a\"\n" \ + ".pushsection __bug_table,\"aw\"\n" \ "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \ "\t" __BUG_REL(%c0) "\t# bug_entry::file\n" \ "\t.word %c1" "\t# bug_entry::line\n" \ @@ -52,7 +52,7 @@ do { \ #define _BUG_FLAGS(ins, flags) \ do { \ asm volatile("1:\t" ins "\n" \ - ".pushsection __bug_table,\"a\"\n" \ + ".pushsection __bug_table,\"aw\"\n" \ "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \ "\t.word %c0" "\t# bug_entry::flags\n" \ "\t.org 2b+%c1\n" \ diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h index df002992d8fd..07b06955a05d 100644 --- a/arch/x86/include/asm/entry_arch.h +++ b/arch/x86/include/asm/entry_arch.h @@ -25,6 +25,8 @@ BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR, smp_kvm_posted_intr_ipi) BUILD_INTERRUPT3(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR, smp_kvm_posted_intr_wakeup_ipi) +BUILD_INTERRUPT3(kvm_posted_intr_nested_ipi, POSTED_INTR_NESTED_VECTOR, + smp_kvm_posted_intr_nested_ipi) #endif /* diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 9b76cd331990..ad1ed531febc 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -15,6 +15,7 @@ typedef struct { #ifdef CONFIG_HAVE_KVM unsigned int kvm_posted_intr_ipis; unsigned int kvm_posted_intr_wakeup_ipis; + unsigned int kvm_posted_intr_nested_ipis; #endif unsigned int x86_platform_ipis; /* arch dependent */ unsigned int apic_perf_irqs; diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index b90e1053049b..d6dbafbd4207 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -30,6 +30,7 @@ extern asmlinkage void apic_timer_interrupt(void); extern asmlinkage void x86_platform_ipi(void); extern asmlinkage void kvm_posted_intr_ipi(void); extern asmlinkage void kvm_posted_intr_wakeup_ipi(void); +extern asmlinkage void kvm_posted_intr_nested_ipi(void); extern asmlinkage void error_interrupt(void); extern asmlinkage void irq_work_interrupt(void); @@ -62,6 +63,7 @@ extern void trace_call_function_single_interrupt(void); #define trace_reboot_interrupt reboot_interrupt #define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi #define trace_kvm_posted_intr_wakeup_ipi kvm_posted_intr_wakeup_ipi +#define trace_kvm_posted_intr_nested_ipi kvm_posted_intr_nested_ipi #endif /* CONFIG_TRACING */ #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 7afb0e2f07f4..48febf07e828 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -328,13 +328,13 @@ static inline unsigned type in##bwl##_p(int port) \ static inline void outs##bwl(int port, const void *addr, unsigned long count) \ { \ asm volatile("rep; outs" #bwl \ - : "+S"(addr), "+c"(count) : "d"(port)); \ + : "+S"(addr), "+c"(count) : "d"(port) : "memory"); \ } \ \ static inline void ins##bwl(int port, void *addr, unsigned long count) \ { \ asm volatile("rep; ins" #bwl \ - : "+D"(addr), "+c"(count) : "d"(port)); \ + : "+D"(addr), "+c"(count) : "d"(port) : "memory"); \ } BUILDIO(b, b, char) diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 6ca9fd6234e1..aaf8d28b5d00 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -83,7 +83,6 @@ */ #define X86_PLATFORM_IPI_VECTOR 0xf7 -#define POSTED_INTR_WAKEUP_VECTOR 0xf1 /* * IRQ work vector: */ @@ -98,6 +97,8 @@ /* Vector for KVM to deliver posted interrupt IPI */ #ifdef CONFIG_HAVE_KVM #define POSTED_INTR_VECTOR 0xf2 +#define POSTED_INTR_WAKEUP_VECTOR 0xf1 +#define POSTED_INTR_NESTED_VECTOR 0xf0 #endif /* diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 34b984c60790..6cf65437b5e5 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -52,10 +52,10 @@ typedef u8 kprobe_opcode_t; #define flush_insn_slot(p) do { } while (0) /* optinsn template addresses */ -extern __visible kprobe_opcode_t optprobe_template_entry; -extern __visible kprobe_opcode_t optprobe_template_val; -extern __visible kprobe_opcode_t optprobe_template_call; -extern __visible kprobe_opcode_t optprobe_template_end; +extern __visible kprobe_opcode_t optprobe_template_entry[]; +extern __visible kprobe_opcode_t optprobe_template_val[]; +extern __visible kprobe_opcode_t optprobe_template_call[]; +extern __visible kprobe_opcode_t optprobe_template_end[]; #define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE) #define MAX_OPTINSN_SIZE \ (((unsigned long)&optprobe_template_end - \ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index ecfcb6643c9b..265c907d7d4c 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -293,7 +293,7 @@ static inline unsigned long __get_current_cr3_fast(void) unsigned long cr3 = __pa(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd); /* For now, be very restrictive about when this can be called. */ - VM_WARN_ON(in_nmi() || !in_atomic()); + VM_WARN_ON(in_nmi() || preemptible()); VM_BUG_ON(cr3 != __read_cr3()); return cr3; diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index cb976bab6299..9ffc36bfe4cd 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -84,7 +84,7 @@ struct pv_init_ops { */ unsigned (*patch)(u8 type, u16 clobber, void *insnbuf, unsigned long addr, unsigned len); -}; +} __no_randomize_layout; struct pv_lazy_ops { @@ -92,12 +92,12 @@ struct pv_lazy_ops { void (*enter)(void); void (*leave)(void); void (*flush)(void); -}; +} __no_randomize_layout; struct pv_time_ops { unsigned long long (*sched_clock)(void); unsigned long long (*steal_clock)(int cpu); -}; +} __no_randomize_layout; struct pv_cpu_ops { /* hooks for various privileged instructions */ @@ -176,7 +176,7 @@ struct pv_cpu_ops { void (*start_context_switch)(struct task_struct *prev); void (*end_context_switch)(struct task_struct *next); -}; +} __no_randomize_layout; struct pv_irq_ops { /* @@ -199,7 +199,7 @@ struct pv_irq_ops { #ifdef CONFIG_X86_64 void (*adjust_exception_frame)(void); #endif -}; +} __no_randomize_layout; struct pv_mmu_ops { unsigned long (*read_cr2)(void); @@ -305,7 +305,7 @@ struct pv_mmu_ops { an mfn. We can tell which is which from the index. */ void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags); -}; +} __no_randomize_layout; struct arch_spinlock; #ifdef CONFIG_SMP @@ -322,7 +322,7 @@ struct pv_lock_ops { void (*kick)(int cpu); struct paravirt_callee_save vcpu_is_preempted; -}; +} __no_randomize_layout; /* This contains all the paravirt structures: we get a convenient * number for each function using the offset which we use to indicate @@ -334,7 +334,7 @@ struct paravirt_patch_template { struct pv_irq_ops pv_irq_ops; struct pv_mmu_ops pv_mmu_ops; struct pv_lock_ops pv_lock_ops; -}; +} __no_randomize_layout; extern struct pv_info pv_info; extern struct pv_init_ops pv_init_ops; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 6a79547e8ee0..028245e1c42b 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -129,7 +129,7 @@ struct cpuinfo_x86 { /* Index into per_cpu list: */ u16 cpu_index; u32 microcode; -}; +} __randomize_layout; struct cpuid_regs { u32 eax, ebx, ecx, edx; diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 6bb680671088..7491e73d9253 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -347,6 +347,14 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, struct mpc_intsrc mp_irq; /* + * Check bus_irq boundary. + */ + if (bus_irq >= NR_IRQS_LEGACY) { + pr_warn("Invalid bus_irq %u for legacy override\n", bus_irq); + return; + } + + /* * Convert 'gsi' to 'ioapic.pin'. */ ioapic = mp_find_ioapic(gsi); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index b4f5f73febdb..237e9c2341c7 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2093,7 +2093,7 @@ static inline void __init check_timer(void) int idx; idx = find_irq_entry(apic1, pin1, mp_INT); if (idx != -1 && irq_trigger(idx)) - unmask_ioapic_irq(irq_get_chip_data(0)); + unmask_ioapic_irq(irq_get_irq_data(0)); } irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index bb5abe8f5fd4..3b9e220621f8 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -134,6 +134,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) n = K6_BUG_LOOP; f_vide = vide; + OPTIMIZER_HIDE_VAR(f_vide); d = rdtsc(); while (n--) f_vide(); diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index d869c8671e36..7cf7c70b6ef2 100644 --- a/arch/x86/kernel/cpu/aperfmperf.c +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -8,20 +8,25 @@ * This file is licensed under GPLv2. */ -#include <linux/jiffies.h> +#include <linux/delay.h> +#include <linux/ktime.h> #include <linux/math64.h> #include <linux/percpu.h> #include <linux/smp.h> struct aperfmperf_sample { unsigned int khz; - unsigned long jiffies; + ktime_t time; u64 aperf; u64 mperf; }; static DEFINE_PER_CPU(struct aperfmperf_sample, samples); +#define APERFMPERF_CACHE_THRESHOLD_MS 10 +#define APERFMPERF_REFRESH_DELAY_MS 20 +#define APERFMPERF_STALE_THRESHOLD_MS 1000 + /* * aperfmperf_snapshot_khz() * On the current CPU, snapshot APERF, MPERF, and jiffies @@ -33,9 +38,11 @@ static void aperfmperf_snapshot_khz(void *dummy) u64 aperf, aperf_delta; u64 mperf, mperf_delta; struct aperfmperf_sample *s = this_cpu_ptr(&samples); + ktime_t now = ktime_get(); + s64 time_delta = ktime_ms_delta(now, s->time); - /* Don't bother re-computing within 10 ms */ - if (time_before(jiffies, s->jiffies + HZ/100)) + /* Don't bother re-computing within the cache threshold time. */ + if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS) return; rdmsrl(MSR_IA32_APERF, aperf); @@ -51,22 +58,21 @@ static void aperfmperf_snapshot_khz(void *dummy) if (mperf_delta == 0) return; - /* - * if (cpu_khz * aperf_delta) fits into ULLONG_MAX, then - * khz = (cpu_khz * aperf_delta) / mperf_delta - */ - if (div64_u64(ULLONG_MAX, cpu_khz) > aperf_delta) - s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta); - else /* khz = aperf_delta / (mperf_delta / cpu_khz) */ - s->khz = div64_u64(aperf_delta, - div64_u64(mperf_delta, cpu_khz)); - s->jiffies = jiffies; + s->time = now; s->aperf = aperf; s->mperf = mperf; + + /* If the previous iteration was too long ago, discard it. */ + if (time_delta > APERFMPERF_STALE_THRESHOLD_MS) + s->khz = 0; + else + s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta); } unsigned int arch_freq_get_on_cpu(int cpu) { + unsigned int khz; + if (!cpu_khz) return 0; @@ -74,6 +80,12 @@ unsigned int arch_freq_get_on_cpu(int cpu) return 0; smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1); + khz = per_cpu(samples.khz, cpu); + if (khz) + return khz; + + msleep(APERFMPERF_REFRESH_DELAY_MS); + smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1); return per_cpu(samples.khz, cpu); } diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 3fe45f84ced4..cbf1f6ba39a8 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -235,8 +235,7 @@ static void __init dtb_add_ioapic(struct device_node *dn) ret = of_address_to_resource(dn, 0, &r); if (ret) { - printk(KERN_ERR "Can't obtain address from node %s.\n", - dn->full_name); + printk(KERN_ERR "Can't obtain address from device node %pOF.\n", dn); return; } mp_register_ioapic(++ioapic_id, r.start, gsi_top, &cfg); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 16f82a3aaec7..8ce4212e2b8d 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -345,21 +345,10 @@ static int hpet_shutdown(struct clock_event_device *evt, int timer) return 0; } -static int hpet_resume(struct clock_event_device *evt, int timer) -{ - if (!timer) { - hpet_enable_legacy_int(); - } else { - struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); - - irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq)); - irq_domain_activate_irq(irq_get_irq_data(hdev->irq)); - disable_hardirq(hdev->irq); - irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); - enable_irq(hdev->irq); - } +static int hpet_resume(struct clock_event_device *evt) +{ + hpet_enable_legacy_int(); hpet_print_config(); - return 0; } @@ -417,7 +406,7 @@ static int hpet_legacy_set_periodic(struct clock_event_device *evt) static int hpet_legacy_resume(struct clock_event_device *evt) { - return hpet_resume(evt, 0); + return hpet_resume(evt); } static int hpet_legacy_next_event(unsigned long delta, @@ -510,8 +499,14 @@ static int hpet_msi_set_periodic(struct clock_event_device *evt) static int hpet_msi_resume(struct clock_event_device *evt) { struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + struct irq_data *data = irq_get_irq_data(hdev->irq); + struct msi_msg msg; - return hpet_resume(evt, hdev->num); + /* Restore the MSI msg and unmask the interrupt */ + irq_chip_compose_msi_msg(data, &msg); + hpet_msi_write(hdev, &msg); + hpet_msi_unmask(data); + return 0; } static int hpet_msi_next_event(unsigned long delta, diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 4aa03c5a14c9..4ed0aba8dbc8 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -155,6 +155,12 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis); seq_puts(p, " Posted-interrupt notification event\n"); + seq_printf(p, "%*s: ", prec, "NPI"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + irq_stats(j)->kvm_posted_intr_nested_ipis); + seq_puts(p, " Nested posted-interrupt event\n"); + seq_printf(p, "%*s: ", prec, "PIW"); for_each_online_cpu(j) seq_printf(p, "%10u ", @@ -313,6 +319,19 @@ __visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs) exiting_irq(); set_irq_regs(old_regs); } + +/* + * Handler for POSTED_INTERRUPT_NESTED_VECTOR. + */ +__visible void smp_kvm_posted_intr_nested_ipi(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + + entering_ack_irq(); + inc_irq_stat(kvm_posted_intr_nested_ipis); + exiting_irq(); + set_irq_regs(old_regs); +} #endif __visible void __irq_entry smp_trace_x86_platform_ipi(struct pt_regs *regs) diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 7468c6987547..c7fd18526c3e 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -150,6 +150,8 @@ static void __init apic_intr_init(void) alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi); /* IPI for KVM to deliver interrupt to wake up tasks */ alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi); + /* IPI for KVM to deliver nested posted interrupt */ + alloc_intr_gate(POSTED_INTR_NESTED_VECTOR, kvm_posted_intr_nested_ipi); #endif /* IPI vectors for APIC spurious and error interrupts */ diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 6b877807598b..f0153714ddac 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -457,6 +457,8 @@ static int arch_copy_kprobe(struct kprobe *p) int arch_prepare_kprobe(struct kprobe *p) { + int ret; + if (alternatives_text_reserved(p->addr, p->addr)) return -EINVAL; @@ -467,7 +469,13 @@ int arch_prepare_kprobe(struct kprobe *p) if (!p->ainsn.insn) return -ENOMEM; - return arch_copy_kprobe(p); + ret = arch_copy_kprobe(p); + if (ret) { + free_insn_slot(p->ainsn.insn, 0); + p->ainsn.insn = NULL; + } + + return ret; } void arch_arm_kprobe(struct kprobe *p) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 71c17a5be983..d04e30e3c0ff 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -151,6 +151,8 @@ void kvm_async_pf_task_wait(u32 token) if (hlist_unhashed(&n.link)) break; + rcu_irq_exit(); + if (!n.halted) { local_irq_enable(); schedule(); @@ -159,11 +161,11 @@ void kvm_async_pf_task_wait(u32 token) /* * We cannot reschedule. So halt. */ - rcu_irq_exit(); native_safe_halt(); local_irq_disable(); - rcu_irq_enter(); } + + rcu_irq_enter(); } if (!n.halted) finish_swait(&n.wq, &wait); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 67393fc88353..a56bf6051f4e 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -471,12 +471,12 @@ static int __init reboot_init(void) /* * The DMI quirks table takes precedence. If no quirks entry - * matches and the ACPI Hardware Reduced bit is set, force EFI - * reboot. + * matches and the ACPI Hardware Reduced bit is set and EFI + * runtime services are enabled, force EFI reboot. */ rv = dmi_check_system(reboot_dmi_table); - if (!rv && efi_reboot_required()) + if (!rv && efi_reboot_required() && !efi_runtime_disabled()) reboot_type = BOOT_EFI; return 0; diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 760433b2574a..2688c7dc5323 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -22,7 +22,7 @@ config KVM depends on HAVE_KVM depends on HIGH_RES_TIMERS # for TASKSTATS/TASK_DELAY_ACCT: - depends on NET + depends on NET && MULTIUSER select PREEMPT_NOTIFIERS select MMU_NOTIFIER select ANON_INODES diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 2695a34fa1c5..337b6d2730fa 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -649,9 +649,10 @@ void kvm_hv_process_stimers(struct kvm_vcpu *vcpu) } if ((stimer->config & HV_STIMER_ENABLE) && - stimer->count) - stimer_start(stimer); - else + stimer->count) { + if (!stimer->msg_pending) + stimer_start(stimer); + } else stimer_cleanup(stimer); } } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 2819d4c123eb..589dcc117086 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1495,11 +1495,10 @@ EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use); static void cancel_hv_timer(struct kvm_lapic *apic) { + WARN_ON(preemptible()); WARN_ON(!apic->lapic_timer.hv_timer_in_use); - preempt_disable(); kvm_x86_ops->cancel_hv_timer(apic->vcpu); apic->lapic_timer.hv_timer_in_use = false; - preempt_enable(); } static bool start_hv_timer(struct kvm_lapic *apic) @@ -1507,6 +1506,7 @@ static bool start_hv_timer(struct kvm_lapic *apic) struct kvm_timer *ktimer = &apic->lapic_timer; int r; + WARN_ON(preemptible()); if (!kvm_x86_ops->set_hv_timer) return false; @@ -1538,6 +1538,8 @@ static bool start_hv_timer(struct kvm_lapic *apic) static void start_sw_timer(struct kvm_lapic *apic) { struct kvm_timer *ktimer = &apic->lapic_timer; + + WARN_ON(preemptible()); if (apic->lapic_timer.hv_timer_in_use) cancel_hv_timer(apic); if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending)) @@ -1552,15 +1554,20 @@ static void start_sw_timer(struct kvm_lapic *apic) static void restart_apic_timer(struct kvm_lapic *apic) { + preempt_disable(); if (!start_hv_timer(apic)) start_sw_timer(apic); + preempt_enable(); } void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; - WARN_ON(!apic->lapic_timer.hv_timer_in_use); + preempt_disable(); + /* If the preempt notifier has already run, it also called apic_timer_expired */ + if (!apic->lapic_timer.hv_timer_in_use) + goto out; WARN_ON(swait_active(&vcpu->wq)); cancel_hv_timer(apic); apic_timer_expired(apic); @@ -1569,6 +1576,8 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) advance_periodic_target_expiration(apic); restart_apic_timer(apic); } +out: + preempt_enable(); } EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer); @@ -1582,9 +1591,11 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; + preempt_disable(); /* Possibly the TSC deadline timer is not enabled yet */ if (apic->lapic_timer.hv_timer_in_use) start_sw_timer(apic); + preempt_enable(); } EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 4d8141e533c3..1107626938cc 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2430,6 +2430,16 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; svm->vmcb->control.exit_code_hi = 0; svm->vmcb->control.exit_info_1 = error_code; + + /* + * FIXME: we should not write CR2 when L1 intercepts an L2 #PF exception. + * The fix is to add the ancillary datum (CR2 or DR6) to structs + * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6 can be + * written only when inject_pending_event runs (DR6 would written here + * too). This should be conditional on a new capability---if the + * capability is disabled, kvm_multiple_exception would write the + * ancillary information to CR2 or DR6, for backwards ABI-compatibility. + */ if (svm->vcpu.arch.exception.nested_apf) svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token; else diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 84e62acf2dd8..9b21b1223035 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -198,7 +198,8 @@ struct loaded_vmcs { struct vmcs *vmcs; struct vmcs *shadow_vmcs; int cpu; - int launched; + bool launched; + bool nmi_known_unmasked; struct list_head loaded_vmcss_on_cpu_link; }; @@ -415,13 +416,10 @@ struct nested_vmx { /* The guest-physical address of the current VMCS L1 keeps for L2 */ gpa_t current_vmptr; - /* The host-usable pointer to the above */ - struct page *current_vmcs12_page; - struct vmcs12 *current_vmcs12; /* * Cache of the guest's VMCS, existing outside of guest memory. * Loaded from guest memory during VMPTRLD. Flushed to guest - * memory during VMXOFF, VMCLEAR, VMPTRLD. + * memory during VMCLEAR and VMPTRLD. */ struct vmcs12 *cached_vmcs12; /* @@ -562,7 +560,6 @@ struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; u8 fail; - bool nmi_known_unmasked; u32 exit_intr_info; u32 idt_vectoring_info; ulong rflags; @@ -927,6 +924,10 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var); static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx); static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx); static int alloc_identity_pagetable(struct kvm *kvm); +static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); +static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); +static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12, + u16 error_code); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -2326,6 +2327,11 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu) __vmx_load_host_state(to_vmx(vcpu)); } +static bool emulation_required(struct kvm_vcpu *vcpu) +{ + return emulate_invalid_guest_state && !guest_state_valid(vcpu); +} + static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu); /* @@ -2363,6 +2369,8 @@ static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { + unsigned long old_rflags = vmx_get_rflags(vcpu); + __set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail); to_vmx(vcpu)->rflags = rflags; if (to_vmx(vcpu)->rmode.vm86_active) { @@ -2370,6 +2378,9 @@ static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; } vmcs_writel(GUEST_RFLAGS, rflags); + + if ((old_rflags ^ to_vmx(vcpu)->rflags) & X86_EFLAGS_VM) + to_vmx(vcpu)->emulation_required = emulation_required(vcpu); } static u32 vmx_get_pkru(struct kvm_vcpu *vcpu) @@ -2418,6 +2429,30 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) vmx_set_interrupt_shadow(vcpu, 0); } +static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, + unsigned long exit_qual) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned int nr = vcpu->arch.exception.nr; + u32 intr_info = nr | INTR_INFO_VALID_MASK; + + if (vcpu->arch.exception.has_error_code) { + vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code; + intr_info |= INTR_INFO_DELIVER_CODE_MASK; + } + + if (kvm_exception_is_soft(nr)) + intr_info |= INTR_TYPE_SOFT_EXCEPTION; + else + intr_info |= INTR_TYPE_HARD_EXCEPTION; + + if (!(vmcs12->idt_vectoring_info_field & VECTORING_INFO_VALID_MASK) && + vmx_get_nmi_mask(vcpu)) + intr_info |= INTR_INFO_UNBLOCK_NMI; + + nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual); +} + /* * KVM wants to inject page-faults which it got to the guest. This function * checks whether in a nested guest, we need to inject them to L1 or L2. @@ -2427,23 +2462,38 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); unsigned int nr = vcpu->arch.exception.nr; - if (!((vmcs12->exception_bitmap & (1u << nr)) || - (nr == PF_VECTOR && vcpu->arch.exception.nested_apf))) - return 0; + if (nr == PF_VECTOR) { + if (vcpu->arch.exception.nested_apf) { + nested_vmx_inject_exception_vmexit(vcpu, + vcpu->arch.apf.nested_apf_token); + return 1; + } + /* + * FIXME: we must not write CR2 when L1 intercepts an L2 #PF exception. + * The fix is to add the ancillary datum (CR2 or DR6) to structs + * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6 + * can be written only when inject_pending_event runs. This should be + * conditional on a new capability---if the capability is disabled, + * kvm_multiple_exception would write the ancillary information to + * CR2 or DR6, for backwards ABI-compatibility. + */ + if (nested_vmx_is_page_fault_vmexit(vmcs12, + vcpu->arch.exception.error_code)) { + nested_vmx_inject_exception_vmexit(vcpu, vcpu->arch.cr2); + return 1; + } + } else { + unsigned long exit_qual = 0; + if (nr == DB_VECTOR) + exit_qual = vcpu->arch.dr6; - if (vcpu->arch.exception.nested_apf) { - vmcs_write32(VM_EXIT_INTR_ERROR_CODE, vcpu->arch.exception.error_code); - nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, - PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | - INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK, - vcpu->arch.apf.nested_apf_token); - return 1; + if (vmcs12->exception_bitmap & (1u << nr)) { + nested_vmx_inject_exception_vmexit(vcpu, exit_qual); + return 1; + } } - nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, - vmcs_read32(VM_EXIT_INTR_INFO), - vmcs_readl(EXIT_QUALIFICATION)); - return 1; + return 0; } static void vmx_queue_exception(struct kvm_vcpu *vcpu) @@ -2657,7 +2707,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) * reason is that if one of these bits is necessary, it will appear * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control * fields of vmcs01 and vmcs02, will turn these bits off - and - * nested_vmx_exit_handled() will not pass related exits to L1. + * nested_vmx_exit_reflected() will not pass related exits to L1. * These rules have exceptions below. */ @@ -3857,11 +3907,6 @@ static __init int alloc_kvm_area(void) return 0; } -static bool emulation_required(struct kvm_vcpu *vcpu) -{ - return emulate_invalid_guest_state && !guest_state_valid(vcpu); -} - static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg, struct kvm_segment *save) { @@ -4950,6 +4995,28 @@ static bool vmx_get_enable_apicv(void) return enable_apicv; } +static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + gfn_t gfn; + + /* + * Don't need to mark the APIC access page dirty; it is never + * written to by the CPU during APIC virtualization. + */ + + if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { + gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + } + + if (nested_cpu_has_posted_intr(vmcs12)) { + gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + } +} + + static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -4957,18 +5024,15 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) void *vapic_page; u16 status; - if (vmx->nested.pi_desc && - vmx->nested.pi_pending) { - vmx->nested.pi_pending = false; - if (!pi_test_and_clear_on(vmx->nested.pi_desc)) - return; - - max_irr = find_last_bit( - (unsigned long *)vmx->nested.pi_desc->pir, 256); + if (!vmx->nested.pi_desc || !vmx->nested.pi_pending) + return; - if (max_irr == 256) - return; + vmx->nested.pi_pending = false; + if (!pi_test_and_clear_on(vmx->nested.pi_desc)) + return; + max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256); + if (max_irr != 256) { vapic_page = kmap(vmx->nested.virtual_apic_page); __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page); kunmap(vmx->nested.virtual_apic_page); @@ -4980,11 +5044,16 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) vmcs_write16(GUEST_INTR_STATUS, status); } } + + nested_mark_vmcs12_pages_dirty(vcpu); } -static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) +static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, + bool nested) { #ifdef CONFIG_SMP + int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR; + if (vcpu->mode == IN_GUEST_MODE) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -5002,8 +5071,7 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) */ WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc)); - apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), - POSTED_INTR_VECTOR); + apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec); return true; } #endif @@ -5018,7 +5086,7 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, if (is_guest_mode(vcpu) && vector == vmx->nested.posted_intr_nv) { /* the PIR and ON have been set by L1. */ - kvm_vcpu_trigger_posted_interrupt(vcpu); + kvm_vcpu_trigger_posted_interrupt(vcpu, true); /* * If a posted intr is not recognized by hardware, * we will accomplish it in the next vmentry. @@ -5052,7 +5120,7 @@ static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) if (pi_test_and_set_on(&vmx->pi_desc)) return; - if (!kvm_vcpu_trigger_posted_interrupt(vcpu)) + if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) kvm_vcpu_kick(vcpu); } @@ -5510,10 +5578,8 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!is_guest_mode(vcpu)) { - ++vcpu->stat.nmi_injections; - vmx->nmi_known_unmasked = false; - } + ++vcpu->stat.nmi_injections; + vmx->loaded_vmcs->nmi_known_unmasked = false; if (vmx->rmode.vm86_active) { if (kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0) != EMULATE_DONE) @@ -5527,16 +5593,21 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu) static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu) { - if (to_vmx(vcpu)->nmi_known_unmasked) + struct vcpu_vmx *vmx = to_vmx(vcpu); + bool masked; + + if (vmx->loaded_vmcs->nmi_known_unmasked) return false; - return vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI; + masked = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI; + vmx->loaded_vmcs->nmi_known_unmasked = !masked; + return masked; } static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) { struct vcpu_vmx *vmx = to_vmx(vcpu); - vmx->nmi_known_unmasked = !masked; + vmx->loaded_vmcs->nmi_known_unmasked = !masked; if (masked) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); @@ -7124,34 +7195,32 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu) return 1; } +static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) +{ + vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS); + vmcs_write64(VMCS_LINK_POINTER, -1ull); +} + static inline void nested_release_vmcs12(struct vcpu_vmx *vmx) { if (vmx->nested.current_vmptr == -1ull) return; - /* current_vmptr and current_vmcs12 are always set/reset together */ - if (WARN_ON(vmx->nested.current_vmcs12 == NULL)) - return; - if (enable_shadow_vmcs) { /* copy to memory all shadowed fields in case they were modified */ copy_shadow_to_vmcs12(vmx); vmx->nested.sync_shadow_vmcs = false; - vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, - SECONDARY_EXEC_SHADOW_VMCS); - vmcs_write64(VMCS_LINK_POINTER, -1ull); + vmx_disable_shadow_vmcs(vmx); } vmx->nested.posted_intr_nv = -1; /* Flush VMCS12 to guest memory */ - memcpy(vmx->nested.current_vmcs12, vmx->nested.cached_vmcs12, - VMCS12_SIZE); + kvm_vcpu_write_guest_page(&vmx->vcpu, + vmx->nested.current_vmptr >> PAGE_SHIFT, + vmx->nested.cached_vmcs12, 0, VMCS12_SIZE); - kunmap(vmx->nested.current_vmcs12_page); - nested_release_page(vmx->nested.current_vmcs12_page); vmx->nested.current_vmptr = -1ull; - vmx->nested.current_vmcs12 = NULL; } /* @@ -7165,12 +7234,14 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.vmxon = false; free_vpid(vmx->nested.vpid02); - nested_release_vmcs12(vmx); + vmx->nested.posted_intr_nv = -1; + vmx->nested.current_vmptr = -1ull; if (vmx->nested.msr_bitmap) { free_page((unsigned long)vmx->nested.msr_bitmap); vmx->nested.msr_bitmap = NULL; } if (enable_shadow_vmcs) { + vmx_disable_shadow_vmcs(vmx); vmcs_clear(vmx->vmcs01.shadow_vmcs); free_vmcs(vmx->vmcs01.shadow_vmcs); vmx->vmcs01.shadow_vmcs = NULL; @@ -7569,14 +7640,14 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) } nested_release_vmcs12(vmx); - vmx->nested.current_vmcs12 = new_vmcs12; - vmx->nested.current_vmcs12_page = page; /* * Load VMCS12 from guest memory since it is not already * cached. */ - memcpy(vmx->nested.cached_vmcs12, - vmx->nested.current_vmcs12, VMCS12_SIZE); + memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE); + kunmap(page); + nested_release_page_clean(page); + set_current_vmptr(vmx, vmptr); } @@ -8009,12 +8080,11 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, * should handle it ourselves in L0 (and then continue L2). Only call this * when in is_guest_mode (L2). */ -static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) +static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) { u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO); struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - u32 exit_reason = vmx->exit_reason; trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason, vmcs_readl(EXIT_QUALIFICATION), @@ -8023,6 +8093,18 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) vmcs_read32(VM_EXIT_INTR_ERROR_CODE), KVM_ISA_VMX); + /* + * The host physical addresses of some pages of guest memory + * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU + * may write to these pages via their host physical address while + * L2 is running, bypassing any address-translation-based dirty + * tracking (e.g. EPT write protection). + * + * Mark them dirty on every exit from L2 to prevent them from + * getting out of sync with dirty tracking. + */ + nested_mark_vmcs12_pages_dirty(vcpu); + if (vmx->nested.nested_run_pending) return false; @@ -8159,6 +8241,29 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) } } +static int nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason) +{ + u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + + /* + * At this point, the exit interruption info in exit_intr_info + * is only valid for EXCEPTION_NMI exits. For EXTERNAL_INTERRUPT + * we need to query the in-kernel LAPIC. + */ + WARN_ON(exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT); + if ((exit_intr_info & + (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) == + (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) { + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + vmcs12->vm_exit_intr_error_code = + vmcs_read32(VM_EXIT_INTR_ERROR_CODE); + } + + nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info, + vmcs_readl(EXIT_QUALIFICATION)); + return 1; +} + static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) { *info1 = vmcs_readl(EXIT_QUALIFICATION); @@ -8405,12 +8510,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) if (vmx->emulation_required) return handle_invalid_guest_state(vcpu); - if (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) { - nested_vmx_vmexit(vcpu, exit_reason, - vmcs_read32(VM_EXIT_INTR_INFO), - vmcs_readl(EXIT_QUALIFICATION)); - return 1; - } + if (is_guest_mode(vcpu) && nested_vmx_exit_reflected(vcpu, exit_reason)) + return nested_vmx_reflect_vmexit(vcpu, exit_reason); if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) { dump_vmcs(); @@ -8736,7 +8837,7 @@ static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) idtv_info_valid = vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK; - if (vmx->nmi_known_unmasked) + if (vmx->loaded_vmcs->nmi_known_unmasked) return; /* * Can't use vmx->exit_intr_info since we're not sure what @@ -8760,7 +8861,7 @@ static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); else - vmx->nmi_known_unmasked = + vmx->loaded_vmcs->nmi_known_unmasked = !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI); } @@ -9213,7 +9314,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; - vmx->nested.current_vmcs12 = NULL; vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED; @@ -9499,12 +9599,15 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, WARN_ON(!is_guest_mode(vcpu)); - if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) - nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason, - vmcs_read32(VM_EXIT_INTR_INFO), - vmcs_readl(EXIT_QUALIFICATION)); - else + if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) { + vmcs12->vm_exit_intr_error_code = fault->error_code; + nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, + PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | + INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK, + fault->address); + } else { kvm_inject_page_fault(vcpu, fault); + } } static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, @@ -10032,6 +10135,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs12->vm_entry_instruction_len); vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, vmcs12->guest_interruptibility_info); + vmx->loaded_vmcs->nmi_known_unmasked = + !(vmcs12->guest_interruptibility_info & GUEST_INTR_STATE_NMI); } else { vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); } @@ -10056,13 +10161,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, /* Posted interrupts setting is only taken from vmcs12. */ if (nested_cpu_has_posted_intr(vmcs12)) { - /* - * Note that we use L0's vector here and in - * vmx_deliver_nested_posted_interrupt. - */ vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; vmx->nested.pi_pending = false; - vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); + vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR); } else { exec_control &= ~PIN_BASED_POSTED_INTR; } @@ -10086,12 +10187,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept, * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when * !enable_ept, EB.PF is 1, so the "or" will always be 1. - * - * A problem with this approach (when !enable_ept) is that L1 may be - * injected with more page faults than it asked for. This could have - * caused problems, but in practice existing hypervisors don't care. - * To fix this, we will need to emulate the PFEC checking (on the L1 - * page tables), using walk_addr(), when injecting PFs to L1. */ vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, enable_ept ? vmcs12->page_fault_error_code_mask : 0); @@ -10488,6 +10583,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) { struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu); u32 exit_qual; int ret; @@ -10512,6 +10608,12 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * for misconfigurations which will anyway be caught by the processor * when using the merged vmcs02. */ + if (interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS) { + nested_vmx_failValid(vcpu, + VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS); + goto out; + } + if (vmcs12->launch_state == launch) { nested_vmx_failValid(vcpu, launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS @@ -10832,13 +10934,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs12->vm_exit_reason = exit_reason; vmcs12->exit_qualification = exit_qualification; - vmcs12->vm_exit_intr_info = exit_intr_info; - if ((vmcs12->vm_exit_intr_info & - (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) == - (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) - vmcs12->vm_exit_intr_error_code = - vmcs_read32(VM_EXIT_INTR_ERROR_CODE); + vmcs12->idt_vectoring_info_field = 0; vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); @@ -10926,7 +11023,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, */ vmx_flush_tlb(vcpu); } - + /* Restore posted intr vector. */ + if (nested_cpu_has_posted_intr(vmcs12)) + vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs); vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp); @@ -11032,8 +11131,15 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmx_switch_vmcs(vcpu, &vmx->vmcs01); - if ((exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) - && nested_exit_intr_ack_set(vcpu)) { + /* + * TODO: SDM says that with acknowledge interrupt on exit, bit 31 of + * the VM-exit interrupt information (valid interrupt) is always set to + * 1 on EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't need + * kvm_cpu_has_interrupt(). See the commit message for details. + */ + if (nested_exit_intr_ack_set(vcpu) && + exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && + kvm_cpu_has_interrupt(vcpu)) { int irq = kvm_cpu_get_interrupt(vcpu); WARN_ON(irq < 0); vmcs12->vm_exit_intr_info = irq | diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5b8f07889f6a..d734aa8c5b4f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -597,8 +597,8 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) (unsigned long *)&vcpu->arch.regs_avail)) return true; - gfn = (kvm_read_cr3(vcpu) & ~31u) >> PAGE_SHIFT; - offset = (kvm_read_cr3(vcpu) & ~31u) & (PAGE_SIZE - 1); + gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT; + offset = (kvm_read_cr3(vcpu) & 0xffffffe0ul) & (PAGE_SIZE - 1); r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte), PFERR_USER_MASK | PFERR_WRITE_MASK); if (r < 0) @@ -3159,15 +3159,18 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, kvm_set_hflags(vcpu, hflags); vcpu->arch.smi_pending = events->smi.pending; - if (events->smi.smm_inside_nmi) - vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; - else - vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; - if (lapic_in_kernel(vcpu)) { - if (events->smi.latched_init) - set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + + if (events->smi.smm) { + if (events->smi.smm_inside_nmi) + vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; else - clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; + if (lapic_in_kernel(vcpu)) { + if (events->smi.latched_init) + set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + else + clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + } } } @@ -6215,6 +6218,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) lapic_irq.shorthand = 0; lapic_irq.dest_mode = 0; + lapic_irq.level = 0; lapic_irq.dest_id = apicid; lapic_irq.msi_redir_hint = false; diff --git a/arch/x86/math-emu/Makefile b/arch/x86/math-emu/Makefile index 9b0c63b60302..1b2dac174321 100644 --- a/arch/x86/math-emu/Makefile +++ b/arch/x86/math-emu/Makefile @@ -5,8 +5,8 @@ #DEBUG = -DDEBUGGING DEBUG = PARANOID = -DPARANOID -EXTRA_CFLAGS := $(PARANOID) $(DEBUG) -fno-builtin $(MATH_EMULATION) -EXTRA_AFLAGS := $(PARANOID) +ccflags-y += $(PARANOID) $(DEBUG) -fno-builtin $(MATH_EMULATION) +asflags-y += $(PARANOID) # From 'C' language sources: C_OBJS =fpu_entry.o errors.o \ diff --git a/arch/x86/math-emu/fpu_emu.h b/arch/x86/math-emu/fpu_emu.h index afbc4d805d66..c9c320dccca1 100644 --- a/arch/x86/math-emu/fpu_emu.h +++ b/arch/x86/math-emu/fpu_emu.h @@ -157,7 +157,7 @@ extern u_char const data_sizes_16[32]; #define signbyte(a) (((u_char *)(a))[9]) #define getsign(a) (signbyte(a) & 0x80) -#define setsign(a,b) { if (b) signbyte(a) |= 0x80; else signbyte(a) &= 0x7f; } +#define setsign(a,b) { if ((b) != 0) signbyte(a) |= 0x80; else signbyte(a) &= 0x7f; } #define copysign(a,b) { if (getsign(a)) signbyte(b) |= 0x80; \ else signbyte(b) &= 0x7f; } #define changesign(a) { signbyte(a) ^= 0x80; } diff --git a/arch/x86/math-emu/reg_compare.c b/arch/x86/math-emu/reg_compare.c index b77360fdbf4a..19b33b50adfa 100644 --- a/arch/x86/math-emu/reg_compare.c +++ b/arch/x86/math-emu/reg_compare.c @@ -168,7 +168,7 @@ static int compare(FPU_REG const *b, int tagb) /* This function requires that st(0) is not empty */ int FPU_compare_st_data(FPU_REG const *loaded_data, u_char loaded_tag) { - int f = 0, c; + int f, c; c = compare(loaded_data, loaded_tag); @@ -189,12 +189,12 @@ int FPU_compare_st_data(FPU_REG const *loaded_data, u_char loaded_tag) case COMP_No_Comp: f = SW_C3 | SW_C2 | SW_C0; break; -#ifdef PARANOID default: +#ifdef PARANOID EXCEPTION(EX_INTERNAL | 0x121); +#endif /* PARANOID */ f = SW_C3 | SW_C2 | SW_C0; break; -#endif /* PARANOID */ } setcc(f); if (c & COMP_Denormal) { @@ -205,7 +205,7 @@ int FPU_compare_st_data(FPU_REG const *loaded_data, u_char loaded_tag) static int compare_st_st(int nr) { - int f = 0, c; + int f, c; FPU_REG *st_ptr; if (!NOT_EMPTY(0) || !NOT_EMPTY(nr)) { @@ -235,12 +235,12 @@ static int compare_st_st(int nr) case COMP_No_Comp: f = SW_C3 | SW_C2 | SW_C0; break; -#ifdef PARANOID default: +#ifdef PARANOID EXCEPTION(EX_INTERNAL | 0x122); +#endif /* PARANOID */ f = SW_C3 | SW_C2 | SW_C0; break; -#endif /* PARANOID */ } setcc(f); if (c & COMP_Denormal) { @@ -283,12 +283,12 @@ static int compare_i_st_st(int nr) case COMP_No_Comp: f = X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF; break; -#ifdef PARANOID default: +#ifdef PARANOID EXCEPTION(EX_INTERNAL | 0x122); +#endif /* PARANOID */ f = 0; break; -#endif /* PARANOID */ } FPU_EFLAGS = (FPU_EFLAGS & ~(X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF)) | f; if (c & COMP_Denormal) { diff --git a/arch/x86/platform/intel-mid/device_libs/platform_max7315.c b/arch/x86/platform/intel-mid/device_libs/platform_max7315.c index 6e075afa7877..58337b2bc682 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_max7315.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_max7315.c @@ -38,8 +38,10 @@ static void __init *max7315_platform_data(void *info) */ strcpy(i2c_info->type, "max7315"); if (nr++) { - sprintf(base_pin_name, "max7315_%d_base", nr); - sprintf(intr_pin_name, "max7315_%d_int", nr); + snprintf(base_pin_name, sizeof(base_pin_name), + "max7315_%d_base", nr); + snprintf(intr_pin_name, sizeof(intr_pin_name), + "max7315_%d_int", nr); } else { strcpy(base_pin_name, "max7315_base"); strcpy(intr_pin_name, "max7315_int"); diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index d4a61ddf9e62..3e4bdb442fbc 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -40,7 +40,6 @@ static int timeout_base_ns[] = { static int timeout_us; static bool nobau = true; static int nobau_perm; -static cycles_t congested_cycles; /* tunables: */ static int max_concurr = MAX_BAU_CONCURRENT; @@ -829,10 +828,10 @@ static void record_send_stats(cycles_t time1, cycles_t time2, if ((completion_status == FLUSH_COMPLETE) && (try == 1)) { bcp->period_requests++; bcp->period_time += elapsed; - if ((elapsed > congested_cycles) && + if ((elapsed > usec_2_cycles(bcp->cong_response_us)) && (bcp->period_requests > bcp->cong_reps) && ((bcp->period_time / bcp->period_requests) > - congested_cycles)) { + usec_2_cycles(bcp->cong_response_us))) { stat->s_congested++; disable_for_period(bcp, stat); } @@ -2222,14 +2221,17 @@ static int __init uv_bau_init(void) else if (is_uv1_hub()) ops = uv1_bau_ops; + nuvhubs = uv_num_possible_blades(); + if (nuvhubs < 2) { + pr_crit("UV: BAU disabled - insufficient hub count\n"); + goto err_bau_disable; + } + for_each_possible_cpu(cur_cpu) { mask = &per_cpu(uv_flush_tlb_mask, cur_cpu); zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cur_cpu)); } - nuvhubs = uv_num_possible_blades(); - congested_cycles = usec_2_cycles(congested_respns_us); - uv_base_pnode = 0x7fffffff; for (uvhub = 0; uvhub < nuvhubs; uvhub++) { cpus = uv_blade_nr_possible_cpus(uvhub); @@ -2242,9 +2244,8 @@ static int __init uv_bau_init(void) enable_timeouts(); if (init_per_cpu(nuvhubs, uv_base_pnode)) { - set_bau_off(); - nobau_perm = 1; - return 0; + pr_crit("UV: BAU disabled - per CPU init failed\n"); + goto err_bau_disable; } vector = UV_BAU_MESSAGE; @@ -2270,6 +2271,16 @@ static int __init uv_bau_init(void) } return 0; + +err_bau_disable: + + for_each_possible_cpu(cur_cpu) + free_cpumask_var(per_cpu(uv_flush_tlb_mask, cur_cpu)); + + set_bau_off(); + nobau_perm = 1; + + return -EINVAL; } core_initcall(uv_bau_init); fs_initcall(uv_ptc_init); diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 1ea598e5f030..51471408fdd1 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -19,6 +19,7 @@ #include <linux/irq_work.h> #include <linux/tick.h> #include <linux/nmi.h> +#include <linux/cpuhotplug.h> #include <asm/paravirt.h> #include <asm/desc.h> @@ -413,7 +414,7 @@ static void xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */ */ tick_nohz_idle_enter(); - cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); + cpuhp_online_idle(CPUHP_AP_ONLINE_IDLE); } #else /* !CONFIG_HOTPLUG_CPU */ diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index a1895a8e85c1..1ecb05db3632 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -309,7 +309,6 @@ static irqreturn_t xen_timer_interrupt(int irq, void *dev_id) void xen_teardown_timer(int cpu) { struct clock_event_device *evt; - BUG_ON(cpu == 0); evt = &per_cpu(xen_clock_events, cpu).evt; if (evt->irq >= 0) { |