diff options
Diffstat (limited to 'arch/x86')
60 files changed, 841 insertions, 406 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 781521b7cf9e..323cb065be5e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -100,6 +100,7 @@ config X86 select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select GENERIC_TIME_VSYSCALL + select HARDLOCKUP_CHECK_TIMESTAMP if X86_64 select HAVE_ACPI_APEI if ACPI select HAVE_ACPI_APEI_NMI if ACPI select HAVE_ALIGNED_STRUCT_PAGE if SLUB @@ -163,7 +164,7 @@ config X86 select HAVE_PCSPKR_PLATFORM select HAVE_PERF_EVENTS select HAVE_PERF_EVENTS_NMI - select HAVE_HARDLOCKUP_DETECTOR_PERF if HAVE_PERF_EVENTS_NMI + select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API 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/compressed/misc.c b/arch/x86/boot/compressed/misc.c index a0838ab929f2..c14217cd0155 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -116,8 +116,7 @@ void __putstr(const char *s) } } - if (boot_params->screen_info.orig_video_mode == 0 && - lines == 0 && cols == 0) + if (lines == 0 || cols == 0) return; x = boot_params->screen_info.orig_x; diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 2ed8f0c25def..1bb08ecffd24 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -520,8 +520,14 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr # the description in lib/decompressor_xxx.c for specific information. # # extra_bytes = (uncompressed_size >> 12) + 65536 + 128 +# +# LZ4 is even worse: data that cannot be further compressed grows by 0.4%, +# or one byte per 256 bytes. OTOH, we can safely get rid of the +128 as +# the size-dependent part now grows so fast. +# +# extra_bytes = (uncompressed_size >> 8) + 65536 -#define ZO_z_extra_bytes ((ZO_z_output_len >> 12) + 65536 + 128) +#define ZO_z_extra_bytes ((ZO_z_output_len >> 8) + 65536) #if ZO_z_output_len > ZO_z_input_len # define ZO_z_extract_offset (ZO_z_output_len + ZO_z_extra_bytes - \ ZO_z_input_len) 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/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S index 1cd792db15ef..1eab79c9ac48 100644 --- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S +++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S @@ -117,11 +117,10 @@ .set T1, REG_T1 .endm -#define K_BASE %r8 #define HASH_PTR %r9 +#define BLOCKS_CTR %r8 #define BUFFER_PTR %r10 #define BUFFER_PTR2 %r13 -#define BUFFER_END %r11 #define PRECALC_BUF %r14 #define WK_BUF %r15 @@ -205,14 +204,14 @@ * blended AVX2 and ALU instruction scheduling * 1 vector iteration per 8 rounds */ - vmovdqu ((i * 2) + PRECALC_OFFSET)(BUFFER_PTR), W_TMP + vmovdqu (i * 2)(BUFFER_PTR), W_TMP .elseif ((i & 7) == 1) - vinsertf128 $1, (((i-1) * 2)+PRECALC_OFFSET)(BUFFER_PTR2),\ + vinsertf128 $1, ((i-1) * 2)(BUFFER_PTR2),\ WY_TMP, WY_TMP .elseif ((i & 7) == 2) vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY .elseif ((i & 7) == 4) - vpaddd K_XMM(K_BASE), WY, WY_TMP + vpaddd K_XMM + K_XMM_AR(%rip), WY, WY_TMP .elseif ((i & 7) == 7) vmovdqu WY_TMP, PRECALC_WK(i&~7) @@ -255,7 +254,7 @@ vpxor WY, WY_TMP, WY_TMP .elseif ((i & 7) == 7) vpxor WY_TMP2, WY_TMP, WY - vpaddd K_XMM(K_BASE), WY, WY_TMP + vpaddd K_XMM + K_XMM_AR(%rip), WY, WY_TMP vmovdqu WY_TMP, PRECALC_WK(i&~7) PRECALC_ROTATE_WY @@ -291,7 +290,7 @@ vpsrld $30, WY, WY vpor WY, WY_TMP, WY .elseif ((i & 7) == 7) - vpaddd K_XMM(K_BASE), WY, WY_TMP + vpaddd K_XMM + K_XMM_AR(%rip), WY, WY_TMP vmovdqu WY_TMP, PRECALC_WK(i&~7) PRECALC_ROTATE_WY @@ -446,6 +445,16 @@ .endm +/* Add constant only if (%2 > %3) condition met (uses RTA as temp) + * %1 + %2 >= %3 ? %4 : 0 + */ +.macro ADD_IF_GE a, b, c, d + mov \a, RTA + add $\d, RTA + cmp $\c, \b + cmovge RTA, \a +.endm + /* * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining */ @@ -463,13 +472,16 @@ lea (2*4*80+32)(%rsp), WK_BUF # Precalc WK for first 2 blocks - PRECALC_OFFSET = 0 + ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 2, 64 .set i, 0 .rept 160 PRECALC i .set i, i + 1 .endr - PRECALC_OFFSET = 128 + + /* Go to next block if needed */ + ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 3, 128 + ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128 xchg WK_BUF, PRECALC_BUF .align 32 @@ -479,8 +491,8 @@ _loop: * we use K_BASE value as a signal of a last block, * it is set below by: cmovae BUFFER_PTR, K_BASE */ - cmp K_BASE, BUFFER_PTR - jne _begin + test BLOCKS_CTR, BLOCKS_CTR + jnz _begin .align 32 jmp _end .align 32 @@ -512,10 +524,10 @@ _loop0: .set j, j+2 .endr - add $(2*64), BUFFER_PTR /* move to next odd-64-byte block */ - cmp BUFFER_END, BUFFER_PTR /* is current block the last one? */ - cmovae K_BASE, BUFFER_PTR /* signal the last iteration smartly */ - + /* Update Counter */ + sub $1, BLOCKS_CTR + /* Move to the next block only if needed*/ + ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 4, 128 /* * rounds * 60,62,64,66,68 @@ -532,8 +544,8 @@ _loop0: UPDATE_HASH 12(HASH_PTR), D UPDATE_HASH 16(HASH_PTR), E - cmp K_BASE, BUFFER_PTR /* is current block the last one? */ - je _loop + test BLOCKS_CTR, BLOCKS_CTR + jz _loop mov TB, B @@ -575,10 +587,10 @@ _loop2: .set j, j+2 .endr - add $(2*64), BUFFER_PTR2 /* move to next even-64-byte block */ - - cmp BUFFER_END, BUFFER_PTR2 /* is current block the last one */ - cmovae K_BASE, BUFFER_PTR /* signal the last iteration smartly */ + /* update counter */ + sub $1, BLOCKS_CTR + /* Move to the next block only if needed*/ + ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128 jmp _loop3 _loop3: @@ -641,19 +653,12 @@ _loop3: avx2_zeroupper - lea K_XMM_AR(%rip), K_BASE - + /* Setup initial values */ mov CTX, HASH_PTR mov BUF, BUFFER_PTR - lea 64(BUF), BUFFER_PTR2 - - shl $6, CNT /* mul by 64 */ - add BUF, CNT - add $64, CNT - mov CNT, BUFFER_END - cmp BUFFER_END, BUFFER_PTR2 - cmovae K_BASE, BUFFER_PTR2 + mov BUF, BUFFER_PTR2 + mov CNT, BLOCKS_CTR xmm_mov BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index f960a043cdeb..fc61739150e7 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -201,7 +201,7 @@ asmlinkage void sha1_transform_avx2(u32 *digest, const char *data, static bool avx2_usable(void) { - if (false && avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) + if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_BMI1) && boot_cpu_has(X86_FEATURE_BMI2)) return true; diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index a9a8027a6c0e..ce8dc33dd640 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -675,13 +675,8 @@ apicinterrupt3 \num trace(\sym) smp_trace(\sym) #endif /* Make sure APIC interrupt handlers end up in the irqentry section: */ -#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) -# define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax" -# define POP_SECTION_IRQENTRY .popsection -#else -# define PUSH_SECTION_IRQENTRY -# define POP_SECTION_IRQENTRY -#endif +#define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax" +#define POP_SECTION_IRQENTRY .popsection .macro apicinterrupt num sym do_sym PUSH_SECTION_IRQENTRY @@ -705,6 +700,7 @@ 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 @@ -1210,6 +1206,8 @@ ENTRY(nmi) * other IST entries. */ + ASM_CLAC + /* Use %rdx as our temp variable throughout */ pushq %rdx diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index ad44af0dd667..f5cbbba99283 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -400,11 +400,24 @@ static int amd_uncore_cpu_starting(unsigned int cpu) if (amd_uncore_llc) { unsigned int apicid = cpu_data(cpu).apicid; - unsigned int nshared; + unsigned int nshared, subleaf, prev_eax = 0; uncore = *per_cpu_ptr(amd_uncore_llc, cpu); - cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx); - nshared = ((eax >> 14) & 0xfff) + 1; + /* + * Iterate over Cache Topology Definition leaves until no + * more cache descriptions are available. + */ + for (subleaf = 0; subleaf < 5; subleaf++) { + cpuid_count(0x8000001d, subleaf, &eax, &ebx, &ecx, &edx); + + /* EAX[0:4] gives type of cache */ + if (!(eax & 0x1f)) + break; + + prev_eax = eax; + } + nshared = ((prev_eax >> 14) & 0xfff) + 1; + uncore->id = apicid - (apicid % nshared); uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc); @@ -555,7 +568,7 @@ static int __init amd_uncore_init(void) ret = 0; } - if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) { + if (boot_cpu_has(X86_FEATURE_PERFCTR_LLC)) { amd_uncore_llc = alloc_percpu(struct amd_uncore *); if (!amd_uncore_llc) { ret = -ENOMEM; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 8e3db8f642a7..80534d3c2480 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -487,22 +487,28 @@ static inline int precise_br_compat(struct perf_event *event) return m == b; } -int x86_pmu_hw_config(struct perf_event *event) +int x86_pmu_max_precise(void) { - if (event->attr.precise_ip) { - int precise = 0; + int precise = 0; - /* Support for constant skid */ - if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) { + /* Support for constant skid */ + if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) { + precise++; + + /* Support for IP fixup */ + if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2) precise++; - /* Support for IP fixup */ - if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2) - precise++; + if (x86_pmu.pebs_prec_dist) + precise++; + } + return precise; +} - if (x86_pmu.pebs_prec_dist) - precise++; - } +int x86_pmu_hw_config(struct perf_event *event) +{ + if (event->attr.precise_ip) { + int precise = x86_pmu_max_precise(); if (event->attr.precise_ip > precise) return -EOPNOTSUPP; @@ -1751,6 +1757,7 @@ ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event) } static struct attribute_group x86_pmu_attr_group; +static struct attribute_group x86_pmu_caps_group; static int __init init_hw_perf_events(void) { @@ -1799,6 +1806,14 @@ static int __init init_hw_perf_events(void) x86_pmu_format_group.attrs = x86_pmu.format_attrs; + if (x86_pmu.caps_attrs) { + struct attribute **tmp; + + tmp = merge_attr(x86_pmu_caps_group.attrs, x86_pmu.caps_attrs); + if (!WARN_ON(!tmp)) + x86_pmu_caps_group.attrs = tmp; + } + if (x86_pmu.event_attrs) x86_pmu_events_group.attrs = x86_pmu.event_attrs; @@ -2114,7 +2129,7 @@ static void refresh_pce(void *ignored) load_mm_cr4(this_cpu_read(cpu_tlbstate.loaded_mm)); } -static void x86_pmu_event_mapped(struct perf_event *event) +static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm) { if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) return; @@ -2129,22 +2144,20 @@ static void x86_pmu_event_mapped(struct perf_event *event) * For now, this can't happen because all callers hold mmap_sem * for write. If this changes, we'll need a different solution. */ - lockdep_assert_held_exclusive(¤t->mm->mmap_sem); + lockdep_assert_held_exclusive(&mm->mmap_sem); - if (atomic_inc_return(¤t->mm->context.perf_rdpmc_allowed) == 1) - on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1); + if (atomic_inc_return(&mm->context.perf_rdpmc_allowed) == 1) + on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1); } -static void x86_pmu_event_unmapped(struct perf_event *event) +static void x86_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm) { - if (!current->mm) - return; if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) return; - if (atomic_dec_and_test(¤t->mm->context.perf_rdpmc_allowed)) - on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1); + if (atomic_dec_and_test(&mm->context.perf_rdpmc_allowed)) + on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1); } static int x86_pmu_event_idx(struct perf_event *event) @@ -2215,10 +2228,30 @@ static struct attribute_group x86_pmu_attr_group = { .attrs = x86_pmu_attrs, }; +static ssize_t max_precise_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%d\n", x86_pmu_max_precise()); +} + +static DEVICE_ATTR_RO(max_precise); + +static struct attribute *x86_pmu_caps_attrs[] = { + &dev_attr_max_precise.attr, + NULL +}; + +static struct attribute_group x86_pmu_caps_group = { + .name = "caps", + .attrs = x86_pmu_caps_attrs, +}; + static const struct attribute_group *x86_pmu_attr_groups[] = { &x86_pmu_attr_group, &x86_pmu_format_group, &x86_pmu_events_group, + &x86_pmu_caps_group, NULL, }; @@ -2337,12 +2370,9 @@ static unsigned long get_segment_base(unsigned int segment) #ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; - if (idx > LDT_ENTRIES) - return 0; - /* IRQs are off, so this synchronizes with smp_store_release */ ldt = lockless_dereference(current->active_mm->context.ldt); - if (!ldt || idx > ldt->nr_entries) + if (!ldt || idx >= ldt->nr_entries) return 0; desc = &ldt->entries[idx]; @@ -2350,7 +2380,7 @@ static unsigned long get_segment_base(unsigned int segment) return 0; #endif } else { - if (idx > GDT_ENTRIES) + if (idx >= GDT_ENTRIES) return 0; desc = raw_cpu_ptr(gdt_page.gdt) + idx; diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 8ae8c5ce3a1f..16076eb34699 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -69,7 +69,7 @@ struct bts_buffer { struct bts_phys buf[0]; }; -struct pmu bts_pmu; +static struct pmu bts_pmu; static size_t buf_size(struct page *page) { @@ -268,7 +268,7 @@ static void bts_event_start(struct perf_event *event, int flags) bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum; bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold; - event->hw.itrace_started = 1; + perf_event_itrace_started(event); event->hw.state = 0; __bts_event_start(event); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 98b0f0729527..829e89cfcee2 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3415,12 +3415,26 @@ static struct attribute *intel_arch3_formats_attr[] = { &format_attr_any.attr, &format_attr_inv.attr, &format_attr_cmask.attr, + NULL, +}; + +static struct attribute *hsw_format_attr[] = { &format_attr_in_tx.attr, &format_attr_in_tx_cp.attr, + &format_attr_offcore_rsp.attr, + &format_attr_ldlat.attr, + NULL +}; - &format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */ - &format_attr_ldlat.attr, /* PEBS load latency */ - NULL, +static struct attribute *nhm_format_attr[] = { + &format_attr_offcore_rsp.attr, + &format_attr_ldlat.attr, + NULL +}; + +static struct attribute *slm_format_attr[] = { + &format_attr_offcore_rsp.attr, + NULL }; static struct attribute *skl_format_attr[] = { @@ -3781,6 +3795,36 @@ done: static DEVICE_ATTR_RW(freeze_on_smi); +static ssize_t branches_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%d\n", x86_pmu.lbr_nr); +} + +static DEVICE_ATTR_RO(branches); + +static struct attribute *lbr_attrs[] = { + &dev_attr_branches.attr, + NULL +}; + +static char pmu_name_str[30]; + +static ssize_t pmu_name_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%s\n", pmu_name_str); +} + +static DEVICE_ATTR_RO(pmu_name); + +static struct attribute *intel_pmu_caps_attrs[] = { + &dev_attr_pmu_name.attr, + NULL +}; + static struct attribute *intel_pmu_attrs[] = { &dev_attr_freeze_on_smi.attr, NULL, @@ -3795,6 +3839,8 @@ __init int intel_pmu_init(void) unsigned int unused; struct extra_reg *er; int version, i; + struct attribute **extra_attr = NULL; + char *name; if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { switch (boot_cpu_data.x86) { @@ -3862,6 +3908,7 @@ __init int intel_pmu_init(void) switch (boot_cpu_data.x86_model) { case INTEL_FAM6_CORE_YONAH: pr_cont("Core events, "); + name = "core"; break; case INTEL_FAM6_CORE2_MEROM: @@ -3877,6 +3924,7 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_core2_event_constraints; x86_pmu.pebs_constraints = intel_core2_pebs_event_constraints; pr_cont("Core2 events, "); + name = "core2"; break; case INTEL_FAM6_NEHALEM: @@ -3905,8 +3953,11 @@ __init int intel_pmu_init(void) intel_pmu_pebs_data_source_nhm(); x86_add_quirk(intel_nehalem_quirk); + x86_pmu.pebs_no_tlb = 1; + extra_attr = nhm_format_attr; pr_cont("Nehalem events, "); + name = "nehalem"; break; case INTEL_FAM6_ATOM_PINEVIEW: @@ -3923,6 +3974,7 @@ __init int intel_pmu_init(void) x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_core2; pr_cont("Atom events, "); + name = "bonnell"; break; case INTEL_FAM6_ATOM_SILVERMONT1: @@ -3940,7 +3992,9 @@ __init int intel_pmu_init(void) x86_pmu.extra_regs = intel_slm_extra_regs; x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.cpu_events = slm_events_attrs; + extra_attr = slm_format_attr; pr_cont("Silvermont events, "); + name = "silvermont"; break; case INTEL_FAM6_ATOM_GOLDMONT: @@ -3965,7 +4019,9 @@ __init int intel_pmu_init(void) x86_pmu.lbr_pt_coexist = true; x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.cpu_events = glm_events_attrs; + extra_attr = slm_format_attr; pr_cont("Goldmont events, "); + name = "goldmont"; break; case INTEL_FAM6_ATOM_GEMINI_LAKE: @@ -3991,7 +4047,9 @@ __init int intel_pmu_init(void) x86_pmu.cpu_events = glm_events_attrs; /* Goldmont Plus has 4-wide pipeline */ event_attr_td_total_slots_scale_glm.event_str = "4"; + extra_attr = slm_format_attr; pr_cont("Goldmont plus events, "); + name = "goldmont_plus"; break; case INTEL_FAM6_WESTMERE: @@ -4020,7 +4078,9 @@ __init int intel_pmu_init(void) X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); intel_pmu_pebs_data_source_nhm(); + extra_attr = nhm_format_attr; pr_cont("Westmere events, "); + name = "westmere"; break; case INTEL_FAM6_SANDYBRIDGE: @@ -4056,7 +4116,10 @@ __init int intel_pmu_init(void) intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = X86_CONFIG(.event=0xb1, .umask=0x01, .inv=1, .cmask=1); + extra_attr = nhm_format_attr; + pr_cont("SandyBridge events, "); + name = "sandybridge"; break; case INTEL_FAM6_IVYBRIDGE: @@ -4090,7 +4153,10 @@ __init int intel_pmu_init(void) intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); + extra_attr = nhm_format_attr; + pr_cont("IvyBridge events, "); + name = "ivybridge"; break; @@ -4118,7 +4184,10 @@ __init int intel_pmu_init(void) x86_pmu.get_event_constraints = hsw_get_event_constraints; x86_pmu.cpu_events = hsw_events_attrs; x86_pmu.lbr_double_abort = true; + extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? + hsw_format_attr : nhm_format_attr; pr_cont("Haswell events, "); + name = "haswell"; break; case INTEL_FAM6_BROADWELL_CORE: @@ -4154,7 +4223,10 @@ __init int intel_pmu_init(void) x86_pmu.get_event_constraints = hsw_get_event_constraints; x86_pmu.cpu_events = hsw_events_attrs; x86_pmu.limit_period = bdw_limit_period; + extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? + hsw_format_attr : nhm_format_attr; pr_cont("Broadwell events, "); + name = "broadwell"; break; case INTEL_FAM6_XEON_PHI_KNL: @@ -4172,8 +4244,9 @@ __init int intel_pmu_init(void) /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; - + extra_attr = slm_format_attr; pr_cont("Knights Landing/Mill events, "); + name = "knights-landing"; break; case INTEL_FAM6_SKYLAKE_MOBILE: @@ -4203,11 +4276,14 @@ __init int intel_pmu_init(void) x86_pmu.hw_config = hsw_hw_config; x86_pmu.get_event_constraints = hsw_get_event_constraints; - x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr, - skl_format_attr); - WARN_ON(!x86_pmu.format_attrs); + extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? + hsw_format_attr : nhm_format_attr; + extra_attr = merge_attr(extra_attr, skl_format_attr); x86_pmu.cpu_events = hsw_events_attrs; + intel_pmu_pebs_data_source_skl( + boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X); pr_cont("Skylake events, "); + name = "skylake"; break; default: @@ -4215,6 +4291,7 @@ __init int intel_pmu_init(void) case 1: x86_pmu.event_constraints = intel_v1_event_constraints; pr_cont("generic architected perfmon v1, "); + name = "generic_arch_v1"; break; default: /* @@ -4222,10 +4299,19 @@ __init int intel_pmu_init(void) */ x86_pmu.event_constraints = intel_gen_event_constraints; pr_cont("generic architected perfmon, "); + name = "generic_arch_v2+"; break; } } + snprintf(pmu_name_str, sizeof pmu_name_str, "%s", name); + + if (version >= 2 && extra_attr) { + x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr, + extra_attr); + WARN_ON(!x86_pmu.format_attrs); + } + if (x86_pmu.num_counters > INTEL_PMC_MAX_GENERIC) { WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!", x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC); @@ -4272,8 +4358,13 @@ __init int intel_pmu_init(void) x86_pmu.lbr_nr = 0; } - if (x86_pmu.lbr_nr) + x86_pmu.caps_attrs = intel_pmu_caps_attrs; + + if (x86_pmu.lbr_nr) { + x86_pmu.caps_attrs = merge_attr(x86_pmu.caps_attrs, lbr_attrs); pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr); + } + /* * Access extra MSR may cause #GP under certain circumstances. * E.g. KVM doesn't support offcore event diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index a322fed5f8ed..e1965e5ff570 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -49,34 +49,47 @@ union intel_x86_pebs_dse { */ #define P(a, b) PERF_MEM_S(a, b) #define OP_LH (P(OP, LOAD) | P(LVL, HIT)) +#define LEVEL(x) P(LVLNUM, x) +#define REM P(REMOTE, REMOTE) #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS)) /* Version for Sandy Bridge and later */ static u64 pebs_data_source[] = { - P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ - OP_LH | P(LVL, L1) | P(SNOOP, NONE), /* 0x01: L1 local */ - OP_LH | P(LVL, LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ - OP_LH | P(LVL, L2) | P(SNOOP, NONE), /* 0x03: L2 hit */ - OP_LH | P(LVL, L3) | P(SNOOP, NONE), /* 0x04: L3 hit */ - OP_LH | P(LVL, L3) | P(SNOOP, MISS), /* 0x05: L3 hit, snoop miss */ - OP_LH | P(LVL, L3) | P(SNOOP, HIT), /* 0x06: L3 hit, snoop hit */ - OP_LH | P(LVL, L3) | P(SNOOP, HITM), /* 0x07: L3 hit, snoop hitm */ - OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HIT), /* 0x08: L3 miss snoop hit */ - OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HITM), /* 0x09: L3 miss snoop hitm*/ - OP_LH | P(LVL, LOC_RAM) | P(SNOOP, HIT), /* 0x0a: L3 miss, shared */ - OP_LH | P(LVL, REM_RAM1) | P(SNOOP, HIT), /* 0x0b: L3 miss, shared */ - OP_LH | P(LVL, LOC_RAM) | SNOOP_NONE_MISS,/* 0x0c: L3 miss, excl */ - OP_LH | P(LVL, REM_RAM1) | SNOOP_NONE_MISS,/* 0x0d: L3 miss, excl */ - OP_LH | P(LVL, IO) | P(SNOOP, NONE), /* 0x0e: I/O */ - OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */ + P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ + OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x01: L1 local */ + OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ + OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* 0x03: L2 hit */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* 0x04: L3 hit */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, MISS), /* 0x05: L3 hit, snoop miss */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT), /* 0x06: L3 hit, snoop hit */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* 0x07: L3 hit, snoop hitm */ + OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HIT), /* 0x08: L3 miss snoop hit */ + OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM), /* 0x09: L3 miss snoop hitm*/ + OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, HIT), /* 0x0a: L3 miss, shared */ + OP_LH | P(LVL, REM_RAM1) | REM | LEVEL(L3) | P(SNOOP, HIT), /* 0x0b: L3 miss, shared */ + OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | SNOOP_NONE_MISS, /* 0x0c: L3 miss, excl */ + OP_LH | P(LVL, REM_RAM1) | LEVEL(RAM) | REM | SNOOP_NONE_MISS, /* 0x0d: L3 miss, excl */ + OP_LH | P(LVL, IO) | LEVEL(NA) | P(SNOOP, NONE), /* 0x0e: I/O */ + OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE), /* 0x0f: uncached */ }; /* Patch up minor differences in the bits */ void __init intel_pmu_pebs_data_source_nhm(void) { - pebs_data_source[0x05] = OP_LH | P(LVL, L3) | P(SNOOP, HIT); - pebs_data_source[0x06] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); - pebs_data_source[0x07] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); + pebs_data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT); + pebs_data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM); + pebs_data_source[0x07] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM); +} + +void __init intel_pmu_pebs_data_source_skl(bool pmem) +{ + u64 pmem_or_l4 = pmem ? LEVEL(PMEM) : LEVEL(L4); + + pebs_data_source[0x08] = OP_LH | pmem_or_l4 | P(SNOOP, HIT); + pebs_data_source[0x09] = OP_LH | pmem_or_l4 | REM | P(SNOOP, HIT); + pebs_data_source[0x0b] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE); + pebs_data_source[0x0c] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOPX, FWD); + pebs_data_source[0x0d] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOP, HITM); } static u64 precise_store_data(u64 status) @@ -149,8 +162,6 @@ static u64 load_latency_data(u64 status) { union intel_x86_pebs_dse dse; u64 val; - int model = boot_cpu_data.x86_model; - int fam = boot_cpu_data.x86; dse.val = status; @@ -162,8 +173,7 @@ static u64 load_latency_data(u64 status) /* * Nehalem models do not support TLB, Lock infos */ - if (fam == 0x6 && (model == 26 || model == 30 - || model == 31 || model == 46)) { + if (x86_pmu.pebs_no_tlb) { val |= P(TLB, NA) | P(LOCK, NA); return val; } @@ -1175,7 +1185,7 @@ static void setup_pebs_sample_data(struct perf_event *event, else regs->flags &= ~PERF_EFLAGS_EXACT; - if ((sample_type & PERF_SAMPLE_ADDR) && + if ((sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) && x86_pmu.intel_cap.pebs_format >= 1) data->addr = pebs->dla; diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 955457a30197..8a6bbacd17dc 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -109,6 +109,9 @@ enum { X86_BR_ZERO_CALL = 1 << 15,/* zero length call */ X86_BR_CALL_STACK = 1 << 16,/* call stack */ X86_BR_IND_JMP = 1 << 17,/* indirect jump */ + + X86_BR_TYPE_SAVE = 1 << 18,/* indicate to save branch type */ + }; #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) @@ -514,6 +517,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) cpuc->lbr_entries[i].in_tx = 0; cpuc->lbr_entries[i].abort = 0; cpuc->lbr_entries[i].cycles = 0; + cpuc->lbr_entries[i].type = 0; cpuc->lbr_entries[i].reserved = 0; } cpuc->lbr_stack.nr = i; @@ -600,6 +604,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) cpuc->lbr_entries[out].in_tx = in_tx; cpuc->lbr_entries[out].abort = abort; cpuc->lbr_entries[out].cycles = cycles; + cpuc->lbr_entries[out].type = 0; cpuc->lbr_entries[out].reserved = 0; out++; } @@ -677,6 +682,10 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_CALL) mask |= X86_BR_CALL | X86_BR_ZERO_CALL; + + if (br_type & PERF_SAMPLE_BRANCH_TYPE_SAVE) + mask |= X86_BR_TYPE_SAVE; + /* * stash actual user request into reg, it may * be used by fixup code for some CPU @@ -930,6 +939,43 @@ static int branch_type(unsigned long from, unsigned long to, int abort) return ret; } +#define X86_BR_TYPE_MAP_MAX 16 + +static int branch_map[X86_BR_TYPE_MAP_MAX] = { + PERF_BR_CALL, /* X86_BR_CALL */ + PERF_BR_RET, /* X86_BR_RET */ + PERF_BR_SYSCALL, /* X86_BR_SYSCALL */ + PERF_BR_SYSRET, /* X86_BR_SYSRET */ + PERF_BR_UNKNOWN, /* X86_BR_INT */ + PERF_BR_UNKNOWN, /* X86_BR_IRET */ + PERF_BR_COND, /* X86_BR_JCC */ + PERF_BR_UNCOND, /* X86_BR_JMP */ + PERF_BR_UNKNOWN, /* X86_BR_IRQ */ + PERF_BR_IND_CALL, /* X86_BR_IND_CALL */ + PERF_BR_UNKNOWN, /* X86_BR_ABORT */ + PERF_BR_UNKNOWN, /* X86_BR_IN_TX */ + PERF_BR_UNKNOWN, /* X86_BR_NO_TX */ + PERF_BR_CALL, /* X86_BR_ZERO_CALL */ + PERF_BR_UNKNOWN, /* X86_BR_CALL_STACK */ + PERF_BR_IND, /* X86_BR_IND_JMP */ +}; + +static int +common_branch_type(int type) +{ + int i; + + type >>= 2; /* skip X86_BR_USER and X86_BR_KERNEL */ + + if (type) { + i = __ffs(type); + if (i < X86_BR_TYPE_MAP_MAX) + return branch_map[i]; + } + + return PERF_BR_UNKNOWN; +} + /* * implement actual branch filter based on user demand. * Hardware may not exactly satisfy that request, thus @@ -946,7 +992,8 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) bool compress = false; /* if sampling all branches, then nothing to filter */ - if ((br_sel & X86_BR_ALL) == X86_BR_ALL) + if (((br_sel & X86_BR_ALL) == X86_BR_ALL) && + ((br_sel & X86_BR_TYPE_SAVE) != X86_BR_TYPE_SAVE)) return; for (i = 0; i < cpuc->lbr_stack.nr; i++) { @@ -967,6 +1014,9 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) cpuc->lbr_entries[i].from = 0; compress = true; } + + if ((br_sel & X86_BR_TYPE_SAVE) == X86_BR_TYPE_SAVE) + cpuc->lbr_entries[i].type = common_branch_type(type); } if (!compress) diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c index eb0533558c2b..d32c0eed38ca 100644 --- a/arch/x86/events/intel/p4.c +++ b/arch/x86/events/intel/p4.c @@ -587,7 +587,7 @@ static __initconst const u64 p4_hw_cache_event_ids * P4_CONFIG_ALIASABLE or bits for P4_PEBS_METRIC, they are * either up to date automatically or not applicable at all. */ -struct p4_event_alias { +static struct p4_event_alias { u64 original; u64 alternative; } p4_event_aliases[] = { diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index ae8324d65e61..81fd41d5a0d9 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -471,8 +471,9 @@ static void pt_config(struct perf_event *event) struct pt *pt = this_cpu_ptr(&pt_ctx); u64 reg; - if (!event->hw.itrace_started) { - event->hw.itrace_started = 1; + /* First round: clear STATUS, in particular the PSB byte counter. */ + if (!event->hw.config) { + perf_event_itrace_started(event); wrmsrl(MSR_IA32_RTIT_STATUS, 0); } diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index a45e2114a846..8e2457cb6b4a 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -559,7 +559,7 @@ static struct attribute_group rapl_pmu_format_group = { .attrs = rapl_formats_attr, }; -const struct attribute_group *rapl_attr_groups[] = { +static const struct attribute_group *rapl_attr_groups[] = { &rapl_pmu_attr_group, &rapl_pmu_format_group, &rapl_pmu_events_group, diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 44ec523287f6..1c5390f1cf09 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -721,7 +721,7 @@ static struct attribute *uncore_pmu_attrs[] = { NULL, }; -static struct attribute_group uncore_pmu_attr_group = { +static const struct attribute_group uncore_pmu_attr_group = { .attrs = uncore_pmu_attrs, }; diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c index cda569332005..6a5cbe90f859 100644 --- a/arch/x86/events/intel/uncore_nhmex.c +++ b/arch/x86/events/intel/uncore_nhmex.c @@ -272,7 +272,7 @@ static struct attribute *nhmex_uncore_ubox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_ubox_format_group = { +static const struct attribute_group nhmex_uncore_ubox_format_group = { .name = "format", .attrs = nhmex_uncore_ubox_formats_attr, }; @@ -299,7 +299,7 @@ static struct attribute *nhmex_uncore_cbox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_cbox_format_group = { +static const struct attribute_group nhmex_uncore_cbox_format_group = { .name = "format", .attrs = nhmex_uncore_cbox_formats_attr, }; @@ -407,7 +407,7 @@ static struct attribute *nhmex_uncore_bbox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_bbox_format_group = { +static const struct attribute_group nhmex_uncore_bbox_format_group = { .name = "format", .attrs = nhmex_uncore_bbox_formats_attr, }; @@ -484,7 +484,7 @@ static struct attribute *nhmex_uncore_sbox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_sbox_format_group = { +static const struct attribute_group nhmex_uncore_sbox_format_group = { .name = "format", .attrs = nhmex_uncore_sbox_formats_attr, }; @@ -898,7 +898,7 @@ static struct attribute *nhmex_uncore_mbox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_mbox_format_group = { +static const struct attribute_group nhmex_uncore_mbox_format_group = { .name = "format", .attrs = nhmex_uncore_mbox_formats_attr, }; @@ -1163,7 +1163,7 @@ static struct attribute *nhmex_uncore_rbox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_rbox_format_group = { +static const struct attribute_group nhmex_uncore_rbox_format_group = { .name = "format", .attrs = nhmex_uncore_rbox_formats_attr, }; diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index a3dcc12bef4a..db1127ce685e 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -130,7 +130,7 @@ static struct attribute *snb_uncore_formats_attr[] = { NULL, }; -static struct attribute_group snb_uncore_format_group = { +static const struct attribute_group snb_uncore_format_group = { .name = "format", .attrs = snb_uncore_formats_attr, }; @@ -289,7 +289,7 @@ static struct attribute *snb_uncore_imc_formats_attr[] = { NULL, }; -static struct attribute_group snb_uncore_imc_format_group = { +static const struct attribute_group snb_uncore_imc_format_group = { .name = "format", .attrs = snb_uncore_imc_formats_attr, }; @@ -769,7 +769,7 @@ static struct attribute *nhm_uncore_formats_attr[] = { NULL, }; -static struct attribute_group nhm_uncore_format_group = { +static const struct attribute_group nhm_uncore_format_group = { .name = "format", .attrs = nhm_uncore_formats_attr, }; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index dae2fedc1601..db1fe377e6dd 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"); @@ -603,27 +602,27 @@ static struct uncore_event_desc snbep_uncore_qpi_events[] = { { /* end: all zeroes */ }, }; -static struct attribute_group snbep_uncore_format_group = { +static const struct attribute_group snbep_uncore_format_group = { .name = "format", .attrs = snbep_uncore_formats_attr, }; -static struct attribute_group snbep_uncore_ubox_format_group = { +static const struct attribute_group snbep_uncore_ubox_format_group = { .name = "format", .attrs = snbep_uncore_ubox_formats_attr, }; -static struct attribute_group snbep_uncore_cbox_format_group = { +static const struct attribute_group snbep_uncore_cbox_format_group = { .name = "format", .attrs = snbep_uncore_cbox_formats_attr, }; -static struct attribute_group snbep_uncore_pcu_format_group = { +static const struct attribute_group snbep_uncore_pcu_format_group = { .name = "format", .attrs = snbep_uncore_pcu_formats_attr, }; -static struct attribute_group snbep_uncore_qpi_format_group = { +static const struct attribute_group snbep_uncore_qpi_format_group = { .name = "format", .attrs = snbep_uncore_qpi_formats_attr, }; @@ -1432,27 +1431,27 @@ static struct attribute *ivbep_uncore_qpi_formats_attr[] = { NULL, }; -static struct attribute_group ivbep_uncore_format_group = { +static const struct attribute_group ivbep_uncore_format_group = { .name = "format", .attrs = ivbep_uncore_formats_attr, }; -static struct attribute_group ivbep_uncore_ubox_format_group = { +static const struct attribute_group ivbep_uncore_ubox_format_group = { .name = "format", .attrs = ivbep_uncore_ubox_formats_attr, }; -static struct attribute_group ivbep_uncore_cbox_format_group = { +static const struct attribute_group ivbep_uncore_cbox_format_group = { .name = "format", .attrs = ivbep_uncore_cbox_formats_attr, }; -static struct attribute_group ivbep_uncore_pcu_format_group = { +static const struct attribute_group ivbep_uncore_pcu_format_group = { .name = "format", .attrs = ivbep_uncore_pcu_formats_attr, }; -static struct attribute_group ivbep_uncore_qpi_format_group = { +static const struct attribute_group ivbep_uncore_qpi_format_group = { .name = "format", .attrs = ivbep_uncore_qpi_formats_attr, }; @@ -1888,7 +1887,7 @@ static struct attribute *knl_uncore_ubox_formats_attr[] = { NULL, }; -static struct attribute_group knl_uncore_ubox_format_group = { +static const struct attribute_group knl_uncore_ubox_format_group = { .name = "format", .attrs = knl_uncore_ubox_formats_attr, }; @@ -1928,7 +1927,7 @@ static struct attribute *knl_uncore_cha_formats_attr[] = { NULL, }; -static struct attribute_group knl_uncore_cha_format_group = { +static const struct attribute_group knl_uncore_cha_format_group = { .name = "format", .attrs = knl_uncore_cha_formats_attr, }; @@ -2038,7 +2037,7 @@ static struct attribute *knl_uncore_pcu_formats_attr[] = { NULL, }; -static struct attribute_group knl_uncore_pcu_format_group = { +static const struct attribute_group knl_uncore_pcu_format_group = { .name = "format", .attrs = knl_uncore_pcu_formats_attr, }; @@ -2188,7 +2187,7 @@ static struct attribute *knl_uncore_irp_formats_attr[] = { NULL, }; -static struct attribute_group knl_uncore_irp_format_group = { +static const struct attribute_group knl_uncore_irp_format_group = { .name = "format", .attrs = knl_uncore_irp_formats_attr, }; @@ -2386,7 +2385,7 @@ static struct attribute *hswep_uncore_ubox_formats_attr[] = { NULL, }; -static struct attribute_group hswep_uncore_ubox_format_group = { +static const struct attribute_group hswep_uncore_ubox_format_group = { .name = "format", .attrs = hswep_uncore_ubox_formats_attr, }; @@ -2440,7 +2439,7 @@ static struct attribute *hswep_uncore_cbox_formats_attr[] = { NULL, }; -static struct attribute_group hswep_uncore_cbox_format_group = { +static const struct attribute_group hswep_uncore_cbox_format_group = { .name = "format", .attrs = hswep_uncore_cbox_formats_attr, }; @@ -2622,7 +2621,7 @@ static struct attribute *hswep_uncore_sbox_formats_attr[] = { NULL, }; -static struct attribute_group hswep_uncore_sbox_format_group = { +static const struct attribute_group hswep_uncore_sbox_format_group = { .name = "format", .attrs = hswep_uncore_sbox_formats_attr, }; @@ -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, @@ -3312,12 +3310,11 @@ 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, }; -static struct attribute_group skx_uncore_chabox_format_group = { +static const struct attribute_group skx_uncore_chabox_format_group = { .name = "format", .attrs = skx_uncore_cha_formats_attr, }; @@ -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; } @@ -3416,7 +3427,7 @@ static struct attribute *skx_uncore_iio_formats_attr[] = { NULL, }; -static struct attribute_group skx_uncore_iio_format_group = { +static const struct attribute_group skx_uncore_iio_format_group = { .name = "format", .attrs = skx_uncore_iio_formats_attr, }; @@ -3473,7 +3484,7 @@ static struct attribute *skx_uncore_formats_attr[] = { NULL, }; -static struct attribute_group skx_uncore_format_group = { +static const struct attribute_group skx_uncore_format_group = { .name = "format", .attrs = skx_uncore_formats_attr, }; @@ -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[] = { @@ -3574,7 +3605,7 @@ static struct attribute *skx_upi_uncore_formats_attr[] = { NULL, }; -static struct attribute_group skx_upi_uncore_format_group = { +static const struct attribute_group skx_upi_uncore_format_group = { .name = "format", .attrs = skx_upi_uncore_formats_attr, }; @@ -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 476aec3a4cab..4196f81ec0e1 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -91,7 +91,7 @@ struct amd_nb { (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \ PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \ PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \ - PERF_SAMPLE_TRANSACTION) + PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR) /* * A debug store configuration. @@ -558,6 +558,7 @@ struct x86_pmu { int attr_rdpmc; struct attribute **format_attrs; struct attribute **event_attrs; + struct attribute **caps_attrs; ssize_t (*events_sysfs_show)(char *page, u64 config); struct attribute **cpu_events; @@ -591,7 +592,8 @@ struct x86_pmu { pebs :1, pebs_active :1, pebs_broken :1, - pebs_prec_dist :1; + pebs_prec_dist :1, + pebs_no_tlb :1; int pebs_record_size; int pebs_buffer_size; void (*drain_pebs)(struct pt_regs *regs); @@ -741,6 +743,8 @@ int x86_reserve_hardware(void); void x86_release_hardware(void); +int x86_pmu_max_precise(void); + void hw_perf_lbr_event_destroy(struct perf_event *event); int x86_setup_perfctr(struct perf_event *event); @@ -947,6 +951,8 @@ void intel_pmu_lbr_init_knl(void); void intel_pmu_pebs_data_source_nhm(void); +void intel_pmu_pebs_data_source_skl(bool pmem); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index ca3c48c0872f..8ea315a11fe0 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -177,7 +177,7 @@ #define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ #define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */ #define X86_FEATURE_PTSC ( 6*32+27) /* performance time-stamp counter */ -#define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */ +#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */ #define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */ /* @@ -286,7 +286,7 @@ #define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ -#define X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE (15*32+15) /* Virtual VMLOAD VMSAVE */ +#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 1c18d83d3f09..9aeb91935ce0 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -247,11 +247,11 @@ extern int force_personality32; /* * This is the base location for PIE (ET_DYN with INTERP) loads. On - * 64-bit, this is raised to 4GB to leave the entire 32-bit address + * 64-bit, this is above 4GB to leave the entire 32-bit address * space open for things that want to use the area for 32-bit pointers. */ #define ELF_ET_DYN_BASE (mmap_is_ia32() ? 0x000400000UL : \ - 0x100000000UL) + (TASK_SIZE / 3 * 2)) /* This yields a mask that user programs can use to figure out what instruction set this CPU supports. This could be done in user space, 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/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 255645f60ca2..554cdb205d17 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -450,10 +450,10 @@ static inline int copy_fpregs_to_fpstate(struct fpu *fpu) return 0; } -static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate) +static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask) { if (use_xsave()) { - copy_kernel_to_xregs(&fpstate->xsave, -1); + copy_kernel_to_xregs(&fpstate->xsave, mask); } else { if (use_fxsr()) copy_kernel_to_fxregs(&fpstate->fxsave); @@ -477,7 +477,7 @@ static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate) : : [addr] "m" (fpstate)); } - __copy_kernel_to_fpregs(fpstate); + __copy_kernel_to_fpregs(fpstate, -1); } extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); 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/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 21126155a739..0ead9dbb9130 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -43,6 +43,9 @@ struct hypervisor_x86 { /* pin current vcpu to specified physical cpu (run rarely) */ void (*pin_vcpu)(int); + + /* called during init_mem_mapping() to setup early mappings. */ + void (*init_mem_mapping)(void); }; extern const struct hypervisor_x86 *x86_hyper; @@ -57,8 +60,15 @@ extern const struct hypervisor_x86 x86_hyper_kvm; extern void init_hypervisor_platform(void); extern bool hypervisor_x2apic_available(void); extern void hypervisor_pin_vcpu(int cpu); + +static inline void hypervisor_init_mem_mapping(void) +{ + if (x86_hyper && x86_hyper->init_mem_mapping) + x86_hyper->init_mem_mapping(); +} #else static inline void init_hypervisor_platform(void) { } static inline bool hypervisor_x2apic_available(void) { return false; } +static inline void hypervisor_init_mem_mapping(void) { } #endif /* CONFIG_HYPERVISOR_GUEST */ #endif /* _ASM_X86_HYPERVISOR_H */ 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/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 87ac4fba6d8e..92c9032502d8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -492,6 +492,7 @@ struct kvm_vcpu_arch { unsigned long cr4; unsigned long cr4_guest_owned_bits; unsigned long cr8; + u32 pkru; u32 hflags; u64 efer; u64 apic_base; @@ -1374,8 +1375,6 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); -void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, - unsigned long address); void kvm_define_shared_msr(unsigned index, u32 msr); int kvm_set_shared_msr(unsigned index, u64 val, u64 mask); diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 265c907d7d4c..7a234be7e298 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -140,9 +140,7 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.execute_only_pkey = -1; } #endif - init_new_context_ldt(tsk, mm); - - return 0; + return init_new_context_ldt(tsk, mm); } static inline void destroy_context(struct mm_struct *mm) { diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index d869c8671e36..0ee83321a313 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 @@ -33,13 +38,18 @@ 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); + unsigned long flags; - /* 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; + local_irq_save(flags); rdmsrl(MSR_IA32_APERF, aperf); rdmsrl(MSR_IA32_MPERF, mperf); + local_irq_restore(flags); aperf_delta = aperf - s->aperf; mperf_delta = mperf - s->mperf; @@ -51,22 +61,21 @@ 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 +83,12 @@ 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/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index d7cc190ae457..f7370abd33c6 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -122,7 +122,7 @@ static struct attribute *thermal_throttle_attrs[] = { NULL }; -static struct attribute_group thermal_attr_group = { +static const struct attribute_group thermal_attr_group = { .attrs = thermal_throttle_attrs, .name = "thermal_throttle" }; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 9cb98ee103db..86e8f0b2537b 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -561,7 +561,7 @@ static struct attribute *mc_default_attrs[] = { NULL }; -static struct attribute_group mc_attr_group = { +static const struct attribute_group mc_attr_group = { .attrs = mc_default_attrs, .name = "microcode", }; @@ -707,7 +707,7 @@ static struct attribute *cpu_root_microcode_attrs[] = { NULL }; -static struct attribute_group cpu_root_microcode_group = { +static const struct attribute_group cpu_root_microcode_group = { .name = "microcode", .attrs = cpu_root_microcode_attrs, }; diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index c5bb63be4ba1..40d5a8a75212 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -237,6 +237,18 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ stop_machine(mtrr_rendezvous_handler, &data, cpu_online_mask); } +static void set_mtrr_cpuslocked(unsigned int reg, unsigned long base, + unsigned long size, mtrr_type type) +{ + struct set_mtrr_data data = { .smp_reg = reg, + .smp_base = base, + .smp_size = size, + .smp_type = type + }; + + stop_machine_cpuslocked(mtrr_rendezvous_handler, &data, cpu_online_mask); +} + static void set_mtrr_from_inactive_cpu(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type) { @@ -370,7 +382,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, /* Search for an empty MTRR */ i = mtrr_if->get_free_region(base, size, replace); if (i >= 0) { - set_mtrr(i, base, size, type); + set_mtrr_cpuslocked(i, base, size, type); if (likely(replace < 0)) { mtrr_usage_table[i] = 1; } else { @@ -378,7 +390,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, if (increment) mtrr_usage_table[i]++; if (unlikely(replace != i)) { - set_mtrr(replace, 0, 0, 0); + set_mtrr_cpuslocked(replace, 0, 0, 0); mtrr_usage_table[replace] = 0; } } @@ -506,7 +518,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) goto out; } if (--mtrr_usage_table[reg] < 1) - set_mtrr(reg, 0, 0, 0); + set_mtrr_cpuslocked(reg, 0, 0, 0); error = reg; out: mutex_unlock(&mtrr_mutex); diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index d907c3d8633f..a4516ca4c4f3 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -527,6 +527,7 @@ static const struct pci_device_id intel_early_ids[] __initconst = { INTEL_BXT_IDS(&gen9_early_ops), INTEL_KBL_IDS(&gen9_early_ops), INTEL_GLK_IDS(&gen9_early_ops), + INTEL_CNL_IDS(&gen9_early_ops), }; static void __init diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 46c3c73e7f43..9ba79543d9ee 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -53,6 +53,7 @@ void __head __startup_64(unsigned long physaddr) pudval_t *pud; pmdval_t *pmd, pmd_entry; int i; + unsigned int *next_pgt_ptr; /* Is the address too large? */ if (physaddr >> MAX_PHYSMEM_BITS) @@ -91,9 +92,9 @@ void __head __startup_64(unsigned long physaddr) * creates a bunch of nonsense entries but that is fine -- * it avoids problems around wraparound. */ - - pud = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); - pmd = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + next_pgt_ptr = fixup_pointer(&next_early_pgt, physaddr); + pud = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); + pmd = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); if (IS_ENABLED(CONFIG_X86_5LEVEL)) { p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); 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/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 69ea0bc1cfa3..4f98aad38237 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -39,6 +39,7 @@ #include <asm/insn.h> #include <asm/debugreg.h> #include <asm/set_memory.h> +#include <asm/sections.h> #include "common.h" @@ -251,10 +252,12 @@ static int can_optimize(unsigned long paddr) /* * Do not optimize in the entry code due to the unstable - * stack handling. + * stack handling and registers setup. */ - if ((paddr >= (unsigned long)__entry_text_start) && - (paddr < (unsigned long)__entry_text_end)) + if (((paddr >= (unsigned long)__entry_text_start) && + (paddr < (unsigned long)__entry_text_end)) || + ((paddr >= (unsigned long)__irqentry_text_start) && + (paddr < (unsigned long)__irqentry_text_end))) return 0; /* Check there is enough space for a relative jump. */ diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index 4afc67f5facc..06e1ff5562c0 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -55,7 +55,7 @@ static struct bin_attribute *boot_params_data_attrs[] = { NULL, }; -static struct attribute_group boot_params_attr_group = { +static const struct attribute_group boot_params_attr_group = { .attrs = boot_params_version_attrs, .bin_attrs = boot_params_data_attrs, }; @@ -202,7 +202,7 @@ static struct bin_attribute *setup_data_data_attrs[] = { NULL, }; -static struct attribute_group setup_data_attr_group = { +static const struct attribute_group setup_data_attr_group = { .attrs = setup_data_type_attrs, .bin_attrs = setup_data_data_attrs, }; 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/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index b474c8de7fba..54b9e89d4d6b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -971,7 +971,8 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle) * Returns zero if CPU booted OK, else error code from * ->wakeup_secondary_cpu. */ -static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) +static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, + int *cpu0_nmi_registered) { volatile u32 *trampoline_status = (volatile u32 *) __va(real_mode_header->trampoline_status); @@ -979,7 +980,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) unsigned long start_ip = real_mode_header->trampoline_start; unsigned long boot_error = 0; - int cpu0_nmi_registered = 0; unsigned long timeout; idle->thread.sp = (unsigned long)task_pt_regs(idle); @@ -1035,7 +1035,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) boot_error = apic->wakeup_secondary_cpu(apicid, start_ip); else boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid, - &cpu0_nmi_registered); + cpu0_nmi_registered); if (!boot_error) { /* @@ -1080,12 +1080,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) */ smpboot_restore_warm_reset_vector(); } - /* - * Clean up the nmi handler. Do this after the callin and callout sync - * to avoid impact of possible long unregister time. - */ - if (cpu0_nmi_registered) - unregister_nmi_handler(NMI_LOCAL, "wake_cpu0"); return boot_error; } @@ -1093,8 +1087,9 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) int native_cpu_up(unsigned int cpu, struct task_struct *tidle) { int apicid = apic->cpu_present_to_apicid(cpu); + int cpu0_nmi_registered = 0; unsigned long flags; - int err; + int err, ret = 0; WARN_ON(irqs_disabled()); @@ -1131,10 +1126,11 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) common_cpu_up(cpu, tidle); - err = do_boot_cpu(apicid, cpu, tidle); + err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered); if (err) { pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu); - return -EIO; + ret = -EIO; + goto unreg_nmi; } /* @@ -1150,7 +1146,15 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) touch_nmi_watchdog(); } - return 0; +unreg_nmi: + /* + * Clean up the nmi handler. Do this after the callin and callout sync + * to avoid impact of possible long unregister time. + */ + if (cpu0_nmi_registered) + unregister_nmi_handler(NMI_LOCAL, "wake_cpu0"); + + return ret; } /** diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index b9389d72b2f7..c29e5bc7e9c9 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -91,10 +91,8 @@ static bool in_entry_code(unsigned long ip) if (addr >= __entry_text_start && addr < __entry_text_end) return true; -#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) if (addr >= __irqentry_text_start && addr < __irqentry_text_end) return true; -#endif return false; } diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 59ca2eea522c..19adbb418443 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -469,7 +469,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; cpuid_mask(&entry->ecx, CPUID_7_ECX); /* PKU is not yet implemented for shadow paging. */ - if (!tdp_enabled) + if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); entry->edx &= kvm_cpuid_7_0_edx_x86_features; entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX); diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 762cdf2595f9..e1e89ee4af75 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -84,11 +84,6 @@ static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu) | ((u64)(kvm_register_read(vcpu, VCPU_REGS_RDX) & -1u) << 32); } -static inline u32 kvm_read_pkru(struct kvm_vcpu *vcpu) -{ - return kvm_x86_ops->get_pkru(vcpu); -} - static inline void enter_guest_mode(struct kvm_vcpu *vcpu) { vcpu->arch.hflags |= HF_GUEST_MASK; 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/mmu.h b/arch/x86/kvm/mmu.h index d7d248a000dd..4b9a3ae6b725 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -185,7 +185,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, * index of the protection domain, so pte_pkey * 2 is * is the index of the first bit for the domain. */ - pkru_bits = (kvm_read_pkru(vcpu) >> (pte_pkey * 2)) & 3; + pkru_bits = (vcpu->arch.pkru >> (pte_pkey * 2)) & 3; /* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */ offset = (pfec & ~1) + diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 4d8141e533c3..af256b786a70 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1100,7 +1100,7 @@ static __init int svm_hardware_setup(void) if (vls) { if (!npt_enabled || - !boot_cpu_has(X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE) || + !boot_cpu_has(X86_FEATURE_V_VMSAVE_VMLOAD) || !IS_ENABLED(CONFIG_X86_64)) { vls = false; } else { @@ -1777,11 +1777,6 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) to_svm(vcpu)->vmcb->save.rflags = rflags; } -static u32 svm_get_pkru(struct kvm_vcpu *vcpu) -{ - return 0; -} - static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { switch (reg) { @@ -2430,6 +2425,16 @@ 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 @@ -5403,8 +5408,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, - .get_pkru = svm_get_pkru, - .tlb_flush = svm_flush_tlb, .run = svm_vcpu_run, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 29fd8af5c347..c6ef2940119b 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -416,13 +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; /* @@ -563,7 +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; @@ -640,8 +636,6 @@ struct vcpu_vmx { u64 current_tsc_ratio; - bool guest_pkru_valid; - u32 guest_pkru; u32 host_pkru; /* @@ -928,6 +922,10 @@ 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); @@ -2383,11 +2381,6 @@ static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) to_vmx(vcpu)->emulation_required = emulation_required(vcpu); } -static u32 vmx_get_pkru(struct kvm_vcpu *vcpu) -{ - return to_vmx(vcpu)->guest_pkru; -} - static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) { u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); @@ -2429,6 +2422,30 @@ 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. @@ -2438,23 +2455,38 @@ 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) @@ -2668,7 +2700,7 @@ 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. */ @@ -4956,6 +4988,28 @@ 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); @@ -4963,18 +5017,15 @@ 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); @@ -4986,11 +5037,16 @@ 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); @@ -5008,8 +5064,7 @@ 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 @@ -5024,7 +5079,7 @@ 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. @@ -5058,7 +5113,7 @@ 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); } @@ -7133,34 +7188,32 @@ 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; } /* @@ -7174,12 +7227,14 @@ 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; @@ -7578,14 +7633,14 @@ 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); } @@ -8018,12 +8073,11 @@ 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), @@ -8032,6 +8086,18 @@ 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; @@ -8168,6 +8234,29 @@ 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); @@ -8414,12 +8503,8 @@ 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(); @@ -8928,8 +9013,10 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); - if (vmx->guest_pkru_valid) - __write_pkru(vmx->guest_pkru); + if (static_cpu_has(X86_FEATURE_PKU) && + kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && + vcpu->arch.pkru != vmx->host_pkru) + __write_pkru(vcpu->arch.pkru); atomic_switch_perf_msrs(vmx); debugctlmsr = get_debugctlmsr(); @@ -9077,13 +9164,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * back on host, so it is safe to read guest PKRU from current * XSAVE. */ - if (boot_cpu_has(X86_FEATURE_OSPKE)) { - vmx->guest_pkru = __read_pkru(); - if (vmx->guest_pkru != vmx->host_pkru) { - vmx->guest_pkru_valid = true; + if (static_cpu_has(X86_FEATURE_PKU) && + kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) { + vcpu->arch.pkru = __read_pkru(); + if (vcpu->arch.pkru != vmx->host_pkru) __write_pkru(vmx->host_pkru); - } else - vmx->guest_pkru_valid = false; } /* @@ -9222,7 +9307,6 @@ 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; @@ -9508,12 +9592,15 @@ 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, @@ -10041,6 +10128,8 @@ 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); } @@ -10065,13 +10154,9 @@ 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; } @@ -10095,12 +10180,6 @@ 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); @@ -10848,13 +10927,8 @@ 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); @@ -10942,7 +11016,9 @@ 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); @@ -11048,8 +11124,15 @@ 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 | @@ -11592,8 +11675,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, - .get_pkru = vmx_get_pkru, - .tlb_flush = vmx_flush_tlb, .run = vmx_vcpu_run, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 82a63c59f77b..272320eb328c 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) & ~31ul) >> PAGE_SHIFT; - offset = (kvm_read_cr3(vcpu) & ~31ul) & (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); + } } } @@ -3242,7 +3245,12 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) u32 size, offset, ecx, edx; cpuid_count(XSTATE_CPUID, index, &size, &offset, &ecx, &edx); - memcpy(dest + offset, src, size); + if (feature == XFEATURE_MASK_PKRU) + memcpy(dest + offset, &vcpu->arch.pkru, + sizeof(vcpu->arch.pkru)); + else + memcpy(dest + offset, src, size); + } valid -= feature; @@ -3280,7 +3288,11 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) u32 size, offset, ecx, edx; cpuid_count(XSTATE_CPUID, index, &size, &offset, &ecx, &edx); - memcpy(dest, src + offset, size); + if (feature == XFEATURE_MASK_PKRU) + memcpy(&vcpu->arch.pkru, src + offset, + sizeof(vcpu->arch.pkru)); + else + memcpy(dest, src + offset, size); } valid -= feature; @@ -6215,6 +6227,7 @@ 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; @@ -6721,17 +6734,6 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page); -void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, - unsigned long address) -{ - /* - * The physical address of apic access page is stored in the VMCS. - * Update it when it becomes invalid. - */ - if (address == gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT)) - kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); -} - /* * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the @@ -7629,7 +7631,9 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) */ vcpu->guest_fpu_loaded = 1; __kernel_fpu_begin(); - __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state); + /* PKRU is separately restored in kvm_x86_ops->run. */ + __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state, + ~XFEATURE_MASK_PKRU); trace_kvm_fpu(1); } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 673541eb3b3f..bf3f1065d6ad 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -18,6 +18,7 @@ #include <asm/dma.h> /* for MAX_DMA_PFN */ #include <asm/microcode.h> #include <asm/kaslr.h> +#include <asm/hypervisor.h> /* * We need to define the tracepoints somewhere, and tlb.c @@ -636,6 +637,8 @@ void __init init_mem_mapping(void) load_cr3(swapper_pg_dir); __flush_tlb_all(); + hypervisor_init_mem_mapping(); + early_memtest(0, max_pfn_mapped << PAGE_SHIFT); } diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 229d04a83f85..a88cfbfbd078 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -50,8 +50,7 @@ unsigned long tasksize_64bit(void) static unsigned long stack_maxrandom_size(unsigned long task_size) { unsigned long max = 0; - if ((current->flags & PF_RANDOMIZE) && - !(current->personality & ADDR_NO_RANDOMIZE)) { + if (current->flags & PF_RANDOMIZE) { max = (-1UL) & __STACK_RND_MASK(task_size == tasksize_32bit()); max <<= PAGE_SHIFT; } @@ -79,13 +78,13 @@ static int mmap_is_legacy(void) static unsigned long arch_rnd(unsigned int rndbits) { + if (!(current->flags & PF_RANDOMIZE)) + return 0; return (get_random_long() & ((1UL << rndbits) - 1)) << PAGE_SHIFT; } unsigned long arch_mmap_rnd(void) { - if (!(current->flags & PF_RANDOMIZE)) - return 0; return arch_rnd(mmap_is_ia32() ? mmap32_rnd_bits : mmap64_rnd_bits); } diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 3e4bdb442fbc..f44c0bc95aa2 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -26,7 +26,7 @@ static struct bau_operations ops __ro_after_init; /* timeouts in nanoseconds (indexed by UVH_AGING_PRESCALE_SEL urgency7 30:28) */ -static int timeout_base_ns[] = { +static const int timeout_base_ns[] = { 20, 160, 1280, @@ -1216,7 +1216,7 @@ static struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg, * set a bit in the UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE register. * Such a message must be ignored. */ -void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp) +static void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp) { unsigned long mmr_image; unsigned char swack_vec; diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index ae4cd58c0c7a..02250b2633b8 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -50,7 +50,7 @@ void foo(void) DEFINE(HOST_GS, GS); DEFINE(HOST_ORIG_AX, ORIG_EAX); #else -#if defined(PTRACE_GETREGSET) && defined(PTRACE_SETREGSET) +#ifdef FP_XSTATE_MAGIC1 DEFINE(HOST_FP_SIZE, sizeof(struct _xstate) / sizeof(unsigned long)); #else DEFINE(HOST_FP_SIZE, sizeof(struct _fpstate) / sizeof(unsigned long)); diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 87d791356ea9..de503c225ae1 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -12,6 +12,7 @@ #include <asm/setup.h> #include <asm/hypervisor.h> #include <asm/e820/api.h> +#include <asm/early_ioremap.h> #include <asm/xen/cpuid.h> #include <asm/xen/hypervisor.h> @@ -21,38 +22,50 @@ #include "mmu.h" #include "smp.h" -void __ref xen_hvm_init_shared_info(void) +static unsigned long shared_info_pfn; + +void xen_hvm_init_shared_info(void) { struct xen_add_to_physmap xatp; - u64 pa; - - if (HYPERVISOR_shared_info == &xen_dummy_shared_info) { - /* - * Search for a free page starting at 4kB physical address. - * Low memory is preferred to avoid an EPT large page split up - * by the mapping. - * Starting below X86_RESERVE_LOW (usually 64kB) is fine as - * the BIOS used for HVM guests is well behaved and won't - * clobber memory other than the first 4kB. - */ - for (pa = PAGE_SIZE; - !e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) || - memblock_is_reserved(pa); - pa += PAGE_SIZE) - ; - - memblock_reserve(pa, PAGE_SIZE); - HYPERVISOR_shared_info = __va(pa); - } xatp.domid = DOMID_SELF; xatp.idx = 0; xatp.space = XENMAPSPACE_shared_info; - xatp.gpfn = virt_to_pfn(HYPERVISOR_shared_info); + xatp.gpfn = shared_info_pfn; if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) BUG(); } +static void __init reserve_shared_info(void) +{ + u64 pa; + + /* + * Search for a free page starting at 4kB physical address. + * Low memory is preferred to avoid an EPT large page split up + * by the mapping. + * Starting below X86_RESERVE_LOW (usually 64kB) is fine as + * the BIOS used for HVM guests is well behaved and won't + * clobber memory other than the first 4kB. + */ + for (pa = PAGE_SIZE; + !e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) || + memblock_is_reserved(pa); + pa += PAGE_SIZE) + ; + + shared_info_pfn = PHYS_PFN(pa); + + memblock_reserve(pa, PAGE_SIZE); + HYPERVISOR_shared_info = early_memremap(pa, PAGE_SIZE); +} + +static void __init xen_hvm_init_mem_mapping(void) +{ + early_memunmap(HYPERVISOR_shared_info, PAGE_SIZE); + HYPERVISOR_shared_info = __va(PFN_PHYS(shared_info_pfn)); +} + static void __init init_hvm_pv_info(void) { int major, minor; @@ -153,6 +166,7 @@ static void __init xen_hvm_guest_init(void) init_hvm_pv_info(); + reserve_shared_info(); xen_hvm_init_shared_info(); /* @@ -218,5 +232,6 @@ const struct hypervisor_x86 x86_hyper_xen_hvm = { .init_platform = xen_hvm_guest_init, .pin_vcpu = xen_pin_vcpu, .x2apic_available = xen_x2apic_para_available, + .init_mem_mapping = xen_hvm_init_mem_mapping, }; EXPORT_SYMBOL(x86_hyper_xen_hvm); |
