diff options
Diffstat (limited to 'arch/x86')
85 files changed, 1434 insertions, 1111 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 90b562a34d65..5ad92419be19 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -14,7 +14,6 @@ config X86_32 select ARCH_WANT_IPC_PARSE_VERSION select CLKSRC_I8253 select CLONE_BACKWARDS - select HAVE_GENERIC_DMA_COHERENT select MODULES_USE_ELF_REL select OLD_SIGACTION @@ -2218,14 +2217,8 @@ config RANDOMIZE_MEMORY_PHYSICAL_PADDING If unsure, leave at the default value. config HOTPLUG_CPU - bool "Support for hot-pluggable CPUs" + def_bool y depends on SMP - ---help--- - Say Y here to allow turning CPUs off and on. CPUs can be - controlled through /sys/devices/system/cpu. - ( Note: power management support will enable this option - automatically on SMP systems. ) - Say N if you want to disable CPU hotplug. config BOOTPARAM_HOTPLUG_CPU0 bool "Set default setting of cpu0_hotpluggable" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 2d8b9d8ca4f8..a587805c6687 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -219,8 +219,12 @@ ifdef CONFIG_RETPOLINE # Additionally, avoid generating expensive indirect jumps which # are subject to retpolines for small number of switch cases. # clang turns off jump table generation by default when under - # retpoline builds, however, gcc does not for x86. - KBUILD_CFLAGS += $(call cc-option,--param=case-values-threshold=20) + # retpoline builds, however, gcc does not for x86. This has + # only been fixed starting from gcc stable version 8.4.0 and + # onwards, but not for older ones. See gcc bug #86952. + ifndef CONFIG_CC_IS_CLANG + KBUILD_CFLAGS += $(call cc-option,-fno-jump-tables) + endif endif archscripts: scripts_basic diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index fa0332dda9f2..2e53c056ba20 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -697,8 +697,8 @@ static bool process_mem_region(struct mem_vector *region, return 1; } } - return 0; #endif + return 0; } #ifdef CONFIG_EFI diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index fd13655e0f9b..d2f184165934 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -120,8 +120,6 @@ static inline void console_init(void) void set_sev_encryption_mask(void); -#endif - /* acpi.c */ #ifdef CONFIG_ACPI acpi_physical_address get_rsdp_addr(void); @@ -135,3 +133,5 @@ int count_immovable_mem_regions(void); #else static inline int count_immovable_mem_regions(void) { return 0; } #endif + +#endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 315a67b8896b..90154df8f125 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -13,8 +13,9 @@ */ #include <linux/types.h> -#include <linux/kernel.h> +#include <linux/compiler.h> #include <linux/errno.h> +#include <linux/limits.h> #include <asm/asm.h> #include "ctype.h" #include "string.h" diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 955ab6a3b61f..1f9607ed087c 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -429,3 +429,7 @@ 421 i386 rt_sigtimedwait_time64 sys_rt_sigtimedwait __ia32_compat_sys_rt_sigtimedwait_time64 422 i386 futex_time64 sys_futex __ia32_sys_futex 423 i386 sched_rr_get_interval_time64 sys_sched_rr_get_interval __ia32_sys_sched_rr_get_interval +424 i386 pidfd_send_signal sys_pidfd_send_signal __ia32_sys_pidfd_send_signal +425 i386 io_uring_setup sys_io_uring_setup __ia32_sys_io_uring_setup +426 i386 io_uring_enter sys_io_uring_enter __ia32_sys_io_uring_enter +427 i386 io_uring_register sys_io_uring_register __ia32_sys_io_uring_register diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 2ae92fddb6d5..92ee0b4378d4 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -345,6 +345,10 @@ 334 common rseq __x64_sys_rseq # don't use numbers 387 through 423, add new calls after the last # 'common' entry +424 common pidfd_send_signal __x64_sys_pidfd_send_signal +425 common io_uring_setup __x64_sys_io_uring_setup +426 common io_uring_enter __x64_sys_io_uring_enter +427 common io_uring_register __x64_sys_io_uring_register # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index b684f0294f35..e2b1447192a8 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1995,7 +1995,7 @@ static int x86_pmu_commit_txn(struct pmu *pmu) */ static void free_fake_cpuc(struct cpu_hw_events *cpuc) { - kfree(cpuc->shared_regs); + intel_cpuc_finish(cpuc); kfree(cpuc); } @@ -2007,14 +2007,11 @@ static struct cpu_hw_events *allocate_fake_cpuc(void) cpuc = kzalloc(sizeof(*cpuc), GFP_KERNEL); if (!cpuc) return ERR_PTR(-ENOMEM); - - /* only needed, if we have extra_regs */ - if (x86_pmu.extra_regs) { - cpuc->shared_regs = allocate_shared_regs(cpu); - if (!cpuc->shared_regs) - goto error; - } cpuc->is_fake = 1; + + if (intel_cpuc_prepare(cpuc, cpu)) + goto error; + return cpuc; error: free_fake_cpuc(cpuc); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7ec265bacb6a..8baa441d8000 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2000,6 +2000,39 @@ static void intel_pmu_nhm_enable_all(int added) intel_pmu_enable_all(added); } +static void intel_set_tfa(struct cpu_hw_events *cpuc, bool on) +{ + u64 val = on ? MSR_TFA_RTM_FORCE_ABORT : 0; + + if (cpuc->tfa_shadow != val) { + cpuc->tfa_shadow = val; + wrmsrl(MSR_TSX_FORCE_ABORT, val); + } +} + +static void intel_tfa_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr) +{ + /* + * We're going to use PMC3, make sure TFA is set before we touch it. + */ + if (cntr == 3 && !cpuc->is_fake) + intel_set_tfa(cpuc, true); +} + +static void intel_tfa_pmu_enable_all(int added) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + /* + * If we find PMC3 is no longer used when we enable the PMU, we can + * clear TFA. + */ + if (!test_bit(3, cpuc->active_mask)) + intel_set_tfa(cpuc, false); + + intel_pmu_enable_all(added); +} + static void enable_counter_freeze(void) { update_debugctlmsr(get_debugctlmsr() | @@ -2770,6 +2803,35 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc) } static struct event_constraint * +dyn_constraint(struct cpu_hw_events *cpuc, struct event_constraint *c, int idx) +{ + WARN_ON_ONCE(!cpuc->constraint_list); + + if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) { + struct event_constraint *cx; + + /* + * grab pre-allocated constraint entry + */ + cx = &cpuc->constraint_list[idx]; + + /* + * initialize dynamic constraint + * with static constraint + */ + *cx = *c; + + /* + * mark constraint as dynamic + */ + cx->flags |= PERF_X86_EVENT_DYNAMIC; + c = cx; + } + + return c; +} + +static struct event_constraint * intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, int idx, struct event_constraint *c) { @@ -2799,27 +2861,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * only needed when constraint has not yet * been cloned (marked dynamic) */ - if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) { - struct event_constraint *cx; - - /* - * grab pre-allocated constraint entry - */ - cx = &cpuc->constraint_list[idx]; - - /* - * initialize dynamic constraint - * with static constraint - */ - *cx = *c; - - /* - * mark constraint as dynamic, so we - * can free it later on - */ - cx->flags |= PERF_X86_EVENT_DYNAMIC; - c = cx; - } + c = dyn_constraint(cpuc, c, idx); /* * From here on, the constraint is dynamic. @@ -3357,6 +3399,26 @@ glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx, return c; } +static bool allow_tsx_force_abort = true; + +static struct event_constraint * +tfa_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct event_constraint *c = hsw_get_event_constraints(cpuc, idx, event); + + /* + * Without TFA we must not use PMC3. + */ + if (!allow_tsx_force_abort && test_bit(3, c->idxmsk) && idx >= 0) { + c = dyn_constraint(cpuc, c, idx); + c->idxmsk64 &= ~(1ULL << 3); + c->weight--; + } + + return c; +} + /* * Broadwell: * @@ -3410,7 +3472,7 @@ ssize_t intel_event_sysfs_show(char *page, u64 config) return x86_event_sysfs_show(page, config, event); } -struct intel_shared_regs *allocate_shared_regs(int cpu) +static struct intel_shared_regs *allocate_shared_regs(int cpu) { struct intel_shared_regs *regs; int i; @@ -3442,23 +3504,24 @@ static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu) return c; } -static int intel_pmu_cpu_prepare(int cpu) -{ - struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); +int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu) +{ if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) { cpuc->shared_regs = allocate_shared_regs(cpu); if (!cpuc->shared_regs) goto err; } - if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { + if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA)) { size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint); - cpuc->constraint_list = kzalloc(sz, GFP_KERNEL); + cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu)); if (!cpuc->constraint_list) goto err_shared_regs; + } + if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { cpuc->excl_cntrs = allocate_excl_cntrs(cpu); if (!cpuc->excl_cntrs) goto err_constraint_list; @@ -3480,6 +3543,11 @@ err: return -ENOMEM; } +static int intel_pmu_cpu_prepare(int cpu) +{ + return intel_cpuc_prepare(&per_cpu(cpu_hw_events, cpu), cpu); +} + static void flip_smm_bit(void *data) { unsigned long set = *(unsigned long *)data; @@ -3554,9 +3622,8 @@ static void intel_pmu_cpu_starting(int cpu) } } -static void free_excl_cntrs(int cpu) +static void free_excl_cntrs(struct cpu_hw_events *cpuc) { - struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); struct intel_excl_cntrs *c; c = cpuc->excl_cntrs; @@ -3564,9 +3631,10 @@ static void free_excl_cntrs(int cpu) if (c->core_id == -1 || --c->refcnt == 0) kfree(c); cpuc->excl_cntrs = NULL; - kfree(cpuc->constraint_list); - cpuc->constraint_list = NULL; } + + kfree(cpuc->constraint_list); + cpuc->constraint_list = NULL; } static void intel_pmu_cpu_dying(int cpu) @@ -3577,9 +3645,8 @@ static void intel_pmu_cpu_dying(int cpu) disable_counter_freeze(); } -static void intel_pmu_cpu_dead(int cpu) +void intel_cpuc_finish(struct cpu_hw_events *cpuc) { - struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); struct intel_shared_regs *pc; pc = cpuc->shared_regs; @@ -3589,7 +3656,12 @@ static void intel_pmu_cpu_dead(int cpu) cpuc->shared_regs = NULL; } - free_excl_cntrs(cpu); + free_excl_cntrs(cpuc); +} + +static void intel_pmu_cpu_dead(int cpu) +{ + intel_cpuc_finish(&per_cpu(cpu_hw_events, cpu)); } static void intel_pmu_sched_task(struct perf_event_context *ctx, @@ -4107,8 +4179,11 @@ static struct attribute *intel_pmu_caps_attrs[] = { NULL }; +static DEVICE_BOOL_ATTR(allow_tsx_force_abort, 0644, allow_tsx_force_abort); + static struct attribute *intel_pmu_attrs[] = { &dev_attr_freeze_on_smi.attr, + NULL, /* &dev_attr_allow_tsx_force_abort.attr.attr */ NULL, }; @@ -4607,6 +4682,15 @@ __init int intel_pmu_init(void) tsx_attr = hsw_tsx_events_attrs; intel_pmu_pebs_data_source_skl( boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X); + + if (boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) { + x86_pmu.flags |= PMU_FL_TFA; + x86_pmu.get_event_constraints = tfa_get_event_constraints; + x86_pmu.enable_all = intel_tfa_pmu_enable_all; + x86_pmu.commit_scheduling = intel_tfa_commit_scheduling; + intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr.attr; + } + pr_cont("Skylake events, "); name = "skylake"; break; @@ -4758,7 +4842,7 @@ static __init int fixup_ht_bug(void) hardlockup_detector_perf_restart(); for_each_online_cpu(c) - free_excl_cntrs(c); + free_excl_cntrs(&per_cpu(cpu_hw_events, c)); cpus_read_unlock(); pr_info("PMU erratum BJ122, BV98, HSD29 workaround disabled, HT off\n"); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index d516161c00c4..9fe64c01a2e5 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -732,6 +732,7 @@ static int uncore_pmu_event_init(struct perf_event *event) /* fixed counters have event field hardcoded to zero */ hwc->config = 0ULL; } else if (is_freerunning_event(event)) { + hwc->config = event->attr.config; if (!check_valid_freerunning_event(box, event)) return -EINVAL; event->hw.idx = UNCORE_PMC_IDX_FREERUNNING; diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index cb46d602a6b8..853a49a8ccf6 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -292,8 +292,8 @@ static inline unsigned int uncore_freerunning_counter(struct intel_uncore_box *box, struct perf_event *event) { - unsigned int type = uncore_freerunning_type(event->attr.config); - unsigned int idx = uncore_freerunning_idx(event->attr.config); + unsigned int type = uncore_freerunning_type(event->hw.config); + unsigned int idx = uncore_freerunning_idx(event->hw.config); struct intel_uncore_pmu *pmu = box->pmu; return pmu->type->freerunning[type].counter_base + @@ -377,7 +377,7 @@ static inline unsigned int uncore_freerunning_bits(struct intel_uncore_box *box, struct perf_event *event) { - unsigned int type = uncore_freerunning_type(event->attr.config); + unsigned int type = uncore_freerunning_type(event->hw.config); return box->pmu->type->freerunning[type].bits; } @@ -385,7 +385,7 @@ unsigned int uncore_freerunning_bits(struct intel_uncore_box *box, static inline int uncore_num_freerunning(struct intel_uncore_box *box, struct perf_event *event) { - unsigned int type = uncore_freerunning_type(event->attr.config); + unsigned int type = uncore_freerunning_type(event->hw.config); return box->pmu->type->freerunning[type].num_counters; } @@ -399,8 +399,8 @@ static inline int uncore_num_freerunning_types(struct intel_uncore_box *box, static inline bool check_valid_freerunning_event(struct intel_uncore_box *box, struct perf_event *event) { - unsigned int type = uncore_freerunning_type(event->attr.config); - unsigned int idx = uncore_freerunning_idx(event->attr.config); + unsigned int type = uncore_freerunning_type(event->hw.config); + unsigned int idx = uncore_freerunning_idx(event->hw.config); return (type < uncore_num_freerunning_types(box, event)) && (idx < uncore_num_freerunning(box, event)); diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index b12517fae77a..13493f43b247 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -442,9 +442,11 @@ static int snb_uncore_imc_event_init(struct perf_event *event) /* must be done before validate_group */ event->hw.event_base = base; - event->hw.config = cfg; event->hw.idx = idx; + /* Convert to standard encoding format for freerunning counters */ + event->hw.config = ((cfg - 1) << 8) | 0x10ff; + /* no group validation needed, we have free running counters */ return 0; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 7e75f474b076..a75955741c50 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -243,6 +243,11 @@ struct cpu_hw_events { int excl_thread_id; /* 0 or 1 */ /* + * SKL TSX_FORCE_ABORT shadow + */ + u64 tfa_shadow; + + /* * AMD specific bits */ struct amd_nb *amd_nb; @@ -682,6 +687,7 @@ do { \ #define PMU_FL_EXCL_CNTRS 0x4 /* has exclusive counter requirements */ #define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */ #define PMU_FL_PEBS_ALL 0x10 /* all events are valid PEBS events */ +#define PMU_FL_TFA 0x20 /* deal with TSX force abort */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr @@ -890,7 +896,8 @@ struct event_constraint * x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event); -struct intel_shared_regs *allocate_shared_regs(int cpu); +extern int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu); +extern void intel_cpuc_finish(struct cpu_hw_events *cpuc); int intel_pmu_init(void); @@ -1026,9 +1033,13 @@ static inline int intel_pmu_init(void) return 0; } -static inline struct intel_shared_regs *allocate_shared_regs(int cpu) +static inline int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu) +{ + return 0; +} + +static inline void intel_cpuc_finish(struct cpu_hw_events *cpuc) { - return NULL; } static inline int is_ht_workaround_enabled(void) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 7abb09e2eeb8..e4ba467a9fc6 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -96,15 +96,20 @@ void __percpu **hyperv_pcpu_input_arg; EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg); u32 hv_max_vp_index; +EXPORT_SYMBOL_GPL(hv_max_vp_index); static int hv_cpu_init(unsigned int cpu) { u64 msr_vp_index; struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()]; void **input_arg; + struct page *pg; input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); - *input_arg = page_address(alloc_page(GFP_KERNEL)); + pg = alloc_page(GFP_KERNEL); + if (unlikely(!pg)) + return -ENOMEM; + *input_arg = page_address(pg); hv_get_vp_index(msr_vp_index); @@ -406,6 +411,13 @@ void hyperv_cleanup(void) /* Reset our OS id */ wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); + /* + * Reset hypercall page reference before reset the page, + * let hypercall operations fail safely rather than + * panic the kernel for using invalid hypercall page + */ + hv_hypercall_pg = NULL; + /* Reset the hypercall page */ hypercall_msr.as_uint64 = 0; wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index ad7b210aa3f6..d153d570bb04 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -36,13 +36,7 @@ * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1). */ -#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 1) -/* Technically wrong, but this avoids compilation errors on some gcc - versions. */ -#define BITOP_ADDR(x) "=m" (*(volatile long *) (x)) -#else #define BITOP_ADDR(x) "+m" (*(volatile long *) (x)) -#endif #define ADDR BITOP_ADDR(addr) diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index 3417110574c1..31c379c1da41 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _CPU_DEVICE_ID -#define _CPU_DEVICE_ID 1 +#ifndef _ASM_X86_CPU_DEVICE_ID +#define _ASM_X86_CPU_DEVICE_ID /* * Declare drivers belonging to specific x86 CPUs @@ -9,8 +9,6 @@ #include <linux/mod_devicetable.h> -extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match); - /* * Match specific microcode revisions. * @@ -22,21 +20,22 @@ extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match); */ struct x86_cpu_desc { - __u8 x86_family; - __u8 x86_vendor; - __u8 x86_model; - __u8 x86_stepping; - __u32 x86_microcode_rev; + u8 x86_family; + u8 x86_vendor; + u8 x86_model; + u8 x86_stepping; + u32 x86_microcode_rev; }; -#define INTEL_CPU_DESC(mod, step, rev) { \ - .x86_family = 6, \ - .x86_vendor = X86_VENDOR_INTEL, \ - .x86_model = mod, \ - .x86_stepping = step, \ - .x86_microcode_rev = rev, \ +#define INTEL_CPU_DESC(model, stepping, revision) { \ + .x86_family = 6, \ + .x86_vendor = X86_VENDOR_INTEL, \ + .x86_model = (model), \ + .x86_stepping = (stepping), \ + .x86_microcode_rev = (revision), \ } +extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match); extern bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table); -#endif +#endif /* _ASM_X86_CPU_DEVICE_ID */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index ce95b8cbd229..0e56ff7e4848 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -112,8 +112,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; test_cpu_cap(c, bit)) #define this_cpu_has(bit) \ - (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ - x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability)) + (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ + x86_this_cpu_test_bit(bit, \ + (unsigned long __percpu *)&cpu_info.x86_capability)) /* * This macro is for detection of features which need kernel diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 6d6122524711..981ff9479648 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -344,6 +344,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 180373360e34..159b5988292f 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -35,6 +35,7 @@ #include <asm/msr-index.h> #include <asm/asm.h> #include <asm/kvm_page_track.h> +#include <asm/kvm_vcpu_regs.h> #include <asm/hyperv-tlfs.h> #define KVM_MAX_VCPUS 288 @@ -137,23 +138,23 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) #define ASYNC_PF_PER_VCPU 64 enum kvm_reg { - VCPU_REGS_RAX = 0, - VCPU_REGS_RCX = 1, - VCPU_REGS_RDX = 2, - VCPU_REGS_RBX = 3, - VCPU_REGS_RSP = 4, - VCPU_REGS_RBP = 5, - VCPU_REGS_RSI = 6, - VCPU_REGS_RDI = 7, + VCPU_REGS_RAX = __VCPU_REGS_RAX, + VCPU_REGS_RCX = __VCPU_REGS_RCX, + VCPU_REGS_RDX = __VCPU_REGS_RDX, + VCPU_REGS_RBX = __VCPU_REGS_RBX, + VCPU_REGS_RSP = __VCPU_REGS_RSP, + VCPU_REGS_RBP = __VCPU_REGS_RBP, + VCPU_REGS_RSI = __VCPU_REGS_RSI, + VCPU_REGS_RDI = __VCPU_REGS_RDI, #ifdef CONFIG_X86_64 - VCPU_REGS_R8 = 8, - VCPU_REGS_R9 = 9, - VCPU_REGS_R10 = 10, - VCPU_REGS_R11 = 11, - VCPU_REGS_R12 = 12, - VCPU_REGS_R13 = 13, - VCPU_REGS_R14 = 14, - VCPU_REGS_R15 = 15, + VCPU_REGS_R8 = __VCPU_REGS_R8, + VCPU_REGS_R9 = __VCPU_REGS_R9, + VCPU_REGS_R10 = __VCPU_REGS_R10, + VCPU_REGS_R11 = __VCPU_REGS_R11, + VCPU_REGS_R12 = __VCPU_REGS_R12, + VCPU_REGS_R13 = __VCPU_REGS_R13, + VCPU_REGS_R14 = __VCPU_REGS_R14, + VCPU_REGS_R15 = __VCPU_REGS_R15, #endif VCPU_REGS_RIP, NR_VCPU_REGS @@ -252,14 +253,14 @@ struct kvm_mmu_memory_cache { * kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used * by indirect shadow page can not be more than 15 bits. * - * Currently, we used 14 bits that are @level, @cr4_pae, @quadrant, @access, + * Currently, we used 14 bits that are @level, @gpte_is_8_bytes, @quadrant, @access, * @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp. */ union kvm_mmu_page_role { u32 word; struct { unsigned level:4; - unsigned cr4_pae:1; + unsigned gpte_is_8_bytes:1; unsigned quadrant:2; unsigned direct:1; unsigned access:3; @@ -319,6 +320,7 @@ struct kvm_mmu_page { struct list_head link; struct hlist_node hash_link; bool unsync; + bool mmio_cached; /* * The following two entries are used to key the shadow page in the @@ -333,10 +335,6 @@ struct kvm_mmu_page { int root_count; /* Currently serving as active root */ unsigned int unsync_children; struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ - - /* The page is obsolete if mmu_valid_gen != kvm->arch.mmu_valid_gen. */ - unsigned long mmu_valid_gen; - DECLARE_BITMAP(unsync_child_bitmap, 512); #ifdef CONFIG_X86_32 @@ -352,6 +350,7 @@ struct kvm_mmu_page { }; struct kvm_pio_request { + unsigned long linear_rip; unsigned long count; int in; int port; @@ -570,6 +569,7 @@ struct kvm_vcpu_arch { bool tpr_access_reporting; u64 ia32_xss; u64 microcode_version; + u64 arch_capabilities; /* * Paging state of the vcpu @@ -848,13 +848,11 @@ struct kvm_arch { unsigned int n_requested_mmu_pages; unsigned int n_max_mmu_pages; unsigned int indirect_shadow_pages; - unsigned long mmu_valid_gen; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; /* * Hash table of struct kvm_mmu_page. */ struct list_head active_mmu_pages; - struct list_head zapped_obsolete_pages; struct kvm_page_track_notifier_node mmu_sp_tracker; struct kvm_page_track_notifier_head track_notifier_head; @@ -1196,6 +1194,8 @@ struct kvm_x86_ops { int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu); + + bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu); }; struct kvm_arch_async_pf { @@ -1255,8 +1255,8 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask); void kvm_mmu_zap_all(struct kvm *kvm); -void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots); -unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm); +void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); +unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); diff --git a/arch/x86/include/asm/kvm_vcpu_regs.h b/arch/x86/include/asm/kvm_vcpu_regs.h new file mode 100644 index 000000000000..1af2cb59233b --- /dev/null +++ b/arch/x86/include/asm/kvm_vcpu_regs.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_KVM_VCPU_REGS_H +#define _ASM_X86_KVM_VCPU_REGS_H + +#define __VCPU_REGS_RAX 0 +#define __VCPU_REGS_RCX 1 +#define __VCPU_REGS_RDX 2 +#define __VCPU_REGS_RBX 3 +#define __VCPU_REGS_RSP 4 +#define __VCPU_REGS_RBP 5 +#define __VCPU_REGS_RSI 6 +#define __VCPU_REGS_RDI 7 + +#ifdef CONFIG_X86_64 +#define __VCPU_REGS_R8 8 +#define __VCPU_REGS_R9 9 +#define __VCPU_REGS_R10 10 +#define __VCPU_REGS_R11 11 +#define __VCPU_REGS_R12 12 +#define __VCPU_REGS_R13 13 +#define __VCPU_REGS_R14 14 +#define __VCPU_REGS_R15 15 +#endif + +#endif /* _ASM_X86_KVM_VCPU_REGS_H */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index c1a812bd5a27..22d05e3835f0 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -48,6 +48,7 @@ #define MCI_STATUS_SYNDV BIT_ULL(53) /* synd reg. valid */ #define MCI_STATUS_DEFERRED BIT_ULL(44) /* uncorrected error, deferred exception */ #define MCI_STATUS_POISON BIT_ULL(43) /* access poisonous data */ +#define MCI_STATUS_SCRUB BIT_ULL(40) /* Error detected during scrub operation */ /* * McaX field if set indicates a given bank supports MCA extensions: @@ -307,11 +308,17 @@ enum smca_bank_types { SMCA_FP, /* Floating Point */ SMCA_L3_CACHE, /* L3 Cache */ SMCA_CS, /* Coherent Slave */ + SMCA_CS_V2, /* Coherent Slave */ SMCA_PIE, /* Power, Interrupts, etc. */ SMCA_UMC, /* Unified Memory Controller */ SMCA_PB, /* Parameter Block */ SMCA_PSP, /* Platform Security Processor */ + SMCA_PSP_V2, /* Platform Security Processor */ SMCA_SMU, /* System Management Unit */ + SMCA_SMU_V2, /* System Management Unit */ + SMCA_MP5, /* Microprocessor 5 Unit */ + SMCA_NBIO, /* Northbridge IO Unit */ + SMCA_PCIE, /* PCI Express Unit */ N_SMCA_BANK_TYPES }; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 8e40c2446fd1..ca5bc0eacb95 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -666,6 +666,12 @@ #define MSR_IA32_TSC_DEADLINE 0x000006E0 + +#define MSR_TSX_FORCE_ABORT 0x0000010F + +#define MSR_TFA_RTM_FORCE_ABORT_BIT 0 +#define MSR_TFA_RTM_FORCE_ABORT BIT_ULL(MSR_TFA_RTM_FORCE_ABORT_BIT) + /* P4/Xeon+ specific */ #define MSR_IA32_MCG_EAX 0x00000180 #define MSR_IA32_MCG_EBX 0x00000181 diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 0ce558a8150d..8f657286d599 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -7,11 +7,7 @@ #endif #ifdef CONFIG_KASAN -#ifdef CONFIG_KASAN_EXTRA -#define KASAN_STACK_ORDER 2 -#else #define KASAN_STACK_ORDER 1 -#endif #else #define KASAN_STACK_ORDER 0 #endif diff --git a/arch/x86/include/asm/processor-cyrix.h b/arch/x86/include/asm/processor-cyrix.h index aaedd73ea2c6..df700a6cc869 100644 --- a/arch/x86/include/asm/processor-cyrix.h +++ b/arch/x86/include/asm/processor-cyrix.h @@ -3,19 +3,6 @@ * NSC/Cyrix CPU indexed register access. Must be inlined instead of * macros to ensure correct access ordering * Access order is always 0x22 (=offset), 0x23 (=value) - * - * When using the old macros a line like - * setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88); - * gets expanded to: - * do { - * outb((CX86_CCR2), 0x22); - * outb((({ - * outb((CX86_CCR2), 0x22); - * inb(0x23); - * }) | 0x88), 0x23); - * } while (0); - * - * which in fact violates the access order (= 0x22, 0x22, 0x23, 0x23). */ static inline u8 getCx86(u8 reg) @@ -29,11 +16,3 @@ static inline void setCx86(u8 reg, u8 data) outb(reg, 0x22); outb(data, 0x23); } - -#define getCx86_old(reg) ({ outb((reg), 0x22); inb(0x23); }) - -#define setCx86_old(reg, data) do { \ - outb((reg), 0x22); \ - outb((data), 0x23); \ -} while (0) - diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 63b3393bd98e..c53682303c9c 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -77,7 +77,11 @@ static inline size_t real_mode_size_needed(void) return ALIGN(real_mode_blob_end - real_mode_blob, PAGE_SIZE); } -void set_real_mode_mem(phys_addr_t mem, size_t size); +static inline void set_real_mode_mem(phys_addr_t mem) +{ + real_mode_header = (struct real_mode_header *) __va(mem); +} + void reserve_real_mode(void); #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h index 55d392c6bd29..f74362b05619 100644 --- a/arch/x86/include/asm/string_32.h +++ b/arch/x86/include/asm/string_32.h @@ -179,14 +179,7 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len) * No 3D Now! */ -#if (__GNUC__ >= 4) #define memcpy(t, f, n) __builtin_memcpy(t, f, n) -#else -#define memcpy(t, f, n) \ - (__builtin_constant_p((n)) \ - ? __constant_memcpy((t), (f), (n)) \ - : __memcpy((t), (f), (n))) -#endif #endif #endif /* !CONFIG_FORTIFY_SOURCE */ @@ -216,29 +209,6 @@ static inline void *__memset_generic(void *s, char c, size_t count) /* we might want to write optimized versions of these later */ #define __constant_count_memset(s, c, count) __memset_generic((s), (c), (count)) -/* - * memset(x, 0, y) is a reasonably common thing to do, so we want to fill - * things 32 bits at a time even when we don't know the size of the - * area at compile-time.. - */ -static __always_inline -void *__constant_c_memset(void *s, unsigned long c, size_t count) -{ - int d0, d1; - asm volatile("rep ; stosl\n\t" - "testb $2,%b3\n\t" - "je 1f\n\t" - "stosw\n" - "1:\ttestb $1,%b3\n\t" - "je 2f\n\t" - "stosb\n" - "2:" - : "=&c" (d0), "=&D" (d1) - : "a" (c), "q" (count), "0" (count/4), "1" ((long)s) - : "memory"); - return s; -} - /* Added by Gertjan van Wingerde to make minix and sysv module work */ #define __HAVE_ARCH_STRNLEN extern size_t strnlen(const char *s, size_t count); @@ -247,72 +217,6 @@ extern size_t strnlen(const char *s, size_t count); #define __HAVE_ARCH_STRSTR extern char *strstr(const char *cs, const char *ct); -/* - * This looks horribly ugly, but the compiler can optimize it totally, - * as we by now know that both pattern and count is constant.. - */ -static __always_inline -void *__constant_c_and_count_memset(void *s, unsigned long pattern, - size_t count) -{ - switch (count) { - case 0: - return s; - case 1: - *(unsigned char *)s = pattern & 0xff; - return s; - case 2: - *(unsigned short *)s = pattern & 0xffff; - return s; - case 3: - *(unsigned short *)s = pattern & 0xffff; - *((unsigned char *)s + 2) = pattern & 0xff; - return s; - case 4: - *(unsigned long *)s = pattern; - return s; - } - -#define COMMON(x) \ - asm volatile("rep ; stosl" \ - x \ - : "=&c" (d0), "=&D" (d1) \ - : "a" (eax), "0" (count/4), "1" ((long)s) \ - : "memory") - - { - int d0, d1; -#if __GNUC__ == 4 && __GNUC_MINOR__ == 0 - /* Workaround for broken gcc 4.0 */ - register unsigned long eax asm("%eax") = pattern; -#else - unsigned long eax = pattern; -#endif - - switch (count % 4) { - case 0: - COMMON(""); - return s; - case 1: - COMMON("\n\tstosb"); - return s; - case 2: - COMMON("\n\tstosw"); - return s; - default: - COMMON("\n\tstosw\n\tstosb"); - return s; - } - } - -#undef COMMON -} - -#define __constant_c_x_memset(s, c, count) \ - (__builtin_constant_p(count) \ - ? __constant_c_and_count_memset((s), (c), (count)) \ - : __constant_c_memset((s), (c), (count))) - #define __memset(s, c, count) \ (__builtin_constant_p(count) \ ? __constant_count_memset((s), (c), (count)) \ @@ -321,15 +225,7 @@ void *__constant_c_and_count_memset(void *s, unsigned long pattern, #define __HAVE_ARCH_MEMSET extern void *memset(void *, int, size_t); #ifndef CONFIG_FORTIFY_SOURCE -#if (__GNUC__ >= 4) #define memset(s, c, count) __builtin_memset(s, c, count) -#else -#define memset(s, c, count) \ - (__builtin_constant_p(c) \ - ? __constant_c_x_memset((s), (0x01010101UL * (unsigned char)(c)), \ - (count)) \ - : __memset((s), (c), (count))) -#endif #endif /* !CONFIG_FORTIFY_SOURCE */ #define __HAVE_ARCH_MEMSET16 diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 4e4194e21a09..75314c3dbe47 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -14,21 +14,6 @@ extern void *memcpy(void *to, const void *from, size_t len); extern void *__memcpy(void *to, const void *from, size_t len); -#ifndef CONFIG_FORTIFY_SOURCE -#if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4 -#define memcpy(dst, src, len) \ -({ \ - size_t __len = (len); \ - void *__ret; \ - if (__builtin_constant_p(len) && __len >= 64) \ - __ret = __memcpy((dst), (src), __len); \ - else \ - __ret = __builtin_memcpy((dst), (src), __len); \ - __ret; \ -}) -#endif -#endif /* !CONFIG_FORTIFY_SOURCE */ - #define __HAVE_ARCH_MEMSET void *memset(void *s, int c, size_t n); void *__memset(void *s, int c, size_t n); diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index 1f86e1b0a5cd..499578f7e6d7 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -23,6 +23,12 @@ struct unwind_state { #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; + /* + * If non-NULL: The current frame is incomplete and doesn't contain a + * valid BP. When looking for the next frame, use this instead of the + * non-existent saved BP. + */ + unsigned long *next_bp; struct pt_regs *regs; #else unsigned long *sp; diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index ef05bea7010d..de6f0d59a24f 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -332,15 +332,11 @@ HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val, return _hypercall4(int, update_va_mapping, va, new_val.pte, new_val.pte >> 32, flags); } -extern int __must_check xen_event_channel_op_compat(int, void *); static inline int HYPERVISOR_event_channel_op(int cmd, void *arg) { - int rc = _hypercall2(int, event_channel_op, cmd, arg); - if (unlikely(rc == -ENOSYS)) - rc = xen_event_channel_op_compat(cmd, arg); - return rc; + return _hypercall2(int, event_channel_op, cmd, arg); } static inline int @@ -355,15 +351,10 @@ HYPERVISOR_console_io(int cmd, int count, char *str) return _hypercall3(int, console_io, cmd, count, str); } -extern int __must_check xen_physdev_op_compat(int, void *); - static inline int HYPERVISOR_physdev_op(int cmd, void *arg) { - int rc = _hypercall2(int, physdev_op, cmd, arg); - if (unlikely(rc == -ENOSYS)) - rc = xen_physdev_op_compat(cmd, arg); - return rc; + return _hypercall2(int, physdev_op, cmd, arg); } static inline int diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild index efe701b7c6ce..59b5ad310f78 100644 --- a/arch/x86/include/uapi/asm/Kbuild +++ b/arch/x86/include/uapi/asm/Kbuild @@ -1,6 +1,3 @@ -include include/uapi/asm-generic/Kbuild.asm - generated-y += unistd_32.h generated-y += unistd_64.h generated-y += unistd_x32.h -generic-y += socket.h diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 2624de16cd7a..8dcbf6890714 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -935,6 +935,9 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) #define HPET_RESOURCE_NAME_SIZE 9 hpet_res = memblock_alloc(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE, SMP_CACHE_BYTES); + if (!hpet_res) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE); hpet_res->name = (void *)&hpet_res[1]; hpet_res->flags = IORESOURCE_MEM; diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 58176b56354e..294ed4392a0e 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -14,6 +14,7 @@ #define pr_fmt(fmt) "AGP: " fmt #include <linux/kernel.h> +#include <linux/kcore.h> #include <linux/types.h> #include <linux/init.h> #include <linux/memblock.h> @@ -57,7 +58,7 @@ int fallback_aper_force __initdata; int fix_aperture __initdata = 1; -#ifdef CONFIG_PROC_VMCORE +#if defined(CONFIG_PROC_VMCORE) || defined(CONFIG_PROC_KCORE) /* * If the first kernel maps the aperture over e820 RAM, the kdump kernel will * use the same range because it will remain configured in the northbridge. @@ -66,20 +67,25 @@ int fix_aperture __initdata = 1; */ static unsigned long aperture_pfn_start, aperture_page_count; -static int gart_oldmem_pfn_is_ram(unsigned long pfn) +static int gart_mem_pfn_is_ram(unsigned long pfn) { return likely((pfn < aperture_pfn_start) || (pfn >= aperture_pfn_start + aperture_page_count)); } -static void exclude_from_vmcore(u64 aper_base, u32 aper_order) +static void __init exclude_from_core(u64 aper_base, u32 aper_order) { aperture_pfn_start = aper_base >> PAGE_SHIFT; aperture_page_count = (32 * 1024 * 1024) << aper_order >> PAGE_SHIFT; - WARN_ON(register_oldmem_pfn_is_ram(&gart_oldmem_pfn_is_ram)); +#ifdef CONFIG_PROC_VMCORE + WARN_ON(register_oldmem_pfn_is_ram(&gart_mem_pfn_is_ram)); +#endif +#ifdef CONFIG_PROC_KCORE + WARN_ON(register_mem_pfn_is_ram(&gart_mem_pfn_is_ram)); +#endif } #else -static void exclude_from_vmcore(u64 aper_base, u32 aper_order) +static void exclude_from_core(u64 aper_base, u32 aper_order) { } #endif @@ -474,7 +480,7 @@ out: * may have allocated the range over its e820 RAM * and fixed up the northbridge */ - exclude_from_vmcore(last_aper_base, last_aper_order); + exclude_from_core(last_aper_base, last_aper_order); return 1; } @@ -520,7 +526,7 @@ out: * overlap with the first kernel's memory. We can't access the * range through vmcore even though it should be part of the dump. */ - exclude_from_vmcore(aper_alloc, aper_order); + exclude_from_core(aper_alloc, aper_order); /* Fix up the north bridges */ for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) { diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 264e3221d923..53aa234a6803 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2581,6 +2581,8 @@ static struct resource * __init ioapic_setup_resources(void) n *= nr_ioapics; mem = memblock_alloc(n, SMP_CACHE_BYTES); + if (!mem) + panic("%s: Failed to allocate %lu bytes\n", __func__, n); res = (void *)mem; mem += sizeof(struct resource) * nr_ioapics; @@ -2625,6 +2627,9 @@ fake_ioapic_page: #endif ioapic_phys = (unsigned long)memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (!ioapic_phys) + panic("%s: Failed to allocate %lu bytes align=0x%lx\n", + __func__, PAGE_SIZE, PAGE_SIZE); ioapic_phys = __pa(ioapic_phys); } set_fixmap_nocache(idx, ioapic_phys); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index d12226f60168..1d9b8aaea06c 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -124,7 +124,7 @@ static void set_cx86_reorder(void) setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ /* Load/Store Serialize to mem access disable (=reorder it) */ - setCx86_old(CX86_PCR0, getCx86_old(CX86_PCR0) & ~0x80); + setCx86(CX86_PCR0, getCx86(CX86_PCR0) & ~0x80); /* set load/store serialize from 1GB to 4GB */ ccr3 |= 0xe0; setCx86(CX86_CCR3, ccr3); @@ -135,11 +135,11 @@ static void set_cx86_memwb(void) pr_info("Enable Memory-Write-back mode on Cyrix/NSC processor.\n"); /* CCR2 bit 2: unlock NW bit */ - setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) & ~0x04); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) & ~0x04); /* set 'Not Write-through' */ write_cr0(read_cr0() | X86_CR0_NW); /* CCR2 bit 2: lock NW bit and set WT1 */ - setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x14); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14); } /* @@ -153,14 +153,14 @@ static void geode_configure(void) local_irq_save(flags); /* Suspend on halt power saving and enable #SUSP pin */ - setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x88); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88); ccr3 = getCx86(CX86_CCR3); setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ /* FPU fast, DTE cache, Mem bypass */ - setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x38); + setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x38); setCx86(CX86_CCR3, ccr3); /* disable MAPEN */ set_cx86_memwb(); @@ -296,7 +296,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) /* GXm supports extended cpuid levels 'ala' AMD */ if (c->cpuid_level == 2) { /* Enable cxMMX extensions (GX1 Datasheet 54) */ - setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7) | 1); + setCx86(CX86_CCR7, getCx86(CX86_CCR7) | 1); /* * GXm : 0x30 ... 0x5f GXm datasheet 51 @@ -319,7 +319,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) if (dir1 > 7) { dir0_msn++; /* M II */ /* Enable MMX extensions (App note 108) */ - setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7)|1); + setCx86(CX86_CCR7, getCx86(CX86_CCR7)|1); } else { /* A 6x86MX - it has the bug. */ set_cpu_bug(c, X86_BUG_COMA); diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 89298c83de53..e64de5149e50 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -88,11 +88,17 @@ static struct smca_bank_name smca_names[] = { [SMCA_FP] = { "floating_point", "Floating Point Unit" }, [SMCA_L3_CACHE] = { "l3_cache", "L3 Cache" }, [SMCA_CS] = { "coherent_slave", "Coherent Slave" }, + [SMCA_CS_V2] = { "coherent_slave", "Coherent Slave" }, [SMCA_PIE] = { "pie", "Power, Interrupts, etc." }, [SMCA_UMC] = { "umc", "Unified Memory Controller" }, [SMCA_PB] = { "param_block", "Parameter Block" }, [SMCA_PSP] = { "psp", "Platform Security Processor" }, + [SMCA_PSP_V2] = { "psp", "Platform Security Processor" }, [SMCA_SMU] = { "smu", "System Management Unit" }, + [SMCA_SMU_V2] = { "smu", "System Management Unit" }, + [SMCA_MP5] = { "mp5", "Microprocessor 5 Unit" }, + [SMCA_NBIO] = { "nbio", "Northbridge IO Unit" }, + [SMCA_PCIE] = { "pcie", "PCI Express Unit" }, }; static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init = @@ -138,30 +144,42 @@ static struct smca_hwid smca_hwid_mcatypes[] = { { SMCA_RESERVED, HWID_MCATYPE(0x00, 0x0), 0x0 }, /* ZN Core (HWID=0xB0) MCA types */ - { SMCA_LS, HWID_MCATYPE(0xB0, 0x0), 0x1FFFEF }, + { SMCA_LS, HWID_MCATYPE(0xB0, 0x0), 0x1FFFFF }, { SMCA_IF, HWID_MCATYPE(0xB0, 0x1), 0x3FFF }, { SMCA_L2_CACHE, HWID_MCATYPE(0xB0, 0x2), 0xF }, { SMCA_DE, HWID_MCATYPE(0xB0, 0x3), 0x1FF }, /* HWID 0xB0 MCATYPE 0x4 is Reserved */ - { SMCA_EX, HWID_MCATYPE(0xB0, 0x5), 0x7FF }, + { SMCA_EX, HWID_MCATYPE(0xB0, 0x5), 0xFFF }, { SMCA_FP, HWID_MCATYPE(0xB0, 0x6), 0x7F }, { SMCA_L3_CACHE, HWID_MCATYPE(0xB0, 0x7), 0xFF }, /* Data Fabric MCA types */ { SMCA_CS, HWID_MCATYPE(0x2E, 0x0), 0x1FF }, - { SMCA_PIE, HWID_MCATYPE(0x2E, 0x1), 0xF }, + { SMCA_PIE, HWID_MCATYPE(0x2E, 0x1), 0x1F }, + { SMCA_CS_V2, HWID_MCATYPE(0x2E, 0x2), 0x3FFF }, /* Unified Memory Controller MCA type */ - { SMCA_UMC, HWID_MCATYPE(0x96, 0x0), 0x3F }, + { SMCA_UMC, HWID_MCATYPE(0x96, 0x0), 0xFF }, /* Parameter Block MCA type */ { SMCA_PB, HWID_MCATYPE(0x05, 0x0), 0x1 }, /* Platform Security Processor MCA type */ { SMCA_PSP, HWID_MCATYPE(0xFF, 0x0), 0x1 }, + { SMCA_PSP_V2, HWID_MCATYPE(0xFF, 0x1), 0x3FFFF }, /* System Management Unit MCA type */ { SMCA_SMU, HWID_MCATYPE(0x01, 0x0), 0x1 }, + { SMCA_SMU_V2, HWID_MCATYPE(0x01, 0x1), 0x7FF }, + + /* Microprocessor 5 Unit MCA type */ + { SMCA_MP5, HWID_MCATYPE(0x01, 0x2), 0x3FF }, + + /* Northbridge IO Unit MCA type */ + { SMCA_NBIO, HWID_MCATYPE(0x18, 0x0), 0x1F }, + + /* PCI Express Unit MCA type */ + { SMCA_PCIE, HWID_MCATYPE(0x46, 0x0), 0x1F }, }; struct smca_bank smca_banks[MAX_NR_BANKS]; @@ -545,6 +563,40 @@ out: return offset; } +/* + * Turn off MC4_MISC thresholding banks on all family 0x15 models since + * they're not supported there. + */ +void disable_err_thresholding(struct cpuinfo_x86 *c) +{ + int i; + u64 hwcr; + bool need_toggle; + u32 msrs[] = { + 0x00000413, /* MC4_MISC0 */ + 0xc0000408, /* MC4_MISC1 */ + }; + + if (c->x86 != 0x15) + return; + + rdmsrl(MSR_K7_HWCR, hwcr); + + /* McStatusWrEn has to be set */ + need_toggle = !(hwcr & BIT(18)); + + if (need_toggle) + wrmsrl(MSR_K7_HWCR, hwcr | BIT(18)); + + /* Clear CntP bit safely */ + for (i = 0; i < ARRAY_SIZE(msrs); i++) + msr_clear_bit(msrs[i], 62); + + /* restore old settings */ + if (need_toggle) + wrmsrl(MSR_K7_HWCR, hwcr); +} + /* cpu init entry point, called from mce.c with preempt off */ void mce_amd_feature_init(struct cpuinfo_x86 *c) { @@ -552,6 +604,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) unsigned int bank, block, cpu = smp_processor_id(); int offset = -1; + disable_err_thresholding(c); + for (bank = 0; bank < mca_cfg.banks; ++bank) { if (mce_flags.smca) smca_configure(bank, cpu); diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c index 1d9b3ce662a0..c038e5c00a59 100644 --- a/arch/x86/kernel/cpu/mce/apei.c +++ b/arch/x86/kernel/cpu/mce/apei.c @@ -64,11 +64,11 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) EXPORT_SYMBOL_GPL(apei_mce_report_mem_error); #define CPER_CREATOR_MCE \ - UUID_LE(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c, \ - 0x64, 0x90, 0xb8, 0x9d) + GUID_INIT(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c, \ + 0x64, 0x90, 0xb8, 0x9d) #define CPER_SECTION_TYPE_MCE \ - UUID_LE(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96, \ - 0x04, 0x4a, 0x38, 0xfc) + GUID_INIT(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96, \ + 0x04, 0x4a, 0x38, 0xfc) /* * CPER specification (in UEFI specification 2.3 appendix N) requires @@ -135,7 +135,7 @@ retry: goto out; /* try to skip other type records in storage */ else if (rc != sizeof(rcd) || - uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE)) + !guid_equal(&rcd.hdr.creator_id, &CPER_CREATOR_MCE)) goto retry; memcpy(m, &rcd.mce, sizeof(*m)); rc = sizeof(*m); diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 6ce290c506d9..b7fb541a4873 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1612,36 +1612,6 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (c->x86 == 0x15 && c->x86_model <= 0xf) mce_flags.overflow_recov = 1; - /* - * Turn off MC4_MISC thresholding banks on those models since - * they're not supported there. - */ - if (c->x86 == 0x15 && - (c->x86_model >= 0x10 && c->x86_model <= 0x1f)) { - int i; - u64 hwcr; - bool need_toggle; - u32 msrs[] = { - 0x00000413, /* MC4_MISC0 */ - 0xc0000408, /* MC4_MISC1 */ - }; - - rdmsrl(MSR_K7_HWCR, hwcr); - - /* McStatusWrEn has to be set */ - need_toggle = !(hwcr & BIT(18)); - - if (need_toggle) - wrmsrl(MSR_K7_HWCR, hwcr | BIT(18)); - - /* Clear CntP bit safely */ - for (i = 0; i < ARRAY_SIZE(msrs); i++) - msr_clear_bit(msrs[i], 62); - - /* restore old settings */ - if (need_toggle) - wrmsrl(MSR_K7_HWCR, hwcr); - } } if (c->x86_vendor == X86_VENDOR_INTEL) { diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index dc3e26e905a3..65201e180fe0 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -165,6 +165,11 @@ static struct severity { SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), KERNEL ), + MCESEV( + PANIC, "Instruction fetch error in kernel", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR), + KERNEL + ), #endif MCESEV( PANIC, "Action required: unknown MCACOD", diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 97f9ada9ceda..5260185cbf7b 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -608,6 +608,8 @@ static int microcode_reload_late(void) if (ret > 0) microcode_check(); + pr_info("Reload completed, microcode revision: 0x%x\n", boot_cpu_data.microcode); + return ret; } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index e81a2db42df7..3fa238a137d2 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -328,6 +328,18 @@ static void __init ms_hyperv_init_platform(void) # ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu; # endif + + /* + * Hyper-V doesn't provide irq remapping for IO-APIC. To enable x2apic, + * set x2apic destination mode to physcial mode when x2apic is available + * and Hyper-V IOMMU driver makes sure cpus assigned with IO-APIC irqs + * have 8-bit APIC id. + */ +# ifdef CONFIG_X86_X2APIC + if (x2apic_supported()) + x2apic_phys = 1; +# endif + #endif } diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 822b7db634ee..e49b77283924 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -4,6 +4,7 @@ #include <linux/sched.h> #include <linux/kernfs.h> +#include <linux/fs_context.h> #include <linux/jump_label.h> #define MSR_IA32_L3_QOS_CFG 0xc81 @@ -40,6 +41,21 @@ #define RMID_VAL_ERROR BIT_ULL(63) #define RMID_VAL_UNAVAIL BIT_ULL(62) + +struct rdt_fs_context { + struct kernfs_fs_context kfc; + bool enable_cdpl2; + bool enable_cdpl3; + bool enable_mba_mbps; +}; + +static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) +{ + struct kernfs_fs_context *kfc = fc->fs_private; + + return container_of(kfc, struct rdt_fs_context, kfc); +} + DECLARE_STATIC_KEY_FALSE(rdt_enable_key); /** diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index f33f11f69078..1573a0a6b525 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -501,11 +501,8 @@ out_unlock: void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms) { unsigned long delay = msecs_to_jiffies(delay_ms); - struct rdt_resource *r; int cpu; - r = &rdt_resources_all[RDT_RESOURCE_L3]; - cpu = cpumask_any(&dom->cpu_mask); dom->cqm_work_cpu = cpu; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 8388adf241b2..399601eda8e4 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -24,6 +24,7 @@ #include <linux/cpu.h> #include <linux/debugfs.h> #include <linux/fs.h> +#include <linux/fs_parser.h> #include <linux/sysfs.h> #include <linux/kernfs.h> #include <linux/seq_buf.h> @@ -32,6 +33,7 @@ #include <linux/sched/task.h> #include <linux/slab.h> #include <linux/task_work.h> +#include <linux/user_namespace.h> #include <uapi/linux/magic.h> @@ -1858,46 +1860,6 @@ static void cdp_disable_all(void) cdpl2_disable(); } -static int parse_rdtgroupfs_options(char *data) -{ - char *token, *o = data; - int ret = 0; - - while ((token = strsep(&o, ",")) != NULL) { - if (!*token) { - ret = -EINVAL; - goto out; - } - - if (!strcmp(token, "cdp")) { - ret = cdpl3_enable(); - if (ret) - goto out; - } else if (!strcmp(token, "cdpl2")) { - ret = cdpl2_enable(); - if (ret) - goto out; - } else if (!strcmp(token, "mba_MBps")) { - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) - ret = set_mba_sc(true); - else - ret = -EINVAL; - if (ret) - goto out; - } else { - ret = -EINVAL; - goto out; - } - } - - return 0; - -out: - pr_err("Invalid mount option \"%s\"\n", token); - - return ret; -} - /* * We don't allow rdtgroup directories to be created anywhere * except the root directory. Thus when looking for the rdtgroup @@ -1969,13 +1931,27 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn, struct rdtgroup *prgrp, struct kernfs_node **mon_data_kn); -static struct dentry *rdt_mount(struct file_system_type *fs_type, - int flags, const char *unused_dev_name, - void *data) +static int rdt_enable_ctx(struct rdt_fs_context *ctx) +{ + int ret = 0; + + if (ctx->enable_cdpl2) + ret = cdpl2_enable(); + + if (!ret && ctx->enable_cdpl3) + ret = cdpl3_enable(); + + if (!ret && ctx->enable_mba_mbps) + ret = set_mba_sc(true); + + return ret; +} + +static int rdt_get_tree(struct fs_context *fc) { + struct rdt_fs_context *ctx = rdt_fc2context(fc); struct rdt_domain *dom; struct rdt_resource *r; - struct dentry *dentry; int ret; cpus_read_lock(); @@ -1984,53 +1960,42 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, * resctrl file system can only be mounted once. */ if (static_branch_unlikely(&rdt_enable_key)) { - dentry = ERR_PTR(-EBUSY); + ret = -EBUSY; goto out; } - ret = parse_rdtgroupfs_options(data); - if (ret) { - dentry = ERR_PTR(ret); + ret = rdt_enable_ctx(ctx); + if (ret < 0) goto out_cdp; - } closid_init(); ret = rdtgroup_create_info_dir(rdtgroup_default.kn); - if (ret) { - dentry = ERR_PTR(ret); - goto out_cdp; - } + if (ret < 0) + goto out_mba; if (rdt_mon_capable) { ret = mongroup_create_dir(rdtgroup_default.kn, NULL, "mon_groups", &kn_mongrp); - if (ret) { - dentry = ERR_PTR(ret); + if (ret < 0) goto out_info; - } kernfs_get(kn_mongrp); ret = mkdir_mondata_all(rdtgroup_default.kn, &rdtgroup_default, &kn_mondata); - if (ret) { - dentry = ERR_PTR(ret); + if (ret < 0) goto out_mongrp; - } kernfs_get(kn_mondata); rdtgroup_default.mon.mon_data_kn = kn_mondata; } ret = rdt_pseudo_lock_init(); - if (ret) { - dentry = ERR_PTR(ret); + if (ret) goto out_mondata; - } - dentry = kernfs_mount(fs_type, flags, rdt_root, - RDTGROUP_SUPER_MAGIC, NULL); - if (IS_ERR(dentry)) + ret = kernfs_get_tree(fc); + if (ret < 0) goto out_psl; if (rdt_alloc_capable) @@ -2059,14 +2024,95 @@ out_mongrp: kernfs_remove(kn_mongrp); out_info: kernfs_remove(kn_info); +out_mba: + if (ctx->enable_mba_mbps) + set_mba_sc(false); out_cdp: cdp_disable_all(); out: rdt_last_cmd_clear(); mutex_unlock(&rdtgroup_mutex); cpus_read_unlock(); + return ret; +} + +enum rdt_param { + Opt_cdp, + Opt_cdpl2, + Opt_mba_mpbs, + nr__rdt_params +}; + +static const struct fs_parameter_spec rdt_param_specs[] = { + fsparam_flag("cdp", Opt_cdp), + fsparam_flag("cdpl2", Opt_cdpl2), + fsparam_flag("mba_mpbs", Opt_mba_mpbs), + {} +}; + +static const struct fs_parameter_description rdt_fs_parameters = { + .name = "rdt", + .specs = rdt_param_specs, +}; + +static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct rdt_fs_context *ctx = rdt_fc2context(fc); + struct fs_parse_result result; + int opt; + + opt = fs_parse(fc, &rdt_fs_parameters, param, &result); + if (opt < 0) + return opt; - return dentry; + switch (opt) { + case Opt_cdp: + ctx->enable_cdpl3 = true; + return 0; + case Opt_cdpl2: + ctx->enable_cdpl2 = true; + return 0; + case Opt_mba_mpbs: + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return -EINVAL; + ctx->enable_mba_mbps = true; + return 0; + } + + return -EINVAL; +} + +static void rdt_fs_context_free(struct fs_context *fc) +{ + struct rdt_fs_context *ctx = rdt_fc2context(fc); + + kernfs_free_fs_context(fc); + kfree(ctx); +} + +static const struct fs_context_operations rdt_fs_context_ops = { + .free = rdt_fs_context_free, + .parse_param = rdt_parse_param, + .get_tree = rdt_get_tree, +}; + +static int rdt_init_fs_context(struct fs_context *fc) +{ + struct rdt_fs_context *ctx; + + ctx = kzalloc(sizeof(struct rdt_fs_context), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->kfc.root = rdt_root; + ctx->kfc.magic = RDTGROUP_SUPER_MAGIC; + fc->fs_private = &ctx->kfc; + fc->ops = &rdt_fs_context_ops; + if (fc->user_ns) + put_user_ns(fc->user_ns); + fc->user_ns = get_user_ns(&init_user_ns); + fc->global = true; + return 0; } static int reset_all_ctrls(struct rdt_resource *r) @@ -2239,9 +2285,10 @@ static void rdt_kill_sb(struct super_block *sb) } static struct file_system_type rdt_fs_type = { - .name = "resctrl", - .mount = rdt_mount, - .kill_sb = rdt_kill_sb, + .name = "resctrl", + .init_fs_context = rdt_init_fs_context, + .parameters = &rdt_fs_parameters, + .kill_sb = rdt_kill_sb, }; static int mon_addfile(struct kernfs_node *parent_kn, const char *name, diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index a687d10da417..2879e234e193 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -14,6 +14,7 @@ #include <linux/acpi.h> #include <linux/firmware-map.h> #include <linux/sort.h> +#include <linux/memory_hotplug.h> #include <asm/e820/api.h> #include <asm/setup.h> @@ -775,7 +776,7 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align) { u64 addr; - addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); + addr = memblock_phys_alloc(size, align); if (addr) { e820__range_update_kexec(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); pr_info("update e820_table_kexec for e820__memblock_alloc_reserved()\n"); @@ -878,6 +879,10 @@ static int __init parse_memopt(char *p) e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1); +#ifdef CONFIG_MEMORY_HOTPLUG + max_mem_size = mem_size; +#endif + return 0; } early_param("mem", parse_memopt); @@ -1092,6 +1097,9 @@ void __init e820__reserve_resources(void) res = memblock_alloc(sizeof(*res) * e820_table->nr_entries, SMP_CACHE_BYTES); + if (!res) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(*res) * e820_table->nr_entries); e820_res = res; for (i = 0; i < e820_table->nr_entries; i++) { diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 3e3789c8f8e1..ef49517f6bb2 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -49,7 +49,7 @@ int ftrace_arch_code_modify_post_process(void) union ftrace_code_union { char code[MCOUNT_INSN_SIZE]; struct { - unsigned char e8; + unsigned char op; int offset; } __attribute__((packed)); }; @@ -59,20 +59,23 @@ static int ftrace_calc_offset(long ip, long addr) return (int)(addr - ip); } -static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +static unsigned char * +ftrace_text_replace(unsigned char op, unsigned long ip, unsigned long addr) { static union ftrace_code_union calc; - calc.e8 = 0xe8; + calc.op = op; calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); - /* - * No locking needed, this must be called via kstop_machine - * which in essence is like running on a uniprocessor machine. - */ return calc.code; } +static unsigned char * +ftrace_call_replace(unsigned long ip, unsigned long addr) +{ + return ftrace_text_replace(0xe8, ip, addr); +} + static inline int within(unsigned long addr, unsigned long start, unsigned long end) { @@ -665,22 +668,6 @@ int __init ftrace_dyn_arch_init(void) return 0; } -#if defined(CONFIG_X86_64) || defined(CONFIG_FUNCTION_GRAPH_TRACER) -static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) -{ - static union ftrace_code_union calc; - - /* Jmp not a call (ignore the .e8) */ - calc.e8 = 0xe9; - calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); - - /* - * ftrace external locks synchronize the access to the static variable. - */ - return calc.code; -} -#endif - /* Currently only x86_64 supports dynamic trampolines */ #ifdef CONFIG_X86_64 @@ -892,8 +879,8 @@ static void *addr_from_call(void *ptr) return NULL; /* Make sure this is a call */ - if (WARN_ON_ONCE(calc.e8 != 0xe8)) { - pr_warn("Expected e8, got %x\n", calc.e8); + if (WARN_ON_ONCE(calc.op != 0xe8)) { + pr_warn("Expected e8, got %x\n", calc.op); return NULL; } @@ -964,6 +951,11 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops) #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_graph_call(void); +static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) +{ + return ftrace_text_replace(0xe9, ip, addr); +} + static int ftrace_mod_jmp(unsigned long ip, void *func) { unsigned char *new; diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index dfd3aca82c61..fb32925a2e62 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -905,6 +905,8 @@ int __init hpet_enable(void) return 0; hpet_set_mapping(); + if (!hpet_virt_address) + return 0; /* * Read the period and check for a sane value: diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index ff9bfd40429e..d73083021002 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -354,6 +354,7 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, #endif default: WARN_ON_ONCE(1); + return -EINVAL; } /* diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 1f3b77367948..22f60dd26460 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -538,9 +538,17 @@ static int bzImage64_cleanup(void *loader_data) #ifdef CONFIG_KEXEC_BZIMAGE_VERIFY_SIG static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) { - return verify_pefile_signature(kernel, kernel_len, - VERIFY_USE_SECONDARY_KEYRING, - VERIFYING_KEXEC_PE_SIGNATURE); + int ret; + + ret = verify_pefile_signature(kernel, kernel_len, + VERIFY_USE_SECONDARY_KEYRING, + VERIFYING_KEXEC_PE_SIGNATURE); + if (ret == -ENOKEY && IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING)) { + ret = verify_pefile_signature(kernel, kernel_len, + VERIFY_USE_PLATFORM_KEYRING, + VERIFYING_KEXEC_PE_SIGNATURE); + } + return ret; } #endif diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index e811d4d1c824..904494b924c1 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -104,12 +104,8 @@ static u64 kvm_sched_clock_read(void) static inline void kvm_sched_clock_init(bool stable) { - if (!stable) { - pv_ops.time.sched_clock = kvm_clock_read; + if (!stable) clear_sched_clock_stable(); - return; - } - kvm_sched_clock_offset = kvm_clock_read(); pv_ops.time.sched_clock = kvm_sched_clock_read; @@ -355,6 +351,20 @@ void __init kvmclock_init(void) machine_ops.crash_shutdown = kvm_crash_shutdown; #endif kvm_get_preset_lpj(); + + /* + * X86_FEATURE_NONSTOP_TSC is TSC runs at constant rate + * with P/T states and does not stop in deep C-states. + * + * Invariant TSC exposed by host means kvmclock is not necessary: + * can use TSC as clocksource. + * + */ + if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && + boot_cpu_has(X86_FEATURE_NONSTOP_TSC) && + !check_tsc_unstable()) + kvm_clock.rating = 299; + clocksource_register_hz(&kvm_clock, NSEC_PER_SEC); pv_info.name = "KVM"; } diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 3482460d984d..1bfe5c6e6cfe 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -598,8 +598,8 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) mpf_base = base; mpf_found = true; - pr_info("found SMP MP-table at [mem %#010lx-%#010lx] mapped at [%p]\n", - base, base + sizeof(*mpf) - 1, mpf); + pr_info("found SMP MP-table at [mem %#010lx-%#010lx]\n", + base, base + sizeof(*mpf) - 1); memblock_reserve(base, sizeof(*mpf)); if (mpf->physptr) diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 13af08827eef..4bf46575568a 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -106,22 +106,22 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size, void *ptr; if (!node_online(node) || !NODE_DATA(node)) { - ptr = memblock_alloc_from_nopanic(size, align, goal); + ptr = memblock_alloc_from(size, align, goal); pr_info("cpu %d has no node %d or node-local memory\n", cpu, node); pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n", cpu, size, __pa(ptr)); } else { - ptr = memblock_alloc_try_nid_nopanic(size, align, goal, - MEMBLOCK_ALLOC_ACCESSIBLE, - node); + ptr = memblock_alloc_try_nid(size, align, goal, + MEMBLOCK_ALLOC_ACCESSIBLE, + node); pr_debug("per cpu data for cpu%d %lu bytes on node%d at %016lx\n", cpu, size, node, __pa(ptr)); } return ptr; #else - return memblock_alloc_from_nopanic(size, align, goal); + return memblock_alloc_from(size, align, goal); #endif } diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index 3dc26f95d46e..9b9fd4826e7a 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -320,10 +320,14 @@ bool unwind_next_frame(struct unwind_state *state) } /* Get the next frame pointer: */ - if (state->regs) + if (state->next_bp) { + next_bp = state->next_bp; + state->next_bp = NULL; + } else if (state->regs) { next_bp = (unsigned long *)state->regs->bp; - else + } else { next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task, *state->bp); + } /* Move to the next frame if it's safe: */ if (!update_stack_state(state, next_bp)) @@ -398,6 +402,21 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, bp = get_frame_pointer(task, regs); + /* + * If we crash with IP==0, the last successfully executed instruction + * was probably an indirect function call with a NULL function pointer. + * That means that SP points into the middle of an incomplete frame: + * *SP is a return pointer, and *(SP-sizeof(unsigned long)) is where we + * would have written a frame pointer if we hadn't crashed. + * Pretend that the frame is complete and that BP points to it, but save + * the real BP so that we can use it when looking for the next frame. + */ + if (regs && regs->ip == 0 && + (unsigned long *)kernel_stack_pointer(regs) >= first_frame) { + state->next_bp = bp; + bp = ((unsigned long *)kernel_stack_pointer(regs)) - 1; + } + /* Initialize stack info and make sure the frame data is accessible: */ get_stack_info(bp, state->task, &state->stack_info, &state->stack_mask); @@ -410,7 +429,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, */ while (!unwind_done(state) && (!on_stack(&state->stack_info, first_frame, sizeof(long)) || - state->bp < first_frame)) + (state->next_bp == NULL && state->bp < first_frame))) unwind_next_frame(state); } EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 26038eacf74a..89be1be1790c 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -113,6 +113,20 @@ static struct orc_entry *orc_ftrace_find(unsigned long ip) } #endif +/* + * If we crash with IP==0, the last successfully executed instruction + * was probably an indirect function call with a NULL function pointer, + * and we don't have unwind information for NULL. + * This hardcoded ORC entry for IP==0 allows us to unwind from a NULL function + * pointer into its parent and then continue normally from there. + */ +static struct orc_entry null_orc_entry = { + .sp_offset = sizeof(long), + .sp_reg = ORC_REG_SP, + .bp_reg = ORC_REG_UNDEFINED, + .type = ORC_TYPE_CALL +}; + static struct orc_entry *orc_find(unsigned long ip) { static struct orc_entry *orc; @@ -120,6 +134,9 @@ static struct orc_entry *orc_find(unsigned long ip) if (!orc_init) return NULL; + if (ip == 0) + return &null_orc_entry; + /* For non-init vmlinux addresses, use the fast lookup table: */ if (ip >= LOOKUP_START_IP && ip < LOOKUP_STOP_IP) { unsigned int idx, start, stop; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index c07958b59f50..fd3951638ae4 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -405,7 +405,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | - F(CLDEMOTE); + F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B); /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 89d20ed1d2e8..421899f6ad7b 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -526,7 +526,9 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, new_config.enable = 0; stimer->config.as_uint64 = new_config.as_uint64; - stimer_mark_pending(stimer, false); + if (stimer->config.enable) + stimer_mark_pending(stimer, false); + return 0; } @@ -542,7 +544,10 @@ static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, stimer->config.enable = 0; else if (stimer->config.auto_enable) stimer->config.enable = 1; - stimer_mark_pending(stimer, false); + + if (stimer->config.enable) + stimer_mark_pending(stimer, false); + return 0; } @@ -1729,7 +1734,7 @@ static int kvm_hv_eventfd_assign(struct kvm *kvm, u32 conn_id, int fd) mutex_lock(&hv->hv_lock); ret = idr_alloc(&hv->conn_to_evt, eventfd, conn_id, conn_id + 1, - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); mutex_unlock(&hv->hv_lock); if (ret >= 0) diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index af192895b1fc..4a6dc54cc12b 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -653,7 +653,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) pid_t pid_nr; int ret; - pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL); + pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL_ACCOUNT); if (!pit) return NULL; diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index bdcd4139eca9..8b38bb4868a6 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -583,7 +583,7 @@ int kvm_pic_init(struct kvm *kvm) struct kvm_pic *s; int ret; - s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL); + s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL_ACCOUNT); if (!s) return -ENOMEM; spin_lock_init(&s->lock); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 4e822ad363f3..1add1bc881e2 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -622,7 +622,7 @@ int kvm_ioapic_init(struct kvm *kvm) struct kvm_ioapic *ioapic; int ret; - ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL); + ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL_ACCOUNT); if (!ioapic) return -ENOMEM; spin_lock_init(&ioapic->lock); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4b6c2da7265c..991fdf7fc17f 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -181,7 +181,8 @@ static void recalculate_apic_map(struct kvm *kvm) max_id = max(max_id, kvm_x2apic_id(vcpu->arch.apic)); new = kvzalloc(sizeof(struct kvm_apic_map) + - sizeof(struct kvm_lapic *) * ((u64)max_id + 1), GFP_KERNEL); + sizeof(struct kvm_lapic *) * ((u64)max_id + 1), + GFP_KERNEL_ACCOUNT); if (!new) goto out; @@ -2259,13 +2260,13 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) ASSERT(vcpu != NULL); apic_debug("apic_init %d\n", vcpu->vcpu_id); - apic = kzalloc(sizeof(*apic), GFP_KERNEL); + apic = kzalloc(sizeof(*apic), GFP_KERNEL_ACCOUNT); if (!apic) goto nomem; vcpu->arch.apic = apic; - apic->regs = (void *)get_zeroed_page(GFP_KERNEL); + apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!apic->regs) { printk(KERN_ERR "malloc apic regs error for vcpu %x\n", vcpu->vcpu_id); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index f2d1d230d5b8..eee455a8a612 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -109,9 +109,11 @@ module_param(dbg, bool, 0644); (((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1)) -#define PT64_BASE_ADDR_MASK __sme_clr((((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))) -#define PT64_DIR_BASE_ADDR_MASK \ - (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1)) +#ifdef CONFIG_DYNAMIC_PHYSICAL_MASK +#define PT64_BASE_ADDR_MASK (physical_mask & ~(u64)(PAGE_SIZE-1)) +#else +#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)) +#endif #define PT64_LVL_ADDR_MASK(level) \ (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \ * PT64_LEVEL_BITS))) - 1)) @@ -180,7 +182,7 @@ struct kvm_shadow_walk_iterator { static const union kvm_mmu_page_role mmu_base_role_mask = { .cr0_wp = 1, - .cr4_pae = 1, + .gpte_is_8_bytes = 1, .nxe = 1, .smep_andnot_wp = 1, .smap_andnot_wp = 1, @@ -330,53 +332,56 @@ static inline bool is_access_track_spte(u64 spte) } /* - * the low bit of the generation number is always presumed to be zero. - * This disables mmio caching during memslot updates. The concept is - * similar to a seqcount but instead of retrying the access we just punt - * and ignore the cache. + * Due to limited space in PTEs, the MMIO generation is a 19 bit subset of + * the memslots generation and is derived as follows: * - * spte bits 3-11 are used as bits 1-9 of the generation number, - * the bits 52-61 are used as bits 10-19 of the generation number. + * Bits 0-8 of the MMIO generation are propagated to spte bits 3-11 + * Bits 9-18 of the MMIO generation are propagated to spte bits 52-61 + * + * The KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS flag is intentionally not included in + * the MMIO generation number, as doing so would require stealing a bit from + * the "real" generation number and thus effectively halve the maximum number + * of MMIO generations that can be handled before encountering a wrap (which + * requires a full MMU zap). The flag is instead explicitly queried when + * checking for MMIO spte cache hits. */ -#define MMIO_SPTE_GEN_LOW_SHIFT 2 -#define MMIO_SPTE_GEN_HIGH_SHIFT 52 +#define MMIO_SPTE_GEN_MASK GENMASK_ULL(18, 0) -#define MMIO_GEN_SHIFT 20 -#define MMIO_GEN_LOW_SHIFT 10 -#define MMIO_GEN_LOW_MASK ((1 << MMIO_GEN_LOW_SHIFT) - 2) -#define MMIO_GEN_MASK ((1 << MMIO_GEN_SHIFT) - 1) +#define MMIO_SPTE_GEN_LOW_START 3 +#define MMIO_SPTE_GEN_LOW_END 11 +#define MMIO_SPTE_GEN_LOW_MASK GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \ + MMIO_SPTE_GEN_LOW_START) -static u64 generation_mmio_spte_mask(unsigned int gen) +#define MMIO_SPTE_GEN_HIGH_START 52 +#define MMIO_SPTE_GEN_HIGH_END 61 +#define MMIO_SPTE_GEN_HIGH_MASK GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \ + MMIO_SPTE_GEN_HIGH_START) +static u64 generation_mmio_spte_mask(u64 gen) { u64 mask; - WARN_ON(gen & ~MMIO_GEN_MASK); + WARN_ON(gen & ~MMIO_SPTE_GEN_MASK); - mask = (gen & MMIO_GEN_LOW_MASK) << MMIO_SPTE_GEN_LOW_SHIFT; - mask |= ((u64)gen >> MMIO_GEN_LOW_SHIFT) << MMIO_SPTE_GEN_HIGH_SHIFT; + mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK; + mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK; return mask; } -static unsigned int get_mmio_spte_generation(u64 spte) +static u64 get_mmio_spte_generation(u64 spte) { - unsigned int gen; + u64 gen; spte &= ~shadow_mmio_mask; - gen = (spte >> MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_GEN_LOW_MASK; - gen |= (spte >> MMIO_SPTE_GEN_HIGH_SHIFT) << MMIO_GEN_LOW_SHIFT; + gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_START; + gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_START; return gen; } -static unsigned int kvm_current_mmio_generation(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_memslots(vcpu)->generation & MMIO_GEN_MASK; -} - static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, unsigned access) { - unsigned int gen = kvm_current_mmio_generation(vcpu); + u64 gen = kvm_vcpu_memslots(vcpu)->generation & MMIO_SPTE_GEN_MASK; u64 mask = generation_mmio_spte_mask(gen); u64 gpa = gfn << PAGE_SHIFT; @@ -386,6 +391,8 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, mask |= (gpa & shadow_nonpresent_or_rsvd_mask) << shadow_nonpresent_or_rsvd_mask_len; + page_header(__pa(sptep))->mmio_cached = true; + trace_mark_mmio_spte(sptep, gfn, access, gen); mmu_spte_set(sptep, mask); } @@ -407,7 +414,7 @@ static gfn_t get_mmio_spte_gfn(u64 spte) static unsigned get_mmio_spte_access(u64 spte) { - u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask; + u64 mask = generation_mmio_spte_mask(MMIO_SPTE_GEN_MASK) | shadow_mmio_mask; return (spte & ~mask) & ~PAGE_MASK; } @@ -424,9 +431,13 @@ static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) { - unsigned int kvm_gen, spte_gen; + u64 kvm_gen, spte_gen, gen; + + gen = kvm_vcpu_memslots(vcpu)->generation; + if (unlikely(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS)) + return false; - kvm_gen = kvm_current_mmio_generation(vcpu); + kvm_gen = gen & MMIO_SPTE_GEN_MASK; spte_gen = get_mmio_spte_generation(spte); trace_check_mmio_spte(spte, kvm_gen, spte_gen); @@ -959,7 +970,7 @@ static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, if (cache->nobjs >= min) return 0; while (cache->nobjs < ARRAY_SIZE(cache->objects)) { - obj = kmem_cache_zalloc(base_cache, GFP_KERNEL); + obj = kmem_cache_zalloc(base_cache, GFP_KERNEL_ACCOUNT); if (!obj) return cache->nobjs >= min ? 0 : -ENOMEM; cache->objects[cache->nobjs++] = obj; @@ -2049,12 +2060,6 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, int direct if (!direct) sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); - - /* - * The active_mmu_pages list is the FIFO list, do not move the - * page until it is zapped. kvm_zap_obsolete_pages depends on - * this feature. See the comments in kvm_zap_obsolete_pages(). - */ list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); kvm_mod_used_mmu_pages(vcpu->kvm, +1); return sp; @@ -2195,35 +2200,33 @@ static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) --kvm->stat.mmu_unsync; } -static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, - struct list_head *invalid_list); +static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, + struct list_head *invalid_list); static void kvm_mmu_commit_zap_page(struct kvm *kvm, struct list_head *invalid_list); -/* - * NOTE: we should pay more attention on the zapped-obsolete page - * (is_obsolete_sp(sp) && sp->role.invalid) when you do hash list walk - * since it has been deleted from active_mmu_pages but still can be found - * at hast list. - * - * for_each_valid_sp() has skipped that kind of pages. - */ + #define for_each_valid_sp(_kvm, _sp, _gfn) \ hlist_for_each_entry(_sp, \ &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \ - if (is_obsolete_sp((_kvm), (_sp)) || (_sp)->role.invalid) { \ + if ((_sp)->role.invalid) { \ } else #define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn) \ for_each_valid_sp(_kvm, _sp, _gfn) \ if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else +static inline bool is_ept_sp(struct kvm_mmu_page *sp) +{ + return sp->role.cr0_wp && sp->role.smap_andnot_wp; +} + /* @sp->gfn should be write-protected at the call site */ static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { - if (sp->role.cr4_pae != !!is_pae(vcpu) - || vcpu->arch.mmu->sync_page(vcpu, sp) == 0) { + if ((!is_ept_sp(sp) && sp->role.gpte_is_8_bytes != !!is_pae(vcpu)) || + vcpu->arch.mmu->sync_page(vcpu, sp) == 0) { kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); return false; } @@ -2231,18 +2234,28 @@ static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, return true; } +static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm, + struct list_head *invalid_list, + bool remote_flush) +{ + if (!remote_flush && !list_empty(invalid_list)) + return false; + + if (!list_empty(invalid_list)) + kvm_mmu_commit_zap_page(kvm, invalid_list); + else + kvm_flush_remote_tlbs(kvm); + return true; +} + static void kvm_mmu_flush_or_zap(struct kvm_vcpu *vcpu, struct list_head *invalid_list, bool remote_flush, bool local_flush) { - if (!list_empty(invalid_list)) { - kvm_mmu_commit_zap_page(vcpu->kvm, invalid_list); + if (kvm_mmu_remote_flush_or_zap(vcpu->kvm, invalid_list, remote_flush)) return; - } - if (remote_flush) - kvm_flush_remote_tlbs(vcpu->kvm); - else if (local_flush) + if (local_flush) kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } @@ -2253,11 +2266,6 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { } static void mmu_audit_disable(void) { } #endif -static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) -{ - return unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); -} - static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { @@ -2421,7 +2429,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, role.level = level; role.direct = direct; if (role.direct) - role.cr4_pae = 0; + role.gpte_is_8_bytes = true; role.access = access; if (!vcpu->arch.mmu->direct_map && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) { @@ -2482,7 +2490,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, if (level > PT_PAGE_TABLE_LEVEL && need_sync) flush |= kvm_sync_pages(vcpu, gfn, &invalid_list); } - sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen; clear_page(sp->spt); trace_kvm_mmu_get_page(sp, true); @@ -2668,17 +2675,22 @@ static int mmu_zap_unsync_children(struct kvm *kvm, return zapped; } -static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, - struct list_head *invalid_list) +static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, + struct kvm_mmu_page *sp, + struct list_head *invalid_list, + int *nr_zapped) { - int ret; + bool list_unstable; trace_kvm_mmu_prepare_zap_page(sp); ++kvm->stat.mmu_shadow_zapped; - ret = mmu_zap_unsync_children(kvm, sp, invalid_list); + *nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list); kvm_mmu_page_unlink_children(kvm, sp); kvm_mmu_unlink_parents(kvm, sp); + /* Zapping children means active_mmu_pages has become unstable. */ + list_unstable = *nr_zapped; + if (!sp->role.invalid && !sp->role.direct) unaccount_shadowed(kvm, sp); @@ -2686,22 +2698,27 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, kvm_unlink_unsync_page(kvm, sp); if (!sp->root_count) { /* Count self */ - ret++; + (*nr_zapped)++; list_move(&sp->link, invalid_list); kvm_mod_used_mmu_pages(kvm, -1); } else { list_move(&sp->link, &kvm->arch.active_mmu_pages); - /* - * The obsolete pages can not be used on any vcpus. - * See the comments in kvm_mmu_invalidate_zap_all_pages(). - */ - if (!sp->role.invalid && !is_obsolete_sp(kvm, sp)) + if (!sp->role.invalid) kvm_reload_remote_mmus(kvm); } sp->role.invalid = 1; - return ret; + return list_unstable; +} + +static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, + struct list_head *invalid_list) +{ + int nr_zapped; + + __kvm_mmu_prepare_zap_page(kvm, sp, invalid_list, &nr_zapped); + return nr_zapped; } static void kvm_mmu_commit_zap_page(struct kvm *kvm, @@ -3703,7 +3720,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) u64 *lm_root; - lm_root = (void*)get_zeroed_page(GFP_KERNEL); + lm_root = (void*)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (lm_root == NULL) return 1; @@ -4204,14 +4221,6 @@ static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3, return false; if (cached_root_available(vcpu, new_cr3, new_role)) { - /* - * It is possible that the cached previous root page is - * obsolete because of a change in the MMU - * generation number. However, that is accompanied by - * KVM_REQ_MMU_RELOAD, which will free the root that we - * have set here and allocate a new one. - */ - kvm_make_request(KVM_REQ_LOAD_CR3, vcpu); if (!skip_tlb_flush) { kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); @@ -4791,7 +4800,6 @@ static union kvm_mmu_role kvm_calc_mmu_role_common(struct kvm_vcpu *vcpu, role.base.access = ACC_ALL; role.base.nxe = !!is_nx(vcpu); - role.base.cr4_pae = !!is_pae(vcpu); role.base.cr0_wp = is_write_protection(vcpu); role.base.smm = is_smm(vcpu); role.base.guest_mode = is_guest_mode(vcpu); @@ -4812,6 +4820,7 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only) role.base.ad_disabled = (shadow_accessed_mask == 0); role.base.level = kvm_x86_ops->get_tdp_level(vcpu); role.base.direct = true; + role.base.gpte_is_8_bytes = true; return role; } @@ -4876,6 +4885,7 @@ kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only) role.base.smap_andnot_wp = role.ext.cr4_smap && !is_write_protection(vcpu); role.base.direct = !is_paging(vcpu); + role.base.gpte_is_8_bytes = !!is_pae(vcpu); if (!is_long_mode(vcpu)) role.base.level = PT32E_ROOT_LEVEL; @@ -4915,18 +4925,26 @@ static union kvm_mmu_role kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, bool execonly) { - union kvm_mmu_role role; + union kvm_mmu_role role = {0}; - /* Base role is inherited from root_mmu */ - role.base.word = vcpu->arch.root_mmu.mmu_role.base.word; - role.ext = kvm_calc_mmu_role_ext(vcpu); + /* SMM flag is inherited from root_mmu */ + role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm; role.base.level = PT64_ROOT_4LEVEL; + role.base.gpte_is_8_bytes = true; role.base.direct = false; role.base.ad_disabled = !accessed_dirty; role.base.guest_mode = true; role.base.access = ACC_ALL; + /* + * WP=1 and NOT_WP=1 is an impossible combination, use WP and the + * SMAP variation to denote shadow EPT entries. + */ + role.base.cr0_wp = true; + role.base.smap_andnot_wp = true; + + role.ext = kvm_calc_mmu_role_ext(vcpu); role.ext.execonly = execonly; return role; @@ -5176,7 +5194,7 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa, gpa, bytes, sp->role.word); offset = offset_in_page(gpa); - pte_size = sp->role.cr4_pae ? 8 : 4; + pte_size = sp->role.gpte_is_8_bytes ? 8 : 4; /* * Sometimes, the OS only writes the last one bytes to update status @@ -5200,7 +5218,7 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) page_offset = offset_in_page(gpa); level = sp->role.level; *nspte = 1; - if (!sp->role.cr4_pae) { + if (!sp->role.gpte_is_8_bytes) { page_offset <<= 1; /* 32->64 */ /* * A 32-bit pde maps 4MB while the shadow pdes map @@ -5390,10 +5408,12 @@ emulate: * This can happen if a guest gets a page-fault on data access but the HW * table walker is not able to read the instruction page (e.g instruction * page is not present in memory). In those cases we simply restart the - * guest. + * guest, with the exception of AMD Erratum 1096 which is unrecoverable. */ - if (unlikely(insn && !insn_len)) - return 1; + if (unlikely(insn && !insn_len)) { + if (!kvm_x86_ops->need_emulation_on_page_fault(vcpu)) + return 1; + } er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len); @@ -5486,6 +5506,79 @@ void kvm_disable_tdp(void) } EXPORT_SYMBOL_GPL(kvm_disable_tdp); + +/* The return value indicates if tlb flush on all vcpus is needed. */ +typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); + +/* The caller should hold mmu-lock before calling this function. */ +static __always_inline bool +slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, int start_level, int end_level, + gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb) +{ + struct slot_rmap_walk_iterator iterator; + bool flush = false; + + for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn, + end_gfn, &iterator) { + if (iterator.rmap) + flush |= fn(kvm, iterator.rmap); + + if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { + if (flush && lock_flush_tlb) { + kvm_flush_remote_tlbs_with_address(kvm, + start_gfn, + iterator.gfn - start_gfn + 1); + flush = false; + } + cond_resched_lock(&kvm->mmu_lock); + } + } + + if (flush && lock_flush_tlb) { + kvm_flush_remote_tlbs_with_address(kvm, start_gfn, + end_gfn - start_gfn + 1); + flush = false; + } + + return flush; +} + +static __always_inline bool +slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, int start_level, int end_level, + bool lock_flush_tlb) +{ + return slot_handle_level_range(kvm, memslot, fn, start_level, + end_level, memslot->base_gfn, + memslot->base_gfn + memslot->npages - 1, + lock_flush_tlb); +} + +static __always_inline bool +slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, bool lock_flush_tlb) +{ + return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, + PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); +} + +static __always_inline bool +slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, bool lock_flush_tlb) +{ + return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL + 1, + PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); +} + +static __always_inline bool +slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, bool lock_flush_tlb) +{ + return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, + PT_PAGE_TABLE_LEVEL, lock_flush_tlb); +} + static void free_mmu_pages(struct kvm_vcpu *vcpu) { free_page((unsigned long)vcpu->arch.mmu->pae_root); @@ -5505,7 +5598,7 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu) * Therefore we need to allocate shadow page tables in the first * 4GB of memory, which happens to fit the DMA32 zone. */ - page = alloc_page(GFP_KERNEL | __GFP_DMA32); + page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_DMA32); if (!page) return -ENOMEM; @@ -5543,105 +5636,62 @@ static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, struct kvm_page_track_notifier_node *node) { - kvm_mmu_invalidate_zap_all_pages(kvm); -} - -void kvm_mmu_init_vm(struct kvm *kvm) -{ - struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; - - node->track_write = kvm_mmu_pte_write; - node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot; - kvm_page_track_register_notifier(kvm, node); -} + struct kvm_mmu_page *sp; + LIST_HEAD(invalid_list); + unsigned long i; + bool flush; + gfn_t gfn; -void kvm_mmu_uninit_vm(struct kvm *kvm) -{ - struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; + spin_lock(&kvm->mmu_lock); - kvm_page_track_unregister_notifier(kvm, node); -} + if (list_empty(&kvm->arch.active_mmu_pages)) + goto out_unlock; -/* The return value indicates if tlb flush on all vcpus is needed. */ -typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); + flush = slot_handle_all_level(kvm, slot, kvm_zap_rmapp, false); -/* The caller should hold mmu-lock before calling this function. */ -static __always_inline bool -slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, int start_level, int end_level, - gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb) -{ - struct slot_rmap_walk_iterator iterator; - bool flush = false; + for (i = 0; i < slot->npages; i++) { + gfn = slot->base_gfn + i; - for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn, - end_gfn, &iterator) { - if (iterator.rmap) - flush |= fn(kvm, iterator.rmap); + for_each_valid_sp(kvm, sp, gfn) { + if (sp->gfn != gfn) + continue; + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + } if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { - if (flush && lock_flush_tlb) { - kvm_flush_remote_tlbs(kvm); - flush = false; - } + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); + flush = false; cond_resched_lock(&kvm->mmu_lock); } } + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); - if (flush && lock_flush_tlb) { - kvm_flush_remote_tlbs(kvm); - flush = false; - } - - return flush; +out_unlock: + spin_unlock(&kvm->mmu_lock); } -static __always_inline bool -slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, int start_level, int end_level, - bool lock_flush_tlb) +void kvm_mmu_init_vm(struct kvm *kvm) { - return slot_handle_level_range(kvm, memslot, fn, start_level, - end_level, memslot->base_gfn, - memslot->base_gfn + memslot->npages - 1, - lock_flush_tlb); -} + struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; -static __always_inline bool -slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, bool lock_flush_tlb) -{ - return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, - PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); + node->track_write = kvm_mmu_pte_write; + node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot; + kvm_page_track_register_notifier(kvm, node); } -static __always_inline bool -slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, bool lock_flush_tlb) +void kvm_mmu_uninit_vm(struct kvm *kvm) { - return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL + 1, - PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); -} + struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; -static __always_inline bool -slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, bool lock_flush_tlb) -{ - return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, - PT_PAGE_TABLE_LEVEL, lock_flush_tlb); + kvm_page_track_unregister_notifier(kvm, node); } void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - bool flush_tlb = true; - bool flush = false; int i; - if (kvm_available_flush_tlb_with_range()) - flush_tlb = false; - spin_lock(&kvm->mmu_lock); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); @@ -5653,17 +5703,12 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) if (start >= end) continue; - flush |= slot_handle_level_range(kvm, memslot, - kvm_zap_rmapp, PT_PAGE_TABLE_LEVEL, - PT_MAX_HUGEPAGE_LEVEL, start, - end - 1, flush_tlb); + slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, + PT_PAGE_TABLE_LEVEL, PT_MAX_HUGEPAGE_LEVEL, + start, end - 1, true); } } - if (flush) - kvm_flush_remote_tlbs_with_address(kvm, gfn_start, - gfn_end - gfn_start + 1); - spin_unlock(&kvm->mmu_lock); } @@ -5815,101 +5860,58 @@ void kvm_mmu_slot_set_dirty(struct kvm *kvm, } EXPORT_SYMBOL_GPL(kvm_mmu_slot_set_dirty); -#define BATCH_ZAP_PAGES 10 -static void kvm_zap_obsolete_pages(struct kvm *kvm) +static void __kvm_mmu_zap_all(struct kvm *kvm, bool mmio_only) { struct kvm_mmu_page *sp, *node; - int batch = 0; + LIST_HEAD(invalid_list); + int ign; + spin_lock(&kvm->mmu_lock); restart: - list_for_each_entry_safe_reverse(sp, node, - &kvm->arch.active_mmu_pages, link) { - int ret; - - /* - * No obsolete page exists before new created page since - * active_mmu_pages is the FIFO list. - */ - if (!is_obsolete_sp(kvm, sp)) - break; - - /* - * Since we are reversely walking the list and the invalid - * list will be moved to the head, skip the invalid page - * can help us to avoid the infinity list walking. - */ - if (sp->role.invalid) + list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) { + if (mmio_only && !sp->mmio_cached) continue; - - /* - * Need not flush tlb since we only zap the sp with invalid - * generation number. - */ - if (batch >= BATCH_ZAP_PAGES && - cond_resched_lock(&kvm->mmu_lock)) { - batch = 0; + if (sp->role.invalid && sp->root_count) + continue; + if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign)) { + WARN_ON_ONCE(mmio_only); goto restart; } - - ret = kvm_mmu_prepare_zap_page(kvm, sp, - &kvm->arch.zapped_obsolete_pages); - batch += ret; - - if (ret) + if (cond_resched_lock(&kvm->mmu_lock)) goto restart; } - /* - * Should flush tlb before free page tables since lockless-walking - * may use the pages. - */ - kvm_mmu_commit_zap_page(kvm, &kvm->arch.zapped_obsolete_pages); -} - -/* - * Fast invalidate all shadow pages and use lock-break technique - * to zap obsolete pages. - * - * It's required when memslot is being deleted or VM is being - * destroyed, in these cases, we should ensure that KVM MMU does - * not use any resource of the being-deleted slot or all slots - * after calling the function. - */ -void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm) -{ - spin_lock(&kvm->mmu_lock); - trace_kvm_mmu_invalidate_zap_all_pages(kvm); - kvm->arch.mmu_valid_gen++; - - /* - * Notify all vcpus to reload its shadow page table - * and flush TLB. Then all vcpus will switch to new - * shadow page table with the new mmu_valid_gen. - * - * Note: we should do this under the protection of - * mmu-lock, otherwise, vcpu would purge shadow page - * but miss tlb flush. - */ - kvm_reload_remote_mmus(kvm); - - kvm_zap_obsolete_pages(kvm); + kvm_mmu_commit_zap_page(kvm, &invalid_list); spin_unlock(&kvm->mmu_lock); } -static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) +void kvm_mmu_zap_all(struct kvm *kvm) { - return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages)); + return __kvm_mmu_zap_all(kvm, false); } -void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots) +void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) { + WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); + + gen &= MMIO_SPTE_GEN_MASK; + /* - * The very rare case: if the generation-number is round, + * Generation numbers are incremented in multiples of the number of + * address spaces in order to provide unique generations across all + * address spaces. Strip what is effectively the address space + * modifier prior to checking for a wrap of the MMIO generation so + * that a wrap in any address space is detected. + */ + gen &= ~((u64)KVM_ADDRESS_SPACE_NUM - 1); + + /* + * The very rare case: if the MMIO generation number has wrapped, * zap all shadow pages. */ - if (unlikely((slots->generation & MMIO_GEN_MASK) == 0)) { + if (unlikely(gen == 0)) { kvm_debug_ratelimited("kvm: zapping shadow pages for mmio generation wraparound\n"); - kvm_mmu_invalidate_zap_all_pages(kvm); + __kvm_mmu_zap_all(kvm, true); } } @@ -5940,24 +5942,16 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) * want to shrink a VM that only started to populate its MMU * anyway. */ - if (!kvm->arch.n_used_mmu_pages && - !kvm_has_zapped_obsolete_pages(kvm)) + if (!kvm->arch.n_used_mmu_pages) continue; idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); - if (kvm_has_zapped_obsolete_pages(kvm)) { - kvm_mmu_commit_zap_page(kvm, - &kvm->arch.zapped_obsolete_pages); - goto unlock; - } - if (prepare_zap_oldest_mmu_page(kvm, &invalid_list)) freed++; kvm_mmu_commit_zap_page(kvm, &invalid_list); -unlock: spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); @@ -6037,7 +6031,7 @@ out: /* * Calculate mmu pages needed for kvm. */ -unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) +unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm) { unsigned int nr_mmu_pages; unsigned int nr_pages = 0; diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index c7b333147c4a..bbdc60f2fae8 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -203,7 +203,6 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, return -(u32)fault & errcode; } -void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm); void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end); void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index c73bf4e4988c..dd30dccd2ad5 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -8,18 +8,16 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvmmmu -#define KVM_MMU_PAGE_FIELDS \ - __field(unsigned long, mmu_valid_gen) \ - __field(__u64, gfn) \ - __field(__u32, role) \ - __field(__u32, root_count) \ +#define KVM_MMU_PAGE_FIELDS \ + __field(__u64, gfn) \ + __field(__u32, role) \ + __field(__u32, root_count) \ __field(bool, unsync) -#define KVM_MMU_PAGE_ASSIGN(sp) \ - __entry->mmu_valid_gen = sp->mmu_valid_gen; \ - __entry->gfn = sp->gfn; \ - __entry->role = sp->role.word; \ - __entry->root_count = sp->root_count; \ +#define KVM_MMU_PAGE_ASSIGN(sp) \ + __entry->gfn = sp->gfn; \ + __entry->role = sp->role.word; \ + __entry->root_count = sp->root_count; \ __entry->unsync = sp->unsync; #define KVM_MMU_PAGE_PRINTK() ({ \ @@ -31,11 +29,10 @@ \ role.word = __entry->role; \ \ - trace_seq_printf(p, "sp gen %lx gfn %llx l%u%s q%u%s %s%s" \ + trace_seq_printf(p, "sp gfn %llx l%u %u-byte q%u%s %s%s" \ " %snxe %sad root %u %s%c", \ - __entry->mmu_valid_gen, \ __entry->gfn, role.level, \ - role.cr4_pae ? " pae" : "", \ + role.gpte_is_8_bytes ? 8 : 4, \ role.quadrant, \ role.direct ? " direct" : "", \ access_str[role.access], \ @@ -283,27 +280,6 @@ TRACE_EVENT( ); TRACE_EVENT( - kvm_mmu_invalidate_zap_all_pages, - TP_PROTO(struct kvm *kvm), - TP_ARGS(kvm), - - TP_STRUCT__entry( - __field(unsigned long, mmu_valid_gen) - __field(unsigned int, mmu_used_pages) - ), - - TP_fast_assign( - __entry->mmu_valid_gen = kvm->arch.mmu_valid_gen; - __entry->mmu_used_pages = kvm->arch.n_used_mmu_pages; - ), - - TP_printk("kvm-mmu-valid-gen %lx used_pages %x", - __entry->mmu_valid_gen, __entry->mmu_used_pages - ) -); - - -TRACE_EVENT( check_mmio_spte, TP_PROTO(u64 spte, unsigned int kvm_gen, unsigned int spte_gen), TP_ARGS(spte, kvm_gen, spte_gen), diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c index 3052a59a3065..fd04d462fdae 100644 --- a/arch/x86/kvm/page_track.c +++ b/arch/x86/kvm/page_track.c @@ -42,7 +42,7 @@ int kvm_page_track_create_memslot(struct kvm_memory_slot *slot, for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) { slot->arch.gfn_track[i] = kvcalloc(npages, sizeof(*slot->arch.gfn_track[i]), - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!slot->arch.gfn_track[i]) goto track_free; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f13a3a24d360..426039285fd1 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -145,7 +145,6 @@ struct kvm_svm { /* Struct members for AVIC */ u32 avic_vm_id; - u32 ldr_mode; struct page *avic_logical_id_table_page; struct page *avic_physical_id_table_page; struct hlist_node hnode; @@ -236,6 +235,7 @@ struct vcpu_svm { bool nrips_enabled : 1; u32 ldr_reg; + u32 dfr_reg; struct page *avic_backing_page; u64 *avic_physical_id_cache; bool avic_is_running; @@ -1795,9 +1795,10 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, /* Avoid using vmalloc for smaller buffers. */ size = npages * sizeof(struct page *); if (size > PAGE_SIZE) - pages = vmalloc(size); + pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO, + PAGE_KERNEL); else - pages = kmalloc(size, GFP_KERNEL); + pages = kmalloc(size, GFP_KERNEL_ACCOUNT); if (!pages) return NULL; @@ -1865,7 +1866,9 @@ static void __unregister_enc_region_locked(struct kvm *kvm, static struct kvm *svm_vm_alloc(void) { - struct kvm_svm *kvm_svm = vzalloc(sizeof(struct kvm_svm)); + struct kvm_svm *kvm_svm = __vmalloc(sizeof(struct kvm_svm), + GFP_KERNEL_ACCOUNT | __GFP_ZERO, + PAGE_KERNEL); return &kvm_svm->kvm; } @@ -1940,7 +1943,7 @@ static int avic_vm_init(struct kvm *kvm) return 0; /* Allocating physical APIC ID table (4KB) */ - p_page = alloc_page(GFP_KERNEL); + p_page = alloc_page(GFP_KERNEL_ACCOUNT); if (!p_page) goto free_avic; @@ -1948,7 +1951,7 @@ static int avic_vm_init(struct kvm *kvm) clear_page(page_address(p_page)); /* Allocating logical APIC ID table (4KB) */ - l_page = alloc_page(GFP_KERNEL); + l_page = alloc_page(GFP_KERNEL_ACCOUNT); if (!l_page) goto free_avic; @@ -2106,6 +2109,7 @@ static int avic_init_vcpu(struct vcpu_svm *svm) INIT_LIST_HEAD(&svm->ir_list); spin_lock_init(&svm->ir_list_lock); + svm->dfr_reg = APIC_DFR_FLAT; return ret; } @@ -2119,13 +2123,14 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) struct page *nested_msrpm_pages; int err; - svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); if (!svm) { err = -ENOMEM; goto out; } - svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL); + svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); if (!svm->vcpu.arch.guest_fpu) { printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); err = -ENOMEM; @@ -2137,19 +2142,19 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) goto free_svm; err = -ENOMEM; - page = alloc_page(GFP_KERNEL); + page = alloc_page(GFP_KERNEL_ACCOUNT); if (!page) goto uninit; - msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); + msrpm_pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER); if (!msrpm_pages) goto free_page1; - nested_msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); + nested_msrpm_pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER); if (!nested_msrpm_pages) goto free_page2; - hsave_page = alloc_page(GFP_KERNEL); + hsave_page = alloc_page(GFP_KERNEL_ACCOUNT); if (!hsave_page) goto free_page3; @@ -4565,8 +4570,7 @@ static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat) return &logical_apic_id_table[index]; } -static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr, - bool valid) +static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr) { bool flat; u32 *entry, new_entry; @@ -4579,31 +4583,39 @@ static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr, new_entry = READ_ONCE(*entry); new_entry &= ~AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; new_entry |= (g_physical_id & AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK); - if (valid) - new_entry |= AVIC_LOGICAL_ID_ENTRY_VALID_MASK; - else - new_entry &= ~AVIC_LOGICAL_ID_ENTRY_VALID_MASK; + new_entry |= AVIC_LOGICAL_ID_ENTRY_VALID_MASK; WRITE_ONCE(*entry, new_entry); return 0; } +static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + bool flat = svm->dfr_reg == APIC_DFR_FLAT; + u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat); + + if (entry) + WRITE_ONCE(*entry, (u32) ~AVIC_LOGICAL_ID_ENTRY_VALID_MASK); +} + static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) { - int ret; + int ret = 0; struct vcpu_svm *svm = to_svm(vcpu); u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR); - if (!ldr) - return 1; + if (ldr == svm->ldr_reg) + return 0; - ret = avic_ldr_write(vcpu, vcpu->vcpu_id, ldr, true); - if (ret && svm->ldr_reg) { - avic_ldr_write(vcpu, 0, svm->ldr_reg, false); - svm->ldr_reg = 0; - } else { + avic_invalidate_logical_id_entry(vcpu); + + if (ldr) + ret = avic_ldr_write(vcpu, vcpu->vcpu_id, ldr); + + if (!ret) svm->ldr_reg = ldr; - } + return ret; } @@ -4637,27 +4649,16 @@ static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu) return 0; } -static int avic_handle_dfr_update(struct kvm_vcpu *vcpu) +static void avic_handle_dfr_update(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); u32 dfr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR); - u32 mod = (dfr >> 28) & 0xf; - - /* - * We assume that all local APICs are using the same type. - * If this changes, we need to flush the AVIC logical - * APID id table. - */ - if (kvm_svm->ldr_mode == mod) - return 0; - clear_page(page_address(kvm_svm->avic_logical_id_table_page)); - kvm_svm->ldr_mode = mod; + if (svm->dfr_reg == dfr) + return; - if (svm->ldr_reg) - avic_handle_ldr_update(vcpu); - return 0; + avic_invalidate_logical_id_entry(vcpu); + svm->dfr_reg = dfr; } static int avic_unaccel_trap_write(struct vcpu_svm *svm) @@ -5125,11 +5126,11 @@ static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - if (!kvm_vcpu_apicv_active(&svm->vcpu)) - return; - - vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; - mark_dirty(vmcb, VMCB_INTR); + if (kvm_vcpu_apicv_active(vcpu)) + vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + else + vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; + mark_dirty(vmcb, VMCB_AVIC); } static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) @@ -5195,7 +5196,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) * Allocating new amd_iommu_pi_data, which will get * add to the per-vcpu ir_list. */ - ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL); + ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT); if (!ir) { ret = -ENOMEM; goto out; @@ -6163,8 +6164,7 @@ static inline void avic_post_state_restore(struct kvm_vcpu *vcpu) { if (avic_handle_apic_id_update(vcpu) != 0) return; - if (avic_handle_dfr_update(vcpu) != 0) - return; + avic_handle_dfr_update(vcpu); avic_handle_ldr_update(vcpu); } @@ -6311,7 +6311,7 @@ static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) if (ret) return ret; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; @@ -6361,7 +6361,7 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) return -EFAULT; - start = kzalloc(sizeof(*start), GFP_KERNEL); + start = kzalloc(sizeof(*start), GFP_KERNEL_ACCOUNT); if (!start) return -ENOMEM; @@ -6458,7 +6458,7 @@ static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) return -EFAULT; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; @@ -6535,7 +6535,7 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) if (copy_from_user(¶ms, measure, sizeof(params))) return -EFAULT; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; @@ -6597,7 +6597,7 @@ static int sev_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; @@ -6618,7 +6618,7 @@ static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; @@ -6646,7 +6646,7 @@ static int __sev_issue_dbg_cmd(struct kvm *kvm, unsigned long src, struct sev_data_dbg *data; int ret; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; @@ -6901,7 +6901,7 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) } ret = -ENOMEM; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) goto e_unpin_memory; @@ -7007,7 +7007,7 @@ static int svm_register_enc_region(struct kvm *kvm, if (range->addr > ULONG_MAX || range->size > ULONG_MAX) return -EINVAL; - region = kzalloc(sizeof(*region), GFP_KERNEL); + region = kzalloc(sizeof(*region), GFP_KERNEL_ACCOUNT); if (!region) return -ENOMEM; @@ -7098,6 +7098,36 @@ static int nested_enable_evmcs(struct kvm_vcpu *vcpu, return -ENODEV; } +static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) +{ + bool is_user, smap; + + is_user = svm_get_cpl(vcpu) == 3; + smap = !kvm_read_cr4_bits(vcpu, X86_CR4_SMAP); + + /* + * Detect and workaround Errata 1096 Fam_17h_00_0Fh + * + * In non SEV guest, hypervisor will be able to read the guest + * memory to decode the instruction pointer when insn_len is zero + * so we return true to indicate that decoding is possible. + * + * But in the SEV guest, the guest memory is encrypted with the + * guest specific key and hypervisor will not be able to decode the + * instruction pointer so we will not able to workaround it. Lets + * print the error and request to kill the guest. + */ + if (is_user && smap) { + if (!sev_guest(vcpu->kvm)) + return true; + + pr_err_ratelimited("KVM: Guest triggered AMD Erratum 1096\n"); + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + } + + return false; +} + static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -7231,6 +7261,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .nested_enable_evmcs = nested_enable_evmcs, .nested_get_evmcs_version = nested_get_evmcs_version, + + .need_emulation_on_page_fault = svm_need_emulation_on_page_fault, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d737a51a53ca..153e539c29c9 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -211,7 +211,6 @@ static void free_nested(struct kvm_vcpu *vcpu) if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon) return; - hrtimer_cancel(&vmx->nested.preemption_timer); vmx->nested.vmxon = false; vmx->nested.smm.vmxon = false; free_vpid(vmx->nested.vpid02); @@ -274,6 +273,7 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu) { vcpu_load(vcpu); + vmx_leave_nested(vcpu); vmx_switch_vmcs(vcpu, &to_vmx(vcpu)->vmcs01); free_nested(vcpu); vcpu_put(vcpu); @@ -1980,17 +1980,6 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) prepare_vmcs02_early_full(vmx, vmcs12); /* - * HOST_RSP is normally set correctly in vmx_vcpu_run() just before - * entry, but only if the current (host) sp changed from the value - * we wrote last (vmx->host_rsp). This cache is no longer relevant - * if we switch vmcs, and rather than hold a separate cache per vmcs, - * here we just force the write to happen on entry. host_rsp will - * also be written unconditionally by nested_vmx_check_vmentry_hw() - * if we are doing early consistency checks via hardware. - */ - vmx->host_rsp = 0; - - /* * PIN CONTROLS */ exec_control = vmcs12->pin_based_vm_exec_control; @@ -2289,10 +2278,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } vmx_set_rflags(vcpu, vmcs12->guest_rflags); - vmx->nested.preemption_timer_expired = false; - if (nested_cpu_has_preemption_timer(vmcs12)) - vmx_start_preemption_timer(vcpu); - /* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the * bitwise-or of what L1 wants to trap for L2, and what we want to * trap. Note that CR0.TS also needs updating - we do this later. @@ -2600,6 +2585,11 @@ static int nested_check_host_control_regs(struct kvm_vcpu *vcpu, !nested_host_cr4_valid(vcpu, vmcs12->host_cr4) || !nested_cr3_valid(vcpu, vmcs12->host_cr3)) return -EINVAL; + + if (is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu) || + is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu)) + return -EINVAL; + /* * If the load IA32_EFER VM-exit control is 1, bits reserved in the * IA32_EFER MSR must be 0 in the field for that register. In addition, @@ -2722,6 +2712,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; + bool vm_fail; if (!nested_early_check) return 0; @@ -2755,29 +2746,34 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->host_state.cr4 = cr4; } - vmx->__launched = vmx->loaded_vmcs->launched; - asm( - /* Set HOST_RSP */ "sub $%c[wordsize], %%" _ASM_SP "\n\t" /* temporarily adjust RSP for CALL */ - __ex("vmwrite %%" _ASM_SP ", %%" _ASM_DX) "\n\t" - "mov %%" _ASM_SP ", %c[host_rsp](%1)\n\t" + "cmp %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t" + "je 1f \n\t" + __ex("vmwrite %%" _ASM_SP ", %[HOST_RSP]") "\n\t" + "mov %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t" + "1: \n\t" "add $%c[wordsize], %%" _ASM_SP "\n\t" /* un-adjust RSP */ /* Check if vmlaunch or vmresume is needed */ - "cmpl $0, %c[launched](%% " _ASM_CX")\n\t" + "cmpb $0, %c[launched](%[loaded_vmcs])\n\t" + /* + * VMLAUNCH and VMRESUME clear RFLAGS.{CF,ZF} on VM-Exit, set + * RFLAGS.CF on VM-Fail Invalid and set RFLAGS.ZF on VM-Fail + * Valid. vmx_vmenter() directly "returns" RFLAGS, and so the + * results of VM-Enter is captured via CC_{SET,OUT} to vm_fail. + */ "call vmx_vmenter\n\t" - /* Set vmx->fail accordingly */ - "setbe %c[fail](%% " _ASM_CX")\n\t" - : ASM_CALL_CONSTRAINT - : "c"(vmx), "d"((unsigned long)HOST_RSP), - [launched]"i"(offsetof(struct vcpu_vmx, __launched)), - [fail]"i"(offsetof(struct vcpu_vmx, fail)), - [host_rsp]"i"(offsetof(struct vcpu_vmx, host_rsp)), + CC_SET(be) + : ASM_CALL_CONSTRAINT, CC_OUT(be) (vm_fail) + : [HOST_RSP]"r"((unsigned long)HOST_RSP), + [loaded_vmcs]"r"(vmx->loaded_vmcs), + [launched]"i"(offsetof(struct loaded_vmcs, launched)), + [host_state_rsp]"i"(offsetof(struct loaded_vmcs, host_state.rsp)), [wordsize]"i"(sizeof(ulong)) - : "rax", "cc", "memory" + : "cc", "memory" ); preempt_enable(); @@ -2787,10 +2783,9 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) if (vmx->msr_autoload.guest.nr) vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); - if (vmx->fail) { + if (vm_fail) { WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) != VMXERR_ENTRY_INVALID_CONTROL_FIELD); - vmx->fail = 0; return 1; } @@ -2813,8 +2808,6 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) return 0; } -STACK_FRAME_NON_STANDARD(nested_vmx_check_vmentry_hw); - static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12); @@ -3031,6 +3024,15 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) kvm_make_request(KVM_REQ_EVENT, vcpu); /* + * Do not start the preemption timer hrtimer until after we know + * we are successful, so that only nested_vmx_vmexit needs to cancel + * the timer. + */ + vmx->nested.preemption_timer_expired = false; + if (nested_cpu_has_preemption_timer(vmcs12)) + vmx_start_preemption_timer(vcpu); + + /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet * returned as far as L1 is concerned. It will only return (and set @@ -3450,13 +3452,10 @@ static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) else vmcs12->guest_activity_state = GUEST_ACTIVITY_ACTIVE; - if (nested_cpu_has_preemption_timer(vmcs12)) { - if (vmcs12->vm_exit_controls & - VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) + if (nested_cpu_has_preemption_timer(vmcs12) && + vmcs12->vm_exit_controls & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) vmcs12->vmx_preemption_timer_value = vmx_get_preemption_timer_value(vcpu); - hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer); - } /* * In some cases (usually, nested EPT), L2 is allowed to change its @@ -3864,6 +3863,9 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, leave_guest_mode(vcpu); + if (nested_cpu_has_preemption_timer(vmcs12)) + hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer); + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) vcpu->arch.tsc_offset -= vmcs12->tsc_offset; @@ -3915,9 +3917,6 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmx_flush_tlb(vcpu, true); } - /* This is needed for same reason as it was needed in prepare_vmcs02 */ - vmx->host_rsp = 0; - /* Unpin physical memory we referred to in vmcs02 */ if (vmx->nested.apic_access_page) { kvm_release_page_dirty(vmx->nested.apic_access_page); @@ -4035,25 +4034,50 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, /* Addr = segment_base + offset */ /* offset = base + [index * scale] + displacement */ off = exit_qualification; /* holds the displacement */ + if (addr_size == 1) + off = (gva_t)sign_extend64(off, 31); + else if (addr_size == 0) + off = (gva_t)sign_extend64(off, 15); if (base_is_valid) off += kvm_register_read(vcpu, base_reg); if (index_is_valid) off += kvm_register_read(vcpu, index_reg)<<scaling; vmx_get_segment(vcpu, &s, seg_reg); - *ret = s.base + off; + /* + * The effective address, i.e. @off, of a memory operand is truncated + * based on the address size of the instruction. Note that this is + * the *effective address*, i.e. the address prior to accounting for + * the segment's base. + */ if (addr_size == 1) /* 32 bit */ - *ret &= 0xffffffff; + off &= 0xffffffff; + else if (addr_size == 0) /* 16 bit */ + off &= 0xffff; /* Checks for #GP/#SS exceptions. */ exn = false; if (is_long_mode(vcpu)) { + /* + * The virtual/linear address is never truncated in 64-bit + * mode, e.g. a 32-bit address size can yield a 64-bit virtual + * address when using FS/GS with a non-zero base. + */ + *ret = s.base + off; + /* Long mode: #GP(0)/#SS(0) if the memory address is in a * non-canonical form. This is the only check on the memory * destination for long mode! */ exn = is_noncanonical_address(*ret, vcpu); - } else if (is_protmode(vcpu)) { + } else { + /* + * When not in long mode, the virtual/linear address is + * unconditionally truncated to 32 bits regardless of the + * address size. + */ + *ret = (s.base + off) & 0xffffffff; + /* Protected mode: apply checks for segment validity in the * following order: * - segment type check (#GP(0) may be thrown) @@ -4077,10 +4101,16 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, /* Protected mode: #GP(0)/#SS(0) if the segment is unusable. */ exn = (s.unusable != 0); - /* Protected mode: #GP(0)/#SS(0) if the memory - * operand is outside the segment limit. + + /* + * Protected mode: #GP(0)/#SS(0) if the memory operand is + * outside the segment limit. All CPUs that support VMX ignore + * limit checks for flat segments, i.e. segments with base==0, + * limit==0xffffffff and of type expand-up data or code. */ - exn = exn || (off + sizeof(u64) > s.limit); + if (!(s.base == 0 && s.limit == 0xffffffff && + ((s.type & 8) || !(s.type & 4)))) + exn = exn || (off + sizeof(u64) > s.limit); } if (exn) { kvm_queue_exception_e(vcpu, @@ -4145,11 +4175,11 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) if (r < 0) goto out_vmcs02; - vmx->nested.cached_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL); + vmx->nested.cached_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT); if (!vmx->nested.cached_vmcs12) goto out_cached_vmcs12; - vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL); + vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT); if (!vmx->nested.cached_shadow_vmcs12) goto out_cached_shadow_vmcs12; @@ -5696,6 +5726,10 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) enable_shadow_vmcs = 0; if (enable_shadow_vmcs) { for (i = 0; i < VMX_BITMAP_NR; i++) { + /* + * The vmx_bitmap is not tied to a VM and so should + * not be charged to a memcg. + */ vmx_bitmap[i] = (unsigned long *) __get_free_page(GFP_KERNEL); if (!vmx_bitmap[i]) { diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index 6def3ba88e3b..cb6079f8a227 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -34,6 +34,7 @@ struct vmcs_host_state { unsigned long cr4; /* May not match real cr4 */ unsigned long gs_base; unsigned long fs_base; + unsigned long rsp; u16 fs_sel, gs_sel, ldt_sel; #ifdef CONFIG_X86_64 diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index bcef2c7e9bc4..7b272738c576 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -1,6 +1,30 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/linkage.h> #include <asm/asm.h> +#include <asm/bitsperlong.h> +#include <asm/kvm_vcpu_regs.h> + +#define WORD_SIZE (BITS_PER_LONG / 8) + +#define VCPU_RAX __VCPU_REGS_RAX * WORD_SIZE +#define VCPU_RCX __VCPU_REGS_RCX * WORD_SIZE +#define VCPU_RDX __VCPU_REGS_RDX * WORD_SIZE +#define VCPU_RBX __VCPU_REGS_RBX * WORD_SIZE +/* Intentionally omit RSP as it's context switched by hardware */ +#define VCPU_RBP __VCPU_REGS_RBP * WORD_SIZE +#define VCPU_RSI __VCPU_REGS_RSI * WORD_SIZE +#define VCPU_RDI __VCPU_REGS_RDI * WORD_SIZE + +#ifdef CONFIG_X86_64 +#define VCPU_R8 __VCPU_REGS_R8 * WORD_SIZE +#define VCPU_R9 __VCPU_REGS_R9 * WORD_SIZE +#define VCPU_R10 __VCPU_REGS_R10 * WORD_SIZE +#define VCPU_R11 __VCPU_REGS_R11 * WORD_SIZE +#define VCPU_R12 __VCPU_REGS_R12 * WORD_SIZE +#define VCPU_R13 __VCPU_REGS_R13 * WORD_SIZE +#define VCPU_R14 __VCPU_REGS_R14 * WORD_SIZE +#define VCPU_R15 __VCPU_REGS_R15 * WORD_SIZE +#endif .text @@ -55,3 +79,146 @@ ENDPROC(vmx_vmenter) ENTRY(vmx_vmexit) ret ENDPROC(vmx_vmexit) + +/** + * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode + * @vmx: struct vcpu_vmx * + * @regs: unsigned long * (to guest registers) + * @launched: %true if the VMCS has been launched + * + * Returns: + * 0 on VM-Exit, 1 on VM-Fail + */ +ENTRY(__vmx_vcpu_run) + push %_ASM_BP + mov %_ASM_SP, %_ASM_BP +#ifdef CONFIG_X86_64 + push %r15 + push %r14 + push %r13 + push %r12 +#else + push %edi + push %esi +#endif + push %_ASM_BX + + /* + * Save @regs, _ASM_ARG2 may be modified by vmx_update_host_rsp() and + * @regs is needed after VM-Exit to save the guest's register values. + */ + push %_ASM_ARG2 + + /* Copy @launched to BL, _ASM_ARG3 is volatile. */ + mov %_ASM_ARG3B, %bl + + /* Adjust RSP to account for the CALL to vmx_vmenter(). */ + lea -WORD_SIZE(%_ASM_SP), %_ASM_ARG2 + call vmx_update_host_rsp + + /* Load @regs to RAX. */ + mov (%_ASM_SP), %_ASM_AX + + /* Check if vmlaunch or vmresume is needed */ + cmpb $0, %bl + + /* Load guest registers. Don't clobber flags. */ + mov VCPU_RBX(%_ASM_AX), %_ASM_BX + mov VCPU_RCX(%_ASM_AX), %_ASM_CX + mov VCPU_RDX(%_ASM_AX), %_ASM_DX + mov VCPU_RSI(%_ASM_AX), %_ASM_SI + mov VCPU_RDI(%_ASM_AX), %_ASM_DI + mov VCPU_RBP(%_ASM_AX), %_ASM_BP +#ifdef CONFIG_X86_64 + mov VCPU_R8 (%_ASM_AX), %r8 + mov VCPU_R9 (%_ASM_AX), %r9 + mov VCPU_R10(%_ASM_AX), %r10 + mov VCPU_R11(%_ASM_AX), %r11 + mov VCPU_R12(%_ASM_AX), %r12 + mov VCPU_R13(%_ASM_AX), %r13 + mov VCPU_R14(%_ASM_AX), %r14 + mov VCPU_R15(%_ASM_AX), %r15 +#endif + /* Load guest RAX. This kills the vmx_vcpu pointer! */ + mov VCPU_RAX(%_ASM_AX), %_ASM_AX + + /* Enter guest mode */ + call vmx_vmenter + + /* Jump on VM-Fail. */ + jbe 2f + + /* Temporarily save guest's RAX. */ + push %_ASM_AX + + /* Reload @regs to RAX. */ + mov WORD_SIZE(%_ASM_SP), %_ASM_AX + + /* Save all guest registers, including RAX from the stack */ + __ASM_SIZE(pop) VCPU_RAX(%_ASM_AX) + mov %_ASM_BX, VCPU_RBX(%_ASM_AX) + mov %_ASM_CX, VCPU_RCX(%_ASM_AX) + mov %_ASM_DX, VCPU_RDX(%_ASM_AX) + mov %_ASM_SI, VCPU_RSI(%_ASM_AX) + mov %_ASM_DI, VCPU_RDI(%_ASM_AX) + mov %_ASM_BP, VCPU_RBP(%_ASM_AX) +#ifdef CONFIG_X86_64 + mov %r8, VCPU_R8 (%_ASM_AX) + mov %r9, VCPU_R9 (%_ASM_AX) + mov %r10, VCPU_R10(%_ASM_AX) + mov %r11, VCPU_R11(%_ASM_AX) + mov %r12, VCPU_R12(%_ASM_AX) + mov %r13, VCPU_R13(%_ASM_AX) + mov %r14, VCPU_R14(%_ASM_AX) + mov %r15, VCPU_R15(%_ASM_AX) +#endif + + /* Clear RAX to indicate VM-Exit (as opposed to VM-Fail). */ + xor %eax, %eax + + /* + * Clear all general purpose registers except RSP and RAX to prevent + * speculative use of the guest's values, even those that are reloaded + * via the stack. In theory, an L1 cache miss when restoring registers + * could lead to speculative execution with the guest's values. + * Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially + * free. RSP and RAX are exempt as RSP is restored by hardware during + * VM-Exit and RAX is explicitly loaded with 0 or 1 to return VM-Fail. + */ +1: xor %ebx, %ebx + xor %ecx, %ecx + xor %edx, %edx + xor %esi, %esi + xor %edi, %edi + xor %ebp, %ebp +#ifdef CONFIG_X86_64 + xor %r8d, %r8d + xor %r9d, %r9d + xor %r10d, %r10d + xor %r11d, %r11d + xor %r12d, %r12d + xor %r13d, %r13d + xor %r14d, %r14d + xor %r15d, %r15d +#endif + + /* "POP" @regs. */ + add $WORD_SIZE, %_ASM_SP + pop %_ASM_BX + +#ifdef CONFIG_X86_64 + pop %r12 + pop %r13 + pop %r14 + pop %r15 +#else + pop %esi + pop %edi +#endif + pop %_ASM_BP + ret + + /* VM-Fail. Out-of-line to avoid a taken Jcc after VM-Exit. */ +2: mov $1, %eax + jmp 1b +ENDPROC(__vmx_vcpu_run) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 30a6bcd735ec..ab432a930ae8 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -246,6 +246,10 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages && !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) { + /* + * This allocation for vmx_l1d_flush_pages is not tied to a VM + * lifetime and so should not be charged to a memcg. + */ page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER); if (!page) return -ENOMEM; @@ -1679,12 +1683,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = to_vmx(vcpu)->spec_ctrl; break; - case MSR_IA32_ARCH_CAPABILITIES: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) - return 1; - msr_info->data = to_vmx(vcpu)->arch_capabilities; - break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; @@ -1891,11 +1889,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, MSR_TYPE_W); break; - case MSR_IA32_ARCH_CAPABILITIES: - if (!msr_info->host_initiated) - return 1; - vmx->arch_capabilities = data; - break; case MSR_IA32_CR_PAT: if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) @@ -2387,13 +2380,13 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, return 0; } -struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu) +struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) { int node = cpu_to_node(cpu); struct page *pages; struct vmcs *vmcs; - pages = __alloc_pages_node(node, GFP_KERNEL, vmcs_config.order); + pages = __alloc_pages_node(node, flags, vmcs_config.order); if (!pages) return NULL; vmcs = page_address(pages); @@ -2440,7 +2433,8 @@ int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) loaded_vmcs_init(loaded_vmcs); if (cpu_has_vmx_msr_bitmap()) { - loaded_vmcs->msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); + loaded_vmcs->msr_bitmap = (unsigned long *) + __get_free_page(GFP_KERNEL_ACCOUNT); if (!loaded_vmcs->msr_bitmap) goto out_vmcs; memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); @@ -2481,7 +2475,7 @@ static __init int alloc_kvm_area(void) for_each_possible_cpu(cpu) { struct vmcs *vmcs; - vmcs = alloc_vmcs_cpu(false, cpu); + vmcs = alloc_vmcs_cpu(false, cpu, GFP_KERNEL); if (!vmcs) { free_kvm_area(); return -ENOMEM; @@ -4083,8 +4077,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) ++vmx->nmsrs; } - vmx->arch_capabilities = kvm_get_arch_capabilities(); - vm_exit_controls_init(vmx, vmx_vmexit_ctrl()); /* 22.2.1, 20.8.1 */ @@ -6360,150 +6352,15 @@ static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->hv_timer_armed = false; } -static void __vmx_vcpu_run(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) +void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp) { - unsigned long evmcs_rsp; - - vmx->__launched = vmx->loaded_vmcs->launched; - - evmcs_rsp = static_branch_unlikely(&enable_evmcs) ? - (unsigned long)¤t_evmcs->host_rsp : 0; - - if (static_branch_unlikely(&vmx_l1d_should_flush)) - vmx_l1d_flush(vcpu); - - asm( - /* Store host registers */ - "push %%" _ASM_DX "; push %%" _ASM_BP ";" - "push %%" _ASM_CX " \n\t" /* placeholder for guest rcx */ - "push %%" _ASM_CX " \n\t" - "sub $%c[wordsize], %%" _ASM_SP "\n\t" /* temporarily adjust RSP for CALL */ - "cmp %%" _ASM_SP ", %c[host_rsp](%%" _ASM_CX ") \n\t" - "je 1f \n\t" - "mov %%" _ASM_SP ", %c[host_rsp](%%" _ASM_CX ") \n\t" - /* Avoid VMWRITE when Enlightened VMCS is in use */ - "test %%" _ASM_SI ", %%" _ASM_SI " \n\t" - "jz 2f \n\t" - "mov %%" _ASM_SP ", (%%" _ASM_SI ") \n\t" - "jmp 1f \n\t" - "2: \n\t" - __ex("vmwrite %%" _ASM_SP ", %%" _ASM_DX) "\n\t" - "1: \n\t" - "add $%c[wordsize], %%" _ASM_SP "\n\t" /* un-adjust RSP */ - - /* Reload cr2 if changed */ - "mov %c[cr2](%%" _ASM_CX "), %%" _ASM_AX " \n\t" - "mov %%cr2, %%" _ASM_DX " \n\t" - "cmp %%" _ASM_AX ", %%" _ASM_DX " \n\t" - "je 3f \n\t" - "mov %%" _ASM_AX", %%cr2 \n\t" - "3: \n\t" - /* Check if vmlaunch or vmresume is needed */ - "cmpl $0, %c[launched](%%" _ASM_CX ") \n\t" - /* Load guest registers. Don't clobber flags. */ - "mov %c[rax](%%" _ASM_CX "), %%" _ASM_AX " \n\t" - "mov %c[rbx](%%" _ASM_CX "), %%" _ASM_BX " \n\t" - "mov %c[rdx](%%" _ASM_CX "), %%" _ASM_DX " \n\t" - "mov %c[rsi](%%" _ASM_CX "), %%" _ASM_SI " \n\t" - "mov %c[rdi](%%" _ASM_CX "), %%" _ASM_DI " \n\t" - "mov %c[rbp](%%" _ASM_CX "), %%" _ASM_BP " \n\t" -#ifdef CONFIG_X86_64 - "mov %c[r8](%%" _ASM_CX "), %%r8 \n\t" - "mov %c[r9](%%" _ASM_CX "), %%r9 \n\t" - "mov %c[r10](%%" _ASM_CX "), %%r10 \n\t" - "mov %c[r11](%%" _ASM_CX "), %%r11 \n\t" - "mov %c[r12](%%" _ASM_CX "), %%r12 \n\t" - "mov %c[r13](%%" _ASM_CX "), %%r13 \n\t" - "mov %c[r14](%%" _ASM_CX "), %%r14 \n\t" - "mov %c[r15](%%" _ASM_CX "), %%r15 \n\t" -#endif - /* Load guest RCX. This kills the vmx_vcpu pointer! */ - "mov %c[rcx](%%" _ASM_CX "), %%" _ASM_CX " \n\t" - - /* Enter guest mode */ - "call vmx_vmenter\n\t" - - /* Save guest's RCX to the stack placeholder (see above) */ - "mov %%" _ASM_CX ", %c[wordsize](%%" _ASM_SP ") \n\t" - - /* Load host's RCX, i.e. the vmx_vcpu pointer */ - "pop %%" _ASM_CX " \n\t" - - /* Set vmx->fail based on EFLAGS.{CF,ZF} */ - "setbe %c[fail](%%" _ASM_CX ")\n\t" - - /* Save all guest registers, including RCX from the stack */ - "mov %%" _ASM_AX ", %c[rax](%%" _ASM_CX ") \n\t" - "mov %%" _ASM_BX ", %c[rbx](%%" _ASM_CX ") \n\t" - __ASM_SIZE(pop) " %c[rcx](%%" _ASM_CX ") \n\t" - "mov %%" _ASM_DX ", %c[rdx](%%" _ASM_CX ") \n\t" - "mov %%" _ASM_SI ", %c[rsi](%%" _ASM_CX ") \n\t" - "mov %%" _ASM_DI ", %c[rdi](%%" _ASM_CX ") \n\t" - "mov %%" _ASM_BP ", %c[rbp](%%" _ASM_CX ") \n\t" -#ifdef CONFIG_X86_64 - "mov %%r8, %c[r8](%%" _ASM_CX ") \n\t" - "mov %%r9, %c[r9](%%" _ASM_CX ") \n\t" - "mov %%r10, %c[r10](%%" _ASM_CX ") \n\t" - "mov %%r11, %c[r11](%%" _ASM_CX ") \n\t" - "mov %%r12, %c[r12](%%" _ASM_CX ") \n\t" - "mov %%r13, %c[r13](%%" _ASM_CX ") \n\t" - "mov %%r14, %c[r14](%%" _ASM_CX ") \n\t" - "mov %%r15, %c[r15](%%" _ASM_CX ") \n\t" - /* - * Clear host registers marked as clobbered to prevent - * speculative use. - */ - "xor %%r8d, %%r8d \n\t" - "xor %%r9d, %%r9d \n\t" - "xor %%r10d, %%r10d \n\t" - "xor %%r11d, %%r11d \n\t" - "xor %%r12d, %%r12d \n\t" - "xor %%r13d, %%r13d \n\t" - "xor %%r14d, %%r14d \n\t" - "xor %%r15d, %%r15d \n\t" -#endif - "mov %%cr2, %%" _ASM_AX " \n\t" - "mov %%" _ASM_AX ", %c[cr2](%%" _ASM_CX ") \n\t" - - "xor %%eax, %%eax \n\t" - "xor %%ebx, %%ebx \n\t" - "xor %%esi, %%esi \n\t" - "xor %%edi, %%edi \n\t" - "pop %%" _ASM_BP "; pop %%" _ASM_DX " \n\t" - : ASM_CALL_CONSTRAINT - : "c"(vmx), "d"((unsigned long)HOST_RSP), "S"(evmcs_rsp), - [launched]"i"(offsetof(struct vcpu_vmx, __launched)), - [fail]"i"(offsetof(struct vcpu_vmx, fail)), - [host_rsp]"i"(offsetof(struct vcpu_vmx, host_rsp)), - [rax]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RAX])), - [rbx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBX])), - [rcx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RCX])), - [rdx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDX])), - [rsi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RSI])), - [rdi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDI])), - [rbp]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBP])), -#ifdef CONFIG_X86_64 - [r8]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R8])), - [r9]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R9])), - [r10]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R10])), - [r11]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R11])), - [r12]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R12])), - [r13]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R13])), - [r14]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R14])), - [r15]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R15])), -#endif - [cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2)), - [wordsize]"i"(sizeof(ulong)) - : "cc", "memory" -#ifdef CONFIG_X86_64 - , "rax", "rbx", "rdi" - , "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15" -#else - , "eax", "ebx", "edi" -#endif - ); + if (unlikely(host_rsp != vmx->loaded_vmcs->host_state.rsp)) { + vmx->loaded_vmcs->host_state.rsp = host_rsp; + vmcs_writel(HOST_RSP, host_rsp); + } } -STACK_FRAME_NON_STANDARD(__vmx_vcpu_run); + +bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched); static void vmx_vcpu_run(struct kvm_vcpu *vcpu) { @@ -6572,7 +6429,16 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) */ x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0); - __vmx_vcpu_run(vcpu, vmx); + if (static_branch_unlikely(&vmx_l1d_should_flush)) + vmx_l1d_flush(vcpu); + + if (vcpu->arch.cr2 != read_cr2()) + write_cr2(vcpu->arch.cr2); + + vmx->fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, + vmx->loaded_vmcs->launched); + + vcpu->arch.cr2 = read_cr2(); /* * We do not use IBRS in the kernel. If this vCPU has used the @@ -6657,7 +6523,9 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) static struct kvm *vmx_vm_alloc(void) { - struct kvm_vmx *kvm_vmx = vzalloc(sizeof(struct kvm_vmx)); + struct kvm_vmx *kvm_vmx = __vmalloc(sizeof(struct kvm_vmx), + GFP_KERNEL_ACCOUNT | __GFP_ZERO, + PAGE_KERNEL); return &kvm_vmx->kvm; } @@ -6673,7 +6541,6 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) if (enable_pml) vmx_destroy_pml_buffer(vmx); free_vpid(vmx->vpid); - leave_guest_mode(vcpu); nested_vmx_free_vcpu(vcpu); free_loaded_vmcs(vmx->loaded_vmcs); kfree(vmx->guest_msrs); @@ -6685,14 +6552,16 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) { int err; - struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + struct vcpu_vmx *vmx; unsigned long *msr_bitmap; int cpu; + vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); if (!vmx) return ERR_PTR(-ENOMEM); - vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL); + vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); if (!vmx->vcpu.arch.guest_fpu) { printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); err = -ENOMEM; @@ -6714,12 +6583,12 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) * for the guest, etc. */ if (enable_pml) { - vmx->pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO); + vmx->pml_pg = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!vmx->pml_pg) goto uninit_vcpu; } - vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL); + vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT); BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0]) > PAGE_SIZE); @@ -7527,6 +7396,11 @@ static int enable_smi_window(struct kvm_vcpu *vcpu) return 0; } +static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) +{ + return 0; +} + static __init int hardware_setup(void) { unsigned long host_bndcfgs; @@ -7829,6 +7703,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .set_nested_state = NULL, .get_vmcs12_pages = NULL, .nested_enable_evmcs = NULL, + .need_emulation_on_page_fault = vmx_need_emulation_on_page_fault, }; static void vmx_cleanup_l1d_flush(void) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 0ac0a64c7790..a1e00d0a2482 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -175,7 +175,6 @@ struct nested_vmx { struct vcpu_vmx { struct kvm_vcpu vcpu; - unsigned long host_rsp; u8 fail; u8 msr_bitmap_mode; u32 exit_intr_info; @@ -191,7 +190,6 @@ struct vcpu_vmx { u64 msr_guest_kernel_gs_base; #endif - u64 arch_capabilities; u64 spec_ctrl; u32 vm_entry_controls_shadow; @@ -209,7 +207,7 @@ struct vcpu_vmx { struct loaded_vmcs vmcs01; struct loaded_vmcs *loaded_vmcs; struct loaded_vmcs *loaded_cpu_state; - bool __launched; /* temporary, used in vmx_vcpu_run */ + struct msr_autoload { struct vmx_msrs guest; struct vmx_msrs host; @@ -339,8 +337,8 @@ static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) static inline void pi_set_sn(struct pi_desc *pi_desc) { - return set_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); + set_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); } static inline void pi_set_on(struct pi_desc *pi_desc) @@ -445,7 +443,8 @@ static inline u32 vmx_vmentry_ctrl(void) { u32 vmentry_ctrl = vmcs_config.vmentry_ctrl; if (pt_mode == PT_MODE_SYSTEM) - vmentry_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | VM_EXIT_CLEAR_IA32_RTIT_CTL); + vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | + VM_ENTRY_LOAD_IA32_RTIT_CTL); /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ return vmentry_ctrl & ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_EFER); @@ -455,9 +454,10 @@ static inline u32 vmx_vmexit_ctrl(void) { u32 vmexit_ctrl = vmcs_config.vmexit_ctrl; if (pt_mode == PT_MODE_SYSTEM) - vmexit_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | VM_ENTRY_LOAD_IA32_RTIT_CTL); + vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | + VM_EXIT_CLEAR_IA32_RTIT_CTL); /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ - return vmcs_config.vmexit_ctrl & + return vmexit_ctrl & ~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER); } @@ -478,7 +478,7 @@ static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) return &(to_vmx(vcpu)->pi_desc); } -struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu); +struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags); void free_vmcs(struct vmcs *vmcs); int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs); void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs); @@ -487,7 +487,8 @@ void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs); static inline struct vmcs *alloc_vmcs(bool shadow) { - return alloc_vmcs_cpu(shadow, raw_smp_processor_id()); + return alloc_vmcs_cpu(shadow, raw_smp_processor_id(), + GFP_KERNEL_ACCOUNT); } u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 941f932373d0..099b851dabaf 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1125,7 +1125,7 @@ static u32 msrs_to_save[] = { #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, - MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES, + MSR_IA32_SPEC_CTRL, MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH, MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK, MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B, @@ -1158,6 +1158,7 @@ static u32 emulated_msrs[] = { MSR_IA32_TSC_ADJUST, MSR_IA32_TSCDEADLINE, + MSR_IA32_ARCH_CAPABILITIES, MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, MSR_IA32_MCG_CTL, @@ -2443,6 +2444,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (msr_info->host_initiated) vcpu->arch.microcode_version = data; break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated) + return 1; + vcpu->arch.arch_capabilities = data; + break; case MSR_EFER: return set_efer(vcpu, data); case MSR_K7_HWCR: @@ -2747,6 +2753,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_UCODE_REV: msr_info->data = vcpu->arch.microcode_version; break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) + return 1; + msr_info->data = vcpu->arch.arch_capabilities; + break; case MSR_IA32_TSC: msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset; break; @@ -3879,7 +3891,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EINVAL; if (!lapic_in_kernel(vcpu)) goto out; - u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); + u.lapic = kzalloc(sizeof(struct kvm_lapic_state), + GFP_KERNEL_ACCOUNT); r = -ENOMEM; if (!u.lapic) @@ -4066,7 +4079,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_GET_XSAVE: { - u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL); + u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL_ACCOUNT); r = -ENOMEM; if (!u.xsave) break; @@ -4090,7 +4103,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_GET_XCRS: { - u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL); + u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL_ACCOUNT); r = -ENOMEM; if (!u.xcrs) break; @@ -6522,14 +6535,27 @@ int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, } EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer); +static int complete_fast_pio_out(struct kvm_vcpu *vcpu) +{ + vcpu->arch.pio.count = 0; + + if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) + return 1; + + return kvm_skip_emulated_instruction(vcpu); +} + static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) { unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX); int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt, size, port, &val, 1); - /* do not return to emulator after return from userspace */ - vcpu->arch.pio.count = 0; + + if (!ret) { + vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu); + vcpu->arch.complete_userspace_io = complete_fast_pio_out; + } return ret; } @@ -6540,6 +6566,11 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu) /* We should only ever be called with arch.pio.count equal to 1 */ BUG_ON(vcpu->arch.pio.count != 1); + if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) { + vcpu->arch.pio.count = 0; + return 1; + } + /* For size less than 4 we merge, else we zero extend */ val = (vcpu->arch.pio.size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX) : 0; @@ -6552,7 +6583,7 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu) vcpu->arch.pio.port, &val, 1); kvm_register_write(vcpu, VCPU_REGS_RAX, val); - return 1; + return kvm_skip_emulated_instruction(vcpu); } static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, @@ -6571,6 +6602,7 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, return ret; } + vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu); vcpu->arch.complete_userspace_io = complete_fast_pio_in; return 0; @@ -6578,16 +6610,13 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in) { - int ret = kvm_skip_emulated_instruction(vcpu); + int ret; - /* - * TODO: we might be squashing a KVM_GUESTDBG_SINGLESTEP-triggered - * KVM_EXIT_DEBUG here. - */ if (in) - return kvm_fast_pio_in(vcpu, size, port) && ret; + ret = kvm_fast_pio_in(vcpu, size, port); else - return kvm_fast_pio_out(vcpu, size, port) && ret; + ret = kvm_fast_pio_out(vcpu, size, port); + return ret && kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_GPL(kvm_fast_pio); @@ -7055,6 +7084,13 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu) { + if (!lapic_in_kernel(vcpu)) { + WARN_ON_ONCE(vcpu->arch.apicv_active); + return; + } + if (!vcpu->arch.apicv_active) + return; + vcpu->arch.apicv_active = false; kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu); } @@ -8725,6 +8761,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { + vcpu->arch.arch_capabilities = kvm_get_arch_capabilities(); vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; kvm_vcpu_mtrr_init(vcpu); vcpu_load(vcpu); @@ -9005,7 +9042,6 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) struct page *page; int r; - vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu); vcpu->arch.emulate_ctxt.ops = &emulate_ops; if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -9026,6 +9062,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) goto fail_free_pio_data; if (irqchip_in_kernel(vcpu->kvm)) { + vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu); r = kvm_create_lapic(vcpu); if (r < 0) goto fail_mmu_destroy; @@ -9033,14 +9070,15 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) static_key_slow_inc(&kvm_no_apic_vcpu); vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4, - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!vcpu->arch.mce_banks) { r = -ENOMEM; goto fail_free_lapic; } vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; - if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL)) { + if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, + GFP_KERNEL_ACCOUNT)) { r = -ENOMEM; goto fail_free_mce_banks; } @@ -9104,7 +9142,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); - INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); @@ -9299,13 +9336,13 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, slot->arch.rmap[i] = kvcalloc(lpages, sizeof(*slot->arch.rmap[i]), - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!slot->arch.rmap[i]) goto out_free; if (i == 0) continue; - linfo = kvcalloc(lpages, sizeof(*linfo), GFP_KERNEL); + linfo = kvcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT); if (!linfo) goto out_free; @@ -9348,13 +9385,13 @@ out_free: return -ENOMEM; } -void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) +void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { /* * memslots->generation has been incremented. * mmio generation may have reached its maximum value. */ - kvm_mmu_invalidate_mmio_sptes(kvm, slots); + kvm_mmu_invalidate_mmio_sptes(kvm, gen); } int kvm_arch_prepare_memory_region(struct kvm *kvm, @@ -9421,13 +9458,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - int nr_mmu_pages = 0; - if (!kvm->arch.n_requested_mmu_pages) - nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); - - if (nr_mmu_pages) - kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); + kvm_mmu_change_mmu_pages(kvm, + kvm_mmu_calculate_default_mmu_pages(kvm)); /* * Dirty logging tracks sptes in 4k granularity, meaning that large @@ -9462,7 +9495,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, void kvm_arch_flush_shadow_all(struct kvm *kvm) { - kvm_mmu_invalidate_zap_all_pages(kvm); + kvm_mmu_zap_all(kvm); } void kvm_arch_flush_shadow_memslot(struct kvm *kvm, diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 224cd0a47568..28406aa1136d 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -181,6 +181,11 @@ static inline bool emul_is_noncanonical_address(u64 la, static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, unsigned access) { + u64 gen = kvm_memslots(vcpu->kvm)->generation; + + if (unlikely(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS)) + return; + /* * If this is a shadow nested page table, the "GVA" is * actually a nGPA. @@ -188,7 +193,7 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, vcpu->arch.mmio_gva = mmu_is_nested(vcpu) ? 0 : gva & PAGE_MASK; vcpu->arch.access = access; vcpu->arch.mmio_gfn = gfn; - vcpu->arch.mmio_gen = kvm_memslots(vcpu->kvm)->generation; + vcpu->arch.mmio_gen = gen; } static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu) diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c index 9baca3e054be..e7925d668b68 100644 --- a/arch/x86/lib/csum-partial_64.c +++ b/arch/x86/lib/csum-partial_64.c @@ -94,7 +94,7 @@ static unsigned do_csum(const unsigned char *buff, unsigned len) : "m" (*(unsigned long *)buff), "r" (zero), "0" (result)); --count; - buff += 8; + buff += 8; } result = add32_with_carry(result>>32, result&0xffffffff); diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 462fde83b515..8dc0fc0b1382 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -24,14 +24,16 @@ extern struct range pfn_mapped[E820_MAX_ENTRIES]; static p4d_t tmp_p4d_table[MAX_PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); -static __init void *early_alloc(size_t size, int nid, bool panic) +static __init void *early_alloc(size_t size, int nid, bool should_panic) { - if (panic) - return memblock_alloc_try_nid(size, size, - __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); - else - return memblock_alloc_try_nid_nopanic(size, size, + void *ptr = memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); + + if (!ptr && should_panic) + panic("%pS: Failed to allocate page, nid=%d from=%lx\n", + (void *)_RET_IP_, nid, __pa(MAX_DMA_ADDRESS)); + + return ptr; } static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index db3165714521..dc726e07d8ba 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -230,7 +230,7 @@ bool mmap_address_hint_valid(unsigned long addr, unsigned long len) /* Can we access it for direct reading/writing? Must be RAM: */ int valid_phys_addr_range(phys_addr_t addr, size_t count) { - return addr + count <= __pa(high_memory); + return addr + count - 1 <= __pa(high_memory - 1); } /* Can we access it through mmap? Must be a valid physical address: */ diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 12c1b7a83ed7..dfb6c4df639a 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -195,15 +195,11 @@ static void __init alloc_node_data(int nid) * Allocate node data. Try node-local memory and then any node. * Never allocate in DMA zone. */ - nd_pa = memblock_phys_alloc_nid(nd_size, SMP_CACHE_BYTES, nid); + nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); if (!nd_pa) { - nd_pa = __memblock_alloc_base(nd_size, SMP_CACHE_BYTES, - MEMBLOCK_ALLOC_ACCESSIBLE); - if (!nd_pa) { - pr_err("Cannot find %zu bytes in any node (initial node: %d)\n", - nd_size, nid); - return; - } + pr_err("Cannot find %zu bytes in any node (initial node: %d)\n", + nd_size, nid); + return; } nd = __va(nd_pa); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 14e6119838a6..4c570612e24e 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -738,7 +738,7 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address, { unsigned long numpages, pmask, psize, lpaddr, pfn, old_pfn; pgprot_t old_prot, new_prot, req_prot, chk_prot; - pte_t new_pte, old_pte, *tmp; + pte_t new_pte, *tmp; enum pg_level level; /* @@ -781,7 +781,7 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address, * Convert protection attributes to 4k-format, as cpa->mask* are set * up accordingly. */ - old_pte = *kpte; + /* Clear PSE (aka _PAGE_PAT) and move PAT bit to correct position */ req_prot = pgprot_large_2_4k(old_prot); diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 4fee5c3003ed..139b28a01ce4 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -77,7 +77,7 @@ static void __init pti_print_if_secure(const char *reason) pr_info("%s\n", reason); } -enum pti_mode { +static enum pti_mode { PTI_AUTO = 0, PTI_FORCE_OFF, PTI_FORCE_ON @@ -602,7 +602,7 @@ static void pti_clone_kernel_text(void) set_memory_global(start, (end_global - start) >> PAGE_SHIFT); } -void pti_set_kernel_image_nonglobal(void) +static void pti_set_kernel_image_nonglobal(void) { /* * The identity map is created with PMDs, regardless of the diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 30a5111ae5fd..527e69b12002 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -635,6 +635,22 @@ static void quirk_no_aersid(struct pci_dev *pdev) DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_BRIDGE_PCI, 8, quirk_no_aersid); +static void quirk_intel_th_dnv(struct pci_dev *dev) +{ + struct resource *r = &dev->resource[4]; + + /* + * Denverton reports 2k of RTIT_BAR (intel_th resource 4), which + * appears to be 4 MB in reality. + */ + if (r->end == r->start + 0x7ff) { + r->start = 0; + r->end = 0x3fffff; + r->flags |= IORESOURCE_UNSET; + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x19e1, quirk_intel_th_dnv); + #ifdef CONFIG_PHYS_ADDR_T_64BIT #define AMD_141b_MMIO_BASE(x) (0x80 + (x) * 0x8) diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 458a0e2bcc57..a25a9fd987a9 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -449,7 +449,7 @@ void __init efi_free_boot_services(void) */ rm_size = real_mode_size_needed(); if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) { - set_real_mode_mem(start, rm_size); + set_real_mode_mem(start); start += rm_size; size -= rm_size; } diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c index b4ab779f1d47..ac9e7bf49b66 100644 --- a/arch/x86/platform/olpc/olpc_dt.c +++ b/arch/x86/platform/olpc/olpc_dt.c @@ -141,6 +141,9 @@ void * __init prom_early_alloc(unsigned long size) * wasted bootmem) and hand off chunks of it to callers. */ res = memblock_alloc(chunk_size, SMP_CACHE_BYTES); + if (!res) + panic("%s: Failed to allocate %zu bytes\n", __func__, + chunk_size); BUG_ON(!res); prom_early_allocated += chunk_size; memset(res, 0, chunk_size); diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index d10105825d57..7dce39c8c034 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -15,15 +15,6 @@ u32 *trampoline_cr4_features; /* Hold the pgd entry used on booting additional CPUs */ pgd_t trampoline_pgd_entry; -void __init set_real_mode_mem(phys_addr_t mem, size_t size) -{ - void *base = __va(mem); - - real_mode_header = (struct real_mode_header *) base; - printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n", - base, (unsigned long long)mem, size); -} - void __init reserve_real_mode(void) { phys_addr_t mem; @@ -42,7 +33,7 @@ void __init reserve_real_mode(void) } memblock_reserve(mem, size); - set_real_mode_mem(mem, size); + set_real_mode_mem(mem); } static void __init setup_real_mode(void) diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index 96cb20de08af..f60501a384f9 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -37,8 +37,7 @@ REALMODE_OBJS = $(addprefix $(obj)/,$(realmode-y)) sed-pasyms := -n -r -e 's/^([0-9a-fA-F]+) [ABCDGRSTVW] (.+)$$/pa_\2 = \2;/p' quiet_cmd_pasyms = PASYMS $@ - cmd_pasyms = $(NM) $(filter-out FORCE,$^) | \ - sed $(sed-pasyms) | sort | uniq > $@ + cmd_pasyms = $(NM) $(real-prereqs) | sed $(sed-pasyms) | sort | uniq > $@ targets += pasyms.h $(obj)/pasyms.h: $(REALMODE_OBJS) FORCE diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 856a85814f00..a21e1734fc1f 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2114,10 +2114,10 @@ void __init xen_relocate_p2m(void) pt = early_memremap(pt_phys, PAGE_SIZE); clear_page(pt); for (idx_pte = 0; - idx_pte < min(n_pte, PTRS_PER_PTE); - idx_pte++) { - set_pte(pt + idx_pte, - pfn_pte(p2m_pfn, PAGE_KERNEL)); + idx_pte < min(n_pte, PTRS_PER_PTE); + idx_pte++) { + pt[idx_pte] = pfn_pte(p2m_pfn, + PAGE_KERNEL); p2m_pfn++; } n_pte -= PTRS_PER_PTE; @@ -2125,8 +2125,7 @@ void __init xen_relocate_p2m(void) make_lowmem_page_readonly(__va(pt_phys)); pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, PFN_DOWN(pt_phys)); - set_pmd(pmd + idx_pt, - __pmd(_PAGE_TABLE | pt_phys)); + pmd[idx_pt] = __pmd(_PAGE_TABLE | pt_phys); pt_phys += PAGE_SIZE; } n_pt -= PTRS_PER_PMD; @@ -2134,7 +2133,7 @@ void __init xen_relocate_p2m(void) make_lowmem_page_readonly(__va(pmd_phys)); pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE, PFN_DOWN(pmd_phys)); - set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys)); + pud[idx_pmd] = __pud(_PAGE_TABLE | pmd_phys); pmd_phys += PAGE_SIZE; } n_pmd -= PTRS_PER_PUD; diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 055e37e43541..95ce9b5be411 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -181,8 +181,15 @@ static void p2m_init_identity(unsigned long *p2m, unsigned long pfn) static void * __ref alloc_p2m_page(void) { - if (unlikely(!slab_is_available())) - return memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (unlikely(!slab_is_available())) { + void *ptr = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + + if (!ptr) + panic("%s: Failed to allocate %lu bytes align=0x%lx\n", + __func__, PAGE_SIZE, PAGE_SIZE); + + return ptr; + } return (void *)__get_free_page(GFP_KERNEL); } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index d5f303c0e656..548d1e0a5ba1 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -12,6 +12,7 @@ #include <linux/memblock.h> #include <linux/cpuidle.h> #include <linux/cpufreq.h> +#include <linux/memory_hotplug.h> #include <asm/elf.h> #include <asm/vdso.h> @@ -589,6 +590,14 @@ static void __init xen_align_and_add_e820_region(phys_addr_t start, if (type == E820_TYPE_RAM) { start = PAGE_ALIGN(start); end &= ~((phys_addr_t)PAGE_SIZE - 1); +#ifdef CONFIG_MEMORY_HOTPLUG + /* + * Don't allow adding memory not in E820 map while booting the + * system. Once the balloon driver is up it will remove that + * restriction again. + */ + max_mem_size = end; +#endif } e820__range_add(start, end - start, type); @@ -748,6 +757,10 @@ char * __init xen_memory_setup(void) memmap.nr_entries = ARRAY_SIZE(xen_e820_table.entries); set_xen_guest_handle(memmap.buffer, xen_e820_table.entries); +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_XEN_BALLOON) + xen_saved_max_mem_size = max_mem_size; +#endif + op = xen_initial_domain() ? XENMEM_machine_memory_map : XENMEM_memory_map; |