diff options
Diffstat (limited to 'arch/x86/kvm/x86.c')
| -rw-r--r-- | arch/x86/kvm/x86.c | 4706 |
1 files changed, 2717 insertions, 1989 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c381770bcbf1..0c6d899d53dd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -25,6 +25,7 @@ #include "tss.h" #include "kvm_cache_regs.h" #include "kvm_emulate.h" +#include "mmu/page_track.h" #include "x86.h" #include "cpuid.h" #include "pmu.h" @@ -58,7 +59,6 @@ #include <linux/sched/stat.h> #include <linux/sched/isolation.h> #include <linux/mem_encrypt.h> -#include <linux/entry-kvm.h> #include <linux/suspend.h> #include <linux/smp.h> @@ -89,12 +89,17 @@ #include "trace.h" #define MAX_IO_MSRS 256 -#define KVM_MAX_MCE_BANKS 32 -struct kvm_caps kvm_caps __read_mostly = { - .supported_mce_cap = MCG_CTL_P | MCG_SER_P, -}; -EXPORT_SYMBOL_GPL(kvm_caps); +/* + * Note, kvm_caps fields should *never* have default values, all fields must be + * recomputed from scratch during vendor module load, e.g. to account for a + * vendor module being reloaded with different module parameters. + */ +struct kvm_caps kvm_caps __read_mostly; +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_caps); + +struct kvm_host_values kvm_host __read_mostly; +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_host); #define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e)) @@ -112,8 +117,6 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif -static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; - #define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE) #define KVM_CAP_PMU_VALID_MASK KVM_PMU_CAP_DISABLE @@ -132,6 +135,9 @@ static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); static DEFINE_MUTEX(vendor_module_lock); +static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); +static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); + struct kvm_x86_ops kvm_x86_ops __read_mostly; #define KVM_X86_OP(func) \ @@ -144,37 +150,22 @@ EXPORT_STATIC_CALL_GPL(kvm_x86_get_cs_db_l_bits); EXPORT_STATIC_CALL_GPL(kvm_x86_cache_reg); static bool __read_mostly ignore_msrs = 0; -module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); +module_param(ignore_msrs, bool, 0644); bool __read_mostly report_ignored_msrs = true; -module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR); -EXPORT_SYMBOL_GPL(report_ignored_msrs); +module_param(report_ignored_msrs, bool, 0644); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(report_ignored_msrs); unsigned int min_timer_period_us = 200; -module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); - -static bool __read_mostly kvmclock_periodic_sync = true; -module_param(kvmclock_periodic_sync, bool, S_IRUGO); +module_param(min_timer_period_us, uint, 0644); /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ static u32 __read_mostly tsc_tolerance_ppm = 250; -module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); - -/* - * lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables - * adaptive tuning starting from default advancement of 1000ns. '0' disables - * advancement entirely. Any other value is used as-is and disables adaptive - * tuning, i.e. allows privileged userspace to set an exact advancement time. - */ -static int __read_mostly lapic_timer_advance_ns = -1; -module_param(lapic_timer_advance_ns, int, S_IRUGO | S_IWUSR); - -static bool __read_mostly vector_hashing = true; -module_param(vector_hashing, bool, S_IRUGO); +module_param(tsc_tolerance_ppm, uint, 0644); bool __read_mostly enable_vmware_backdoor = false; -module_param(enable_vmware_backdoor, bool, S_IRUGO); -EXPORT_SYMBOL_GPL(enable_vmware_backdoor); +module_param(enable_vmware_backdoor, bool, 0444); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_vmware_backdoor); /* * Flags to manipulate forced emulation behavior (any non-zero value will @@ -185,11 +176,11 @@ static int __read_mostly force_emulation_prefix; module_param(force_emulation_prefix, int, 0644); int __read_mostly pi_inject_timer = -1; -module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR); +module_param(pi_inject_timer, bint, 0644); /* Enable/disable PMU virtualization */ bool __read_mostly enable_pmu = true; -EXPORT_SYMBOL_GPL(enable_pmu); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_pmu); module_param(enable_pmu, bool, 0444); bool __read_mostly eager_page_split = true; @@ -216,26 +207,35 @@ struct kvm_user_return_msrs { }; u32 __read_mostly kvm_nr_uret_msrs; -EXPORT_SYMBOL_GPL(kvm_nr_uret_msrs); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_nr_uret_msrs); static u32 __read_mostly kvm_uret_msrs_list[KVM_MAX_NR_USER_RETURN_MSRS]; -static struct kvm_user_return_msrs __percpu *user_return_msrs; +static DEFINE_PER_CPU(struct kvm_user_return_msrs, user_return_msrs); #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ | XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512 \ | XFEATURE_MASK_PKRU | XFEATURE_MASK_XTILE) -u64 __read_mostly host_efer; -EXPORT_SYMBOL_GPL(host_efer); +#define XFEATURE_MASK_CET_ALL (XFEATURE_MASK_CET_USER | XFEATURE_MASK_CET_KERNEL) +/* + * Note, KVM supports exposing PT to the guest, but does not support context + * switching PT via XSTATE (KVM's PT virtualization relies on perf; swapping + * PT via guest XSTATE would clobber perf state), i.e. KVM doesn't support + * IA32_XSS[bit 8] (guests can/must use RDMSR/WRMSR to save/restore PT MSRs). + */ +#define KVM_SUPPORTED_XSS (XFEATURE_MASK_CET_ALL) bool __read_mostly allow_smaller_maxphyaddr = 0; -EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(allow_smaller_maxphyaddr); bool __read_mostly enable_apicv = true; -EXPORT_SYMBOL_GPL(enable_apicv); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_apicv); + +bool __read_mostly enable_ipiv = true; +EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_ipiv); -u64 __read_mostly host_xss; -EXPORT_SYMBOL_GPL(host_xss); +bool __read_mostly enable_device_posted_irqs = true; +EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_device_posted_irqs); const struct _kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), @@ -310,29 +310,246 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { sizeof(kvm_vcpu_stats_desc), }; -u64 __read_mostly host_xcr0; - static struct kmem_cache *x86_emulator_cache; /* - * When called, it means the previous get/set msr reached an invalid msr. - * Return true if we want to ignore/silent this failed msr access. + * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) track + * the set of MSRs that KVM exposes to userspace through KVM_GET_MSRS, + * KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. msrs_to_save holds MSRs that + * require host support, i.e. should be probed via RDMSR. emulated_msrs holds + * MSRs that KVM emulates without strictly requiring host support. + * msr_based_features holds MSRs that enumerate features, i.e. are effectively + * CPUID leafs. Note, msr_based_features isn't mutually exclusive with + * msrs_to_save and emulated_msrs. + */ + +static const u32 msrs_to_save_base[] = { + MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, + MSR_STAR, +#ifdef CONFIG_X86_64 + MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, +#endif + MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, + MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, + MSR_IA32_SPEC_CTRL, MSR_IA32_TSX_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, + MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B, + MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B, + MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, + MSR_IA32_UMWAIT_CONTROL, + + MSR_IA32_XFD, MSR_IA32_XFD_ERR, MSR_IA32_XSS, + + MSR_IA32_U_CET, MSR_IA32_S_CET, + MSR_IA32_PL0_SSP, MSR_IA32_PL1_SSP, MSR_IA32_PL2_SSP, + MSR_IA32_PL3_SSP, MSR_IA32_INT_SSP_TAB, +}; + +static const u32 msrs_to_save_pmu[] = { + MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, + MSR_ARCH_PERFMON_FIXED_CTR0 + 2, + MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, + MSR_CORE_PERF_GLOBAL_CTRL, + MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG, + + /* This part of MSRs should match KVM_MAX_NR_INTEL_GP_COUNTERS. */ + MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, + MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3, + MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5, + MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7, + MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, + MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, + MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, + MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7, + + MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, + MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, + + /* This part of MSRs should match KVM_MAX_NR_AMD_GP_COUNTERS. */ + MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, + MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, + MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, + MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, + + MSR_AMD64_PERF_CNTR_GLOBAL_CTL, + MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, + MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, + MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET, +}; + +static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) + + ARRAY_SIZE(msrs_to_save_pmu)]; +static unsigned num_msrs_to_save; + +static const u32 emulated_msrs_all[] = { + MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, + MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, + +#ifdef CONFIG_KVM_HYPERV + HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, + HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, + HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY, + HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2, + HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL, + HV_X64_MSR_RESET, + HV_X64_MSR_VP_INDEX, + HV_X64_MSR_VP_RUNTIME, + HV_X64_MSR_SCONTROL, + HV_X64_MSR_STIMER0_CONFIG, + HV_X64_MSR_VP_ASSIST_PAGE, + HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL, + HV_X64_MSR_TSC_EMULATION_STATUS, HV_X64_MSR_TSC_INVARIANT_CONTROL, + HV_X64_MSR_SYNDBG_OPTIONS, + HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, + HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, + HV_X64_MSR_SYNDBG_PENDING_BUFFER, +#endif + + MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, + MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, + + MSR_IA32_TSC_ADJUST, + MSR_IA32_TSC_DEADLINE, + MSR_IA32_ARCH_CAPABILITIES, + MSR_IA32_PERF_CAPABILITIES, + MSR_IA32_MISC_ENABLE, + MSR_IA32_MCG_STATUS, + MSR_IA32_MCG_CTL, + MSR_IA32_MCG_EXT_CTL, + MSR_IA32_SMBASE, + MSR_SMI_COUNT, + MSR_PLATFORM_INFO, + MSR_MISC_FEATURES_ENABLES, + MSR_AMD64_VIRT_SPEC_CTRL, + MSR_AMD64_TSC_RATIO, + MSR_IA32_POWER_CTL, + MSR_IA32_UCODE_REV, + + /* + * KVM always supports the "true" VMX control MSRs, even if the host + * does not. The VMX MSRs as a whole are considered "emulated" as KVM + * doesn't strictly require them to exist in the host (ignoring that + * KVM would refuse to load in the first place if the core set of MSRs + * aren't supported). + */ + MSR_IA32_VMX_BASIC, + MSR_IA32_VMX_TRUE_PINBASED_CTLS, + MSR_IA32_VMX_TRUE_PROCBASED_CTLS, + MSR_IA32_VMX_TRUE_EXIT_CTLS, + MSR_IA32_VMX_TRUE_ENTRY_CTLS, + MSR_IA32_VMX_MISC, + MSR_IA32_VMX_CR0_FIXED0, + MSR_IA32_VMX_CR4_FIXED0, + MSR_IA32_VMX_VMCS_ENUM, + MSR_IA32_VMX_PROCBASED_CTLS2, + MSR_IA32_VMX_EPT_VPID_CAP, + MSR_IA32_VMX_VMFUNC, + + MSR_K7_HWCR, + MSR_KVM_POLL_CONTROL, +}; + +static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; +static unsigned num_emulated_msrs; + +/* + * List of MSRs that control the existence of MSR-based features, i.e. MSRs + * that are effectively CPUID leafs. VMX MSRs are also included in the set of + * feature MSRs, but are handled separately to allow expedited lookups. + */ +static const u32 msr_based_features_all_except_vmx[] = { + MSR_AMD64_DE_CFG, + MSR_IA32_UCODE_REV, + MSR_IA32_ARCH_CAPABILITIES, + MSR_IA32_PERF_CAPABILITIES, + MSR_PLATFORM_INFO, +}; + +static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all_except_vmx) + + (KVM_LAST_EMULATED_VMX_MSR - KVM_FIRST_EMULATED_VMX_MSR + 1)]; +static unsigned int num_msr_based_features; + +/* + * All feature MSRs except uCode revID, which tracks the currently loaded uCode + * patch, are immutable once the vCPU model is defined. */ -static bool kvm_msr_ignored_check(u32 msr, u64 data, bool write) +static bool kvm_is_immutable_feature_msr(u32 msr) { - const char *op = write ? "wrmsr" : "rdmsr"; + int i; - if (ignore_msrs) { - if (report_ignored_msrs) - kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n", - op, msr, data); - /* Mask the error */ + if (msr >= KVM_FIRST_EMULATED_VMX_MSR && msr <= KVM_LAST_EMULATED_VMX_MSR) return true; - } else { + + for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) { + if (msr == msr_based_features_all_except_vmx[i]) + return msr != MSR_IA32_UCODE_REV; + } + + return false; +} + +static bool kvm_is_advertised_msr(u32 msr_index) +{ + unsigned int i; + + for (i = 0; i < num_msrs_to_save; i++) { + if (msrs_to_save[i] == msr_index) + return true; + } + + for (i = 0; i < num_emulated_msrs; i++) { + if (emulated_msrs[i] == msr_index) + return true; + } + + return false; +} + +typedef int (*msr_access_t)(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated); + +static __always_inline int kvm_do_msr_access(struct kvm_vcpu *vcpu, u32 msr, + u64 *data, bool host_initiated, + enum kvm_msr_access rw, + msr_access_t msr_access_fn) +{ + const char *op = rw == MSR_TYPE_W ? "wrmsr" : "rdmsr"; + int ret; + + BUILD_BUG_ON(rw != MSR_TYPE_R && rw != MSR_TYPE_W); + + /* + * Zero the data on read failures to avoid leaking stack data to the + * guest and/or userspace, e.g. if the failure is ignored below. + */ + ret = msr_access_fn(vcpu, msr, data, host_initiated); + if (ret && rw == MSR_TYPE_R) + *data = 0; + + if (ret != KVM_MSR_RET_UNSUPPORTED) + return ret; + + /* + * Userspace is allowed to read MSRs, and write '0' to MSRs, that KVM + * advertises to userspace, even if an MSR isn't fully supported. + * Simply check that @data is '0', which covers both the write '0' case + * and all reads (in which case @data is zeroed on failure; see above). + */ + if (host_initiated && !*data && kvm_is_advertised_msr(msr)) + return 0; + + if (!ignore_msrs) { kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n", - op, msr, data); - return false; + op, msr, *data); + return ret; } + + if (report_ignored_msrs) + kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n", op, msr, *data); + + return 0; } static struct kmem_cache *kvm_alloc_emulator_cache(void) @@ -355,28 +572,30 @@ static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu) vcpu->arch.apf.gfns[i] = ~0; } +static void kvm_destroy_user_return_msrs(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + WARN_ON_ONCE(per_cpu(user_return_msrs, cpu).registered); + + kvm_nr_uret_msrs = 0; +} + static void kvm_on_user_return(struct user_return_notifier *urn) { unsigned slot; struct kvm_user_return_msrs *msrs = container_of(urn, struct kvm_user_return_msrs, urn); struct kvm_user_return_msr_values *values; - unsigned long flags; - /* - * Disabling irqs at this point since the following code could be - * interrupted and executed through kvm_arch_hardware_disable() - */ - local_irq_save(flags); - if (msrs->registered) { - msrs->registered = false; - user_return_notifier_unregister(urn); - } - local_irq_restore(flags); + msrs->registered = false; + user_return_notifier_unregister(urn); + for (slot = 0; slot < kvm_nr_uret_msrs; ++slot) { values = &msrs->values[slot]; if (values->host != values->curr) { - wrmsrl(kvm_uret_msrs_list[slot], values->host); + wrmsrq(kvm_uret_msrs_list[slot], values->host); values->curr = values->host; } } @@ -388,10 +607,10 @@ static int kvm_probe_user_return_msr(u32 msr) int ret; preempt_disable(); - ret = rdmsrl_safe(msr, &val); + ret = rdmsrq_safe(msr, &val); if (ret) goto out; - ret = wrmsrl_safe(msr, val); + ret = wrmsrq_safe(msr, val); out: preempt_enable(); return ret; @@ -407,7 +626,7 @@ int kvm_add_user_return_msr(u32 msr) kvm_uret_msrs_list[kvm_nr_uret_msrs] = msr; return kvm_nr_uret_msrs++; } -EXPORT_SYMBOL_GPL(kvm_add_user_return_msr); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_add_user_return_msr); int kvm_find_user_return_msr(u32 msr) { @@ -419,84 +638,60 @@ int kvm_find_user_return_msr(u32 msr) } return -1; } -EXPORT_SYMBOL_GPL(kvm_find_user_return_msr); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_find_user_return_msr); static void kvm_user_return_msr_cpu_online(void) { - unsigned int cpu = smp_processor_id(); - struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu); + struct kvm_user_return_msrs *msrs = this_cpu_ptr(&user_return_msrs); u64 value; int i; for (i = 0; i < kvm_nr_uret_msrs; ++i) { - rdmsrl_safe(kvm_uret_msrs_list[i], &value); + rdmsrq_safe(kvm_uret_msrs_list[i], &value); msrs->values[i].host = value; msrs->values[i].curr = value; } } +static void kvm_user_return_register_notifier(struct kvm_user_return_msrs *msrs) +{ + if (!msrs->registered) { + msrs->urn.on_user_return = kvm_on_user_return; + user_return_notifier_register(&msrs->urn); + msrs->registered = true; + } +} + int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask) { - unsigned int cpu = smp_processor_id(); - struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu); + struct kvm_user_return_msrs *msrs = this_cpu_ptr(&user_return_msrs); int err; value = (value & mask) | (msrs->values[slot].host & ~mask); if (value == msrs->values[slot].curr) return 0; - err = wrmsrl_safe(kvm_uret_msrs_list[slot], value); + err = wrmsrq_safe(kvm_uret_msrs_list[slot], value); if (err) return 1; msrs->values[slot].curr = value; - if (!msrs->registered) { - msrs->urn.on_user_return = kvm_on_user_return; - user_return_notifier_register(&msrs->urn); - msrs->registered = true; - } + kvm_user_return_register_notifier(msrs); return 0; } -EXPORT_SYMBOL_GPL(kvm_set_user_return_msr); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_user_return_msr); -static void drop_user_return_notifiers(void) +u64 kvm_get_user_return_msr(unsigned int slot) { - unsigned int cpu = smp_processor_id(); - struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu); - - if (msrs->registered) - kvm_on_user_return(&msrs->urn); + return this_cpu_ptr(&user_return_msrs)->values[slot].curr; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_user_return_msr); -u64 kvm_get_apic_base(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.apic_base; -} - -enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu) -{ - return kvm_apic_mode(kvm_get_apic_base(vcpu)); -} -EXPORT_SYMBOL_GPL(kvm_get_apic_mode); - -int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +static void drop_user_return_notifiers(void) { - enum lapic_mode old_mode = kvm_get_apic_mode(vcpu); - enum lapic_mode new_mode = kvm_apic_mode(msr_info->data); - u64 reserved_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu) | 0x2ff | - (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE); - - if ((msr_info->data & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID) - return 1; - if (!msr_info->host_initiated) { - if (old_mode == LAPIC_MODE_X2APIC && new_mode == LAPIC_MODE_XAPIC) - return 1; - if (old_mode == LAPIC_MODE_DISABLED && new_mode == LAPIC_MODE_X2APIC) - return 1; - } + struct kvm_user_return_msrs *msrs = this_cpu_ptr(&user_return_msrs); - kvm_lapic_set_base(vcpu, msr_info->data); - kvm_recalculate_apic_map(vcpu->kvm); - return 0; + if (msrs->registered) + kvm_on_user_return(&msrs->urn); } /* @@ -511,7 +706,7 @@ noinstr void kvm_spurious_fault(void) /* Fault while not rebooting. We want the trace. */ BUG_ON(!kvm_rebooting); } -EXPORT_SYMBOL_GPL(kvm_spurious_fault); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_spurious_fault); #define EXCPT_BENIGN 0 #define EXCPT_CONTRIBUTORY 1 @@ -616,7 +811,7 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu, ex->has_payload = false; ex->payload = 0; } -EXPORT_SYMBOL_GPL(kvm_deliver_exception_payload); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_deliver_exception_payload); static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vector, bool has_error_code, u32 error_code, @@ -633,15 +828,9 @@ static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vecto ex->payload = payload; } -/* Forcibly leave the nested mode in cases like a vCPU reset */ -static void kvm_leave_nested(struct kvm_vcpu *vcpu) -{ - kvm_x86_ops.nested_ops->leave_nested(vcpu); -} - -static void kvm_multiple_exception(struct kvm_vcpu *vcpu, - unsigned nr, bool has_error, u32 error_code, - bool has_payload, unsigned long payload, bool reinject) +static void kvm_multiple_exception(struct kvm_vcpu *vcpu, unsigned int nr, + bool has_error, u32 error_code, + bool has_payload, unsigned long payload) { u32 prev_nr; int class1, class2; @@ -649,13 +838,10 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, kvm_make_request(KVM_REQ_EVENT, vcpu); /* - * If the exception is destined for L2 and isn't being reinjected, - * morph it to a VM-Exit if L1 wants to intercept the exception. A - * previously injected exception is not checked because it was checked - * when it was original queued, and re-checking is incorrect if _L1_ - * injected the exception, in which case it's exempt from interception. + * If the exception is destined for L2, morph it to a VM-Exit if L1 + * wants to intercept the exception. */ - if (!reinject && is_guest_mode(vcpu) && + if (is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, nr, error_code)) { kvm_queue_exception_vmexit(vcpu, nr, has_error, error_code, has_payload, payload); @@ -664,28 +850,9 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) { queue: - if (reinject) { - /* - * On VM-Entry, an exception can be pending if and only - * if event injection was blocked by nested_run_pending. - * In that case, however, vcpu_enter_guest() requests an - * immediate exit, and the guest shouldn't proceed far - * enough to need reinjection. - */ - WARN_ON_ONCE(kvm_is_exception_pending(vcpu)); - vcpu->arch.exception.injected = true; - if (WARN_ON_ONCE(has_payload)) { - /* - * A reinjected event has already - * delivered its payload. - */ - has_payload = false; - payload = 0; - } - } else { - vcpu->arch.exception.pending = true; - vcpu->arch.exception.injected = false; - } + vcpu->arch.exception.pending = true; + vcpu->arch.exception.injected = false; + vcpu->arch.exception.has_error_code = has_error; vcpu->arch.exception.vector = nr; vcpu->arch.exception.error_code = error_code; @@ -726,29 +893,52 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr) { - kvm_multiple_exception(vcpu, nr, false, 0, false, 0, false); + kvm_multiple_exception(vcpu, nr, false, 0, false, 0); } -EXPORT_SYMBOL_GPL(kvm_queue_exception); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_queue_exception); -void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr) -{ - kvm_multiple_exception(vcpu, nr, false, 0, false, 0, true); -} -EXPORT_SYMBOL_GPL(kvm_requeue_exception); void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long payload) { - kvm_multiple_exception(vcpu, nr, false, 0, true, payload, false); + kvm_multiple_exception(vcpu, nr, false, 0, true, payload); } -EXPORT_SYMBOL_GPL(kvm_queue_exception_p); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_queue_exception_p); static void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code, unsigned long payload) { - kvm_multiple_exception(vcpu, nr, true, error_code, - true, payload, false); + kvm_multiple_exception(vcpu, nr, true, error_code, true, payload); +} + +void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned int nr, + bool has_error_code, u32 error_code) +{ + + /* + * On VM-Entry, an exception can be pending if and only if event + * injection was blocked by nested_run_pending. In that case, however, + * vcpu_enter_guest() requests an immediate exit, and the guest + * shouldn't proceed far enough to need reinjection. + */ + WARN_ON_ONCE(kvm_is_exception_pending(vcpu)); + + /* + * Do not check for interception when injecting an event for L2, as the + * exception was checked for intercept when it was original queued, and + * re-checking is incorrect if _L1_ injected the exception, in which + * case it's exempt from interception. + */ + kvm_make_request(KVM_REQ_EVENT, vcpu); + + vcpu->arch.exception.injected = true; + vcpu->arch.exception.has_error_code = has_error_code; + vcpu->arch.exception.vector = nr; + vcpu->arch.exception.error_code = error_code; + vcpu->arch.exception.has_payload = false; + vcpu->arch.exception.payload = 0; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_requeue_exception); int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err) { @@ -759,7 +949,7 @@ int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err) return 1; } -EXPORT_SYMBOL_GPL(kvm_complete_insn_gp); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_complete_insn_gp); static int complete_emulated_insn_gp(struct kvm_vcpu *vcpu, int err) { @@ -809,7 +999,7 @@ void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, fault_mmu->inject_page_fault(vcpu, fault); } -EXPORT_SYMBOL_GPL(kvm_inject_emulated_page_fault); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_inject_emulated_page_fault); void kvm_inject_nmi(struct kvm_vcpu *vcpu) { @@ -819,15 +1009,9 @@ void kvm_inject_nmi(struct kvm_vcpu *vcpu) void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) { - kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, false); + kvm_multiple_exception(vcpu, nr, true, error_code, false, 0); } -EXPORT_SYMBOL_GPL(kvm_queue_exception_e); - -void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) -{ - kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, true); -} -EXPORT_SYMBOL_GPL(kvm_requeue_exception_e); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_queue_exception_e); /* * Checks if cpl <= required_cpl; if true, return true. Otherwise queue @@ -835,7 +1019,7 @@ EXPORT_SYMBOL_GPL(kvm_requeue_exception_e); */ bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) { - if (static_call(kvm_x86_get_cpl)(vcpu) <= required_cpl) + if (kvm_x86_call(get_cpl)(vcpu) <= required_cpl) return true; kvm_queue_exception_e(vcpu, GP_VECTOR, 0); return false; @@ -849,7 +1033,14 @@ bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr) kvm_queue_exception(vcpu, UD_VECTOR); return false; } -EXPORT_SYMBOL_GPL(kvm_require_dr); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_require_dr); + +static bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu) +{ + u64 mask = KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT; + + return (vcpu->arch.apf.msr_en_val & mask) == mask; +} static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) { @@ -904,7 +1095,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) return 1; } -EXPORT_SYMBOL_GPL(load_pdptrs); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(load_pdptrs); static bool kvm_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { @@ -919,7 +1110,7 @@ static bool kvm_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) return false; - return static_call(kvm_x86_is_valid_cr0)(vcpu, cr0); + return kvm_x86_call(is_valid_cr0)(vcpu, cr0); } void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0) @@ -943,26 +1134,26 @@ void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned lon } if ((cr0 ^ old_cr0) & X86_CR0_PG) { - kvm_clear_async_pf_completion_queue(vcpu); - kvm_async_pf_hash_reset(vcpu); - /* * Clearing CR0.PG is defined to flush the TLB from the guest's * perspective. */ if (!(cr0 & X86_CR0_PG)) kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + /* + * Check for async #PF completion events when enabling paging, + * as the vCPU may have previously encountered async #PFs (it's + * entirely legal for the guest to toggle paging on/off without + * waiting for the async #PF queue to drain). + */ + else if (kvm_pv_async_pf_enabled(vcpu)) + kvm_make_request(KVM_REQ_APF_READY, vcpu); } if ((cr0 ^ old_cr0) & KVM_MMU_CR0_ROLE_BITS) kvm_mmu_reset_context(vcpu); - - if (((cr0 ^ old_cr0) & X86_CR0_CD) && - kvm_arch_has_noncoherent_dma(vcpu->kvm) && - !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) - kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL); } -EXPORT_SYMBOL_GPL(kvm_post_set_cr0); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_post_set_cr0); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { @@ -983,7 +1174,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!is_pae(vcpu)) return 1; - static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); + kvm_x86_call(get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); if (cs_l) return 1; } @@ -997,44 +1188,53 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) (is_64_bit_mode(vcpu) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE))) return 1; - static_call(kvm_x86_set_cr0)(vcpu, cr0); + if (!(cr0 & X86_CR0_WP) && kvm_is_cr4_bit_set(vcpu, X86_CR4_CET)) + return 1; + + kvm_x86_call(set_cr0)(vcpu, cr0); kvm_post_set_cr0(vcpu, old_cr0, cr0); return 0; } -EXPORT_SYMBOL_GPL(kvm_set_cr0); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_cr0); void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) { (void)kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0eul) | (msw & 0x0f)); } -EXPORT_SYMBOL_GPL(kvm_lmsw); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_lmsw); -void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) +static void kvm_load_xfeatures(struct kvm_vcpu *vcpu, bool load_guest) { if (vcpu->arch.guest_state_protected) return; - if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) { + if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) + return; - if (vcpu->arch.xcr0 != host_xcr0) - xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); + if (vcpu->arch.xcr0 != kvm_host.xcr0) + xsetbv(XCR_XFEATURE_ENABLED_MASK, + load_guest ? vcpu->arch.xcr0 : kvm_host.xcr0); - if (vcpu->arch.xsaves_enabled && - vcpu->arch.ia32_xss != host_xss) - wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss); - } + if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) && + vcpu->arch.ia32_xss != kvm_host.xss) + wrmsrq(MSR_IA32_XSS, load_guest ? vcpu->arch.ia32_xss : kvm_host.xss); +} + +static void kvm_load_guest_pkru(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.guest_state_protected) + return; if (cpu_feature_enabled(X86_FEATURE_PKU) && vcpu->arch.pkru != vcpu->arch.host_pkru && ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) - write_pkru(vcpu->arch.pkru); + wrpkru(vcpu->arch.pkru); } -EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state); -void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) +static void kvm_load_host_pkru(struct kvm_vcpu *vcpu) { if (vcpu->arch.guest_state_protected) return; @@ -1044,21 +1244,9 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) { vcpu->arch.pkru = rdpkru(); if (vcpu->arch.pkru != vcpu->arch.host_pkru) - write_pkru(vcpu->arch.host_pkru); - } - - if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) { - - if (vcpu->arch.xcr0 != host_xcr0) - xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); - - if (vcpu->arch.xsaves_enabled && - vcpu->arch.ia32_xss != host_xss) - wrmsrl(MSR_IA32_XSS, host_xss); + wrpkru(vcpu->arch.host_pkru); } - } -EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state); #ifdef CONFIG_X86_64 static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu) @@ -1067,7 +1255,7 @@ static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu) } #endif -static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) +int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { u64 xcr0 = xcr; u64 old_xcr0 = vcpu->arch.xcr0; @@ -1108,14 +1296,15 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) vcpu->arch.xcr0 = xcr0; if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND) - kvm_update_cpuid_runtime(vcpu); + vcpu->arch.cpuid_dynamic_bits_dirty = true; return 0; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_set_xcr); int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu) { /* Note, #UD due to CR4.OSXSAVE=0 has priority over the intercept. */ - if (static_call(kvm_x86_get_cpl)(vcpu) != 0 || + if (kvm_x86_call(get_cpl)(vcpu) != 0 || __kvm_set_xcr(vcpu, kvm_rcx_read(vcpu), kvm_read_edx_eax(vcpu))) { kvm_inject_gp(vcpu, 0); return 1; @@ -1123,24 +1312,12 @@ int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } -EXPORT_SYMBOL_GPL(kvm_emulate_xsetbv); - -bool __kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) -{ - if (cr4 & cr4_reserved_bits) - return false; - - if (cr4 & vcpu->arch.cr4_guest_rsvd_bits) - return false; - - return true; -} -EXPORT_SYMBOL_GPL(__kvm_is_valid_cr4); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_xsetbv); static bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { return __kvm_is_valid_cr4(vcpu, cr4) && - static_call(kvm_x86_is_valid_cr4)(vcpu, cr4); + kvm_x86_call(is_valid_cr4)(vcpu, cr4); } void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4) @@ -1183,7 +1360,7 @@ void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned lon kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } -EXPORT_SYMBOL_GPL(kvm_post_set_cr4); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_post_set_cr4); int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { @@ -1208,13 +1385,16 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; } - static_call(kvm_x86_set_cr4)(vcpu, cr4); + if ((cr4 & X86_CR4_CET) && !kvm_is_cr0_bit_set(vcpu, X86_CR0_WP)) + return 1; + + kvm_x86_call(set_cr4)(vcpu, cr4); kvm_post_set_cr4(vcpu, old_cr4, cr4); return 0; } -EXPORT_SYMBOL_GPL(kvm_set_cr4); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_cr4); static void kvm_invalidate_pcid(struct kvm_vcpu *vcpu, unsigned long pcid) { @@ -1280,7 +1460,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) * stuff CR3, e.g. for RSM emulation, and there is no guarantee that * the current vCPU mode is accurate. */ - if (kvm_vcpu_is_illegal_gpa(vcpu, cr3)) + if (!kvm_vcpu_is_legal_cr3(vcpu, cr3)) return 1; if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3)) @@ -1306,7 +1486,7 @@ handle_tlb_flush: return 0; } -EXPORT_SYMBOL_GPL(kvm_set_cr3); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_cr3); int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) { @@ -1318,7 +1498,7 @@ int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) vcpu->arch.cr8 = cr8; return 0; } -EXPORT_SYMBOL_GPL(kvm_set_cr8); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_cr8); unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) { @@ -1327,7 +1507,7 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) else return vcpu->arch.cr8; } -EXPORT_SYMBOL_GPL(kvm_get_cr8); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_cr8); static void kvm_update_dr0123(struct kvm_vcpu *vcpu) { @@ -1347,21 +1527,21 @@ void kvm_update_dr7(struct kvm_vcpu *vcpu) dr7 = vcpu->arch.guest_debug_dr7; else dr7 = vcpu->arch.dr7; - static_call(kvm_x86_set_dr7)(vcpu, dr7); + kvm_x86_call(set_dr7)(vcpu, dr7); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_BP_ENABLED; if (dr7 & DR7_BP_EN_MASK) vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED; } -EXPORT_SYMBOL_GPL(kvm_update_dr7); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_update_dr7); static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) { u64 fixed = DR6_FIXED_1; - if (!guest_cpuid_has(vcpu, X86_FEATURE_RTM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_RTM)) fixed |= DR6_RTM; - if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) fixed |= DR6_BUS_LOCK; return fixed; } @@ -1393,34 +1573,31 @@ int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) return 0; } -EXPORT_SYMBOL_GPL(kvm_set_dr); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_dr); -void kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) +unsigned long kvm_get_dr(struct kvm_vcpu *vcpu, int dr) { size_t size = ARRAY_SIZE(vcpu->arch.db); switch (dr) { case 0 ... 3: - *val = vcpu->arch.db[array_index_nospec(dr, size)]; - break; + return vcpu->arch.db[array_index_nospec(dr, size)]; case 4: case 6: - *val = vcpu->arch.dr6; - break; + return vcpu->arch.dr6; case 5: default: /* 7 */ - *val = vcpu->arch.dr7; - break; + return vcpu->arch.dr7; } } -EXPORT_SYMBOL_GPL(kvm_get_dr); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_dr); int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu) { - u32 ecx = kvm_rcx_read(vcpu); + u32 pmc = kvm_rcx_read(vcpu); u64 data; - if (kvm_pmu_rdpmc(vcpu, ecx, &data)) { + if (kvm_pmu_rdpmc(vcpu, pmc, &data)) { kvm_inject_gp(vcpu, 0); return 1; } @@ -1429,176 +1606,7 @@ int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu) kvm_rdx_write(vcpu, data >> 32); return kvm_skip_emulated_instruction(vcpu); } -EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc); - -/* - * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) track - * the set of MSRs that KVM exposes to userspace through KVM_GET_MSRS, - * KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. msrs_to_save holds MSRs that - * require host support, i.e. should be probed via RDMSR. emulated_msrs holds - * MSRs that KVM emulates without strictly requiring host support. - * msr_based_features holds MSRs that enumerate features, i.e. are effectively - * CPUID leafs. Note, msr_based_features isn't mutually exclusive with - * msrs_to_save and emulated_msrs. - */ - -static const u32 msrs_to_save_base[] = { - MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, - MSR_STAR, -#ifdef CONFIG_X86_64 - MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, -#endif - MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, - MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, - MSR_IA32_SPEC_CTRL, MSR_IA32_TSX_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, - MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B, - MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B, - MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, - MSR_IA32_UMWAIT_CONTROL, - - MSR_IA32_XFD, MSR_IA32_XFD_ERR, -}; - -static const u32 msrs_to_save_pmu[] = { - MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, - MSR_ARCH_PERFMON_FIXED_CTR0 + 2, - MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, - MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL, - MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG, - - /* This part of MSRs should match KVM_INTEL_PMC_MAX_GENERIC. */ - MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, - MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3, - MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5, - MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7, - MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, - MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, - MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, - MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7, - - MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, - MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, - - /* This part of MSRs should match KVM_AMD_PMC_MAX_GENERIC. */ - MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, - MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, - MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, - MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, - - MSR_AMD64_PERF_CNTR_GLOBAL_CTL, - MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, - MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, -}; - -static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) + - ARRAY_SIZE(msrs_to_save_pmu)]; -static unsigned num_msrs_to_save; - -static const u32 emulated_msrs_all[] = { - MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, - MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, - HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, - HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, - HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY, - HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2, - HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL, - HV_X64_MSR_RESET, - HV_X64_MSR_VP_INDEX, - HV_X64_MSR_VP_RUNTIME, - HV_X64_MSR_SCONTROL, - HV_X64_MSR_STIMER0_CONFIG, - HV_X64_MSR_VP_ASSIST_PAGE, - HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL, - HV_X64_MSR_TSC_EMULATION_STATUS, HV_X64_MSR_TSC_INVARIANT_CONTROL, - HV_X64_MSR_SYNDBG_OPTIONS, - HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, - HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, - HV_X64_MSR_SYNDBG_PENDING_BUFFER, - - MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, - MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, - - MSR_IA32_TSC_ADJUST, - MSR_IA32_TSC_DEADLINE, - MSR_IA32_ARCH_CAPABILITIES, - MSR_IA32_PERF_CAPABILITIES, - MSR_IA32_MISC_ENABLE, - MSR_IA32_MCG_STATUS, - MSR_IA32_MCG_CTL, - MSR_IA32_MCG_EXT_CTL, - MSR_IA32_SMBASE, - MSR_SMI_COUNT, - MSR_PLATFORM_INFO, - MSR_MISC_FEATURES_ENABLES, - MSR_AMD64_VIRT_SPEC_CTRL, - MSR_AMD64_TSC_RATIO, - MSR_IA32_POWER_CTL, - MSR_IA32_UCODE_REV, - - /* - * KVM always supports the "true" VMX control MSRs, even if the host - * does not. The VMX MSRs as a whole are considered "emulated" as KVM - * doesn't strictly require them to exist in the host (ignoring that - * KVM would refuse to load in the first place if the core set of MSRs - * aren't supported). - */ - MSR_IA32_VMX_BASIC, - MSR_IA32_VMX_TRUE_PINBASED_CTLS, - MSR_IA32_VMX_TRUE_PROCBASED_CTLS, - MSR_IA32_VMX_TRUE_EXIT_CTLS, - MSR_IA32_VMX_TRUE_ENTRY_CTLS, - MSR_IA32_VMX_MISC, - MSR_IA32_VMX_CR0_FIXED0, - MSR_IA32_VMX_CR4_FIXED0, - MSR_IA32_VMX_VMCS_ENUM, - MSR_IA32_VMX_PROCBASED_CTLS2, - MSR_IA32_VMX_EPT_VPID_CAP, - MSR_IA32_VMX_VMFUNC, - - MSR_K7_HWCR, - MSR_KVM_POLL_CONTROL, -}; - -static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; -static unsigned num_emulated_msrs; - -/* - * List of MSRs that control the existence of MSR-based features, i.e. MSRs - * that are effectively CPUID leafs. VMX MSRs are also included in the set of - * feature MSRs, but are handled separately to allow expedited lookups. - */ -static const u32 msr_based_features_all_except_vmx[] = { - MSR_AMD64_DE_CFG, - MSR_IA32_UCODE_REV, - MSR_IA32_ARCH_CAPABILITIES, - MSR_IA32_PERF_CAPABILITIES, -}; - -static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all_except_vmx) + - (KVM_LAST_EMULATED_VMX_MSR - KVM_FIRST_EMULATED_VMX_MSR + 1)]; -static unsigned int num_msr_based_features; - -/* - * All feature MSRs except uCode revID, which tracks the currently loaded uCode - * patch, are immutable once the vCPU model is defined. - */ -static bool kvm_is_immutable_feature_msr(u32 msr) -{ - int i; - - if (msr >= KVM_FIRST_EMULATED_VMX_MSR && msr <= KVM_LAST_EMULATED_VMX_MSR) - return true; - - for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) { - if (msr == msr_based_features_all_except_vmx[i]) - return msr != MSR_IA32_UCODE_REV; - } - - return false; -} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_rdpmc); /* * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM @@ -1616,16 +1624,12 @@ static bool kvm_is_immutable_feature_msr(u32 msr) ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ - ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO) + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO | ARCH_CAP_ITS_NO) static u64 kvm_get_arch_capabilities(void) { - u64 data = 0; - - if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) { - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data); - data &= KVM_SUPPORTED_ARCH_CAP; - } + u64 data = kvm_host.arch_capabilities & KVM_SUPPORTED_ARCH_CAP; /* * If nx_huge_pages is enabled, KVM's shadow paging will ensure that @@ -1653,6 +1657,10 @@ static u64 kvm_get_arch_capabilities(void) data |= ARCH_CAP_SSB_NO; if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + data |= ARCH_CAP_RFDS_NO; + if (!boot_cpu_has_bug(X86_BUG_ITS)) + data |= ARCH_CAP_ITS_NO; if (!boot_cpu_has(X86_FEATURE_RTM)) { /* @@ -1679,63 +1687,52 @@ static u64 kvm_get_arch_capabilities(void) return data; } -static int kvm_get_msr_feature(struct kvm_msr_entry *msr) +static int kvm_get_feature_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated) { - switch (msr->index) { + WARN_ON_ONCE(!host_initiated); + + switch (index) { case MSR_IA32_ARCH_CAPABILITIES: - msr->data = kvm_get_arch_capabilities(); + *data = kvm_get_arch_capabilities(); break; case MSR_IA32_PERF_CAPABILITIES: - msr->data = kvm_caps.supported_perf_cap; + *data = kvm_caps.supported_perf_cap; + break; + case MSR_PLATFORM_INFO: + *data = MSR_PLATFORM_INFO_CPUID_FAULT; break; case MSR_IA32_UCODE_REV: - rdmsrl_safe(msr->index, &msr->data); + rdmsrq_safe(index, data); break; default: - return static_call(kvm_x86_get_msr_feature)(msr); + return kvm_x86_call(get_feature_msr)(index, data); } return 0; } -static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +static int do_get_feature_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { - struct kvm_msr_entry msr; - int r; - - msr.index = index; - r = kvm_get_msr_feature(&msr); - - if (r == KVM_MSR_RET_INVALID) { - /* Unconditionally clear the output for simplicity */ - *data = 0; - if (kvm_msr_ignored_check(index, 0, false)) - r = 0; - } - - if (r) - return r; - - *data = msr.data; - - return 0; + return kvm_do_msr_access(vcpu, index, data, true, MSR_TYPE_R, + kvm_get_feature_msr); } static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { - if (efer & EFER_AUTOIBRS && !guest_cpuid_has(vcpu, X86_FEATURE_AUTOIBRS)) + if (efer & EFER_AUTOIBRS && !guest_cpu_cap_has(vcpu, X86_FEATURE_AUTOIBRS)) return false; - if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT)) + if (efer & EFER_FFXSR && !guest_cpu_cap_has(vcpu, X86_FEATURE_FXSR_OPT)) return false; - if (efer & EFER_SVME && !guest_cpuid_has(vcpu, X86_FEATURE_SVM)) + if (efer & EFER_SVME && !guest_cpu_cap_has(vcpu, X86_FEATURE_SVM)) return false; if (efer & (EFER_LME | EFER_LMA) && - !guest_cpuid_has(vcpu, X86_FEATURE_LM)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) return false; - if (efer & EFER_NX && !guest_cpuid_has(vcpu, X86_FEATURE_NX)) + if (efer & EFER_NX && !guest_cpu_cap_has(vcpu, X86_FEATURE_NX)) return false; return true; @@ -1748,7 +1745,7 @@ bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) return __kvm_valid_efer(vcpu, efer); } -EXPORT_SYMBOL_GPL(kvm_valid_efer); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_valid_efer); static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { @@ -1771,7 +1768,7 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info) efer &= ~EFER_LMA; efer |= vcpu->arch.efer & EFER_LMA; - r = static_call(kvm_x86_set_efer)(vcpu, efer); + r = kvm_x86_call(set_efer)(vcpu, efer); if (r) { WARN_ON(r > 0); return r; @@ -1780,6 +1777,10 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if ((efer ^ old_efer) & KVM_MMU_EFER_ROLE_BITS) kvm_mmu_reset_context(vcpu); + if (!static_cpu_has(X86_FEATURE_XSAVES) && + (efer & EFER_SVME)) + kvm_hv_xsaves_xsavec_maybe_warn(vcpu); + return 0; } @@ -1787,7 +1788,7 @@ void kvm_enable_efer_bits(u64 mask) { efer_reserved_bits &= ~mask; } -EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_enable_efer_bits); bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type) { @@ -1830,7 +1831,7 @@ out: return allowed; } -EXPORT_SYMBOL_GPL(kvm_msr_allowed); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_msr_allowed); /* * Write @data into the MSR specified by @index. Select MSR specific fault @@ -1849,7 +1850,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, case MSR_KERNEL_GS_BASE: case MSR_CSTAR: case MSR_LSTAR: - if (is_noncanonical_address(data, vcpu)) + if (is_noncanonical_msr_address(data, vcpu)) return 1; break; case MSR_IA32_SYSENTER_EIP: @@ -1866,15 +1867,15 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, * value, and that something deterministic happens if the guest * invokes 64-bit SYSENTER. */ - data = __canonical_address(data, vcpu_virt_addr_bits(vcpu)); + data = __canonical_address(data, max_host_virt_addr_bits()); break; case MSR_TSC_AUX: if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) return 1; if (!host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && - !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID)) return 1; /* @@ -1882,34 +1883,73 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, * incomplete and conflicting architectural behavior. Current * AMD CPUs completely ignore bits 63:32, i.e. they aren't * reserved and always read as zeros. Enforce Intel's reserved - * bits check if and only if the guest CPU is Intel, and clear - * the bits in all other cases. This ensures cross-vendor - * migration will provide consistent behavior for the guest. + * bits check if the guest CPU is Intel compatible, otherwise + * clear the bits. This ensures cross-vendor migration will + * provide consistent behavior for the guest. */ - if (guest_cpuid_is_intel(vcpu) && (data >> 32) != 0) + if (guest_cpuid_is_intel_compatible(vcpu) && (data >> 32) != 0) return 1; data = (u32)data; break; + case MSR_IA32_U_CET: + case MSR_IA32_S_CET: + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_IBT)) + return KVM_MSR_RET_UNSUPPORTED; + if (!kvm_is_valid_u_s_cet(vcpu, data)) + return 1; + break; + case MSR_KVM_INTERNAL_GUEST_SSP: + if (!host_initiated) + return 1; + fallthrough; + /* + * Note that the MSR emulation here is flawed when a vCPU + * doesn't support the Intel 64 architecture. The expected + * architectural behavior in this case is that the upper 32 + * bits do not exist and should always read '0'. However, + * because the actual hardware on which the virtual CPU is + * running does support Intel 64, XRSTORS/XSAVES in the + * guest could observe behavior that violates the + * architecture. Intercepting XRSTORS/XSAVES for this + * special case isn't deemed worthwhile. + */ + case MSR_IA32_PL0_SSP ... MSR_IA32_INT_SSP_TAB: + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) + return KVM_MSR_RET_UNSUPPORTED; + /* + * MSR_IA32_INT_SSP_TAB is not present on processors that do + * not support Intel 64 architecture. + */ + if (index == MSR_IA32_INT_SSP_TAB && !guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) + return KVM_MSR_RET_UNSUPPORTED; + if (is_noncanonical_msr_address(data, vcpu)) + return 1; + /* All SSP MSRs except MSR_IA32_INT_SSP_TAB must be 4-byte aligned */ + if (index != MSR_IA32_INT_SSP_TAB && !IS_ALIGNED(data, 4)) + return 1; + break; } msr.data = data; msr.index = index; msr.host_initiated = host_initiated; - return static_call(kvm_x86_set_msr)(vcpu, &msr); + return kvm_x86_call(set_msr)(vcpu, &msr); +} + +static int _kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated) +{ + return __kvm_set_msr(vcpu, index, *data, host_initiated); } static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, u32 index, u64 data, bool host_initiated) { - int ret = __kvm_set_msr(vcpu, index, data, host_initiated); - - if (ret == KVM_MSR_RET_INVALID) - if (kvm_msr_ignored_check(index, data, true)) - ret = 0; - - return ret; + return kvm_do_msr_access(vcpu, index, &data, host_initiated, MSR_TYPE_W, + _kvm_set_msr); } /* @@ -1918,8 +1958,8 @@ static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, - bool host_initiated) +static int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated) { struct msr_data msr; int ret; @@ -1930,61 +1970,82 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, return 1; if (!host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && - !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID)) return 1; break; + case MSR_IA32_U_CET: + case MSR_IA32_S_CET: + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_IBT)) + return KVM_MSR_RET_UNSUPPORTED; + break; + case MSR_KVM_INTERNAL_GUEST_SSP: + if (!host_initiated) + return 1; + fallthrough; + case MSR_IA32_PL0_SSP ... MSR_IA32_INT_SSP_TAB: + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) + return KVM_MSR_RET_UNSUPPORTED; + break; } msr.index = index; msr.host_initiated = host_initiated; - ret = static_call(kvm_x86_get_msr)(vcpu, &msr); + ret = kvm_x86_call(get_msr)(vcpu, &msr); if (!ret) *data = msr.data; return ret; } -static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, - u32 index, u64 *data, bool host_initiated) +int kvm_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data) { - int ret = __kvm_get_msr(vcpu, index, data, host_initiated); + return __kvm_set_msr(vcpu, index, data, true); +} - if (ret == KVM_MSR_RET_INVALID) { - /* Unconditionally clear *data for simplicity */ - *data = 0; - if (kvm_msr_ignored_check(index, 0, false)) - ret = 0; - } +int kvm_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data) +{ + return __kvm_get_msr(vcpu, index, data, true); +} - return ret; +static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, + u32 index, u64 *data, bool host_initiated) +{ + return kvm_do_msr_access(vcpu, index, data, host_initiated, MSR_TYPE_R, + __kvm_get_msr); } -static int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data) +int __kvm_emulate_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data) { - if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) - return KVM_MSR_RET_FILTERED; return kvm_get_msr_ignored_check(vcpu, index, data, false); } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_emulate_msr_read); -static int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data) +int __kvm_emulate_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data) { - if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE)) - return KVM_MSR_RET_FILTERED; return kvm_set_msr_ignored_check(vcpu, index, data, false); } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_emulate_msr_write); -int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) +int kvm_emulate_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data) { - return kvm_get_msr_ignored_check(vcpu, index, data, false); + if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) + return KVM_MSR_RET_FILTERED; + + return __kvm_emulate_msr_read(vcpu, index, data); } -EXPORT_SYMBOL_GPL(kvm_get_msr); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_msr_read); -int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) +int kvm_emulate_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data) { - return kvm_set_msr_ignored_check(vcpu, index, data, false); + if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE)) + return KVM_MSR_RET_FILTERED; + + return __kvm_emulate_msr_write(vcpu, index, data); } -EXPORT_SYMBOL_GPL(kvm_set_msr); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_msr_write); + static void complete_userspace_rdmsr(struct kvm_vcpu *vcpu) { @@ -2007,7 +2068,7 @@ static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) static int complete_fast_msr_access(struct kvm_vcpu *vcpu) { - return static_call(kvm_x86_complete_emulated_msr)(vcpu, vcpu->run->msr.error); + return kvm_x86_call(complete_emulated_msr)(vcpu, vcpu->run->msr.error); } static int complete_fast_rdmsr(struct kvm_vcpu *vcpu) @@ -2016,10 +2077,19 @@ static int complete_fast_rdmsr(struct kvm_vcpu *vcpu) return complete_fast_msr_access(vcpu); } +static int complete_fast_rdmsr_imm(struct kvm_vcpu *vcpu) +{ + if (!vcpu->run->msr.error) + kvm_register_write(vcpu, vcpu->arch.cui_rdmsr_imm_reg, + vcpu->run->msr.data); + + return complete_fast_msr_access(vcpu); +} + static u64 kvm_msr_reason(int r) { switch (r) { - case KVM_MSR_RET_INVALID: + case KVM_MSR_RET_UNSUPPORTED: return KVM_MSR_EXIT_REASON_UNKNOWN; case KVM_MSR_RET_FILTERED: return KVM_MSR_EXIT_REASON_FILTER; @@ -2050,55 +2120,82 @@ static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index, return 1; } -int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) +static int __kvm_emulate_rdmsr(struct kvm_vcpu *vcpu, u32 msr, int reg, + int (*complete_rdmsr)(struct kvm_vcpu *)) { - u32 ecx = kvm_rcx_read(vcpu); u64 data; int r; - r = kvm_get_msr_with_filter(vcpu, ecx, &data); + r = kvm_emulate_msr_read(vcpu, msr, &data); if (!r) { - trace_kvm_msr_read(ecx, data); + trace_kvm_msr_read(msr, data); - kvm_rax_write(vcpu, data & -1u); - kvm_rdx_write(vcpu, (data >> 32) & -1u); + if (reg < 0) { + kvm_rax_write(vcpu, data & -1u); + kvm_rdx_write(vcpu, (data >> 32) & -1u); + } else { + kvm_register_write(vcpu, reg, data); + } } else { /* MSR read failed? See if we should ask user space */ - if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_RDMSR, 0, - complete_fast_rdmsr, r)) + if (kvm_msr_user_space(vcpu, msr, KVM_EXIT_X86_RDMSR, 0, + complete_rdmsr, r)) return 0; - trace_kvm_msr_read_ex(ecx); + trace_kvm_msr_read_ex(msr); } - return static_call(kvm_x86_complete_emulated_msr)(vcpu, r); + return kvm_x86_call(complete_emulated_msr)(vcpu, r); } -EXPORT_SYMBOL_GPL(kvm_emulate_rdmsr); -int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) +int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) { - u32 ecx = kvm_rcx_read(vcpu); - u64 data = kvm_read_edx_eax(vcpu); - int r; + return __kvm_emulate_rdmsr(vcpu, kvm_rcx_read(vcpu), -1, + complete_fast_rdmsr); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_rdmsr); - r = kvm_set_msr_with_filter(vcpu, ecx, data); +int kvm_emulate_rdmsr_imm(struct kvm_vcpu *vcpu, u32 msr, int reg) +{ + vcpu->arch.cui_rdmsr_imm_reg = reg; + return __kvm_emulate_rdmsr(vcpu, msr, reg, complete_fast_rdmsr_imm); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_rdmsr_imm); + +static int __kvm_emulate_wrmsr(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + int r; + + r = kvm_emulate_msr_write(vcpu, msr, data); if (!r) { - trace_kvm_msr_write(ecx, data); + trace_kvm_msr_write(msr, data); } else { /* MSR write failed? See if we should ask user space */ - if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_WRMSR, data, + if (kvm_msr_user_space(vcpu, msr, KVM_EXIT_X86_WRMSR, data, complete_fast_msr_access, r)) return 0; /* Signal all other negative errors to userspace */ if (r < 0) return r; - trace_kvm_msr_write_ex(ecx, data); + trace_kvm_msr_write_ex(msr, data); } - return static_call(kvm_x86_complete_emulated_msr)(vcpu, r); + return kvm_x86_call(complete_emulated_msr)(vcpu, r); } -EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr); + +int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) +{ + return __kvm_emulate_wrmsr(vcpu, kvm_rcx_read(vcpu), + kvm_read_edx_eax(vcpu)); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_wrmsr); + +int kvm_emulate_wrmsr_imm(struct kvm_vcpu *vcpu, u32 msr, int reg) +{ + return __kvm_emulate_wrmsr(vcpu, msr, kvm_register_read(vcpu, reg)); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_wrmsr_imm); int kvm_emulate_as_nop(struct kvm_vcpu *vcpu) { @@ -2110,22 +2207,41 @@ int kvm_emulate_invd(struct kvm_vcpu *vcpu) /* Treat an INVD instruction as a NOP and just skip it. */ return kvm_emulate_as_nop(vcpu); } -EXPORT_SYMBOL_GPL(kvm_emulate_invd); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_invd); + +fastpath_t handle_fastpath_invd(struct kvm_vcpu *vcpu) +{ + if (!kvm_emulate_invd(vcpu)) + return EXIT_FASTPATH_EXIT_USERSPACE; + + return EXIT_FASTPATH_REENTER_GUEST; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(handle_fastpath_invd); int kvm_handle_invalid_op(struct kvm_vcpu *vcpu) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } -EXPORT_SYMBOL_GPL(kvm_handle_invalid_op); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_handle_invalid_op); static int kvm_emulate_monitor_mwait(struct kvm_vcpu *vcpu, const char *insn) { - if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS) && - !guest_cpuid_has(vcpu, X86_FEATURE_MWAIT)) + bool enabled; + + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS)) + goto emulate_as_nop; + + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) + enabled = guest_cpu_cap_has(vcpu, X86_FEATURE_MWAIT); + else + enabled = vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT; + + if (!enabled) return kvm_handle_invalid_op(vcpu); +emulate_as_nop: pr_warn_once("%s instruction emulated as NOP!\n", insn); return kvm_emulate_as_nop(vcpu); } @@ -2133,86 +2249,57 @@ int kvm_emulate_mwait(struct kvm_vcpu *vcpu) { return kvm_emulate_monitor_mwait(vcpu, "MWAIT"); } -EXPORT_SYMBOL_GPL(kvm_emulate_mwait); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_mwait); int kvm_emulate_monitor(struct kvm_vcpu *vcpu) { return kvm_emulate_monitor_mwait(vcpu, "MONITOR"); } -EXPORT_SYMBOL_GPL(kvm_emulate_monitor); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_monitor); static inline bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu) { xfer_to_guest_mode_prepare(); - return vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) || - xfer_to_guest_mode_work_pending(); -} -/* - * The fast path for frequent and performance sensitive wrmsr emulation, - * i.e. the sending of IPI, sending IPI early in the VM-Exit flow reduces - * the latency of virtual IPI by avoiding the expensive bits of transitioning - * from guest to host, e.g. reacquiring KVM's SRCU lock. In contrast to the - * other cases which must be called after interrupts are enabled on the host. - */ -static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data) -{ - if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(vcpu->arch.apic)) - return 1; - - if (((data & APIC_SHORT_MASK) == APIC_DEST_NOSHORT) && - ((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) && - ((data & APIC_MODE_MASK) == APIC_DM_FIXED) && - ((u32)(data >> 32) != X2APIC_BROADCAST)) - return kvm_x2apic_icr_write(vcpu->arch.apic, data); - - return 1; + return READ_ONCE(vcpu->mode) == EXITING_GUEST_MODE || + kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending(); } -static int handle_fastpath_set_tscdeadline(struct kvm_vcpu *vcpu, u64 data) +static fastpath_t __handle_fastpath_wrmsr(struct kvm_vcpu *vcpu, u32 msr, u64 data) { - if (!kvm_can_use_hv_timer(vcpu)) - return 1; - - kvm_set_lapic_tscdeadline_msr(vcpu, data); - return 0; -} - -fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) -{ - u32 msr = kvm_rcx_read(vcpu); - u64 data; - fastpath_t ret = EXIT_FASTPATH_NONE; - - kvm_vcpu_srcu_read_lock(vcpu); - switch (msr) { case APIC_BASE_MSR + (APIC_ICR >> 4): - data = kvm_read_edx_eax(vcpu); - if (!handle_fastpath_set_x2apic_icr_irqoff(vcpu, data)) { - kvm_skip_emulated_instruction(vcpu); - ret = EXIT_FASTPATH_EXIT_HANDLED; - } + if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(vcpu->arch.apic) || + kvm_x2apic_icr_write_fast(vcpu->arch.apic, data)) + return EXIT_FASTPATH_NONE; break; case MSR_IA32_TSC_DEADLINE: - data = kvm_read_edx_eax(vcpu); - if (!handle_fastpath_set_tscdeadline(vcpu, data)) { - kvm_skip_emulated_instruction(vcpu); - ret = EXIT_FASTPATH_REENTER_GUEST; - } + kvm_set_lapic_tscdeadline_msr(vcpu, data); break; default: - break; + return EXIT_FASTPATH_NONE; } - if (ret != EXIT_FASTPATH_NONE) - trace_kvm_msr_write(msr, data); + trace_kvm_msr_write(msr, data); - kvm_vcpu_srcu_read_unlock(vcpu); + if (!kvm_skip_emulated_instruction(vcpu)) + return EXIT_FASTPATH_EXIT_USERSPACE; - return ret; + return EXIT_FASTPATH_REENTER_GUEST; +} + +fastpath_t handle_fastpath_wrmsr(struct kvm_vcpu *vcpu) +{ + return __handle_fastpath_wrmsr(vcpu, kvm_rcx_read(vcpu), + kvm_read_edx_eax(vcpu)); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(handle_fastpath_wrmsr); + +fastpath_t handle_fastpath_wrmsr_imm(struct kvm_vcpu *vcpu, u32 msr, int reg) +{ + return __handle_fastpath_wrmsr(vcpu, msr, kvm_register_read(vcpu, reg)); } -EXPORT_SYMBOL_GPL(handle_fastpath_set_msr_irqoff); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(handle_fastpath_wrmsr_imm); /* * Adapt set_msr() to msr_io()'s calling convention @@ -2229,16 +2316,13 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) /* * Disallow writes to immutable feature MSRs after KVM_RUN. KVM does * not support modifying the guest vCPU model on the fly, e.g. changing - * the nVMX capabilities while L2 is running is nonsensical. Ignore + * the nVMX capabilities while L2 is running is nonsensical. Allow * writes of the same value, e.g. to allow userspace to blindly stuff * all MSRs when emulating RESET. */ - if (kvm_vcpu_has_run(vcpu) && kvm_is_immutable_feature_msr(index)) { - if (do_get_msr(vcpu, index, &val) || *data != val) - return -EINVAL; - - return 0; - } + if (kvm_vcpu_has_run(vcpu) && kvm_is_immutable_feature_msr(index) && + (do_get_msr(vcpu, index, &val) || *data != val)) + return -EINVAL; return kvm_set_msr_ignored_check(vcpu, index, *data, true); } @@ -2332,14 +2416,9 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_o if (kvm_write_guest(kvm, wall_clock, &version, sizeof(version))) return; - /* - * The guest calculates current wall clock time by adding - * system time (updated by kvm_guest_time_update below) to the - * wall clock specified here. We do the reverse here. - */ - wall_nsec = ktime_get_real_ns() - get_kvmclock_ns(kvm); + wall_nsec = kvm_get_wall_clock_epoch(kvm); - wc.nsec = do_div(wall_nsec, 1000000000); + wc.nsec = do_div(wall_nsec, NSEC_PER_SEC); wc.sec = (u32)wall_nsec; /* overflow in 2106 guest time */ wc.version = version; @@ -2510,32 +2589,35 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) } #ifdef CONFIG_X86_64 -static inline int gtod_is_based_on_tsc(int mode) +static inline bool gtod_is_based_on_tsc(int mode) { return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK; } #endif -static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) +static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool new_generation) { #ifdef CONFIG_X86_64 - bool vcpus_matched; struct kvm_arch *ka = &vcpu->kvm->arch; struct pvclock_gtod_data *gtod = &pvclock_gtod_data; - vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == - atomic_read(&vcpu->kvm->online_vcpus)); + /* + * To use the masterclock, the host clocksource must be based on TSC + * and all vCPUs must have matching TSCs. Note, the count for matching + * vCPUs doesn't include the reference vCPU, hence "+1". + */ + bool use_master_clock = (ka->nr_vcpus_matched_tsc + 1 == + atomic_read(&vcpu->kvm->online_vcpus)) && + gtod_is_based_on_tsc(gtod->clock.vclock_mode); /* - * Once the masterclock is enabled, always perform request in - * order to update it. - * - * In order to enable masterclock, the host clocksource must be TSC - * and the vcpus need to have matched TSCs. When that happens, - * perform request to enable masterclock. + * Request a masterclock update if the masterclock needs to be toggled + * on/off, or when starting a new generation and the masterclock is + * enabled (compute_guest_tsc() requires the masterclock snapshot to be + * taken _after_ the new generation is created). */ - if (ka->use_master_clock || - (gtod_is_based_on_tsc(gtod->clock.vclock_mode) && vcpus_matched)) + if ((ka->use_master_clock && new_generation) || + (ka->use_master_clock != use_master_clock)) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc, @@ -2583,7 +2665,7 @@ u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) return vcpu->arch.l1_tsc_offset + kvm_scale_tsc(host_tsc, vcpu->arch.l1_tsc_scaling_ratio); } -EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_read_l1_tsc); u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier) { @@ -2598,7 +2680,7 @@ u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier) nested_offset += l2_offset; return nested_offset; } -EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_offset); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_calc_nested_tsc_offset); u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier) { @@ -2608,10 +2690,13 @@ u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier) return l1_multiplier; } -EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_multiplier); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_calc_nested_tsc_multiplier); static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 l1_offset) { + if (vcpu->arch.guest_tsc_protected) + return; + trace_kvm_write_tsc_offset(vcpu->vcpu_id, vcpu->arch.l1_tsc_offset, l1_offset); @@ -2626,12 +2711,12 @@ static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 l1_offset) if (is_guest_mode(vcpu)) vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset( l1_offset, - static_call(kvm_x86_get_l2_tsc_offset)(vcpu), - static_call(kvm_x86_get_l2_tsc_multiplier)(vcpu)); + kvm_x86_call(get_l2_tsc_offset)(vcpu), + kvm_x86_call(get_l2_tsc_multiplier)(vcpu)); else vcpu->arch.tsc_offset = l1_offset; - static_call(kvm_x86_write_tsc_offset)(vcpu, vcpu->arch.tsc_offset); + kvm_x86_call(write_tsc_offset)(vcpu); } static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier) @@ -2642,13 +2727,12 @@ static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multipli if (is_guest_mode(vcpu)) vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier( l1_multiplier, - static_call(kvm_x86_get_l2_tsc_multiplier)(vcpu)); + kvm_x86_call(get_l2_tsc_multiplier)(vcpu)); else vcpu->arch.tsc_scaling_ratio = l1_multiplier; if (kvm_caps.has_tsc_control) - static_call(kvm_x86_write_tsc_multiplier)( - vcpu, vcpu->arch.tsc_scaling_ratio); + kvm_x86_call(write_tsc_multiplier)(vcpu); } static inline bool kvm_check_tsc_unstable(void) @@ -2670,12 +2754,18 @@ static inline bool kvm_check_tsc_unstable(void) * participates in. */ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc, - u64 ns, bool matched) + u64 ns, bool matched, bool user_set_tsc) { struct kvm *kvm = vcpu->kvm; lockdep_assert_held(&kvm->arch.tsc_write_lock); + if (vcpu->arch.guest_tsc_protected) + return; + + if (user_set_tsc) + vcpu->kvm->arch.user_set_tsc = true; + /* * We also track th most recent recorded KHZ, write and time to * allow the matching interval to be extended at each write. @@ -2713,11 +2803,12 @@ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc, vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec; vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write; - kvm_track_tsc_matching(vcpu); + kvm_track_tsc_matching(vcpu, !matched); } -static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) +static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value) { + u64 data = user_value ? *user_value : 0; struct kvm *kvm = vcpu->kvm; u64 offset, ns, elapsed; unsigned long flags; @@ -2732,25 +2823,35 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) if (vcpu->arch.virtual_tsc_khz) { if (data == 0) { /* - * detection of vcpu initialization -- need to sync - * with other vCPUs. This particularly helps to keep - * kvm_clock stable after CPU hotplug + * Force synchronization when creating a vCPU, or when + * userspace explicitly writes a zero value. */ synchronizing = true; - } else { + } else if (kvm->arch.user_set_tsc) { u64 tsc_exp = kvm->arch.last_tsc_write + nsec_to_cycles(vcpu, elapsed); u64 tsc_hz = vcpu->arch.virtual_tsc_khz * 1000LL; /* - * Special case: TSC write with a small delta (1 second) - * of virtual cycle time against real time is - * interpreted as an attempt to synchronize the CPU. + * Here lies UAPI baggage: when a user-initiated TSC write has + * a small delta (1 second) of virtual cycle time against the + * previously set vCPU, we assume that they were intended to be + * in sync and the delta was only due to the racy nature of the + * legacy API. + * + * This trick falls down when restoring a guest which genuinely + * has been running for less time than the 1 second of imprecision + * which we allow for in the legacy API. In this case, the first + * value written by userspace (on any vCPU) should not be subject + * to this 'correction' to make it sync up with values that only + * come from the kernel's default vCPU creation. Make the 1-second + * slop hack only trigger if the user_set_tsc flag is already set. */ synchronizing = data < tsc_exp + tsc_hz && data + tsc_hz > tsc_exp; } } + /* * For a reliable TSC, we can match TSC offsets, and for an unstable * TSC, we add elapsed time in this computation. We could let the @@ -2769,7 +2870,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) matched = true; } - __kvm_synchronize_tsc(vcpu, offset, data, ns, matched); + __kvm_synchronize_tsc(vcpu, offset, data, ns, matched, !!user_value); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); } @@ -2846,7 +2947,11 @@ static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp, return v * clock->mult; } -static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp) +/* + * As with get_kvmclock_base_ns(), this counts from boot time, at the + * frequency of CLOCK_MONOTONIC_RAW (hence adding gtos->offs_boot). + */ +static int do_kvmclock_base(s64 *t, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; @@ -2865,6 +2970,29 @@ static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp) return mode; } +/* + * This calculates CLOCK_MONOTONIC at the time of the TSC snapshot, with + * no boot time offset. + */ +static int do_monotonic(s64 *t, u64 *tsc_timestamp) +{ + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + unsigned long seq; + int mode; + u64 ns; + + do { + seq = read_seqcount_begin(>od->seq); + ns = gtod->clock.base_cycles; + ns += vgettsc(>od->clock, tsc_timestamp, &mode); + ns >>= gtod->clock.shift; + ns += ktime_to_ns(gtod->clock.offset); + } while (unlikely(read_seqcount_retry(>od->seq, seq))); + *t = ns; + + return mode; +} + static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; @@ -2886,18 +3014,42 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp) return mode; } -/* returns true if host is using TSC based clocksource */ +/* + * Calculates the kvmclock_base_ns (CLOCK_MONOTONIC_RAW + boot time) and + * reports the TSC value from which it do so. Returns true if host is + * using TSC based clocksource. + */ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) { /* checked again under seqlock below */ if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; - return gtod_is_based_on_tsc(do_monotonic_raw(kernel_ns, - tsc_timestamp)); + return gtod_is_based_on_tsc(do_kvmclock_base(kernel_ns, + tsc_timestamp)); +} + +/* + * Calculates CLOCK_MONOTONIC and reports the TSC value from which it did + * so. Returns true if host is using TSC based clocksource. + */ +bool kvm_get_monotonic_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) +{ + /* checked again under seqlock below */ + if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) + return false; + + return gtod_is_based_on_tsc(do_monotonic(kernel_ns, + tsc_timestamp)); } -/* returns true if host is using TSC based clocksource */ +/* + * Calculates CLOCK_REALTIME and reports the TSC value from which it did + * so. Returns true if host is using TSC based clocksource. + * + * DO NOT USE this for anything related to migration. You want CLOCK_TAI + * for that. + */ static bool kvm_get_walltime_and_clockread(struct timespec64 *ts, u64 *tsc_timestamp) { @@ -3096,14 +3248,17 @@ u64 get_kvmclock_ns(struct kvm *kvm) return data.clock; } -static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, +static void kvm_setup_guest_pvclock(struct pvclock_vcpu_time_info *ref_hv_clock, + struct kvm_vcpu *vcpu, struct gfn_to_pfn_cache *gpc, unsigned int offset) { - struct kvm_vcpu_arch *vcpu = &v->arch; struct pvclock_vcpu_time_info *guest_hv_clock; + struct pvclock_vcpu_time_info hv_clock; unsigned long flags; + memcpy(&hv_clock, ref_hv_clock, sizeof(hv_clock)); + read_lock_irqsave(&gpc->lock, flags); while (!kvm_gpc_check(gpc, offset + sizeof(*guest_hv_clock))) { read_unlock_irqrestore(&gpc->lock, flags); @@ -3123,37 +3278,33 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, * it is consistent. */ - guest_hv_clock->version = vcpu->hv_clock.version = (guest_hv_clock->version + 1) | 1; + guest_hv_clock->version = hv_clock.version = (guest_hv_clock->version + 1) | 1; smp_wmb(); /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */ - vcpu->hv_clock.flags |= (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED); + hv_clock.flags |= (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED); - if (vcpu->pvclock_set_guest_stopped_request) { - vcpu->hv_clock.flags |= PVCLOCK_GUEST_STOPPED; - vcpu->pvclock_set_guest_stopped_request = false; - } + memcpy(guest_hv_clock, &hv_clock, sizeof(*guest_hv_clock)); - memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock)); smp_wmb(); - guest_hv_clock->version = ++vcpu->hv_clock.version; + guest_hv_clock->version = ++hv_clock.version; - mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT); + kvm_gpc_mark_dirty_in_slot(gpc); read_unlock_irqrestore(&gpc->lock, flags); - trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock); + trace_kvm_pvclock_update(vcpu->vcpu_id, &hv_clock); } -static int kvm_guest_time_update(struct kvm_vcpu *v) +int kvm_guest_time_update(struct kvm_vcpu *v) { + struct pvclock_vcpu_time_info hv_clock = {}; unsigned long flags, tgt_tsc_khz; unsigned seq; struct kvm_vcpu_arch *vcpu = &v->arch; struct kvm_arch *ka = &v->kvm->arch; s64 kernel_ns; u64 tsc_timestamp, host_tsc; - u8 pvclock_flags; bool use_master_clock; kernel_ns = 0; @@ -3209,64 +3360,158 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) /* With all the info we got, fill in the values */ - if (kvm_caps.has_tsc_control) + if (kvm_caps.has_tsc_control) { tgt_tsc_khz = kvm_scale_tsc(tgt_tsc_khz, v->arch.l1_tsc_scaling_ratio); + tgt_tsc_khz = tgt_tsc_khz ? : 1; + } if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) { kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL, - &vcpu->hv_clock.tsc_shift, - &vcpu->hv_clock.tsc_to_system_mul); + &vcpu->pvclock_tsc_shift, + &vcpu->pvclock_tsc_mul); vcpu->hw_tsc_khz = tgt_tsc_khz; - kvm_xen_update_tsc_info(v); } - vcpu->hv_clock.tsc_timestamp = tsc_timestamp; - vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset; + hv_clock.tsc_shift = vcpu->pvclock_tsc_shift; + hv_clock.tsc_to_system_mul = vcpu->pvclock_tsc_mul; + hv_clock.tsc_timestamp = tsc_timestamp; + hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset; vcpu->last_guest_tsc = tsc_timestamp; /* If the host uses TSC clocksource, then it is stable */ - pvclock_flags = 0; + hv_clock.flags = 0; if (use_master_clock) - pvclock_flags |= PVCLOCK_TSC_STABLE_BIT; + hv_clock.flags |= PVCLOCK_TSC_STABLE_BIT; - vcpu->hv_clock.flags = pvclock_flags; + if (vcpu->pv_time.active) { + /* + * GUEST_STOPPED is only supported by kvmclock, and KVM's + * historic behavior is to only process the request if kvmclock + * is active/enabled. + */ + if (vcpu->pvclock_set_guest_stopped_request) { + hv_clock.flags |= PVCLOCK_GUEST_STOPPED; + vcpu->pvclock_set_guest_stopped_request = false; + } + kvm_setup_guest_pvclock(&hv_clock, v, &vcpu->pv_time, 0); + + hv_clock.flags &= ~PVCLOCK_GUEST_STOPPED; + } + + kvm_hv_setup_tsc_page(v->kvm, &hv_clock); + +#ifdef CONFIG_KVM_XEN + /* + * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless + * explicitly told to use TSC as its clocksource Xen will not set this bit. + * This default behaviour led to bugs in some guest kernels which cause + * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags. + * + * Note! Clear TSC_STABLE only for Xen clocks, i.e. the order matters! + */ + if (ka->xen.hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE) + hv_clock.flags &= ~PVCLOCK_TSC_STABLE_BIT; - if (vcpu->pv_time.active) - kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0); if (vcpu->xen.vcpu_info_cache.active) - kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache, + kvm_setup_guest_pvclock(&hv_clock, v, &vcpu->xen.vcpu_info_cache, offsetof(struct compat_vcpu_info, time)); if (vcpu->xen.vcpu_time_info_cache.active) - kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0); - kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); + kvm_setup_guest_pvclock(&hv_clock, v, &vcpu->xen.vcpu_time_info_cache, 0); +#endif return 0; } /* + * The pvclock_wall_clock ABI tells the guest the wall clock time at + * which it started (i.e. its epoch, when its kvmclock was zero). + * + * In fact those clocks are subtly different; wall clock frequency is + * adjusted by NTP and has leap seconds, while the kvmclock is a + * simple function of the TSC without any such adjustment. + * + * Perhaps the ABI should have exposed CLOCK_TAI and a ratio between + * that and kvmclock, but even that would be subject to change over + * time. + * + * Attempt to calculate the epoch at a given moment using the *same* + * TSC reading via kvm_get_walltime_and_clockread() to obtain both + * wallclock and kvmclock times, and subtracting one from the other. + * + * Fall back to using their values at slightly different moments by + * calling ktime_get_real_ns() and get_kvmclock_ns() separately. + */ +uint64_t kvm_get_wall_clock_epoch(struct kvm *kvm) +{ +#ifdef CONFIG_X86_64 + struct pvclock_vcpu_time_info hv_clock; + struct kvm_arch *ka = &kvm->arch; + unsigned long seq, local_tsc_khz; + struct timespec64 ts; + uint64_t host_tsc; + + do { + seq = read_seqcount_begin(&ka->pvclock_sc); + + local_tsc_khz = 0; + if (!ka->use_master_clock) + break; + + /* + * The TSC read and the call to get_cpu_tsc_khz() must happen + * on the same CPU. + */ + get_cpu(); + + local_tsc_khz = get_cpu_tsc_khz(); + + if (local_tsc_khz && + !kvm_get_walltime_and_clockread(&ts, &host_tsc)) + local_tsc_khz = 0; /* Fall back to old method */ + + put_cpu(); + + /* + * These values must be snapshotted within the seqcount loop. + * After that, it's just mathematics which can happen on any + * CPU at any time. + */ + hv_clock.tsc_timestamp = ka->master_cycle_now; + hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; + + } while (read_seqcount_retry(&ka->pvclock_sc, seq)); + + /* + * If the conditions were right, and obtaining the wallclock+TSC was + * successful, calculate the KVM clock at the corresponding time and + * subtract one from the other to get the guest's epoch in nanoseconds + * since 1970-01-01. + */ + if (local_tsc_khz) { + kvm_get_time_scale(NSEC_PER_SEC, local_tsc_khz * NSEC_PER_USEC, + &hv_clock.tsc_shift, + &hv_clock.tsc_to_system_mul); + return ts.tv_nsec + NSEC_PER_SEC * ts.tv_sec - + __pvclock_read_cycles(&hv_clock, host_tsc); + } +#endif + return ktime_get_real_ns() - get_kvmclock_ns(kvm); +} + +/* * kvmclock updates which are isolated to a given vcpu, such as * vcpu->cpu migration, should not allow system_timestamp from - * the rest of the vcpus to remain static. Otherwise ntp frequency - * correction applies to one vcpu's system_timestamp but not - * the others. + * the rest of the vcpus to remain static. * * So in those cases, request a kvmclock update for all vcpus. - * We need to rate-limit these requests though, as they can - * considerably slow guests that have a large number of vcpus. - * The time for a remote vcpu to update its kvmclock is bound - * by the delay we use to rate-limit the updates. + * The worst case for a remote vcpu to update its kvmclock + * is then bounded by maximum nohz sleep latency. */ - -#define KVMCLOCK_UPDATE_DELAY msecs_to_jiffies(100) - -static void kvmclock_update_fn(struct work_struct *work) +static void kvm_gen_kvmclock_update(struct kvm_vcpu *v) { unsigned long i; - struct delayed_work *dwork = to_delayed_work(work); - struct kvm_arch *ka = container_of(dwork, struct kvm_arch, - kvmclock_update_work); - struct kvm *kvm = container_of(ka, struct kvm, arch); struct kvm_vcpu *vcpu; + struct kvm *kvm = v->kvm; kvm_for_each_vcpu(i, vcpu, kvm) { kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -3274,32 +3519,6 @@ static void kvmclock_update_fn(struct work_struct *work) } } -static void kvm_gen_kvmclock_update(struct kvm_vcpu *v) -{ - struct kvm *kvm = v->kvm; - - kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); - schedule_delayed_work(&kvm->arch.kvmclock_update_work, - KVMCLOCK_UPDATE_DELAY); -} - -#define KVMCLOCK_SYNC_PERIOD (300 * HZ) - -static void kvmclock_sync_fn(struct work_struct *work) -{ - struct delayed_work *dwork = to_delayed_work(work); - struct kvm_arch *ka = container_of(dwork, struct kvm_arch, - kvmclock_sync_work); - struct kvm *kvm = container_of(ka, struct kvm, arch); - - if (!kvmclock_periodic_sync) - return; - - schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0); - schedule_delayed_work(&kvm->arch.kvmclock_sync_work, - KVMCLOCK_SYNC_PERIOD); -} - /* These helpers are safe iff @msr is known to be an MCx bank MSR. */ static bool is_mci_control_msr(u32 msr) { @@ -3316,7 +3535,7 @@ static bool is_mci_status_msr(u32 msr) static bool can_set_mci_status(struct kvm_vcpu *vcpu) { /* McStatusWrEn enabled? */ - if (guest_cpuid_is_amd_or_hygon(vcpu)) + if (guest_cpuid_is_amd_compatible(vcpu)) return !!(vcpu->arch.msr_hwcr & BIT_ULL(18)); return false; @@ -3394,13 +3613,6 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 0; } -static inline bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu) -{ - u64 mask = KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT; - - return (vcpu->arch.apf.msr_en_val & mask) == mask; -} - static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) { gpa_t gpa = data & ~0x3f; @@ -3432,7 +3644,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) sizeof(u64))) return 1; - vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS); + vcpu->arch.apf.send_always = (data & KVM_ASYNC_PF_SEND_ALWAYS); vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT; kvm_async_pf_wakeup_all(vcpu); @@ -3465,7 +3677,7 @@ static void kvmclock_reset(struct kvm_vcpu *vcpu) static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; - static_call(kvm_x86_flush_tlb_all)(vcpu); + kvm_x86_call(flush_tlb_all)(vcpu); /* Flushing all ASIDs flushes the current ASID... */ kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); @@ -3486,7 +3698,7 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) kvm_mmu_sync_prev_roots(vcpu); } - static_call(kvm_x86_flush_tlb_guest)(vcpu); + kvm_x86_call(flush_tlb_guest)(vcpu); /* * Flushing all "guest" TLB is always a superset of Hyper-V's fine @@ -3499,7 +3711,7 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; - static_call(kvm_x86_flush_tlb_current)(vcpu); + kvm_x86_call(flush_tlb_current)(vcpu); } /* @@ -3516,7 +3728,7 @@ void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu)) kvm_vcpu_flush_tlb_guest(vcpu); } -EXPORT_SYMBOL_GPL(kvm_service_local_tlb_flush_requests); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_service_local_tlb_flush_requests); static void record_steal_time(struct kvm_vcpu *vcpu) { @@ -3616,16 +3828,64 @@ static void record_steal_time(struct kvm_vcpu *vcpu) mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } -static bool kvm_is_msr_to_save(u32 msr_index) +/* + * Returns true if the MSR in question is managed via XSTATE, i.e. is context + * switched with the rest of guest FPU state. + * + * Note, S_CET is _not_ saved/restored via XSAVES/XRSTORS. + */ +static bool is_xstate_managed_msr(struct kvm_vcpu *vcpu, u32 msr) { - unsigned int i; + if (!vcpu) + return false; - for (i = 0; i < num_msrs_to_save; i++) { - if (msrs_to_save[i] == msr_index) - return true; + switch (msr) { + case MSR_IA32_U_CET: + return guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) || + guest_cpu_cap_has(vcpu, X86_FEATURE_IBT); + case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP: + return guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK); + default: + return false; } +} - return false; +/* + * Lock (and if necessary, re-load) the guest FPU, i.e. XSTATE, and access an + * MSR that is managed via XSTATE. Note, the caller is responsible for doing + * the initial FPU load, this helper only ensures that guest state is resident + * in hardware (the kernel can load its FPU state in IRQ context). + * + * Note, loading guest values for U_CET and PL[0-3]_SSP while executing in the + * kernel is safe, as U_CET is specific to userspace, and PL[0-3]_SSP are only + * consumed when transitioning to lower privilege levels, i.e. are effectively + * only consumed by userspace as well. + */ +static __always_inline void kvm_access_xstate_msr(struct kvm_vcpu *vcpu, + struct msr_data *msr_info, + int access) +{ + BUILD_BUG_ON(access != MSR_TYPE_R && access != MSR_TYPE_W); + + KVM_BUG_ON(!is_xstate_managed_msr(vcpu, msr_info->index), vcpu->kvm); + KVM_BUG_ON(!vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm); + + kvm_fpu_get(); + if (access == MSR_TYPE_R) + rdmsrq(msr_info->index, msr_info->data); + else + wrmsrq(msr_info->index, msr_info->data); + kvm_fpu_put(); +} + +static void kvm_set_xstate_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + kvm_access_xstate_msr(vcpu, msr_info, MSR_TYPE_W); +} + +static void kvm_get_xstate_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + kvm_access_xstate_msr(vcpu, msr_info, MSR_TYPE_R); } int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -3633,7 +3893,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) u32 msr = msr_info->index; u64 data = msr_info->data; - if (msr && msr == vcpu->kvm->arch.xen_hvm_config.msr) + /* + * Do not allow host-initiated writes to trigger the Xen hypercall + * page setup; it could incur locking paths which are not expected + * if userspace sets the MSR in an unusual location. + */ + if (kvm_xen_is_hypercall_page_msr(vcpu->kvm, msr) && + !msr_info->host_initiated) return kvm_xen_write_hypercall_page(vcpu, data); switch (msr) { @@ -3643,6 +3909,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_PATCH_LOADER: case MSR_AMD64_BU_CFG2: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: break; @@ -3651,13 +3918,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.microcode_version = data; break; case MSR_IA32_ARCH_CAPABILITIES: - if (!msr_info->host_initiated) - return 1; + if (!msr_info->host_initiated || + !guest_cpu_cap_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) + return KVM_MSR_RET_UNSUPPORTED; vcpu->arch.arch_capabilities = data; break; case MSR_IA32_PERF_CAPABILITIES: - if (!msr_info->host_initiated) - return 1; + if (!msr_info->host_initiated || + !guest_cpu_cap_has(vcpu, X86_FEATURE_PDCM)) + return KVM_MSR_RET_UNSUPPORTED; + if (data & ~kvm_caps.supported_perf_cap) return 1; @@ -3672,20 +3942,39 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.perf_capabilities = data; kvm_pmu_refresh(vcpu); break; - case MSR_IA32_PRED_CMD: - if (!msr_info->host_initiated && !guest_has_pred_cmd_msr(vcpu)) - return 1; + case MSR_IA32_PRED_CMD: { + u64 reserved_bits = ~(PRED_CMD_IBPB | PRED_CMD_SBPB); - if (!boot_cpu_has(X86_FEATURE_IBPB) || (data & ~PRED_CMD_IBPB)) + if (!msr_info->host_initiated) { + if ((!guest_has_pred_cmd_msr(vcpu))) + return 1; + + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_IBPB)) + reserved_bits |= PRED_CMD_IBPB; + + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SBPB)) + reserved_bits |= PRED_CMD_SBPB; + } + + if (!boot_cpu_has(X86_FEATURE_IBPB)) + reserved_bits |= PRED_CMD_IBPB; + + if (!boot_cpu_has(X86_FEATURE_SBPB)) + reserved_bits |= PRED_CMD_SBPB; + + if (data & reserved_bits) return 1; + if (!data) break; - wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + wrmsrq(MSR_IA32_PRED_CMD, data); break; + } case MSR_IA32_FLUSH_CMD: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)) return 1; if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D) || (data & ~L1D_FLUSH)) @@ -3693,7 +3982,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!data) break; - wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH); + wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH); break; case MSR_EFER: return set_efer(vcpu, msr_info); @@ -3702,13 +3991,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) data &= ~(u64)0x100; /* ignore ignne emulation enable */ data &= ~(u64)0x8; /* ignore TLB cache disable */ - /* Handle McStatusWrEn */ - if (data == BIT_ULL(18)) { - vcpu->arch.msr_hwcr = data; - } else if (data != 0) { + /* + * Allow McStatusWrEn and TscFreqSel. (Linux guests from v3.2 + * through at least v6.6 whine if TscFreqSel is clear, + * depending on F/M/S. + */ + if (data & ~(BIT_ULL(18) | BIT_ULL(24))) { kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } + vcpu->arch.msr_hwcr = data; break; case MSR_FAM10H_MMIO_CONF_BASE: if (data != 0) { @@ -3726,14 +4018,14 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_MTRRdefType: return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: - return kvm_set_apic_base(vcpu, msr_info); + return kvm_apic_set_base(vcpu, data, msr_info->host_initiated); case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_write(vcpu, msr, data); case MSR_IA32_TSC_DEADLINE: kvm_set_lapic_tscdeadline_msr(vcpu, data); break; case MSR_IA32_TSC_ADJUST: - if (guest_cpuid_has(vcpu, X86_FEATURE_TSC_ADJUST)) { + if (guest_cpu_cap_has(vcpu, X86_FEATURE_TSC_ADJUST)) { if (!msr_info->host_initiated) { s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr; adjust_tsc_offset_guest(vcpu, adj); @@ -3760,10 +4052,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT) && ((old_val ^ data) & MSR_IA32_MISC_ENABLE_MWAIT)) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_XMM3)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_XMM3)) return 1; vcpu->arch.ia32_misc_enable_msr = data; - kvm_update_cpuid_runtime(vcpu); + vcpu->arch.cpuid_dynamic_bits_dirty = true; } else { vcpu->arch.ia32_misc_enable_msr = data; } @@ -3779,26 +4071,23 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_TSC: if (msr_info->host_initiated) { - kvm_synchronize_tsc(vcpu, data); - } else { + kvm_synchronize_tsc(vcpu, &data); + } else if (!vcpu->arch.guest_tsc_protected) { u64 adj = kvm_compute_l1_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset; adjust_tsc_offset_guest(vcpu, adj); vcpu->arch.ia32_tsc_adjust_msr += adj; } break; case MSR_IA32_XSS: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) - return 1; - /* - * KVM supports exposing PT to the guest, but does not support - * IA32_XSS[bit 8]. Guests have to use RDMSR/WRMSR rather than - * XSAVES/XRSTORS to save/restore PT MSRs. - */ - if (data & ~kvm_caps.supported_xss) + if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) + return KVM_MSR_RET_UNSUPPORTED; + + if (data & ~vcpu->arch.guest_supported_xss) return 1; + if (vcpu->arch.ia32_xss == data) + break; vcpu->arch.ia32_xss = data; - kvm_update_cpuid_runtime(vcpu); + vcpu->arch.cpuid_dynamic_bits_dirty = true; break; case MSR_SMI_COUNT: if (!msr_info->host_initiated) @@ -3849,7 +4138,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return 1; if (data & 0x1) { - vcpu->arch.apf.pageready_pending = false; + /* + * Pairs with the smp_mb__after_atomic() in + * kvm_arch_async_page_present_queued(). + */ + smp_store_mb(vcpu->arch.apf.pageready_pending, false); + kvm_check_async_pf_completion(vcpu); } break; @@ -3916,6 +4210,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * the need to ignore the workaround. */ break; +#ifdef CONFIG_KVM_HYPERV case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: case HV_X64_MSR_SYNDBG_OPTIONS: @@ -3928,6 +4223,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_set_msr_common(vcpu, msr, data, msr_info->host_initiated); +#endif case MSR_IA32_BBL_CR_CTL3: /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. @@ -3935,19 +4231,17 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_AMD64_OSVW_ID_LENGTH: - if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; vcpu->arch.osvw.length = data; break; case MSR_AMD64_OSVW_STATUS: - if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; vcpu->arch.osvw.status = data; break; case MSR_PLATFORM_INFO: - if (!msr_info->host_initiated || - (!(data & MSR_PLATFORM_INFO_CPUID_FAULT) && - cpuid_fault_enabled(vcpu))) + if (!msr_info->host_initiated) return 1; vcpu->arch.msr_platform_info = data; break; @@ -3961,7 +4255,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) #ifdef CONFIG_X86_64 case MSR_IA32_XFD: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; if (data & ~kvm_guest_supported_xfd(vcpu)) @@ -3971,7 +4265,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_XFD_ERR: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; if (data & ~kvm_guest_supported_xfd(vcpu)) @@ -3980,23 +4274,19 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.guest_fpu.xfd_err = data; break; #endif + case MSR_IA32_U_CET: + case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP: + kvm_set_xstate_msr(vcpu, msr_info); + break; default: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); - /* - * Userspace is allowed to write '0' to MSRs that KVM reports - * as to-be-saved, even if an MSRs isn't fully supported. - */ - if (msr_info->host_initiated && !data && - kvm_is_msr_to_save(msr)) - break; - - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } return 0; } -EXPORT_SYMBOL_GPL(kvm_set_msr_common); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_msr_common); static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) { @@ -4067,6 +4357,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_BU_CFG2: case MSR_IA32_PERF_CTL: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: /* * Intel Sandy Bridge CPUs must support the RAPL (running average power @@ -4093,15 +4384,13 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) 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; + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) + return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->arch.arch_capabilities; break; case MSR_IA32_PERF_CAPABILITIES: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) - return 1; + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_PDCM)) + return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->arch.perf_capabilities; break; case MSR_IA32_POWER_CTL: @@ -4155,7 +4444,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 1 << 24; break; case MSR_IA32_APICBASE: - msr_info->data = kvm_get_apic_base(vcpu); + msr_info->data = vcpu->arch.apic_base; break; case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); @@ -4272,6 +4561,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ msr_info->data = 0x20000000; break; +#ifdef CONFIG_KVM_HYPERV case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: case HV_X64_MSR_SYNDBG_OPTIONS: @@ -4285,6 +4575,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_hv_get_msr_common(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); +#endif case MSR_IA32_BBL_CR_CTL3: /* This legacy MSR exists but isn't fully documented in current * silicon. It is however accessed by winxp in very narrow @@ -4299,12 +4590,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0xbe702111; break; case MSR_AMD64_OSVW_ID_LENGTH: - if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; msr_info->data = vcpu->arch.osvw.length; break; case MSR_AMD64_OSVW_STATUS: - if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; msr_info->data = vcpu->arch.osvw.status; break; @@ -4323,38 +4614,32 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) #ifdef CONFIG_X86_64 case MSR_IA32_XFD: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; msr_info->data = vcpu->arch.guest_fpu.fpstate->xfd; break; case MSR_IA32_XFD_ERR: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; msr_info->data = vcpu->arch.guest_fpu.xfd_err; break; #endif + case MSR_IA32_U_CET: + case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP: + kvm_get_xstate_msr(vcpu, msr_info); + break; default: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info); - /* - * Userspace is allowed to read MSRs that KVM reports as - * to-be-saved, even if an MSR isn't fully supported. - */ - if (msr_info->host_initiated && - kvm_is_msr_to_save(msr_info->index)) { - msr_info->data = 0; - break; - } - - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } return 0; } -EXPORT_SYMBOL_GPL(kvm_get_msr_common); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_msr_common); /* * Read or write a bunch of msrs. All parameters are kernel addresses. @@ -4366,11 +4651,25 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, int (*do_msr)(struct kvm_vcpu *vcpu, unsigned index, u64 *data)) { + bool fpu_loaded = false; int i; - for (i = 0; i < msrs->nmsrs; ++i) + for (i = 0; i < msrs->nmsrs; ++i) { + /* + * If userspace is accessing one or more XSTATE-managed MSRs, + * temporarily load the guest's FPU state so that the guest's + * MSR value(s) is resident in hardware and thus can be accessed + * via RDMSR/WRMSR. + */ + if (!fpu_loaded && is_xstate_managed_msr(vcpu, entries[i].index)) { + kvm_load_guest_fpu(vcpu); + fpu_loaded = true; + } if (do_msr(vcpu, entries[i].index, &entries[i].data)) break; + } + if (fpu_loaded) + kvm_put_guest_fpu(vcpu); return i; } @@ -4422,6 +4721,24 @@ static inline bool kvm_can_mwait_in_guest(void) boot_cpu_has(X86_FEATURE_ARAT); } +static u64 kvm_get_allowed_disable_exits(void) +{ + u64 r = KVM_X86_DISABLE_EXITS_PAUSE; + + if (boot_cpu_has(X86_FEATURE_APERFMPERF)) + r |= KVM_X86_DISABLE_EXITS_APERFMPERF; + + if (!mitigate_smt_rsb) { + r |= KVM_X86_DISABLE_EXITS_HLT | + KVM_X86_DISABLE_EXITS_CSTATE; + + if (kvm_can_mwait_in_guest()) + r |= KVM_X86_DISABLE_EXITS_MWAIT; + } + return r; +} + +#ifdef CONFIG_KVM_HYPERV static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 __user *cpuid_arg) { @@ -4442,6 +4759,17 @@ static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, return 0; } +#endif + +static bool kvm_is_vm_type_supported(unsigned long type) +{ + return type < 32 && (kvm_caps.supported_vm_types & BIT(type)); +} + +static inline u64 kvm_sync_valid_fields(struct kvm *kvm) +{ + return kvm && kvm->arch.has_protected_state ? 0 : KVM_SYNC_X86_VALID_FIELDS; +} int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { @@ -4455,22 +4783,27 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_EXT_CPUID: case KVM_CAP_EXT_EMUL_CPUID: case KVM_CAP_CLOCKSOURCE: +#ifdef CONFIG_KVM_IOAPIC case KVM_CAP_PIT: + case KVM_CAP_PIT2: + case KVM_CAP_PIT_STATE2: + case KVM_CAP_REINJECT_CONTROL: +#endif case KVM_CAP_NOP_IO_DELAY: case KVM_CAP_MP_STATE: case KVM_CAP_SYNC_MMU: case KVM_CAP_USER_NMI: - case KVM_CAP_REINJECT_CONTROL: case KVM_CAP_IRQ_INJECT_STATUS: case KVM_CAP_IOEVENTFD: case KVM_CAP_IOEVENTFD_NO_LENGTH: - case KVM_CAP_PIT2: - case KVM_CAP_PIT_STATE2: + case KVM_CAP_SET_IDENTITY_MAP_ADDR: case KVM_CAP_VCPU_EVENTS: +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: + case KVM_CAP_HYPERV_TIME: case KVM_CAP_HYPERV_SYNIC: case KVM_CAP_HYPERV_SYNIC2: case KVM_CAP_HYPERV_VP_INDEX: @@ -4480,6 +4813,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_CPUID: case KVM_CAP_HYPERV_ENFORCE_CPUID: case KVM_CAP_SYS_HYPERV_CPUID: +#endif case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: @@ -4488,8 +4822,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ASYNC_PF_INT: case KVM_CAP_GET_TSC_KHZ: case KVM_CAP_KVMCLOCK_CTRL: - case KVM_CAP_READONLY_MEM: - case KVM_CAP_HYPERV_TIME: case KVM_CAP_IOAPIC_POLARITY_IGNORED: case KVM_CAP_TSC_DEADLINE_TIMER: case KVM_CAP_DISABLE_QUIRKS: @@ -4520,8 +4852,17 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ENABLE_CAP: case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: case KVM_CAP_IRQFD_RESAMPLE: + case KVM_CAP_MEMORY_FAULT_INFO: + case KVM_CAP_X86_GUEST_MODE: + case KVM_CAP_ONE_REG: r = 1; break; + case KVM_CAP_PRE_FAULT_MEMORY: + r = tdp_enabled; + break; + case KVM_CAP_X86_APIC_BUS_CYCLES_NS: + r = APIC_BUS_CYCLE_NS_DEFAULT; + break; case KVM_CAP_EXIT_HYPERCALL: r = KVM_EXIT_HYPERCALL_VALID_MASK; break; @@ -4533,28 +4874,22 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | KVM_XEN_HVM_CONFIG_SHARED_INFO | KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL | - KVM_XEN_HVM_CONFIG_EVTCHN_SEND; + KVM_XEN_HVM_CONFIG_EVTCHN_SEND | + KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE | + KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA; if (sched_info_on()) r |= KVM_XEN_HVM_CONFIG_RUNSTATE | KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG; break; #endif case KVM_CAP_SYNC_REGS: - r = KVM_SYNC_X86_VALID_FIELDS; + r = kvm_sync_valid_fields(kvm); break; case KVM_CAP_ADJUST_CLOCK: r = KVM_CLOCK_VALID_FLAGS; break; case KVM_CAP_X86_DISABLE_EXITS: - r = KVM_X86_DISABLE_EXITS_PAUSE; - - if (!mitigate_smt_rsb) { - r |= KVM_X86_DISABLE_EXITS_HLT | - KVM_X86_DISABLE_EXITS_CSTATE; - - if (kvm_can_mwait_in_guest()) - r |= KVM_X86_DISABLE_EXITS_MWAIT; - } + r = kvm_get_allowed_disable_exits(); break; case KVM_CAP_X86_SMM: if (!IS_ENABLED(CONFIG_KVM_SMM)) @@ -4568,13 +4903,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) * fringe case that is not enabled except via specific settings * of the module parameters. */ - r = static_call(kvm_x86_has_emulated_msr)(kvm, MSR_IA32_SMBASE); + r = kvm_x86_call(has_emulated_msr)(kvm, MSR_IA32_SMBASE); break; case KVM_CAP_NR_VCPUS: r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; + if (kvm) + r = kvm->max_vcpus; break; case KVM_CAP_MAX_VCPU_ID: r = KVM_MAX_VCPU_IDS; @@ -4599,12 +4936,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = kvm_x86_ops.nested_ops->get_state ? kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0; break; +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: r = kvm_x86_ops.enable_l2_tlb_flush != NULL; break; case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: r = kvm_x86_ops.nested_ops->enable_evmcs != NULL; break; +#endif case KVM_CAP_SMALLER_MAXPHYADDR: r = (int) allow_smaller_maxphyaddr; break; @@ -4628,58 +4967,61 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = enable_pmu ? KVM_CAP_PMU_VALID_MASK : 0; break; case KVM_CAP_DISABLE_QUIRKS2: - r = KVM_X86_VALID_QUIRKS; + r = kvm_caps.supported_quirks; break; case KVM_CAP_X86_NOTIFY_VMEXIT: r = kvm_caps.has_notify_vmexit; break; + case KVM_CAP_VM_TYPES: + r = kvm_caps.supported_vm_types; + break; + case KVM_CAP_READONLY_MEM: + r = kvm ? kvm_arch_has_readonly_mem(kvm) : 1; + break; default: break; } return r; } -static inline void __user *kvm_get_attr_addr(struct kvm_device_attr *attr) -{ - void __user *uaddr = (void __user*)(unsigned long)attr->addr; - - if ((u64)(unsigned long)uaddr != attr->addr) - return ERR_PTR_USR(-EFAULT); - return uaddr; -} - -static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr) +static int __kvm_x86_dev_get_attr(struct kvm_device_attr *attr, u64 *val) { - u64 __user *uaddr = kvm_get_attr_addr(attr); - - if (attr->group) + if (attr->group) { + if (kvm_x86_ops.dev_get_attr) + return kvm_x86_call(dev_get_attr)(attr->group, attr->attr, val); return -ENXIO; - - if (IS_ERR(uaddr)) - return PTR_ERR(uaddr); + } switch (attr->attr) { case KVM_X86_XCOMP_GUEST_SUPP: - if (put_user(kvm_caps.supported_xcr0, uaddr)) - return -EFAULT; + *val = kvm_caps.supported_xcr0; return 0; default: return -ENXIO; - break; } } +static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr) +{ + u64 __user *uaddr = u64_to_user_ptr(attr->addr); + int r; + u64 val; + + r = __kvm_x86_dev_get_attr(attr, &val); + if (r < 0) + return r; + + if (put_user(val, uaddr)) + return -EFAULT; + + return 0; +} + static int kvm_x86_dev_has_attr(struct kvm_device_attr *attr) { - if (attr->group) - return -ENXIO; + u64 val; - switch (attr->attr) { - case KVM_X86_XCOMP_GUEST_SUPP: - return 0; - default: - return -ENXIO; - } + return __kvm_x86_dev_get_attr(attr, &val); } long kvm_arch_dev_ioctl(struct file *filp, @@ -4765,11 +5107,13 @@ long kvm_arch_dev_ioctl(struct file *filp, break; } case KVM_GET_MSRS: - r = msr_io(NULL, argp, do_get_msr_feature, 1); + r = msr_io(NULL, argp, do_get_feature_msr, 1); break; +#ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp); break; +#endif case KVM_GET_DEVICE_ATTR: { struct kvm_device_attr attr; r = -EFAULT; @@ -4794,28 +5138,46 @@ out: return r; } -static void wbinvd_ipi(void *garbage) -{ - wbinvd(); -} - static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu) { return kvm_arch_has_noncoherent_dma(vcpu->kvm); } +static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu); + void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + + kvm_request_l1tf_flush_l1d(); + + if (vcpu->scheduled_out && pmu->version && pmu->event_count) { + pmu->need_cleanup = true; + kvm_make_request(KVM_REQ_PMU, vcpu); + } + /* Address WBINVD may be executed by guest */ if (need_emulate_wbinvd(vcpu)) { - if (static_call(kvm_x86_has_wbinvd_exit)()) + if (kvm_x86_call(has_wbinvd_exit)()) cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); else if (vcpu->cpu != -1 && vcpu->cpu != cpu) - smp_call_function_single(vcpu->cpu, - wbinvd_ipi, NULL, 1); + wbinvd_on_cpu(vcpu->cpu); } - static_call(kvm_x86_vcpu_load)(vcpu, cpu); + kvm_x86_call(vcpu_load)(vcpu, cpu); + + if (vcpu != per_cpu(last_vcpu, cpu)) { + /* + * Flush the branch predictor when switching vCPUs on the same + * physical CPU, as each vCPU needs its own branch prediction + * domain. No IBPB is needed when switching between L1 and L2 + * on the same vCPU unless IBRS is advertised to the vCPU; that + * is handled on the nested VM-Exit path. + */ + if (static_branch_likely(&switch_vcpu_ibpb)) + indirect_branch_prediction_barrier(); + per_cpu(last_vcpu, cpu) = vcpu; + } /* Save host pkru register if supported */ vcpu->arch.host_pkru = read_pkru(); @@ -4837,7 +5199,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) u64 offset = kvm_compute_l1_tsc_offset(vcpu, vcpu->arch.last_guest_tsc); kvm_vcpu_write_tsc_offset(vcpu, offset); - vcpu->arch.tsc_catchup = 1; + if (!vcpu->arch.guest_tsc_protected) + vcpu->arch.tsc_catchup = 1; } if (kvm_lapic_hv_timer_in_use(vcpu)) @@ -4909,8 +5272,13 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) int idx; if (vcpu->preempted) { - if (!vcpu->arch.guest_state_protected) - vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu); + /* + * Assume protected guests are in-kernel. Inefficient yielding + * due to false positives is preferable to never yielding due + * to false negatives. + */ + vcpu->arch.preempted_in_kernel = vcpu->arch.guest_state_protected || + !kvm_x86_call(get_cpl_no_cache)(vcpu); /* * Take the srcu lock as memslots will be accessed to check the gfn @@ -4924,14 +5292,17 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) srcu_read_unlock(&vcpu->kvm->srcu, idx); } - static_call(kvm_x86_vcpu_put)(vcpu); + kvm_x86_call(vcpu_put)(vcpu); vcpu->arch.last_host_tsc = rdtsc(); } static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); + if (vcpu->arch.apic->guest_apic_protected) + return -EINVAL; + + kvm_x86_call(sync_pir_to_irr)(vcpu); return kvm_apic_get_state(vcpu, s); } @@ -4941,6 +5312,9 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, { int r; + if (vcpu->arch.apic->guest_apic_protected) + return -EINVAL; + r = kvm_apic_set_state(vcpu, s); if (r) return r; @@ -5048,7 +5422,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, kvm_apic_after_set_mcg_cap(vcpu); - static_call(kvm_x86_setup_mce)(vcpu); + kvm_x86_call(setup_mce)(vcpu); out: return r; } @@ -5208,11 +5582,11 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->interrupt.injected = vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft; events->interrupt.nr = vcpu->arch.interrupt.nr; - events->interrupt.shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); + events->interrupt.shadow = kvm_x86_call(get_interrupt_shadow)(vcpu); events->nmi.injected = vcpu->arch.nmi_injected; events->nmi.pending = kvm_get_nr_pending_nmis(vcpu); - events->nmi.masked = static_call(kvm_x86_get_nmi_mask)(vcpu); + events->nmi.masked = kvm_x86_call(get_nmi_mask)(vcpu); /* events->sipi_vector is never valid when reporting to user space */ @@ -5262,12 +5636,6 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR)) return -EINVAL; - /* INITs are latched while in SMM */ - if (events->flags & KVM_VCPUEVENT_VALID_SMM && - (events->smi.smm || events->smi.pending) && - vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) - return -EINVAL; - process_nmi(vcpu); /* @@ -5294,16 +5662,17 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.interrupt.nr = events->interrupt.nr; vcpu->arch.interrupt.soft = events->interrupt.soft; if (events->flags & KVM_VCPUEVENT_VALID_SHADOW) - static_call(kvm_x86_set_interrupt_shadow)(vcpu, - events->interrupt.shadow); + kvm_x86_call(set_interrupt_shadow)(vcpu, + events->interrupt.shadow); vcpu->arch.nmi_injected = events->nmi.injected; if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) { vcpu->arch.nmi_pending = 0; atomic_set(&vcpu->arch.nmi_queued, events->nmi.pending); - kvm_make_request(KVM_REQ_NMI, vcpu); + if (events->nmi.pending) + kvm_make_request(KVM_REQ_NMI, vcpu); } - static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked); + kvm_x86_call(set_nmi_mask)(vcpu, events->nmi.masked); if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR && lapic_in_kernel(vcpu)) @@ -5353,21 +5722,35 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, return 0; } -static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, - struct kvm_debugregs *dbgregs) +static int kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, + struct kvm_debugregs *dbgregs) { - unsigned long val; + unsigned int i; + + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; memset(dbgregs, 0, sizeof(*dbgregs)); - memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); - kvm_get_dr(vcpu, 6, &val); - dbgregs->dr6 = val; + + BUILD_BUG_ON(ARRAY_SIZE(vcpu->arch.db) != ARRAY_SIZE(dbgregs->db)); + for (i = 0; i < ARRAY_SIZE(vcpu->arch.db); i++) + dbgregs->db[i] = vcpu->arch.db[i]; + + dbgregs->dr6 = vcpu->arch.dr6; dbgregs->dr7 = vcpu->arch.dr7; + return 0; } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, struct kvm_debugregs *dbgregs) { + unsigned int i; + + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + if (dbgregs->flags) return -EINVAL; @@ -5376,7 +5759,9 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, if (!kvm_dr7_valid(dbgregs->dr7)) return -EINVAL; - memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); + for (i = 0; i < ARRAY_SIZE(vcpu->arch.db); i++) + vcpu->arch.db[i] = dbgregs->db[i]; + kvm_update_dr0123(vcpu); vcpu->arch.dr6 = dbgregs->dr6; vcpu->arch.dr7 = dbgregs->dr7; @@ -5385,33 +5770,45 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, return 0; } -static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, - struct kvm_xsave *guest_xsave) + +static int kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, + u8 *state, unsigned int size) { + /* + * Only copy state for features that are enabled for the guest. The + * state itself isn't problematic, but setting bits in the header for + * features that are supported in *this* host but not exposed to the + * guest can result in KVM_SET_XSAVE failing when live migrating to a + * compatible host without the features that are NOT exposed to the + * guest. + * + * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if + * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't + * supported by the host. + */ + u64 supported_xcr0 = vcpu->arch.guest_supported_xcr0 | + XFEATURE_MASK_FPSSE; + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; - fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, - guest_xsave->region, - sizeof(guest_xsave->region), - vcpu->arch.pkru); + fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size, + supported_xcr0, vcpu->arch.pkru); + return 0; } -static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, - u8 *state, unsigned int size) +static int kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, + struct kvm_xsave *guest_xsave) { - if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return; - - fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, - state, size, vcpu->arch.pkru); + return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region, + sizeof(guest_xsave->region)); } static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return 0; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu, guest_xsave->region, @@ -5419,18 +5816,23 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, &vcpu->arch.pkru); } -static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, - struct kvm_xcrs *guest_xcrs) +static int kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, + struct kvm_xcrs *guest_xcrs) { + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + if (!boot_cpu_has(X86_FEATURE_XSAVE)) { guest_xcrs->nr_xcrs = 0; - return; + return 0; } guest_xcrs->nr_xcrs = 1; guest_xcrs->flags = 0; guest_xcrs->xcrs[0].xcr = XCR_XFEATURE_ENABLED_MASK; guest_xcrs->xcrs[0].value = vcpu->arch.xcr0; + return 0; } static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, @@ -5438,6 +5840,10 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, { int i, r = 0; + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + if (!boot_cpu_has(X86_FEATURE_XSAVE)) return -EINVAL; @@ -5490,12 +5896,9 @@ static int kvm_arch_tsc_has_attr(struct kvm_vcpu *vcpu, static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - u64 __user *uaddr = kvm_get_attr_addr(attr); + u64 __user *uaddr = u64_to_user_ptr(attr->addr); int r; - if (IS_ERR(uaddr)) - return PTR_ERR(uaddr); - switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: r = -EFAULT; @@ -5513,13 +5916,10 @@ static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - u64 __user *uaddr = kvm_get_attr_addr(attr); + u64 __user *uaddr = u64_to_user_ptr(attr->addr); struct kvm *kvm = vcpu->kvm; int r; - if (IS_ERR(uaddr)) - return PTR_ERR(uaddr); - switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: { u64 offset, tsc, ns; @@ -5539,7 +5939,7 @@ static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio) + offset; ns = get_kvmclock_base_ns(); - __kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched); + __kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched, true); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); r = 0; @@ -5583,14 +5983,11 @@ static int kvm_vcpu_ioctl_device_attr(struct kvm_vcpu *vcpu, static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, struct kvm_enable_cap *cap) { - int r; - uint16_t vmcs_version; - void __user *user_ptr; - if (cap->flags) return -EINVAL; switch (cap->cap) { +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV_SYNIC2: if (cap->args[0]) return -EINVAL; @@ -5602,36 +5999,168 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return kvm_hv_activate_synic(vcpu, cap->cap == KVM_CAP_HYPERV_SYNIC2); case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: - if (!kvm_x86_ops.nested_ops->enable_evmcs) - return -ENOTTY; - r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version); - if (!r) { - user_ptr = (void __user *)(uintptr_t)cap->args[0]; - if (copy_to_user(user_ptr, &vmcs_version, - sizeof(vmcs_version))) - r = -EFAULT; + { + int r; + uint16_t vmcs_version; + void __user *user_ptr; + + if (!kvm_x86_ops.nested_ops->enable_evmcs) + return -ENOTTY; + r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version); + if (!r) { + user_ptr = (void __user *)(uintptr_t)cap->args[0]; + if (copy_to_user(user_ptr, &vmcs_version, + sizeof(vmcs_version))) + r = -EFAULT; + } + return r; } - return r; case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: if (!kvm_x86_ops.enable_l2_tlb_flush) return -ENOTTY; - return static_call(kvm_x86_enable_l2_tlb_flush)(vcpu); + return kvm_x86_call(enable_l2_tlb_flush)(vcpu); case KVM_CAP_HYPERV_ENFORCE_CPUID: return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]); +#endif case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; - if (vcpu->arch.pv_cpuid.enforce) - kvm_update_pv_runtime(vcpu); - return 0; default: return -EINVAL; } } +struct kvm_x86_reg_id { + __u32 index; + __u8 type; + __u8 rsvd1; + __u8 rsvd2:4; + __u8 size:4; + __u8 x86; +}; + +static int kvm_translate_kvm_reg(struct kvm_vcpu *vcpu, + struct kvm_x86_reg_id *reg) +{ + switch (reg->index) { + case KVM_REG_GUEST_SSP: + /* + * FIXME: If host-initiated accesses are ever exempted from + * ignore_msrs (in kvm_do_msr_access()), drop this manual check + * and rely on KVM's standard checks to reject accesses to regs + * that don't exist. + */ + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) + return -EINVAL; + + reg->type = KVM_X86_REG_TYPE_MSR; + reg->index = MSR_KVM_INTERNAL_GUEST_SSP; + break; + default: + return -EINVAL; + } + return 0; +} + +static int kvm_get_one_msr(struct kvm_vcpu *vcpu, u32 msr, u64 __user *user_val) +{ + u64 val; + + if (do_get_msr(vcpu, msr, &val)) + return -EINVAL; + + if (put_user(val, user_val)) + return -EFAULT; + + return 0; +} + +static int kvm_set_one_msr(struct kvm_vcpu *vcpu, u32 msr, u64 __user *user_val) +{ + u64 val; + + if (get_user(val, user_val)) + return -EFAULT; + + if (do_set_msr(vcpu, msr, &val)) + return -EINVAL; + + return 0; +} + +static int kvm_get_set_one_reg(struct kvm_vcpu *vcpu, unsigned int ioctl, + void __user *argp) +{ + struct kvm_one_reg one_reg; + struct kvm_x86_reg_id *reg; + u64 __user *user_val; + bool load_fpu; + int r; + + if (copy_from_user(&one_reg, argp, sizeof(one_reg))) + return -EFAULT; + + if ((one_reg.id & KVM_REG_ARCH_MASK) != KVM_REG_X86) + return -EINVAL; + + reg = (struct kvm_x86_reg_id *)&one_reg.id; + if (reg->rsvd1 || reg->rsvd2) + return -EINVAL; + + if (reg->type == KVM_X86_REG_TYPE_KVM) { + r = kvm_translate_kvm_reg(vcpu, reg); + if (r) + return r; + } + + if (reg->type != KVM_X86_REG_TYPE_MSR) + return -EINVAL; + + if ((one_reg.id & KVM_REG_SIZE_MASK) != KVM_REG_SIZE_U64) + return -EINVAL; + + guard(srcu)(&vcpu->kvm->srcu); + + load_fpu = is_xstate_managed_msr(vcpu, reg->index); + if (load_fpu) + kvm_load_guest_fpu(vcpu); + + user_val = u64_to_user_ptr(one_reg.addr); + if (ioctl == KVM_GET_ONE_REG) + r = kvm_get_one_msr(vcpu, reg->index, user_val); + else + r = kvm_set_one_msr(vcpu, reg->index, user_val); + + if (load_fpu) + kvm_put_guest_fpu(vcpu); + return r; +} + +static int kvm_get_reg_list(struct kvm_vcpu *vcpu, + struct kvm_reg_list __user *user_list) +{ + u64 nr_regs = guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) ? 1 : 0; + u64 user_nr_regs; + + if (get_user(user_nr_regs, &user_list->n)) + return -EFAULT; + + if (put_user(nr_regs, &user_list->n)) + return -EFAULT; + + if (user_nr_regs < nr_regs) + return -E2BIG; + + if (nr_regs && + put_user(KVM_X86_REG_KVM(KVM_REG_GUEST_SSP), &user_list->reg[0])) + return -EFAULT; + + return 0; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -5654,8 +6183,7 @@ 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_ACCOUNT); + u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); r = -ENOMEM; if (!u.lapic) @@ -5749,6 +6277,13 @@ long kvm_arch_vcpu_ioctl(struct file *filp, srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } + case KVM_GET_ONE_REG: + case KVM_SET_ONE_REG: + r = kvm_get_set_one_reg(vcpu, ioctl, argp); + break; + case KVM_GET_REG_LIST: + r = kvm_get_reg_list(vcpu, argp); + break; case KVM_TPR_ACCESS_REPORTING: { struct kvm_tpr_access_ctl tac; @@ -5815,13 +6350,17 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events))) break; + kvm_vcpu_srcu_read_lock(vcpu); r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events); + kvm_vcpu_srcu_read_unlock(vcpu); break; } case KVM_GET_DEBUGREGS: { struct kvm_debugregs dbgregs; - kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs); + r = kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs); + if (r < 0) + break; r = -EFAULT; if (copy_to_user(argp, &dbgregs, @@ -5846,12 +6385,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (vcpu->arch.guest_fpu.uabi_size > sizeof(struct kvm_xsave)) break; - u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL_ACCOUNT); + u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL); r = -ENOMEM; if (!u.xsave) break; - kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave); + r = kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave); + if (r < 0) + break; r = -EFAULT; if (copy_to_user(argp, u.xsave, sizeof(struct kvm_xsave))) @@ -5875,12 +6416,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_GET_XSAVE2: { int size = vcpu->arch.guest_fpu.uabi_size; - u.xsave = kzalloc(size, GFP_KERNEL_ACCOUNT); + u.xsave = kzalloc(size, GFP_KERNEL); r = -ENOMEM; if (!u.xsave) break; - kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size); + r = kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size); + if (r < 0) + break; r = -EFAULT; if (copy_to_user(argp, u.xsave, size)) @@ -5891,12 +6434,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } case KVM_GET_XCRS: { - u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL_ACCOUNT); + u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL); r = -ENOMEM; if (!u.xcrs) break; - kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs); + r = kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs); + if (r < 0) + break; r = -EFAULT; if (copy_to_user(argp, u.xcrs, @@ -5919,6 +6464,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, u32 user_tsc_khz; r = -EINVAL; + + if (vcpu->arch.guest_tsc_protected) + goto out; + user_tsc_khz = (u32)arg; if (kvm_caps.has_tsc_control && @@ -6012,9 +6561,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } +#ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp); break; +#endif #ifdef CONFIG_KVM_XEN case KVM_XEN_VCPU_GET_ATTR: { struct kvm_xen_vcpu_attr xva; @@ -6038,6 +6589,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } #endif case KVM_GET_SREGS2: { + r = -EINVAL; + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + goto out; + u.sregs2 = kzalloc(sizeof(struct kvm_sregs2), GFP_KERNEL); r = -ENOMEM; if (!u.sregs2) @@ -6050,6 +6606,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SET_SREGS2: { + r = -EINVAL; + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + goto out; + u.sregs2 = memdup_user(argp, sizeof(struct kvm_sregs2)); if (IS_ERR(u.sregs2)) { r = PTR_ERR(u.sregs2); @@ -6064,6 +6625,12 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_SET_DEVICE_ATTR: r = kvm_vcpu_ioctl_device_attr(vcpu, ioctl, argp); break; + case KVM_MEMORY_ENCRYPT_OP: + r = -ENOTTY; + if (!kvm_x86_ops.vcpu_mem_enc_ioctl) + goto out; + r = kvm_x86_ops.vcpu_mem_enc_ioctl(vcpu, argp); + break; default: r = -EINVAL; } @@ -6085,14 +6652,14 @@ static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr) if (addr > (unsigned int)(-3 * PAGE_SIZE)) return -EINVAL; - ret = static_call(kvm_x86_set_tss_addr)(kvm, addr); + ret = kvm_x86_call(set_tss_addr)(kvm, addr); return ret; } static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) { - return static_call(kvm_x86_set_identity_map_addr)(kvm, ident_addr); + return kvm_x86_call(set_identity_map_addr)(kvm, ident_addr); } static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, @@ -6110,135 +6677,6 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, return 0; } -static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) -{ - struct kvm_pic *pic = kvm->arch.vpic; - int r; - - r = 0; - switch (chip->chip_id) { - case KVM_IRQCHIP_PIC_MASTER: - memcpy(&chip->chip.pic, &pic->pics[0], - sizeof(struct kvm_pic_state)); - break; - case KVM_IRQCHIP_PIC_SLAVE: - memcpy(&chip->chip.pic, &pic->pics[1], - sizeof(struct kvm_pic_state)); - break; - case KVM_IRQCHIP_IOAPIC: - kvm_get_ioapic(kvm, &chip->chip.ioapic); - break; - default: - r = -EINVAL; - break; - } - return r; -} - -static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) -{ - struct kvm_pic *pic = kvm->arch.vpic; - int r; - - r = 0; - switch (chip->chip_id) { - case KVM_IRQCHIP_PIC_MASTER: - spin_lock(&pic->lock); - memcpy(&pic->pics[0], &chip->chip.pic, - sizeof(struct kvm_pic_state)); - spin_unlock(&pic->lock); - break; - case KVM_IRQCHIP_PIC_SLAVE: - spin_lock(&pic->lock); - memcpy(&pic->pics[1], &chip->chip.pic, - sizeof(struct kvm_pic_state)); - spin_unlock(&pic->lock); - break; - case KVM_IRQCHIP_IOAPIC: - kvm_set_ioapic(kvm, &chip->chip.ioapic); - break; - default: - r = -EINVAL; - break; - } - kvm_pic_update_irq(pic); - return r; -} - -static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) -{ - struct kvm_kpit_state *kps = &kvm->arch.vpit->pit_state; - - BUILD_BUG_ON(sizeof(*ps) != sizeof(kps->channels)); - - mutex_lock(&kps->lock); - memcpy(ps, &kps->channels, sizeof(*ps)); - mutex_unlock(&kps->lock); - return 0; -} - -static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) -{ - int i; - struct kvm_pit *pit = kvm->arch.vpit; - - mutex_lock(&pit->pit_state.lock); - memcpy(&pit->pit_state.channels, ps, sizeof(*ps)); - for (i = 0; i < 3; i++) - kvm_pit_load_count(pit, i, ps->channels[i].count, 0); - mutex_unlock(&pit->pit_state.lock); - return 0; -} - -static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) -{ - mutex_lock(&kvm->arch.vpit->pit_state.lock); - memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels, - sizeof(ps->channels)); - ps->flags = kvm->arch.vpit->pit_state.flags; - mutex_unlock(&kvm->arch.vpit->pit_state.lock); - memset(&ps->reserved, 0, sizeof(ps->reserved)); - return 0; -} - -static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) -{ - int start = 0; - int i; - u32 prev_legacy, cur_legacy; - struct kvm_pit *pit = kvm->arch.vpit; - - mutex_lock(&pit->pit_state.lock); - prev_legacy = pit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; - cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY; - if (!prev_legacy && cur_legacy) - start = 1; - memcpy(&pit->pit_state.channels, &ps->channels, - sizeof(pit->pit_state.channels)); - pit->pit_state.flags = ps->flags; - for (i = 0; i < 3; i++) - kvm_pit_load_count(pit, i, pit->pit_state.channels[i].count, - start && i == 0); - mutex_unlock(&pit->pit_state.lock); - return 0; -} - -static int kvm_vm_ioctl_reinject(struct kvm *kvm, - struct kvm_reinject_control *control) -{ - struct kvm_pit *pit = kvm->arch.vpit; - - /* pit->pit_state.lock was overloaded to prevent userspace from getting - * an inconsistent state after running multiple KVM_REINJECT_CONTROL - * ioctls in parallel. Use a separate lock if that ioctl isn't rare. - */ - mutex_lock(&pit->pit_state.lock); - kvm_pit_set_reinject(pit, control->pit_reinject); - mutex_unlock(&pit->pit_state.lock); - - return 0; -} - void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { @@ -6251,22 +6689,13 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) struct kvm_vcpu *vcpu; unsigned long i; + if (!kvm->arch.cpu_dirty_log_size) + return; + kvm_for_each_vcpu(i, vcpu, kvm) kvm_vcpu_kick(vcpu); } -int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, - bool line_status) -{ - if (!irqchip_in_kernel(kvm)) - return -ENXIO; - - irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, - irq_event->irq, irq_event->level, - line_status); - return 0; -} - int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { @@ -6278,11 +6707,11 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, switch (cap->cap) { case KVM_CAP_DISABLE_QUIRKS2: r = -EINVAL; - if (cap->args[0] & ~KVM_X86_VALID_QUIRKS) + if (cap->args[0] & ~kvm_caps.supported_quirks) break; fallthrough; case KVM_CAP_DISABLE_QUIRKS: - kvm->arch.disabled_quirks = cap->args[0]; + kvm->arch.disabled_quirks |= cap->args[0] & kvm_caps.supported_quirks; r = 0; break; case KVM_CAP_SPLIT_IRQCHIP: { @@ -6295,9 +6724,6 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, goto split_irqchip_unlock; if (kvm->created_vcpus) goto split_irqchip_unlock; - r = kvm_setup_empty_irq_routing(kvm); - if (r) - goto split_irqchip_unlock; /* Pairs with irqchip_in_kernel. */ smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT; @@ -6322,30 +6748,26 @@ split_irqchip_unlock: break; case KVM_CAP_X86_DISABLE_EXITS: r = -EINVAL; - if (cap->args[0] & ~KVM_X86_DISABLE_VALID_EXITS) + if (cap->args[0] & ~kvm_get_allowed_disable_exits()) break; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE) - kvm->arch.pause_in_guest = true; + mutex_lock(&kvm->lock); + if (kvm->created_vcpus) + goto disable_exits_unlock; #define SMT_RSB_MSG "This processor is affected by the Cross-Thread Return Predictions vulnerability. " \ "KVM_CAP_X86_DISABLE_EXITS should only be used with SMT disabled or trusted guests." - if (!mitigate_smt_rsb) { - if (boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible() && - (cap->args[0] & ~KVM_X86_DISABLE_EXITS_PAUSE)) - pr_warn_once(SMT_RSB_MSG); - - if ((cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) && - kvm_can_mwait_in_guest()) - kvm->arch.mwait_in_guest = true; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT) - kvm->arch.hlt_in_guest = true; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE) - kvm->arch.cstate_in_guest = true; - } + if (!mitigate_smt_rsb && boot_cpu_has_bug(X86_BUG_SMT_RSB) && + cpu_smt_possible() && + (cap->args[0] & ~(KVM_X86_DISABLE_EXITS_PAUSE | + KVM_X86_DISABLE_EXITS_APERFMPERF))) + pr_warn_once(SMT_RSB_MSG); + kvm_disable_exits(kvm, cap->args[0]); r = 0; +disable_exits_unlock: + mutex_unlock(&kvm->lock); break; case KVM_CAP_MSR_PLATFORM_INFO: kvm->arch.guest_can_read_msr_platform_info = cap->args[0]; @@ -6402,14 +6824,14 @@ split_irqchip_unlock: if (!kvm_x86_ops.vm_copy_enc_context_from) break; - r = static_call(kvm_x86_vm_copy_enc_context_from)(kvm, cap->args[0]); + r = kvm_x86_call(vm_copy_enc_context_from)(kvm, cap->args[0]); break; case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM: r = -EINVAL; if (!kvm_x86_ops.vm_move_enc_context_from) break; - r = static_call(kvm_x86_vm_move_enc_context_from)(kvm, cap->args[0]); + r = kvm_x86_call(vm_move_enc_context_from)(kvm, cap->args[0]); break; case KVM_CAP_EXIT_HYPERCALL: if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) { @@ -6444,7 +6866,9 @@ split_irqchip_unlock: break; mutex_lock(&kvm->lock); - if (kvm->arch.max_vcpu_ids == cap->args[0]) { + if (kvm->arch.bsp_vcpu_id > cap->args[0]) { + ; + } else if (kvm->arch.max_vcpu_ids == cap->args[0]) { r = 0; } else if (!kvm->arch.max_vcpu_ids) { kvm->arch.max_vcpu_ids = cap->args[0]; @@ -6497,6 +6921,30 @@ split_irqchip_unlock: } mutex_unlock(&kvm->lock); break; + case KVM_CAP_X86_APIC_BUS_CYCLES_NS: { + u64 bus_cycle_ns = cap->args[0]; + u64 unused; + + /* + * Guard against overflow in tmict_to_ns(). 128 is the highest + * divide value that can be programmed in APIC_TDCR. + */ + r = -EINVAL; + if (!bus_cycle_ns || + check_mul_overflow((u64)U32_MAX * 128, bus_cycle_ns, &unused)) + break; + + r = 0; + mutex_lock(&kvm->lock); + if (!irqchip_in_kernel(kvm)) + r = -ENXIO; + else if (kvm->created_vcpus) + r = -EINVAL; + else + kvm->arch.apic_bus_cycle_ns = bus_cycle_ns; + mutex_unlock(&kvm->lock); + break; + } default: r = -EINVAL; break; @@ -6532,7 +6980,7 @@ static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter) static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, struct kvm_msr_filter_range *user_range) { - unsigned long *bitmap = NULL; + unsigned long *bitmap; size_t bitmap_size; if (!user_range->nmsrs) @@ -6602,7 +7050,11 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, kvm_free_msr_filter(old_filter); - kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED); + /* + * Recalc MSR intercepts as userspace may want to intercept accesses to + * MSRs that KVM would otherwise pass through to the guest. + */ + kvm_make_all_cpus_request(kvm, KVM_REQ_RECALC_INTERCEPTS); return 0; } @@ -6668,23 +7120,15 @@ static int kvm_arch_suspend_notifier(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long i; - int ret = 0; - mutex_lock(&kvm->lock); - kvm_for_each_vcpu(i, vcpu, kvm) { - if (!vcpu->arch.pv_time.active) - continue; - - ret = kvm_set_guest_paused(vcpu); - if (ret) { - kvm_err("Failed to pause guest VCPU%d: %d\n", - vcpu->vcpu_id, ret); - break; - } - } - mutex_unlock(&kvm->lock); + /* + * Ignore the return, marking the guest paused only "fails" if the vCPU + * isn't using kvmclock; continuing on is correct and desirable. + */ + kvm_for_each_vcpu(i, vcpu, kvm) + (void)kvm_set_guest_paused(vcpu); - return ret ? NOTIFY_BAD : NOTIFY_DONE; + return NOTIFY_DONE; } int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state) @@ -6756,14 +7200,29 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) return 0; } +long kvm_arch_vcpu_unlocked_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + struct kvm_vcpu *vcpu = filp->private_data; + void __user *argp = (void __user *)arg; + + if (ioctl == KVM_MEMORY_ENCRYPT_OP && + kvm_x86_ops.vcpu_mem_enc_unlocked_ioctl) + return kvm_x86_call(vcpu_mem_enc_unlocked_ioctl)(vcpu, argp); + + return -ENOIOCTLCMD; +} + int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; int r = -ENOTTY; + +#ifdef CONFIG_KVM_IOAPIC /* * This union makes it completely explicit to gcc-3.x - * that these two variables' stack usage should be + * that these three variables' stack usage should be * combined, not added together. */ union { @@ -6771,6 +7230,7 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) struct kvm_pit_state2 ps2; struct kvm_pit_config pit_config; } u; +#endif switch (ioctl) { case KVM_SET_TSS_ADDR: @@ -6794,6 +7254,7 @@ set_identity_unlock: case KVM_SET_NR_MMU_PAGES: r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg); break; +#ifdef CONFIG_KVM_IOAPIC case KVM_CREATE_IRQCHIP: { mutex_lock(&kvm->lock); @@ -6801,6 +7262,15 @@ set_identity_unlock: if (irqchip_in_kernel(kvm)) goto create_irqchip_unlock; + /* + * Disallow an in-kernel I/O APIC if the VM has protected EOIs, + * i.e. if KVM can't intercept EOIs and thus can't properly + * emulate level-triggered interrupts. + */ + r = -ENOTTY; + if (kvm->arch.has_protected_eoi) + goto create_irqchip_unlock; + r = -EINVAL; if (kvm->created_vcpus) goto create_irqchip_unlock; @@ -6815,7 +7285,7 @@ set_identity_unlock: goto create_irqchip_unlock; } - r = kvm_setup_default_irq_routing(kvm); + r = kvm_setup_default_ioapic_and_pic_routing(kvm); if (r) { kvm_ioapic_destroy(kvm); kvm_pic_destroy(kvm); @@ -6842,6 +7312,9 @@ set_identity_unlock: r = -EEXIST; if (kvm->arch.vpit) goto create_pit_unlock; + r = -ENOENT; + if (!pic_in_kernel(kvm)) + goto create_pit_unlock; r = -ENOMEM; kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags); if (kvm->arch.vpit) @@ -6860,7 +7333,7 @@ set_identity_unlock: } r = -ENXIO; - if (!irqchip_kernel(kvm)) + if (!irqchip_full(kvm)) goto get_irqchip_out; r = kvm_vm_ioctl_get_irqchip(kvm, chip); if (r) @@ -6884,7 +7357,7 @@ set_identity_unlock: } r = -ENXIO; - if (!irqchip_kernel(kvm)) + if (!irqchip_full(kvm)) goto set_irqchip_out; r = kvm_vm_ioctl_set_irqchip(kvm, chip); set_irqchip_out: @@ -6957,11 +7430,15 @@ set_pit2_out: r = kvm_vm_ioctl_reinject(kvm, &control); break; } +#endif case KVM_SET_BOOT_CPU_ID: r = 0; mutex_lock(&kvm->lock); if (kvm->created_vcpus) r = -EBUSY; + else if (arg > KVM_MAX_VCPU_IDS || + (kvm->arch.max_vcpu_ids && arg > kvm->arch.max_vcpu_ids)) + r = -EINVAL; else kvm->arch.bsp_vcpu_id = arg; mutex_unlock(&kvm->lock); @@ -7024,23 +7501,25 @@ set_pit2_out: if (user_tsc_khz == 0) user_tsc_khz = tsc_khz; - WRITE_ONCE(kvm->arch.default_tsc_khz, user_tsc_khz); - r = 0; - + mutex_lock(&kvm->lock); + if (!kvm->created_vcpus) { + WRITE_ONCE(kvm->arch.default_tsc_khz, user_tsc_khz); + r = 0; + } + mutex_unlock(&kvm->lock); goto out; } case KVM_GET_TSC_KHZ: { r = READ_ONCE(kvm->arch.default_tsc_khz); goto out; } - case KVM_MEMORY_ENCRYPT_OP: { + case KVM_MEMORY_ENCRYPT_OP: r = -ENOTTY; if (!kvm_x86_ops.mem_enc_ioctl) goto out; - r = static_call(kvm_x86_mem_enc_ioctl)(kvm, argp); + r = kvm_x86_call(mem_enc_ioctl)(kvm, argp); break; - } case KVM_MEMORY_ENCRYPT_REG_REGION: { struct kvm_enc_region region; @@ -7052,7 +7531,7 @@ set_pit2_out: if (!kvm_x86_ops.mem_enc_register_region) goto out; - r = static_call(kvm_x86_mem_enc_register_region)(kvm, ®ion); + r = kvm_x86_call(mem_enc_register_region)(kvm, ®ion); break; } case KVM_MEMORY_ENCRYPT_UNREG_REGION: { @@ -7066,9 +7545,10 @@ set_pit2_out: if (!kvm_x86_ops.mem_enc_unregister_region) goto out; - r = static_call(kvm_x86_mem_enc_unregister_region)(kvm, ®ion); + r = kvm_x86_call(mem_enc_unregister_region)(kvm, ®ion); break; } +#ifdef CONFIG_KVM_HYPERV case KVM_HYPERV_EVENTFD: { struct kvm_hyperv_eventfd hvevfd; @@ -7078,6 +7558,7 @@ set_pit2_out: r = kvm_vm_ioctl_hv_eventfd(kvm, &hvevfd); break; } +#endif case KVM_SET_PMU_EVENT_FILTER: r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); break; @@ -7100,11 +7581,9 @@ out: static void kvm_probe_feature_msr(u32 msr_index) { - struct kvm_msr_entry msr = { - .index = msr_index, - }; + u64 data; - if (kvm_get_msr_feature(&msr)) + if (kvm_get_feature_msr(NULL, msr_index, &data, true)) return; msr_based_features[num_msr_based_features++] = msr_index; @@ -7158,17 +7637,20 @@ static void kvm_probe_msr_to_save(u32 msr_index) intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)) return; break; - case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX: + case MSR_ARCH_PERFMON_PERFCTR0 ... + MSR_ARCH_PERFMON_PERFCTR0 + KVM_MAX_NR_GP_COUNTERS - 1: if (msr_index - MSR_ARCH_PERFMON_PERFCTR0 >= kvm_pmu_cap.num_counters_gp) return; break; - case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX: + case MSR_ARCH_PERFMON_EVENTSEL0 ... + MSR_ARCH_PERFMON_EVENTSEL0 + KVM_MAX_NR_GP_COUNTERS - 1: if (msr_index - MSR_ARCH_PERFMON_EVENTSEL0 >= kvm_pmu_cap.num_counters_gp) return; break; - case MSR_ARCH_PERFMON_FIXED_CTR0 ... MSR_ARCH_PERFMON_FIXED_CTR_MAX: + case MSR_ARCH_PERFMON_FIXED_CTR0 ... + MSR_ARCH_PERFMON_FIXED_CTR0 + KVM_MAX_NR_FIXED_COUNTERS - 1: if (msr_index - MSR_ARCH_PERFMON_FIXED_CTR0 >= kvm_pmu_cap.num_counters_fixed) return; @@ -7176,6 +7658,7 @@ static void kvm_probe_msr_to_save(u32 msr_index) case MSR_AMD64_PERF_CNTR_GLOBAL_CTL: case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS: case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR: + case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET: if (!kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2)) return; break; @@ -7188,6 +7671,24 @@ static void kvm_probe_msr_to_save(u32 msr_index) if (!(kvm_get_arch_capabilities() & ARCH_CAP_TSX_CTRL_MSR)) return; break; + case MSR_IA32_XSS: + if (!kvm_caps.supported_xss) + return; + break; + case MSR_IA32_U_CET: + case MSR_IA32_S_CET: + if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && + !kvm_cpu_cap_has(X86_FEATURE_IBT)) + return; + break; + case MSR_IA32_INT_SSP_TAB: + if (!kvm_cpu_cap_has(X86_FEATURE_LM)) + return; + fallthrough; + case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP: + if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK)) + return; + break; default: break; } @@ -7199,7 +7700,7 @@ static void kvm_init_msr_lists(void) { unsigned i; - BUILD_BUG_ON_MSG(KVM_PMC_MAX_FIXED != 3, + BUILD_BUG_ON_MSG(KVM_MAX_NR_FIXED_COUNTERS != 3, "Please update the fixed PMCs in msrs_to_save_pmu[]"); num_msrs_to_save = 0; @@ -7215,7 +7716,8 @@ static void kvm_init_msr_lists(void) } for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { - if (!static_call(kvm_x86_has_emulated_msr)(NULL, emulated_msrs_all[i])) + if (!kvm_x86_call(has_emulated_msr)(NULL, + emulated_msrs_all[i])) continue; emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; @@ -7274,13 +7776,13 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) void kvm_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { - static_call(kvm_x86_set_segment)(vcpu, var, seg); + kvm_x86_call(set_segment)(vcpu, var, seg); } void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { - static_call(kvm_x86_get_segment)(vcpu, var, seg); + kvm_x86_call(get_segment)(vcpu, var, seg); } gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u64 access, @@ -7303,21 +7805,21 @@ gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; + u64 access = (kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } -EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_gva_to_gpa_read); gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; + u64 access = (kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_WRITE_MASK; return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } -EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_write); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_gva_to_gpa_write); /* uses this to access any guest's mapped memory without checking CPL */ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, @@ -7366,7 +7868,7 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; + u64 access = (kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; unsigned offset; int ret; @@ -7391,7 +7893,7 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { - u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; + u64 access = (kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; /* * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED @@ -7403,7 +7905,7 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu, return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); } -EXPORT_SYMBOL_GPL(kvm_read_guest_virt); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_read_guest_virt); static int emulator_read_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, @@ -7414,7 +7916,7 @@ static int emulator_read_std(struct x86_emulate_ctxt *ctxt, if (system) access |= PFERR_IMPLICIT_ACCESS; - else if (static_call(kvm_x86_get_cpl)(vcpu) == 3) + else if (kvm_x86_call(get_cpl)(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); @@ -7459,7 +7961,7 @@ static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *v if (system) access |= PFERR_IMPLICIT_ACCESS; - else if (static_call(kvm_x86_get_cpl)(vcpu) == 3) + else if (kvm_x86_call(get_cpl)(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, @@ -7470,18 +7972,18 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { /* kvm_write_guest_virt_system can pull in tons of pages. */ - vcpu->arch.l1tf_flush_l1d = true; + kvm_request_l1tf_flush_l1d(); return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, PFERR_WRITE_MASK, exception); } -EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_write_guest_virt_system); -static int kvm_can_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +static int kvm_check_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { - return static_call(kvm_x86_can_emulate_instruction)(vcpu, emul_type, - insn, insn_len); + return kvm_x86_call(check_emulate_instruction)(vcpu, emul_type, + insn, insn_len); } int handle_ud(struct kvm_vcpu *vcpu) @@ -7491,8 +7993,10 @@ int handle_ud(struct kvm_vcpu *vcpu) int emul_type = EMULTYPE_TRAP_UD; char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; + int r; - if (unlikely(!kvm_can_emulate_insn(vcpu, emul_type, NULL, 0))) + r = kvm_check_emulate_insn(vcpu, emul_type, NULL, 0); + if (r != X86EMUL_CONTINUE) return 1; if (fep_flags && @@ -7507,7 +8011,7 @@ int handle_ud(struct kvm_vcpu *vcpu) return kvm_emulate_instruction(vcpu, emul_type); } -EXPORT_SYMBOL_GPL(handle_ud); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(handle_ud); static int vcpu_is_mmio_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t gpa, bool write) @@ -7529,8 +8033,8 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, bool write) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - u64 access = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0) - | (write ? PFERR_WRITE_MASK : 0); + u64 access = ((kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0) + | (write ? PFERR_WRITE_MASK : 0); /* * currently PKRU is only applied to ept enabled guest so @@ -7728,7 +8232,7 @@ static int emulator_read_write(struct x86_emulate_ctxt *ctxt, return rc; if (!vcpu->mmio_nr_fragments) - return rc; + return X86EMUL_CONTINUE; gpa = vcpu->mmio_fragments[0].gpa; @@ -7826,6 +8330,16 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (r < 0) return X86EMUL_UNHANDLEABLE; + + /* + * Mark the page dirty _before_ checking whether or not the CMPXCHG was + * successful, as the old value is written back on failure. Note, for + * live migration, this is unnecessarily conservative as CMPXCHG writes + * back the original value and the access is atomic, but KVM's ABI is + * that all writes are dirty logged, regardless of the value written. + */ + kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa)); + if (r) return X86EMUL_CMPXCHG_FAILED; @@ -7946,7 +8460,7 @@ static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) { - return static_call(kvm_x86_get_segment_base)(vcpu, seg); + return kvm_x86_call(get_segment_base)(vcpu, seg); } static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address) @@ -7959,12 +8473,11 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) if (!need_emulate_wbinvd(vcpu)) return X86EMUL_CONTINUE; - if (static_call(kvm_x86_has_wbinvd_exit)()) { + if (kvm_x86_call(has_wbinvd_exit)()) { int cpu = get_cpu(); cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); - on_each_cpu_mask(vcpu->arch.wbinvd_dirty_mask, - wbinvd_ipi, NULL, 1); + wbinvd_on_cpus_mask(vcpu->arch.wbinvd_dirty_mask); put_cpu(); cpumask_clear(vcpu->arch.wbinvd_dirty_mask); } else @@ -7977,7 +8490,7 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) kvm_emulate_wbinvd_noskip(vcpu); return kvm_skip_emulated_instruction(vcpu); } -EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_wbinvd); @@ -7986,10 +8499,9 @@ static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt) kvm_emulate_wbinvd_noskip(emul_to_vcpu(ctxt)); } -static void emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, - unsigned long *dest) +static unsigned long emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr) { - kvm_get_dr(emul_to_vcpu(ctxt), dr, dest); + return kvm_get_dr(emul_to_vcpu(ctxt), dr); } static int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, @@ -8064,27 +8576,27 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt) { - return static_call(kvm_x86_get_cpl)(emul_to_vcpu(ctxt)); + return kvm_x86_call(get_cpl)(emul_to_vcpu(ctxt)); } static void emulator_get_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - static_call(kvm_x86_get_gdt)(emul_to_vcpu(ctxt), dt); + kvm_x86_call(get_gdt)(emul_to_vcpu(ctxt), dt); } static void emulator_get_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - static_call(kvm_x86_get_idt)(emul_to_vcpu(ctxt), dt); + kvm_x86_call(get_idt)(emul_to_vcpu(ctxt), dt); } static void emulator_set_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - static_call(kvm_x86_set_gdt)(emul_to_vcpu(ctxt), dt); + kvm_x86_call(set_gdt)(emul_to_vcpu(ctxt), dt); } static void emulator_set_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - static_call(kvm_x86_set_idt)(emul_to_vcpu(ctxt), dt); + kvm_x86_call(set_idt)(emul_to_vcpu(ctxt), dt); } static unsigned long emulator_get_cached_segment_base( @@ -8165,7 +8677,7 @@ static int emulator_get_msr_with_filter(struct x86_emulate_ctxt *ctxt, struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int r; - r = kvm_get_msr_with_filter(vcpu, msr_index, pdata); + r = kvm_emulate_msr_read(vcpu, msr_index, pdata); if (r < 0) return X86EMUL_UNHANDLEABLE; @@ -8188,7 +8700,7 @@ static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt, struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int r; - r = kvm_set_msr_with_filter(vcpu, msr_index, data); + r = kvm_emulate_msr_write(vcpu, msr_index, data); if (r < 0) return X86EMUL_UNHANDLEABLE; @@ -8208,15 +8720,21 @@ static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt, static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata) { - return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); + /* + * Treat emulator accesses to the current shadow stack pointer as host- + * initiated, as they aren't true MSR accesses (SSP is a "just a reg"), + * and this API is used only for implicit accesses, i.e. not RDMSR, and + * so the index is fully KVM-controlled. + */ + if (unlikely(msr_index == MSR_KVM_INTERNAL_GUEST_SSP)) + return kvm_msr_read(emul_to_vcpu(ctxt), msr_index, pdata); + + return __kvm_emulate_msr_read(emul_to_vcpu(ctxt), msr_index, pdata); } -static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, - u32 pmc) +static int emulator_check_rdpmc_early(struct x86_emulate_ctxt *ctxt, u32 pmc) { - if (kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc)) - return 0; - return -EINVAL; + return kvm_pmu_check_rdpmc_early(emul_to_vcpu(ctxt), pmc); } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, @@ -8234,8 +8752,8 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt, struct x86_instruction_info *info, enum x86_intercept_stage stage) { - return static_call(kvm_x86_check_intercept)(emul_to_vcpu(ctxt), info, stage, - &ctxt->exception); + return kvm_x86_call(check_intercept)(emul_to_vcpu(ctxt), info, stage, + &ctxt->exception); } static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, @@ -8245,24 +8763,24 @@ static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, exact_only); } -static bool emulator_guest_has_long_mode(struct x86_emulate_ctxt *ctxt) -{ - return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_LM); -} - static bool emulator_guest_has_movbe(struct x86_emulate_ctxt *ctxt) { - return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_MOVBE); + return guest_cpu_cap_has(emul_to_vcpu(ctxt), X86_FEATURE_MOVBE); } static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt) { - return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR); + return guest_cpu_cap_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR); } static bool emulator_guest_has_rdpid(struct x86_emulate_ctxt *ctxt) { - return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID); + return guest_cpu_cap_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID); +} + +static bool emulator_guest_cpuid_is_intel_compatible(struct x86_emulate_ctxt *ctxt) +{ + return guest_cpuid_is_intel_compatible(emul_to_vcpu(ctxt)); } static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg) @@ -8277,7 +8795,7 @@ static void emulator_write_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg, ulon static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked) { - static_call(kvm_x86_set_nmi_mask)(emul_to_vcpu(ctxt), masked); + kvm_x86_call(set_nmi_mask)(emul_to_vcpu(ctxt), masked); } static bool emulator_is_smm(struct x86_emulate_ctxt *ctxt) @@ -8285,11 +8803,6 @@ static bool emulator_is_smm(struct x86_emulate_ctxt *ctxt) return is_smm(emul_to_vcpu(ctxt)); } -static bool emulator_is_guest_mode(struct x86_emulate_ctxt *ctxt) -{ - return is_guest_mode(emul_to_vcpu(ctxt)); -} - #ifndef CONFIG_KVM_SMM static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) { @@ -8303,6 +8816,14 @@ static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt) kvm_make_request(KVM_REQ_TRIPLE_FAULT, emul_to_vcpu(ctxt)); } +static int emulator_get_xcr(struct x86_emulate_ctxt *ctxt, u32 index, u64 *xcr) +{ + if (index != XCR_XFEATURE_ENABLED_MASK) + return 1; + *xcr = emul_to_vcpu(ctxt)->arch.xcr0; + return 0; +} + static int emulator_set_xcr(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr) { return __kvm_set_xcr(emul_to_vcpu(ctxt), index, xcr); @@ -8316,6 +8837,22 @@ static void emulator_vm_bugged(struct x86_emulate_ctxt *ctxt) kvm_vm_bugged(kvm); } +static gva_t emulator_get_untagged_addr(struct x86_emulate_ctxt *ctxt, + gva_t addr, unsigned int flags) +{ + if (!kvm_x86_ops.get_untagged_addr) + return addr; + + return kvm_x86_call(get_untagged_addr)(emul_to_vcpu(ctxt), + addr, flags); +} + +static bool emulator_is_canonical_addr(struct x86_emulate_ctxt *ctxt, + gva_t addr, unsigned int flags) +{ + return !is_noncanonical_address(addr, emul_to_vcpu(ctxt), flags); +} + static const struct x86_emulate_ops emulate_ops = { .vm_bugged = emulator_vm_bugged, .read_gpr = emulator_read_gpr, @@ -8344,28 +8881,30 @@ static const struct x86_emulate_ops emulate_ops = { .set_msr_with_filter = emulator_set_msr_with_filter, .get_msr_with_filter = emulator_get_msr_with_filter, .get_msr = emulator_get_msr, - .check_pmc = emulator_check_pmc, + .check_rdpmc_early = emulator_check_rdpmc_early, .read_pmc = emulator_read_pmc, .halt = emulator_halt, .wbinvd = emulator_wbinvd, .fix_hypercall = emulator_fix_hypercall, .intercept = emulator_intercept, .get_cpuid = emulator_get_cpuid, - .guest_has_long_mode = emulator_guest_has_long_mode, .guest_has_movbe = emulator_guest_has_movbe, .guest_has_fxsr = emulator_guest_has_fxsr, .guest_has_rdpid = emulator_guest_has_rdpid, + .guest_cpuid_is_intel_compatible = emulator_guest_cpuid_is_intel_compatible, .set_nmi_mask = emulator_set_nmi_mask, .is_smm = emulator_is_smm, - .is_guest_mode = emulator_is_guest_mode, .leave_smm = emulator_leave_smm, .triple_fault = emulator_triple_fault, + .get_xcr = emulator_get_xcr, .set_xcr = emulator_set_xcr, + .get_untagged_addr = emulator_get_untagged_addr, + .is_canonical_addr = emulator_is_canonical_addr, }; static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) { - u32 int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); + u32 int_shadow = kvm_x86_call(get_interrupt_shadow)(vcpu); /* * an sti; sti; sequence only disable interrupts for the first * instruction. So, if the last instruction, be it emulated or @@ -8376,7 +8915,7 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) if (int_shadow & mask) mask = 0; if (unlikely(int_shadow || mask)) { - static_call(kvm_x86_set_interrupt_shadow)(vcpu, mask); + kvm_x86_call(set_interrupt_shadow)(vcpu, mask); if (!mask) kvm_make_request(KVM_REQ_EVENT, vcpu); } @@ -8417,7 +8956,7 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int cs_db, cs_l; - static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); + kvm_x86_call(get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); ctxt->gpa_available = false; ctxt->eflags = kvm_get_rflags(vcpu); @@ -8458,7 +8997,7 @@ void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) kvm_set_rflags(vcpu, ctxt->eflags); } } -EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_inject_realmode_interrupt); static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, u8 ndata, u8 *insn_bytes, u8 insn_size) @@ -8473,9 +9012,8 @@ static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, */ memset(&info, 0, sizeof(info)); - static_call(kvm_x86_get_exit_info)(vcpu, (u32 *)&info[0], &info[1], - &info[2], (u32 *)&info[3], - (u32 *)&info[4]); + kvm_x86_call(get_exit_info)(vcpu, (u32 *)&info[0], &info[1], &info[2], + (u32 *)&info[3], (u32 *)&info[4]); run->exit_reason = KVM_EXIT_INTERNAL_ERROR; run->emulation_failure.suberror = KVM_INTERNAL_ERROR_EMULATION; @@ -8524,13 +9062,47 @@ void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, { prepare_emulation_failure_exit(vcpu, data, ndata, NULL, 0); } -EXPORT_SYMBOL_GPL(__kvm_prepare_emulation_failure_exit); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_prepare_emulation_failure_exit); void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu) { __kvm_prepare_emulation_failure_exit(vcpu, NULL, 0); } -EXPORT_SYMBOL_GPL(kvm_prepare_emulation_failure_exit); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_prepare_emulation_failure_exit); + +void kvm_prepare_event_vectoring_exit(struct kvm_vcpu *vcpu, gpa_t gpa) +{ + u32 reason, intr_info, error_code; + struct kvm_run *run = vcpu->run; + u64 info1, info2; + int ndata = 0; + + kvm_x86_call(get_exit_info)(vcpu, &reason, &info1, &info2, + &intr_info, &error_code); + + run->internal.data[ndata++] = info2; + run->internal.data[ndata++] = reason; + run->internal.data[ndata++] = info1; + run->internal.data[ndata++] = gpa; + run->internal.data[ndata++] = vcpu->arch.last_vmentry_cpu; + + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; + run->internal.ndata = ndata; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_prepare_event_vectoring_exit); + +void kvm_prepare_unexpected_reason_exit(struct kvm_vcpu *vcpu, u64 exit_reason) +{ + vcpu_unimpl(vcpu, "unexpected exit reason 0x%llx\n", exit_reason); + + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; + vcpu->run->internal.ndata = 2; + vcpu->run->internal.data[0] = exit_reason; + vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_prepare_unexpected_reason_exit); static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) { @@ -8552,7 +9124,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) kvm_queue_exception(vcpu, UD_VECTOR); - if (!is_guest_mode(vcpu) && static_call(kvm_x86_get_cpl)(vcpu) == 0) { + if (!is_guest_mode(vcpu) && kvm_x86_call(get_cpl)(vcpu) == 0) { prepare_emulation_ctxt_failure_exit(vcpu); return 0; } @@ -8560,125 +9132,41 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) return 1; } -static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - int emulation_type) +static bool kvm_unprotect_and_retry_on_failure(struct kvm_vcpu *vcpu, + gpa_t cr2_or_gpa, + int emulation_type) { - gpa_t gpa = cr2_or_gpa; - kvm_pfn_t pfn; - if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) return false; - if (WARN_ON_ONCE(is_guest_mode(vcpu)) || - WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF))) - return false; - - if (!vcpu->arch.mmu->root_role.direct) { - /* - * Write permission should be allowed since only - * write access need to be emulated. - */ - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); - - /* - * If the mapping is invalid in guest, let cpu retry - * it to generate fault. - */ - if (gpa == INVALID_GPA) - return true; - } - - /* - * Do not retry the unhandleable instruction if it faults on the - * readonly host memory, otherwise it will goto a infinite loop: - * retry instruction -> write #PF -> emulation fail -> retry - * instruction -> ... - */ - pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa)); - /* - * If the instruction failed on the error pfn, it can not be fixed, - * report the error to userspace. + * If the failed instruction faulted on an access to page tables that + * are used to translate any part of the instruction, KVM can't resolve + * the issue by unprotecting the gfn, as zapping the shadow page will + * result in the instruction taking a !PRESENT page fault and thus put + * the vCPU into an infinite loop of page faults. E.g. KVM will create + * a SPTE and write-protect the gfn to resolve the !PRESENT fault, and + * then zap the SPTE to unprotect the gfn, and then do it all over + * again. Report the error to userspace. */ - if (is_error_noslot_pfn(pfn)) + if (emulation_type & EMULTYPE_WRITE_PF_TO_SP) return false; - kvm_release_pfn_clean(pfn); - - /* The instructions are well-emulated on direct mmu. */ - if (vcpu->arch.mmu->root_role.direct) { - unsigned int indirect_shadow_pages; - - write_lock(&vcpu->kvm->mmu_lock); - indirect_shadow_pages = vcpu->kvm->arch.indirect_shadow_pages; - write_unlock(&vcpu->kvm->mmu_lock); - - if (indirect_shadow_pages) - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); - - return true; - } - /* - * if emulation was due to access to shadowed page table - * and it failed try to unshadow page and re-enter the - * guest to let CPU execute the instruction. + * If emulation may have been triggered by a write to a shadowed page + * table, unprotect the gfn (zap any relevant SPTEs) and re-enter the + * guest to let the CPU re-execute the instruction in the hope that the + * CPU can cleanly execute the instruction that KVM failed to emulate. */ - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + __kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa, true); /* - * If the access faults on its page table, it can not - * be fixed by unprotecting shadow page and it should - * be reported to userspace. + * Retry even if _this_ vCPU didn't unprotect the gfn, as it's possible + * all SPTEs were already zapped by a different task. The alternative + * is to report the error to userspace and likely terminate the guest, + * and the last_retry_{eip,addr} checks will prevent retrying the page + * fault indefinitely, i.e. there's nothing to lose by retrying. */ - return !(emulation_type & EMULTYPE_WRITE_PF_TO_SP); -} - -static bool retry_instruction(struct x86_emulate_ctxt *ctxt, - gpa_t cr2_or_gpa, int emulation_type) -{ - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa; - - last_retry_eip = vcpu->arch.last_retry_eip; - last_retry_addr = vcpu->arch.last_retry_addr; - - /* - * If the emulation is caused by #PF and it is non-page_table - * writing instruction, it means the VM-EXIT is caused by shadow - * page protected, we can zap the shadow page and retry this - * instruction directly. - * - * Note: if the guest uses a non-page-table modifying instruction - * on the PDE that points to the instruction, then we will unmap - * the instruction and go to an infinite loop. So, we cache the - * last retried eip and the last fault address, if we meet the eip - * and the address again, we can break out of the potential infinite - * loop. - */ - vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0; - - if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) - return false; - - if (WARN_ON_ONCE(is_guest_mode(vcpu)) || - WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF))) - return false; - - if (x86_page_table_writing_insn(ctxt)) - return false; - - if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa) - return false; - - vcpu->arch.last_retry_eip = ctxt->eip; - vcpu->arch.last_retry_addr = cr2_or_gpa; - - if (!vcpu->arch.mmu->root_role.direct) - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); - - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); - return true; } @@ -8717,14 +9205,14 @@ static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu) int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) { - unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); + unsigned long rflags = kvm_x86_call(get_rflags)(vcpu); int r; - r = static_call(kvm_x86_skip_emulated_instruction)(vcpu); + r = kvm_x86_call(skip_emulated_instruction)(vcpu); if (unlikely(!r)) return 0; - kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS); + kvm_pmu_instruction_retired(vcpu); /* * rflags is the old, "raw" value of the flags. The new value has @@ -8738,23 +9226,21 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) r = kvm_vcpu_do_singlestep(vcpu); return r; } -EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_skip_emulated_instruction); static bool kvm_is_code_breakpoint_inhibited(struct kvm_vcpu *vcpu) { - u32 shadow; - if (kvm_get_rflags(vcpu) & X86_EFLAGS_RF) return true; /* - * Intel CPUs inhibit code #DBs when MOV/POP SS blocking is active, - * but AMD CPUs do not. MOV/POP SS blocking is rare, check that first - * to avoid the relatively expensive CPUID lookup. + * Intel compatible CPUs inhibit code #DBs when MOV/POP SS blocking is + * active, but AMD compatible CPUs do not. */ - shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); - return (shadow & KVM_X86_SHADOW_INT_MOV_SS) && - guest_cpuid_is_intel(vcpu); + if (!guest_cpuid_is_intel_compatible(vcpu)) + return false; + + return kvm_x86_call(get_interrupt_shadow)(vcpu) & KVM_X86_SHADOW_INT_MOV_SS; } static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu, @@ -8846,6 +9332,23 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) return false; } +static bool is_soft_int_instruction(struct x86_emulate_ctxt *ctxt, + int emulation_type) +{ + u8 vector = EMULTYPE_GET_SOFT_INT_VECTOR(emulation_type); + + switch (ctxt->b) { + case 0xcc: + return vector == BP_VECTOR; + case 0xcd: + return vector == ctxt->src.val; + case 0xce: + return vector == OF_VECTOR; + default: + return false; + } +} + /* * Decode an instruction for emulation. The caller is responsible for handling * code breakpoints. Note, manually detecting code breakpoints is unnecessary @@ -8871,7 +9374,7 @@ int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, return r; } -EXPORT_SYMBOL_GPL(x86_decode_emulated_instruction); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(x86_decode_emulated_instruction); int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len) @@ -8880,10 +9383,30 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; bool writeback = true; - if (unlikely(!kvm_can_emulate_insn(vcpu, emulation_type, insn, insn_len))) - return 1; + if ((emulation_type & EMULTYPE_ALLOW_RETRY_PF) && + (WARN_ON_ONCE(is_guest_mode(vcpu)) || + WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF)))) + emulation_type &= ~EMULTYPE_ALLOW_RETRY_PF; + + r = kvm_check_emulate_insn(vcpu, emulation_type, insn, insn_len); + if (r != X86EMUL_CONTINUE) { + if (r == X86EMUL_RETRY_INSTR || r == X86EMUL_PROPAGATE_FAULT) + return 1; + + if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, + emulation_type)) + return 1; - vcpu->arch.l1tf_flush_l1d = true; + if (r == X86EMUL_UNHANDLEABLE_VECTORING) { + kvm_prepare_event_vectoring_exit(vcpu, cr2_or_gpa); + return 0; + } + + WARN_ON_ONCE(r != X86EMUL_UNHANDLEABLE); + return handle_emulation_failure(vcpu, emulation_type); + } + + kvm_request_l1tf_flush_l1d(); if (!(emulation_type & EMULTYPE_NO_DECODE)) { kvm_clear_exception_queue(vcpu); @@ -8904,8 +9427,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, kvm_queue_exception(vcpu, UD_VECTOR); return 1; } - if (reexecute_instruction(vcpu, cr2_or_gpa, - emulation_type)) + if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, + emulation_type)) return 1; if (ctxt->have_exception && @@ -8936,6 +9459,10 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * injecting single-step #DBs. */ if (emulation_type & EMULTYPE_SKIP) { + if (emulation_type & EMULTYPE_SKIP_SOFT_INT && + !is_soft_int_instruction(ctxt, emulation_type)) + return 0; + if (ctxt->mode != X86EMUL_MODE_PROT64) ctxt->eip = (u32)ctxt->_eip; else @@ -8952,7 +9479,15 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, return 1; } - if (retry_instruction(ctxt, cr2_or_gpa, emulation_type)) + /* + * If emulation was caused by a write-protection #PF on a non-page_table + * writing instruction, try to unprotect the gfn, i.e. zap shadow pages, + * and retry the instruction, as the vCPU is likely no longer using the + * gfn as a page table. + */ + if ((emulation_type & EMULTYPE_ALLOW_RETRY_PF) && + !x86_page_table_writing_insn(ctxt) && + kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa)) return 1; /* this is needed for vmware backdoor interface to work since it @@ -8977,13 +9512,21 @@ restart: ctxt->exception.address = 0; } - r = x86_emulate_insn(ctxt); + /* + * Check L1's instruction intercepts when emulating instructions for + * L2, unless KVM is re-emulating a previously decoded instruction, + * e.g. to complete userspace I/O, in which case KVM has already + * checked the intercepts. + */ + r = x86_emulate_insn(ctxt, is_guest_mode(vcpu) && + !(emulation_type & EMULTYPE_NO_DECODE)); if (r == EMULATION_INTERCEPTED) return 1; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2_or_gpa, emulation_type)) + if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, + emulation_type)) return 1; return handle_emulation_failure(vcpu, emulation_type); @@ -9020,7 +9563,7 @@ restart: writeback: if (writeback) { - unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); + unsigned long rflags = kvm_x86_call(get_rflags)(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; @@ -9031,13 +9574,13 @@ writeback: */ if (!ctxt->have_exception || exception_type(ctxt->exception.vector) == EXCPT_TRAP) { - kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS); + kvm_pmu_instruction_retired(vcpu); if (ctxt->is_branch) - kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); + kvm_pmu_branch_retired(vcpu); kvm_rip_write(vcpu, ctxt->eip); if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) r = kvm_vcpu_do_singlestep(vcpu); - static_call_cond(kvm_x86_update_emulated_instruction)(vcpu); + kvm_x86_call(update_emulated_instruction)(vcpu); __kvm_set_rflags(vcpu, ctxt->eflags); } @@ -9059,14 +9602,14 @@ int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type) { return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0); } -EXPORT_SYMBOL_GPL(kvm_emulate_instruction); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_instruction); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, void *insn, int insn_len) { return x86_emulate_instruction(vcpu, 0, 0, insn, insn_len); } -EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_instruction_from_buffer); static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu) { @@ -9078,7 +9621,7 @@ 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))) + if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip))) return 1; return kvm_skip_emulated_instruction(vcpu); @@ -9103,7 +9646,7 @@ static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, complete_fast_pio_out_port_0x7e; kvm_skip_emulated_instruction(vcpu); } else { - vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu); + vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu); vcpu->arch.complete_userspace_io = complete_fast_pio_out; } return 0; @@ -9116,7 +9659,7 @@ 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))) { + if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip))) { vcpu->arch.pio.count = 0; return 1; } @@ -9145,7 +9688,7 @@ 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.cui_linear_rip = kvm_get_linear_rip(vcpu); vcpu->arch.complete_userspace_io = complete_fast_pio_in; return 0; @@ -9161,7 +9704,7 @@ int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in) ret = kvm_fast_pio_out(vcpu, size, port); return ret && kvm_skip_emulated_instruction(vcpu); } -EXPORT_SYMBOL_GPL(kvm_fast_pio); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_fast_pio); static int kvmclock_cpu_down_prep(unsigned int cpu) { @@ -9172,7 +9715,7 @@ static int kvmclock_cpu_down_prep(unsigned int cpu) static void tsc_khz_changed(void *data) { struct cpufreq_freqs *freq = data; - unsigned long khz = 0; + unsigned long khz; WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_CONSTANT_TSC)); @@ -9436,7 +9979,7 @@ static int kvm_x86_check_processor_compatibility(void) __cr4_reserved_bits(cpu_has, &boot_cpu_data)) return -EIO; - return static_call(kvm_x86_check_processor_compatibility)(); + return kvm_x86_call(check_processor_compatibility)(); } static void kvm_x86_check_cpu_compat(void *ret) @@ -9444,12 +9987,14 @@ static void kvm_x86_check_cpu_compat(void *ret) *(int *)ret = kvm_x86_check_processor_compatibility(); } -static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) +int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) { u64 host_pat; int r, cpu; - if (kvm_x86_ops.hardware_enable) { + guard(mutex)(&vendor_module_lock); + + if (kvm_x86_ops.enable_virtualization_cpu) { pr_err("already loaded vendor module '%s'\n", kvm_x86_ops.name); return -EEXIST; } @@ -9476,46 +10021,68 @@ static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) * with an exception. PAT[0] is set to WB on RESET and also by the * kernel, i.e. failure indicates a kernel bug or broken firmware. */ - if (rdmsrl_safe(MSR_IA32_CR_PAT, &host_pat) || + if (rdmsrq_safe(MSR_IA32_CR_PAT, &host_pat) || (host_pat & GENMASK(2, 0)) != 6) { pr_err("host PAT[0] is not WB\n"); return -EIO; } + if (boot_cpu_has(X86_FEATURE_SHSTK) || boot_cpu_has(X86_FEATURE_IBT)) { + rdmsrq(MSR_IA32_S_CET, kvm_host.s_cet); + /* + * Linux doesn't yet support supervisor shadow stacks (SSS), so + * KVM doesn't save/restore the associated MSRs, i.e. KVM may + * clobber the host values. Yell and refuse to load if SSS is + * unexpectedly enabled, e.g. to avoid crashing the host. + */ + if (WARN_ON_ONCE(kvm_host.s_cet & CET_SHSTK_EN)) + return -EIO; + } + + memset(&kvm_caps, 0, sizeof(kvm_caps)); + x86_emulator_cache = kvm_alloc_emulator_cache(); if (!x86_emulator_cache) { pr_err("failed to allocate cache for x86 emulator\n"); return -ENOMEM; } - user_return_msrs = alloc_percpu(struct kvm_user_return_msrs); - if (!user_return_msrs) { - pr_err("failed to allocate percpu kvm_user_return_msrs\n"); - r = -ENOMEM; - goto out_free_x86_emulator_cache; - } - kvm_nr_uret_msrs = 0; - r = kvm_mmu_vendor_module_init(); if (r) - goto out_free_percpu; + goto out_free_x86_emulator_cache; + + kvm_caps.supported_vm_types = BIT(KVM_X86_DEFAULT_VM); + kvm_caps.supported_mce_cap = MCG_CTL_P | MCG_SER_P; if (boot_cpu_has(X86_FEATURE_XSAVE)) { - host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - kvm_caps.supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0; + kvm_host.xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); + kvm_caps.supported_xcr0 = kvm_host.xcr0 & KVM_SUPPORTED_XCR0; + } + + if (boot_cpu_has(X86_FEATURE_XSAVES)) { + rdmsrq(MSR_IA32_XSS, kvm_host.xss); + kvm_caps.supported_xss = kvm_host.xss & KVM_SUPPORTED_XSS; } - rdmsrl_safe(MSR_EFER, &host_efer); + kvm_caps.supported_quirks = KVM_X86_VALID_QUIRKS; + kvm_caps.inapplicable_quirks = KVM_X86_CONDITIONAL_QUIRKS; - if (boot_cpu_has(X86_FEATURE_XSAVES)) - rdmsrl(MSR_IA32_XSS, host_xss); + rdmsrq_safe(MSR_EFER, &kvm_host.efer); kvm_init_pmu_capability(ops->pmu_ops); + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrq(MSR_IA32_ARCH_CAPABILITIES, kvm_host.arch_capabilities); + + WARN_ON_ONCE(kvm_nr_uret_msrs); + r = ops->hardware_setup(); if (r != 0) goto out_mmu_exit; + enable_device_posted_irqs &= enable_apicv && + irq_remapping_cap(IRQ_POSTING_CAP); + kvm_ops_update(ops); for_each_online_cpu(cpu) { @@ -9542,12 +10109,25 @@ static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) kvm_register_perf_callbacks(ops->handle_intel_pt_intr); + if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled) + kvm_caps.supported_vm_types |= BIT(KVM_X86_SW_PROTECTED_VM); + + /* KVM always ignores guest PAT for shadow paging. */ + if (!tdp_enabled) + kvm_caps.supported_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT; + if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) kvm_caps.supported_xss = 0; -#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) - cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); -#undef __kvm_cpu_cap_has + if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && + !kvm_cpu_cap_has(X86_FEATURE_IBT)) + kvm_caps.supported_xss &= ~XFEATURE_MASK_CET_ALL; + + if ((kvm_caps.supported_xss & XFEATURE_MASK_CET_ALL) != XFEATURE_MASK_CET_ALL) { + kvm_cpu_cap_clear(X86_FEATURE_SHSTK); + kvm_cpu_cap_clear(X86_FEATURE_IBT); + kvm_caps.supported_xss &= ~XFEATURE_MASK_CET_ALL; + } if (kvm_caps.has_tsc_control) { /* @@ -9565,28 +10145,16 @@ static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) return 0; out_unwind_ops: - kvm_x86_ops.hardware_enable = NULL; - static_call(kvm_x86_hardware_unsetup)(); + kvm_x86_ops.enable_virtualization_cpu = NULL; + kvm_x86_call(hardware_unsetup)(); out_mmu_exit: + kvm_destroy_user_return_msrs(); kvm_mmu_vendor_module_exit(); -out_free_percpu: - free_percpu(user_return_msrs); out_free_x86_emulator_cache: kmem_cache_destroy(x86_emulator_cache); return r; } - -int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) -{ - int r; - - mutex_lock(&vendor_module_lock); - r = __kvm_x86_vendor_init(ops); - mutex_unlock(&vendor_module_lock); - - return r; -} -EXPORT_SYMBOL_GPL(kvm_x86_vendor_init); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_x86_vendor_init); void kvm_x86_vendor_exit(void) { @@ -9608,64 +10176,19 @@ void kvm_x86_vendor_exit(void) irq_work_sync(&pvclock_irq_work); cancel_work_sync(&pvclock_gtod_work); #endif - static_call(kvm_x86_hardware_unsetup)(); + kvm_x86_call(hardware_unsetup)(); + kvm_destroy_user_return_msrs(); kvm_mmu_vendor_module_exit(); - free_percpu(user_return_msrs); kmem_cache_destroy(x86_emulator_cache); #ifdef CONFIG_KVM_XEN static_key_deferred_flush(&kvm_xen_enabled); WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key)); #endif mutex_lock(&vendor_module_lock); - kvm_x86_ops.hardware_enable = NULL; + kvm_x86_ops.enable_virtualization_cpu = NULL; mutex_unlock(&vendor_module_lock); } -EXPORT_SYMBOL_GPL(kvm_x86_vendor_exit); - -static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) -{ - /* - * The vCPU has halted, e.g. executed HLT. Update the run state if the - * local APIC is in-kernel, the run loop will detect the non-runnable - * state and halt the vCPU. Exit to userspace if the local APIC is - * managed by userspace, in which case userspace is responsible for - * handling wake events. - */ - ++vcpu->stat.halt_exits; - if (lapic_in_kernel(vcpu)) { - vcpu->arch.mp_state = state; - return 1; - } else { - vcpu->run->exit_reason = reason; - return 0; - } -} - -int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu) -{ - return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); -} -EXPORT_SYMBOL_GPL(kvm_emulate_halt_noskip); - -int kvm_emulate_halt(struct kvm_vcpu *vcpu) -{ - int ret = kvm_skip_emulated_instruction(vcpu); - /* - * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered - * KVM_EXIT_DEBUG here. - */ - return kvm_emulate_halt_noskip(vcpu) && ret; -} -EXPORT_SYMBOL_GPL(kvm_emulate_halt); - -int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) -{ - int ret = kvm_skip_emulated_instruction(vcpu); - - return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, - KVM_EXIT_AP_RESET_HOLD) && ret; -} -EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_x86_vendor_exit); #ifdef CONFIG_X86_64 static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, @@ -9729,20 +10252,25 @@ bool kvm_apicv_activated(struct kvm *kvm) { return (READ_ONCE(kvm->arch.apicv_inhibit_reasons) == 0); } -EXPORT_SYMBOL_GPL(kvm_apicv_activated); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_apicv_activated); bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu) { ulong vm_reasons = READ_ONCE(vcpu->kvm->arch.apicv_inhibit_reasons); - ulong vcpu_reasons = static_call(kvm_x86_vcpu_get_apicv_inhibit_reasons)(vcpu); + ulong vcpu_reasons = + kvm_x86_call(vcpu_get_apicv_inhibit_reasons)(vcpu); return (vm_reasons | vcpu_reasons) == 0; } -EXPORT_SYMBOL_GPL(kvm_vcpu_apicv_activated); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_apicv_activated); static void set_or_clear_apicv_inhibit(unsigned long *inhibits, enum kvm_apicv_inhibit reason, bool set) { + const struct trace_print_flags apicv_inhibits[] = { APICV_INHIBIT_REASONS }; + + BUILD_BUG_ON(ARRAY_SIZE(apicv_inhibits) != NR_APICV_INHIBIT_REASONS); + if (set) __set_bit(reason, inhibits); else @@ -9753,15 +10281,12 @@ static void set_or_clear_apicv_inhibit(unsigned long *inhibits, static void kvm_apicv_init(struct kvm *kvm) { - unsigned long *inhibits = &kvm->arch.apicv_inhibit_reasons; + enum kvm_apicv_inhibit reason = enable_apicv ? APICV_INHIBIT_REASON_ABSENT : + APICV_INHIBIT_REASON_DISABLED; - init_rwsem(&kvm->arch.apicv_update_lock); - - set_or_clear_apicv_inhibit(inhibits, APICV_INHIBIT_REASON_ABSENT, true); + set_or_clear_apicv_inhibit(&kvm->arch.apicv_inhibit_reasons, reason, true); - if (!enable_apicv) - set_or_clear_apicv_inhibit(inhibits, - APICV_INHIBIT_REASON_DISABLE, true); + init_rwsem(&kvm->arch.apicv_update_lock); } static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) @@ -9777,8 +10302,11 @@ static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) rcu_read_lock(); map = rcu_dereference(vcpu->kvm->arch.apic_map); - if (likely(map) && dest_id <= map->max_apic_id && map->phys_map[dest_id]) - target = map->phys_map[dest_id]->vcpu; + if (likely(map) && dest_id <= map->max_apic_id) { + dest_id = array_index_nospec(dest_id, map->max_apic_id + 1); + if (map->phys_map[dest_id]) + target = map->phys_map[dest_id]->vcpu; + } rcu_read_unlock(); @@ -9802,33 +10330,27 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu) { u64 ret = vcpu->run->hypercall.ret; - if (!is_64_bit_mode(vcpu)) + if (!is_64_bit_hypercall(vcpu)) ret = (u32)ret; kvm_rax_write(vcpu, ret); - ++vcpu->stat.hypercalls; return kvm_skip_emulated_instruction(vcpu); } -int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) +int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, int cpl, + int (*complete_hypercall)(struct kvm_vcpu *)) { - unsigned long nr, a0, a1, a2, a3, ret; - int op_64_bit; + unsigned long ret; + unsigned long nr = kvm_rax_read(vcpu); + unsigned long a0 = kvm_rbx_read(vcpu); + unsigned long a1 = kvm_rcx_read(vcpu); + unsigned long a2 = kvm_rdx_read(vcpu); + unsigned long a3 = kvm_rsi_read(vcpu); + int op_64_bit = is_64_bit_hypercall(vcpu); - if (kvm_xen_hypercall_enabled(vcpu->kvm)) - return kvm_xen_hypercall(vcpu); - - if (kvm_hv_hypercall_enabled(vcpu)) - return kvm_hv_hypercall(vcpu); - - nr = kvm_rax_read(vcpu); - a0 = kvm_rbx_read(vcpu); - a1 = kvm_rcx_read(vcpu); - a2 = kvm_rdx_read(vcpu); - a3 = kvm_rsi_read(vcpu); + ++vcpu->stat.hypercalls; trace_kvm_hypercall(nr, a0, a1, a2, a3); - op_64_bit = is_64_bit_hypercall(vcpu); if (!op_64_bit) { nr &= 0xFFFFFFFF; a0 &= 0xFFFFFFFF; @@ -9837,7 +10359,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) a3 &= 0xFFFFFFFF; } - if (static_call(kvm_x86_get_cpl)(vcpu) != 0) { + if (cpl) { ret = -KVM_EPERM; goto out; } @@ -9878,7 +10400,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) u64 gpa = a0, npages = a1, attrs = a2; ret = -KVM_ENOSYS; - if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) + if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) break; if (!PAGE_ALIGNED(gpa) || !npages || @@ -9889,6 +10411,13 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; + /* + * In principle this should have been -KVM_ENOSYS, but userspace (QEMU <=9.2) + * assumed that vcpu->run->hypercall.ret is never changed by KVM and thus that + * it was always zero on KVM_EXIT_HYPERCALL. Since KVM is now overwriting + * vcpu->run->hypercall.ret, ensuring that it is zero to not break QEMU. + */ + vcpu->run->hypercall.ret = 0; vcpu->run->hypercall.args[0] = gpa; vcpu->run->hypercall.args[1] = npages; vcpu->run->hypercall.args[2] = attrs; @@ -9897,22 +10426,32 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) vcpu->run->hypercall.flags |= KVM_EXIT_HYPERCALL_LONG_MODE; WARN_ON_ONCE(vcpu->run->hypercall.flags & KVM_EXIT_HYPERCALL_MBZ); - vcpu->arch.complete_userspace_io = complete_hypercall_exit; + vcpu->arch.complete_userspace_io = complete_hypercall; return 0; } default: ret = -KVM_ENOSYS; break; } + out: - if (!op_64_bit) - ret = (u32)ret; - kvm_rax_write(vcpu, ret); + vcpu->run->hypercall.ret = ret; + return 1; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(____kvm_emulate_hypercall); - ++vcpu->stat.hypercalls; - return kvm_skip_emulated_instruction(vcpu); +int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) +{ + if (kvm_xen_hypercall_enabled(vcpu->kvm)) + return kvm_xen_hypercall(vcpu); + + if (kvm_hv_hypercall_enabled(vcpu)) + return kvm_hv_hypercall(vcpu); + + return __kvm_emulate_hypercall(vcpu, kvm_x86_call(get_cpl)(vcpu), + complete_hypercall_exit); } -EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_hypercall); static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) { @@ -9931,7 +10470,7 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) return X86EMUL_PROPAGATE_FAULT; } - static_call(kvm_x86_patch_hypercall)(vcpu, instruction); + kvm_x86_call(patch_hypercall)(vcpu, instruction); return emulator_write_emulated(ctxt, rip, instruction, 3, &ctxt->exception); @@ -9948,9 +10487,9 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; - kvm_run->if_flag = static_call(kvm_x86_get_if_flag)(vcpu); + kvm_run->if_flag = kvm_x86_call(get_if_flag)(vcpu); kvm_run->cr8 = kvm_get_cr8(vcpu); - kvm_run->apic_base = kvm_get_apic_base(vcpu); + kvm_run->apic_base = vcpu->arch.apic_base; kvm_run->ready_for_interrupt_injection = pic_in_kernel(vcpu->kvm) || @@ -9958,6 +10497,8 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) if (is_smm(vcpu)) kvm_run->flags |= KVM_RUN_X86_SMM; + if (is_guest_mode(vcpu)) + kvm_run->flags |= KVM_RUN_X86_GUEST_MODE; } static void update_cr8_intercept(struct kvm_vcpu *vcpu) @@ -9983,7 +10524,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) tpr = kvm_lapic_get_cr8(vcpu); - static_call(kvm_x86_update_cr8_intercept)(vcpu, tpr, max_irr); + kvm_x86_call(update_cr8_intercept)(vcpu, tpr, max_irr); } @@ -10013,7 +10554,7 @@ static void kvm_inject_exception(struct kvm_vcpu *vcpu) vcpu->arch.exception.error_code, vcpu->arch.exception.injected); - static_call(kvm_x86_inject_exception)(vcpu); + kvm_x86_call(inject_exception)(vcpu); } /* @@ -10041,7 +10582,7 @@ static void kvm_inject_exception(struct kvm_vcpu *vcpu) * * But, if a VM-Exit occurs during instruction execution, and KVM does NOT skip * the instruction or inject an exception, then KVM can incorrecty inject a new - * asynchrounous event if the event became pending after the CPU fetched the + * asynchronous event if the event became pending after the CPU fetched the * instruction (in the guest). E.g. if a page fault (#PF, #NPF, EPT violation) * occurs and is resolved by KVM, a coincident NMI, SMI, IRQ, etc... can be * injected on the restarted instruction instead of being deferred until the @@ -10062,7 +10603,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, int r; /* - * Process nested events first, as nested VM-Exit supercedes event + * Process nested events first, as nested VM-Exit supersedes event * re-injection. If there's an event queued for re-injection, it will * be saved into the appropriate vmc{b,s}12 fields on nested VM-Exit. */ @@ -10099,9 +10640,9 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, else if (kvm_is_exception_pending(vcpu)) ; /* see above */ else if (vcpu->arch.nmi_injected) - static_call(kvm_x86_inject_nmi)(vcpu); + kvm_x86_call(inject_nmi)(vcpu); else if (vcpu->arch.interrupt.injected) - static_call(kvm_x86_inject_irq)(vcpu, true); + kvm_x86_call(inject_irq)(vcpu, true); /* * Exceptions that morph to VM-Exits are handled above, and pending @@ -10186,7 +10727,8 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, */ #ifdef CONFIG_KVM_SMM if (vcpu->arch.smi_pending) { - r = can_inject ? static_call(kvm_x86_smi_allowed)(vcpu, true) : -EBUSY; + r = can_inject ? kvm_x86_call(smi_allowed)(vcpu, true) : + -EBUSY; if (r < 0) goto out; if (r) { @@ -10195,27 +10737,29 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, enter_smm(vcpu); can_inject = false; } else - static_call(kvm_x86_enable_smi_window)(vcpu); + kvm_x86_call(enable_smi_window)(vcpu); } #endif if (vcpu->arch.nmi_pending) { - r = can_inject ? static_call(kvm_x86_nmi_allowed)(vcpu, true) : -EBUSY; + r = can_inject ? kvm_x86_call(nmi_allowed)(vcpu, true) : + -EBUSY; if (r < 0) goto out; if (r) { --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; - static_call(kvm_x86_inject_nmi)(vcpu); + kvm_x86_call(inject_nmi)(vcpu); can_inject = false; - WARN_ON(static_call(kvm_x86_nmi_allowed)(vcpu, true) < 0); + WARN_ON(kvm_x86_call(nmi_allowed)(vcpu, true) < 0); } if (vcpu->arch.nmi_pending) - static_call(kvm_x86_enable_nmi_window)(vcpu); + kvm_x86_call(enable_nmi_window)(vcpu); } if (kvm_cpu_has_injectable_intr(vcpu)) { - r = can_inject ? static_call(kvm_x86_interrupt_allowed)(vcpu, true) : -EBUSY; + r = can_inject ? kvm_x86_call(interrupt_allowed)(vcpu, true) : + -EBUSY; if (r < 0) goto out; if (r) { @@ -10223,17 +10767,17 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, if (!WARN_ON_ONCE(irq == -1)) { kvm_queue_interrupt(vcpu, irq, false); - static_call(kvm_x86_inject_irq)(vcpu, false); - WARN_ON(static_call(kvm_x86_interrupt_allowed)(vcpu, true) < 0); + kvm_x86_call(inject_irq)(vcpu, false); + WARN_ON(kvm_x86_call(interrupt_allowed)(vcpu, true) < 0); } } if (kvm_cpu_has_injectable_intr(vcpu)) - static_call(kvm_x86_enable_irq_window)(vcpu); + kvm_x86_call(enable_irq_window)(vcpu); } if (is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->has_events && - kvm_x86_ops.nested_ops->has_events(vcpu)) + kvm_x86_ops.nested_ops->has_events(vcpu, true)) *req_immediate_exit = true; /* @@ -10274,7 +10818,7 @@ static void process_nmi(struct kvm_vcpu *vcpu) * blocks NMIs). KVM will immediately inject one of the two NMIs, and * will request an NMI window to handle the second NMI. */ - if (static_call(kvm_x86_get_nmi_mask)(vcpu) || vcpu->arch.nmi_injected) + if (kvm_x86_call(get_nmi_mask)(vcpu) || vcpu->arch.nmi_injected) limit = 1; else limit = 2; @@ -10283,14 +10827,14 @@ static void process_nmi(struct kvm_vcpu *vcpu) * Adjust the limit to account for pending virtual NMIs, which aren't * tracked in vcpu->arch.nmi_pending. */ - if (static_call(kvm_x86_is_vnmi_pending)(vcpu)) + if (kvm_x86_call(is_vnmi_pending)(vcpu)) limit--; vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit); if (vcpu->arch.nmi_pending && - (static_call(kvm_x86_set_vnmi_pending)(vcpu))) + (kvm_x86_call(set_vnmi_pending)(vcpu))) vcpu->arch.nmi_pending--; if (vcpu->arch.nmi_pending) @@ -10301,7 +10845,7 @@ static void process_nmi(struct kvm_vcpu *vcpu) int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu) { return vcpu->arch.nmi_pending + - static_call(kvm_x86_is_vnmi_pending)(vcpu); + kvm_x86_call(is_vnmi_pending)(vcpu); } void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, @@ -10335,7 +10879,7 @@ void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) apic->apicv_active = activate; kvm_apic_update_apicv(vcpu); - static_call(kvm_x86_refresh_apicv_exec_ctrl)(vcpu); + kvm_x86_call(refresh_apicv_exec_ctrl)(vcpu); /* * When APICv gets disabled, we may still have injected interrupts @@ -10350,7 +10894,7 @@ out: preempt_enable(); up_read(&vcpu->kvm->arch.apicv_update_lock); } -EXPORT_SYMBOL_GPL(__kvm_vcpu_update_apicv); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_vcpu_update_apicv); static void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) { @@ -10362,8 +10906,8 @@ static void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) * deleted if any vCPU has xAPIC virtualization and x2APIC enabled, but * and hardware doesn't support x2APIC virtualization. E.g. some AMD * CPUs support AVIC but not x2APIC. KVM still allows enabling AVIC in - * this case so that KVM can the AVIC doorbell to inject interrupts to - * running vCPUs, but KVM must not create SPTEs for the APIC base as + * this case so that KVM can use the AVIC doorbell to inject interrupts + * to running vCPUs, but KVM must not create SPTEs for the APIC base as * the vCPU would incorrectly be able to access the vAPIC page via MMIO * despite being in x2APIC mode. For simplicity, inhibiting the APIC * access page is sticky. @@ -10392,11 +10936,11 @@ void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, if (!!old != !!new) { /* * Kick all vCPUs before setting apicv_inhibit_reasons to avoid - * false positives in the sanity check WARN in svm_vcpu_run(). + * false positives in the sanity check WARN in vcpu_enter_guest(). * This task will wait for all vCPUs to ack the kick IRQ before * updating apicv_inhibit_reasons, and all other vCPUs will * block on acquiring apicv_update_lock so that vCPUs can't - * redo svm_vcpu_run() without seeing the new inhibit state. + * redo vcpu_enter_guest() without seeing the new inhibit state. * * Note, holding apicv_update_lock and taking it in the read * side (handling the request) also prevents other vCPUs from @@ -10426,7 +10970,7 @@ void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, __kvm_set_or_clear_apicv_inhibit(kvm, reason, set); up_write(&kvm->arch.apicv_update_lock); } -EXPORT_SYMBOL_GPL(kvm_set_or_clear_apicv_inhibit); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_or_clear_apicv_inhibit); static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { @@ -10434,14 +10978,16 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) return; bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256); + vcpu->arch.highest_stale_pending_ioapic_eoi = -1; + + kvm_x86_call(sync_pir_to_irr)(vcpu); if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); - else { - static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); - if (ioapic_in_kernel(vcpu->kvm)) - kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); - } +#ifdef CONFIG_KVM_IOAPIC + else if (ioapic_in_kernel(vcpu->kvm)) + kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); +#endif if (is_guest_mode(vcpu)) vcpu->arch.load_eoi_exitmap_pending = true; @@ -10451,26 +10997,27 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) { - u64 eoi_exit_bitmap[4]; - if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; +#ifdef CONFIG_KVM_HYPERV if (to_hv_vcpu(vcpu)) { + u64 eoi_exit_bitmap[4]; + bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, to_hv_synic(vcpu)->vec_bitmap, 256); - static_call_cond(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); + kvm_x86_call(load_eoi_exitmap)(vcpu, eoi_exit_bitmap); return; } - - static_call_cond(kvm_x86_load_eoi_exitmap)( +#endif + kvm_x86_call(load_eoi_exitmap)( vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors); } void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) { - static_call_cond(kvm_x86_guest_memory_reclaimed)(kvm); + kvm_x86_call(guest_memory_reclaimed)(kvm); } static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) @@ -10478,14 +11025,8 @@ static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) if (!lapic_in_kernel(vcpu)) return; - static_call_cond(kvm_x86_set_apic_access_page_addr)(vcpu); -} - -void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) -{ - smp_send_reschedule(vcpu->cpu); + kvm_x86_call(set_apic_access_page_addr)(vcpu); } -EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit); /* * Called within kvm->srcu read side. @@ -10500,6 +11041,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) dm_request_for_irq_injection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); fastpath_t exit_fastpath; + u64 run_flags, debug_ctl; bool req_immediate_exit = false; @@ -10554,9 +11096,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * the flushes are considered "remote" and not "local" because * the requests can be initiated from other vCPUs. */ +#ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu) && kvm_hv_vcpu_flush_tlb(vcpu)) kvm_vcpu_flush_tlb_guest(vcpu); +#endif if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; @@ -10582,16 +11126,16 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) record_steal_time(vcpu); + if (kvm_check_request(KVM_REQ_PMU, vcpu)) + kvm_pmu_handle_event(vcpu); + if (kvm_check_request(KVM_REQ_PMI, vcpu)) + kvm_pmu_deliver_pmi(vcpu); #ifdef CONFIG_KVM_SMM if (kvm_check_request(KVM_REQ_SMI, vcpu)) process_smi(vcpu); #endif if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); - if (kvm_check_request(KVM_REQ_PMU, vcpu)) - kvm_pmu_handle_event(vcpu); - if (kvm_check_request(KVM_REQ_PMI, vcpu)) - kvm_pmu_deliver_pmi(vcpu); if (kvm_check_request(KVM_REQ_IOAPIC_EOI_EXIT, vcpu)) { BUG_ON(vcpu->arch.pending_ioapic_eoi > 255); if (test_bit(vcpu->arch.pending_ioapic_eoi, @@ -10609,6 +11153,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu_load_eoi_exitmap(vcpu); if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu)) kvm_vcpu_reload_apic_access_page(vcpu); +#ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH; @@ -10639,15 +11184,25 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) */ if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu)) kvm_hv_process_stimers(vcpu); +#endif if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu)) kvm_vcpu_update_apicv(vcpu); if (kvm_check_request(KVM_REQ_APF_READY, vcpu)) kvm_check_async_pf_completion(vcpu); - if (kvm_check_request(KVM_REQ_MSR_FILTER_CHANGED, vcpu)) - static_call(kvm_x86_msr_filter_changed)(vcpu); + + if (kvm_check_request(KVM_REQ_RECALC_INTERCEPTS, vcpu)) + kvm_x86_call(recalc_intercepts)(vcpu); if (kvm_check_request(KVM_REQ_UPDATE_CPU_DIRTY_LOGGING, vcpu)) - static_call(kvm_x86_update_cpu_dirty_logging)(vcpu); + kvm_x86_call(update_cpu_dirty_logging)(vcpu); + + if (kvm_check_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu)) { + kvm_vcpu_reset(vcpu, true); + if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE) { + r = 1; + goto out; + } + } } if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win || @@ -10669,7 +11224,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto out; } if (req_int_win) - static_call(kvm_x86_enable_irq_window)(vcpu); + kvm_x86_call(enable_irq_window)(vcpu); if (kvm_lapic_enabled(vcpu)) { update_cr8_intercept(vcpu); @@ -10684,7 +11239,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) preempt_disable(); - static_call(kvm_x86_prepare_switch_to_guest)(vcpu); + kvm_x86_call(prepare_switch_to_guest)(vcpu); /* * Disable IRQs before setting IN_GUEST_MODE. Posted interrupt @@ -10720,7 +11275,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * i.e. they can post interrupts even if APICv is temporarily disabled. */ if (kvm_lapic_enabled(vcpu)) - static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); + kvm_x86_call(sync_pir_to_irr)(vcpu); if (kvm_vcpu_exit_request(vcpu)) { vcpu->mode = OUTSIDE_GUEST_MODE; @@ -10732,9 +11287,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } + run_flags = 0; if (req_immediate_exit) { + run_flags |= KVM_RUN_FORCE_IMMEDIATE_EXIT; kvm_make_request(KVM_REQ_EVENT, vcpu); - static_call(kvm_x86_request_immediate_exit)(vcpu); } fpregs_assert_state_consistent(); @@ -10742,46 +11298,74 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) switch_fpu_return(); if (vcpu->arch.guest_fpu.xfd_err) - wrmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); + wrmsrq(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); - if (unlikely(vcpu->arch.switch_db_regs)) { - set_debugreg(0, 7); + kvm_load_xfeatures(vcpu, true); + + if (unlikely(vcpu->arch.switch_db_regs && + !(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH))) { + set_debugreg(DR7_FIXED_1, 7); set_debugreg(vcpu->arch.eff_db[0], 0); set_debugreg(vcpu->arch.eff_db[1], 1); set_debugreg(vcpu->arch.eff_db[2], 2); set_debugreg(vcpu->arch.eff_db[3], 3); + /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */ + if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) + run_flags |= KVM_RUN_LOAD_GUEST_DR6; } else if (unlikely(hw_breakpoint_active())) { - set_debugreg(0, 7); + set_debugreg(DR7_FIXED_1, 7); } + /* + * Refresh the host DEBUGCTL snapshot after disabling IRQs, as DEBUGCTL + * can be modified in IRQ context, e.g. via SMP function calls. Inform + * vendor code if any host-owned bits were changed, e.g. so that the + * value loaded into hardware while running the guest can be updated. + */ + debug_ctl = get_debugctlmsr(); + if ((debug_ctl ^ vcpu->arch.host_debugctl) & kvm_x86_ops.HOST_OWNED_DEBUGCTL && + !vcpu->arch.guest_state_protected) + run_flags |= KVM_RUN_LOAD_DEBUGCTL; + vcpu->arch.host_debugctl = debug_ctl; + guest_timing_enter_irqoff(); + /* + * Swap PKRU with hardware breakpoints disabled to minimize the number + * of flows where non-KVM code can run with guest state loaded. + */ + kvm_load_guest_pkru(vcpu); + for (;;) { /* * Assert that vCPU vs. VM APICv state is consistent. An APICv * update must kick and wait for all vCPUs before toggling the - * per-VM state, and responsing vCPUs must wait for the update + * per-VM state, and responding vCPUs must wait for the update * to complete before servicing KVM_REQ_APICV_UPDATE. */ WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) && (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED)); - exit_fastpath = static_call(kvm_x86_vcpu_run)(vcpu); + exit_fastpath = kvm_x86_call(vcpu_run)(vcpu, run_flags); if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; if (kvm_lapic_enabled(vcpu)) - static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); + kvm_x86_call(sync_pir_to_irr)(vcpu); if (unlikely(kvm_vcpu_exit_request(vcpu))) { exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; break; } + run_flags = 0; + /* Note, VM-Exits that go down the "slow" path are accounted below. */ ++vcpu->stat.exits; } + kvm_load_host_pkru(vcpu); + /* * Do this here before restoring debug registers on the host. And * since we do this before handling the vmexit, a DR access vmexit @@ -10790,7 +11374,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); - static_call(kvm_x86_sync_dirty_debug_regs)(vcpu); + WARN_ON(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH); + kvm_x86_call(sync_dirty_debug_regs)(vcpu); kvm_update_dr0123(vcpu); kvm_update_dr7(vcpu); } @@ -10811,6 +11396,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); + kvm_load_xfeatures(vcpu, false); + /* * Sync xfd before calling handle_exit_irqoff() which may * rely on the fact that guest_fpu::xfd is up-to-date (e.g. @@ -10819,10 +11406,19 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (vcpu->arch.xfd_no_write_intercept) fpu_sync_guest_vmexit_xfd_state(); - static_call(kvm_x86_handle_exit_irqoff)(vcpu); + kvm_x86_call(handle_exit_irqoff)(vcpu); if (vcpu->arch.guest_fpu.xfd_err) - wrmsrl(MSR_IA32_XFD_ERR, 0); + wrmsrq(MSR_IA32_XFD_ERR, 0); + + /* + * Mark this CPU as needing a branch predictor flush before running + * userspace. Must be done before enabling preemption to ensure it gets + * set for the CPU that actually ran the guest, and not the CPU that it + * may migrate to. + */ + if (cpu_feature_enabled(X86_FEATURE_IBPB_EXIT_TO_USER)) + this_cpu_write(x86_ibpb_exit_to_user, true); /* * Consume any pending interrupts, including the possible source of @@ -10852,9 +11448,16 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_vcpu_srcu_read_lock(vcpu); /* + * Call this to ensure WC buffers in guest are evicted after each VM + * Exit, so that the evicted WC writes can be snooped across all cpus + */ + smp_mb__after_srcu_read_lock(); + + /* * Profile KVM exit RIPs: */ - if (unlikely(prof_on == KVM_PROFILING)) { + if (unlikely(prof_on == KVM_PROFILING && + !vcpu->arch.guest_state_protected)) { unsigned long rip = kvm_rip_read(vcpu); profile_hit(KVM_PROFILING, (void *)rip); } @@ -10865,19 +11468,82 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (vcpu->arch.apic_attention) kvm_lapic_sync_from_vapic(vcpu); - r = static_call(kvm_x86_handle_exit)(vcpu, exit_fastpath); + if (unlikely(exit_fastpath == EXIT_FASTPATH_EXIT_USERSPACE)) + return 0; + + r = kvm_x86_call(handle_exit)(vcpu, exit_fastpath); return r; cancel_injection: if (req_immediate_exit) kvm_make_request(KVM_REQ_EVENT, vcpu); - static_call(kvm_x86_cancel_injection)(vcpu); + kvm_x86_call(cancel_injection)(vcpu); if (unlikely(vcpu->arch.apic_attention)) kvm_lapic_sync_from_vapic(vcpu); out: return r; } +static bool kvm_vcpu_running(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && + !vcpu->arch.apf.halted); +} + +bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) +{ + if (!list_empty_careful(&vcpu->async_pf.done)) + return true; + + if (kvm_apic_has_pending_init_or_sipi(vcpu) && + kvm_apic_init_sipi_allowed(vcpu)) + return true; + + if (kvm_is_exception_pending(vcpu)) + return true; + + if (kvm_test_request(KVM_REQ_NMI, vcpu) || + (vcpu->arch.nmi_pending && + kvm_x86_call(nmi_allowed)(vcpu, false))) + return true; + +#ifdef CONFIG_KVM_SMM + if (kvm_test_request(KVM_REQ_SMI, vcpu) || + (vcpu->arch.smi_pending && + kvm_x86_call(smi_allowed)(vcpu, false))) + return true; +#endif + + if (kvm_test_request(KVM_REQ_PMI, vcpu)) + return true; + + if (kvm_test_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu)) + return true; + + if (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu)) + return true; + + if (kvm_hv_has_stimer_pending(vcpu)) + return true; + + if (is_guest_mode(vcpu) && + kvm_x86_ops.nested_ops->has_events && + kvm_x86_ops.nested_ops->has_events(vcpu, false)) + return true; + + if (kvm_xen_has_pending_events(vcpu)) + return true; + + return false; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_has_events); + +int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_running(vcpu) || vcpu->arch.pv.pv_unhalted || + kvm_vcpu_has_events(vcpu); +} + /* Called within kvm->srcu read side. */ static inline int vcpu_block(struct kvm_vcpu *vcpu) { @@ -10921,7 +11587,10 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu) * causes a spurious wakeup from HLT). */ if (is_guest_mode(vcpu)) { - if (kvm_check_nested_events(vcpu) < 0) + int r = kvm_check_nested_events(vcpu); + + WARN_ON_ONCE(r == -EBUSY); + if (r < 0) return 0; } @@ -10930,9 +11599,7 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu) switch(vcpu->arch.mp_state) { case KVM_MP_STATE_HALTED: case KVM_MP_STATE_AP_RESET_HOLD: - vcpu->arch.pv.pv_unhalted = false; - vcpu->arch.mp_state = - KVM_MP_STATE_RUNNABLE; + kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); fallthrough; case KVM_MP_STATE_RUNNABLE: vcpu->arch.apf.halted = false; @@ -10946,18 +11613,12 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu) return 1; } -static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) -{ - return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && - !vcpu->arch.apf.halted); -} - /* Called within kvm->srcu read side. */ static int vcpu_run(struct kvm_vcpu *vcpu) { int r; - vcpu->arch.l1tf_flush_l1d = true; + vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; for (;;) { /* @@ -10993,7 +11654,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (__xfer_to_guest_mode_work_pending()) { kvm_vcpu_srcu_read_unlock(vcpu); - r = xfer_to_guest_mode_handle_work(vcpu); + r = kvm_xfer_to_guest_mode_handle_work(vcpu); kvm_vcpu_srcu_read_lock(vcpu); if (r) return r; @@ -11003,6 +11664,91 @@ static int vcpu_run(struct kvm_vcpu *vcpu) return r; } +static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) +{ + /* + * The vCPU has halted, e.g. executed HLT. Update the run state if the + * local APIC is in-kernel, the run loop will detect the non-runnable + * state and halt the vCPU. Exit to userspace if the local APIC is + * managed by userspace, in which case userspace is responsible for + * handling wake events. + */ + ++vcpu->stat.halt_exits; + if (lapic_in_kernel(vcpu)) { + if (kvm_vcpu_has_events(vcpu) || vcpu->arch.pv.pv_unhalted) + state = KVM_MP_STATE_RUNNABLE; + kvm_set_mp_state(vcpu, state); + return 1; + } else { + vcpu->run->exit_reason = reason; + return 0; + } +} + +int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu) +{ + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_halt_noskip); + +int kvm_emulate_halt(struct kvm_vcpu *vcpu) +{ + int ret = kvm_skip_emulated_instruction(vcpu); + /* + * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered + * KVM_EXIT_DEBUG here. + */ + return kvm_emulate_halt_noskip(vcpu) && ret; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_halt); + +fastpath_t handle_fastpath_hlt(struct kvm_vcpu *vcpu) +{ + if (!kvm_emulate_halt(vcpu)) + return EXIT_FASTPATH_EXIT_USERSPACE; + + if (kvm_vcpu_running(vcpu)) + return EXIT_FASTPATH_REENTER_GUEST; + + return EXIT_FASTPATH_EXIT_HANDLED; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(handle_fastpath_hlt); + +int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) +{ + int ret = kvm_skip_emulated_instruction(vcpu); + + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, + KVM_EXIT_AP_RESET_HOLD) && ret; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_ap_reset_hold); + +bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_apicv_active(vcpu) && + kvm_x86_call(dy_apicv_has_pending_interrupt)(vcpu); +} + +bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.preempted_in_kernel; +} + +bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) +{ + if (READ_ONCE(vcpu->arch.pv.pv_unhalted)) + return true; + + if (kvm_test_request(KVM_REQ_NMI, vcpu) || +#ifdef CONFIG_KVM_SMM + kvm_test_request(KVM_REQ_SMI, vcpu) || +#endif + kvm_test_request(KVM_REQ_EVENT, vcpu)) + return true; + + return kvm_arch_dy_has_pending_interrupt(vcpu); +} + static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); @@ -11081,6 +11827,9 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) /* Swap (qemu) user FPU context for the guest FPU context. */ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { + if (KVM_BUG_ON(vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm)) + return; + /* Exclude PKRU, it's restored separately immediately after VM-Exit. */ fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, true); trace_kvm_fpu(1); @@ -11089,17 +11838,47 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) /* When vcpu_run ends, restore user space FPU context. */ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { + if (KVM_BUG_ON(!vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm)) + return; + fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, false); ++vcpu->stat.fpu_reload; trace_kvm_fpu(0); } +static int kvm_x86_vcpu_pre_run(struct kvm_vcpu *vcpu) +{ + /* + * SIPI_RECEIVED is obsolete; KVM leaves the vCPU in Wait-For-SIPI and + * tracks the pending SIPI separately. SIPI_RECEIVED is still accepted + * by KVM_SET_VCPU_EVENTS for backwards compatibility, but should be + * converted to INIT_RECEIVED. + */ + if (WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED)) + return -EINVAL; + + /* + * Disallow running the vCPU if userspace forced it into an impossible + * MP_STATE, e.g. if the vCPU is in WFS but SIPI is blocked. + */ + if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED && + !kvm_apic_init_sipi_allowed(vcpu)) + return -EINVAL; + + return kvm_x86_call(vcpu_pre_run)(vcpu); +} + int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = &vcpu->arch.exception; struct kvm_run *kvm_run = vcpu->run; + u64 sync_valid_fields; int r; + r = kvm_mmu_post_init_vm(vcpu->kvm); + if (r) + return r; + vcpu_load(vcpu); kvm_sigset_activate(vcpu); kvm_run->flags = 0; @@ -11107,16 +11886,21 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_vcpu_srcu_read_lock(vcpu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { - if (kvm_run->immediate_exit) { + if (!vcpu->wants_to_run) { r = -EINTR; goto out; } + /* - * It should be impossible for the hypervisor timer to be in - * use before KVM has ever run the vCPU. + * Don't bother switching APIC timer emulation from the + * hypervisor timer to the software timer, the only way for the + * APIC timer to be active is if userspace stuffed vCPU state, + * i.e. put the vCPU into a nonsensical state. Only an INIT + * will transition the vCPU out of UNINITIALIZED (without more + * state stuffing from userspace), which will reset the local + * APIC and thus cancel the timer or drop the IRQ (if the timer + * already expired). */ - WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu)); - kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_block(vcpu); kvm_vcpu_srcu_read_lock(vcpu); @@ -11134,8 +11918,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) goto out; } - if ((kvm_run->kvm_valid_regs & ~KVM_SYNC_X86_VALID_FIELDS) || - (kvm_run->kvm_dirty_regs & ~KVM_SYNC_X86_VALID_FIELDS)) { + sync_valid_fields = kvm_sync_valid_fields(vcpu->kvm); + if ((kvm_run->kvm_valid_regs & ~sync_valid_fields) || + (kvm_run->kvm_dirty_regs & ~sync_valid_fields)) { r = -EINVAL; goto out; } @@ -11180,12 +11965,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) WARN_ON_ONCE(vcpu->mmio_needed); } - if (kvm_run->immediate_exit) { + if (!vcpu->wants_to_run) { r = -EINTR; goto out; } - r = static_call(kvm_x86_vcpu_pre_run)(vcpu); + r = kvm_x86_vcpu_pre_run(vcpu); if (r <= 0) goto out; @@ -11193,7 +11978,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) out: kvm_put_guest_fpu(vcpu); - if (kvm_run->kvm_valid_regs) + if (kvm_run->kvm_valid_regs && likely(!vcpu->arch.guest_state_protected)) store_regs(vcpu); post_kvm_run_save(vcpu); kvm_vcpu_srcu_read_unlock(vcpu); @@ -11241,6 +12026,10 @@ static void __get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + vcpu_load(vcpu); __get_regs(vcpu, regs); vcpu_put(vcpu); @@ -11282,6 +12071,10 @@ static void __set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + vcpu_load(vcpu); __set_regs(vcpu, regs); vcpu_put(vcpu); @@ -11305,10 +12098,10 @@ static void __get_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) kvm_get_segment(vcpu, &sregs->tr, VCPU_SREG_TR); kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); - static_call(kvm_x86_get_idt)(vcpu, &dt); + kvm_x86_call(get_idt)(vcpu, &dt); sregs->idt.limit = dt.size; sregs->idt.base = dt.address; - static_call(kvm_x86_get_gdt)(vcpu, &dt); + kvm_x86_call(get_gdt)(vcpu, &dt); sregs->gdt.limit = dt.size; sregs->gdt.base = dt.address; @@ -11320,7 +12113,7 @@ skip_protected_regs: sregs->cr4 = kvm_read_cr4(vcpu); sregs->cr8 = kvm_get_cr8(vcpu); sregs->efer = vcpu->arch.efer; - sregs->apic_base = kvm_get_apic_base(vcpu); + sregs->apic_base = vcpu->arch.apic_base; } static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) @@ -11354,6 +12147,10 @@ static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + vcpu_load(vcpu); __get_sregs(vcpu, sregs); vcpu_put(vcpu); @@ -11366,8 +12163,7 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, int r; vcpu_load(vcpu); - if (kvm_mpx_supported()) - kvm_load_guest_fpu(vcpu); + kvm_vcpu_srcu_read_lock(vcpu); r = kvm_apic_accept_events(vcpu); if (r < 0) @@ -11382,8 +12178,7 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, mp_state->mp_state = vcpu->arch.mp_state; out: - if (kvm_mpx_supported()) - kvm_put_guest_fpu(vcpu); + kvm_vcpu_srcu_read_unlock(vcpu); vcpu_put(vcpu); return r; } @@ -11413,21 +12208,16 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, } /* - * Pending INITs are reported using KVM_SET_VCPU_EVENTS, disallow - * forcing the guest into INIT/SIPI if those events are supposed to be - * blocked. KVM prioritizes SMI over INIT, so reject INIT/SIPI state - * if an SMI is pending as well. + * SIPI_RECEIVED is obsolete and no longer used internally; KVM instead + * leaves the vCPU in INIT_RECIEVED (Wait-For-SIPI) and pends the SIPI. + * Translate SIPI_RECEIVED as appropriate for backwards compatibility. */ - if ((!kvm_apic_init_sipi_allowed(vcpu) || vcpu->arch.smi_pending) && - (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED || - mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED)) - goto out; - if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) { - vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; + mp_state->mp_state = KVM_MP_STATE_INIT_RECEIVED; set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events); - } else - vcpu->arch.mp_state = mp_state->mp_state; + } + + kvm_set_mp_state(vcpu, mp_state->mp_state); kvm_make_request(KVM_REQ_EVENT, vcpu); ret = 0; @@ -11442,22 +12232,49 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int ret; + if (kvm_is_cr4_bit_set(vcpu, X86_CR4_CET)) { + u64 u_cet, s_cet; + + /* + * Check both User and Supervisor on task switches as inter- + * privilege level task switches are impacted by CET at both + * the current privilege level and the new privilege level, and + * that information is not known at this time. The expectation + * is that the guest won't require emulation of task switches + * while using IBT or Shadow Stacks. + */ + if (__kvm_emulate_msr_read(vcpu, MSR_IA32_U_CET, &u_cet) || + __kvm_emulate_msr_read(vcpu, MSR_IA32_S_CET, &s_cet)) + goto unhandled_task_switch; + + if ((u_cet | s_cet) & (CET_ENDBR_EN | CET_SHSTK_EN)) + goto unhandled_task_switch; + } + init_emulate_ctxt(vcpu); ret = emulator_task_switch(ctxt, tss_selector, idt_index, reason, has_error_code, error_code); - if (ret) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; - return 0; - } + + /* + * Report an error userspace if MMIO is needed, as KVM doesn't support + * MMIO during a task switch (or any other complex operation). + */ + if (ret || vcpu->mmio_needed) + goto unhandled_task_switch; kvm_rip_write(vcpu, ctxt->eip); kvm_set_rflags(vcpu, ctxt->eflags); return 1; + +unhandled_task_switch: + vcpu->mmio_needed = false; + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return 0; } -EXPORT_SYMBOL_GPL(kvm_task_switch); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_task_switch); static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { @@ -11469,7 +12286,7 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) */ if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) return false; - if (kvm_vcpu_is_illegal_gpa(vcpu, sregs->cr3)) + if (!kvm_vcpu_is_legal_cr3(vcpu, sregs->cr3)) return false; } else { /* @@ -11487,16 +12304,13 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, int *mmu_reset_needed, bool update_pdptrs) { - struct msr_data apic_base_msr; int idx; struct desc_ptr dt; if (!kvm_is_valid_sregs(vcpu, sregs)) return -EINVAL; - apic_base_msr.data = sregs->apic_base; - apic_base_msr.host_initiated = true; - if (kvm_set_apic_base(vcpu, &apic_base_msr)) + if (kvm_apic_set_base(vcpu, sregs->apic_base, true)) return -EINVAL; if (vcpu->arch.guest_state_protected) @@ -11504,28 +12318,27 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, dt.size = sregs->idt.limit; dt.address = sregs->idt.base; - static_call(kvm_x86_set_idt)(vcpu, &dt); + kvm_x86_call(set_idt)(vcpu, &dt); dt.size = sregs->gdt.limit; dt.address = sregs->gdt.base; - static_call(kvm_x86_set_gdt)(vcpu, &dt); + kvm_x86_call(set_gdt)(vcpu, &dt); vcpu->arch.cr2 = sregs->cr2; *mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); - static_call_cond(kvm_x86_post_set_cr3)(vcpu, sregs->cr3); + kvm_x86_call(post_set_cr3)(vcpu, sregs->cr3); kvm_set_cr8(vcpu, sregs->cr8); *mmu_reset_needed |= vcpu->arch.efer != sregs->efer; - static_call(kvm_x86_set_efer)(vcpu, sregs->efer); + kvm_x86_call(set_efer)(vcpu, sregs->efer); *mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; - static_call(kvm_x86_set_cr0)(vcpu, sregs->cr0); - vcpu->arch.cr0 = sregs->cr0; + kvm_x86_call(set_cr0)(vcpu, sregs->cr0); *mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; - static_call(kvm_x86_set_cr4)(vcpu, sregs->cr4); + kvm_x86_call(set_cr4)(vcpu, sregs->cr4); if (update_pdptrs) { idx = srcu_read_lock(&vcpu->kvm->srcu); @@ -11552,7 +12365,7 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, if (kvm_vcpu_is_bsp(vcpu) && kvm_rip_read(vcpu) == 0xfff0 && sregs->cs.selector == 0xf000 && sregs->cs.base == 0xffff0000 && !is_protmode(vcpu)) - vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); return 0; } @@ -11566,8 +12379,10 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) if (ret) return ret; - if (mmu_reset_needed) + if (mmu_reset_needed) { kvm_mmu_reset_context(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + } max_bits = KVM_NR_INTERRUPTS; pending_vec = find_first_bit( @@ -11608,8 +12423,10 @@ static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) mmu_reset_needed = 1; vcpu->arch.pdptrs_from_userspace = true; } - if (mmu_reset_needed) + if (mmu_reset_needed) { kvm_mmu_reset_context(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + } return 0; } @@ -11618,6 +12435,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, { int ret; + if (vcpu->kvm->arch.has_protected_state && + vcpu->arch.guest_state_protected) + return -EINVAL; + vcpu_load(vcpu); ret = __set_sregs(vcpu, sregs); vcpu_put(vcpu); @@ -11695,7 +12516,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, */ kvm_set_rflags(vcpu, rflags); - static_call(kvm_x86_update_exception_bitmap)(vcpu); + kvm_x86_call(update_exception_bitmap)(vcpu); kvm_arch_vcpu_guestdbg_update_apicv_inhibit(vcpu->kvm); @@ -11735,7 +12556,7 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) struct fxregs_state *fxsave; if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return 0; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; vcpu_load(vcpu); @@ -11758,7 +12579,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) struct fxregs_state *fxsave; if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return 0; + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; vcpu_load(vcpu); @@ -11798,15 +12619,22 @@ static int sync_regs(struct kvm_vcpu *vcpu) __set_regs(vcpu, &vcpu->run->s.regs.regs); vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_REGS; } + if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_SREGS) { - if (__set_sregs(vcpu, &vcpu->run->s.regs.sregs)) + struct kvm_sregs sregs = vcpu->run->s.regs.sregs; + + if (__set_sregs(vcpu, &sregs)) return -EINVAL; + vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_SREGS; } + if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_EVENTS) { - if (kvm_vcpu_ioctl_x86_set_vcpu_events( - vcpu, &vcpu->run->s.regs.events)) + struct kvm_vcpu_events events = vcpu->run->s.regs.events; + + if (kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events)) return -EINVAL; + vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_EVENTS; } @@ -11825,7 +12653,7 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) if (id >= kvm->arch.max_vcpu_ids) return -EINVAL; - return static_call(kvm_x86_vcpu_precreate)(kvm); + return kvm_x86_call(vcpu_precreate)(kvm); } int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) @@ -11837,38 +12665,20 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; - kvm_gpc_init(&vcpu->arch.pv_time, vcpu->kvm, vcpu, KVM_HOST_USES_PFN); + kvm_gpc_init(&vcpu->arch.pv_time, vcpu->kvm); if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) - vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); else - vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; + kvm_set_mp_state(vcpu, KVM_MP_STATE_UNINITIALIZED); r = kvm_mmu_create(vcpu); if (r < 0) return r; - if (irqchip_in_kernel(vcpu->kvm)) { - r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); - if (r < 0) - goto fail_mmu_destroy; - - /* - * Defer evaluating inhibits until the vCPU is first run, as - * this vCPU will not get notified of any changes until this - * vCPU is visible to other vCPUs (marked online and added to - * the set of vCPUs). Opportunistically mark APICv active as - * VMX in particularly is highly unlikely to have inhibits. - * Ignore the current per-VM APICv state so that vCPU creation - * is guaranteed to run with a deterministic value, the request - * will ensure the vCPU gets the correct state before VM-Entry. - */ - if (enable_apicv) { - vcpu->arch.apic->apicv_active = true; - kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); - } - } else - static_branch_inc(&kvm_has_noapic_vcpu); + r = kvm_create_lapic(vcpu); + if (r < 0) + goto fail_mmu_destroy; r = -ENOMEM; @@ -11897,14 +12707,13 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) goto free_emulate_ctxt; } - vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); - vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); - - vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; - kvm_async_pf_hash_reset(vcpu); - vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap; + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) { + vcpu->arch.arch_capabilities = kvm_get_arch_capabilities(); + vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; + vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap; + } kvm_pmu_init(vcpu); vcpu->arch.pending_external_vector = -1; @@ -11914,15 +12723,13 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.hv_root_tdp = INVALID_PAGE; #endif - r = static_call(kvm_x86_vcpu_create)(vcpu); + r = kvm_x86_call(vcpu_create)(vcpu); if (r) goto free_guest_fpu; - vcpu->arch.arch_capabilities = kvm_get_arch_capabilities(); - vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; kvm_xen_init_vcpu(vcpu); - kvm_vcpu_mtrr_init(vcpu); vcpu_load(vcpu); + kvm_vcpu_after_set_cpuid(vcpu); kvm_set_tsc_khz(vcpu, vcpu->kvm->arch.default_tsc_khz); kvm_vcpu_reset(vcpu, false); kvm_init_mmu(vcpu); @@ -11948,31 +12755,31 @@ fail_mmu_destroy: void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { - struct kvm *kvm = vcpu->kvm; - if (mutex_lock_killable(&vcpu->mutex)) return; vcpu_load(vcpu); - kvm_synchronize_tsc(vcpu, 0); + kvm_synchronize_tsc(vcpu, NULL); vcpu_put(vcpu); /* poll control enabled by default */ vcpu->arch.msr_kvm_poll_control = 1; mutex_unlock(&vcpu->mutex); - - if (kvmclock_periodic_sync && vcpu->vcpu_idx == 0) - schedule_delayed_work(&kvm->arch.kvmclock_sync_work, - KVMCLOCK_SYNC_PERIOD); } void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - int idx; + int idx, cpu; + + kvm_clear_async_pf_completion_queue(vcpu); + kvm_mmu_unload(vcpu); kvmclock_reset(vcpu); - static_call(kvm_x86_vcpu_free)(vcpu); + for_each_possible_cpu(cpu) + cmpxchg(per_cpu_ptr(&last_vcpu, cpu), vcpu, NULL); + + kvm_x86_call(vcpu_free)(vcpu); kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); @@ -11989,8 +12796,53 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) srcu_read_unlock(&vcpu->kvm->srcu, idx); free_page((unsigned long)vcpu->arch.pio_data); kvfree(vcpu->arch.cpuid_entries); - if (!lapic_in_kernel(vcpu)) - static_branch_dec(&kvm_has_noapic_vcpu); +} + +static void kvm_xstate_reset(struct kvm_vcpu *vcpu, bool init_event) +{ + struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate; + u64 xfeatures_mask; + bool fpu_in_use; + int i; + + /* + * Guest FPU state is zero allocated and so doesn't need to be manually + * cleared on RESET, i.e. during vCPU creation. + */ + if (!init_event || !fpstate) + return; + + /* + * On INIT, only select XSTATE components are zeroed, most components + * are unchanged. Currently, the only components that are zeroed and + * supported by KVM are MPX and CET related. + */ + xfeatures_mask = (kvm_caps.supported_xcr0 | kvm_caps.supported_xss) & + (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR | + XFEATURE_MASK_CET_ALL); + if (!xfeatures_mask) + return; + + BUILD_BUG_ON(sizeof(xfeatures_mask) * BITS_PER_BYTE <= XFEATURE_MAX); + + /* + * Unload guest FPU state (if necessary) before zeroing XSTATE fields + * as the kernel can only modify the state when its resident in memory, + * i.e. when it's not loaded into hardware. + * + * WARN if the vCPU's desire to run, i.e. whether or not its in KVM_RUN, + * doesn't match the loaded/in-use state of the FPU, as KVM_RUN is the + * only path that can trigger INIT emulation _and_ loads FPU state, and + * KVM_RUN should _always_ load FPU state. + */ + WARN_ON_ONCE(vcpu->wants_to_run != fpstate->in_use); + fpu_in_use = fpstate->in_use; + if (fpu_in_use) + kvm_put_guest_fpu(vcpu); + for_each_set_bit(i, (unsigned long *)&xfeatures_mask, XFEATURE_MAX) + fpstate_clear_xstate_component(fpstate, i); + if (fpu_in_use) + kvm_load_guest_fpu(vcpu); } void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -12050,33 +12902,19 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; - if (vcpu->arch.guest_fpu.fpstate && kvm_mpx_supported()) { - struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate; - - /* - * All paths that lead to INIT are required to load the guest's - * FPU state (because most paths are buried in KVM_RUN). - */ - if (init_event) - kvm_put_guest_fpu(vcpu); - - fpstate_clear_xstate_component(fpstate, XFEATURE_BNDREGS); - fpstate_clear_xstate_component(fpstate, XFEATURE_BNDCSR); - - if (init_event) - kvm_load_guest_fpu(vcpu); - } + kvm_xstate_reset(vcpu, init_event); if (!init_event) { - kvm_pmu_reset(vcpu); vcpu->arch.smbase = 0x30000; + vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; + vcpu->arch.msr_misc_features_enables = 0; vcpu->arch.ia32_misc_enable_msr = MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL | MSR_IA32_MISC_ENABLE_BTS_UNAVAIL; __kvm_set_xcr(vcpu, 0, XFEATURE_MASK_FP); - __kvm_set_msr(vcpu, MSR_IA32_XSS, 0, true); + kvm_msr_write(vcpu, MSR_IA32_XSS, 0); } /* All GPRs except RDX (handled below) are zeroed on RESET/INIT. */ @@ -12093,7 +12931,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) cpuid_0x1 = kvm_find_cpuid_entry(vcpu, 1); kvm_rdx_write(vcpu, cpuid_0x1 ? cpuid_0x1->eax : 0x600); - static_call(kvm_x86_vcpu_reset)(vcpu, init_event); + kvm_x86_call(vcpu_reset)(vcpu, init_event); kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); kvm_rip_write(vcpu, 0xfff0); @@ -12112,10 +12950,10 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) else new_cr0 |= X86_CR0_NW | X86_CR0_CD; - static_call(kvm_x86_set_cr0)(vcpu, new_cr0); - static_call(kvm_x86_set_cr4)(vcpu, 0); - static_call(kvm_x86_set_efer)(vcpu, 0); - static_call(kvm_x86_update_exception_bitmap)(vcpu); + kvm_x86_call(set_cr0)(vcpu, new_cr0); + kvm_x86_call(set_cr4)(vcpu, 0); + kvm_x86_call(set_efer)(vcpu, 0); + kvm_x86_call(update_exception_bitmap)(vcpu); /* * On the standard CR0/CR4/EFER modification paths, there are several @@ -12142,7 +12980,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) if (init_event) kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); } -EXPORT_SYMBOL_GPL(kvm_vcpu_reset); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_reset); void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) { @@ -12154,9 +12992,19 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); kvm_rip_write(vcpu, 0); } -EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_deliver_sipi_vector); + +void kvm_arch_enable_virtualization(void) +{ + cpu_emergency_register_virt_callback(kvm_x86_ops.emergency_disable_virtualization_cpu); +} -int kvm_arch_hardware_enable(void) +void kvm_arch_disable_virtualization(void) +{ + cpu_emergency_unregister_virt_callback(kvm_x86_ops.emergency_disable_virtualization_cpu); +} + +int kvm_arch_enable_virtualization_cpu(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; @@ -12172,7 +13020,7 @@ int kvm_arch_hardware_enable(void) if (ret) return ret; - ret = static_call(kvm_x86_hardware_enable)(); + ret = kvm_x86_call(enable_virtualization_cpu)(); if (ret != 0) return ret; @@ -12252,40 +13100,42 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { - static_call(kvm_x86_hardware_disable)(); - drop_user_return_notifiers(); + kvm_x86_call(disable_virtualization_cpu)(); + + /* + * Leave the user-return notifiers as-is when disabling virtualization + * for reboot, i.e. when disabling via IPI function call, and instead + * pin kvm.ko (if it's a module) to defend against use-after-free (in + * the *very* unlikely scenario module unload is racing with reboot). + * On a forced reboot, tasks aren't frozen before shutdown, and so KVM + * could be actively modifying user-return MSR state when the IPI to + * disable virtualization arrives. Handle the extreme edge case here + * instead of trying to account for it in the normal flows. + */ + if (in_task() || WARN_ON_ONCE(!kvm_rebooting)) + drop_user_return_notifiers(); + else + __module_get(THIS_MODULE); } bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) { return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_is_reset_bsp); bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) { return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0; } -__read_mostly DEFINE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu); -EXPORT_SYMBOL_GPL(kvm_has_noapic_vcpu); - -void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) -{ - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - - vcpu->arch.l1tf_flush_l1d = true; - if (pmu->version && unlikely(pmu->event_count)) { - pmu->need_cleanup = true; - kvm_make_request(KVM_REQ_PMU, vcpu); - } - static_call(kvm_x86_sched_in)(vcpu, cpu); -} - void kvm_arch_free_vm(struct kvm *kvm) { - kfree(to_kvm_hv(kvm)->hv_pa_pg); +#if IS_ENABLED(CONFIG_HYPERV) + kfree(kvm->arch.hv_pa_pg); +#endif __kvm_arch_free_vm(kvm); } @@ -12295,31 +13145,31 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) int ret; unsigned long flags; - if (type) + if (!kvm_is_vm_type_supported(type)) return -EINVAL; + kvm->arch.vm_type = type; + kvm->arch.has_private_mem = + (type == KVM_X86_SW_PROTECTED_VM); + /* Decided by the vendor code for other VM types. */ + kvm->arch.pre_fault_allowed = + type == KVM_X86_DEFAULT_VM || type == KVM_X86_SW_PROTECTED_VM; + kvm->arch.disabled_quirks = kvm_caps.inapplicable_quirks & kvm_caps.supported_quirks; + ret = kvm_page_track_init(kvm); if (ret) goto out; ret = kvm_mmu_init_vm(kvm); if (ret) - goto out_page_track; + goto out_cleanup_page_track; - ret = static_call(kvm_x86_vm_init)(kvm); + ret = kvm_x86_call(vm_init)(kvm); if (ret) goto out_uninit_mmu; - INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); - INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); - /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ - set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); - /* Reserve bit 1 of irq_sources_bitmap for irqfd-resampler */ - set_bit(KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, - &kvm->arch.irq_sources_bitmap); - raw_spin_lock_init(&kvm->arch.tsc_write_lock); mutex_init(&kvm->arch.apic_map_lock); seqcount_raw_spinlock_init(&kvm->arch.pvclock_sc, &kvm->arch.tsc_write_lock); @@ -12330,6 +13180,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); kvm->arch.default_tsc_khz = max_tsc_khz ? : tsc_khz; + kvm->arch.apic_bus_cycle_ns = APIC_BUS_CYCLE_NS_DEFAULT; kvm->arch.guest_can_read_msr_platform_info = true; kvm->arch.enable_pmu = enable_pmu; @@ -12338,53 +13189,28 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.hv_root_tdp = INVALID_PAGE; #endif - INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); - INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn); - kvm_apicv_init(kvm); kvm_hv_init_vm(kvm); kvm_xen_init_vm(kvm); + if (ignore_msrs && !report_ignored_msrs) { + pr_warn_once("Running KVM with ignore_msrs=1 and report_ignored_msrs=0 is not a\n" + "a supported configuration. Lying to the guest about the existence of MSRs\n" + "may cause the guest operating system to hang or produce errors. If a guest\n" + "does not run without ignore_msrs=1, please report it to kvm@vger.kernel.org.\n"); + } + + once_init(&kvm->arch.nx_once); return 0; out_uninit_mmu: kvm_mmu_uninit_vm(kvm); -out_page_track: +out_cleanup_page_track: kvm_page_track_cleanup(kvm); out: return ret; } -int kvm_arch_post_init_vm(struct kvm *kvm) -{ - return kvm_mmu_post_init_vm(kvm); -} - -static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) -{ - vcpu_load(vcpu); - kvm_mmu_unload(vcpu); - vcpu_put(vcpu); -} - -static void kvm_unload_vcpu_mmus(struct kvm *kvm) -{ - unsigned long i; - struct kvm_vcpu *vcpu; - - kvm_for_each_vcpu(i, vcpu, kvm) { - kvm_clear_async_pf_completion_queue(vcpu); - kvm_unload_vcpu_mmu(vcpu); - } -} - -void kvm_arch_sync_events(struct kvm *kvm) -{ - cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work); - cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work); - kvm_free_pit(kvm); -} - /** * __x86_set_memory_region: Setup KVM internal memory slot * @@ -12415,7 +13241,8 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *slot; - /* Called with kvm->slots_lock held. */ + lockdep_assert_held(&kvm->slots_lock); + if (WARN_ON(id >= KVM_MEM_SLOTS_NUM)) return ERR_PTR_USR(-EINVAL); @@ -12440,15 +13267,15 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, hva = slot->userspace_addr; } - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - struct kvm_userspace_memory_region m; + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { + struct kvm_userspace_memory_region2 m; m.slot = id | (i << 16); m.flags = 0; m.guest_phys_addr = gpa; m.userspace_addr = hva; m.memory_size = size; - r = __kvm_set_memory_region(kvm, &m); + r = kvm_set_internal_memslot(kvm, &m); if (r < 0) return ERR_PTR_USR(r); } @@ -12458,11 +13285,22 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, return (void __user *)hva; } -EXPORT_SYMBOL_GPL(__x86_set_memory_region); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__x86_set_memory_region); void kvm_arch_pre_destroy_vm(struct kvm *kvm) { + /* + * Stop all background workers and kthreads before destroying vCPUs, as + * iterating over vCPUs in a different task while vCPUs are being freed + * is unsafe, i.e. will lead to use-after-free. The PIT also needs to + * be stopped before IRQ routing is freed. + */ +#ifdef CONFIG_KVM_IOAPIC + kvm_free_pit(kvm); +#endif + kvm_mmu_pre_destroy_vm(kvm); + static_call_cond(kvm_x86_vm_pre_destroy)(kvm); } void kvm_arch_destroy_vm(struct kvm *kvm) @@ -12481,18 +13319,19 @@ void kvm_arch_destroy_vm(struct kvm *kvm) __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); mutex_unlock(&kvm->slots_lock); } - kvm_unload_vcpu_mmus(kvm); - static_call_cond(kvm_x86_vm_destroy)(kvm); + kvm_destroy_vcpus(kvm); kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1)); +#ifdef CONFIG_KVM_IOAPIC kvm_pic_destroy(kvm); kvm_ioapic_destroy(kvm); - kvm_destroy_vcpus(kvm); +#endif kvfree(rcu_dereference_check(kvm->arch.apic_map, 1)); kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1)); kvm_mmu_uninit_vm(kvm); kvm_page_track_cleanup(kvm); kvm_xen_destroy_vm(kvm); kvm_hv_destroy_vm(kvm); + kvm_x86_call(vm_destroy)(kvm); } static void memslot_rmap_free(struct kvm_memory_slot *slot) @@ -12500,7 +13339,7 @@ static void memslot_rmap_free(struct kvm_memory_slot *slot) int i; for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { - kvfree(slot->arch.rmap[i]); + vfree(slot->arch.rmap[i]); slot->arch.rmap[i] = NULL; } } @@ -12512,7 +13351,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) memslot_rmap_free(slot); for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { - kvfree(slot->arch.lpage_info[i - 1]); + vfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } @@ -12549,7 +13388,7 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm, /* * Clear out the previous array pointers for the KVM_MR_MOVE case. The - * old arrays will be freed by __kvm_set_memory_region() if installing + * old arrays will be freed by kvm_set_memory_region() if installing * the new memslot is successful. */ memset(&slot->arch, 0, sizeof(slot->arch)); @@ -12591,6 +13430,10 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm, } } +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + kvm_mmu_init_memslot_memory_attributes(kvm, slot); +#endif + if (kvm_page_track_create_memslot(kvm, slot, npages)) goto out_free; @@ -12600,7 +13443,7 @@ out_free: memslot_rmap_free(slot); for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { - kvfree(slot->arch.lpage_info[i - 1]); + vfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } return -ENOMEM; @@ -12627,10 +13470,20 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *new, enum kvm_mr_change change) { + /* + * KVM doesn't support moving memslots when there are external page + * trackers attached to the VM, i.e. if KVMGT is in use. + */ + if (change == KVM_MR_MOVE && kvm_page_track_has_external_user(kvm)) + return -EINVAL; + if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) { if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn()) return -EINVAL; + if (kvm_is_gfn_alias(kvm, new->base_gfn + new->npages - 1)) + return -EINVAL; + return kvm_alloc_memslot_metadata(kvm, new); } @@ -12647,7 +13500,7 @@ static void kvm_mmu_update_cpu_dirty_logging(struct kvm *kvm, bool enable) { int nr_slots; - if (!kvm_x86_ops.cpu_dirty_log_size) + if (!kvm->arch.cpu_dirty_log_size) return; nr_slots = atomic_read(&kvm->nr_memslots_dirty_logging); @@ -12699,19 +13552,15 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, if (!log_dirty_pages) { /* - * Dirty logging tracks sptes in 4k granularity, meaning that - * large sptes have to be split. If live migration succeeds, - * the guest in the source machine will be destroyed and large - * sptes will be created in the destination. However, if the - * guest continues to run in the source machine (for example if - * live migration fails), small sptes will remain around and - * cause bad performance. + * Recover huge page mappings in the slot now that dirty logging + * is disabled, i.e. now that KVM does not have to track guest + * writes at 4KiB granularity. * - * Scan sptes if dirty logging has been stopped, dropping those - * which can be collapsed into a single large-page spte. Later - * page faults will create the large-page sptes. + * Dirty logging might be disabled by userspace if an ongoing VM + * live migration is cancelled and the VM must continue running + * on the source. */ - kvm_mmu_zap_collapsible_sptes(kvm, new); + kvm_mmu_recover_huge_pages(kvm, new); } else { /* * Initially-all-set does not require write protecting any page, @@ -12723,7 +13572,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, if (READ_ONCE(eager_page_split)) kvm_mmu_slot_try_split_huge_pages(kvm, new, PG_LEVEL_4K); - if (kvm_x86_ops.cpu_dirty_log_size) { + if (kvm->arch.cpu_dirty_log_size) { kvm_mmu_slot_leaf_clear_dirty(kvm, new); kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_2M); } else { @@ -12772,7 +13621,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * See is_writable_pte() for more details (the case involving * access-tracked SPTEs is particularly relevant). */ - kvm_arch_flush_remote_tlbs_memslot(kvm, new); + kvm_flush_remote_tlbs_memslot(kvm, new); } } @@ -12781,6 +13630,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { + if (change == KVM_MR_DELETE) + kvm_page_track_delete_slot(kvm, old); + if (!kvm->arch.n_requested_mmu_pages && (change == KVM_MR_CREATE || change == KVM_MR_DELETE)) { unsigned long nr_mmu_pages; @@ -12797,108 +13649,23 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, kvm_arch_free_memslot(kvm, old); } -void kvm_arch_flush_shadow_all(struct kvm *kvm) -{ - kvm_mmu_zap_all(kvm); -} - -void kvm_arch_flush_shadow_memslot(struct kvm *kvm, - struct kvm_memory_slot *slot) -{ - kvm_page_track_flush_slot(kvm, slot); -} - -static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) -{ - return (is_guest_mode(vcpu) && - static_call(kvm_x86_guest_apic_has_interrupt)(vcpu)); -} - -static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) -{ - if (!list_empty_careful(&vcpu->async_pf.done)) - return true; - - if (kvm_apic_has_pending_init_or_sipi(vcpu) && - kvm_apic_init_sipi_allowed(vcpu)) - return true; - - if (vcpu->arch.pv.pv_unhalted) - return true; - - if (kvm_is_exception_pending(vcpu)) - return true; - - if (kvm_test_request(KVM_REQ_NMI, vcpu) || - (vcpu->arch.nmi_pending && - static_call(kvm_x86_nmi_allowed)(vcpu, false))) - return true; - -#ifdef CONFIG_KVM_SMM - if (kvm_test_request(KVM_REQ_SMI, vcpu) || - (vcpu->arch.smi_pending && - static_call(kvm_x86_smi_allowed)(vcpu, false))) - return true; -#endif - - if (kvm_arch_interrupt_allowed(vcpu) && - (kvm_cpu_has_interrupt(vcpu) || - kvm_guest_apic_has_interrupt(vcpu))) - return true; - - if (kvm_hv_has_stimer_pending(vcpu)) - return true; - - if (is_guest_mode(vcpu) && - kvm_x86_ops.nested_ops->has_events && - kvm_x86_ops.nested_ops->has_events(vcpu)) - return true; - - if (kvm_xen_has_pending_events(vcpu)) - return true; - - return false; -} - -int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) +bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) { - return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); -} + WARN_ON_ONCE(!kvm_arch_pmi_in_guest(vcpu)); -bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) -{ - if (kvm_vcpu_apicv_active(vcpu) && - static_call(kvm_x86_dy_apicv_has_pending_interrupt)(vcpu)) + if (vcpu->arch.guest_state_protected) return true; - return false; + return kvm_x86_call(get_cpl)(vcpu) == 0; } -bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) +unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu) { - if (READ_ONCE(vcpu->arch.pv.pv_unhalted)) - return true; + WARN_ON_ONCE(!kvm_arch_pmi_in_guest(vcpu)); - if (kvm_test_request(KVM_REQ_NMI, vcpu) || -#ifdef CONFIG_KVM_SMM - kvm_test_request(KVM_REQ_SMI, vcpu) || -#endif - kvm_test_request(KVM_REQ_EVENT, vcpu)) - return true; - - return kvm_arch_dy_has_pending_interrupt(vcpu); -} - -bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) -{ if (vcpu->arch.guest_state_protected) - return true; - - return vcpu->arch.preempted_in_kernel; -} + return 0; -unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu) -{ return kvm_rip_read(vcpu); } @@ -12909,7 +13676,7 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) { - return static_call(kvm_x86_interrupt_allowed)(vcpu, false); + return kvm_x86_call(interrupt_allowed)(vcpu, false); } unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu) @@ -12923,31 +13690,31 @@ unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu) return (u32)(get_segment_base(vcpu, VCPU_SREG_CS) + kvm_rip_read(vcpu)); } -EXPORT_SYMBOL_GPL(kvm_get_linear_rip); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_linear_rip); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip) { return kvm_get_linear_rip(vcpu) == linear_rip; } -EXPORT_SYMBOL_GPL(kvm_is_linear_rip); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_is_linear_rip); unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) { unsigned long rflags; - rflags = static_call(kvm_x86_get_rflags)(vcpu); + rflags = kvm_x86_call(get_rflags)(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) rflags &= ~X86_EFLAGS_TF; return rflags; } -EXPORT_SYMBOL_GPL(kvm_get_rflags); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_rflags); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip)) rflags |= X86_EFLAGS_TF; - static_call(kvm_x86_set_rflags)(vcpu, rflags); + kvm_x86_call(set_rflags)(vcpu, rflags); } void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) @@ -12955,7 +13722,7 @@ void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) __kvm_set_rflags(vcpu, rflags); kvm_make_request(KVM_REQ_EVENT, vcpu); } -EXPORT_SYMBOL_GPL(kvm_set_rflags); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_rflags); static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) { @@ -13058,8 +13825,8 @@ static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu) if (!kvm_pv_async_pf_enabled(vcpu)) return false; - if (vcpu->arch.apf.send_user_only && - static_call(kvm_x86_get_cpl)(vcpu) == 0) + if (!vcpu->arch.apf.send_always && + (vcpu->arch.guest_state_protected || !kvm_x86_call(get_cpl)(vcpu))) return false; if (is_guest_mode(vcpu)) { @@ -13144,18 +13911,22 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, if ((work->wakeup_all || work->notpresent_injected) && kvm_pv_async_pf_enabled(vcpu) && !apf_put_user_ready(vcpu, work->arch.token)) { - vcpu->arch.apf.pageready_pending = true; + WRITE_ONCE(vcpu->arch.apf.pageready_pending, true); kvm_apic_set_irq(vcpu, &irq, NULL); } vcpu->arch.apf.halted = false; - vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); } void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu) { kvm_make_request(KVM_REQ_APF_READY, vcpu); - if (!vcpu->arch.apf.pageready_pending) + + /* Pairs with smp_store_mb() in kvm_set_msr_common(). */ + smp_mb__after_atomic(); + + if (!READ_ONCE(vcpu->arch.apf.pageready_pending)) kvm_vcpu_kick(vcpu); } @@ -13167,116 +13938,69 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) return kvm_lapic_enabled(vcpu) && apf_pageready_slot_free(vcpu); } -void kvm_arch_start_assignment(struct kvm *kvm) -{ - if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1) - static_call_cond(kvm_x86_pi_start_assignment)(kvm); -} -EXPORT_SYMBOL_GPL(kvm_arch_start_assignment); - -void kvm_arch_end_assignment(struct kvm *kvm) +static void kvm_noncoherent_dma_assignment_start_or_stop(struct kvm *kvm) { - atomic_dec(&kvm->arch.assigned_device_count); -} -EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); - -bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm) -{ - return raw_atomic_read(&kvm->arch.assigned_device_count); + /* + * Non-coherent DMA assignment and de-assignment may affect whether or + * not KVM honors guest PAT, and thus may cause changes in EPT SPTEs + * due to toggling the "ignore PAT" bit. Zap all SPTEs when the first + * (or last) non-coherent device is (un)registered to so that new SPTEs + * with the correct "ignore guest PAT" setting are created. + * + * If KVM always honors guest PAT, however, there is nothing to do. + */ + if (kvm_check_has_quirk(kvm, KVM_X86_QUIRK_IGNORE_GUEST_PAT)) + kvm_zap_gfn_range(kvm, gpa_to_gfn(0), gpa_to_gfn(~0ULL)); } -EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { - atomic_inc(&kvm->arch.noncoherent_dma_count); + if (atomic_inc_return(&kvm->arch.noncoherent_dma_count) == 1) + kvm_noncoherent_dma_assignment_start_or_stop(kvm); } -EXPORT_SYMBOL_GPL(kvm_arch_register_noncoherent_dma); void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm) { - atomic_dec(&kvm->arch.noncoherent_dma_count); + if (!atomic_dec_return(&kvm->arch.noncoherent_dma_count)) + kvm_noncoherent_dma_assignment_start_or_stop(kvm); } -EXPORT_SYMBOL_GPL(kvm_arch_unregister_noncoherent_dma); bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) { return atomic_read(&kvm->arch.noncoherent_dma_count); } -EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma); - -bool kvm_arch_has_irq_bypass(void) -{ - return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP); -} - -int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, - struct irq_bypass_producer *prod) -{ - struct kvm_kernel_irqfd *irqfd = - container_of(cons, struct kvm_kernel_irqfd, consumer); - int ret; - - irqfd->producer = prod; - kvm_arch_start_assignment(irqfd->kvm); - ret = static_call(kvm_x86_pi_update_irte)(irqfd->kvm, - prod->irq, irqfd->gsi, 1); - - if (ret) - kvm_arch_end_assignment(irqfd->kvm); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_arch_has_noncoherent_dma); - return ret; -} - -void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, - struct irq_bypass_producer *prod) -{ - int ret; - struct kvm_kernel_irqfd *irqfd = - container_of(cons, struct kvm_kernel_irqfd, consumer); - - WARN_ON(irqfd->producer != prod); - irqfd->producer = NULL; - - /* - * When producer of consumer is unregistered, we change back to - * remapped mode, so we can re-use the current implementation - * when the irq is masked/disabled or the consumer side (KVM - * int this case doesn't want to receive the interrupts. - */ - ret = static_call(kvm_x86_pi_update_irte)(irqfd->kvm, prod->irq, irqfd->gsi, 0); - if (ret) - printk(KERN_INFO "irq bypass consumer (token %p) unregistration" - " fails: %d\n", irqfd->consumer.token, ret); - - kvm_arch_end_assignment(irqfd->kvm); -} - -int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) +bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { - return static_call(kvm_x86_pi_update_irte)(kvm, host_irq, guest_irq, set); + return (vcpu->arch.msr_kvm_poll_control & 1) == 0; } -bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old, - struct kvm_kernel_irq_routing_entry *new) +#ifdef CONFIG_KVM_GUEST_MEMFD +/* + * KVM doesn't yet support initializing guest_memfd memory as shared for VMs + * with private memory (the private vs. shared tracking needs to be moved into + * guest_memfd). + */ +bool kvm_arch_supports_gmem_init_shared(struct kvm *kvm) { - if (new->type != KVM_IRQ_ROUTING_MSI) - return true; - - return !!memcmp(&old->msi, &new->msi, sizeof(new->msi)); + return !kvm_arch_has_private_mem(kvm); } -bool kvm_vector_hashing_enabled(void) +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE +int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order) { - return vector_hashing; + return kvm_x86_call(gmem_prepare)(kvm, pfn, gfn, max_order); } +#endif -bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE +void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) { - return (vcpu->arch.msr_kvm_poll_control & 1) == 0; + kvm_x86_call(gmem_invalidate)(start, end); } -EXPORT_SYMBOL_GPL(kvm_arch_no_poll); - +#endif +#endif int kvm_spec_ctrl_test_value(u64 value) { @@ -13291,18 +14015,18 @@ int kvm_spec_ctrl_test_value(u64 value) local_irq_save(flags); - if (rdmsrl_safe(MSR_IA32_SPEC_CTRL, &saved_value)) + if (rdmsrq_safe(MSR_IA32_SPEC_CTRL, &saved_value)) ret = 1; - else if (wrmsrl_safe(MSR_IA32_SPEC_CTRL, value)) + else if (wrmsrq_safe(MSR_IA32_SPEC_CTRL, value)) ret = 1; else - wrmsrl(MSR_IA32_SPEC_CTRL, saved_value); + wrmsrq(MSR_IA32_SPEC_CTRL, saved_value); local_irq_restore(flags); return ret; } -EXPORT_SYMBOL_GPL(kvm_spec_ctrl_test_value); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_spec_ctrl_test_value); void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code) { @@ -13327,7 +14051,7 @@ void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_c } vcpu->arch.walk_mmu->inject_page_fault(vcpu, &fault); } -EXPORT_SYMBOL_GPL(kvm_fixup_and_inject_pf_error); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_fixup_and_inject_pf_error); /* * Handles kvm_read/write_guest_virt*() result and either injects #PF or returns @@ -13356,7 +14080,7 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, return 0; } -EXPORT_SYMBOL_GPL(kvm_handle_memory_failure); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_handle_memory_failure); int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) { @@ -13381,8 +14105,12 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) switch (type) { case INVPCID_TYPE_INDIV_ADDR: + /* + * LAM doesn't apply to addresses that are inputs to TLB + * invalidation. + */ if ((!pcid_enabled && (operand.pcid != 0)) || - is_noncanonical_address(operand.gla, vcpu)) { + is_noncanonical_invlpg_address(operand.gla, vcpu)) { kvm_inject_gp(vcpu, 0); return 1; } @@ -13416,7 +14144,7 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) return 1; } } -EXPORT_SYMBOL_GPL(kvm_handle_invpcid); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_handle_invpcid); static int complete_sev_es_emulated_mmio(struct kvm_vcpu *vcpu) { @@ -13501,7 +14229,7 @@ int kvm_sev_es_mmio_write(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes, return 0; } -EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_write); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_sev_es_mmio_write); int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes, void *data) @@ -13539,7 +14267,7 @@ int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes, return 0; } -EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_read); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_sev_es_mmio_read); static void advance_sev_es_emulated_pio(struct kvm_vcpu *vcpu, unsigned count, int size) { @@ -13627,10 +14355,11 @@ int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size, return in ? kvm_sev_es_ins(vcpu, size, port) : kvm_sev_es_outs(vcpu, size, port); } -EXPORT_SYMBOL_GPL(kvm_sev_es_string_io); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_sev_es_string_io); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_entry); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_mmio); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); @@ -13647,7 +14376,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window_update); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full); -EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log); @@ -13658,9 +14386,12 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_rmp_fault); static int __init kvm_x86_init(void) { + kvm_init_xstate_sizes(); + kvm_mmu_x86_module_init(); mitigate_smt_rsb &= boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible(); return 0; @@ -13669,9 +14400,6 @@ module_init(kvm_x86_init); static void __exit kvm_x86_exit(void) { - /* - * If module_init() is implemented, module_exit() must also be - * implemented to allow module unload. - */ + WARN_ON_ONCE(static_branch_unlikely(&kvm_has_noapic_vcpu)); } module_exit(kvm_x86_exit); |