diff options
Diffstat (limited to 'arch/x86/kvm/x86.c')
| -rw-r--r-- | arch/x86/kvm/x86.c | 12204 |
1 files changed, 8385 insertions, 3819 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 02c8e095a239..0c6d899d53dd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Kernel-based Virtual Machine driver for Linux * @@ -13,22 +14,25 @@ * Yaniv Kamay <yaniv@qumranet.com> * Amit Shah <amit.shah@qumranet.com> * Ben-Ami Yassour <benami@il.ibm.com> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "irq.h" +#include "ioapic.h" #include "mmu.h" #include "i8254.h" #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" #include "hyperv.h" +#include "lapic.h" +#include "xen.h" +#include "smm.h" #include <linux/clocksource.h> #include <linux/interrupt.h> @@ -40,7 +44,6 @@ #include <linux/mman.h> #include <linux/highmem.h> #include <linux/iommu.h> -#include <linux/intel-iommu.h> #include <linux/cpufreq.h> #include <linux/user-return-notifier.h> #include <linux/srcu.h> @@ -54,33 +57,54 @@ #include <linux/kvm_irqfd.h> #include <linux/irqbypass.h> #include <linux/sched/stat.h> +#include <linux/sched/isolation.h> #include <linux/mem_encrypt.h> +#include <linux/suspend.h> +#include <linux/smp.h> +#include <trace/events/ipi.h> #include <trace/events/kvm.h> #include <asm/debugreg.h> #include <asm/msr.h> #include <asm/desc.h> #include <asm/mce.h> +#include <asm/pkru.h> #include <linux/kernel_stat.h> -#include <asm/fpu/internal.h> /* Ugh! */ +#include <asm/fpu/api.h> +#include <asm/fpu/xcr.h> +#include <asm/fpu/xstate.h> #include <asm/pvclock.h> #include <asm/div64.h> #include <asm/irq_remapping.h> #include <asm/mshyperv.h> #include <asm/hypervisor.h> +#include <asm/tlbflush.h> #include <asm/intel_pt.h> +#include <asm/emulate_prefix.h> +#include <asm/sgx.h> +#include <clocksource/hyperv_timer.h> #define CREATE_TRACE_POINTS #include "trace.h" #define MAX_IO_MSRS 256 -#define KVM_MAX_MCE_BANKS 32 -u64 __read_mostly kvm_mce_cap_supported = MCG_CTL_P | MCG_SER_P; -EXPORT_SYMBOL_GPL(kvm_mce_cap_supported); + +/* + * 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)) #define emul_to_vcpu(ctxt) \ - container_of(ctxt, struct kvm_vcpu, arch.emulate_ctxt) + ((struct kvm_vcpu *)(ctxt)->vcpu) /* EFER defaults: * - enable syscall per default because its emulated by KVM @@ -93,270 +117,596 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif -#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM -#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +#define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE) + +#define KVM_CAP_PMU_VALID_MASK KVM_PMU_CAP_DISABLE #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) static void update_cr8_intercept(struct kvm_vcpu *vcpu); static void process_nmi(struct kvm_vcpu *vcpu); -static void enter_smm(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); static int sync_regs(struct kvm_vcpu *vcpu); +static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu); + +static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); +static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); -struct kvm_x86_ops *kvm_x86_ops __read_mostly; -EXPORT_SYMBOL_GPL(kvm_x86_ops); +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) \ + DEFINE_STATIC_CALL_NULL(kvm_x86_##func, \ + *(((struct kvm_x86_ops *)0)->func)); +#define KVM_X86_OP_OPTIONAL KVM_X86_OP +#define KVM_X86_OP_OPTIONAL_RET0 KVM_X86_OP +#include <asm/kvm-x86-ops.h> +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); -static bool __read_mostly report_ignored_msrs = true; -module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR); +bool __read_mostly report_ignored_msrs = true; +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); - -bool __read_mostly kvm_has_tsc_control; -EXPORT_SYMBOL_GPL(kvm_has_tsc_control); -u32 __read_mostly kvm_max_guest_tsc_khz; -EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz); -u8 __read_mostly kvm_tsc_scaling_ratio_frac_bits; -EXPORT_SYMBOL_GPL(kvm_tsc_scaling_ratio_frac_bits); -u64 __read_mostly kvm_max_tsc_scaling_ratio; -EXPORT_SYMBOL_GPL(kvm_max_tsc_scaling_ratio); -u64 __read_mostly kvm_default_tsc_scaling_ratio; -EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio); +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); +module_param(tsc_tolerance_ppm, uint, 0644); -/* lapic timer advance (tscdeadline mode only) in nanoseconds */ -unsigned int __read_mostly lapic_timer_advance_ns = 1000; -module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR); -EXPORT_SYMBOL_GPL(lapic_timer_advance_ns); +bool __read_mostly enable_vmware_backdoor = false; +module_param(enable_vmware_backdoor, bool, 0444); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_vmware_backdoor); -static bool __read_mostly vector_hashing = true; -module_param(vector_hashing, bool, S_IRUGO); +/* + * Flags to manipulate forced emulation behavior (any non-zero value will + * enable forced emulation). + */ +#define KVM_FEP_CLEAR_RFLAGS_RF BIT(1) +static int __read_mostly force_emulation_prefix; +module_param(force_emulation_prefix, int, 0644); -bool __read_mostly enable_vmware_backdoor = false; -module_param(enable_vmware_backdoor, bool, S_IRUGO); -EXPORT_SYMBOL_GPL(enable_vmware_backdoor); +int __read_mostly pi_inject_timer = -1; +module_param(pi_inject_timer, bint, 0644); -static bool __read_mostly force_emulation_prefix = false; -module_param(force_emulation_prefix, bool, S_IRUGO); +/* Enable/disable PMU virtualization */ +bool __read_mostly enable_pmu = true; +EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_pmu); +module_param(enable_pmu, bool, 0444); -#define KVM_NR_SHARED_MSRS 16 +bool __read_mostly eager_page_split = true; +module_param(eager_page_split, bool, 0644); -struct kvm_shared_msrs_global { - int nr; - u32 msrs[KVM_NR_SHARED_MSRS]; -}; +/* Enable/disable SMT_RSB bug mitigation */ +static bool __read_mostly mitigate_smt_rsb; +module_param(mitigate_smt_rsb, bool, 0444); -struct kvm_shared_msrs { +/* + * Restoring the host value for MSRs that are only consumed when running in + * usermode, e.g. SYSCALL MSRs and TSC_AUX, can be deferred until the CPU + * returns to userspace, i.e. the kernel can run with the guest's value. + */ +#define KVM_MAX_NR_USER_RETURN_MSRS 16 + +struct kvm_user_return_msrs { struct user_return_notifier urn; bool registered; - struct kvm_shared_msr_values { + struct kvm_user_return_msr_values { u64 host; u64 curr; - } values[KVM_NR_SHARED_MSRS]; + } values[KVM_MAX_NR_USER_RETURN_MSRS]; +}; + +u32 __read_mostly 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 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) + +#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_FOR_KVM_INTERNAL(allow_smaller_maxphyaddr); + +bool __read_mostly enable_apicv = true; +EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_apicv); + +bool __read_mostly enable_ipiv = true; +EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_ipiv); + +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(), + STATS_DESC_COUNTER(VM, mmu_shadow_zapped), + STATS_DESC_COUNTER(VM, mmu_pte_write), + STATS_DESC_COUNTER(VM, mmu_pde_zapped), + STATS_DESC_COUNTER(VM, mmu_flooded), + STATS_DESC_COUNTER(VM, mmu_recycled), + STATS_DESC_COUNTER(VM, mmu_cache_miss), + STATS_DESC_ICOUNTER(VM, mmu_unsync), + STATS_DESC_ICOUNTER(VM, pages_4k), + STATS_DESC_ICOUNTER(VM, pages_2m), + STATS_DESC_ICOUNTER(VM, pages_1g), + STATS_DESC_ICOUNTER(VM, nx_lpage_splits), + STATS_DESC_PCOUNTER(VM, max_mmu_rmap_size), + STATS_DESC_PCOUNTER(VM, max_mmu_page_hash_collisions) +}; + +const struct kvm_stats_header kvm_vm_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vm_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vm_stats_desc), +}; + +const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { + KVM_GENERIC_VCPU_STATS(), + STATS_DESC_COUNTER(VCPU, pf_taken), + STATS_DESC_COUNTER(VCPU, pf_fixed), + STATS_DESC_COUNTER(VCPU, pf_emulate), + STATS_DESC_COUNTER(VCPU, pf_spurious), + STATS_DESC_COUNTER(VCPU, pf_fast), + STATS_DESC_COUNTER(VCPU, pf_mmio_spte_created), + STATS_DESC_COUNTER(VCPU, pf_guest), + STATS_DESC_COUNTER(VCPU, tlb_flush), + STATS_DESC_COUNTER(VCPU, invlpg), + STATS_DESC_COUNTER(VCPU, exits), + STATS_DESC_COUNTER(VCPU, io_exits), + STATS_DESC_COUNTER(VCPU, mmio_exits), + STATS_DESC_COUNTER(VCPU, signal_exits), + STATS_DESC_COUNTER(VCPU, irq_window_exits), + STATS_DESC_COUNTER(VCPU, nmi_window_exits), + STATS_DESC_COUNTER(VCPU, l1d_flush), + STATS_DESC_COUNTER(VCPU, halt_exits), + STATS_DESC_COUNTER(VCPU, request_irq_exits), + STATS_DESC_COUNTER(VCPU, irq_exits), + STATS_DESC_COUNTER(VCPU, host_state_reload), + STATS_DESC_COUNTER(VCPU, fpu_reload), + STATS_DESC_COUNTER(VCPU, insn_emulation), + STATS_DESC_COUNTER(VCPU, insn_emulation_fail), + STATS_DESC_COUNTER(VCPU, hypercalls), + STATS_DESC_COUNTER(VCPU, irq_injections), + STATS_DESC_COUNTER(VCPU, nmi_injections), + STATS_DESC_COUNTER(VCPU, req_event), + STATS_DESC_COUNTER(VCPU, nested_run), + STATS_DESC_COUNTER(VCPU, directed_yield_attempted), + STATS_DESC_COUNTER(VCPU, directed_yield_successful), + STATS_DESC_COUNTER(VCPU, preemption_reported), + STATS_DESC_COUNTER(VCPU, preemption_other), + STATS_DESC_IBOOLEAN(VCPU, guest_mode), + STATS_DESC_COUNTER(VCPU, notify_window_exits), +}; + +const struct kvm_stats_header kvm_vcpu_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vcpu_stats_desc), +}; + +static struct kmem_cache *x86_emulator_cache; + +/* + * 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 struct kvm_shared_msrs_global __read_mostly shared_msrs_global; -static struct kvm_shared_msrs __percpu *shared_msrs; - -struct kvm_stats_debugfs_item debugfs_entries[] = { - { "pf_fixed", VCPU_STAT(pf_fixed) }, - { "pf_guest", VCPU_STAT(pf_guest) }, - { "tlb_flush", VCPU_STAT(tlb_flush) }, - { "invlpg", VCPU_STAT(invlpg) }, - { "exits", VCPU_STAT(exits) }, - { "io_exits", VCPU_STAT(io_exits) }, - { "mmio_exits", VCPU_STAT(mmio_exits) }, - { "signal_exits", VCPU_STAT(signal_exits) }, - { "irq_window", VCPU_STAT(irq_window_exits) }, - { "nmi_window", VCPU_STAT(nmi_window_exits) }, - { "halt_exits", VCPU_STAT(halt_exits) }, - { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, - { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) }, - { "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) }, - { "halt_wakeup", VCPU_STAT(halt_wakeup) }, - { "hypercalls", VCPU_STAT(hypercalls) }, - { "request_irq", VCPU_STAT(request_irq_exits) }, - { "irq_exits", VCPU_STAT(irq_exits) }, - { "host_state_reload", VCPU_STAT(host_state_reload) }, - { "fpu_reload", VCPU_STAT(fpu_reload) }, - { "insn_emulation", VCPU_STAT(insn_emulation) }, - { "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) }, - { "irq_injections", VCPU_STAT(irq_injections) }, - { "nmi_injections", VCPU_STAT(nmi_injections) }, - { "req_event", VCPU_STAT(req_event) }, - { "l1d_flush", VCPU_STAT(l1d_flush) }, - { "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) }, - { "mmu_pte_write", VM_STAT(mmu_pte_write) }, - { "mmu_pte_updated", VM_STAT(mmu_pte_updated) }, - { "mmu_pde_zapped", VM_STAT(mmu_pde_zapped) }, - { "mmu_flooded", VM_STAT(mmu_flooded) }, - { "mmu_recycled", VM_STAT(mmu_recycled) }, - { "mmu_cache_miss", VM_STAT(mmu_cache_miss) }, - { "mmu_unsync", VM_STAT(mmu_unsync) }, - { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, - { "largepages", VM_STAT(lpages) }, - { "max_mmu_page_hash_collisions", - VM_STAT(max_mmu_page_hash_collisions) }, - { NULL } +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, }; -u64 __read_mostly host_xcr0; +static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) + + ARRAY_SIZE(msrs_to_save_pmu)]; +static unsigned num_msrs_to_save; -struct kmem_cache *x86_fpu_cache; -EXPORT_SYMBOL_GPL(x86_fpu_cache); +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_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; +} + +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 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) +{ + unsigned int useroffset = offsetof(struct x86_emulate_ctxt, src); + unsigned int size = sizeof(struct x86_emulate_ctxt); + + return kmem_cache_create_usercopy("x86_emulator", size, + __alignof__(struct x86_emulate_ctxt), + SLAB_ACCOUNT, useroffset, + size - useroffset, NULL); +} static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt); static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu) { int i; - for (i = 0; i < roundup_pow_of_two(ASYNC_PF_PER_VCPU); i++) + for (i = 0; i < ASYNC_PF_PER_VCPU; i++) 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_shared_msrs *locals - = container_of(urn, struct kvm_shared_msrs, urn); - struct kvm_shared_msr_values *values; - unsigned long flags; + struct kvm_user_return_msrs *msrs + = container_of(urn, struct kvm_user_return_msrs, urn); + struct kvm_user_return_msr_values *values; - /* - * Disabling irqs at this point since the following code could be - * interrupted and executed through kvm_arch_hardware_disable() - */ - local_irq_save(flags); - if (locals->registered) { - locals->registered = false; - user_return_notifier_unregister(urn); - } - local_irq_restore(flags); - for (slot = 0; slot < shared_msrs_global.nr; ++slot) { - values = &locals->values[slot]; + 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(shared_msrs_global.msrs[slot], values->host); + wrmsrq(kvm_uret_msrs_list[slot], values->host); values->curr = values->host; } } } -static void shared_msr_update(unsigned slot, u32 msr) +static int kvm_probe_user_return_msr(u32 msr) { - u64 value; - unsigned int cpu = smp_processor_id(); - struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); + u64 val; + int ret; - /* only read, and nobody should modify it at this time, - * so don't need lock */ - if (slot >= shared_msrs_global.nr) { - printk(KERN_ERR "kvm: invalid MSR slot!"); - return; - } - rdmsrl_safe(msr, &value); - smsr->values[slot].host = value; - smsr->values[slot].curr = value; + preempt_disable(); + ret = rdmsrq_safe(msr, &val); + if (ret) + goto out; + ret = wrmsrq_safe(msr, val); +out: + preempt_enable(); + return ret; } -void kvm_define_shared_msr(unsigned slot, u32 msr) +int kvm_add_user_return_msr(u32 msr) { - BUG_ON(slot >= KVM_NR_SHARED_MSRS); - shared_msrs_global.msrs[slot] = msr; - if (slot >= shared_msrs_global.nr) - shared_msrs_global.nr = slot + 1; -} -EXPORT_SYMBOL_GPL(kvm_define_shared_msr); + BUG_ON(kvm_nr_uret_msrs >= KVM_MAX_NR_USER_RETURN_MSRS); -static void kvm_shared_msr_cpu_online(void) -{ - unsigned i; + if (kvm_probe_user_return_msr(msr)) + return -1; - for (i = 0; i < shared_msrs_global.nr; ++i) - shared_msr_update(i, shared_msrs_global.msrs[i]); + kvm_uret_msrs_list[kvm_nr_uret_msrs] = msr; + return kvm_nr_uret_msrs++; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_add_user_return_msr); -int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) +int kvm_find_user_return_msr(u32 msr) { - unsigned int cpu = smp_processor_id(); - struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); - int err; - - if (((value ^ smsr->values[slot].curr) & mask) == 0) - return 0; - smsr->values[slot].curr = value; - err = wrmsrl_safe(shared_msrs_global.msrs[slot], value); - if (err) - return 1; + int i; - if (!smsr->registered) { - smsr->urn.on_user_return = kvm_on_user_return; - user_return_notifier_register(&smsr->urn); - smsr->registered = true; + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + if (kvm_uret_msrs_list[i] == msr) + return i; } - return 0; + return -1; } -EXPORT_SYMBOL_GPL(kvm_set_shared_msr); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_find_user_return_msr); -static void drop_user_return_notifiers(void) +static void kvm_user_return_msr_cpu_online(void) { - unsigned int cpu = smp_processor_id(); - struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); + struct kvm_user_return_msrs *msrs = this_cpu_ptr(&user_return_msrs); + u64 value; + int i; - if (smsr->registered) - kvm_on_user_return(&smsr->urn); + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + rdmsrq_safe(kvm_uret_msrs_list[i], &value); + msrs->values[i].host = value; + msrs->values[i].curr = value; + } } -u64 kvm_get_apic_base(struct kvm_vcpu *vcpu) +static void kvm_user_return_register_notifier(struct kvm_user_return_msrs *msrs) { - return vcpu->arch.apic_base; + if (!msrs->registered) { + msrs->urn.on_user_return = kvm_on_user_return; + user_return_notifier_register(&msrs->urn); + msrs->registered = true; + } } -EXPORT_SYMBOL_GPL(kvm_get_apic_base); -enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu) +int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask) { - return kvm_apic_mode(kvm_get_apic_base(vcpu)); + 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 = wrmsrq_safe(kvm_uret_msrs_list[slot], value); + if (err) + return 1; + + msrs->values[slot].curr = value; + kvm_user_return_register_notifier(msrs); + return 0; } -EXPORT_SYMBOL_GPL(kvm_get_apic_mode); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_user_return_msr); -int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +u64 kvm_get_user_return_msr(unsigned int slot) { - enum lapic_mode old_mode = kvm_get_apic_mode(vcpu); - enum lapic_mode new_mode = kvm_apic_mode(msr_info->data); - u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) | 0x2ff | - (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE); + return this_cpu_ptr(&user_return_msrs)->values[slot].curr; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_user_return_msr); - 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; - } +static void drop_user_return_notifiers(void) +{ + struct kvm_user_return_msrs *msrs = this_cpu_ptr(&user_return_msrs); - kvm_lapic_set_base(vcpu, msr_info->data); - return 0; + if (msrs->registered) + kvm_on_user_return(&msrs->urn); } -EXPORT_SYMBOL_GPL(kvm_set_apic_base); -asmlinkage __visible void kvm_spurious_fault(void) +/* + * Handle a fault on a hardware virtualization (VMX or SVM) instruction. + * + * Hardware virtualization extension instructions may fault if a reboot turns + * off virtualization while processes are running. Usually after catching the + * fault we just panic; during reboot instead the instruction is ignored. + */ +noinstr void kvm_spurious_fault(void) { /* Fault while not rebooting. We want the trace. */ - BUG(); + 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 @@ -383,6 +733,7 @@ static int exception_class(int vector) #define EXCPT_TRAP 1 #define EXCPT_ABORT 2 #define EXCPT_INTERRUPT 3 +#define EXCPT_DB 4 static int exception_type(int vector) { @@ -393,8 +744,14 @@ static int exception_type(int vector) mask = 1 << vector; - /* #DB is trap, as instruction watchpoints are handled elsewhere */ - if (mask & ((1 << DB_VECTOR) | (1 << BP_VECTOR) | (1 << OF_VECTOR))) + /* + * #DBs can be trap-like or fault-like, the caller must check other CPU + * state, e.g. DR6, to determine whether a #DB is a trap or fault. + */ + if (mask & (1 << DB_VECTOR)) + return EXCPT_DB; + + if (mask & ((1 << BP_VECTOR) | (1 << OF_VECTOR))) return EXCPT_TRAP; if (mask & ((1 << DF_VECTOR) | (1 << MC_VECTOR))) @@ -404,16 +761,13 @@ static int exception_type(int vector) return EXCPT_FAULT; } -void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) +void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu, + struct kvm_queued_exception *ex) { - unsigned nr = vcpu->arch.exception.nr; - bool has_payload = vcpu->arch.exception.has_payload; - unsigned long payload = vcpu->arch.exception.payload; - - if (!has_payload) + if (!ex->has_payload) return; - switch (nr) { + switch (ex->vector) { case DB_VECTOR: /* * "Certain debug exceptions may clear bit 0-3. The @@ -422,90 +776,96 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) */ vcpu->arch.dr6 &= ~DR_TRAP_BITS; /* - * DR6.RTM is set by all #DB exceptions that don't clear it. + * In order to reflect the #DB exception payload in guest + * dr6, three components need to be considered: active low + * bit, FIXED_1 bits and active high bits (e.g. DR6_BD, + * DR6_BS and DR6_BT) + * DR6_ACTIVE_LOW contains the FIXED_1 and active low bits. + * In the target guest dr6: + * FIXED_1 bits should always be set. + * Active low bits should be cleared if 1-setting in payload. + * Active high bits should be set if 1-setting in payload. + * + * Note, the payload is compatible with the pending debug + * exceptions/exit qualification under VMX, that active_low bits + * are active high in payload. + * So they need to be flipped for DR6. */ - vcpu->arch.dr6 |= DR6_RTM; - vcpu->arch.dr6 |= payload; + vcpu->arch.dr6 |= DR6_ACTIVE_LOW; + vcpu->arch.dr6 |= ex->payload; + vcpu->arch.dr6 ^= ex->payload & DR6_ACTIVE_LOW; + /* - * Bit 16 should be set in the payload whenever the #DB - * exception should clear DR6.RTM. This makes the payload - * compatible with the pending debug exceptions under VMX. - * Though not currently documented in the SDM, this also - * makes the payload compatible with the exit qualification - * for #DB exceptions under VMX. + * The #DB payload is defined as compatible with the 'pending + * debug exceptions' field under VMX, not DR6. While bit 12 is + * defined in the 'pending debug exceptions' field (enabled + * breakpoint), it is reserved and must be zero in DR6. */ - vcpu->arch.dr6 ^= payload & DR6_RTM; + vcpu->arch.dr6 &= ~BIT(12); break; case PF_VECTOR: - vcpu->arch.cr2 = payload; + vcpu->arch.cr2 = ex->payload; break; } - vcpu->arch.exception.has_payload = false; - vcpu->arch.exception.payload = 0; + ex->has_payload = false; + ex->payload = 0; +} +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, + bool has_payload, unsigned long payload) +{ + struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit; + + ex->vector = vector; + ex->injected = false; + ex->pending = true; + ex->has_error_code = has_error_code; + ex->error_code = error_code; + ex->has_payload = has_payload; + ex->payload = payload; } -EXPORT_SYMBOL_GPL(kvm_deliver_exception_payload); -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; kvm_make_request(KVM_REQ_EVENT, vcpu); + /* + * If the exception is destined for L2, morph it to a VM-Exit if L1 + * wants to intercept the exception. + */ + 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); + return; + } + if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) { queue: - if (has_error && !is_protmode(vcpu)) - has_error = false; - if (reinject) { - /* - * On vmentry, vcpu->arch.exception.pending is only - * true if an 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(vcpu->arch.exception.pending); - 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.nr = nr; + vcpu->arch.exception.vector = nr; vcpu->arch.exception.error_code = error_code; vcpu->arch.exception.has_payload = has_payload; vcpu->arch.exception.payload = payload; - /* - * In guest mode, payload delivery should be deferred, - * so that the L1 hypervisor can intercept #PF before - * CR2 is modified (or intercept #DB before DR6 is - * modified under nVMX). However, for ABI - * compatibility with KVM_GET_VCPU_EVENTS and - * KVM_SET_VCPU_EVENTS, we can't delay payload - * delivery unless userspace has enabled this - * functionality via the per-VM capability, - * KVM_CAP_EXCEPTION_PAYLOAD. - */ - if (!vcpu->kvm->arch.exception_payload_enabled || - !is_guest_mode(vcpu)) - kvm_deliver_exception_payload(vcpu); + if (!is_guest_mode(vcpu)) + kvm_deliver_exception_payload(vcpu, + &vcpu->arch.exception); return; } /* to check exception */ - prev_nr = vcpu->arch.exception.nr; + prev_nr = vcpu->arch.exception.vector; if (prev_nr == DF_VECTOR) { /* triple fault -> shutdown */ kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); @@ -513,51 +873,72 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, } class1 = exception_class(prev_nr); class2 = exception_class(nr); - if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY) - || (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) { + if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY) || + (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) { /* - * Generate double fault per SDM Table 5-5. Set - * exception.pending = true so that the double fault - * can trigger a nested vmexit. + * Synthesize #DF. Clear the previously injected or pending + * exception so as not to incorrectly trigger shutdown. */ - vcpu->arch.exception.pending = true; vcpu->arch.exception.injected = false; - vcpu->arch.exception.has_error_code = true; - vcpu->arch.exception.nr = DF_VECTOR; - vcpu->arch.exception.error_code = 0; - vcpu->arch.exception.has_payload = false; - vcpu->arch.exception.payload = 0; - } else + vcpu->arch.exception.pending = false; + + kvm_queue_exception_e(vcpu, DF_VECTOR, 0); + } else { /* replace previous exception with a new one in a hope that instruction re-execution will regenerate lost exception */ goto queue; + } } 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); -static void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, - unsigned long payload) +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_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) { @@ -568,51 +949,69 @@ 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) +{ + if (err) { + kvm_inject_gp(vcpu, 0); + return 1; + } + + return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE | EMULTYPE_SKIP | + EMULTYPE_COMPLETE_USER_EXIT); +} void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { ++vcpu->stat.pf_guest; - vcpu->arch.exception.nested_apf = - is_guest_mode(vcpu) && fault->async_page_fault; - if (vcpu->arch.exception.nested_apf) { - vcpu->arch.apf.nested_apf_token = fault->address; - kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code); - } else { + + /* + * Async #PF in L2 is always forwarded to L1 as a VM-Exit regardless of + * whether or not L1 wants to intercept "regular" #PF. + */ + if (is_guest_mode(vcpu) && fault->async_page_fault) + kvm_queue_exception_vmexit(vcpu, PF_VECTOR, + true, fault->error_code, + true, fault->address); + else kvm_queue_exception_e_p(vcpu, PF_VECTOR, fault->error_code, fault->address); - } } -EXPORT_SYMBOL_GPL(kvm_inject_page_fault); -static bool kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) +void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, + struct x86_exception *fault) { - if (mmu_is_nested(vcpu) && !fault->nested_page_fault) - vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault); - else - vcpu->arch.mmu->inject_page_fault(vcpu, fault); + struct kvm_mmu *fault_mmu; + WARN_ON_ONCE(fault->vector != PF_VECTOR); + + fault_mmu = fault->nested_page_fault ? vcpu->arch.mmu : + vcpu->arch.walk_mmu; + + /* + * Invalidate the TLB entry for the faulting address, if it exists, + * else the access will fault indefinitely (and to emulate hardware). + */ + if ((fault->error_code & PFERR_PRESENT_MASK) && + !(fault->error_code & PFERR_RSVD_MASK)) + kvm_mmu_invalidate_addr(vcpu, fault_mmu, fault->address, + KVM_MMU_ROOT_CURRENT); - return fault->nested_page_fault; + fault_mmu->inject_page_fault(vcpu, fault); } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_inject_emulated_page_fault); void kvm_inject_nmi(struct kvm_vcpu *vcpu) { atomic_inc(&vcpu->arch.nmi_queued); kvm_make_request(KVM_REQ_NMI, vcpu); } -EXPORT_SYMBOL_GPL(kvm_inject_nmi); 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 @@ -620,207 +1019,243 @@ EXPORT_SYMBOL_GPL(kvm_requeue_exception_e); */ bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) { - if (kvm_x86_ops->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; } -EXPORT_SYMBOL_GPL(kvm_require_cpl); bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr) { - if ((dr != 4 && dr != 5) || !kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + if ((dr != 4 && dr != 5) || !kvm_is_cr4_bit_set(vcpu, X86_CR4_DE)) return true; kvm_queue_exception(vcpu, UD_VECTOR); return false; } -EXPORT_SYMBOL_GPL(kvm_require_dr); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_require_dr); -/* - * This function will be used to read from the physical memory of the currently - * running guest. The difference to kvm_vcpu_read_guest_page is that this function - * can read from guest physical or from the guest's guest physical memory. - */ -int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gfn_t ngfn, void *data, int offset, int len, - u32 access) +static bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu) { - struct x86_exception exception; - gfn_t real_gfn; - gpa_t ngpa; - - ngpa = gfn_to_gpa(ngfn); - real_gfn = mmu->translate_gpa(vcpu, ngpa, access, &exception); - if (real_gfn == UNMAPPED_GVA) - return -EFAULT; - - real_gfn = gpa_to_gfn(real_gfn); + u64 mask = KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT; - return kvm_vcpu_read_guest_page(vcpu, real_gfn, data, offset, len); + return (vcpu->arch.apf.msr_en_val & mask) == mask; } -EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu); -static int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, - void *data, int offset, int len, u32 access) +static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) { - return kvm_read_guest_page_mmu(vcpu, vcpu->arch.walk_mmu, gfn, - data, offset, len, access); + return vcpu->arch.reserved_gpa_bits | rsvd_bits(5, 8) | rsvd_bits(1, 2); } /* - * Load the pae pdptrs. Return true is they are all valid. + * Load the pae pdptrs. Return 1 if they are all valid, 0 otherwise. */ -int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) +int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT; - unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2; + gpa_t real_gpa; int i; int ret; u64 pdpte[ARRAY_SIZE(mmu->pdptrs)]; - ret = kvm_read_guest_page_mmu(vcpu, mmu, pdpt_gfn, pdpte, - offset * sizeof(u64), sizeof(pdpte), - PFERR_USER_MASK|PFERR_WRITE_MASK); - if (ret < 0) { - ret = 0; - goto out; - } + /* + * If the MMU is nested, CR3 holds an L2 GPA and needs to be translated + * to an L1 GPA. + */ + real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(pdpt_gfn), + PFERR_USER_MASK | PFERR_WRITE_MASK, NULL); + if (real_gpa == INVALID_GPA) + return 0; + + /* Note the offset, PDPTRs are 32 byte aligned when using PAE paging. */ + ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(real_gpa), pdpte, + cr3 & GENMASK(11, 5), sizeof(pdpte)); + if (ret < 0) + return 0; + for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { if ((pdpte[i] & PT_PRESENT_MASK) && - (pdpte[i] & - vcpu->arch.mmu->guest_rsvd_check.rsvd_bits_mask[0][2])) { - ret = 0; - goto out; + (pdpte[i] & pdptr_rsvd_bits(vcpu))) { + return 0; } } - ret = 1; + + /* + * Marking VCPU_EXREG_PDPTR dirty doesn't work for !tdp_enabled. + * Shadow page roots need to be reconstructed instead. + */ + if (!tdp_enabled && memcmp(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs))) + kvm_mmu_free_roots(vcpu->kvm, mmu, KVM_MMU_ROOT_CURRENT); memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); - __set_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail); - __set_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_dirty); -out: + kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu); + vcpu->arch.pdptrs_from_userspace = false; - return ret; + return 1; } -EXPORT_SYMBOL_GPL(load_pdptrs); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(load_pdptrs); -bool pdptrs_changed(struct kvm_vcpu *vcpu) +static bool kvm_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { - u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)]; - bool changed = true; - int offset; - gfn_t gfn; - int r; +#ifdef CONFIG_X86_64 + if (cr0 & 0xffffffff00000000UL) + return false; +#endif - if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu)) + if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) return false; - if (!test_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail)) - return true; + if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) + return false; - gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT; - offset = (kvm_read_cr3(vcpu) & 0xffffffe0ul) & (PAGE_SIZE - 1); - r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte), - PFERR_USER_MASK | PFERR_WRITE_MASK); - if (r < 0) - goto out; - changed = memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0; -out: + 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) +{ + /* + * CR0.WP is incorporated into the MMU role, but only for non-nested, + * indirect shadow MMUs. If paging is disabled, no updates are needed + * as there are no permission bits to emulate. If TDP is enabled, the + * MMU's metadata needs to be updated, e.g. so that emulating guest + * translations does the right thing, but there's no need to unload the + * root as CR0.WP doesn't affect SPTEs. + */ + if ((cr0 ^ old_cr0) == X86_CR0_WP) { + if (!(cr0 & X86_CR0_PG)) + return; - return changed; + if (tdp_enabled) { + kvm_init_mmu(vcpu); + return; + } + } + + if ((cr0 ^ old_cr0) & X86_CR0_PG) { + /* + * 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); } -EXPORT_SYMBOL_GPL(pdptrs_changed); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_post_set_cr0); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { unsigned long old_cr0 = kvm_read_cr0(vcpu); - unsigned long update_bits = X86_CR0_PG | X86_CR0_WP; - - cr0 |= X86_CR0_ET; -#ifdef CONFIG_X86_64 - if (cr0 & 0xffffffff00000000UL) + if (!kvm_is_valid_cr0(vcpu, cr0)) return 1; -#endif - cr0 &= ~CR0_RESERVED_BITS; - - if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) - return 1; + cr0 |= X86_CR0_ET; - if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) - return 1; + /* Write to CR0 reserved bits are ignored, even on Intel. */ + cr0 &= ~CR0_RESERVED_BITS; - if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { #ifdef CONFIG_X86_64 - if ((vcpu->arch.efer & EFER_LME)) { - int cs_db, cs_l; + if ((vcpu->arch.efer & EFER_LME) && !is_paging(vcpu) && + (cr0 & X86_CR0_PG)) { + int cs_db, cs_l; - if (!is_pae(vcpu)) - return 1; - kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); - if (cs_l) - return 1; - } else -#endif - if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, - kvm_read_cr3(vcpu))) + if (!is_pae(vcpu)) + return 1; + kvm_x86_call(get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); + if (cs_l) return 1; } - - if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) +#endif + if (!(vcpu->arch.efer & EFER_LME) && (cr0 & X86_CR0_PG) && + is_pae(vcpu) && ((cr0 ^ old_cr0) & X86_CR0_PDPTR_BITS) && + !load_pdptrs(vcpu, kvm_read_cr3(vcpu))) return 1; - kvm_x86_ops->set_cr0(vcpu, cr0); + if (!(cr0 & X86_CR0_PG) && + (is_64_bit_mode(vcpu) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE))) + return 1; - if ((cr0 ^ old_cr0) & X86_CR0_PG) { - kvm_clear_async_pf_completion_queue(vcpu); - kvm_async_pf_hash_reset(vcpu); - } + if (!(cr0 & X86_CR0_WP) && kvm_is_cr4_bit_set(vcpu, X86_CR4_CET)) + return 1; - if ((cr0 ^ old_cr0) & update_bits) - kvm_mmu_reset_context(vcpu); + kvm_x86_call(set_cr0)(vcpu, cr0); - 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); + 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); -static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) +static void kvm_load_xfeatures(struct kvm_vcpu *vcpu, bool load_guest) { - if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && - !vcpu->guest_xcr0_loaded) { - /* kvm_set_xcr() also depends on this */ - if (vcpu->arch.xcr0 != host_xcr0) - xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); - vcpu->guest_xcr0_loaded = 1; - } + if (vcpu->arch.guest_state_protected) + return; + + if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) + return; + + if (vcpu->arch.xcr0 != kvm_host.xcr0) + xsetbv(XCR_XFEATURE_ENABLED_MASK, + load_guest ? vcpu->arch.xcr0 : kvm_host.xcr0); + + 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_put_guest_xcr0(struct kvm_vcpu *vcpu) +static void kvm_load_guest_pkru(struct kvm_vcpu *vcpu) { - if (vcpu->guest_xcr0_loaded) { - if (vcpu->arch.xcr0 != host_xcr0) - xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); - vcpu->guest_xcr0_loaded = 0; + 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))) + wrpkru(vcpu->arch.pkru); +} + +static void kvm_load_host_pkru(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.guest_state_protected) + return; + + if (cpu_feature_enabled(X86_FEATURE_PKU) && + ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || + kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) { + vcpu->arch.pkru = rdpkru(); + if (vcpu->arch.pkru != vcpu->arch.host_pkru) + wrpkru(vcpu->arch.host_pkru); } } -static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) +#ifdef CONFIG_X86_64 +static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.guest_supported_xcr0 & XFEATURE_MASK_USER_DYNAMIC; +} +#endif + +int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { u64 xcr0 = xcr; u64 old_xcr0 = vcpu->arch.xcr0; @@ -837,7 +1272,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) /* * Do not allow the guest to set bits that we do not support * saving. However, xcr0 bit 0 is always set, even if the - * emulated CPU does not support XSAVE (see fx_init). + * emulated CPU does not support XSAVE (see kvm_vcpu_reset()). */ valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP; if (xcr0 & ~valid_bits) @@ -853,120 +1288,205 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512) return 1; } + + if ((xcr0 & XFEATURE_MASK_XTILE) && + ((xcr0 & XFEATURE_MASK_XTILE) != XFEATURE_MASK_XTILE)) + return 1; + vcpu->arch.xcr0 = xcr0; if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND) - kvm_update_cpuid(vcpu); + vcpu->arch.cpuid_dynamic_bits_dirty = true; return 0; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_set_xcr); -int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) +int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu) { - if (kvm_x86_ops->get_cpl(vcpu) != 0 || - __kvm_set_xcr(vcpu, index, xcr)) { + /* Note, #UD due to CR4.OSXSAVE=0 has priority over the intercept. */ + 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; } - return 0; + + return kvm_skip_emulated_instruction(vcpu); } -EXPORT_SYMBOL_GPL(kvm_set_xcr); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_xsetbv); -int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +static bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { - unsigned long old_cr4 = kvm_read_cr4(vcpu); - unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; - - if (cr4 & CR4_RESERVED_BITS) - return 1; + return __kvm_is_valid_cr4(vcpu, cr4) && + kvm_x86_call(is_valid_cr4)(vcpu, cr4); +} - if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE)) - return 1; +void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4) +{ + if ((cr4 ^ old_cr4) & KVM_MMU_CR4_ROLE_BITS) + kvm_mmu_reset_context(vcpu); - if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP)) - return 1; + /* + * If CR4.PCIDE is changed 0 -> 1, there is no need to flush the TLB + * according to the SDM; however, stale prev_roots could be reused + * incorrectly in the future after a MOV to CR3 with NOFLUSH=1, so we + * free them all. This is *not* a superset of KVM_REQ_TLB_FLUSH_GUEST + * or KVM_REQ_TLB_FLUSH_CURRENT, because the hardware TLB is not flushed, + * so fall through. + */ + if (!tdp_enabled && + (cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) + kvm_mmu_unload(vcpu); - if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP)) - return 1; + /* + * The TLB has to be flushed for all PCIDs if any of the following + * (architecturally required) changes happen: + * - CR4.PCIDE is changed from 1 to 0 + * - CR4.PGE is toggled + * + * This is a superset of KVM_REQ_TLB_FLUSH_CURRENT. + */ + if (((cr4 ^ old_cr4) & X86_CR4_PGE) || + (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); - if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE)) - return 1; + /* + * The TLB has to be flushed for the current PCID if any of the + * following (architecturally required) changes happen: + * - CR4.SMEP is changed from 0 to 1 + * - CR4.PAE is toggled + */ + else if (((cr4 ^ old_cr4) & X86_CR4_PAE) || + ((cr4 & X86_CR4_SMEP) && !(old_cr4 & X86_CR4_SMEP))) + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); - if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE)) - return 1; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_post_set_cr4); - if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57)) - return 1; +int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + unsigned long old_cr4 = kvm_read_cr4(vcpu); - if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP)) + if (!kvm_is_valid_cr4(vcpu, cr4)) return 1; if (is_long_mode(vcpu)) { if (!(cr4 & X86_CR4_PAE)) return 1; + if ((cr4 ^ old_cr4) & X86_CR4_LA57) + return 1; } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) - && ((cr4 ^ old_cr4) & pdptr_bits) - && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, - kvm_read_cr3(vcpu))) + && ((cr4 ^ old_cr4) & X86_CR4_PDPTR_BITS) + && !load_pdptrs(vcpu, kvm_read_cr3(vcpu))) return 1; if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_PCID)) - return 1; - /* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */ if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu)) return 1; } - if (kvm_x86_ops->set_cr4(vcpu, cr4)) + if ((cr4 & X86_CR4_CET) && !kvm_is_cr0_bit_set(vcpu, X86_CR0_WP)) return 1; - if (((cr4 ^ old_cr4) & pdptr_bits) || - (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) - kvm_mmu_reset_context(vcpu); + kvm_x86_call(set_cr4)(vcpu, cr4); - if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE)) - kvm_update_cpuid(vcpu); + 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) +{ + struct kvm_mmu *mmu = vcpu->arch.mmu; + unsigned long roots_to_free = 0; + int i; + + /* + * MOV CR3 and INVPCID are usually not intercepted when using TDP, but + * this is reachable when running EPT=1 and unrestricted_guest=0, and + * also via the emulator. KVM's TDP page tables are not in the scope of + * the invalidation, but the guest's TLB entries need to be flushed as + * the CPU may have cached entries in its TLB for the target PCID. + */ + if (unlikely(tdp_enabled)) { + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + return; + } + + /* + * If neither the current CR3 nor any of the prev_roots use the given + * PCID, then nothing needs to be done here because a resync will + * happen anyway before switching to any other CR3. + */ + if (kvm_get_active_pcid(vcpu) == pcid) { + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); + } + + /* + * If PCID is disabled, there is no need to free prev_roots even if the + * PCIDs for them are also 0, because MOV to CR3 always flushes the TLB + * with PCIDE=0. + */ + if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)) + return; + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) + if (kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd) == pcid) + roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); + + kvm_mmu_free_roots(vcpu->kvm, mmu, roots_to_free); +} int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { bool skip_tlb_flush = false; + unsigned long pcid = 0; #ifdef CONFIG_X86_64 - bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE); - - if (pcid_enabled) { + if (kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)) { skip_tlb_flush = cr3 & X86_CR3_PCID_NOFLUSH; cr3 &= ~X86_CR3_PCID_NOFLUSH; + pcid = cr3 & X86_CR3_PCID_MASK; } #endif - if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) { - if (!skip_tlb_flush) { - kvm_mmu_sync_roots(vcpu); - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); - } - return 0; - } + /* PDPTRs are always reloaded for PAE paging. */ + if (cr3 == kvm_read_cr3(vcpu) && !is_pae_paging(vcpu)) + goto handle_tlb_flush; - if (is_long_mode(vcpu) && - (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63))) + /* + * Do not condition the GPA check on long mode, this helper is used to + * stuff CR3, e.g. for RSM emulation, and there is no guarantee that + * the current vCPU mode is accurate. + */ + if (!kvm_vcpu_is_legal_cr3(vcpu, cr3)) return 1; - else if (is_pae(vcpu) && is_paging(vcpu) && - !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) + + if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3)) return 1; - kvm_mmu_new_cr3(vcpu, cr3, skip_tlb_flush); + if (cr3 != kvm_read_cr3(vcpu)) + kvm_mmu_new_pgd(vcpu, cr3); + vcpu->arch.cr3 = cr3; - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); + /* Do not call post_set_cr3, we do not get here for confidential guests. */ + +handle_tlb_flush: + /* + * A load of CR3 that flushes the TLB flushes only the current PCID, + * even if PCID is disabled, in which case PCID=0 is flushed. It's a + * moot point in the end because _disabling_ PCID will flush all PCIDs, + * and it's impossible to use a non-zero PCID when PCID is disabled, + * i.e. only PCID=0 can be relevant. + */ + if (!skip_tlb_flush) + kvm_invalidate_pcid(vcpu, pcid); 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) { @@ -978,7 +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) { @@ -987,7 +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) { @@ -996,17 +1516,10 @@ static void kvm_update_dr0123(struct kvm_vcpu *vcpu) if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { for (i = 0; i < KVM_NR_DB_REGS; i++) vcpu->arch.eff_db[i] = vcpu->arch.db[i]; - vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD; } } -static void kvm_update_dr6(struct kvm_vcpu *vcpu) -{ - if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) - kvm_x86_ops->set_dr6(vcpu, vcpu->arch.dr6); -} - -static void kvm_update_dr7(struct kvm_vcpu *vcpu) +void kvm_update_dr7(struct kvm_vcpu *vcpu) { unsigned long dr7; @@ -1014,42 +1527,45 @@ static void kvm_update_dr7(struct kvm_vcpu *vcpu) dr7 = vcpu->arch.guest_debug_dr7; else dr7 = vcpu->arch.dr7; - kvm_x86_ops->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_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_cpu_cap_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) + fixed |= DR6_BUS_LOCK; return fixed; } -static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) +int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) { + size_t size = ARRAY_SIZE(vcpu->arch.db); + switch (dr) { case 0 ... 3: - vcpu->arch.db[dr] = val; + vcpu->arch.db[array_index_nospec(dr, size)] = val; if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) vcpu->arch.eff_db[dr] = val; break; case 4: - /* fall through */ case 6: - if (val & 0xffffffff00000000ULL) - return -1; /* #GP */ + if (!kvm_dr6_valid(val)) + return 1; /* #GP */ vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu); - kvm_update_dr6(vcpu); break; case 5: - /* fall through */ default: /* 7 */ - if (val & 0xffffffff00000000ULL) - return -1; /* #GP */ + if (!kvm_dr7_valid(val)) + return 1; /* #GP */ vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; kvm_update_dr7(vcpu); break; @@ -1057,162 +1573,77 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) return 0; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_dr); -int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) +unsigned long kvm_get_dr(struct kvm_vcpu *vcpu, int dr) { - if (__kvm_set_dr(vcpu, dr, val)) { - kvm_inject_gp(vcpu, 0); - return 1; - } - return 0; -} -EXPORT_SYMBOL_GPL(kvm_set_dr); + size_t size = ARRAY_SIZE(vcpu->arch.db); -int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) -{ switch (dr) { case 0 ... 3: - *val = vcpu->arch.db[dr]; - break; + return vcpu->arch.db[array_index_nospec(dr, size)]; case 4: - /* fall through */ case 6: - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) - *val = vcpu->arch.dr6; - else - *val = kvm_x86_ops->get_dr6(vcpu); - break; + return vcpu->arch.dr6; case 5: - /* fall through */ default: /* 7 */ - *val = vcpu->arch.dr7; - break; + return vcpu->arch.dr7; } - return 0; } -EXPORT_SYMBOL_GPL(kvm_get_dr); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_dr); -bool kvm_rdpmc(struct kvm_vcpu *vcpu) +int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu) { - u32 ecx = kvm_register_read(vcpu, VCPU_REGS_RCX); + u32 pmc = kvm_rcx_read(vcpu); u64 data; - int err; - - err = kvm_pmu_rdpmc(vcpu, ecx, &data); - if (err) - return err; - kvm_register_write(vcpu, VCPU_REGS_RAX, (u32)data); - kvm_register_write(vcpu, VCPU_REGS_RDX, data >> 32); - return err; -} -EXPORT_SYMBOL_GPL(kvm_rdpmc); - -/* - * List of msr numbers which we expose to userspace through KVM_GET_MSRS - * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. - * - * This list is modified at module load time to reflect the - * capabilities of the host cpu. This capabilities test skips MSRs that are - * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs - * may depend on host virtualization features rather than host cpu features. - */ - -static u32 msrs_to_save[] = { - 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_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, - MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES, - 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, -}; - -static unsigned num_msrs_to_save; -static u32 emulated_msrs[] = { - 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, - - MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, - MSR_KVM_PV_EOI_EN, - - MSR_IA32_TSC_ADJUST, - MSR_IA32_TSCDEADLINE, - 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, -}; + if (kvm_pmu_rdpmc(vcpu, pmc, &data)) { + kvm_inject_gp(vcpu, 0); + return 1; + } -static unsigned num_emulated_msrs; + kvm_rax_write(vcpu, (u32)data); + kvm_rdx_write(vcpu, data >> 32); + return kvm_skip_emulated_instruction(vcpu); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_rdpmc); /* - * List of msr numbers which are used to expose MSR-based features that - * can be used by a hypervisor to validate requested CPU features. + * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM + * does not yet virtualize. These include: + * 10 - MISC_PACKAGE_CTRLS + * 11 - ENERGY_FILTERING_CTL + * 12 - DOITM + * 18 - FB_CLEAR_CTRL + * 21 - XAPIC_DISABLE_STATUS + * 23 - OVERCLOCKING_STATUS */ -static u32 msr_based_features[] = { - MSR_IA32_VMX_BASIC, - MSR_IA32_VMX_TRUE_PINBASED_CTLS, - MSR_IA32_VMX_PINBASED_CTLS, - MSR_IA32_VMX_TRUE_PROCBASED_CTLS, - MSR_IA32_VMX_PROCBASED_CTLS, - MSR_IA32_VMX_TRUE_EXIT_CTLS, - MSR_IA32_VMX_EXIT_CTLS, - MSR_IA32_VMX_TRUE_ENTRY_CTLS, - MSR_IA32_VMX_ENTRY_CTLS, - MSR_IA32_VMX_MISC, - MSR_IA32_VMX_CR0_FIXED0, - MSR_IA32_VMX_CR0_FIXED1, - MSR_IA32_VMX_CR4_FIXED0, - MSR_IA32_VMX_CR4_FIXED1, - MSR_IA32_VMX_VMCS_ENUM, - MSR_IA32_VMX_PROCBASED_CTLS2, - MSR_IA32_VMX_EPT_VPID_CAP, - MSR_IA32_VMX_VMFUNC, - MSR_F10H_DECFG, - MSR_IA32_UCODE_REV, - MSR_IA32_ARCH_CAPABILITIES, -}; - -static unsigned int num_msr_based_features; +#define KVM_SUPPORTED_ARCH_CAP \ + (ARCH_CAP_RDCL_NO | ARCH_CAP_IBRS_ALL | ARCH_CAP_RSBA | \ + 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_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO | ARCH_CAP_ITS_NO) -u64 kvm_get_arch_capabilities(void) +static u64 kvm_get_arch_capabilities(void) { - u64 data; + u64 data = kvm_host.arch_capabilities & KVM_SUPPORTED_ARCH_CAP; - rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data); + /* + * If nx_huge_pages is enabled, KVM's shadow paging will ensure that + * the nested hypervisor runs with NX huge pages. If it is not, + * L1 is anyway vulnerable to ITLB_MULTIHIT exploits from other + * L1 guests, so it need not worry about its own (L2) guests. + */ + data |= ARCH_CAP_PSCHANGE_MC_NO; /* * If we're doing cache flushes (either "always" or "cond") * we will do one whenever the guest does a vmlaunch/vmresume. * If an outer hypervisor is doing the cache flush for us - * (VMENTER_L1D_FLUSH_NESTED_VM), we can safely pass that + * (ARCH_CAP_SKIP_VMENTRY_L1DFLUSH), we can safely pass that * capability to the guest too, and if EPT is disabled we're not * vulnerable. Overall, only VMENTER_L1D_FLUSH_NEVER will * require a nested hypervisor to do a flush of its own. @@ -1220,76 +1651,136 @@ u64 kvm_get_arch_capabilities(void) if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER) data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH; + if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + data |= ARCH_CAP_RDCL_NO; + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + 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)) { + /* + * If RTM=0 because the kernel has disabled TSX, the host might + * have TAA_NO or TSX_CTRL. Clear TAA_NO (the guest sees RTM=0 + * and therefore knows that there cannot be TAA) but keep + * TSX_CTRL: some buggy userspaces leave it set on tsx=on hosts, + * and we want to allow migrating those guests to tsx=off hosts. + */ + data &= ~ARCH_CAP_TAA_NO; + } else if (!boot_cpu_has_bug(X86_BUG_TAA)) { + data |= ARCH_CAP_TAA_NO; + } else { + /* + * Nothing to do here; we emulate TSX_CTRL if present on the + * host so the guest can choose between disabling TSX or + * using VERW to clear CPU buffers. + */ + } + + if (!boot_cpu_has_bug(X86_BUG_GDS) || gds_ucode_mitigated()) + data |= ARCH_CAP_GDS_NO; + return data; } -EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities); -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: + *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: - if (kvm_x86_ops->get_msr_feature(msr)) - return 1; + 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; + return kvm_do_msr_access(vcpu, index, data, true, MSR_TYPE_R, + kvm_get_feature_msr); +} - msr.index = index; - r = kvm_get_msr_feature(&msr); - if (r) - return r; +static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) +{ + if (efer & EFER_AUTOIBRS && !guest_cpu_cap_has(vcpu, X86_FEATURE_AUTOIBRS)) + return false; - *data = msr.data; + if (efer & EFER_FFXSR && !guest_cpu_cap_has(vcpu, X86_FEATURE_FXSR_OPT)) + return false; - return 0; -} + if (efer & EFER_SVME && !guest_cpu_cap_has(vcpu, X86_FEATURE_SVM)) + return false; + + if (efer & (EFER_LME | EFER_LMA) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) + return false; + + if (efer & EFER_NX && !guest_cpu_cap_has(vcpu, X86_FEATURE_NX)) + return false; + return true; + +} bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { if (efer & efer_reserved_bits) return false; - if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT)) - return false; - - if (efer & EFER_SVME && !guest_cpuid_has(vcpu, X86_FEATURE_SVM)) - return false; - - return true; + 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, u64 efer) +static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { u64 old_efer = vcpu->arch.efer; + u64 efer = msr_info->data; + int r; - if (!kvm_valid_efer(vcpu, efer)) + if (efer & efer_reserved_bits) return 1; - if (is_paging(vcpu) - && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) - return 1; + if (!msr_info->host_initiated) { + if (!__kvm_valid_efer(vcpu, efer)) + return 1; + + if (is_paging(vcpu) && + (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) + return 1; + } efer &= ~EFER_LMA; efer |= vcpu->arch.efer & EFER_LMA; - kvm_x86_ops->set_efer(vcpu, efer); + r = kvm_x86_call(set_efer)(vcpu, efer); + if (r) { + WARN_ON(r > 0); + return r; + } - /* Update reserved bits */ - if ((efer ^ old_efer) & EFER_NX) + 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; } @@ -1297,22 +1788,69 @@ 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) +{ + struct kvm_x86_msr_filter *msr_filter; + struct msr_bitmap_range *ranges; + struct kvm *kvm = vcpu->kvm; + bool allowed; + int idx; + u32 i; + + /* x2APIC MSRs do not support filtering. */ + if (index >= 0x800 && index <= 0x8ff) + return true; + + idx = srcu_read_lock(&kvm->srcu); + + msr_filter = srcu_dereference(kvm->arch.msr_filter, &kvm->srcu); + if (!msr_filter) { + allowed = true; + goto out; + } + + allowed = msr_filter->default_allow; + ranges = msr_filter->ranges; + + for (i = 0; i < msr_filter->count; i++) { + u32 start = ranges[i].base; + u32 end = start + ranges[i].nmsrs; + u32 flags = ranges[i].flags; + unsigned long *bitmap = ranges[i].bitmap; + + if ((index >= start) && (index < end) && (flags & type)) { + allowed = test_bit(index - start, bitmap); + break; + } + } + +out: + srcu_read_unlock(&kvm->srcu, idx); + + return allowed; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_msr_allowed); /* - * Writes msr value into into the appropriate "register". + * Write @data into the MSR specified by @index. Select MSR specific fault + * checks are bypassed if @host_initiated is %true. * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) +static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, + bool host_initiated) { - switch (msr->index) { + struct msr_data msr; + + switch (index) { case MSR_FS_BASE: case MSR_GS_BASE: case MSR_KERNEL_GS_BASE: case MSR_CSTAR: case MSR_LSTAR: - if (is_noncanonical_address(msr->data, vcpu)) + if (is_noncanonical_msr_address(data, vcpu)) return 1; break; case MSR_IA32_SYSENTER_EIP: @@ -1329,54 +1867,484 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) * value, and that something deterministic happens if the guest * invokes 64-bit SYSENTER. */ - msr->data = get_canonical(msr->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_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID)) + return 1; + + /* + * Per Intel's SDM, bits 63:32 are reserved, but AMD's APM has + * 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 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_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; } - return kvm_x86_ops->set_msr(vcpu, msr); + + msr.data = data; + msr.index = index; + msr.host_initiated = host_initiated; + + 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) +{ + return kvm_do_msr_access(vcpu, index, &data, host_initiated, MSR_TYPE_W, + _kvm_set_msr); } -EXPORT_SYMBOL_GPL(kvm_set_msr); /* - * Adapt set_msr() to msr_io()'s calling convention + * Read the MSR specified by @index into @data. Select MSR specific fault + * checks are bypassed if @host_initiated is %true. + * Returns 0 on success, non-0 otherwise. + * Assumes vcpu_load() was already called. */ -static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +static int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated) { struct msr_data msr; - int r; + int ret; + + switch (index) { + case MSR_TSC_AUX: + if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) + return 1; + + if (!host_initiated && + !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 = true; - r = kvm_get_msr(vcpu, &msr); - if (r) - return r; + msr.host_initiated = host_initiated; - *data = msr.data; - return 0; + ret = kvm_x86_call(get_msr)(vcpu, &msr); + if (!ret) + *data = msr.data; + return ret; +} + +int kvm_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data) +{ + return __kvm_set_msr(vcpu, index, data, true); +} + +int kvm_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data) +{ + return __kvm_get_msr(vcpu, index, data, true); +} + +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); +} + +int __kvm_emulate_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data) +{ + return kvm_get_msr_ignored_check(vcpu, index, data, false); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_emulate_msr_read); + +int __kvm_emulate_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data) +{ + return kvm_set_msr_ignored_check(vcpu, index, data, false); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_emulate_msr_write); + +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_emulate_msr_read(vcpu, index, data); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_msr_read); + +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_emulate_msr_write(vcpu, index, data); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_msr_write); + + +static void complete_userspace_rdmsr(struct kvm_vcpu *vcpu) +{ + if (!vcpu->run->msr.error) { + kvm_rax_write(vcpu, (u32)vcpu->run->msr.data); + kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32); + } +} + +static int complete_emulated_msr_access(struct kvm_vcpu *vcpu) +{ + return complete_emulated_insn_gp(vcpu, vcpu->run->msr.error); +} + +static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) +{ + complete_userspace_rdmsr(vcpu); + return complete_emulated_msr_access(vcpu); +} + +static int complete_fast_msr_access(struct kvm_vcpu *vcpu) +{ + return kvm_x86_call(complete_emulated_msr)(vcpu, vcpu->run->msr.error); +} + +static int complete_fast_rdmsr(struct kvm_vcpu *vcpu) +{ + complete_userspace_rdmsr(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_UNSUPPORTED: + return KVM_MSR_EXIT_REASON_UNKNOWN; + case KVM_MSR_RET_FILTERED: + return KVM_MSR_EXIT_REASON_FILTER; + default: + return KVM_MSR_EXIT_REASON_INVAL; + } +} + +static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index, + u32 exit_reason, u64 data, + int (*completion)(struct kvm_vcpu *vcpu), + int r) +{ + u64 msr_reason = kvm_msr_reason(r); + + /* Check if the user wanted to know about this MSR fault */ + if (!(vcpu->kvm->arch.user_space_msr_mask & msr_reason)) + return 0; + + vcpu->run->exit_reason = exit_reason; + vcpu->run->msr.error = 0; + memset(vcpu->run->msr.pad, 0, sizeof(vcpu->run->msr.pad)); + vcpu->run->msr.reason = msr_reason; + vcpu->run->msr.index = index; + vcpu->run->msr.data = data; + vcpu->arch.complete_userspace_io = completion; + + return 1; +} + +static int __kvm_emulate_rdmsr(struct kvm_vcpu *vcpu, u32 msr, int reg, + int (*complete_rdmsr)(struct kvm_vcpu *)) +{ + u64 data; + int r; + + r = kvm_emulate_msr_read(vcpu, msr, &data); + + if (!r) { + trace_kvm_msr_read(msr, data); + + 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, msr, KVM_EXIT_X86_RDMSR, 0, + complete_rdmsr, r)) + return 0; + trace_kvm_msr_read_ex(msr); + } + + return kvm_x86_call(complete_emulated_msr)(vcpu, r); +} + +int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) +{ + return __kvm_emulate_rdmsr(vcpu, kvm_rcx_read(vcpu), -1, + complete_fast_rdmsr); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_rdmsr); + +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(msr, data); + } else { + /* MSR write failed? See if we should ask user space */ + 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(msr, data); + } + + return kvm_x86_call(complete_emulated_msr)(vcpu, r); +} + +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) +{ + return kvm_skip_emulated_instruction(vcpu); +} + +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_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_FOR_KVM_INTERNAL(kvm_handle_invalid_op); + + +static int kvm_emulate_monitor_mwait(struct kvm_vcpu *vcpu, const char *insn) +{ + 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); +} +int kvm_emulate_mwait(struct kvm_vcpu *vcpu) +{ + return kvm_emulate_monitor_mwait(vcpu, "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_FOR_KVM_INTERNAL(kvm_emulate_monitor); + +static inline bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu) +{ + xfer_to_guest_mode_prepare(); + + return READ_ONCE(vcpu->mode) == EXITING_GUEST_MODE || + kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending(); +} + +static fastpath_t __handle_fastpath_wrmsr(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + switch (msr) { + case APIC_BASE_MSR + (APIC_ICR >> 4): + 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: + kvm_set_lapic_tscdeadline_msr(vcpu, data); + break; + default: + return EXIT_FASTPATH_NONE; + } + + trace_kvm_msr_write(msr, data); + + if (!kvm_skip_emulated_instruction(vcpu)) + return EXIT_FASTPATH_EXIT_USERSPACE; + + 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_FOR_KVM_INTERNAL(handle_fastpath_wrmsr_imm); + +/* + * Adapt set_msr() to msr_io()'s calling convention + */ +static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +{ + return kvm_get_msr_ignored_check(vcpu, index, data, true); } static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { - struct msr_data msr; + u64 val; - msr.data = *data; - msr.index = index; - msr.host_initiated = true; - return kvm_set_msr(vcpu, &msr); + /* + * 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. 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) && + (do_get_msr(vcpu, index, &val) || *data != val)) + return -EINVAL; + + return kvm_set_msr_ignored_check(vcpu, index, *data, true); } #ifdef CONFIG_X86_64 +struct pvclock_clock { + int vclock_mode; + u64 cycle_last; + u64 mask; + u32 mult; + u32 shift; + u64 base_cycles; + u64 offset; +}; + struct pvclock_gtod_data { seqcount_t seq; - struct { /* extract of a clocksource struct */ - int vclock_mode; - u64 cycle_last; - u64 mask; - u32 mult; - u32 shift; - } clock; + struct pvclock_clock clock; /* extract of a clocksource struct */ + struct pvclock_clock raw_clock; /* extract of a clocksource struct */ - u64 boot_ns; - u64 nsec_base; + ktime_t offs_boot; u64 wall_time_sec; }; @@ -1385,44 +2353,53 @@ static struct pvclock_gtod_data pvclock_gtod_data; static void update_pvclock_gtod(struct timekeeper *tk) { struct pvclock_gtod_data *vdata = &pvclock_gtod_data; - u64 boot_ns; - - boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot)); write_seqcount_begin(&vdata->seq); /* copy pvclock gtod data */ - vdata->clock.vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode; + vdata->clock.vclock_mode = tk->tkr_mono.clock->vdso_clock_mode; vdata->clock.cycle_last = tk->tkr_mono.cycle_last; vdata->clock.mask = tk->tkr_mono.mask; vdata->clock.mult = tk->tkr_mono.mult; vdata->clock.shift = tk->tkr_mono.shift; + vdata->clock.base_cycles = tk->tkr_mono.xtime_nsec; + vdata->clock.offset = tk->tkr_mono.base; - vdata->boot_ns = boot_ns; - vdata->nsec_base = tk->tkr_mono.xtime_nsec; + vdata->raw_clock.vclock_mode = tk->tkr_raw.clock->vdso_clock_mode; + vdata->raw_clock.cycle_last = tk->tkr_raw.cycle_last; + vdata->raw_clock.mask = tk->tkr_raw.mask; + vdata->raw_clock.mult = tk->tkr_raw.mult; + vdata->raw_clock.shift = tk->tkr_raw.shift; + vdata->raw_clock.base_cycles = tk->tkr_raw.xtime_nsec; + vdata->raw_clock.offset = tk->tkr_raw.base; vdata->wall_time_sec = tk->xtime_sec; + vdata->offs_boot = tk->offs_boot; + write_seqcount_end(&vdata->seq); } -#endif -void kvm_set_pending_timer(struct kvm_vcpu *vcpu) +static s64 get_kvmclock_base_ns(void) { - /* - * Note: KVM_REQ_PENDING_TIMER is implicitly checked in - * vcpu_enter_guest. This function is only called from - * the physical CPU that is running vcpu. - */ - kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu); + /* Count up from boot time, but with the frequency of the raw clock. */ + return ktime_to_ns(ktime_add(ktime_get_raw(), pvclock_gtod_data.offs_boot)); } +#else +static s64 get_kvmclock_base_ns(void) +{ + /* Master clock not used, so we can just use CLOCK_BOOTTIME. */ + return ktime_get_boottime_ns(); +} +#endif -static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) +static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs) { int version; int r; struct pvclock_wall_clock wc; - struct timespec64 boot; + u32 wc_sec_hi; + u64 wall_nsec; if (!wall_clock) return; @@ -1439,28 +2416,49 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) 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. guest system time equals host - * system time for us, thus we must fill in host boot time here. - */ - getboottime64(&boot); + wall_nsec = kvm_get_wall_clock_epoch(kvm); - if (kvm->arch.kvmclock_offset) { - struct timespec64 ts = ns_to_timespec64(kvm->arch.kvmclock_offset); - boot = timespec64_sub(boot, ts); - } - wc.sec = (u32)boot.tv_sec; /* overflow in 2106 guest time */ - wc.nsec = boot.tv_nsec; + wc.nsec = do_div(wall_nsec, NSEC_PER_SEC); + wc.sec = (u32)wall_nsec; /* overflow in 2106 guest time */ wc.version = version; kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc)); + if (sec_hi_ofs) { + wc_sec_hi = wall_nsec >> 32; + kvm_write_guest(kvm, wall_clock + sec_hi_ofs, + &wc_sec_hi, sizeof(wc_sec_hi)); + } + version++; kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); } +static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time, + bool old_msr, bool host_initiated) +{ + struct kvm_arch *ka = &vcpu->kvm->arch; + + if (vcpu->vcpu_id == 0 && !host_initiated) { + if (ka->boot_vcpu_runs_old_kvmclock != old_msr) + kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); + + ka->boot_vcpu_runs_old_kvmclock = old_msr; + } + + vcpu->arch.time = system_time; + kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); + + /* we verify if the enable bit is set... */ + if (system_time & 1) + kvm_gpc_activate(&vcpu->arch.pv_time, system_time & ~1ULL, + sizeof(struct pvclock_vcpu_time_info)); + else + kvm_gpc_deactivate(&vcpu->arch.pv_time); + + return; +} + static uint32_t div_frac(uint32_t dividend, uint32_t divisor) { do_shl32_div32(dividend, divisor); @@ -1493,9 +2491,6 @@ static void kvm_get_time_scale(uint64_t scaled_hz, uint64_t base_hz, *pshift = shift; *pmultiplier = div_frac(scaled64, tps32); - - pr_debug("%s: base_hz %llu => %llu, shift %d, mul %u\n", - __func__, base_hz, scaled_hz, shift, *pmultiplier); } #ifdef CONFIG_X86_64 @@ -1512,39 +2507,41 @@ static u32 adjust_tsc_khz(u32 khz, s32 ppm) return v; } +static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier); + static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) { u64 ratio; /* Guest TSC same frequency as host TSC? */ if (!scale) { - vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio; + kvm_vcpu_write_tsc_multiplier(vcpu, kvm_caps.default_tsc_scaling_ratio); return 0; } /* TSC scaling supported? */ - if (!kvm_has_tsc_control) { + if (!kvm_caps.has_tsc_control) { if (user_tsc_khz > tsc_khz) { vcpu->arch.tsc_catchup = 1; vcpu->arch.tsc_always_catchup = 1; return 0; } else { - WARN(1, "user requested TSC rate below hardware speed\n"); + pr_warn_ratelimited("user requested TSC rate below hardware speed\n"); return -1; } } /* TSC scaling required - calculate ratio */ - ratio = mul_u64_u32_div(1ULL << kvm_tsc_scaling_ratio_frac_bits, + ratio = mul_u64_u32_div(1ULL << kvm_caps.tsc_scaling_ratio_frac_bits, user_tsc_khz, tsc_khz); - if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) { - WARN_ONCE(1, "Invalid TSC scaling ratio - virtual-tsc-khz=%u\n", - user_tsc_khz); + if (ratio == 0 || ratio >= kvm_caps.max_tsc_scaling_ratio) { + pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n", + user_tsc_khz); return -1; } - vcpu->arch.tsc_scaling_ratio = ratio; + kvm_vcpu_write_tsc_multiplier(vcpu, ratio); return 0; } @@ -1556,7 +2553,7 @@ static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) /* tsc_khz can be zero if TSC calibration fails */ if (user_tsc_khz == 0) { /* set tsc_scaling_ratio to a safe value */ - vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio; + kvm_vcpu_write_tsc_multiplier(vcpu, kvm_caps.default_tsc_scaling_ratio); return -1; } @@ -1575,7 +2572,8 @@ static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm); thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm); if (user_tsc_khz < thresh_lo || user_tsc_khz > thresh_hi) { - pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", user_tsc_khz, thresh_lo, thresh_hi); + pr_debug("requested TSC rate %u falls outside tolerance [%u,%u]\n", + user_tsc_khz, thresh_lo, thresh_hi); use_scaling = 1; } return set_tsc_khz(vcpu, user_tsc_khz, use_scaling); @@ -1590,31 +2588,36 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) return tsc; } -static inline int gtod_is_based_on_tsc(int mode) +#ifdef CONFIG_X86_64 +static inline bool gtod_is_based_on_tsc(int mode) { - return mode == VCLOCK_TSC || mode == VCLOCK_HVCLOCK; + 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, @@ -1623,12 +2626,6 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) #endif } -static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset) -{ - u64 curr_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu); - vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset; -} - /* * Multiply tsc by a fixed point number represented by ratio. * @@ -1637,45 +2634,105 @@ static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset) * (frac) represent the fractional part, ie. ratio represents a fixed * point number (mult + frac * 2^(-N)). * - * N equals to kvm_tsc_scaling_ratio_frac_bits. + * N equals to kvm_caps.tsc_scaling_ratio_frac_bits. */ static inline u64 __scale_tsc(u64 ratio, u64 tsc) { - return mul_u64_u64_shr(tsc, ratio, kvm_tsc_scaling_ratio_frac_bits); + return mul_u64_u64_shr(tsc, ratio, kvm_caps.tsc_scaling_ratio_frac_bits); } -u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) +u64 kvm_scale_tsc(u64 tsc, u64 ratio) { u64 _tsc = tsc; - u64 ratio = vcpu->arch.tsc_scaling_ratio; - if (ratio != kvm_default_tsc_scaling_ratio) + if (ratio != kvm_caps.default_tsc_scaling_ratio) _tsc = __scale_tsc(ratio, tsc); return _tsc; } -EXPORT_SYMBOL_GPL(kvm_scale_tsc); -static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) +static u64 kvm_compute_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) { u64 tsc; - tsc = kvm_scale_tsc(vcpu, rdtsc()); + tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio); return target_tsc - tsc; } u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { - u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu); + return vcpu->arch.l1_tsc_offset + + kvm_scale_tsc(host_tsc, vcpu->arch.l1_tsc_scaling_ratio); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_read_l1_tsc); - return tsc_offset + kvm_scale_tsc(vcpu, host_tsc); +u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier) +{ + u64 nested_offset; + + if (l2_multiplier == kvm_caps.default_tsc_scaling_ratio) + nested_offset = l1_offset; + else + nested_offset = mul_s64_u64_shr((s64) l1_offset, l2_multiplier, + kvm_caps.tsc_scaling_ratio_frac_bits); + + nested_offset += l2_offset; + return nested_offset; } -EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_calc_nested_tsc_offset); -static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier) { - vcpu->arch.tsc_offset = kvm_x86_ops->write_l1_tsc_offset(vcpu, offset); + if (l2_multiplier != kvm_caps.default_tsc_scaling_ratio) + return mul_u64_u64_shr(l1_multiplier, l2_multiplier, + kvm_caps.tsc_scaling_ratio_frac_bits); + + return l1_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); + + vcpu->arch.l1_tsc_offset = l1_offset; + + /* + * If we are here because L1 chose not to trap WRMSR to TSC then + * according to the spec this should set L1's TSC (as opposed to + * setting L1's offset for L2). + */ + if (is_guest_mode(vcpu)) + vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset( + l1_offset, + kvm_x86_call(get_l2_tsc_offset)(vcpu), + kvm_x86_call(get_l2_tsc_multiplier)(vcpu)); + else + vcpu->arch.tsc_offset = l1_offset; + + kvm_x86_call(write_tsc_offset)(vcpu); +} + +static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier) +{ + vcpu->arch.l1_tsc_scaling_ratio = l1_multiplier; + + /* Userspace is changing the multiplier while L2 is active */ + if (is_guest_mode(vcpu)) + vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier( + l1_multiplier, + kvm_x86_call(get_l2_tsc_multiplier)(vcpu)); + else + vcpu->arch.tsc_scaling_ratio = l1_multiplier; + + if (kvm_caps.has_tsc_control) + kvm_x86_call(write_tsc_multiplier)(vcpu); } static inline bool kvm_check_tsc_unstable(void) @@ -1685,49 +2742,116 @@ static inline bool kvm_check_tsc_unstable(void) * TSC is marked unstable when we're running on Hyper-V, * 'TSC page' clocksource is good. */ - if (pvclock_gtod_data.clock.vclock_mode == VCLOCK_HVCLOCK) + if (pvclock_gtod_data.clock.vclock_mode == VDSO_CLOCKMODE_HVCLOCK) return false; #endif return check_tsc_unstable(); } -void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) +/* + * Infers attempts to synchronize the guest's tsc from host writes. Sets the + * offset for the vcpu and tracks the TSC matching generation that the vcpu + * participates in. + */ +static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc, + 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. + */ + kvm->arch.last_tsc_nsec = ns; + kvm->arch.last_tsc_write = tsc; + kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz; + kvm->arch.last_tsc_offset = offset; + + vcpu->arch.last_guest_tsc = tsc; + + kvm_vcpu_write_tsc_offset(vcpu, offset); + + if (!matched) { + /* + * We split periods of matched TSC writes into generations. + * For each generation, we track the original measured + * nanosecond time, offset, and write, so if TSCs are in + * sync, we can match exact offset, and if not, we can match + * exact software computation in compute_guest_tsc() + * + * These values are tracked in kvm->arch.cur_xxx variables. + */ + kvm->arch.cur_tsc_generation++; + kvm->arch.cur_tsc_nsec = ns; + kvm->arch.cur_tsc_write = tsc; + kvm->arch.cur_tsc_offset = offset; + kvm->arch.nr_vcpus_matched_tsc = 0; + } else if (vcpu->arch.this_tsc_generation != kvm->arch.cur_tsc_generation) { + kvm->arch.nr_vcpus_matched_tsc++; + } + + /* Keep track of which generation this VCPU has synchronized to */ + vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation; + 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, !matched); +} + +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; - bool matched; - bool already_matched; - u64 data = msr->data; + bool matched = false; bool synchronizing = false; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); - offset = kvm_compute_tsc_offset(vcpu, data); - ns = ktime_get_boot_ns(); + offset = kvm_compute_l1_tsc_offset(vcpu, data); + ns = get_kvmclock_base_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; if (vcpu->arch.virtual_tsc_khz) { - if (data == 0 && msr->host_initiated) { + 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 @@ -1738,80 +2862,31 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) { if (!kvm_check_tsc_unstable()) { offset = kvm->arch.cur_tsc_offset; - pr_debug("kvm: matched tsc offset for %llu\n", data); } else { u64 delta = nsec_to_cycles(vcpu, elapsed); data += delta; - offset = kvm_compute_tsc_offset(vcpu, data); - pr_debug("kvm: adjusted tsc offset by %llu\n", delta); + offset = kvm_compute_l1_tsc_offset(vcpu, data); } matched = true; - already_matched = (vcpu->arch.this_tsc_generation == kvm->arch.cur_tsc_generation); - } else { - /* - * We split periods of matched TSC writes into generations. - * For each generation, we track the original measured - * nanosecond time, offset, and write, so if TSCs are in - * sync, we can match exact offset, and if not, we can match - * exact software computation in compute_guest_tsc() - * - * These values are tracked in kvm->arch.cur_xxx variables. - */ - kvm->arch.cur_tsc_generation++; - kvm->arch.cur_tsc_nsec = ns; - kvm->arch.cur_tsc_write = data; - kvm->arch.cur_tsc_offset = offset; - matched = false; - pr_debug("kvm: new tsc generation %llu, clock %llu\n", - kvm->arch.cur_tsc_generation, data); } - /* - * We also track th most recent recorded KHZ, write and time to - * allow the matching interval to be extended at each write. - */ - kvm->arch.last_tsc_nsec = ns; - kvm->arch.last_tsc_write = data; - kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz; - - vcpu->arch.last_guest_tsc = data; - - /* Keep track of which generation this VCPU has synchronized to */ - vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation; - vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec; - vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write; - - if (!msr->host_initiated && guest_cpuid_has(vcpu, X86_FEATURE_TSC_ADJUST)) - update_ia32_tsc_adjust_msr(vcpu, offset); - - kvm_vcpu_write_tsc_offset(vcpu, offset); + __kvm_synchronize_tsc(vcpu, offset, data, ns, matched, !!user_value); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); - - spin_lock(&kvm->arch.pvclock_gtod_sync_lock); - if (!matched) { - kvm->arch.nr_vcpus_matched_tsc = 0; - } else if (!already_matched) { - kvm->arch.nr_vcpus_matched_tsc++; - } - - kvm_track_tsc_matching(vcpu); - spin_unlock(&kvm->arch.pvclock_gtod_sync_lock); } -EXPORT_SYMBOL_GPL(kvm_write_tsc); - static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { - u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu); + u64 tsc_offset = vcpu->arch.l1_tsc_offset; kvm_vcpu_write_tsc_offset(vcpu, tsc_offset + adjustment); } static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) { - if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio) + if (vcpu->arch.l1_tsc_scaling_ratio != kvm_caps.default_tsc_scaling_ratio) WARN_ON(adjustment < 0); - adjustment = kvm_scale_tsc(vcpu, (u64) adjustment); + adjustment = kvm_scale_tsc((u64) adjustment, + vcpu->arch.l1_tsc_scaling_ratio); adjust_tsc_offset_guest(vcpu, adjustment); } @@ -1837,43 +2912,46 @@ static u64 read_tsc(void) return last; } -static inline u64 vgettsc(u64 *tsc_timestamp, int *mode) +static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp, + int *mode) { - long v; - struct pvclock_gtod_data *gtod = &pvclock_gtod_data; u64 tsc_pg_val; + long v; - switch (gtod->clock.vclock_mode) { - case VCLOCK_HVCLOCK: - tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(), - tsc_timestamp); - if (tsc_pg_val != U64_MAX) { + switch (clock->vclock_mode) { + case VDSO_CLOCKMODE_HVCLOCK: + if (hv_read_tsc_page_tsc(hv_get_tsc_page(), + tsc_timestamp, &tsc_pg_val)) { /* TSC page valid */ - *mode = VCLOCK_HVCLOCK; - v = (tsc_pg_val - gtod->clock.cycle_last) & - gtod->clock.mask; + *mode = VDSO_CLOCKMODE_HVCLOCK; + v = (tsc_pg_val - clock->cycle_last) & + clock->mask; } else { /* TSC page invalid */ - *mode = VCLOCK_NONE; + *mode = VDSO_CLOCKMODE_NONE; } break; - case VCLOCK_TSC: - *mode = VCLOCK_TSC; + case VDSO_CLOCKMODE_TSC: + *mode = VDSO_CLOCKMODE_TSC; *tsc_timestamp = read_tsc(); - v = (*tsc_timestamp - gtod->clock.cycle_last) & - gtod->clock.mask; + v = (*tsc_timestamp - clock->cycle_last) & + clock->mask; break; default: - *mode = VCLOCK_NONE; + *mode = VDSO_CLOCKMODE_NONE; } - if (*mode == VCLOCK_NONE) + if (*mode == VDSO_CLOCKMODE_NONE) *tsc_timestamp = v = 0; - return v * gtod->clock.mult; + return v * clock->mult; } -static int do_monotonic_boot(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; @@ -1882,10 +2960,33 @@ static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp) do { seq = read_seqcount_begin(>od->seq); - ns = gtod->nsec_base; - ns += vgettsc(tsc_timestamp, &mode); + ns = gtod->raw_clock.base_cycles; + ns += vgettsc(>od->raw_clock, tsc_timestamp, &mode); + ns >>= gtod->raw_clock.shift; + ns += ktime_to_ns(ktime_add(gtod->raw_clock.offset, gtod->offs_boot)); + } while (unlikely(read_seqcount_retry(>od->seq, seq))); + *t = ns; + + 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 += gtod->boot_ns; + ns += ktime_to_ns(gtod->clock.offset); } while (unlikely(read_seqcount_retry(>od->seq, seq))); *t = ns; @@ -1902,8 +3003,8 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp) do { seq = read_seqcount_begin(>od->seq); ts->tv_sec = gtod->wall_time_sec; - ns = gtod->nsec_base; - ns += vgettsc(tsc_timestamp, &mode); + ns = gtod->clock.base_cycles; + ns += vgettsc(>od->clock, tsc_timestamp, &mode); ns >>= gtod->clock.shift; } while (unlikely(read_seqcount_retry(>od->seq, seq))); @@ -1913,18 +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_boot(kernel_ns, - tsc_timestamp)); + return gtod_is_based_on_tsc(do_kvmclock_base(kernel_ns, + tsc_timestamp)); } -/* returns true if host is using TSC based clocksource */ +/* + * 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)); +} + +/* + * 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) { @@ -1984,6 +3109,7 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) int vclock_mode; bool host_tsc_clocksource, vcpus_matched; + lockdep_assert_held(&kvm->arch.tsc_write_lock); vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == atomic_read(&kvm->online_vcpus)); @@ -2008,131 +3134,177 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) #endif } -void kvm_make_mclock_inprogress_request(struct kvm *kvm) +static void kvm_make_mclock_inprogress_request(struct kvm *kvm) { kvm_make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS); } -static void kvm_gen_update_masterclock(struct kvm *kvm) +static void __kvm_start_pvclock_update(struct kvm *kvm) { -#ifdef CONFIG_X86_64 - int i; - struct kvm_vcpu *vcpu; - struct kvm_arch *ka = &kvm->arch; + raw_spin_lock_irq(&kvm->arch.tsc_write_lock); + write_seqcount_begin(&kvm->arch.pvclock_sc); +} - spin_lock(&ka->pvclock_gtod_sync_lock); +static void kvm_start_pvclock_update(struct kvm *kvm) +{ kvm_make_mclock_inprogress_request(kvm); + /* no guest entries from this point */ - pvclock_update_vm_gtod_copy(kvm); + __kvm_start_pvclock_update(kvm); +} + +static void kvm_end_pvclock_update(struct kvm *kvm) +{ + struct kvm_arch *ka = &kvm->arch; + struct kvm_vcpu *vcpu; + unsigned long i; + write_seqcount_end(&ka->pvclock_sc); + raw_spin_unlock_irq(&ka->tsc_write_lock); kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); /* guest entries allowed */ kvm_for_each_vcpu(i, vcpu, kvm) kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); +} - spin_unlock(&ka->pvclock_gtod_sync_lock); -#endif +static void kvm_update_masterclock(struct kvm *kvm) +{ + kvm_hv_request_tsc_page_update(kvm); + kvm_start_pvclock_update(kvm); + pvclock_update_vm_gtod_copy(kvm); + kvm_end_pvclock_update(kvm); } -u64 get_kvmclock_ns(struct kvm *kvm) +/* + * Use the kernel's tsc_khz directly if the TSC is constant, otherwise use KVM's + * per-CPU value (which may be zero if a CPU is going offline). Note, tsc_khz + * can change during boot even if the TSC is constant, as it's possible for KVM + * to be loaded before TSC calibration completes. Ideally, KVM would get a + * notification when calibration completes, but practically speaking calibration + * will complete before userspace is alive enough to create VMs. + */ +static unsigned long get_cpu_tsc_khz(void) +{ + if (static_cpu_has(X86_FEATURE_CONSTANT_TSC)) + return tsc_khz; + else + return __this_cpu_read(cpu_tsc_khz); +} + +/* Called within read_seqcount_begin/retry for kvm->pvclock_sc. */ +static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) { struct kvm_arch *ka = &kvm->arch; struct pvclock_vcpu_time_info hv_clock; - u64 ret; - - spin_lock(&ka->pvclock_gtod_sync_lock); - if (!ka->use_master_clock) { - spin_unlock(&ka->pvclock_gtod_sync_lock); - return ktime_get_boot_ns() + ka->kvmclock_offset; - } - - hv_clock.tsc_timestamp = ka->master_cycle_now; - hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; - spin_unlock(&ka->pvclock_gtod_sync_lock); /* both __this_cpu_read() and rdtsc() should be on the same cpu */ get_cpu(); - if (__this_cpu_read(cpu_tsc_khz)) { - kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL, + data->flags = 0; + if (ka->use_master_clock && + (static_cpu_has(X86_FEATURE_CONSTANT_TSC) || __this_cpu_read(cpu_tsc_khz))) { +#ifdef CONFIG_X86_64 + struct timespec64 ts; + + if (kvm_get_walltime_and_clockread(&ts, &data->host_tsc)) { + data->realtime = ts.tv_nsec + NSEC_PER_SEC * ts.tv_sec; + data->flags |= KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC; + } else +#endif + data->host_tsc = rdtsc(); + + data->flags |= KVM_CLOCK_TSC_STABLE; + hv_clock.tsc_timestamp = ka->master_cycle_now; + hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; + kvm_get_time_scale(NSEC_PER_SEC, get_cpu_tsc_khz() * 1000LL, &hv_clock.tsc_shift, &hv_clock.tsc_to_system_mul); - ret = __pvclock_read_cycles(&hv_clock, rdtsc()); - } else - ret = ktime_get_boot_ns() + ka->kvmclock_offset; + data->clock = __pvclock_read_cycles(&hv_clock, data->host_tsc); + } else { + data->clock = get_kvmclock_base_ns() + ka->kvmclock_offset; + } put_cpu(); +} - return ret; +static void get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) +{ + struct kvm_arch *ka = &kvm->arch; + unsigned seq; + + do { + seq = read_seqcount_begin(&ka->pvclock_sc); + __get_kvmclock(kvm, data); + } while (read_seqcount_retry(&ka->pvclock_sc, seq)); } -static void kvm_setup_pvclock_page(struct kvm_vcpu *v) +u64 get_kvmclock_ns(struct kvm *kvm) { - struct kvm_vcpu_arch *vcpu = &v->arch; - struct pvclock_vcpu_time_info guest_hv_clock; + struct kvm_clock_data data; - if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time, - &guest_hv_clock, sizeof(guest_hv_clock)))) - return; + get_kvmclock(kvm, &data); + return data.clock; +} - /* This VCPU is paused, but it's legal for a guest to read another +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 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); + + if (kvm_gpc_refresh(gpc, offset + sizeof(*guest_hv_clock))) + return; + + read_lock_irqsave(&gpc->lock, flags); + } + + guest_hv_clock = (void *)(gpc->khva + offset); + + /* + * This VCPU is paused, but it's legal for a guest to read another * VCPU's kvmclock, so we really have to follow the specification where * it says that version is odd if data is being modified, and even after * it is consistent. - * - * Version field updates must be kept separate. This is because - * kvm_write_guest_cached might use a "rep movs" instruction, and - * writes within a string instruction are weakly ordered. So there - * are three writes overall. - * - * As a small optimization, only write the version field in the first - * and third write. The vcpu->pv_time cache is still valid, because the - * version field is the first in the struct. */ - BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0); - - if (guest_hv_clock.version & 1) - ++guest_hv_clock.version; /* first time write, random junk */ - - vcpu->hv_clock.version = guest_hv_clock.version + 1; - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock.version)); + 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)); - trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock); + smp_wmb(); - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock)); + guest_hv_clock->version = ++hv_clock.version; - smp_wmb(); + kvm_gpc_mark_dirty_in_slot(gpc); + read_unlock_irqrestore(&gpc->lock, flags); - vcpu->hv_clock.version++; - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock.version)); + 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; @@ -2142,17 +3314,18 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) * If the host uses TSC clock, then passthrough TSC as stable * to the guest. */ - spin_lock(&ka->pvclock_gtod_sync_lock); - use_master_clock = ka->use_master_clock; - if (use_master_clock) { - host_tsc = ka->master_cycle_now; - kernel_ns = ka->master_kernel_ns; - } - spin_unlock(&ka->pvclock_gtod_sync_lock); + do { + seq = read_seqcount_begin(&ka->pvclock_sc); + use_master_clock = ka->use_master_clock; + if (use_master_clock) { + host_tsc = ka->master_cycle_now; + kernel_ns = ka->master_kernel_ns; + } + } while (read_seqcount_retry(&ka->pvclock_sc, seq)); /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); - tgt_tsc_khz = __this_cpu_read(cpu_tsc_khz); + tgt_tsc_khz = get_cpu_tsc_khz(); if (unlikely(tgt_tsc_khz == 0)) { local_irq_restore(flags); kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); @@ -2160,7 +3333,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) } if (!use_master_clock) { host_tsc = rdtsc(); - kernel_ns = ktime_get_boot_ns(); + kernel_ns = get_kvmclock_base_ns(); } tsc_timestamp = kvm_read_l1_tsc(v, host_tsc); @@ -2187,58 +3360,158 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) /* With all the info we got, fill in the values */ - if (kvm_has_tsc_control) - tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz); + 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; } - 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; + + 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; + } - vcpu->hv_clock.flags = pvclock_flags; + kvm_hv_setup_tsc_page(v->kvm, &hv_clock); - if (vcpu->pv_time_enabled) - kvm_setup_pvclock_page(v); - if (v == kvm_get_vcpu(v->kvm, 0)) - kvm_hv_setup_tsc_page(v->kvm, &vcpu->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->xen.vcpu_info_cache.active) + 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(&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) { - int 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); + unsigned long i; struct kvm_vcpu *vcpu; + struct kvm *kvm = v->kvm; kvm_for_each_vcpu(i, vcpu, kvm) { kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -2246,30 +3519,26 @@ static void kvmclock_update_fn(struct work_struct *work) } } -static void kvm_gen_kvmclock_update(struct kvm_vcpu *v) +/* These helpers are safe iff @msr is known to be an MCx bank MSR. */ +static bool is_mci_control_msr(u32 msr) { - struct kvm *kvm = v->kvm; - - kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); - schedule_delayed_work(&kvm->arch.kvmclock_update_work, - KVMCLOCK_UPDATE_DELAY); + return (msr & 3) == 0; } - -#define KVMCLOCK_SYNC_PERIOD (300 * HZ) - -static void kvmclock_sync_fn(struct work_struct *work) +static bool is_mci_status_msr(u32 msr) { - 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); + return (msr & 3) == 1; +} - if (!kvmclock_periodic_sync) - return; +/* + * On AMD, HWCR[McStatusWrEn] controls whether setting MCi_STATUS results in #GP. + */ +static bool can_set_mci_status(struct kvm_vcpu *vcpu) +{ + /* McStatusWrEn enabled? */ + if (guest_cpuid_is_amd_compatible(vcpu)) + return !!(vcpu->arch.msr_hwcr & BIT_ULL(18)); - schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0); - schedule_delayed_work(&kvm->arch.kvmclock_sync_work, - KVMCLOCK_SYNC_PERIOD); + return false; } static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -2278,6 +3547,7 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) unsigned bank_num = mcg_cap & 0xff; u32 msr = msr_info->index; u64 data = msr_info->data; + u32 offset, last_msr; switch (msr) { case MSR_IA32_MCG_STATUS: @@ -2291,144 +3561,347 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vcpu->arch.mcg_ctl = data; break; + case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1: + last_msr = MSR_IA32_MCx_CTL2(bank_num) - 1; + if (msr > last_msr) + return 1; + + if (!(mcg_cap & MCG_CMCI_P) && (data || !msr_info->host_initiated)) + return 1; + /* An attempt to write a 1 to a reserved bit raises #GP */ + if (data & ~(MCI_CTL2_CMCI_EN | MCI_CTL2_CMCI_THRESHOLD_MASK)) + return 1; + offset = array_index_nospec(msr - MSR_IA32_MC0_CTL2, + last_msr + 1 - MSR_IA32_MC0_CTL2); + vcpu->arch.mci_ctl2_banks[offset] = data; + break; + case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: + last_msr = MSR_IA32_MCx_CTL(bank_num) - 1; + if (msr > last_msr) + return 1; + + /* + * Only 0 or all 1s can be written to IA32_MCi_CTL, all other + * values are architecturally undefined. But, some Linux + * kernels clear bit 10 in bank 4 to workaround a BIOS/GART TLB + * issue on AMD K8s, allow bit 10 to be clear when setting all + * other bits in order to avoid an uncaught #GP in the guest. + * + * UNIXWARE clears bit 0 of MC1_CTL to ignore correctable, + * single-bit ECC data errors. + */ + if (is_mci_control_msr(msr) && + data != 0 && (data | (1 << 10) | 1) != ~(u64)0) + return 1; + + /* + * All CPUs allow writing 0 to MCi_STATUS MSRs to clear the MSR. + * AMD-based CPUs allow non-zero values, but if and only if + * HWCR[McStatusWrEn] is set. + */ + if (!msr_info->host_initiated && is_mci_status_msr(msr) && + data != 0 && !can_set_mci_status(vcpu)) + return 1; + + offset = array_index_nospec(msr - MSR_IA32_MC0_CTL, + last_msr + 1 - MSR_IA32_MC0_CTL); + vcpu->arch.mce_banks[offset] = data; + break; default: - if (msr >= MSR_IA32_MC0_CTL && - msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = msr - MSR_IA32_MC0_CTL; - /* only 0 or all 1s can be written to IA32_MCi_CTL - * some Linux kernels though clear bit 10 in bank 4 to - * workaround a BIOS/GART TBL issue on AMD K8s, ignore - * this to avoid an uncatched #GP in the guest - */ - if ((offset & 0x3) == 0 && - data != 0 && (data | (1 << 10)) != ~(u64)0) - return -1; - if (!msr_info->host_initiated && - (offset & 0x3) == 1 && data != 0) - return -1; - vcpu->arch.mce_banks[offset] = data; - break; - } return 1; } return 0; } -static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data) -{ - struct kvm *kvm = vcpu->kvm; - int lm = is_long_mode(vcpu); - u8 *blob_addr = lm ? (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_64 - : (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_32; - u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 - : kvm->arch.xen_hvm_config.blob_size_32; - u32 page_num = data & ~PAGE_MASK; - u64 page_addr = data & PAGE_MASK; - u8 *page; - int r; - - r = -E2BIG; - if (page_num >= blob_size) - goto out; - r = -ENOMEM; - page = memdup_user(blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE); - if (IS_ERR(page)) { - r = PTR_ERR(page); - goto out; - } - if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) - goto out_free; - r = 0; -out_free: - kfree(page); -out: - return r; -} - static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) { gpa_t gpa = data & ~0x3f; - /* Bits 3:5 are reserved, Should be zero */ - if (data & 0x38) + /* Bits 4:5 are reserved, Should be zero */ + if (data & 0x30) + return 1; + + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_VMEXIT) && + (data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT)) return 1; - vcpu->arch.apf.msr_val = data; + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT) && + (data & KVM_ASYNC_PF_DELIVERY_AS_INT)) + return 1; - if (!(data & KVM_ASYNC_PF_ENABLED)) { + if (!lapic_in_kernel(vcpu)) + return data ? 1 : 0; + + vcpu->arch.apf.msr_en_val = data; + + if (!kvm_pv_async_pf_enabled(vcpu)) { kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu); return 0; } if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa, - sizeof(u32))) + 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); + + return 0; +} + +static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data) +{ + /* Bits 8-63 are reserved */ + if (data >> 8) + return 1; + + if (!lapic_in_kernel(vcpu)) + return 1; + + vcpu->arch.apf.msr_int_val = data; + + vcpu->arch.apf.vec = data & KVM_ASYNC_PF_VEC_MASK; + return 0; } static void kvmclock_reset(struct kvm_vcpu *vcpu) { - vcpu->arch.pv_time_enabled = false; + kvm_gpc_deactivate(&vcpu->arch.pv_time); + vcpu->arch.time = 0; } -static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) +static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; - kvm_x86_ops->tlb_flush(vcpu, invalidate_gpa); + kvm_x86_call(flush_tlb_all)(vcpu); + + /* Flushing all ASIDs flushes the current ASID... */ + kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } +static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) +{ + ++vcpu->stat.tlb_flush; + + if (!tdp_enabled) { + /* + * A TLB flush on behalf of the guest is equivalent to + * INVPCID(all), toggling CR4.PGE, etc., which requires + * a forced sync of the shadow page tables. Ensure all the + * roots are synced and the guest TLB in hardware is clean. + */ + kvm_mmu_sync_roots(vcpu); + kvm_mmu_sync_prev_roots(vcpu); + } + + kvm_x86_call(flush_tlb_guest)(vcpu); + + /* + * Flushing all "guest" TLB is always a superset of Hyper-V's fine + * grained flushing. + */ + kvm_hv_vcpu_purge_flush_tlb(vcpu); +} + + +static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu) +{ + ++vcpu->stat.tlb_flush; + kvm_x86_call(flush_tlb_current)(vcpu); +} + +/* + * Service "local" TLB flush requests, which are specific to the current MMU + * context. In addition to the generic event handling in vcpu_enter_guest(), + * TLB flushes that are targeted at an MMU context also need to be serviced + * prior before nested VM-Enter/VM-Exit. + */ +void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu) +{ + if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) + kvm_vcpu_flush_tlb_current(vcpu); + + if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu)) + kvm_vcpu_flush_tlb_guest(vcpu); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_service_local_tlb_flush_requests); + static void record_steal_time(struct kvm_vcpu *vcpu) { + struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; + struct kvm_steal_time __user *st; + struct kvm_memslots *slots; + gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; + u64 steal; + u32 version; + + if (kvm_xen_msr_enabled(vcpu->kvm)) { + kvm_xen_runstate_set_running(vcpu); + return; + } + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)))) + if (WARN_ON_ONCE(current->mm != vcpu->kvm->mm)) return; + slots = kvm_memslots(vcpu->kvm); + + if (unlikely(slots->generation != ghc->generation || + gpa != ghc->gpa || + kvm_is_error_hva(ghc->hva) || !ghc->memslot)) { + /* We rely on the fact that it fits in a single page. */ + BUILD_BUG_ON((sizeof(*st) - 1) & KVM_STEAL_VALID_BITS); + + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gpa, sizeof(*st)) || + kvm_is_error_hva(ghc->hva) || !ghc->memslot) + return; + } + + st = (struct kvm_steal_time __user *)ghc->hva; /* * Doing a TLB flush here, on the guest's behalf, can avoid * expensive IPIs. */ - if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB) - kvm_vcpu_flush_tlb(vcpu, false); + if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) { + u8 st_preempted = 0; + int err = -EFAULT; + + if (!user_access_begin(st, sizeof(*st))) + return; + + asm volatile("1: xchgb %0, %2\n" + "xor %1, %1\n" + "2:\n" + _ASM_EXTABLE_UA(1b, 2b) + : "+q" (st_preempted), + "+&r" (err), + "+m" (st->preempted)); + if (err) + goto out; + + user_access_end(); + + vcpu->arch.st.preempted = 0; + + trace_kvm_pv_tlb_flush(vcpu->vcpu_id, + st_preempted & KVM_VCPU_FLUSH_TLB); + if (st_preempted & KVM_VCPU_FLUSH_TLB) + kvm_vcpu_flush_tlb_guest(vcpu); - if (vcpu->arch.st.steal.version & 1) - vcpu->arch.st.steal.version += 1; /* first time write, random junk */ + if (!user_access_begin(st, sizeof(*st))) + goto dirty; + } else { + if (!user_access_begin(st, sizeof(*st))) + return; - vcpu->arch.st.steal.version += 1; + unsafe_put_user(0, &st->preempted, out); + vcpu->arch.st.preempted = 0; + } - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); + unsafe_get_user(version, &st->version, out); + if (version & 1) + version += 1; /* first time write, random junk */ + + version += 1; + unsafe_put_user(version, &st->version, out); smp_wmb(); - vcpu->arch.st.steal.steal += current->sched_info.run_delay - + unsafe_get_user(steal, &st->steal, out); + steal += current->sched_info.run_delay - vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; + unsafe_put_user(steal, &st->steal, out); - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); + version += 1; + unsafe_put_user(version, &st->version, out); - smp_wmb(); + out: + user_access_end(); + dirty: + mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); +} - vcpu->arch.st.steal.version += 1; +/* + * 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) +{ + if (!vcpu) + return false; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); + 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; + } +} + +/* + * 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) { - bool pr = false; u32 msr = msr_info->index; u64 data = msr_info->data; + /* + * 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) { case MSR_AMD64_NB_CFG: case MSR_IA32_UCODE_WRITE: @@ -2436,6 +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; @@ -2443,66 +3917,177 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (msr_info->host_initiated) vcpu->arch.microcode_version = data; break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated || + !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 || + !guest_cpu_cap_has(vcpu, X86_FEATURE_PDCM)) + return KVM_MSR_RET_UNSUPPORTED; + + if (data & ~kvm_caps.supported_perf_cap) + return 1; + + /* + * Note, this is not just a performance optimization! KVM + * disallows changing feature MSRs after the vCPU has run; PMU + * refresh will bug the VM if called after the vCPU has run. + */ + if (vcpu->arch.perf_capabilities == data) + break; + + vcpu->arch.perf_capabilities = data; + kvm_pmu_refresh(vcpu); + break; + case MSR_IA32_PRED_CMD: { + u64 reserved_bits = ~(PRED_CMD_IBPB | PRED_CMD_SBPB); + + 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; + + wrmsrq(MSR_IA32_PRED_CMD, data); + break; + } + case MSR_IA32_FLUSH_CMD: + if (!msr_info->host_initiated && + !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)) + return 1; + + if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D) || (data & ~L1D_FLUSH)) + return 1; + if (!data) + break; + + wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH); + break; case MSR_EFER: - return set_efer(vcpu, data); + return set_efer(vcpu, msr_info); case MSR_K7_HWCR: data &= ~(u64)0x40; /* ignore flush filter disable */ data &= ~(u64)0x100; /* ignore ignne emulation enable */ data &= ~(u64)0x8; /* ignore TLB cache disable */ - data &= ~(u64)0x40000; /* ignore Mc status write enable */ - if (data != 0) { - vcpu_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", - data); + + /* + * 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) { - vcpu_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: " - "0x%llx\n", data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } break; - case MSR_IA32_DEBUGCTLMSR: - if (!data) { - /* We support the non-activated case already */ - break; - } else if (data & ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_BTF)) { - /* Values other than LBR and BTF are vendor-specific, - thus reserved and should throw a #GP */ + case MSR_IA32_CR_PAT: + if (!kvm_pat_valid(data)) return 1; - } - vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", - __func__, data); + + vcpu->arch.pat = data; break; - case 0x200 ... 0x2ff: + case MTRRphysBase_MSR(0) ... MSR_MTRRfix4K_F8000: + case MSR_MTRRdefType: return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: - return kvm_set_apic_base(vcpu, msr_info); - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + 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_TSCDEADLINE: + 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); + /* Before back to guest, tsc_timestamp must be adjusted + * as well, otherwise guest's percpu pvclock time could jump. + */ + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); } vcpu->arch.ia32_tsc_adjust_msr = data; } break; - case MSR_IA32_MISC_ENABLE: - vcpu->arch.ia32_misc_enable_msr = data; + case MSR_IA32_MISC_ENABLE: { + u64 old_val = vcpu->arch.ia32_misc_enable_msr; + + if (!msr_info->host_initiated) { + /* RO bits */ + if ((old_val ^ data) & MSR_IA32_MISC_ENABLE_PMU_RO_MASK) + return 1; + + /* R bits, i.e. writes are ignored, but don't fault. */ + data = data & ~MSR_IA32_MISC_ENABLE_EMON; + data |= old_val & MSR_IA32_MISC_ENABLE_EMON; + } + + if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT) && + ((old_val ^ data) & MSR_IA32_MISC_ENABLE_MWAIT)) { + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_XMM3)) + return 1; + vcpu->arch.ia32_misc_enable_msr = data; + vcpu->arch.cpuid_dynamic_bits_dirty = true; + } else { + vcpu->arch.ia32_misc_enable_msr = data; + } break; + } case MSR_IA32_SMBASE: - if (!msr_info->host_initiated) + if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated) return 1; vcpu->arch.smbase = data; break; + case MSR_IA32_POWER_CTL: + vcpu->arch.msr_ia32_power_ctl = data; + break; case MSR_IA32_TSC: - kvm_write_tsc(vcpu, msr_info); + if (msr_info->host_initiated) { + 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 (!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; + vcpu->arch.cpuid_dynamic_bits_dirty = true; break; case MSR_SMI_COUNT: if (!msr_info->host_initiated) @@ -2510,46 +4095,61 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.smi_count = data; break; case MSR_KVM_WALL_CLOCK_NEW: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) + return 1; + + vcpu->kvm->arch.wall_clock = data; + kvm_write_wall_clock(vcpu->kvm, data, 0); + break; case MSR_KVM_WALL_CLOCK: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) + return 1; + vcpu->kvm->arch.wall_clock = data; - kvm_write_wall_clock(vcpu->kvm, data); + kvm_write_wall_clock(vcpu->kvm, data, 0); break; case MSR_KVM_SYSTEM_TIME_NEW: - case MSR_KVM_SYSTEM_TIME: { - struct kvm_arch *ka = &vcpu->kvm->arch; - - kvmclock_reset(vcpu); - - if (vcpu->vcpu_id == 0 && !msr_info->host_initiated) { - bool tmp = (msr == MSR_KVM_SYSTEM_TIME); - - if (ka->boot_vcpu_runs_old_kvmclock != tmp) - kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); - - ka->boot_vcpu_runs_old_kvmclock = tmp; - } - - vcpu->arch.time = data; - kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); - - /* we verify if the enable bit is set... */ - if (!(data & 1)) - break; + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) + return 1; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, - &vcpu->arch.pv_time, data & ~1ULL, - sizeof(struct pvclock_vcpu_time_info))) - vcpu->arch.pv_time_enabled = false; - else - vcpu->arch.pv_time_enabled = true; + kvm_write_system_time(vcpu, data, false, msr_info->host_initiated); + break; + case MSR_KVM_SYSTEM_TIME: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) + return 1; + kvm_write_system_time(vcpu, data, true, msr_info->host_initiated); break; - } case MSR_KVM_ASYNC_PF_EN: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + return 1; + if (kvm_pv_enable_async_pf(vcpu, data)) return 1; break; + case MSR_KVM_ASYNC_PF_INT: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) + return 1; + + if (kvm_pv_enable_async_pf_int(vcpu, data)) + return 1; + break; + case MSR_KVM_ASYNC_PF_ACK: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) + return 1; + if (data & 0x1) { + /* + * 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; case MSR_KVM_STEAL_TIME: + if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME)) + return 1; if (unlikely(!sched_info_on())) return 1; @@ -2557,11 +4157,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & KVM_STEAL_RESERVED_MASK) return 1; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime, - data & KVM_STEAL_VALID_BITS, - sizeof(struct kvm_steal_time))) - return 1; - vcpu->arch.st.msr_val = data; if (!(data & KVM_MSR_ENABLED)) @@ -2571,26 +4166,39 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_KVM_PV_EOI_EN: - if (kvm_lapic_enable_pv_eoi(vcpu, data, sizeof(u8))) + if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI)) + return 1; + + if (kvm_lapic_set_pv_eoi(vcpu, data, sizeof(u8))) return 1; break; + case MSR_KVM_POLL_CONTROL: + if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL)) + return 1; + + /* only enable bit supported */ + if (data & (-1ULL << 1)) + return 1; + + vcpu->arch.msr_kvm_poll_control = data; + break; + case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: + case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1: return set_msr_mce(vcpu, msr_info); case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: - pr = true; /* fall through */ case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); - if (pr || data != 0) - vcpu_unimpl(vcpu, "disabled perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); + if (data) + kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_K7_CLK_CTL: /* @@ -2602,37 +4210,38 @@ 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: case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: + 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. */ - if (report_ignored_msrs) - vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", - msr, data); + 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; @@ -2643,44 +4252,48 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vcpu->arch.msr_misc_features_enables = data; break; +#ifdef CONFIG_X86_64 + case MSR_IA32_XFD: + if (!msr_info->host_initiated && + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) + return 1; + + if (data & ~kvm_guest_supported_xfd(vcpu)) + return 1; + + fpu_update_guest_xfd(&vcpu->arch.guest_fpu, data); + break; + case MSR_IA32_XFD_ERR: + if (!msr_info->host_initiated && + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) + return 1; + + if (data & ~kvm_guest_supported_xfd(vcpu)) + return 1; + + 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 (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) - return xen_hvm_config(vcpu, data); if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); - if (!ignore_msrs) { - vcpu_debug_ratelimited(vcpu, "unhandled wrmsr: 0x%x data 0x%llx\n", - msr, data); - return 1; - } else { - if (report_ignored_msrs) - vcpu_unimpl(vcpu, - "ignored wrmsr: 0x%x data 0x%llx\n", - msr, data); - break; - } + + return KVM_MSR_RET_UNSUPPORTED; } return 0; } -EXPORT_SYMBOL_GPL(kvm_set_msr_common); - - -/* - * Reads an msr value (of 'msr_index') into 'pdata'. - * Returns 0 on success, non-0 otherwise. - * Assumes vcpu_load() was already called. - */ -int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) -{ - return kvm_x86_ops->get_msr(vcpu, msr); -} -EXPORT_SYMBOL_GPL(kvm_get_msr); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_msr_common); static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) { u64 data; u64 mcg_cap = vcpu->arch.mcg_cap; unsigned bank_num = mcg_cap & 0xff; + u32 offset, last_msr; switch (msr) { case MSR_IA32_P5_MC_ADDR: @@ -2698,13 +4311,27 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) case MSR_IA32_MCG_STATUS: data = vcpu->arch.mcg_status; break; + case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1: + last_msr = MSR_IA32_MCx_CTL2(bank_num) - 1; + if (msr > last_msr) + return 1; + + if (!(mcg_cap & MCG_CMCI_P) && !host) + return 1; + offset = array_index_nospec(msr - MSR_IA32_MC0_CTL2, + last_msr + 1 - MSR_IA32_MC0_CTL2); + data = vcpu->arch.mci_ctl2_banks[offset]; + break; + case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: + last_msr = MSR_IA32_MCx_CTL(bank_num) - 1; + if (msr > last_msr) + return 1; + + offset = array_index_nospec(msr - MSR_IA32_MC0_CTL, + last_msr + 1 - MSR_IA32_MC0_CTL); + data = vcpu->arch.mce_banks[offset]; + break; default: - if (msr >= MSR_IA32_MC0_CTL && - msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = msr - MSR_IA32_MC0_CTL; - data = vcpu->arch.mce_banks[offset]; - break; - } return 1; } *pdata = data; @@ -2716,15 +4343,13 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr_info->index) { case MSR_IA32_PLATFORM_ID: case MSR_IA32_EBL_CR_POWERON: - case MSR_IA32_DEBUGCTLMSR: case MSR_IA32_LASTBRANCHFROMIP: case MSR_IA32_LASTBRANCHTOIP: case MSR_IA32_LASTINTFROMIP: case MSR_IA32_LASTINTTOIP: - case MSR_K8_SYSCFG: + case MSR_AMD64_SYSCFG: case MSR_K8_TSEG_ADDR: case MSR_K8_TSEG_MASK: - case MSR_K7_HWCR: case MSR_VM_HSAVE_PA: case MSR_K8_INT_PENDING_MSG: case MSR_AMD64_NB_CFG: @@ -2732,26 +4357,74 @@ 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 + * limit) MSRs. Just return 0, as we do not want to expose the host + * data here. Do not conditionalize this on CPUID, as KVM does not do + * so for existing CPU-specific MSRs. + */ + case MSR_RAPL_POWER_UNIT: + case MSR_PP0_ENERGY_STATUS: /* Power plane 0 (core) */ + case MSR_PP1_ENERGY_STATUS: /* Power plane 1 (graphics uncore) */ + case MSR_PKG_ENERGY_STATUS: /* Total package */ + case MSR_DRAM_ENERGY_STATUS: /* DRAM controller */ msr_info->data = 0; break; - case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) - return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data); + return kvm_pmu_get_msr(vcpu, msr_info); msr_info->data = 0; break; case MSR_IA32_UCODE_REV: msr_info->data = vcpu->arch.microcode_version; break; - case MSR_IA32_TSC: - msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset; + case MSR_IA32_ARCH_CAPABILITIES: + 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 (!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: + msr_info->data = vcpu->arch.msr_ia32_power_ctl; + break; + case MSR_IA32_TSC: { + /* + * Intel SDM states that MSR_IA32_TSC read adds the TSC offset + * even when not intercepted. AMD manual doesn't explicitly + * state this but appears to behave the same. + * + * On userspace reads and writes, however, we unconditionally + * return L1's TSC value to ensure backwards-compatible + * behavior for migration. + */ + u64 offset, ratio; + + if (msr_info->host_initiated) { + offset = vcpu->arch.l1_tsc_offset; + ratio = vcpu->arch.l1_tsc_scaling_ratio; + } else { + offset = vcpu->arch.tsc_offset; + ratio = vcpu->arch.tsc_scaling_ratio; + } + + msr_info->data = kvm_scale_tsc(rdtsc(), ratio) + offset; + break; + } + case MSR_IA32_CR_PAT: + msr_info->data = vcpu->arch.pat; break; case MSR_MTRRcap: - case 0x200 ... 0x2ff: + case MTRRphysBase_MSR(0) ... MSR_MTRRfix4K_F8000: + case MSR_MTRRdefType: return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); case 0xcd: /* fsb frequency */ msr_info->data = 3; @@ -2771,12 +4444,11 @@ 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 + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); - break; - case MSR_IA32_TSCDEADLINE: + case MSR_IA32_TSC_DEADLINE: msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu); break; case MSR_IA32_TSC_ADJUST: @@ -2786,7 +4458,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.ia32_misc_enable_msr; break; case MSR_IA32_SMBASE: - if (!msr_info->host_initiated) + if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated) return 1; msr_info->data = vcpu->arch.smbase; break; @@ -2803,30 +4475,80 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.efer; break; case MSR_KVM_WALL_CLOCK: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) + return 1; + + msr_info->data = vcpu->kvm->arch.wall_clock; + break; case MSR_KVM_WALL_CLOCK_NEW: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) + return 1; + msr_info->data = vcpu->kvm->arch.wall_clock; break; case MSR_KVM_SYSTEM_TIME: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) + return 1; + + msr_info->data = vcpu->arch.time; + break; case MSR_KVM_SYSTEM_TIME_NEW: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) + return 1; + msr_info->data = vcpu->arch.time; break; case MSR_KVM_ASYNC_PF_EN: - msr_info->data = vcpu->arch.apf.msr_val; + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + return 1; + + msr_info->data = vcpu->arch.apf.msr_en_val; + break; + case MSR_KVM_ASYNC_PF_INT: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) + return 1; + + msr_info->data = vcpu->arch.apf.msr_int_val; + break; + case MSR_KVM_ASYNC_PF_ACK: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) + return 1; + + msr_info->data = 0; break; case MSR_KVM_STEAL_TIME: + if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME)) + return 1; + msr_info->data = vcpu->arch.st.msr_val; break; case MSR_KVM_PV_EOI_EN: + if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI)) + return 1; + msr_info->data = vcpu->arch.pv_eoi.msr_val; break; + case MSR_KVM_POLL_CONTROL: + if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL)) + return 1; + + msr_info->data = vcpu->arch.msr_kvm_poll_control; + break; case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: case MSR_IA32_MCG_CAP: case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: + case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1: return get_msr_mce(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); + case MSR_IA32_XSS: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) + return 1; + msr_info->data = vcpu->arch.ia32_xss; + break; case MSR_K7_CLK_CTL: /* * Provide expected ramp-up count for K7. All other @@ -2839,17 +4561,21 @@ 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: case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: + case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_get_msr_common(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); - break; +#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 @@ -2864,12 +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; @@ -2882,24 +4608,38 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_MISC_FEATURES_ENABLES: msr_info->data = vcpu->arch.msr_misc_features_enables; break; - default: - if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) - return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data); - if (!ignore_msrs) { - vcpu_debug_ratelimited(vcpu, "unhandled rdmsr: 0x%x\n", - msr_info->index); + case MSR_K7_HWCR: + msr_info->data = vcpu->arch.msr_hwcr; + break; +#ifdef CONFIG_X86_64 + case MSR_IA32_XFD: + if (!msr_info->host_initiated && + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; - } else { - if (report_ignored_msrs) - vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", - msr_info->index); - msr_info->data = 0; - } + + msr_info->data = vcpu->arch.guest_fpu.fpstate->xfd; break; + case MSR_IA32_XFD_ERR: + if (!msr_info->host_initiated && + !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); + + 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. @@ -2911,11 +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; } @@ -2932,8 +4686,8 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, { struct kvm_msrs msrs; struct kvm_msr_entry *entries; - int r, n; unsigned size; + int r; r = -EFAULT; if (copy_from_user(&msrs, user_msrs, sizeof(msrs))) @@ -2950,17 +4704,11 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, goto out; } - r = n = __msr_io(vcpu, &msrs, entries, do_msr); - if (r < 0) - goto out_free; + r = __msr_io(vcpu, &msrs, entries, do_msr); - r = -EFAULT; if (writeback && copy_to_user(user_msrs->entries, entries, size)) - goto out_free; - - r = n; + r = -EFAULT; -out_free: kfree(entries); out: return r; @@ -2973,6 +4721,56 @@ 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) +{ + struct kvm_cpuid2 cpuid; + int r; + + r = -EFAULT; + if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) + return r; + + r = kvm_get_hv_cpuid(vcpu, &cpuid, cpuid_arg->entries); + if (r) + return r; + + r = -EFAULT; + if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid))) + return r; + + 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) { int r = 0; @@ -2985,63 +4783,118 @@ 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_XEN_HVM: 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: case KVM_CAP_HYPERV_EVENTFD: case KVM_CAP_HYPERV_TLBFLUSH: case KVM_CAP_HYPERV_SEND_IPI: - case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: 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: case KVM_CAP_XSAVE: case KVM_CAP_ASYNC_PF: + 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: case KVM_CAP_SET_BOOT_CPU_ID: case KVM_CAP_SPLIT_IRQCHIP: case KVM_CAP_IMMEDIATE_EXIT: + case KVM_CAP_PMU_EVENT_FILTER: + case KVM_CAP_PMU_EVENT_MASKED_EVENTS: case KVM_CAP_GET_MSR_FEATURES: case KVM_CAP_MSR_PLATFORM_INFO: case KVM_CAP_EXCEPTION_PAYLOAD: + case KVM_CAP_X86_TRIPLE_FAULT_EVENT: + case KVM_CAP_SET_GUEST_DEBUG: + case KVM_CAP_LAST_CPU: + case KVM_CAP_X86_USER_SPACE_MSR: + case KVM_CAP_X86_MSR_FILTER: + case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: +#ifdef CONFIG_X86_SGX_KVM + case KVM_CAP_SGX_ATTRIBUTE: +#endif + case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: + case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM: + case KVM_CAP_SREGS2: + case KVM_CAP_EXIT_ON_EMULATION_FAILURE: + case KVM_CAP_VCPU_ATTRIBUTES: + case KVM_CAP_SYS_ATTRIBUTES: + case KVM_CAP_VAPIC: + 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; + case KVM_CAP_SET_GUEST_DEBUG2: + return KVM_GUESTDBG_VALID_MASK; +#ifdef CONFIG_KVM_XEN + case KVM_CAP_XEN_HVM: + r = KVM_XEN_HVM_CONFIG_HYPERCALL_MSR | + 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_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_TSC_STABLE; + r = KVM_CLOCK_VALID_FLAGS; break; case KVM_CAP_X86_DISABLE_EXITS: - r |= KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE; - 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)) + break; + /* SMBASE is usually relocated above 1M on modern chipsets, * and SMM handlers might indeed rely on 4G segment limits, * so do not report SMM to be available if real mode is @@ -3050,19 +4903,18 @@ 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 = kvm_x86_ops->has_emulated_msr(MSR_IA32_SMBASE); - break; - case KVM_CAP_VAPIC: - r = !kvm_x86_ops->cpu_has_accelerated_tpr(); + r = kvm_x86_call(has_emulated_msr)(kvm, MSR_IA32_SMBASE); break; case KVM_CAP_NR_VCPUS: - r = KVM_SOFT_MAX_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_NR_MEMSLOTS: - r = KVM_USER_MEM_SLOTS; + case KVM_CAP_MAX_VCPU_ID: + r = KVM_MAX_VCPU_IDS; break; case KVM_CAP_PV_MMU: /* obsolete */ r = 0; @@ -3074,20 +4926,102 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = boot_cpu_has(X86_FEATURE_XSAVE); break; case KVM_CAP_TSC_CONTROL: - r = kvm_has_tsc_control; + case KVM_CAP_VM_TSC_CONTROL: + r = kvm_caps.has_tsc_control; break; case KVM_CAP_X2APIC_API: r = KVM_X2APIC_API_VALID_FLAGS; break; case KVM_CAP_NESTED_STATE: - r = kvm_x86_ops->get_nested_state ? - kvm_x86_ops->get_nested_state(NULL, 0, 0) : 0; + 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; + case KVM_CAP_STEAL_TIME: + r = sched_info_on(); + break; + case KVM_CAP_X86_BUS_LOCK_EXIT: + if (kvm_caps.has_bus_lock_exit) + r = KVM_BUS_LOCK_DETECTION_OFF | + KVM_BUS_LOCK_DETECTION_EXIT; + else + r = 0; + break; + case KVM_CAP_XSAVE2: { + r = xstate_required_size(kvm_get_filtered_xcr0(), false); + if (r < sizeof(struct kvm_xsave)) + r = sizeof(struct kvm_xsave); + break; + } + case KVM_CAP_PMU_CAPABILITY: + r = enable_pmu ? KVM_CAP_PMU_VALID_MASK : 0; + break; + case KVM_CAP_DISABLE_QUIRKS2: + 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 int __kvm_x86_dev_get_attr(struct kvm_device_attr *attr, u64 *val) +{ + if (attr->group) { + if (kvm_x86_ops.dev_get_attr) + return kvm_x86_call(dev_get_attr)(attr->group, attr->attr, val); + return -ENXIO; + } + + switch (attr->attr) { + case KVM_X86_XCOMP_GUEST_SUPP: + *val = kvm_caps.supported_xcr0; + return 0; + default: + return -ENXIO; + } +} +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) +{ + u64 val; + + return __kvm_x86_dev_get_attr(attr, &val); } long kvm_arch_dev_ioctl(struct file *filp, @@ -3143,10 +5077,10 @@ long kvm_arch_dev_ioctl(struct file *filp, r = 0; break; } - case KVM_X86_GET_MCE_CAP_SUPPORTED: { + case KVM_X86_GET_MCE_CAP_SUPPORTED: r = -EFAULT; - if (copy_to_user(argp, &kvm_mce_cap_supported, - sizeof(kvm_mce_cap_supported))) + if (copy_to_user(argp, &kvm_caps.supported_mce_cap, + sizeof(kvm_caps.supported_mce_cap))) goto out; r = 0; break; @@ -3173,38 +5107,80 @@ 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; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_x86_dev_get_attr(&attr); + break; + } + case KVM_HAS_DEVICE_ATTR: { + struct kvm_device_attr attr; + r = -EFAULT; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_x86_dev_has_attr(&attr); break; } default: r = -EINVAL; + break; } 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 (kvm_x86_ops->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); } - kvm_x86_ops->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(); /* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) { @@ -3220,10 +5196,11 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) mark_tsc_unstable("KVM discovered backwards TSC"); if (kvm_check_tsc_unstable()) { - u64 offset = kvm_compute_tsc_offset(vcpu, + 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)) @@ -3245,56 +5222,87 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { + struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; + struct kvm_steal_time __user *st; + struct kvm_memslots *slots; + static const u8 preempted = KVM_VCPU_PREEMPTED; + gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; + + /* + * The vCPU can be marked preempted if and only if the VM-Exit was on + * an instruction boundary and will not trigger guest emulation of any + * kind (see vcpu_run). Vendor specific code controls (conservatively) + * when this is true, for example allowing the vCPU to be marked + * preempted if and only if the VM-Exit was due to a host interrupt. + */ + if (!vcpu->arch.at_instruction_boundary) { + vcpu->stat.preemption_other++; + return; + } + + vcpu->stat.preemption_reported++; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED; + if (vcpu->arch.st.preempted) + return; - kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal.preempted, - offsetof(struct kvm_steal_time, preempted), - sizeof(vcpu->arch.st.steal.preempted)); + /* This happens on process exit */ + if (unlikely(current->mm != vcpu->kvm->mm)) + return; + + slots = kvm_memslots(vcpu->kvm); + + if (unlikely(slots->generation != ghc->generation || + gpa != ghc->gpa || + kvm_is_error_hva(ghc->hva) || !ghc->memslot)) + return; + + st = (struct kvm_steal_time __user *)ghc->hva; + BUILD_BUG_ON(sizeof(st->preempted) != sizeof(preempted)); + + if (!copy_to_user_nofault(&st->preempted, &preempted, sizeof(preempted))) + vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; + + mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { int idx; - if (vcpu->preempted) - vcpu->arch.preempted_in_kernel = !kvm_x86_ops->get_cpl(vcpu); + if (vcpu->preempted) { + /* + * 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); - /* - * Disable page faults because we're in atomic context here. - * kvm_write_guest_offset_cached() would call might_fault() - * that relies on pagefault_disable() to tell if there's a - * bug. NOTE: the write to guest memory may not go through if - * during postcopy live migration or if there's heavy guest - * paging. - */ - pagefault_disable(); - /* - * kvm_memslots() will be called by - * kvm_write_guest_offset_cached() so take the srcu lock. - */ - idx = srcu_read_lock(&vcpu->kvm->srcu); - kvm_steal_time_set_preempted(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - pagefault_enable(); - kvm_x86_ops->vcpu_put(vcpu); + /* + * Take the srcu lock as memslots will be accessed to check the gfn + * cache generation against the memslots generation. + */ + idx = srcu_read_lock(&vcpu->kvm->srcu); + if (kvm_xen_msr_enabled(vcpu->kvm)) + kvm_xen_runstate_set_preempted(vcpu); + else + kvm_steal_time_set_preempted(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + } + + kvm_x86_call(vcpu_put)(vcpu); vcpu->arch.last_host_tsc = rdtsc(); - /* - * If userspace has set any breakpoints or watchpoints, dr6 is restored - * on every vmexit, but if not, we might have a stale dr6 from the - * guest. do_debug expects dr6 to be cleared after it runs, do the same. - */ - set_debugreg(0, 6); } static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - if (vcpu->arch.apicv_active) - kvm_x86_ops->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); } @@ -3304,6 +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; @@ -3314,22 +5325,33 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) { + /* + * We can accept userspace's request for interrupt injection + * as long as we have a place to store the interrupt number. + * The actual injection will happen when the CPU is able to + * deliver the interrupt. + */ + if (kvm_cpu_has_extint(vcpu)) + return false; + + /* Acknowledging ExtINT does not happen if LINT0 is masked. */ return (!lapic_in_kernel(vcpu) || kvm_apic_accept_pic_intr(vcpu)); } -/* - * if userspace requested an interrupt window, check that the - * interrupt window is open. - * - * No need to exit to userspace if we already have an interrupt queued. - */ static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) { - return kvm_arch_interrupt_allowed(vcpu) && - !kvm_cpu_has_interrupt(vcpu) && + /* + * Do not cause an interrupt window exit if an exception + * is pending or an event needs reinjection; userspace + * might want to inject the interrupt manually using KVM_SET_REGS + * or KVM_SET_SREGS. For that to work, we must be at an + * instruction boundary and with no events half-injected. + */ + return (kvm_arch_interrupt_allowed(vcpu) && + kvm_cpu_accept_dm_intr(vcpu) && !kvm_event_needs_reinjection(vcpu) && - kvm_cpu_accept_dm_intr(vcpu); + !kvm_is_exception_pending(vcpu)); } static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, @@ -3366,13 +5388,6 @@ static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu) return 0; } -static int kvm_vcpu_ioctl_smi(struct kvm_vcpu *vcpu) -{ - kvm_make_request(KVM_REQ_SMI, vcpu); - - return 0; -} - static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu, struct kvm_tpr_access_ctl *tac) { @@ -3389,25 +5404,65 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, unsigned bank_num = mcg_cap & 0xff, bank; r = -EINVAL; - if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS) + if (!bank_num || bank_num > KVM_MAX_MCE_BANKS) goto out; - if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000)) + if (mcg_cap & ~(kvm_caps.supported_mce_cap | 0xff | 0xff0000)) goto out; r = 0; vcpu->arch.mcg_cap = mcg_cap; /* Init IA32_MCG_CTL to all 1s */ if (mcg_cap & MCG_CTL_P) vcpu->arch.mcg_ctl = ~(u64)0; - /* Init IA32_MCi_CTL to all 1s */ - for (bank = 0; bank < bank_num; bank++) + /* Init IA32_MCi_CTL to all 1s, IA32_MCi_CTL2 to all 0s */ + for (bank = 0; bank < bank_num; bank++) { vcpu->arch.mce_banks[bank*4] = ~(u64)0; + if (mcg_cap & MCG_CMCI_P) + vcpu->arch.mci_ctl2_banks[bank] = 0; + } + + kvm_apic_after_set_mcg_cap(vcpu); - if (kvm_x86_ops->setup_mce) - kvm_x86_ops->setup_mce(vcpu); + kvm_x86_call(setup_mce)(vcpu); out: return r; } +/* + * Validate this is an UCNA (uncorrectable no action) error by checking the + * MCG_STATUS and MCi_STATUS registers: + * - none of the bits for Machine Check Exceptions are set + * - both the VAL (valid) and UC (uncorrectable) bits are set + * MCI_STATUS_PCC - Processor Context Corrupted + * MCI_STATUS_S - Signaled as a Machine Check Exception + * MCI_STATUS_AR - Software recoverable Action Required + */ +static bool is_ucna(struct kvm_x86_mce *mce) +{ + return !mce->mcg_status && + !(mce->status & (MCI_STATUS_PCC | MCI_STATUS_S | MCI_STATUS_AR)) && + (mce->status & MCI_STATUS_VAL) && + (mce->status & MCI_STATUS_UC); +} + +static int kvm_vcpu_x86_set_ucna(struct kvm_vcpu *vcpu, struct kvm_x86_mce *mce, u64* banks) +{ + u64 mcg_cap = vcpu->arch.mcg_cap; + + banks[1] = mce->status; + banks[2] = mce->addr; + banks[3] = mce->misc; + vcpu->arch.mcg_status = mce->mcg_status; + + if (!(mcg_cap & MCG_CMCI_P) || + !(vcpu->arch.mci_ctl2_banks[mce->bank] & MCI_CTL2_CMCI_EN)) + return 0; + + if (lapic_in_kernel(vcpu)) + kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTCMCI); + + return 0; +} + static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, struct kvm_x86_mce *mce) { @@ -3417,6 +5472,12 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, if (mce->bank >= bank_num || !(mce->status & MCI_STATUS_VAL)) return -EINVAL; + + banks += array_index_nospec(4 * mce->bank, 4 * bank_num); + + if (is_ucna(mce)) + return kvm_vcpu_x86_set_ucna(vcpu, mce, banks); + /* * if IA32_MCG_CTL is not all 1s, the uncorrected error * reporting is disabled @@ -3424,7 +5485,6 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, if ((mce->status & MCI_STATUS_UC) && (mcg_cap & MCG_CTL_P) && vcpu->arch.mcg_ctl != ~(u64)0) return 0; - banks += 4 * mce->bank; /* * if IA32_MCi_CTL is not all 1s, the uncorrected error * reporting is disabled for the bank @@ -3433,7 +5493,7 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, return 0; if (mce->status & MCI_STATUS_UC) { if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) || - !kvm_read_cr4_bits(vcpu, X86_CR4_MCE)) { + !kvm_is_cr4_bit_set(vcpu, X86_CR4_MCE)) { kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); return 0; } @@ -3459,52 +5519,83 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { + struct kvm_queued_exception *ex; + process_nmi(vcpu); +#ifdef CONFIG_KVM_SMM + if (kvm_check_request(KVM_REQ_SMI, vcpu)) + process_smi(vcpu); +#endif + + /* + * KVM's ABI only allows for one exception to be migrated. Luckily, + * the only time there can be two queued exceptions is if there's a + * non-exiting _injected_ exception, and a pending exiting exception. + * In that case, ignore the VM-Exiting exception as it's an extension + * of the injected exception. + */ + if (vcpu->arch.exception_vmexit.pending && + !vcpu->arch.exception.pending && + !vcpu->arch.exception.injected) + ex = &vcpu->arch.exception_vmexit; + else + ex = &vcpu->arch.exception; + + /* + * In guest mode, payload delivery should be deferred if the exception + * will be intercepted by L1, e.g. KVM should not modifying CR2 if L1 + * intercepts #PF, ditto for DR6 and #DBs. If the per-VM capability, + * KVM_CAP_EXCEPTION_PAYLOAD, is not set, userspace may or may not + * propagate the payload and so it cannot be safely deferred. Deliver + * the payload if the capability hasn't been requested. + */ + if (!vcpu->kvm->arch.exception_payload_enabled && + ex->pending && ex->has_payload) + kvm_deliver_exception_payload(vcpu, ex); + + memset(events, 0, sizeof(*events)); + /* * The API doesn't provide the instruction length for software * exceptions, so don't report them. As long as the guest RIP * isn't advanced, we should expect to encounter the exception * again. */ - if (kvm_exception_is_soft(vcpu->arch.exception.nr)) { - events->exception.injected = 0; - events->exception.pending = 0; - } else { - events->exception.injected = vcpu->arch.exception.injected; - events->exception.pending = vcpu->arch.exception.pending; + if (!kvm_exception_is_soft(ex->vector)) { + events->exception.injected = ex->injected; + events->exception.pending = ex->pending; /* * For ABI compatibility, deliberately conflate * pending and injected exceptions when * KVM_CAP_EXCEPTION_PAYLOAD isn't enabled. */ if (!vcpu->kvm->arch.exception_payload_enabled) - events->exception.injected |= - vcpu->arch.exception.pending; + events->exception.injected |= ex->pending; } - events->exception.nr = vcpu->arch.exception.nr; - events->exception.has_error_code = vcpu->arch.exception.has_error_code; - events->exception.error_code = vcpu->arch.exception.error_code; - events->exception_has_payload = vcpu->arch.exception.has_payload; - events->exception_payload = vcpu->arch.exception.payload; + events->exception.nr = ex->vector; + events->exception.has_error_code = ex->has_error_code; + events->exception.error_code = ex->error_code; + events->exception_has_payload = ex->has_payload; + events->exception_payload = ex->payload; events->interrupt.injected = vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft; events->interrupt.nr = vcpu->arch.interrupt.nr; - events->interrupt.soft = 0; - events->interrupt.shadow = kvm_x86_ops->get_interrupt_shadow(vcpu); + events->interrupt.shadow = kvm_x86_call(get_interrupt_shadow)(vcpu); events->nmi.injected = vcpu->arch.nmi_injected; - events->nmi.pending = vcpu->arch.nmi_pending != 0; - events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu); - events->nmi.pad = 0; + events->nmi.pending = kvm_get_nr_pending_nmis(vcpu); + events->nmi.masked = kvm_x86_call(get_nmi_mask)(vcpu); - events->sipi_vector = 0; /* never valid when reporting to user space */ + /* events->sipi_vector is never valid when reporting to user space */ +#ifdef CONFIG_KVM_SMM events->smi.smm = is_smm(vcpu); events->smi.pending = vcpu->arch.smi_pending; events->smi.smm_inside_nmi = !!(vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK); +#endif events->smi.latched_init = kvm_lapic_latched_init(vcpu); events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING @@ -3512,12 +5603,12 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, | KVM_VCPUEVENT_VALID_SMM); if (vcpu->kvm->arch.exception_payload_enabled) events->flags |= KVM_VCPUEVENT_VALID_PAYLOAD; - - memset(&events->reserved, 0, sizeof(events->reserved)); + if (vcpu->kvm->arch.triple_fault_event) { + events->triple_fault.pending = kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu); + events->flags |= KVM_VCPUEVENT_VALID_TRIPLE_FAULT; + } } -static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags); - static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { @@ -3525,7 +5616,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, | KVM_VCPUEVENT_VALID_SIPI_VECTOR | KVM_VCPUEVENT_VALID_SHADOW | KVM_VCPUEVENT_VALID_SMM - | KVM_VCPUEVENT_VALID_PAYLOAD)) + | KVM_VCPUEVENT_VALID_PAYLOAD + | KVM_VCPUEVENT_VALID_TRIPLE_FAULT)) return -EINVAL; if (events->flags & KVM_VCPUEVENT_VALID_PAYLOAD) { @@ -3544,16 +5636,23 @@ 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); + + /* + * Flag that userspace is stuffing an exception, the next KVM_RUN will + * morph the exception to a VM-Exit if appropriate. Do this only for + * pending exceptions, already-injected exceptions are not subject to + * intercpetion. Note, userspace that conflates pending and injected + * is hosed, and will incorrectly convert an injected exception into a + * pending exception, which in turn may cause a spurious VM-Exit. + */ + vcpu->arch.exception_from_userspace = events->exception.pending; + + vcpu->arch.exception_vmexit.pending = false; + vcpu->arch.exception.injected = events->exception.injected; vcpu->arch.exception.pending = events->exception.pending; - vcpu->arch.exception.nr = events->exception.nr; + vcpu->arch.exception.vector = events->exception.nr; vcpu->arch.exception.has_error_code = events->exception.has_error_code; vcpu->arch.exception.error_code = events->exception.error_code; vcpu->arch.exception.has_payload = events->exception_has_payload; @@ -3563,25 +5662,28 @@ 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) - kvm_x86_ops->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 = events->nmi.pending; - kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked); + if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) { + vcpu->arch.nmi_pending = 0; + atomic_set(&vcpu->arch.nmi_queued, events->nmi.pending); + if (events->nmi.pending) + kvm_make_request(KVM_REQ_NMI, vcpu); + } + kvm_x86_call(set_nmi_mask)(vcpu, events->nmi.masked); if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR && lapic_in_kernel(vcpu)) vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { - u32 hflags = vcpu->arch.hflags; - if (events->smi.smm) - hflags |= HF_SMM_MASK; - else - hflags &= ~HF_SMM_MASK; - kvm_set_hflags(vcpu, hflags); +#ifdef CONFIG_KVM_SMM + if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { + kvm_leave_nested(vcpu); + kvm_smm_changed(vcpu, events->smi.smm); + } vcpu->arch.smi_pending = events->smi.pending; @@ -3590,13 +5692,29 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; else vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; - if (lapic_in_kernel(vcpu)) { - if (events->smi.latched_init) - set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); - else - clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); - } } + +#else + if (events->smi.smm || events->smi.pending || + events->smi.smm_inside_nmi) + return -EINVAL; +#endif + + if (lapic_in_kernel(vcpu)) { + if (events->smi.latched_init) + set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + else + clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + } + } + + if (events->flags & KVM_VCPUEVENT_VALID_TRIPLE_FAULT) { + if (!vcpu->kvm->arch.triple_fault_event) + return -EINVAL; + if (events->triple_fault.pending) + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + else + kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); } kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -3604,182 +5722,117 @@ 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; - dbgregs->flags = 0; - memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved)); + 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; - if (dbgregs->dr6 & ~0xffffffffull) + if (!kvm_dr6_valid(dbgregs->dr6)) return -EINVAL; - if (dbgregs->dr7 & ~0xffffffffull) + 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; - kvm_update_dr6(vcpu); vcpu->arch.dr7 = dbgregs->dr7; kvm_update_dr7(vcpu); return 0; } -#define XSTATE_COMPACTION_ENABLED (1ULL << 63) -static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) +static int kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, + u8 *state, unsigned int size) { - struct xregs_state *xsave = &vcpu->arch.guest_fpu->state.xsave; - u64 xstate_bv = xsave->header.xfeatures; - u64 valid; - - /* - * Copy legacy XSAVE area, to avoid complications with CPUID - * leaves 0 and 1 in the loop below. - */ - memcpy(dest, xsave, XSAVE_HDR_OFFSET); - - /* Set XSTATE_BV */ - xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE; - *(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv; - /* - * Copy each region from the possibly compacted offset to the - * non-compacted offset. - */ - valid = xstate_bv & ~XFEATURE_MASK_FPSSE; - while (valid) { - u64 feature = valid & -valid; - int index = fls64(feature) - 1; - void *src = get_xsave_addr(xsave, feature); - - if (src) { - u32 size, offset, ecx, edx; - cpuid_count(XSTATE_CPUID, index, - &size, &offset, &ecx, &edx); - if (feature == XFEATURE_MASK_PKRU) - memcpy(dest + offset, &vcpu->arch.pkru, - sizeof(vcpu->arch.pkru)); - else - memcpy(dest + offset, src, size); - - } - - valid -= feature; - } -} - -static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) -{ - struct xregs_state *xsave = &vcpu->arch.guest_fpu->state.xsave; - u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET); - u64 valid; - - /* - * Copy legacy XSAVE area, to avoid complications with CPUID - * leaves 0 and 1 in the loop below. + * 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. */ - memcpy(xsave, src, XSAVE_HDR_OFFSET); + u64 supported_xcr0 = vcpu->arch.guest_supported_xcr0 | + XFEATURE_MASK_FPSSE; - /* Set XSTATE_BV and possibly XCOMP_BV. */ - xsave->header.xfeatures = xstate_bv; - if (boot_cpu_has(X86_FEATURE_XSAVES)) - xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; - /* - * Copy each region from the non-compacted offset to the - * possibly compacted offset. - */ - valid = xstate_bv & ~XFEATURE_MASK_FPSSE; - while (valid) { - u64 feature = valid & -valid; - int index = fls64(feature) - 1; - void *dest = get_xsave_addr(xsave, feature); - - if (dest) { - u32 size, offset, ecx, edx; - cpuid_count(XSTATE_CPUID, index, - &size, &offset, &ecx, &edx); - if (feature == XFEATURE_MASK_PKRU) - memcpy(&vcpu->arch.pkru, src + offset, - sizeof(vcpu->arch.pkru)); - else - memcpy(dest, src + offset, size); - } - - valid -= feature; - } + 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_xsave(struct kvm_vcpu *vcpu, - struct kvm_xsave *guest_xsave) +static int kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, + struct kvm_xsave *guest_xsave) { - if (boot_cpu_has(X86_FEATURE_XSAVE)) { - memset(guest_xsave, 0, sizeof(struct kvm_xsave)); - fill_xsave((u8 *) guest_xsave->region, vcpu); - } else { - memcpy(guest_xsave->region, - &vcpu->arch.guest_fpu->state.fxsave, - sizeof(struct fxregs_state)); - *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] = - XFEATURE_MASK_FPSSE; - } + return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region, + sizeof(guest_xsave->region)); } -#define XSAVE_MXCSR_OFFSET 24 - static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { - u64 xstate_bv = - *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)]; - u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)]; + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) + return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; - if (boot_cpu_has(X86_FEATURE_XSAVE)) { - /* - * Here we allow setting states that are not present in - * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility - * with old userspace. - */ - if (xstate_bv & ~kvm_supported_xcr0() || - mxcsr & ~mxcsr_feature_mask) - return -EINVAL; - load_xsave(vcpu, (u8 *)guest_xsave->region); - } else { - if (xstate_bv & ~XFEATURE_MASK_FPSSE || - mxcsr & ~mxcsr_feature_mask) - return -EINVAL; - memcpy(&vcpu->arch.guest_fpu->state.fxsave, - guest_xsave->region, sizeof(struct fxregs_state)); - } - return 0; + return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu, + guest_xsave->region, + kvm_caps.supported_xcr0, + &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, @@ -3787,6 +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; @@ -3813,47 +5870,295 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, */ static int kvm_set_guest_paused(struct kvm_vcpu *vcpu) { - if (!vcpu->arch.pv_time_enabled) + if (!vcpu->arch.pv_time.active) return -EINVAL; vcpu->arch.pvclock_set_guest_stopped_request = true; kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); return 0; } -static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, - struct kvm_enable_cap *cap) +static int kvm_arch_tsc_has_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) { int r; - uint16_t vmcs_version; - void __user *user_ptr; + switch (attr->attr) { + case KVM_VCPU_TSC_OFFSET: + r = 0; + break; + default: + r = -ENXIO; + } + + return r; +} + +static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + u64 __user *uaddr = u64_to_user_ptr(attr->addr); + int r; + + switch (attr->attr) { + case KVM_VCPU_TSC_OFFSET: + r = -EFAULT; + if (put_user(vcpu->arch.l1_tsc_offset, uaddr)) + break; + r = 0; + break; + default: + r = -ENXIO; + } + + return r; +} + +static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + u64 __user *uaddr = u64_to_user_ptr(attr->addr); + struct kvm *kvm = vcpu->kvm; + int r; + + switch (attr->attr) { + case KVM_VCPU_TSC_OFFSET: { + u64 offset, tsc, ns; + unsigned long flags; + bool matched; + + r = -EFAULT; + if (get_user(offset, uaddr)) + break; + + raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); + + matched = (vcpu->arch.virtual_tsc_khz && + kvm->arch.last_tsc_khz == vcpu->arch.virtual_tsc_khz && + kvm->arch.last_tsc_offset == offset); + + 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, true); + raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); + + r = 0; + break; + } + default: + r = -ENXIO; + } + + return r; +} + +static int kvm_vcpu_ioctl_device_attr(struct kvm_vcpu *vcpu, + unsigned int ioctl, + void __user *argp) +{ + struct kvm_device_attr attr; + int r; + + if (copy_from_user(&attr, argp, sizeof(attr))) + return -EFAULT; + + if (attr.group != KVM_VCPU_TSC_CTRL) + return -ENXIO; + + switch (ioctl) { + case KVM_HAS_DEVICE_ATTR: + r = kvm_arch_tsc_has_attr(vcpu, &attr); + break; + case KVM_GET_DEVICE_ATTR: + r = kvm_arch_tsc_get_attr(vcpu, &attr); + break; + case KVM_SET_DEVICE_ATTR: + r = kvm_arch_tsc_set_attr(vcpu, &attr); + break; + } + + return r; +} + +static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, + struct kvm_enable_cap *cap) +{ if (cap->flags) return -EINVAL; switch (cap->cap) { +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV_SYNIC2: if (cap->args[0]) return -EINVAL; + fallthrough; + case KVM_CAP_HYPERV_SYNIC: if (!irqchip_in_kernel(vcpu->kvm)) return -EINVAL; return kvm_hv_activate_synic(vcpu, cap->cap == KVM_CAP_HYPERV_SYNIC2); case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: - if (!kvm_x86_ops->nested_enable_evmcs) - return -ENOTTY; - r = kvm_x86_ops->nested_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 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]; + 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, @@ -3863,6 +6168,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int r; union { + struct kvm_sregs2 *sregs2; struct kvm_lapic_state *lapic; struct kvm_xsave *xsave; struct kvm_xcrs *xcrs; @@ -3918,7 +6224,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SMI: { - r = kvm_vcpu_ioctl_smi(vcpu); + r = kvm_inject_smi(vcpu); break; } case KVM_SET_CPUID: { @@ -3971,6 +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; @@ -4037,13 +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, @@ -4064,12 +6381,18 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_GET_XSAVE: { + r = -EINVAL; + if (vcpu->arch.guest_fpu.uabi_size > sizeof(struct kvm_xsave)) + break; + 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))) @@ -4078,7 +6401,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SET_XSAVE: { - u.xsave = memdup_user(argp, sizeof(*u.xsave)); + int size = vcpu->arch.guest_fpu.uabi_size; + + u.xsave = memdup_user(argp, size); if (IS_ERR(u.xsave)) { r = PTR_ERR(u.xsave); goto out_nofree; @@ -4087,13 +6412,36 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave); break; } + + case KVM_GET_XSAVE2: { + int size = vcpu->arch.guest_fpu.uabi_size; + + u.xsave = kzalloc(size, GFP_KERNEL); + r = -ENOMEM; + if (!u.xsave) + break; + + 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)) + break; + + r = 0; + break; + } + case KVM_GET_XCRS: { 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, @@ -4116,9 +6464,14 @@ 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 (user_tsc_khz >= kvm_max_guest_tsc_khz) + if (kvm_caps.has_tsc_control && + user_tsc_khz >= kvm_caps.max_guest_tsc_khz) goto out; if (user_tsc_khz == 0) @@ -4151,7 +6504,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, u32 user_data_size; r = -EINVAL; - if (!kvm_x86_ops->get_nested_state) + if (!kvm_x86_ops.nested_ops->get_state) break; BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size)); @@ -4159,8 +6512,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (get_user(user_data_size, &user_kvm_nested_state->size)) break; - r = kvm_x86_ops->get_nested_state(vcpu, user_kvm_nested_state, - user_data_size); + r = kvm_x86_ops.nested_ops->get_state(vcpu, user_kvm_nested_state, + user_data_size); if (r < 0) break; @@ -4178,9 +6531,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_SET_NESTED_STATE: { struct kvm_nested_state __user *user_kvm_nested_state = argp; struct kvm_nested_state kvm_state; + int idx; r = -EINVAL; - if (!kvm_x86_ops->set_nested_state) + if (!kvm_x86_ops.nested_ops->set_state) break; r = -EFAULT; @@ -4193,7 +6547,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (kvm_state.flags & ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE - | KVM_STATE_NESTED_EVMCS)) + | KVM_STATE_NESTED_EVMCS | KVM_STATE_NESTED_MTF_PENDING + | KVM_STATE_NESTED_GIF_SET)) break; /* nested_run_pending implies guest_mode. */ @@ -4201,28 +6556,81 @@ long kvm_arch_vcpu_ioctl(struct file *filp, && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE)) break; - r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); + idx = srcu_read_lock(&vcpu->kvm->srcu); + r = kvm_x86_ops.nested_ops->set_state(vcpu, user_kvm_nested_state, &kvm_state); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } - case KVM_GET_SUPPORTED_HV_CPUID: { - struct kvm_cpuid2 __user *cpuid_arg = argp; - struct kvm_cpuid2 cpuid; +#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; r = -EFAULT; - if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) + if (copy_from_user(&xva, argp, sizeof(xva))) goto out; + r = kvm_xen_vcpu_get_attr(vcpu, &xva); + if (!r && copy_to_user(argp, &xva, sizeof(xva))) + r = -EFAULT; + break; + } + case KVM_XEN_VCPU_SET_ATTR: { + struct kvm_xen_vcpu_attr xva; - r = kvm_vcpu_ioctl_get_hv_cpuid(vcpu, &cpuid, - cpuid_arg->entries); - if (r) + r = -EFAULT; + if (copy_from_user(&xva, argp, sizeof(xva))) + goto out; + r = kvm_xen_vcpu_set_attr(vcpu, &xva); + break; + } +#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) + goto out; + __get_sregs2(vcpu, u.sregs2); r = -EFAULT; - if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid))) + if (copy_to_user(argp, u.sregs2, sizeof(struct kvm_sregs2))) goto out; r = 0; 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); + u.sregs2 = NULL; + goto out; + } + r = __set_sregs2(vcpu, u.sregs2); + break; + } + case KVM_HAS_DEVICE_ATTR: + case KVM_GET_DEVICE_ATTR: + 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; } @@ -4244,18 +6652,18 @@ static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr) if (addr > (unsigned int)(-3 * PAGE_SIZE)) return -EINVAL; - ret = kvm_x86_ops->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 kvm_x86_ops->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, - u32 kvm_nr_mmu_pages) + unsigned long kvm_nr_mmu_pages) { if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES) return -EINVAL; @@ -4269,313 +6677,552 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, return 0; } -static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { - return kvm->arch.n_max_mmu_pages; + + /* + * Flush all CPUs' dirty log buffers to the dirty_bitmap. Called + * before reporting dirty_bitmap to userspace. KVM flushes the buffers + * on all VM-Exits, thus we only need to kick running vCPUs to force a + * VM-Exit. + */ + 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); } -static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) +int kvm_vm_ioctl_enable_cap(struct kvm *kvm, + struct kvm_enable_cap *cap) { - 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)); + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_DISABLE_QUIRKS2: + r = -EINVAL; + if (cap->args[0] & ~kvm_caps.supported_quirks) + break; + fallthrough; + case KVM_CAP_DISABLE_QUIRKS: + kvm->arch.disabled_quirks |= cap->args[0] & kvm_caps.supported_quirks; + r = 0; break; - case KVM_IRQCHIP_PIC_SLAVE: - memcpy(&chip->chip.pic, &pic->pics[1], - sizeof(struct kvm_pic_state)); + case KVM_CAP_SPLIT_IRQCHIP: { + mutex_lock(&kvm->lock); + r = -EINVAL; + if (cap->args[0] > MAX_NR_RESERVED_IOAPIC_PINS) + goto split_irqchip_unlock; + r = -EEXIST; + if (irqchip_in_kernel(kvm)) + goto split_irqchip_unlock; + if (kvm->created_vcpus) + goto split_irqchip_unlock; + /* Pairs with irqchip_in_kernel. */ + smp_wmb(); + kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT; + kvm->arch.nr_reserved_ioapic_pins = cap->args[0]; + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_ABSENT); + r = 0; +split_irqchip_unlock: + mutex_unlock(&kvm->lock); break; - case KVM_IRQCHIP_IOAPIC: - kvm_get_ioapic(kvm, &chip->chip.ioapic); + } + case KVM_CAP_X2APIC_API: + r = -EINVAL; + if (cap->args[0] & ~KVM_X2APIC_API_VALID_FLAGS) + break; + + if (cap->args[0] & KVM_X2APIC_API_USE_32BIT_IDS) + kvm->arch.x2apic_format = true; + if (cap->args[0] & KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) + kvm->arch.x2apic_broadcast_quirk_disabled = true; + + r = 0; break; - default: + case KVM_CAP_X86_DISABLE_EXITS: r = -EINVAL; + if (cap->args[0] & ~kvm_get_allowed_disable_exits()) + break; + + 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 && 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]; + r = 0; + break; + case KVM_CAP_EXCEPTION_PAYLOAD: + kvm->arch.exception_payload_enabled = cap->args[0]; + r = 0; + break; + case KVM_CAP_X86_TRIPLE_FAULT_EVENT: + kvm->arch.triple_fault_event = cap->args[0]; + r = 0; + break; + case KVM_CAP_X86_USER_SPACE_MSR: + r = -EINVAL; + if (cap->args[0] & ~KVM_MSR_EXIT_REASON_VALID_MASK) + break; + kvm->arch.user_space_msr_mask = cap->args[0]; + r = 0; + break; + case KVM_CAP_X86_BUS_LOCK_EXIT: + r = -EINVAL; + if (cap->args[0] & ~KVM_BUS_LOCK_DETECTION_VALID_MODE) + break; + + if ((cap->args[0] & KVM_BUS_LOCK_DETECTION_OFF) && + (cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT)) + break; + + if (kvm_caps.has_bus_lock_exit && + cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT) + kvm->arch.bus_lock_detection_enabled = true; + r = 0; + break; +#ifdef CONFIG_X86_SGX_KVM + case KVM_CAP_SGX_ATTRIBUTE: { + unsigned long allowed_attributes = 0; + + r = sgx_set_attribute(&allowed_attributes, cap->args[0]); + if (r) + break; + + /* KVM only supports the PROVISIONKEY privileged attribute. */ + if ((allowed_attributes & SGX_ATTR_PROVISIONKEY) && + !(allowed_attributes & ~SGX_ATTR_PROVISIONKEY)) + kvm->arch.sgx_provisioning_allowed = true; + else + r = -EINVAL; break; } - return r; -} +#endif + case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: + r = -EINVAL; + if (!kvm_x86_ops.vm_copy_enc_context_from) + break; -static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) -{ - struct kvm_pic *pic = kvm->arch.vpic; - int r; + 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 = 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); + 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) { + r = -EINVAL; + break; + } + kvm->arch.hypercall_exit_enabled = cap->args[0]; + r = 0; + break; + case KVM_CAP_EXIT_ON_EMULATION_FAILURE: + r = -EINVAL; + if (cap->args[0] & ~1) + break; + kvm->arch.exit_on_emulation_error = cap->args[0]; + r = 0; + break; + case KVM_CAP_PMU_CAPABILITY: + r = -EINVAL; + if (!enable_pmu || (cap->args[0] & ~KVM_CAP_PMU_VALID_MASK)) + break; + + mutex_lock(&kvm->lock); + if (!kvm->created_vcpus) { + kvm->arch.enable_pmu = !(cap->args[0] & KVM_PMU_CAP_DISABLE); + r = 0; + } + mutex_unlock(&kvm->lock); + break; + case KVM_CAP_MAX_VCPU_ID: + r = -EINVAL; + if (cap->args[0] > KVM_MAX_VCPU_IDS) + break; + + mutex_lock(&kvm->lock); + 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]; + r = 0; + } + mutex_unlock(&kvm->lock); + break; + case KVM_CAP_X86_NOTIFY_VMEXIT: + r = -EINVAL; + if ((u32)cap->args[0] & ~KVM_X86_NOTIFY_VMEXIT_VALID_BITS) + break; + if (!kvm_caps.has_notify_vmexit) + break; + if (!((u32)cap->args[0] & KVM_X86_NOTIFY_VMEXIT_ENABLED)) + break; + mutex_lock(&kvm->lock); + if (!kvm->created_vcpus) { + kvm->arch.notify_window = cap->args[0] >> 32; + kvm->arch.notify_vmexit_flags = (u32)cap->args[0]; + r = 0; + } + mutex_unlock(&kvm->lock); + break; + case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: + r = -EINVAL; + + /* + * Since the risk of disabling NX hugepages is a guest crashing + * the system, ensure the userspace process has permission to + * reboot the system. + * + * Note that unlike the reboot() syscall, the process must have + * this capability in the root namespace because exposing + * /dev/kvm into a container does not limit the scope of the + * iTLB multihit bug to that container. In other words, + * this must use capable(), not ns_capable(). + */ + if (!capable(CAP_SYS_BOOT)) { + r = -EPERM; + break; + } + + if (cap->args[0]) + break; + + mutex_lock(&kvm->lock); + if (!kvm->created_vcpus) { + kvm->arch.disable_nx_huge_pages = true; + r = 0; + } + 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; } - kvm_pic_update_irq(pic); return r; } -static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) +static struct kvm_x86_msr_filter *kvm_alloc_msr_filter(bool default_allow) { - struct kvm_kpit_state *kps = &kvm->arch.vpit->pit_state; + struct kvm_x86_msr_filter *msr_filter; - BUILD_BUG_ON(sizeof(*ps) != sizeof(kps->channels)); + msr_filter = kzalloc(sizeof(*msr_filter), GFP_KERNEL_ACCOUNT); + if (!msr_filter) + return NULL; - mutex_lock(&kps->lock); - memcpy(ps, &kps->channels, sizeof(*ps)); - mutex_unlock(&kps->lock); - return 0; + msr_filter->default_allow = default_allow; + return msr_filter; } -static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) +static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter) { - int i; - struct kvm_pit *pit = kvm->arch.vpit; + u32 i; - 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; -} + if (!msr_filter) + return; -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; -} + for (i = 0; i < msr_filter->count; i++) + kfree(msr_filter->ranges[i].bitmap); -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; + kfree(msr_filter); } -static int kvm_vm_ioctl_reinject(struct kvm *kvm, - struct kvm_reinject_control *control) +static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, + struct kvm_msr_filter_range *user_range) { - struct kvm_pit *pit = kvm->arch.vpit; + unsigned long *bitmap; + size_t bitmap_size; - if (!pit) - return -ENXIO; + if (!user_range->nmsrs) + return 0; - /* 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); + if (user_range->flags & ~KVM_MSR_FILTER_RANGE_VALID_MASK) + return -EINVAL; + + if (!user_range->flags) + return -EINVAL; + + bitmap_size = BITS_TO_LONGS(user_range->nmsrs) * sizeof(long); + if (!bitmap_size || bitmap_size > KVM_MSR_FILTER_MAX_BITMAP_SIZE) + return -EINVAL; + + bitmap = memdup_user((__user u8*)user_range->bitmap, bitmap_size); + if (IS_ERR(bitmap)) + return PTR_ERR(bitmap); + msr_filter->ranges[msr_filter->count] = (struct msr_bitmap_range) { + .flags = user_range->flags, + .base = user_range->base, + .nmsrs = user_range->nmsrs, + .bitmap = bitmap, + }; + + msr_filter->count++; return 0; } -/** - * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot - * @kvm: kvm instance - * @log: slot id and address to which we copy the log - * - * Steps 1-4 below provide general overview of dirty page logging. See - * kvm_get_dirty_log_protect() function description for additional details. - * - * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we - * always flush the TLB (step 4) even if previous step failed and the dirty - * bitmap may be corrupt. Regardless of previous outcome the KVM logging API - * does not preclude user space subsequent dirty log read. Flushing TLB ensures - * writes will be marked dirty for next log read. - * - * 1. Take a snapshot of the bit and clear it if needed. - * 2. Write protect the corresponding page. - * 3. Copy the snapshot to the userspace. - * 4. Flush TLB's if needed. - */ -int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) +static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, + struct kvm_msr_filter *filter) { - bool flush = false; + struct kvm_x86_msr_filter *new_filter, *old_filter; + bool default_allow; + bool empty = true; int r; + u32 i; - mutex_lock(&kvm->slots_lock); + if (filter->flags & ~KVM_MSR_FILTER_VALID_MASK) + return -EINVAL; - /* - * Flush potentially hardware-cached dirty pages to dirty_bitmap. - */ - if (kvm_x86_ops->flush_log_dirty) - kvm_x86_ops->flush_log_dirty(kvm); + for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) + empty &= !filter->ranges[i].nmsrs; + + default_allow = !(filter->flags & KVM_MSR_FILTER_DEFAULT_DENY); + if (empty && !default_allow) + return -EINVAL; - r = kvm_get_dirty_log_protect(kvm, log, &flush); + new_filter = kvm_alloc_msr_filter(default_allow); + if (!new_filter) + return -ENOMEM; + + for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) { + r = kvm_add_msr_filter(new_filter, &filter->ranges[i]); + if (r) { + kvm_free_msr_filter(new_filter); + return r; + } + } + + mutex_lock(&kvm->lock); + old_filter = rcu_replace_pointer(kvm->arch.msr_filter, new_filter, + mutex_is_locked(&kvm->lock)); + mutex_unlock(&kvm->lock); + synchronize_srcu(&kvm->srcu); + + kvm_free_msr_filter(old_filter); /* - * All the TLBs can be flushed out of mmu lock, see the comments in - * kvm_mmu_slot_remove_write_access(). + * Recalc MSR intercepts as userspace may want to intercept accesses to + * MSRs that KVM would otherwise pass through to the guest. */ - lockdep_assert_held(&kvm->slots_lock); - if (flush) - kvm_flush_remote_tlbs(kvm); + kvm_make_all_cpus_request(kvm, KVM_REQ_RECALC_INTERCEPTS); - mutex_unlock(&kvm->slots_lock); - return r; + return 0; } -int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, struct kvm_clear_dirty_log *log) +#ifdef CONFIG_KVM_COMPAT +/* for KVM_X86_SET_MSR_FILTER */ +struct kvm_msr_filter_range_compat { + __u32 flags; + __u32 nmsrs; + __u32 base; + __u32 bitmap; +}; + +struct kvm_msr_filter_compat { + __u32 flags; + struct kvm_msr_filter_range_compat ranges[KVM_MSR_FILTER_MAX_RANGES]; +}; + +#define KVM_X86_SET_MSR_FILTER_COMPAT _IOW(KVMIO, 0xc6, struct kvm_msr_filter_compat) + +long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) { - bool flush = false; - int r; + void __user *argp = (void __user *)arg; + struct kvm *kvm = filp->private_data; + long r = -ENOTTY; - mutex_lock(&kvm->slots_lock); + switch (ioctl) { + case KVM_X86_SET_MSR_FILTER_COMPAT: { + struct kvm_msr_filter __user *user_msr_filter = argp; + struct kvm_msr_filter_compat filter_compat; + struct kvm_msr_filter filter; + int i; + + if (copy_from_user(&filter_compat, user_msr_filter, + sizeof(filter_compat))) + return -EFAULT; + + filter.flags = filter_compat.flags; + for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { + struct kvm_msr_filter_range_compat *cr; + + cr = &filter_compat.ranges[i]; + filter.ranges[i] = (struct kvm_msr_filter_range) { + .flags = cr->flags, + .nmsrs = cr->nmsrs, + .base = cr->base, + .bitmap = (__u8 *)(ulong)cr->bitmap, + }; + } - /* - * Flush potentially hardware-cached dirty pages to dirty_bitmap. - */ - if (kvm_x86_ops->flush_log_dirty) - kvm_x86_ops->flush_log_dirty(kvm); + r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); + break; + } + } - r = kvm_clear_dirty_log_protect(kvm, log, &flush); + return r; +} +#endif + +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER +static int kvm_arch_suspend_notifier(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + unsigned long i; /* - * All the TLBs can be flushed out of mmu lock, see the comments in - * kvm_mmu_slot_remove_write_access(). + * Ignore the return, marking the guest paused only "fails" if the vCPU + * isn't using kvmclock; continuing on is correct and desirable. */ - lockdep_assert_held(&kvm->slots_lock); - if (flush) - kvm_flush_remote_tlbs(kvm); + kvm_for_each_vcpu(i, vcpu, kvm) + (void)kvm_set_guest_paused(vcpu); - mutex_unlock(&kvm->slots_lock); - return r; + return NOTIFY_DONE; } -int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, - bool line_status) +int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state) { - if (!irqchip_in_kernel(kvm)) - return -ENXIO; + switch (state) { + case PM_HIBERNATION_PREPARE: + case PM_SUSPEND_PREPARE: + return kvm_arch_suspend_notifier(kvm); + } + + return NOTIFY_DONE; +} +#endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ + +static int kvm_vm_ioctl_get_clock(struct kvm *kvm, void __user *argp) +{ + struct kvm_clock_data data = { 0 }; + + get_kvmclock(kvm, &data); + if (copy_to_user(argp, &data, sizeof(data))) + return -EFAULT; - 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) +static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) { - int r; + struct kvm_arch *ka = &kvm->arch; + struct kvm_clock_data data; + u64 now_raw_ns; - if (cap->flags) + if (copy_from_user(&data, argp, sizeof(data))) + return -EFAULT; + + /* + * Only KVM_CLOCK_REALTIME is used, but allow passing the + * result of KVM_GET_CLOCK back to KVM_SET_CLOCK. + */ + if (data.flags & ~KVM_CLOCK_VALID_FLAGS) return -EINVAL; - switch (cap->cap) { - case KVM_CAP_DISABLE_QUIRKS: - kvm->arch.disabled_quirks = cap->args[0]; - r = 0; - break; - case KVM_CAP_SPLIT_IRQCHIP: { - mutex_lock(&kvm->lock); - r = -EINVAL; - if (cap->args[0] > MAX_NR_RESERVED_IOAPIC_PINS) - goto split_irqchip_unlock; - r = -EEXIST; - if (irqchip_in_kernel(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; - kvm->arch.nr_reserved_ioapic_pins = cap->args[0]; - r = 0; -split_irqchip_unlock: - mutex_unlock(&kvm->lock); - break; + kvm_hv_request_tsc_page_update(kvm); + kvm_start_pvclock_update(kvm); + pvclock_update_vm_gtod_copy(kvm); + + /* + * This pairs with kvm_guest_time_update(): when masterclock is + * in use, we use master_kernel_ns + kvmclock_offset to set + * unsigned 'system_time' so if we use get_kvmclock_ns() (which + * is slightly ahead) here we risk going negative on unsigned + * 'system_time' when 'data.clock' is very small. + */ + if (data.flags & KVM_CLOCK_REALTIME) { + u64 now_real_ns = ktime_get_real_ns(); + + /* + * Avoid stepping the kvmclock backwards. + */ + if (now_real_ns > data.realtime) + data.clock += now_real_ns - data.realtime; } - case KVM_CAP_X2APIC_API: - r = -EINVAL; - if (cap->args[0] & ~KVM_X2APIC_API_VALID_FLAGS) - break; - if (cap->args[0] & KVM_X2APIC_API_USE_32BIT_IDS) - kvm->arch.x2apic_format = true; - if (cap->args[0] & KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) - kvm->arch.x2apic_broadcast_quirk_disabled = true; + if (ka->use_master_clock) + now_raw_ns = ka->master_kernel_ns; + else + now_raw_ns = get_kvmclock_base_ns(); + ka->kvmclock_offset = data.clock - now_raw_ns; + kvm_end_pvclock_update(kvm); + return 0; +} - r = 0; - break; - case KVM_CAP_X86_DISABLE_EXITS: - r = -EINVAL; - if (cap->args[0] & ~KVM_X86_DISABLE_VALID_EXITS) - break; +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 ((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_PAUSE) - kvm->arch.pause_in_guest = true; - r = 0; - break; - case KVM_CAP_MSR_PLATFORM_INFO: - kvm->arch.guest_can_read_msr_platform_info = cap->args[0]; - r = 0; - break; - case KVM_CAP_EXCEPTION_PAYLOAD: - kvm->arch.exception_payload_enabled = cap->args[0]; - r = 0; - break; - default: - r = -EINVAL; - break; - } - return r; + 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; } -long kvm_arch_vm_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) +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 { @@ -4583,6 +7230,7 @@ long kvm_arch_vm_ioctl(struct file *filp, struct kvm_pit_state2 ps2; struct kvm_pit_config pit_config; } u; +#endif switch (ioctl) { case KVM_SET_TSS_ADDR: @@ -4606,9 +7254,7 @@ set_identity_unlock: case KVM_SET_NR_MMU_PAGES: r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg); break; - case KVM_GET_NR_MMU_PAGES: - r = kvm_vm_ioctl_get_nr_mmu_pages(kvm); - break; +#ifdef CONFIG_KVM_IOAPIC case KVM_CREATE_IRQCHIP: { mutex_lock(&kvm->lock); @@ -4616,6 +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; @@ -4630,7 +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); @@ -4639,6 +7294,7 @@ set_identity_unlock: /* Write kvm->irq_routing before enabling irqchip_in_kernel. */ smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL; + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_ABSENT); create_irqchip_unlock: mutex_unlock(&kvm->lock); break; @@ -4656,6 +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) @@ -4674,7 +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) @@ -4698,12 +7357,9 @@ 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); - if (r) - goto set_irqchip_out; - r = 0; set_irqchip_out: kfree(chip); break; @@ -4728,10 +7384,13 @@ set_identity_unlock: r = -EFAULT; if (copy_from_user(&u.ps, argp, sizeof(u.ps))) goto out; + mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) - goto out; + goto set_pit_out; r = kvm_vm_ioctl_set_pit(kvm, &u.ps); +set_pit_out: + mutex_unlock(&kvm->lock); break; } case KVM_GET_PIT2: { @@ -4751,10 +7410,13 @@ set_identity_unlock: r = -EFAULT; if (copy_from_user(&u.ps2, argp, sizeof(u.ps2))) goto out; + mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) - goto out; + goto set_pit2_out; r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2); +set_pit2_out: + mutex_unlock(&kvm->lock); break; } case KVM_REINJECT_CONTROL: { @@ -4762,75 +7424,102 @@ set_identity_unlock: r = -EFAULT; if (copy_from_user(&control, argp, sizeof(control))) goto out; + r = -ENXIO; + if (!kvm->arch.vpit) + goto 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); break; +#ifdef CONFIG_KVM_XEN case KVM_XEN_HVM_CONFIG: { struct kvm_xen_hvm_config xhc; r = -EFAULT; if (copy_from_user(&xhc, argp, sizeof(xhc))) goto out; - r = -EINVAL; - if (xhc.flags) - goto out; - memcpy(&kvm->arch.xen_hvm_config, &xhc, sizeof(xhc)); - r = 0; + r = kvm_xen_hvm_config(kvm, &xhc); break; } - case KVM_SET_CLOCK: { - struct kvm_clock_data user_ns; - u64 now_ns; + case KVM_XEN_HVM_GET_ATTR: { + struct kvm_xen_hvm_attr xha; r = -EFAULT; - if (copy_from_user(&user_ns, argp, sizeof(user_ns))) + if (copy_from_user(&xha, argp, sizeof(xha))) goto out; + r = kvm_xen_hvm_get_attr(kvm, &xha); + if (!r && copy_to_user(argp, &xha, sizeof(xha))) + r = -EFAULT; + break; + } + case KVM_XEN_HVM_SET_ATTR: { + struct kvm_xen_hvm_attr xha; - r = -EINVAL; - if (user_ns.flags) + r = -EFAULT; + if (copy_from_user(&xha, argp, sizeof(xha))) goto out; - - r = 0; - /* - * TODO: userspace has to take care of races with VCPU_RUN, so - * kvm_gen_update_masterclock() can be cut down to locked - * pvclock_update_vm_gtod_copy(). - */ - kvm_gen_update_masterclock(kvm); - now_ns = get_kvmclock_ns(kvm); - kvm->arch.kvmclock_offset += user_ns.clock - now_ns; - kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); + r = kvm_xen_hvm_set_attr(kvm, &xha); break; } - case KVM_GET_CLOCK: { - struct kvm_clock_data user_ns; - u64 now_ns; - - now_ns = get_kvmclock_ns(kvm); - user_ns.clock = now_ns; - user_ns.flags = kvm->arch.use_master_clock ? KVM_CLOCK_TSC_STABLE : 0; - memset(&user_ns.pad, 0, sizeof(user_ns.pad)); + case KVM_XEN_HVM_EVTCHN_SEND: { + struct kvm_irq_routing_xen_evtchn uxe; r = -EFAULT; - if (copy_to_user(argp, &user_ns, sizeof(user_ns))) + if (copy_from_user(&uxe, argp, sizeof(uxe))) goto out; - r = 0; + r = kvm_xen_hvm_evtchn_send(kvm, &uxe); break; } - case KVM_MEMORY_ENCRYPT_OP: { - r = -ENOTTY; - if (kvm_x86_ops->mem_enc_op) - r = kvm_x86_ops->mem_enc_op(kvm, argp); +#endif + case KVM_SET_CLOCK: + r = kvm_vm_ioctl_set_clock(kvm, argp); + break; + case KVM_GET_CLOCK: + r = kvm_vm_ioctl_get_clock(kvm, argp); break; + case KVM_SET_TSC_KHZ: { + u32 user_tsc_khz; + + r = -EINVAL; + user_tsc_khz = (u32)arg; + + if (kvm_caps.has_tsc_control && + user_tsc_khz >= kvm_caps.max_guest_tsc_khz) + goto out; + + if (user_tsc_khz == 0) + user_tsc_khz = tsc_khz; + + 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: + r = -ENOTTY; + if (!kvm_x86_ops.mem_enc_ioctl) + goto out; + + r = kvm_x86_call(mem_enc_ioctl)(kvm, argp); + break; case KVM_MEMORY_ENCRYPT_REG_REGION: { struct kvm_enc_region region; @@ -4839,8 +7528,10 @@ set_identity_unlock: goto out; r = -ENOTTY; - if (kvm_x86_ops->mem_enc_reg_region) - r = kvm_x86_ops->mem_enc_reg_region(kvm, ®ion); + if (!kvm_x86_ops.mem_enc_register_region) + goto out; + + r = kvm_x86_call(mem_enc_register_region)(kvm, ®ion); break; } case KVM_MEMORY_ENCRYPT_UNREG_REGION: { @@ -4851,10 +7542,13 @@ set_identity_unlock: goto out; r = -ENOTTY; - if (kvm_x86_ops->mem_enc_unreg_region) - r = kvm_x86_ops->mem_enc_unreg_region(kvm, ®ion); + if (!kvm_x86_ops.mem_enc_unregister_region) + goto out; + + r = kvm_x86_call(mem_enc_unregister_region)(kvm, ®ion); break; } +#ifdef CONFIG_KVM_HYPERV case KVM_HYPERV_EVENTFD: { struct kvm_hyperv_eventfd hvevfd; @@ -4864,6 +7558,20 @@ set_identity_unlock: 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; + case KVM_X86_SET_MSR_FILTER: { + struct kvm_msr_filter __user *user_msr_filter = argp; + struct kvm_msr_filter filter; + + if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) + return -EFAULT; + + r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); + break; + } default: r = -ENOTTY; } @@ -4871,84 +7579,155 @@ out: return r; } -static void kvm_init_msr_list(void) +static void kvm_probe_feature_msr(u32 msr_index) { - u32 dummy[2]; - unsigned i, j; + u64 data; - for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { - if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) - continue; + if (kvm_get_feature_msr(NULL, msr_index, &data, true)) + return; - /* - * Even MSRs that are valid in the host may not be exposed - * to the guests in some cases. - */ - switch (msrs_to_save[i]) { - case MSR_IA32_BNDCFGS: - if (!kvm_mpx_supported()) - continue; - break; - case MSR_TSC_AUX: - if (!kvm_x86_ops->rdtscp_supported()) - continue; - break; - case MSR_IA32_RTIT_CTL: - case MSR_IA32_RTIT_STATUS: - if (!kvm_x86_ops->pt_supported()) - continue; - break; - case MSR_IA32_RTIT_CR3_MATCH: - if (!kvm_x86_ops->pt_supported() || - !intel_pt_validate_hw_cap(PT_CAP_cr3_filtering)) - continue; - break; - case MSR_IA32_RTIT_OUTPUT_BASE: - case MSR_IA32_RTIT_OUTPUT_MASK: - if (!kvm_x86_ops->pt_supported() || - (!intel_pt_validate_hw_cap(PT_CAP_topa_output) && - !intel_pt_validate_hw_cap(PT_CAP_single_range_output))) - continue; - break; - case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: { - if (!kvm_x86_ops->pt_supported() || - msrs_to_save[i] - MSR_IA32_RTIT_ADDR0_A >= - intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) - continue; - break; - } - default: - break; - } + msr_based_features[num_msr_based_features++] = msr_index; +} - if (j < i) - msrs_to_save[j] = msrs_to_save[i]; - j++; - } - num_msrs_to_save = j; +static void kvm_probe_msr_to_save(u32 msr_index) +{ + u32 dummy[2]; - for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) { - if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i])) - continue; + if (rdmsr_safe(msr_index, &dummy[0], &dummy[1])) + return; - if (j < i) - emulated_msrs[j] = emulated_msrs[i]; - j++; + /* + * Even MSRs that are valid in the host may not be exposed to guests in + * some cases. + */ + switch (msr_index) { + case MSR_IA32_BNDCFGS: + if (!kvm_mpx_supported()) + return; + break; + case MSR_TSC_AUX: + if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP) && + !kvm_cpu_cap_has(X86_FEATURE_RDPID)) + return; + break; + case MSR_IA32_UMWAIT_CONTROL: + if (!kvm_cpu_cap_has(X86_FEATURE_WAITPKG)) + return; + break; + case MSR_IA32_RTIT_CTL: + case MSR_IA32_RTIT_STATUS: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) + return; + break; + case MSR_IA32_RTIT_CR3_MATCH: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || + !intel_pt_validate_hw_cap(PT_CAP_cr3_filtering)) + return; + break; + case MSR_IA32_RTIT_OUTPUT_BASE: + case MSR_IA32_RTIT_OUTPUT_MASK: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || + (!intel_pt_validate_hw_cap(PT_CAP_topa_output) && + !intel_pt_validate_hw_cap(PT_CAP_single_range_output))) + return; + break; + case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || + (msr_index - MSR_IA32_RTIT_ADDR0_A >= + intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)) + return; + break; + 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_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_CTR0 + KVM_MAX_NR_FIXED_COUNTERS - 1: + if (msr_index - MSR_ARCH_PERFMON_FIXED_CTR0 >= + kvm_pmu_cap.num_counters_fixed) + return; + break; + 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; + case MSR_IA32_XFD: + case MSR_IA32_XFD_ERR: + if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) + return; + break; + case MSR_IA32_TSX_CTRL: + 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; } - num_emulated_msrs = j; - for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) { - struct kvm_msr_entry msr; + msrs_to_save[num_msrs_to_save++] = msr_index; +} - msr.index = msr_based_features[i]; - if (kvm_get_msr_feature(&msr)) +static void kvm_init_msr_lists(void) +{ + unsigned i; + + 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; + num_emulated_msrs = 0; + num_msr_based_features = 0; + + for (i = 0; i < ARRAY_SIZE(msrs_to_save_base); i++) + kvm_probe_msr_to_save(msrs_to_save_base[i]); + + if (enable_pmu) { + for (i = 0; i < ARRAY_SIZE(msrs_to_save_pmu); i++) + kvm_probe_msr_to_save(msrs_to_save_pmu[i]); + } + + for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { + if (!kvm_x86_call(has_emulated_msr)(NULL, + emulated_msrs_all[i])) continue; - if (j < i) - msr_based_features[j] = msr_based_features[i]; - j++; + emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; } - num_msr_based_features = j; + + for (i = KVM_FIRST_EMULATED_VMX_MSR; i <= KVM_LAST_EMULATED_VMX_MSR; i++) + kvm_probe_feature_msr(i); + + for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) + kvm_probe_feature_msr(msr_based_features_all_except_vmx[i]); } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, @@ -4994,28 +7773,29 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) return handled; } -static void kvm_set_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) +void kvm_set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) { - kvm_x86_ops->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) { - kvm_x86_ops->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, u32 access, +gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u64 access, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.mmu; gpa_t t_gpa; BUG_ON(!mmu_is_nested(vcpu)); /* NPT walks are always user-walks */ access |= PFERR_USER_MASK; - t_gpa = vcpu->arch.mmu->gva_to_gpa(vcpu, gpa, access, exception); + t_gpa = mmu->gva_to_gpa(vcpu, mmu, gpa, access, exception); return t_gpa; } @@ -5023,48 +7803,48 @@ gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); -} + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, - struct x86_exception *exception) -{ - u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; - access |= PFERR_FETCH_MASK; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + 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_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) { - u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + + u64 access = (kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_WRITE_MASK; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } +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, struct x86_exception *exception) { - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, 0, exception); + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + + return mmu->gva_to_gpa(vcpu, mmu, gva, 0, exception); } static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, - struct kvm_vcpu *vcpu, u32 access, + struct kvm_vcpu *vcpu, u64 access, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { - gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access, - exception); + gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception); unsigned offset = addr & (PAGE_SIZE-1); unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; - if (gpa == UNMAPPED_GVA) + if (gpa == INVALID_GPA) return X86EMUL_PROPAGATE_FAULT; ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, data, offset, toread); @@ -5087,14 +7867,15 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, struct x86_exception *exception) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + u64 access = (kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; unsigned offset; int ret; /* Inline kvm_read_guest_virt_helper for speed. */ - gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access|PFERR_FETCH_MASK, - exception); - if (unlikely(gpa == UNMAPPED_GVA)) + gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access|PFERR_FETCH_MASK, + exception); + if (unlikely(gpa == INVALID_GPA)) return X86EMUL_PROPAGATE_FAULT; offset = addr & (PAGE_SIZE-1); @@ -5112,51 +7893,50 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { - u32 access = (kvm_x86_ops->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 + * is returned, but our callers are not ready for that and they blindly + * call kvm_inject_page_fault. Ensure that they at least do not leak + * uninitialized kernel stack memory into cr2 and error code. + */ + memset(exception, 0, sizeof(*exception)); 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, struct x86_exception *exception, bool system) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - u32 access = 0; + u64 access = 0; - if (!system && kvm_x86_ops->get_cpl(vcpu) == 3) + if (system) + access |= PFERR_IMPLICIT_ACCESS; + 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); } -static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt, - unsigned long addr, void *val, unsigned int bytes) -{ - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - int r = kvm_vcpu_read_guest(vcpu, addr, val, bytes); - - return r < 0 ? X86EMUL_IO_NEEDED : X86EMUL_CONTINUE; -} - static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, - struct kvm_vcpu *vcpu, u32 access, + struct kvm_vcpu *vcpu, u64 access, struct x86_exception *exception) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { - gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, - access, - exception); + gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception); unsigned offset = addr & (PAGE_SIZE-1); unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; - if (gpa == UNMAPPED_GVA) + if (gpa == INVALID_GPA) return X86EMUL_PROPAGATE_FAULT; ret = kvm_vcpu_write_guest(vcpu, gpa, data, towrite); if (ret < 0) { @@ -5177,9 +7957,11 @@ static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *v bool system) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - u32 access = PFERR_WRITE_MASK; + u64 access = PFERR_WRITE_MASK; - if (!system && kvm_x86_ops->get_cpl(vcpu) == 3) + if (system) + access |= PFERR_IMPLICIT_ACCESS; + else if (kvm_x86_call(get_cpl)(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, @@ -5190,36 +7972,46 @@ 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_check_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) +{ + return kvm_x86_call(check_emulate_instruction)(vcpu, emul_type, + insn, insn_len); +} int handle_ud(struct kvm_vcpu *vcpu) { + static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX }; + int fep_flags = READ_ONCE(force_emulation_prefix); int emul_type = EMULTYPE_TRAP_UD; - enum emulation_result er; char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; + int r; - if (force_emulation_prefix && + r = kvm_check_emulate_insn(vcpu, emul_type, NULL, 0); + if (r != X86EMUL_CONTINUE) + return 1; + + if (fep_flags && kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu), sig, sizeof(sig), &e) == 0 && - memcmp(sig, "\xf\xbkvm", sizeof(sig)) == 0) { + memcmp(sig, kvm_emulate_prefix, sizeof(sig)) == 0) { + if (fep_flags & KVM_FEP_CLEAR_RFLAGS_RF) + kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) & ~X86_EFLAGS_RF); kvm_rip_write(vcpu, kvm_rip_read(vcpu) + sizeof(sig)); - emul_type = 0; + emul_type = EMULTYPE_TRAP_UD_FORCED; } - er = kvm_emulate_instruction(vcpu, emul_type); - if (er == EMULATE_USER_EXIT) - return 0; - if (er != EMULATE_DONE) - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; + 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) @@ -5240,26 +8032,27 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t *gpa, struct x86_exception *exception, bool write) { - u32 access = ((kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0) - | (write ? PFERR_WRITE_MASK : 0); + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + 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 * there is no pkey in EPT page table for L1 guest or EPT * shadow page table for L2 guest. */ - if (vcpu_match_mmio_gva(vcpu, gva) - && !permission_fault(vcpu, vcpu->arch.walk_mmu, - vcpu->arch.access, 0, access)) { + if (vcpu_match_mmio_gva(vcpu, gva) && (!is_paging(vcpu) || + !permission_fault(vcpu, vcpu->arch.walk_mmu, + vcpu->arch.mmio_access, 0, access))) { *gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT | (gva & (PAGE_SIZE - 1)); trace_vcpu_match_mmio(gva, *gpa, write, false); return 1; } - *gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + *gpa = mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); - if (*gpa == UNMAPPED_GVA) + if (*gpa == INVALID_GPA) return -1; return vcpu_is_mmio_gpa(vcpu, gva, *gpa, write); @@ -5359,7 +8152,7 @@ static int emulator_read_write_onepage(unsigned long addr, void *val, int handled, ret; bool write = ops->write; struct kvm_mmio_fragment *frag; - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; /* * If the exit was due to a NPF we may already have a GPA. @@ -5368,10 +8161,9 @@ static int emulator_read_write_onepage(unsigned long addr, void *val, * operation using rep will only have the initial GPA from the NPF * occurred. */ - if (vcpu->arch.gpa_available && - emulator_can_use_gpa(ctxt) && - (addr & ~PAGE_MASK) == (vcpu->arch.gpa_val & ~PAGE_MASK)) { - gpa = vcpu->arch.gpa_val; + if (ctxt->gpa_available && emulator_can_use_gpa(ctxt) && + (addr & ~PAGE_MASK) == (ctxt->gpa_val & ~PAGE_MASK)) { + gpa = ctxt->gpa_val; ret = vcpu_is_mmio_gpa(vcpu, addr, gpa, write); } else { ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write); @@ -5440,7 +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; @@ -5475,15 +8267,8 @@ static int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, exception, &write_emultor); } -#define CMPXCHG_TYPE(t, ptr, old, new) \ - (cmpxchg((t *)(ptr), *(t *)(old), *(t *)(new)) == *(t *)(old)) - -#ifdef CONFIG_X86_64 -# define CMPXCHG64(ptr, old, new) CMPXCHG_TYPE(u64, ptr, old, new) -#else -# define CMPXCHG64(ptr, old, new) \ - (cmpxchg64((u64 *)(ptr), *(u64 *)(old), *(u64 *)(new)) == *(u64 *)(old)) -#endif +#define emulator_try_cmpxchg_user(t, ptr, old, new) \ + (__try_cmpxchg_user((t __user *)(ptr), (t *)(old), *(t *)(new), efault ## t)) static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, unsigned long addr, @@ -5493,10 +8278,10 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, struct x86_exception *exception) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + u64 page_line_mask; + unsigned long hva; gpa_t gpa; - struct page *page; - char *kaddr; - bool exchanged; + int r; /* guests cmpxchg8b have to be emulated atomically */ if (bytes > 8 || (bytes & (bytes - 1))) @@ -5504,84 +8289,111 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL); - if (gpa == UNMAPPED_GVA || + if (gpa == INVALID_GPA || (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) goto emul_write; - if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK)) + /* + * Emulate the atomic as a straight write to avoid #AC if SLD is + * enabled in the host and the access splits a cache line. + */ + if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) + page_line_mask = ~(cache_line_size() - 1); + else + page_line_mask = PAGE_MASK; + + if (((gpa + bytes - 1) & page_line_mask) != (gpa & page_line_mask)) goto emul_write; - page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT); - if (is_error_page(page)) + hva = kvm_vcpu_gfn_to_hva(vcpu, gpa_to_gfn(gpa)); + if (kvm_is_error_hva(hva)) goto emul_write; - kaddr = kmap_atomic(page); - kaddr += offset_in_page(gpa); + hva += offset_in_page(gpa); + switch (bytes) { case 1: - exchanged = CMPXCHG_TYPE(u8, kaddr, old, new); + r = emulator_try_cmpxchg_user(u8, hva, old, new); break; case 2: - exchanged = CMPXCHG_TYPE(u16, kaddr, old, new); + r = emulator_try_cmpxchg_user(u16, hva, old, new); break; case 4: - exchanged = CMPXCHG_TYPE(u32, kaddr, old, new); + r = emulator_try_cmpxchg_user(u32, hva, old, new); break; case 8: - exchanged = CMPXCHG64(kaddr, old, new); + r = emulator_try_cmpxchg_user(u64, hva, old, new); break; default: BUG(); } - kunmap_atomic(kaddr); - kvm_release_page_dirty(page); - if (!exchanged) + 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; - kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); kvm_page_track_write(vcpu, gpa, new, bytes); return X86EMUL_CONTINUE; emul_write: - printk_once(KERN_WARNING "kvm: emulating exchange as write\n"); + pr_warn_once("emulating exchange as write\n"); return emulator_write_emulated(ctxt, addr, new, bytes, exception); } -static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) +static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, + unsigned short port, void *data, + unsigned int count, bool in) { - int r = 0, i; + unsigned i; + int r; - for (i = 0; i < vcpu->arch.pio.count; i++) { - if (vcpu->arch.pio.in) - r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, - vcpu->arch.pio.size, pd); + WARN_ON_ONCE(vcpu->arch.pio.count); + for (i = 0; i < count; i++) { + if (in) + r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, port, size, data); else - r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, - vcpu->arch.pio.port, vcpu->arch.pio.size, - pd); - if (r) + r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, port, size, data); + + if (r) { + if (i == 0) + goto userspace_io; + + /* + * Userspace must have unregistered the device while PIO + * was running. Drop writes / read as 0. + */ + if (in) + memset(data, 0, size * (count - i)); break; - pd += vcpu->arch.pio.size; + } + + data += size; } - return r; -} + return 1; -static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, - unsigned short port, void *val, - unsigned int count, bool in) -{ +userspace_io: vcpu->arch.pio.port = port; vcpu->arch.pio.in = in; - vcpu->arch.pio.count = count; + vcpu->arch.pio.count = count; vcpu->arch.pio.size = size; - if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { - vcpu->arch.pio.count = 0; - return 1; - } + if (in) + memset(vcpu->arch.pio_data, 0, size * count); + else + memcpy(vcpu->arch.pio_data, data, size * count); vcpu->run->exit_reason = KVM_EXIT_IO; vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; @@ -5589,48 +8401,66 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; vcpu->run->io.count = count; vcpu->run->io.port = port; - return 0; } +static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, + unsigned short port, void *val, unsigned int count) +{ + int r = emulator_pio_in_out(vcpu, size, port, val, count, true); + if (r) + trace_kvm_pio(KVM_PIO_IN, port, size, count, val); + + return r; +} + +static void complete_emulator_pio_in(struct kvm_vcpu *vcpu, void *val) +{ + int size = vcpu->arch.pio.size; + unsigned int count = vcpu->arch.pio.count; + memcpy(val, vcpu->arch.pio_data, size * count); + trace_kvm_pio(KVM_PIO_IN, vcpu->arch.pio.port, size, count, vcpu->arch.pio_data); + vcpu->arch.pio.count = 0; +} + static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, int size, unsigned short port, void *val, unsigned int count) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - int ret; - - if (vcpu->arch.pio.count) - goto data_avail; - - memset(vcpu->arch.pio_data, 0, size * count); - - ret = emulator_pio_in_out(vcpu, size, port, val, count, true); - if (ret) { -data_avail: - memcpy(val, vcpu->arch.pio_data, size * count); - trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data); - vcpu->arch.pio.count = 0; + if (vcpu->arch.pio.count) { + /* + * Complete a previous iteration that required userspace I/O. + * Note, @count isn't guaranteed to match pio.count as userspace + * can modify ECX before rerunning the vCPU. Ignore any such + * shenanigans as KVM doesn't support modifying the rep count, + * and the emulator ensures @count doesn't overflow the buffer. + */ + complete_emulator_pio_in(vcpu, val); return 1; } - return 0; + return emulator_pio_in(vcpu, size, port, val, count); +} + +static int emulator_pio_out(struct kvm_vcpu *vcpu, int size, + unsigned short port, const void *val, + unsigned int count) +{ + trace_kvm_pio(KVM_PIO_OUT, port, size, count, val); + return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); } static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, int size, unsigned short port, const void *val, unsigned int count) { - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - - memcpy(vcpu->arch.pio_data, val, size * count); - trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data); - return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); + return emulator_pio_out(emul_to_vcpu(ctxt), size, port, val, count); } static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) { - return kvm_x86_ops->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) @@ -5643,12 +8473,11 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) if (!need_emulate_wbinvd(vcpu)) return X86EMUL_CONTINUE; - if (kvm_x86_ops->has_wbinvd_exit()) { + if (kvm_x86_call(has_wbinvd_exit)()) { int cpu = get_cpu(); cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); - smp_call_function_many(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 @@ -5661,7 +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); @@ -5670,17 +8499,16 @@ static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt) kvm_emulate_wbinvd_noskip(emul_to_vcpu(ctxt)); } -static int 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) { - return 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, unsigned long value) { - return __kvm_set_dr(emul_to_vcpu(ctxt), dr, value); + return kvm_set_dr(emul_to_vcpu(ctxt), dr, value); } static u64 mk_cr_64(u64 curr_cr, u32 new_val) @@ -5748,27 +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 kvm_x86_ops->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) { - kvm_x86_ops->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) { - kvm_x86_ops->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) { - kvm_x86_ops->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) { - kvm_x86_ops->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( @@ -5843,51 +8671,70 @@ static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector, return; } -static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, - u32 msr_index, u64 *pdata) +static int emulator_get_msr_with_filter(struct x86_emulate_ctxt *ctxt, + u32 msr_index, u64 *pdata) { - struct msr_data msr; + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int r; - msr.index = msr_index; - msr.host_initiated = false; - r = kvm_get_msr(emul_to_vcpu(ctxt), &msr); - if (r) - return r; + r = kvm_emulate_msr_read(vcpu, msr_index, pdata); + if (r < 0) + return X86EMUL_UNHANDLEABLE; - *pdata = msr.data; - return 0; -} + if (r) { + if (kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0, + complete_emulated_rdmsr, r)) + return X86EMUL_IO_NEEDED; -static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, - u32 msr_index, u64 data) -{ - struct msr_data msr; + trace_kvm_msr_read_ex(msr_index); + return X86EMUL_PROPAGATE_FAULT; + } - msr.data = data; - msr.index = msr_index; - msr.host_initiated = false; - return kvm_set_msr(emul_to_vcpu(ctxt), &msr); + trace_kvm_msr_read(msr_index, *pdata); + return X86EMUL_CONTINUE; } -static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt) +static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt, + u32 msr_index, u64 data) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + int r; + + r = kvm_emulate_msr_write(vcpu, msr_index, data); + if (r < 0) + return X86EMUL_UNHANDLEABLE; + + if (r) { + if (kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data, + complete_emulated_msr_access, r)) + return X86EMUL_IO_NEEDED; + + trace_kvm_msr_write_ex(msr_index, data); + return X86EMUL_PROPAGATE_FAULT; + } - return vcpu->arch.smbase; + trace_kvm_msr_write(msr_index, data); + return X86EMUL_CONTINUE; } -static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase) +static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, + u32 msr_index, u64 *pdata) { - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + /* + * 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); - vcpu->arch.smbase = smbase; + 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) { - return kvm_pmu_is_valid_msr_idx(emul_to_vcpu(ctxt), pmc); + return kvm_pmu_check_rdpmc_early(emul_to_vcpu(ctxt), pmc); } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, @@ -5905,51 +8752,113 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt, struct x86_instruction_info *info, enum x86_intercept_stage stage) { - return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage); + return kvm_x86_call(check_intercept)(emul_to_vcpu(ctxt), info, stage, + &ctxt->exception); } static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, - u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool check_limit) + u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, + bool exact_only) { - return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, check_limit); + return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, exact_only); +} + +static bool emulator_guest_has_movbe(struct x86_emulate_ctxt *ctxt) +{ + 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_cpu_cap_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR); +} + +static bool emulator_guest_has_rdpid(struct x86_emulate_ctxt *ctxt) +{ + 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) { - return kvm_register_read(emul_to_vcpu(ctxt), reg); + return kvm_register_read_raw(emul_to_vcpu(ctxt), reg); } static void emulator_write_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg, ulong val) { - kvm_register_write(emul_to_vcpu(ctxt), reg, val); + kvm_register_write_raw(emul_to_vcpu(ctxt), reg, val); } static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked) { - kvm_x86_ops->set_nmi_mask(emul_to_vcpu(ctxt), masked); + kvm_x86_call(set_nmi_mask)(emul_to_vcpu(ctxt), masked); } -static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) +static bool emulator_is_smm(struct x86_emulate_ctxt *ctxt) { - return emul_to_vcpu(ctxt)->arch.hflags; + return is_smm(emul_to_vcpu(ctxt)); } -static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags) +#ifndef CONFIG_KVM_SMM +static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) { - kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags); + WARN_ON_ONCE(1); + return X86EMUL_UNHANDLEABLE; } +#endif -static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, u64 smbase) +static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt) { - return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smbase); + 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); +} + +static void emulator_vm_bugged(struct x86_emulate_ctxt *ctxt) +{ + struct kvm *kvm = emul_to_vcpu(ctxt)->kvm; + + if (!kvm->vm_bugged) + 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, .write_gpr = emulator_write_gpr, .read_std = emulator_read_std, .write_std = emulator_write_std, - .read_phys = kvm_read_guest_phys_system, .fetch = kvm_fetch_guest_virt, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, @@ -5969,26 +8878,33 @@ static const struct x86_emulate_ops emulate_ops = { .cpl = emulator_get_cpl, .get_dr = emulator_get_dr, .set_dr = emulator_set_dr, - .get_smbase = emulator_get_smbase, - .set_smbase = emulator_set_smbase, - .set_msr = emulator_set_msr, + .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_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, - .get_hflags = emulator_get_hflags, - .set_hflags = emulator_set_hflags, - .pre_leave_smm = emulator_pre_leave_smm, + .is_smm = emulator_is_smm, + .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 = kvm_x86_ops->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 @@ -5999,33 +8915,50 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) if (int_shadow & mask) mask = 0; if (unlikely(int_shadow || mask)) { - kvm_x86_ops->set_interrupt_shadow(vcpu, mask); + kvm_x86_call(set_interrupt_shadow)(vcpu, mask); if (!mask) kvm_make_request(KVM_REQ_EVENT, vcpu); } } -static bool inject_emulated_exception(struct kvm_vcpu *vcpu) +static void inject_emulated_exception(struct kvm_vcpu *vcpu) { - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; - if (ctxt->exception.vector == PF_VECTOR) - return kvm_propagate_fault(vcpu, &ctxt->exception); + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; - if (ctxt->exception.error_code_valid) + if (ctxt->exception.vector == PF_VECTOR) + kvm_inject_emulated_page_fault(vcpu, &ctxt->exception); + else if (ctxt->exception.error_code_valid) kvm_queue_exception_e(vcpu, ctxt->exception.vector, ctxt->exception.error_code); else kvm_queue_exception(vcpu, ctxt->exception.vector); - return false; +} + +static struct x86_emulate_ctxt *alloc_emulate_ctxt(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt; + + ctxt = kmem_cache_zalloc(x86_emulator_cache, GFP_KERNEL_ACCOUNT); + if (!ctxt) { + pr_err("failed to allocate vcpu's emulator\n"); + return NULL; + } + + ctxt->vcpu = vcpu; + ctxt->ops = &emulate_ops; + vcpu->arch.emulate_ctxt = ctxt; + + return ctxt; } static void init_emulate_ctxt(struct kvm_vcpu *vcpu) { - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int cs_db, cs_l; - kvm_x86_ops->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); ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0; @@ -6035,17 +8968,18 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) (cs_l && is_long_mode(vcpu)) ? X86EMUL_MODE_PROT64 : cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK); - BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); - BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK); + ctxt->interruptibility = 0; + ctxt->have_exception = false; + ctxt->exception.vector = -1; + ctxt->perm_ok = false; init_decode_cache(ctxt); vcpu->arch.emulate_regs_need_sync_from_vcpu = false; } -int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) +void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) { - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int ret; init_emulate_ctxt(vcpu); @@ -6055,186 +8989,190 @@ int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) ctxt->_eip = ctxt->eip + inc_eip; ret = emulate_int_real(ctxt, irq); - if (ret != X86EMUL_CONTINUE) - return EMULATE_FAIL; - - ctxt->eip = ctxt->_eip; - kvm_rip_write(vcpu, ctxt->eip); - kvm_set_rflags(vcpu, ctxt->eflags); - - return EMULATE_DONE; -} -EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt); - -static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) -{ - int r = EMULATE_DONE; - - ++vcpu->stat.insn_emulation_fail; - trace_kvm_emulate_insn_failed(vcpu); - - if (emulation_type & EMULTYPE_NO_UD_ON_FAIL) - return EMULATE_FAIL; - - if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; - r = EMULATE_USER_EXIT; + if (ret != X86EMUL_CONTINUE) { + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + } else { + ctxt->eip = ctxt->_eip; + kvm_rip_write(vcpu, ctxt->eip); + kvm_set_rflags(vcpu, ctxt->eflags); } - - kvm_queue_exception(vcpu, UD_VECTOR); - - return r; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_inject_realmode_interrupt); -static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, - bool write_fault_to_shadow_pgtable, - int emulation_type) +static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, + u8 ndata, u8 *insn_bytes, u8 insn_size) { - gpa_t gpa = cr2; - kvm_pfn_t pfn; - - if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) - return false; - - if (WARN_ON_ONCE(is_guest_mode(vcpu))) - return false; - - if (!vcpu->arch.mmu->direct_map) { - /* - * Write permission should be allowed since only - * write access need to be emulated. - */ - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); - - /* - * If the mapping is invalid in guest, let cpu retry - * it to generate fault. - */ - if (gpa == UNMAPPED_GVA) - return true; - } + struct kvm_run *run = vcpu->run; + u64 info[5]; + u8 info_start; /* - * 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 -> ... + * Zero the whole array used to retrieve the exit info, as casting to + * u32 for select entries will leave some chunks uninitialized. */ - pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa)); + memset(&info, 0, sizeof(info)); + + 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; /* - * If the instruction failed on the error pfn, it can not be fixed, - * report the error to userspace. + * There's currently space for 13 entries, but 5 are used for the exit + * reason and info. Restrict to 4 to reduce the maintenance burden + * when expanding kvm_run.emulation_failure in the future. */ - if (is_error_noslot_pfn(pfn)) - return false; + if (WARN_ON_ONCE(ndata > 4)) + ndata = 4; - kvm_release_pfn_clean(pfn); + /* Always include the flags as a 'data' entry. */ + info_start = 1; + run->emulation_failure.flags = 0; - /* The instructions are well-emulated on direct mmu. */ - if (vcpu->arch.mmu->direct_map) { - unsigned int indirect_shadow_pages; - - spin_lock(&vcpu->kvm->mmu_lock); - indirect_shadow_pages = vcpu->kvm->arch.indirect_shadow_pages; - spin_unlock(&vcpu->kvm->mmu_lock); + if (insn_size) { + BUILD_BUG_ON((sizeof(run->emulation_failure.insn_size) + + sizeof(run->emulation_failure.insn_bytes) != 16)); + info_start += 2; + run->emulation_failure.flags |= + KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES; + run->emulation_failure.insn_size = insn_size; + memset(run->emulation_failure.insn_bytes, 0x90, + sizeof(run->emulation_failure.insn_bytes)); + memcpy(run->emulation_failure.insn_bytes, insn_bytes, insn_size); + } - if (indirect_shadow_pages) - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + memcpy(&run->internal.data[info_start], info, sizeof(info)); + memcpy(&run->internal.data[info_start + ARRAY_SIZE(info)], data, + ndata * sizeof(data[0])); - return true; - } + run->emulation_failure.ndata = info_start + ARRAY_SIZE(info) + ndata; +} - /* - * 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. - */ - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); +static void prepare_emulation_ctxt_failure_exit(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; - /* - * If the access faults on its page table, it can not - * be fixed by unprotecting shadow page and it should - * be reported to userspace. - */ - return !write_fault_to_shadow_pgtable; + prepare_emulation_failure_exit(vcpu, NULL, 0, ctxt->fetch.data, + ctxt->fetch.end - ctxt->fetch.data); } -static bool retry_instruction(struct x86_emulate_ctxt *ctxt, - unsigned long cr2, int emulation_type) +void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, + u8 ndata) { - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - unsigned long last_retry_eip, last_retry_addr, gpa = cr2; + prepare_emulation_failure_exit(vcpu, data, ndata, NULL, 0); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_prepare_emulation_failure_exit); - last_retry_eip = vcpu->arch.last_retry_eip; - last_retry_addr = vcpu->arch.last_retry_addr; +void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu) +{ + __kvm_prepare_emulation_failure_exit(vcpu, NULL, 0); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_prepare_emulation_failure_exit); - /* - * 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; +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; - if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) - return false; + kvm_x86_call(get_exit_info)(vcpu, &reason, &info1, &info2, + &intr_info, &error_code); - if (WARN_ON_ONCE(is_guest_mode(vcpu))) - return false; + 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; - if (x86_page_table_writing_insn(ctxt)) - return false; + 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); - if (ctxt->eip == last_retry_eip && last_retry_addr == cr2) - return false; +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->arch.last_retry_eip = ctxt->eip; - vcpu->arch.last_retry_addr = cr2; + 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); - if (!vcpu->arch.mmu->direct_map) - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); +static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) +{ + struct kvm *kvm = vcpu->kvm; - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + ++vcpu->stat.insn_emulation_fail; + trace_kvm_emulate_insn_failed(vcpu); - return true; -} + if (emulation_type & EMULTYPE_VMWARE_GP) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } -static int complete_emulated_mmio(struct kvm_vcpu *vcpu); -static int complete_emulated_pio(struct kvm_vcpu *vcpu); + if (kvm->arch.exit_on_emulation_error || + (emulation_type & EMULTYPE_SKIP)) { + prepare_emulation_ctxt_failure_exit(vcpu); + return 0; + } -static void kvm_smm_changed(struct kvm_vcpu *vcpu) -{ - if (!(vcpu->arch.hflags & HF_SMM_MASK)) { - /* This is a good place to trace that we are exiting SMM. */ - trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, false); + kvm_queue_exception(vcpu, UD_VECTOR); - /* Process a latched INIT or SMI, if any. */ - kvm_make_request(KVM_REQ_EVENT, vcpu); + if (!is_guest_mode(vcpu) && kvm_x86_call(get_cpl)(vcpu) == 0) { + prepare_emulation_ctxt_failure_exit(vcpu); + return 0; } - kvm_mmu_reset_context(vcpu); + return 1; } -static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags) +static bool kvm_unprotect_and_retry_on_failure(struct kvm_vcpu *vcpu, + gpa_t cr2_or_gpa, + int emulation_type) { - unsigned changed = vcpu->arch.hflags ^ emul_flags; + if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) + return false; - vcpu->arch.hflags = emul_flags; + /* + * 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 (emulation_type & EMULTYPE_WRITE_PF_TO_SP) + return false; - if (changed & HF_SMM_MASK) - kvm_smm_changed(vcpu); + /* + * 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_gfn_and_retry(vcpu, cr2_or_gpa, true); + + /* + * 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 true; } +static int complete_emulated_mmio(struct kvm_vcpu *vcpu); +static int complete_emulated_pio(struct kvm_vcpu *vcpu); + static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, unsigned long *db) { @@ -6250,27 +9188,31 @@ static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, return dr6; } -static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r) +static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { - kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | DR6_RTM; - kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; + kvm_run->debug.arch.dr6 = DR6_BS | DR6_ACTIVE_LOW; + kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu); kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; - *r = EMULATE_USER_EXIT; - } else { - kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BS); + return 0; } + kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BS); + return 1; } int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) { - unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); - int r = EMULATE_DONE; + unsigned long rflags = kvm_x86_call(get_rflags)(vcpu); + int r; + + r = kvm_x86_call(skip_emulated_instruction)(vcpu); + if (unlikely(!r)) + return 0; - kvm_x86_ops->skip_emulated_instruction(vcpu); + kvm_pmu_instruction_retired(vcpu); /* * rflags is the old, "raw" value of the flags. The new value has @@ -6281,13 +9223,49 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) * that sets the TF flag". */ if (unlikely(rflags & X86_EFLAGS_TF)) - kvm_vcpu_do_singlestep(vcpu, &r); - return r == EMULATE_DONE; + 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_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) +static bool kvm_is_code_breakpoint_inhibited(struct kvm_vcpu *vcpu) { + if (kvm_get_rflags(vcpu) & X86_EFLAGS_RF) + return true; + + /* + * Intel compatible CPUs inhibit code #DBs when MOV/POP SS blocking is + * active, but AMD compatible CPUs do not. + */ + 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, + int emulation_type, int *r) +{ + WARN_ON_ONCE(emulation_type & EMULTYPE_NO_DECODE); + + /* + * Do not check for code breakpoints if hardware has already done the + * checks, as inferred from the emulation type. On NO_DECODE and SKIP, + * the instruction has passed all exception checks, and all intercepted + * exceptions that trigger emulation have lower priority than code + * breakpoints, i.e. the fact that the intercepted exception occurred + * means any code breakpoints have already been serviced. + * + * Note, KVM needs to check for code #DBs on EMULTYPE_TRAP_UD_FORCED as + * hardware has checked the RIP of the magic prefix, but not the RIP of + * the instruction being emulated. The intent of forced emulation is + * to behave as if KVM intercepted the instruction without an exception + * and without a prefix. + */ + if (emulation_type & (EMULTYPE_NO_DECODE | EMULTYPE_SKIP | + EMULTYPE_TRAP_UD | EMULTYPE_VMWARE_GP | EMULTYPE_PF)) + return false; + if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) && (vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) { struct kvm_run *kvm_run = vcpu->run; @@ -6297,27 +9275,25 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) vcpu->arch.eff_db); if (dr6 != 0) { - kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM; + kvm_run->debug.arch.dr6 = dr6 | DR6_ACTIVE_LOW; kvm_run->debug.arch.pc = eip; kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; - *r = EMULATE_USER_EXIT; + *r = 0; return true; } } if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK) && - !(kvm_get_rflags(vcpu) & X86_EFLAGS_RF)) { + !kvm_is_code_breakpoint_inhibited(vcpu)) { unsigned long eip = kvm_get_linear_rip(vcpu); u32 dr6 = kvm_vcpu_check_hw_bp(eip, 0, vcpu->arch.dr7, vcpu->arch.db); if (dr6 != 0) { - vcpu->arch.dr6 &= ~15; - vcpu->arch.dr6 |= dr6 | DR6_RTM; - kvm_queue_exception(vcpu, DB_VECTOR); - *r = EMULATE_DONE; + kvm_queue_exception_p(vcpu, DB_VECTOR, dr6); + *r = 1; return true; } } @@ -6356,77 +9332,163 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) return false; } -int x86_emulate_instruction(struct kvm_vcpu *vcpu, - unsigned long cr2, - int emulation_type, - void *insn, - int insn_len) +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 + * (and wrong) when emulating on an intercepted fault-like exception[*], as + * code breakpoints have higher priority and thus have already been done by + * hardware. + * + * [*] Except #MC, which is higher priority, but KVM should never emulate in + * response to a machine check. + */ +int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, + void *insn, int insn_len) { + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int r; - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + + init_emulate_ctxt(vcpu); + + r = x86_decode_insn(ctxt, insn, insn_len, emulation_type); + + trace_kvm_emulate_insn_start(vcpu); + ++vcpu->stat.insn_emulation; + + return r; +} +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) +{ + int r; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; bool writeback = true; - bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable; - vcpu->arch.l1tf_flush_l1d = true; + 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; - /* - * Clear write_fault_to_shadow_pgtable here to ensure it is - * never reused. - */ - vcpu->arch.write_fault_to_shadow_pgtable = false; - kvm_clear_exception_queue(vcpu); + 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; + + 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)) { - init_emulate_ctxt(vcpu); + kvm_clear_exception_queue(vcpu); /* - * We will reenter on the same instruction since - * we do not set complete_userspace_io. This does not - * handle watchpoints yet, those would be handled in - * the emulate_ops. + * Return immediately if RIP hits a code breakpoint, such #DBs + * are fault-like and are higher priority than any faults on + * the code fetch itself. */ - if (!(emulation_type & EMULTYPE_SKIP) && - kvm_vcpu_check_breakpoint(vcpu, &r)) + if (kvm_vcpu_check_code_breakpoint(vcpu, emulation_type, &r)) return r; - ctxt->interruptibility = 0; - ctxt->have_exception = false; - ctxt->exception.vector = -1; - ctxt->perm_ok = false; - - ctxt->ud = emulation_type & EMULTYPE_TRAP_UD; - - r = x86_decode_insn(ctxt, insn, insn_len); - - trace_kvm_emulate_insn_start(vcpu); - ++vcpu->stat.insn_emulation; + r = x86_decode_emulated_instruction(vcpu, emulation_type, + insn, insn_len); if (r != EMULATION_OK) { - if (emulation_type & EMULTYPE_TRAP_UD) - return EMULATE_FAIL; - if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, - emulation_type)) - return EMULATE_DONE; - if (ctxt->have_exception && inject_emulated_exception(vcpu)) - return EMULATE_DONE; - if (emulation_type & EMULTYPE_SKIP) - return EMULATE_FAIL; + if ((emulation_type & EMULTYPE_TRAP_UD) || + (emulation_type & EMULTYPE_TRAP_UD_FORCED)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, + emulation_type)) + return 1; + + if (ctxt->have_exception && + !(emulation_type & EMULTYPE_SKIP)) { + /* + * #UD should result in just EMULATION_FAILED, and trap-like + * exception should not be encountered during decode. + */ + WARN_ON_ONCE(ctxt->exception.vector == UD_VECTOR || + exception_type(ctxt->exception.vector) == EXCPT_TRAP); + inject_emulated_exception(vcpu); + return 1; + } return handle_emulation_failure(vcpu, emulation_type); } } - if ((emulation_type & EMULTYPE_VMWARE) && - !is_vmware_backdoor_opcode(ctxt)) - return EMULATE_FAIL; + if ((emulation_type & EMULTYPE_VMWARE_GP) && + !is_vmware_backdoor_opcode(ctxt)) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } + /* + * EMULTYPE_SKIP without EMULTYPE_COMPLETE_USER_EXIT is intended for + * use *only* by vendor callbacks for kvm_skip_emulated_instruction(). + * The caller is responsible for updating interruptibility state and + * injecting single-step #DBs. + */ if (emulation_type & EMULTYPE_SKIP) { - kvm_rip_write(vcpu, ctxt->_eip); + 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 + ctxt->eip = ctxt->_eip; + + if (emulation_type & EMULTYPE_COMPLETE_USER_EXIT) { + r = 1; + goto writeback; + } + + kvm_rip_write(vcpu, ctxt->eip); if (ctxt->eflags & X86_EFLAGS_RF) kvm_set_rflags(vcpu, ctxt->eflags & ~X86_EFLAGS_RF); - return EMULATE_DONE; + return 1; } - if (retry_instruction(ctxt, cr2, emulation_type)) - return EMULATE_DONE; + /* + * 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 changes registers values during IO operation */ @@ -6436,26 +9498,45 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, } restart: - /* Save the faulting GPA (cr2) in the address field */ - ctxt->exception.address = cr2; + if (emulation_type & EMULTYPE_PF) { + /* Save the faulting GPA (cr2) in the address field */ + ctxt->exception.address = cr2_or_gpa; + + /* With shadow page tables, cr2 contains a GVA or nGPA. */ + if (vcpu->arch.mmu->root_role.direct) { + ctxt->gpa_available = true; + ctxt->gpa_val = cr2_or_gpa; + } + } else { + /* Sanitize the address out of an abundance of paranoia. */ + 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 EMULATE_DONE; + return 1; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, - emulation_type)) - return EMULATE_DONE; + if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, + emulation_type)) + return 1; return handle_emulation_failure(vcpu, emulation_type); } if (ctxt->have_exception) { - r = EMULATE_DONE; - if (inject_emulated_exception(vcpu)) - return r; + WARN_ON_ONCE(vcpu->mmio_needed && !vcpu->mmio_is_write); + vcpu->mmio_needed = false; + r = 1; + inject_emulated_exception(vcpu); } else if (vcpu->arch.pio.count) { if (!vcpu->arch.pio.in) { /* FIXME: return into emulator if single-stepping. */ @@ -6464,28 +9545,44 @@ restart: writeback = false; vcpu->arch.complete_userspace_io = complete_emulated_pio; } - r = EMULATE_USER_EXIT; + r = 0; } else if (vcpu->mmio_needed) { + ++vcpu->stat.mmio_exits; + if (!vcpu->mmio_is_write) writeback = false; - r = EMULATE_USER_EXIT; + r = 0; vcpu->arch.complete_userspace_io = complete_emulated_mmio; + } else if (vcpu->arch.complete_userspace_io) { + writeback = false; + r = 0; } else if (r == EMULATION_RESTART) goto restart; else - r = EMULATE_DONE; + r = 1; +writeback: if (writeback) { - unsigned long rflags = kvm_x86_ops->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; - kvm_rip_write(vcpu, ctxt->eip); - if (r == EMULATE_DONE && - (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) - kvm_vcpu_do_singlestep(vcpu, &r); + + /* + * Note, EXCPT_DB is assumed to be fault-like as the emulator + * only supports code breakpoints and general detect #DB, both + * of which are fault-like. + */ if (!ctxt->have_exception || - exception_type(ctxt->exception.vector) == EXCPT_TRAP) + exception_type(ctxt->exception.vector) == EXCPT_TRAP) { + kvm_pmu_instruction_retired(vcpu); + if (ctxt->is_branch) + 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); + kvm_x86_call(update_emulated_instruction)(vcpu); __kvm_set_rflags(vcpu, ctxt->eflags); + } /* * For STI, interrupts are shadowed; so KVM_REQ_EVENT will @@ -6505,24 +9602,54 @@ 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) +{ + vcpu->arch.pio.count = 0; + return 1; +} + +static int complete_fast_pio_out(struct kvm_vcpu *vcpu) +{ + vcpu->arch.pio.count = 0; + + if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip))) + return 1; + + return kvm_skip_emulated_instruction(vcpu); +} static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) { - unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX); - int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt, - size, port, &val, 1); - /* do not return to emulator after return from userspace */ - vcpu->arch.pio.count = 0; - return ret; + unsigned long val = kvm_rax_read(vcpu); + int ret = emulator_pio_out(vcpu, size, port, &val, 1); + + if (ret) + return ret; + + /* + * Workaround userspace that relies on old KVM behavior of %rip being + * incremented prior to exiting to userspace to handle "OUT 0x7e". + */ + if (port == 0x7e && + kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) { + vcpu->arch.complete_userspace_io = + complete_fast_pio_out_port_0x7e; + kvm_skip_emulated_instruction(vcpu); + } else { + vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu); + vcpu->arch.complete_userspace_io = complete_fast_pio_out; + } + return 0; } static int complete_fast_pio_in(struct kvm_vcpu *vcpu) @@ -6532,19 +9659,18 @@ 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.cui_linear_rip))) { + vcpu->arch.pio.count = 0; + return 1; + } + /* For size less than 4 we merge, else we zero extend */ - val = (vcpu->arch.pio.size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX) - : 0; + val = (vcpu->arch.pio.size < 4) ? kvm_rax_read(vcpu) : 0; - /* - * Since vcpu->arch.pio.count == 1 let emulator_pio_in_emulated perform - * the copy and tracing - */ - emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, vcpu->arch.pio.size, - vcpu->arch.pio.port, &val, 1); - kvm_register_write(vcpu, VCPU_REGS_RAX, val); + complete_emulator_pio_in(vcpu, &val); + kvm_rax_write(vcpu, val); - return 1; + return kvm_skip_emulated_instruction(vcpu); } static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, @@ -6554,15 +9680,15 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, int ret; /* For size less than 4 we merge, else we zero extend */ - val = (size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX) : 0; + val = (size < 4) ? kvm_rax_read(vcpu) : 0; - ret = emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, size, port, - &val, 1); + ret = emulator_pio_in(vcpu, size, port, &val, 1); if (ret) { - kvm_register_write(vcpu, VCPU_REGS_RAX, val); + kvm_rax_write(vcpu, val); return ret; } + vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu); vcpu->arch.complete_userspace_io = complete_fast_pio_in; return 0; @@ -6570,18 +9696,15 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in) { - int ret = kvm_skip_emulated_instruction(vcpu); + int ret; - /* - * TODO: we might be squashing a KVM_GUESTDBG_SINGLESTEP-triggered - * KVM_EXIT_DEBUG here. - */ if (in) - return kvm_fast_pio_in(vcpu, size, port) && ret; + ret = kvm_fast_pio_in(vcpu, size, port); else - return kvm_fast_pio_out(vcpu, size, port) && ret; + ret = kvm_fast_pio_out(vcpu, size, port); + return ret && kvm_skip_emulated_instruction(vcpu); } -EXPORT_SYMBOL_GPL(kvm_fast_pio); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_fast_pio); static int kvmclock_cpu_down_prep(unsigned int cpu) { @@ -6592,11 +9715,13 @@ 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)); if (data) khz = freq->new; - else if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + else khz = cpufreq_quick_get(raw_smp_processor_id()); if (!khz) khz = tsc_khz; @@ -6607,46 +9732,38 @@ static void tsc_khz_changed(void *data) static void kvm_hyperv_tsc_notifier(void) { struct kvm *kvm; - struct kvm_vcpu *vcpu; int cpu; - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_make_mclock_inprogress_request(kvm); + /* no guest entries from this point */ hyperv_stop_tsc_emulation(); /* TSC frequency always matches when on Hyper-V */ - for_each_present_cpu(cpu) - per_cpu(cpu_tsc_khz, cpu) = tsc_khz; - kvm_max_guest_tsc_khz = tsc_khz; + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + for_each_present_cpu(cpu) + per_cpu(cpu_tsc_khz, cpu) = tsc_khz; + } + kvm_caps.max_guest_tsc_khz = tsc_khz; list_for_each_entry(kvm, &vm_list, vm_list) { - struct kvm_arch *ka = &kvm->arch; - - spin_lock(&ka->pvclock_gtod_sync_lock); - + __kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); - - kvm_for_each_vcpu(cpu, vcpu, kvm) - kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); - - kvm_for_each_vcpu(cpu, vcpu, kvm) - kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); - - spin_unlock(&ka->pvclock_gtod_sync_lock); + kvm_end_pvclock_update(kvm); } - spin_unlock(&kvm_lock); + + mutex_unlock(&kvm_lock); } #endif -static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val, - void *data) +static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu) { - struct cpufreq_freqs *freq = data; struct kvm *kvm; struct kvm_vcpu *vcpu; - int i, send_ipi = 0; + int send_ipi = 0; + unsigned long i; /* * We allow guests to temporarily run on slowing clocks, @@ -6687,24 +9804,19 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va * */ - if (val == CPUFREQ_PRECHANGE && freq->old > freq->new) - return 0; - if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new) - return 0; - - smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1); + smp_call_function_single(cpu, tsc_khz_changed, freq, 1); - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { - if (vcpu->cpu != freq->cpu) + if (vcpu->cpu != cpu) continue; kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); - if (vcpu->cpu != smp_processor_id()) + if (vcpu->cpu != raw_smp_processor_id()) send_ipi = 1; } } - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); if (freq->old < freq->new && send_ipi) { /* @@ -6719,8 +9831,24 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va * guest context is entered kvmclock will be updated, * so the guest will not see stale values. */ - smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1); + smp_call_function_single(cpu, tsc_khz_changed, freq, 1); } +} + +static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct cpufreq_freqs *freq = data; + int cpu; + + if (val == CPUFREQ_PRECHANGE && freq->old > freq->new) + return 0; + if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new) + return 0; + + for_each_cpu(cpu, freq->policy->cpus) + __kvmclock_cpufreq_notifier(freq, cpu); + return 0; } @@ -6736,111 +9864,60 @@ static int kvmclock_cpu_online(unsigned int cpu) static void kvm_timer_init(void) { - max_tsc_khz = tsc_khz; - if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { -#ifdef CONFIG_CPU_FREQ - struct cpufreq_policy policy; - int cpu; - - memset(&policy, 0, sizeof(policy)); - cpu = get_cpu(); - cpufreq_get_policy(&policy, cpu); - if (policy.cpuinfo.max_freq) - max_tsc_khz = policy.cpuinfo.max_freq; - put_cpu(); -#endif + max_tsc_khz = tsc_khz; + + if (IS_ENABLED(CONFIG_CPU_FREQ)) { + struct cpufreq_policy *policy; + int cpu; + + cpu = get_cpu(); + policy = cpufreq_cpu_get(cpu); + if (policy) { + if (policy->cpuinfo.max_freq) + max_tsc_khz = policy->cpuinfo.max_freq; + cpufreq_cpu_put(policy); + } + put_cpu(); + } cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); - } - pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz); - - cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online", - kvmclock_cpu_online, kvmclock_cpu_down_prep); -} - -DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu); -EXPORT_PER_CPU_SYMBOL_GPL(current_vcpu); - -int kvm_is_in_guest(void) -{ - return __this_cpu_read(current_vcpu) != NULL; -} - -static int kvm_is_user_mode(void) -{ - int user_mode = 3; - - if (__this_cpu_read(current_vcpu)) - user_mode = kvm_x86_ops->get_cpl(__this_cpu_read(current_vcpu)); - - return user_mode != 0; -} - -static unsigned long kvm_get_guest_ip(void) -{ - unsigned long ip = 0; - if (__this_cpu_read(current_vcpu)) - ip = kvm_rip_read(__this_cpu_read(current_vcpu)); - - return ip; -} - -static struct perf_guest_info_callbacks kvm_guest_cbs = { - .is_in_guest = kvm_is_in_guest, - .is_user_mode = kvm_is_user_mode, - .get_guest_ip = kvm_get_guest_ip, -}; - -static void kvm_set_mmio_spte_mask(void) -{ - u64 mask; - int maxphyaddr = boot_cpu_data.x86_phys_bits; - - /* - * Set the reserved bits and the present bit of an paging-structure - * entry to generate page fault with PFER.RSV = 1. - */ - - /* - * Mask the uppermost physical address bit, which would be reserved as - * long as the supported physical address width is less than 52. - */ - mask = 1ull << 51; - - /* Set the present bit. */ - mask |= 1ull; - - /* - * If reserved bit is not supported, clear the present bit to disable - * mmio page fault. - */ - if (IS_ENABLED(CONFIG_X86_64) && maxphyaddr == 52) - mask &= ~1ull; - - kvm_mmu_set_mmio_spte_mask(mask, mask); + cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online", + kvmclock_cpu_online, kvmclock_cpu_down_prep); + } } #ifdef CONFIG_X86_64 static void pvclock_gtod_update_fn(struct work_struct *work) { struct kvm *kvm; - struct kvm_vcpu *vcpu; - int i; + unsigned long i; - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); atomic_set(&kvm_guest_has_master_clock, 0); - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); } static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); /* + * Indirection to move queue_work() out of the tk_core.seq write held + * region to prevent possible deadlocks against time accessors which + * are invoked with work related locks held. + */ +static void pvclock_irq_work_fn(struct irq_work *w) +{ + queue_work(system_long_wq, &pvclock_gtod_work); +} + +static DEFINE_IRQ_WORK(pvclock_irq_work, pvclock_irq_work_fn); + +/* * Notification about pvclock gtod data update. */ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, @@ -6851,13 +9928,14 @@ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, update_pvclock_gtod(tk); - /* disable master clock if host does not trust, or does not - * use, TSC based clocksource. + /* + * Disable master clock if host does not trust, or does not use, + * TSC based clocksource. Delegate queue_work() to irq_work as + * this is invoked with tk_core.seq write held. */ if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) && atomic_read(&kvm_guest_has_master_clock) != 0) - queue_work(system_long_wq, &pvclock_gtod_work); - + irq_work_queue(&pvclock_irq_work); return 0; } @@ -6866,26 +9944,59 @@ static struct notifier_block pvclock_gtod_notifier = { }; #endif -int kvm_arch_init(void *opaque) +static inline void kvm_ops_update(struct kvm_x86_init_ops *ops) { - int r; - struct kvm_x86_ops *ops = opaque; + memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); - if (kvm_x86_ops) { - printk(KERN_ERR "kvm: already loaded the other module\n"); - r = -EEXIST; - goto out; - } +#define __KVM_X86_OP(func) \ + static_call_update(kvm_x86_##func, kvm_x86_ops.func); +#define KVM_X86_OP(func) \ + WARN_ON(!kvm_x86_ops.func); __KVM_X86_OP(func) +#define KVM_X86_OP_OPTIONAL __KVM_X86_OP +#define KVM_X86_OP_OPTIONAL_RET0(func) \ + static_call_update(kvm_x86_##func, (void *)kvm_x86_ops.func ? : \ + (void *)__static_call_return0); +#include <asm/kvm-x86-ops.h> +#undef __KVM_X86_OP - if (!ops->cpu_has_kvm_support()) { - printk(KERN_ERR "kvm: no hardware support\n"); - r = -EOPNOTSUPP; - goto out; - } - if (ops->disabled_by_bios()) { - printk(KERN_ERR "kvm: disabled by bios\n"); - r = -EOPNOTSUPP; - goto out; + kvm_pmu_ops_update(ops->pmu_ops); +} + +static int kvm_x86_check_processor_compatibility(void) +{ + int cpu = smp_processor_id(); + struct cpuinfo_x86 *c = &cpu_data(cpu); + + /* + * Compatibility checks are done when loading KVM and when enabling + * hardware, e.g. during CPU hotplug, to ensure all online CPUs are + * compatible, i.e. KVM should never perform a compatibility check on + * an offline CPU. + */ + WARN_ON(!cpu_online(cpu)); + + if (__cr4_reserved_bits(cpu_has, c) != + __cr4_reserved_bits(cpu_has, &boot_cpu_data)) + return -EIO; + + return kvm_x86_call(check_processor_compatibility)(); +} + +static void kvm_x86_check_cpu_compat(void *ret) +{ + *(int *)ret = kvm_x86_check_processor_compatibility(); +} + +int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) +{ + u64 host_pat; + int r, cpu; + + 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; } /* @@ -6894,45 +10005,101 @@ int kvm_arch_init(void *opaque) * vCPU's FPU state as a fxregs_state struct. */ if (!boot_cpu_has(X86_FEATURE_FPU) || !boot_cpu_has(X86_FEATURE_FXSR)) { - printk(KERN_ERR "kvm: inadequate fpu\n"); - r = -EOPNOTSUPP; - goto out; + pr_err("inadequate fpu\n"); + return -EOPNOTSUPP; } - r = -ENOMEM; - x86_fpu_cache = kmem_cache_create("x86_fpu", sizeof(struct fpu), - __alignof__(struct fpu), SLAB_ACCOUNT, - NULL); - if (!x86_fpu_cache) { - printk(KERN_ERR "kvm: failed to allocate cache for x86 fpu\n"); - goto out; + if (IS_ENABLED(CONFIG_PREEMPT_RT) && !boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + pr_err("RT requires X86_FEATURE_CONSTANT_TSC\n"); + return -EOPNOTSUPP; } - shared_msrs = alloc_percpu(struct kvm_shared_msrs); - if (!shared_msrs) { - printk(KERN_ERR "kvm: failed to allocate percpu kvm_shared_msrs\n"); - goto out_free_x86_fpu_cache; + /* + * KVM assumes that PAT entry '0' encodes WB memtype and simply zeroes + * the PAT bits in SPTEs. Bail if PAT[0] is programmed to something + * other than WB. Note, EPT doesn't utilize the PAT, but don't bother + * 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 (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; } - r = kvm_mmu_module_init(); + 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; + } + + r = kvm_mmu_vendor_module_init(); if (r) - goto out_free_percpu; + goto out_free_x86_emulator_cache; - kvm_set_mmio_spte_mask(); + kvm_caps.supported_vm_types = BIT(KVM_X86_DEFAULT_VM); + kvm_caps.supported_mce_cap = MCG_CTL_P | MCG_SER_P; - kvm_x86_ops = ops; + if (boot_cpu_has(X86_FEATURE_XSAVE)) { + kvm_host.xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); + kvm_caps.supported_xcr0 = kvm_host.xcr0 & KVM_SUPPORTED_XCR0; + } - kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, - PT_DIRTY_MASK, PT64_NX_MASK, 0, - PT_PRESENT_MASK, 0, sme_me_mask); - kvm_timer_init(); + if (boot_cpu_has(X86_FEATURE_XSAVES)) { + rdmsrq(MSR_IA32_XSS, kvm_host.xss); + kvm_caps.supported_xss = kvm_host.xss & KVM_SUPPORTED_XSS; + } - perf_register_guest_info_callbacks(&kvm_guest_cbs); + kvm_caps.supported_quirks = KVM_X86_VALID_QUIRKS; + kvm_caps.inapplicable_quirks = KVM_X86_CONDITIONAL_QUIRKS; - if (boot_cpu_has(X86_FEATURE_XSAVE)) - host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); + rdmsrq_safe(MSR_EFER, &kvm_host.efer); - kvm_lapic_init(); + 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) { + smp_call_function_single(cpu, kvm_x86_check_cpu_compat, &r, 1); + if (r < 0) + goto out_unwind_ops; + } + + /* + * Point of no return! DO NOT add error paths below this point unless + * absolutely necessary, as most operations from this point forward + * require unwinding. + */ + kvm_timer_init(); + + if (pi_inject_timer == -1) + pi_inject_timer = housekeeping_enabled(HK_TYPE_TIMER); #ifdef CONFIG_X86_64 pvclock_gtod_register_notifier(&pvclock_gtod_notifier); @@ -6940,61 +10107,88 @@ int kvm_arch_init(void *opaque) set_hv_tscchange_cb(kvm_hyperv_tsc_notifier); #endif + 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; + + 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) { + /* + * Make sure the user can only configure tsc_khz values that + * fit into a signed integer. + * A min value is not calculated because it will always + * be 1 on all machines. + */ + u64 max = min(0x7fffffffULL, + __scale_tsc(kvm_caps.max_tsc_scaling_ratio, tsc_khz)); + kvm_caps.max_guest_tsc_khz = max; + } + kvm_caps.default_tsc_scaling_ratio = 1ULL << kvm_caps.tsc_scaling_ratio_frac_bits; + kvm_init_msr_lists(); return 0; -out_free_percpu: - free_percpu(shared_msrs); -out_free_x86_fpu_cache: - kmem_cache_destroy(x86_fpu_cache); -out: +out_unwind_ops: + 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_x86_emulator_cache: + kmem_cache_destroy(x86_emulator_cache); return r; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_x86_vendor_init); -void kvm_arch_exit(void) +void kvm_x86_vendor_exit(void) { + kvm_unregister_perf_callbacks(); + #ifdef CONFIG_X86_64 if (hypervisor_is_type(X86_HYPER_MS_HYPERV)) clear_hv_tscchange_cb(); #endif kvm_lapic_exit(); - perf_unregister_guest_info_callbacks(&kvm_guest_cbs); - if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); - cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE); + cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE); + } #ifdef CONFIG_X86_64 pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); + irq_work_sync(&pvclock_irq_work); + cancel_work_sync(&pvclock_gtod_work); #endif - kvm_x86_ops = NULL; - kvm_mmu_module_exit(); - free_percpu(shared_msrs); - kmem_cache_destroy(x86_fpu_cache); -} - -int kvm_vcpu_halt(struct kvm_vcpu *vcpu) -{ - ++vcpu->stat.halt_exits; - if (lapic_in_kernel(vcpu)) { - vcpu->arch.mp_state = KVM_MP_STATE_HALTED; - return 1; - } else { - vcpu->run->exit_reason = KVM_EXIT_HLT; - return 0; - } -} -EXPORT_SYMBOL_GPL(kvm_vcpu_halt); - -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_vcpu_halt(vcpu) && ret; + kvm_x86_call(hardware_unsetup)(); + kvm_destroy_user_return_msrs(); + kvm_mmu_vendor_module_exit(); + 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.enable_virtualization_cpu = NULL; + mutex_unlock(&vendor_module_lock); } -EXPORT_SYMBOL_GPL(kvm_emulate_halt); +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, @@ -7008,7 +10202,14 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK) return -KVM_EOPNOTSUPP; - if (kvm_get_walltime_and_clockread(&ts, &cycle) == false) + /* + * When tsc is in permanent catchup mode guests won't be able to use + * pvclock_read_retry loop to get consistent view of pvclock + */ + if (vcpu->arch.tsc_always_catchup) + return -KVM_EOPNOTSUPP; + + if (!kvm_get_walltime_and_clockread(&ts, &cycle)) return -KVM_EOPNOTSUPP; clock_pairing.sec = ts.tv_sec; @@ -7031,43 +10232,125 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, * * @apicid - apicid of vcpu to be kicked. */ -static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) +static void kvm_pv_kick_cpu_op(struct kvm *kvm, int apicid) { - struct kvm_lapic_irq lapic_irq; - - lapic_irq.shorthand = 0; - lapic_irq.dest_mode = 0; - lapic_irq.level = 0; - lapic_irq.dest_id = apicid; - lapic_irq.msi_redir_hint = false; + /* + * All other fields are unused for APIC_DM_REMRD, but may be consumed by + * common code, e.g. for tracing. Defer initialization to the compiler. + */ + struct kvm_lapic_irq lapic_irq = { + .delivery_mode = APIC_DM_REMRD, + .dest_mode = APIC_DEST_PHYSICAL, + .shorthand = APIC_DEST_NOSHORT, + .dest_id = apicid, + }; - lapic_irq.delivery_mode = APIC_DM_REMRD; kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); } -void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu) +bool kvm_apicv_activated(struct kvm *kvm) { - vcpu->arch.apicv_active = false; - kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu); + return (READ_ONCE(kvm->arch.apicv_inhibit_reasons) == 0); } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_apicv_activated); -int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) +bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu) { - unsigned long nr, a0, a1, a2, a3, ret; - int op_64_bit; + ulong vm_reasons = READ_ONCE(vcpu->kvm->arch.apicv_inhibit_reasons); + ulong vcpu_reasons = + kvm_x86_call(vcpu_get_apicv_inhibit_reasons)(vcpu); - if (kvm_hv_hypercall_enabled(vcpu->kvm)) - return kvm_hv_hypercall(vcpu); + return (vm_reasons | vcpu_reasons) == 0; +} +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 }; - nr = kvm_register_read(vcpu, VCPU_REGS_RAX); - a0 = kvm_register_read(vcpu, VCPU_REGS_RBX); - a1 = kvm_register_read(vcpu, VCPU_REGS_RCX); - a2 = kvm_register_read(vcpu, VCPU_REGS_RDX); - a3 = kvm_register_read(vcpu, VCPU_REGS_RSI); + BUILD_BUG_ON(ARRAY_SIZE(apicv_inhibits) != NR_APICV_INHIBIT_REASONS); + + if (set) + __set_bit(reason, inhibits); + else + __clear_bit(reason, inhibits); + + trace_kvm_apicv_inhibit_changed(reason, set, *inhibits); +} + +static void kvm_apicv_init(struct kvm *kvm) +{ + enum kvm_apicv_inhibit reason = enable_apicv ? APICV_INHIBIT_REASON_ABSENT : + APICV_INHIBIT_REASON_DISABLED; + + set_or_clear_apicv_inhibit(&kvm->arch.apicv_inhibit_reasons, reason, true); + + init_rwsem(&kvm->arch.apicv_update_lock); +} + +static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) +{ + struct kvm_vcpu *target = NULL; + struct kvm_apic_map *map; + + vcpu->stat.directed_yield_attempted++; + + if (single_task_running()) + goto no_yield; + + rcu_read_lock(); + map = rcu_dereference(vcpu->kvm->arch.apic_map); + + 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(); + + if (!target || !READ_ONCE(target->ready)) + goto no_yield; + + /* Ignore requests to yield to self */ + if (vcpu == target) + goto no_yield; + + if (kvm_vcpu_yield_to(target) <= 0) + goto no_yield; + + vcpu->stat.directed_yield_successful++; + +no_yield: + return; +} + +static int complete_hypercall_exit(struct kvm_vcpu *vcpu) +{ + u64 ret = vcpu->run->hypercall.ret; + + if (!is_64_bit_hypercall(vcpu)) + ret = (u32)ret; + kvm_rax_write(vcpu, ret); + return kvm_skip_emulated_instruction(vcpu); +} + +int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, int cpl, + int (*complete_hypercall)(struct kvm_vcpu *)) +{ + 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); + + ++vcpu->stat.hypercalls; trace_kvm_hypercall(nr, a0, a1, a2, a3); - op_64_bit = is_64_bit_mode(vcpu); if (!op_64_bit) { nr &= 0xFFFFFFFF; a0 &= 0xFFFFFFFF; @@ -7076,40 +10359,99 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) a3 &= 0xFFFFFFFF; } - if (kvm_x86_ops->get_cpl(vcpu) != 0) { + if (cpl) { ret = -KVM_EPERM; goto out; } + ret = -KVM_ENOSYS; + switch (nr) { case KVM_HC_VAPIC_POLL_IRQ: ret = 0; break; case KVM_HC_KICK_CPU: - kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1); + if (!guest_pv_has(vcpu, KVM_FEATURE_PV_UNHALT)) + break; + + kvm_pv_kick_cpu_op(vcpu->kvm, a1); + kvm_sched_yield(vcpu, a1); ret = 0; break; #ifdef CONFIG_X86_64 case KVM_HC_CLOCK_PAIRING: ret = kvm_pv_clock_pairing(vcpu, a0, a1); break; +#endif case KVM_HC_SEND_IPI: + if (!guest_pv_has(vcpu, KVM_FEATURE_PV_SEND_IPI)) + break; + ret = kvm_pv_send_ipi(vcpu->kvm, a0, a1, a2, a3, op_64_bit); break; -#endif + case KVM_HC_SCHED_YIELD: + if (!guest_pv_has(vcpu, KVM_FEATURE_PV_SCHED_YIELD)) + break; + + kvm_sched_yield(vcpu, a0); + ret = 0; + break; + case KVM_HC_MAP_GPA_RANGE: { + u64 gpa = a0, npages = a1, attrs = a2; + + ret = -KVM_ENOSYS; + if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) + break; + + if (!PAGE_ALIGNED(gpa) || !npages || + gpa_to_gfn(gpa) + npages <= gpa_to_gfn(gpa)) { + ret = -KVM_EINVAL; + break; + } + + 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; + vcpu->run->hypercall.flags = 0; + if (op_64_bit) + 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; + return 0; + } default: ret = -KVM_ENOSYS; break; } + out: - if (!op_64_bit) - ret = (u32)ret; - kvm_register_write(vcpu, VCPU_REGS_RAX, 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) { @@ -7117,7 +10459,18 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) char instruction[3]; unsigned long rip = kvm_rip_read(vcpu); - kvm_x86_ops->patch_hypercall(vcpu, instruction); + /* + * If the quirk is disabled, synthesize a #UD and let the guest pick up + * the pieces. + */ + if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_FIX_HYPERCALL_INSN)) { + ctxt->exception.error_code_valid = false; + ctxt->exception.vector = UD_VECTOR; + ctxt->have_exception = true; + return X86EMUL_PROPAGATE_FAULT; + } + + kvm_x86_call(patch_hypercall)(vcpu, instruction); return emulator_write_emulated(ctxt, rip, instruction, 3, &ctxt->exception); @@ -7129,30 +10482,36 @@ static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) likely(!pic_in_kernel(vcpu->kvm)); } +/* Called within kvm->srcu read side. */ static void post_kvm_run_save(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; - kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; - kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0; + 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) || kvm_vcpu_ready_for_interrupt_injection(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) { int max_irr, tpr; - if (!kvm_x86_ops->update_cr8_intercept) + if (!kvm_x86_ops.update_cr8_intercept) return; if (!lapic_in_kernel(vcpu)) return; - if (vcpu->arch.apicv_active) + if (vcpu->arch.apic->apicv_active) return; if (!vcpu->arch.apic->vapic_addr) @@ -7165,381 +10524,453 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) tpr = kvm_lapic_get_cr8(vcpu); - kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr); + kvm_x86_call(update_cr8_intercept)(vcpu, tpr, max_irr); +} + + +int kvm_check_nested_events(struct kvm_vcpu *vcpu) +{ + if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + kvm_x86_ops.nested_ops->triple_fault(vcpu); + return 1; + } + + return kvm_x86_ops.nested_ops->check_events(vcpu); } -static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) +static void kvm_inject_exception(struct kvm_vcpu *vcpu) { + /* + * Suppress the error code if the vCPU is in Real Mode, as Real Mode + * exceptions don't report error codes. The presence of an error code + * is carried with the exception and only stripped when the exception + * is injected as intercepted #PF VM-Exits for AMD's Paged Real Mode do + * report an error code despite the CPU being in Real Mode. + */ + vcpu->arch.exception.has_error_code &= is_protmode(vcpu); + + trace_kvm_inj_exception(vcpu->arch.exception.vector, + vcpu->arch.exception.has_error_code, + vcpu->arch.exception.error_code, + vcpu->arch.exception.injected); + + kvm_x86_call(inject_exception)(vcpu); +} + +/* + * Check for any event (interrupt or exception) that is ready to be injected, + * and if there is at least one event, inject the event with the highest + * priority. This handles both "pending" events, i.e. events that have never + * been injected into the guest, and "injected" events, i.e. events that were + * injected as part of a previous VM-Enter, but weren't successfully delivered + * and need to be re-injected. + * + * Note, this is not guaranteed to be invoked on a guest instruction boundary, + * i.e. doesn't guarantee that there's an event window in the guest. KVM must + * be able to inject exceptions in the "middle" of an instruction, and so must + * also be able to re-inject NMIs and IRQs in the middle of an instruction. + * I.e. for exceptions and re-injected events, NOT invoking this on instruction + * boundaries is necessary and correct. + * + * For simplicity, KVM uses a single path to inject all events (except events + * that are injected directly from L1 to L2) and doesn't explicitly track + * instruction boundaries for asynchronous events. However, because VM-Exits + * that can occur during instruction execution typically result in KVM skipping + * the instruction or injecting an exception, e.g. instruction and exception + * intercepts, and because pending exceptions have higher priority than pending + * interrupts, KVM still honors instruction boundaries in most scenarios. + * + * 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 + * 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 + * instruction completes. + * + * In practice, this virtualization hole is unlikely to be observed by the + * guest, and even less likely to cause functional problems. To detect the + * hole, the guest would have to trigger an event on a side effect of an early + * phase of instruction execution, e.g. on the instruction fetch from memory. + * And for it to be a functional problem, the guest would need to depend on the + * ordering between that side effect, the instruction completing, _and_ the + * delivery of the asynchronous event. + */ +static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, + bool *req_immediate_exit) +{ + bool can_inject; int r; - /* try to reinject previous events if any */ + /* + * 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. + */ + if (is_guest_mode(vcpu)) + r = kvm_check_nested_events(vcpu); + else + r = 0; + /* + * Re-inject exceptions and events *especially* if immediate entry+exit + * to/from L2 is needed, as any event that has already been injected + * into L2 needs to complete its lifecycle before injecting a new event. + * + * Don't re-inject an NMI or interrupt if there is a pending exception. + * This collision arises if an exception occurred while vectoring the + * injected event, KVM intercepted said exception, and KVM ultimately + * determined the fault belongs to the guest and queues the exception + * for injection back into the guest. + * + * "Injected" interrupts can also collide with pending exceptions if + * userspace ignores the "ready for injection" flag and blindly queues + * an interrupt. In that case, prioritizing the exception is correct, + * as the exception "occurred" before the exit to userspace. Trap-like + * exceptions, e.g. most #DBs, have higher priority than interrupts. + * And while fault-like exceptions, e.g. #GP and #PF, are the lowest + * priority, they're only generated (pended) during instruction + * execution, and interrupts are recognized at instruction boundaries. + * Thus a pending fault-like exception means the fault occurred on the + * *previous* instruction and must be serviced prior to recognizing any + * new events in order to fully complete the previous instruction. + */ if (vcpu->arch.exception.injected) - kvm_x86_ops->queue_exception(vcpu); - /* - * Do not inject an NMI or interrupt if there is a pending - * exception. Exceptions and interrupts are recognized at - * instruction boundaries, i.e. the start of an instruction. - * Trap-like exceptions, e.g. #DB, have higher priority than - * NMIs and interrupts, i.e. traps are recognized before an - * NMI/interrupt that's pending on the same instruction. - * Fault-like exceptions, e.g. #GP and #PF, are the lowest - * priority, but are only generated (pended) during instruction - * execution, i.e. a pending fault-like exception means the - * fault occurred on the *previous* instruction and must be - * serviced prior to recognizing any new events in order to - * fully complete the previous instruction. - */ - else if (!vcpu->arch.exception.pending) { - if (vcpu->arch.nmi_injected) - kvm_x86_ops->set_nmi(vcpu); - else if (vcpu->arch.interrupt.injected) - kvm_x86_ops->set_irq(vcpu); - } - - /* - * Call check_nested_events() even if we reinjected a previous event - * in order for caller to determine if it should require immediate-exit - * from L2 to L1 due to pending L1 events which require exit - * from L2 to L1. - */ - if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { - r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); - if (r != 0) - return r; - } + kvm_inject_exception(vcpu); + else if (kvm_is_exception_pending(vcpu)) + ; /* see above */ + else if (vcpu->arch.nmi_injected) + kvm_x86_call(inject_nmi)(vcpu); + else if (vcpu->arch.interrupt.injected) + kvm_x86_call(inject_irq)(vcpu, true); - /* try to inject new event if pending */ - if (vcpu->arch.exception.pending) { - trace_kvm_inj_exception(vcpu->arch.exception.nr, - vcpu->arch.exception.has_error_code, - vcpu->arch.exception.error_code); + /* + * Exceptions that morph to VM-Exits are handled above, and pending + * exceptions on top of injected exceptions that do not VM-Exit should + * either morph to #DF or, sadly, override the injected exception. + */ + WARN_ON_ONCE(vcpu->arch.exception.injected && + vcpu->arch.exception.pending); - WARN_ON_ONCE(vcpu->arch.exception.injected); - vcpu->arch.exception.pending = false; - vcpu->arch.exception.injected = true; + /* + * Bail if immediate entry+exit to/from the guest is needed to complete + * nested VM-Enter or event re-injection so that a different pending + * event can be serviced (or if KVM needs to exit to userspace). + * + * Otherwise, continue processing events even if VM-Exit occurred. The + * VM-Exit will have cleared exceptions that were meant for L2, but + * there may now be events that can be injected into L1. + */ + if (r < 0) + goto out; - if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT) + /* + * A pending exception VM-Exit should either result in nested VM-Exit + * or force an immediate re-entry and exit to/from L2, and exception + * VM-Exits cannot be injected (flag should _never_ be set). + */ + WARN_ON_ONCE(vcpu->arch.exception_vmexit.injected || + vcpu->arch.exception_vmexit.pending); + + /* + * New events, other than exceptions, cannot be injected if KVM needs + * to re-inject a previous event. See above comments on re-injecting + * for why pending exceptions get priority. + */ + can_inject = !kvm_event_needs_reinjection(vcpu); + + if (vcpu->arch.exception.pending) { + /* + * Fault-class exceptions, except #DBs, set RF=1 in the RFLAGS + * value pushed on the stack. Trap-like exception and all #DBs + * leave RF as-is (KVM follows Intel's behavior in this regard; + * AMD states that code breakpoint #DBs excplitly clear RF=0). + * + * Note, most versions of Intel's SDM and AMD's APM incorrectly + * describe the behavior of General Detect #DBs, which are + * fault-like. They do _not_ set RF, a la code breakpoints. + */ + if (exception_type(vcpu->arch.exception.vector) == EXCPT_FAULT) __kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) | X86_EFLAGS_RF); - if (vcpu->arch.exception.nr == DB_VECTOR) { - /* - * This code assumes that nSVM doesn't use - * check_nested_events(). If it does, the - * DR6/DR7 changes should happen before L1 - * gets a #VMEXIT for an intercepted #DB in - * L2. (Under VMX, on the other hand, the - * DR6/DR7 changes should not happen in the - * event of a VM-exit to L1 for an intercepted - * #DB in L2.) - */ - kvm_deliver_exception_payload(vcpu); + if (vcpu->arch.exception.vector == DB_VECTOR) { + kvm_deliver_exception_payload(vcpu, &vcpu->arch.exception); if (vcpu->arch.dr7 & DR7_GD) { vcpu->arch.dr7 &= ~DR7_GD; kvm_update_dr7(vcpu); } } - kvm_x86_ops->queue_exception(vcpu); + kvm_inject_exception(vcpu); + + vcpu->arch.exception.pending = false; + vcpu->arch.exception.injected = true; + + can_inject = false; } - /* Don't consider new event if we re-injected an event */ - if (kvm_event_needs_reinjection(vcpu)) + /* Don't inject interrupts if the user asked to avoid doing so */ + if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ) return 0; - if (vcpu->arch.smi_pending && !is_smm(vcpu) && - kvm_x86_ops->smi_allowed(vcpu)) { - vcpu->arch.smi_pending = false; - ++vcpu->arch.smi_count; - enter_smm(vcpu); - } else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) { - --vcpu->arch.nmi_pending; - vcpu->arch.nmi_injected = true; - kvm_x86_ops->set_nmi(vcpu); - } else if (kvm_cpu_has_injectable_intr(vcpu)) { - /* - * Because interrupts can be injected asynchronously, we are - * calling check_nested_events again here to avoid a race condition. - * See https://lkml.org/lkml/2014/7/2/60 for discussion about this - * proposal and current concerns. Perhaps we should be setting - * KVM_REQ_EVENT only on certain events and not unconditionally? - */ - if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { - r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); - if (r != 0) - return r; + /* + * Finally, inject interrupt events. If an event cannot be injected + * due to architectural conditions (e.g. IF=0) a window-open exit + * will re-request KVM_REQ_EVENT. Sometimes however an event is pending + * and can architecturally be injected, but we cannot do it right now: + * an interrupt could have arrived just now and we have to inject it + * as a vmexit, or there could already an event in the queue, which is + * indicated by can_inject. In that case we request an immediate exit + * in order to make progress and get back here for another iteration. + * The kvm_x86_ops hooks communicate this by returning -EBUSY. + */ +#ifdef CONFIG_KVM_SMM + if (vcpu->arch.smi_pending) { + r = can_inject ? kvm_x86_call(smi_allowed)(vcpu, true) : + -EBUSY; + if (r < 0) + goto out; + if (r) { + vcpu->arch.smi_pending = false; + ++vcpu->arch.smi_count; + enter_smm(vcpu); + can_inject = false; + } else + kvm_x86_call(enable_smi_window)(vcpu); + } +#endif + + if (vcpu->arch.nmi_pending) { + 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; + kvm_x86_call(inject_nmi)(vcpu); + can_inject = false; + WARN_ON(kvm_x86_call(nmi_allowed)(vcpu, true) < 0); } - if (kvm_x86_ops->interrupt_allowed(vcpu)) { - kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), - false); - kvm_x86_ops->set_irq(vcpu); + if (vcpu->arch.nmi_pending) + kvm_x86_call(enable_nmi_window)(vcpu); + } + + if (kvm_cpu_has_injectable_intr(vcpu)) { + r = can_inject ? kvm_x86_call(interrupt_allowed)(vcpu, true) : + -EBUSY; + if (r < 0) + goto out; + if (r) { + int irq = kvm_cpu_get_interrupt(vcpu); + + if (!WARN_ON_ONCE(irq == -1)) { + kvm_queue_interrupt(vcpu, irq, false); + kvm_x86_call(inject_irq)(vcpu, false); + WARN_ON(kvm_x86_call(interrupt_allowed)(vcpu, true) < 0); + } } + if (kvm_cpu_has_injectable_intr(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, true)) + *req_immediate_exit = true; + + /* + * KVM must never queue a new exception while injecting an event; KVM + * is done emulating and should only propagate the to-be-injected event + * to the VMCS/VMCB. Queueing a new exception can put the vCPU into an + * infinite loop as KVM will bail from VM-Enter to inject the pending + * exception and start the cycle all over. + * + * Exempt triple faults as they have special handling and won't put the + * vCPU into an infinite loop. Triple fault can be queued when running + * VMX without unrestricted guest, as that requires KVM to emulate Real + * Mode events (see kvm_inject_realmode_interrupt()). + */ + WARN_ON_ONCE(vcpu->arch.exception.pending || + vcpu->arch.exception_vmexit.pending); return 0; + +out: + if (r == -EBUSY) { + *req_immediate_exit = true; + r = 0; + } + return r; } static void process_nmi(struct kvm_vcpu *vcpu) { - unsigned limit = 2; + unsigned int limit; /* - * x86 is limited to one NMI running, and one NMI pending after it. - * If an NMI is already in progress, limit further NMIs to just one. - * Otherwise, allow two (and we'll inject the first one immediately). + * x86 is limited to one NMI pending, but because KVM can't react to + * incoming NMIs as quickly as bare metal, e.g. if the vCPU is + * scheduled out, KVM needs to play nice with two queued NMIs showing + * up at the same time. To handle this scenario, allow two NMIs to be + * (temporarily) pending so long as NMIs are not blocked and KVM is not + * waiting for a previous NMI injection to complete (which effectively + * blocks NMIs). KVM will immediately inject one of the two NMIs, and + * will request an NMI window to handle the second NMI. */ - if (kvm_x86_ops->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; + + /* + * Adjust the limit to account for pending virtual NMIs, which aren't + * tracked in vcpu->arch.nmi_pending. + */ + 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); - kvm_make_request(KVM_REQ_EVENT, vcpu); -} -static u32 enter_smm_get_segment_flags(struct kvm_segment *seg) -{ - u32 flags = 0; - flags |= seg->g << 23; - flags |= seg->db << 22; - flags |= seg->l << 21; - flags |= seg->avl << 20; - flags |= seg->present << 15; - flags |= seg->dpl << 13; - flags |= seg->s << 12; - flags |= seg->type << 8; - return flags; + if (vcpu->arch.nmi_pending && + (kvm_x86_call(set_vnmi_pending)(vcpu))) + vcpu->arch.nmi_pending--; + + if (vcpu->arch.nmi_pending) + kvm_make_request(KVM_REQ_EVENT, vcpu); } -static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n) +/* Return total number of NMIs pending injection to the VM */ +int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu) { - struct kvm_segment seg; - int offset; - - kvm_get_segment(vcpu, &seg, n); - put_smstate(u32, buf, 0x7fa8 + n * 4, seg.selector); - - if (n < 3) - offset = 0x7f84 + n * 12; - else - offset = 0x7f2c + (n - 3) * 12; - - put_smstate(u32, buf, offset + 8, seg.base); - put_smstate(u32, buf, offset + 4, seg.limit); - put_smstate(u32, buf, offset, enter_smm_get_segment_flags(&seg)); + return vcpu->arch.nmi_pending + + kvm_x86_call(is_vnmi_pending)(vcpu); } -#ifdef CONFIG_X86_64 -static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n) +void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, + unsigned long *vcpu_bitmap) { - struct kvm_segment seg; - int offset; - u16 flags; - - kvm_get_segment(vcpu, &seg, n); - offset = 0x7e00 + n * 16; - - flags = enter_smm_get_segment_flags(&seg) >> 8; - put_smstate(u16, buf, offset, seg.selector); - put_smstate(u16, buf, offset + 2, flags); - put_smstate(u32, buf, offset + 4, seg.limit); - put_smstate(u64, buf, offset + 8, seg.base); + kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, vcpu_bitmap); } -#endif -static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf) +void kvm_make_scan_ioapic_request(struct kvm *kvm) { - struct desc_ptr dt; - struct kvm_segment seg; - unsigned long val; - int i; - - put_smstate(u32, buf, 0x7ffc, kvm_read_cr0(vcpu)); - put_smstate(u32, buf, 0x7ff8, kvm_read_cr3(vcpu)); - put_smstate(u32, buf, 0x7ff4, kvm_get_rflags(vcpu)); - put_smstate(u32, buf, 0x7ff0, kvm_rip_read(vcpu)); - - for (i = 0; i < 8; i++) - put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read(vcpu, i)); - - kvm_get_dr(vcpu, 6, &val); - put_smstate(u32, buf, 0x7fcc, (u32)val); - kvm_get_dr(vcpu, 7, &val); - put_smstate(u32, buf, 0x7fc8, (u32)val); - - kvm_get_segment(vcpu, &seg, VCPU_SREG_TR); - put_smstate(u32, buf, 0x7fc4, seg.selector); - put_smstate(u32, buf, 0x7f64, seg.base); - put_smstate(u32, buf, 0x7f60, seg.limit); - put_smstate(u32, buf, 0x7f5c, enter_smm_get_segment_flags(&seg)); - - kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR); - put_smstate(u32, buf, 0x7fc0, seg.selector); - put_smstate(u32, buf, 0x7f80, seg.base); - put_smstate(u32, buf, 0x7f7c, seg.limit); - put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg)); - - kvm_x86_ops->get_gdt(vcpu, &dt); - put_smstate(u32, buf, 0x7f74, dt.address); - put_smstate(u32, buf, 0x7f70, dt.size); - - kvm_x86_ops->get_idt(vcpu, &dt); - put_smstate(u32, buf, 0x7f58, dt.address); - put_smstate(u32, buf, 0x7f54, dt.size); - - for (i = 0; i < 6; i++) - enter_smm_save_seg_32(vcpu, buf, i); - - put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu)); - - /* revision id */ - put_smstate(u32, buf, 0x7efc, 0x00020000); - put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase); + kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); } -static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) +void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) { -#ifdef CONFIG_X86_64 - struct desc_ptr dt; - struct kvm_segment seg; - unsigned long val; - int i; - - for (i = 0; i < 16; i++) - put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read(vcpu, i)); - - put_smstate(u64, buf, 0x7f78, kvm_rip_read(vcpu)); - put_smstate(u32, buf, 0x7f70, kvm_get_rflags(vcpu)); - - kvm_get_dr(vcpu, 6, &val); - put_smstate(u64, buf, 0x7f68, val); - kvm_get_dr(vcpu, 7, &val); - put_smstate(u64, buf, 0x7f60, val); - - put_smstate(u64, buf, 0x7f58, kvm_read_cr0(vcpu)); - put_smstate(u64, buf, 0x7f50, kvm_read_cr3(vcpu)); - put_smstate(u64, buf, 0x7f48, kvm_read_cr4(vcpu)); + struct kvm_lapic *apic = vcpu->arch.apic; + bool activate; - put_smstate(u32, buf, 0x7f00, vcpu->arch.smbase); - - /* revision id */ - put_smstate(u32, buf, 0x7efc, 0x00020064); + if (!lapic_in_kernel(vcpu)) + return; - put_smstate(u64, buf, 0x7ed0, vcpu->arch.efer); + down_read(&vcpu->kvm->arch.apicv_update_lock); + preempt_disable(); - kvm_get_segment(vcpu, &seg, VCPU_SREG_TR); - put_smstate(u16, buf, 0x7e90, seg.selector); - put_smstate(u16, buf, 0x7e92, enter_smm_get_segment_flags(&seg) >> 8); - put_smstate(u32, buf, 0x7e94, seg.limit); - put_smstate(u64, buf, 0x7e98, seg.base); + /* Do not activate APICV when APIC is disabled */ + activate = kvm_vcpu_apicv_activated(vcpu) && + (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED); - kvm_x86_ops->get_idt(vcpu, &dt); - put_smstate(u32, buf, 0x7e84, dt.size); - put_smstate(u64, buf, 0x7e88, dt.address); + if (apic->apicv_active == activate) + goto out; - kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR); - put_smstate(u16, buf, 0x7e70, seg.selector); - put_smstate(u16, buf, 0x7e72, enter_smm_get_segment_flags(&seg) >> 8); - put_smstate(u32, buf, 0x7e74, seg.limit); - put_smstate(u64, buf, 0x7e78, seg.base); + apic->apicv_active = activate; + kvm_apic_update_apicv(vcpu); + kvm_x86_call(refresh_apicv_exec_ctrl)(vcpu); - kvm_x86_ops->get_gdt(vcpu, &dt); - put_smstate(u32, buf, 0x7e64, dt.size); - put_smstate(u64, buf, 0x7e68, dt.address); + /* + * When APICv gets disabled, we may still have injected interrupts + * pending. At the same time, KVM_REQ_EVENT may not be set as APICv was + * still active when the interrupt got accepted. Make sure + * kvm_check_and_inject_events() is called to check for that. + */ + if (!apic->apicv_active) + kvm_make_request(KVM_REQ_EVENT, vcpu); - for (i = 0; i < 6; i++) - enter_smm_save_seg_64(vcpu, buf, i); -#else - WARN_ON_ONCE(1); -#endif +out: + preempt_enable(); + up_read(&vcpu->kvm->arch.apicv_update_lock); } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_vcpu_update_apicv); -static void enter_smm(struct kvm_vcpu *vcpu) +static void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) { - struct kvm_segment cs, ds; - struct desc_ptr dt; - char buf[512]; - u32 cr0; - - trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true); - memset(buf, 0, 512); - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) - enter_smm_save_state_64(vcpu, buf); - else - enter_smm_save_state_32(vcpu, buf); + if (!lapic_in_kernel(vcpu)) + return; /* - * Give pre_enter_smm() a chance to make ISA-specific changes to the - * vCPU state (e.g. leave guest mode) after we've saved the state into - * the SMM state-save area. + * Due to sharing page tables across vCPUs, the xAPIC memslot must be + * 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 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. */ - kvm_x86_ops->pre_enter_smm(vcpu, buf); - - vcpu->arch.hflags |= HF_SMM_MASK; - kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); - - if (kvm_x86_ops->get_nmi_mask(vcpu)) - vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; - else - kvm_x86_ops->set_nmi_mask(vcpu, true); - - kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); - kvm_rip_write(vcpu, 0x8000); - - cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG); - kvm_x86_ops->set_cr0(vcpu, cr0); - vcpu->arch.cr0 = cr0; - - kvm_x86_ops->set_cr4(vcpu, 0); + if (apic_x2apic_mode(vcpu->arch.apic) && + kvm_x86_ops.allow_apicv_in_x2apic_without_x2apic_virtualization) + kvm_inhibit_apic_access_page(vcpu); - /* Undocumented: IDT limit is set to zero on entry to SMM. */ - dt.address = dt.size = 0; - kvm_x86_ops->set_idt(vcpu, &dt); - - __kvm_set_dr(vcpu, 7, DR7_FIXED_1); + __kvm_vcpu_update_apicv(vcpu); +} - cs.selector = (vcpu->arch.smbase >> 4) & 0xffff; - cs.base = vcpu->arch.smbase; +void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, + enum kvm_apicv_inhibit reason, bool set) +{ + unsigned long old, new; - ds.selector = 0; - ds.base = 0; + lockdep_assert_held_write(&kvm->arch.apicv_update_lock); - cs.limit = ds.limit = 0xffffffff; - cs.type = ds.type = 0x3; - cs.dpl = ds.dpl = 0; - cs.db = ds.db = 0; - cs.s = ds.s = 1; - cs.l = ds.l = 0; - cs.g = ds.g = 1; - cs.avl = ds.avl = 0; - cs.present = ds.present = 1; - cs.unusable = ds.unusable = 0; - cs.padding = ds.padding = 0; + if (!(kvm_x86_ops.required_apicv_inhibits & BIT(reason))) + return; - kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); - kvm_set_segment(vcpu, &ds, VCPU_SREG_DS); - kvm_set_segment(vcpu, &ds, VCPU_SREG_ES); - kvm_set_segment(vcpu, &ds, VCPU_SREG_FS); - kvm_set_segment(vcpu, &ds, VCPU_SREG_GS); - kvm_set_segment(vcpu, &ds, VCPU_SREG_SS); + old = new = kvm->arch.apicv_inhibit_reasons; - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) - kvm_x86_ops->set_efer(vcpu, 0); + set_or_clear_apicv_inhibit(&new, reason, set); - kvm_update_cpuid(vcpu); - kvm_mmu_reset_context(vcpu); + if (!!old != !!new) { + /* + * Kick all vCPUs before setting apicv_inhibit_reasons to avoid + * 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 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 + * servicing the request with a stale apicv_inhibit_reasons. + */ + kvm_make_all_cpus_request(kvm, KVM_REQ_APICV_UPDATE); + kvm->arch.apicv_inhibit_reasons = new; + if (new) { + unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE); + int idx = srcu_read_lock(&kvm->srcu); + + kvm_zap_gfn_range(kvm, gfn, gfn+1); + srcu_read_unlock(&kvm->srcu, idx); + } + } else { + kvm->arch.apicv_inhibit_reasons = new; + } } -static void process_smi(struct kvm_vcpu *vcpu) +void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, + enum kvm_apicv_inhibit reason, bool set) { - vcpu->arch.smi_pending = true; - kvm_make_request(KVM_REQ_EVENT, vcpu); -} + if (!enable_apicv) + return; -void kvm_make_scan_ioapic_request(struct kvm *kvm) -{ - kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); + down_write(&kvm->arch.apicv_update_lock); + __kvm_set_or_clear_apicv_inhibit(kvm, reason, set); + up_write(&kvm->arch.apicv_update_lock); } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_or_clear_apicv_inhibit); static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { @@ -7547,15 +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 { - if (vcpu->arch.apicv_active) - kvm_x86_ops->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; @@ -7565,63 +10997,39 @@ 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; - bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, - vcpu_to_synic(vcpu)->vec_bitmap, 256); - kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); +#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); + kvm_x86_call(load_eoi_exitmap)(vcpu, eoi_exit_bitmap); + return; + } +#endif + kvm_x86_call(load_eoi_exitmap)( + vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors); } -int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, - unsigned long start, unsigned long end, - bool blockable) +void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) { - unsigned long apic_address; - - /* - * The physical address of apic access page is stored in the VMCS. - * Update it when it becomes invalid. - */ - apic_address = gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); - if (start <= apic_address && apic_address < end) - kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); - - return 0; + kvm_x86_call(guest_memory_reclaimed)(kvm); } -void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) +static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) { - struct page *page = NULL; - if (!lapic_in_kernel(vcpu)) return; - if (!kvm_x86_ops->set_apic_access_page_addr) - return; - - page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); - if (is_error_page(page)) - return; - kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page)); - - /* - * Do not pin apic access page in memory, the MMU notifier - * will call us again if it is migrated or swapped out. - */ - put_page(page); -} -EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page); - -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. * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the * userspace. @@ -7632,18 +11040,34 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) bool req_int_win = 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; if (kvm_request_pending(vcpu)) { - if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) - kvm_x86_ops->get_vmcs12_pages(vcpu); - if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) - kvm_mmu_unload(vcpu); + if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) { + r = -EIO; + goto out; + } + + if (kvm_dirty_ring_check_request(vcpu)) { + r = 0; + goto out; + } + + if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { + if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) { + r = 0; + goto out; + } + } + if (kvm_check_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu)) + kvm_mmu_free_obsolete_roots(vcpu); if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu)) __kvm_migrate_timers(vcpu); if (kvm_check_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu)) - kvm_gen_update_masterclock(vcpu->kvm); + kvm_update_masterclock(vcpu->kvm); if (kvm_check_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu)) kvm_gen_kvmclock_update(vcpu); if (kvm_check_request(KVM_REQ_CLOCK_UPDATE, vcpu)) { @@ -7653,20 +11077,46 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu)) kvm_mmu_sync_roots(vcpu); - if (kvm_check_request(KVM_REQ_LOAD_CR3, vcpu)) - kvm_mmu_load_cr3(vcpu); + if (kvm_check_request(KVM_REQ_LOAD_MMU_PGD, vcpu)) + kvm_mmu_load_pgd(vcpu); + + /* + * Note, the order matters here, as flushing "all" TLB entries + * also flushes the "current" TLB entries, i.e. servicing the + * flush "all" will clear any request to flush "current". + */ if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) - kvm_vcpu_flush_tlb(vcpu, true); + kvm_vcpu_flush_tlb_all(vcpu); + + kvm_service_local_tlb_flush_requests(vcpu); + + /* + * Fall back to a "full" guest flush if Hyper-V's precise + * flushing fails. Note, Hyper-V's flushing is per-vCPU, but + * 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; r = 0; goto out; } - if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { - vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; - vcpu->mmio_needed = 0; - r = 0; - goto out; + if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + if (is_guest_mode(vcpu)) + kvm_x86_ops.nested_ops->triple_fault(vcpu); + + if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; + vcpu->mmio_needed = 0; + r = 0; + goto out; + } } if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) { /* Page is swapped out. Do synthetic halt */ @@ -7676,14 +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_SMI, vcpu)) - process_smi(vcpu); - 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); +#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_IOAPIC_EOI_EXIT, vcpu)) { BUG_ON(vcpu->arch.pending_ioapic_eoi > 255); if (test_bit(vcpu->arch.pending_ioapic_eoi, @@ -7701,21 +11153,26 @@ 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; + vcpu->run->system_event.ndata = 0; r = 0; goto out; } if (kvm_check_request(KVM_REQ_HV_RESET, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_RESET; + vcpu->run->system_event.ndata = 0; r = 0; goto out; } if (kvm_check_request(KVM_REQ_HV_EXIT, vcpu)) { + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + vcpu->run->exit_reason = KVM_EXIT_HYPERV; - vcpu->run->hyperv = vcpu->arch.hyperv.exit; + vcpu->run->hyperv = hv_vcpu->exit; r = 0; goto out; } @@ -7727,42 +11184,47 @@ 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_RECALC_INTERCEPTS, vcpu)) + kvm_x86_call(recalc_intercepts)(vcpu); + + if (kvm_check_request(KVM_REQ_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) { + if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win || + kvm_xen_has_interrupt(vcpu)) { ++vcpu->stat.req_event; - kvm_apic_accept_events(vcpu); + r = kvm_apic_accept_events(vcpu); + if (r < 0) { + r = 0; + goto out; + } if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { r = 1; goto out; } - if (inject_pending_event(vcpu, req_int_win) != 0) - req_immediate_exit = true; - else { - /* Enable SMI/NMI/IRQ window open exits if needed. - * - * SMIs have three cases: - * 1) They can be nested, and then there is nothing to - * do here because RSM will cause a vmexit anyway. - * 2) There is an ISA-specific reason why SMI cannot be - * injected, and the moment when this changes can be - * intercepted. - * 3) Or the SMI can be pending because - * inject_pending_event has completed the injection - * of an IRQ or NMI from the previous vmexit, and - * then we request an immediate exit to inject the - * SMI. - */ - if (vcpu->arch.smi_pending && !is_smm(vcpu)) - if (!kvm_x86_ops->enable_smi_window(vcpu)) - req_immediate_exit = true; - if (vcpu->arch.nmi_pending) - kvm_x86_ops->enable_nmi_window(vcpu); - if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) - kvm_x86_ops->enable_irq_window(vcpu); - WARN_ON(vcpu->arch.exception.pending); + r = kvm_check_and_inject_events(vcpu, &req_immediate_exit); + if (r < 0) { + r = 0; + goto out; } + if (req_int_win) + kvm_x86_call(enable_irq_window)(vcpu); if (kvm_lapic_enabled(vcpu)) { update_cr8_intercept(vcpu); @@ -7777,7 +11239,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) preempt_disable(); - kvm_x86_ops->prepare_guest_switch(vcpu); + kvm_x86_call(prepare_switch_to_guest)(vcpu); /* * Disable IRQs before setting IN_GUEST_MODE. Posted interrupt @@ -7785,15 +11247,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * result in virtual interrupt delivery. */ local_irq_disable(); - vcpu->mode = IN_GUEST_MODE; - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + /* Store vcpu->apicv_active before vcpu->mode. */ + smp_store_release(&vcpu->mode, IN_GUEST_MODE); + + kvm_vcpu_srcu_read_unlock(vcpu); /* * 1) We should set ->mode before checking ->requests. Please see * the comment in kvm_vcpu_exiting_guest_mode(). * - * 2) For APICv, we should set ->mode before checking PIR.ON. This + * 2) For APICv, we should set ->mode before checking PID.ON. This * pairs with the memory barrier implicit in pi_test_and_set_on * (see vmx_deliver_posted_interrupt). * @@ -7804,46 +11268,103 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) smp_mb__after_srcu_read_unlock(); /* - * This handles the case where a posted interrupt was - * notified with kvm_vcpu_kick. + * Process pending posted interrupts to handle the case where the + * notification IRQ arrived in the host, or was never sent (because the + * target vCPU wasn't running). Do this regardless of the vCPU's APICv + * status, KVM doesn't update assigned devices when APICv is inhibited, + * i.e. they can post interrupts even if APICv is temporarily disabled. */ - if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active) - kvm_x86_ops->sync_pir_to_irr(vcpu); + if (kvm_lapic_enabled(vcpu)) + kvm_x86_call(sync_pir_to_irr)(vcpu); - if (vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) - || need_resched() || signal_pending(current)) { + if (kvm_vcpu_exit_request(vcpu)) { vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); local_irq_enable(); preempt_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); r = 1; goto cancel_injection; } - kvm_load_guest_xcr0(vcpu); - + run_flags = 0; if (req_immediate_exit) { + run_flags |= KVM_RUN_FORCE_IMMEDIATE_EXIT; kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_x86_ops->request_immediate_exit(vcpu); } - trace_kvm_entry(vcpu->vcpu_id); - if (lapic_timer_advance_ns) - wait_lapic_expire(vcpu); - guest_enter_irqoff(); + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); + + if (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); - set_debugreg(vcpu->arch.dr6, 6); - vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; + /* 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(DR7_FIXED_1, 7); } - kvm_x86_ops->run(vcpu); + /* + * 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 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 = kvm_x86_call(vcpu_run)(vcpu, run_flags); + if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) + break; + + if (kvm_lapic_enabled(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 @@ -7853,11 +11374,10 @@ 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); - kvm_x86_ops->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_dr6(vcpu); kvm_update_dr7(vcpu); - vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } /* @@ -7870,30 +11390,74 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (hw_breakpoint_active()) hw_breakpoint_restore(); + vcpu->arch.last_vmentry_cpu = vcpu->cpu; vcpu->arch.last_guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_put_guest_xcr0(vcpu); + kvm_load_xfeatures(vcpu, false); - kvm_before_interrupt(vcpu); - kvm_x86_ops->handle_external_intr(vcpu); - kvm_after_interrupt(vcpu); + /* + * Sync xfd before calling handle_exit_irqoff() which may + * rely on the fact that guest_fpu::xfd is up-to-date (e.g. + * in #NM irqoff handler). + */ + if (vcpu->arch.xfd_no_write_intercept) + fpu_sync_guest_vmexit_xfd_state(); + + kvm_x86_call(handle_exit_irqoff)(vcpu); + + if (vcpu->arch.guest_fpu.xfd_err) + 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 + * VM-Exit on SVM and any ticks that occur between VM-Exit and now. + * An instruction is required after local_irq_enable() to fully unblock + * interrupts on processors that implement an interrupt shadow, the + * stat.exits increment will do nicely. + */ + kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); + local_irq_enable(); ++vcpu->stat.exits; + local_irq_disable(); + kvm_after_interrupt(vcpu); - guest_exit_irqoff(); + /* + * Wait until after servicing IRQs to account guest time so that any + * ticks that occurred while running the guest are properly accounted + * to the guest. Waiting until IRQs are enabled degrades the accuracy + * of accounting via context tracking, but the loss of accuracy is + * acceptable for all known use cases. + */ + guest_timing_exit_irqoff(); local_irq_enable(); preempt_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + 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); } @@ -7904,79 +11468,179 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (vcpu->arch.apic_attention) kvm_lapic_sync_from_vapic(vcpu); - vcpu->arch.gpa_available = false; - r = kvm_x86_ops->handle_exit(vcpu); + if (unlikely(exit_fastpath == EXIT_FASTPATH_EXIT_USERSPACE)) + return 0; + + r = kvm_x86_call(handle_exit)(vcpu, exit_fastpath); return r; cancel_injection: - kvm_x86_ops->cancel_injection(vcpu); + if (req_immediate_exit) + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_x86_call(cancel_injection)(vcpu); if (unlikely(vcpu->arch.apic_attention)) kvm_lapic_sync_from_vapic(vcpu); out: return r; } -static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) +static bool kvm_vcpu_running(struct kvm_vcpu *vcpu) { - if (!kvm_arch_vcpu_runnable(vcpu) && - (!kvm_x86_ops->pre_block || kvm_x86_ops->pre_block(vcpu) == 0)) { - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - kvm_vcpu_block(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && + !vcpu->arch.apf.halted); +} - if (kvm_x86_ops->post_block) - kvm_x86_ops->post_block(vcpu); +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_check_request(KVM_REQ_UNHALT, vcpu)) + 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) +{ + bool hv_timer; + + if (!kvm_arch_vcpu_runnable(vcpu)) { + /* + * Switch to the software timer before halt-polling/blocking as + * the guest's timer may be a break event for the vCPU, and the + * hypervisor timer runs only when the CPU is in guest mode. + * Switch before halt-polling so that KVM recognizes an expired + * timer before blocking. + */ + hv_timer = kvm_lapic_hv_timer_in_use(vcpu); + if (hv_timer) + kvm_lapic_switch_to_sw_timer(vcpu); + + kvm_vcpu_srcu_read_unlock(vcpu); + if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) + kvm_vcpu_halt(vcpu); + else + kvm_vcpu_block(vcpu); + kvm_vcpu_srcu_read_lock(vcpu); + + if (hv_timer) + kvm_lapic_switch_to_hv_timer(vcpu); + + /* + * If the vCPU is not runnable, a signal or another host event + * of some kind is pending; service it without changing the + * vCPU's activity state. + */ + if (!kvm_arch_vcpu_runnable(vcpu)) return 1; } - kvm_apic_accept_events(vcpu); + /* + * Evaluate nested events before exiting the halted state. This allows + * the halt state to be recorded properly in the VMCS12's activity + * state field (AMD does not have a similar field and a VM-Exit always + * causes a spurious wakeup from HLT). + */ + if (is_guest_mode(vcpu)) { + int r = kvm_check_nested_events(vcpu); + + WARN_ON_ONCE(r == -EBUSY); + if (r < 0) + return 0; + } + + if (kvm_apic_accept_events(vcpu) < 0) + return 0; switch(vcpu->arch.mp_state) { case KVM_MP_STATE_HALTED: - vcpu->arch.pv.pv_unhalted = false; - vcpu->arch.mp_state = - KVM_MP_STATE_RUNNABLE; + case KVM_MP_STATE_AP_RESET_HOLD: + kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); + fallthrough; case KVM_MP_STATE_RUNNABLE: vcpu->arch.apf.halted = false; break; case KVM_MP_STATE_INIT_RECEIVED: break; default: - return -EINTR; + WARN_ON_ONCE(1); break; } return 1; } -static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) -{ - if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) - kvm_x86_ops->check_nested_events(vcpu, false); - - return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && - !vcpu->arch.apf.halted); -} - +/* Called within kvm->srcu read side. */ static int vcpu_run(struct kvm_vcpu *vcpu) { int r; - struct kvm *kvm = vcpu->kvm; - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - vcpu->arch.l1tf_flush_l1d = true; + vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; for (;;) { + /* + * If another guest vCPU requests a PV TLB flush in the middle + * of instruction emulation, the rest of the emulation could + * use a stale page translation. Assume that any code after + * this point can start executing an instruction. + */ + vcpu->arch.at_instruction_boundary = false; if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); } else { - r = vcpu_block(kvm, vcpu); + r = vcpu_block(vcpu); } if (r <= 0) break; - kvm_clear_request(KVM_REQ_PENDING_TIMER, vcpu); + kvm_clear_request(KVM_REQ_UNBLOCK, vcpu); + if (kvm_xen_has_pending_events(vcpu)) + kvm_xen_inject_pending_events(vcpu); + if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); @@ -7988,35 +11652,106 @@ static int vcpu_run(struct kvm_vcpu *vcpu) break; } - kvm_check_async_pf_completion(vcpu); - - if (signal_pending(current)) { - r = -EINTR; - vcpu->run->exit_reason = KVM_EXIT_INTR; - ++vcpu->stat.signal_exits; - break; - } - if (need_resched()) { - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - cond_resched(); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + if (__xfer_to_guest_mode_work_pending()) { + kvm_vcpu_srcu_read_unlock(vcpu); + r = kvm_xfer_to_guest_mode_handle_work(vcpu); + kvm_vcpu_srcu_read_lock(vcpu); + if (r) + return r; } } - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - return r; } -static inline int complete_emulated_io(struct kvm_vcpu *vcpu) +static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) { - int r; - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - if (r != EMULATE_DONE) + /* + * 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; - return 1; + } +} + +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); } static int complete_emulated_pio(struct kvm_vcpu *vcpu) @@ -8092,57 +11827,105 @@ 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) { - preempt_disable(); - copy_fpregs_to_fpstate(¤t->thread.fpu); - /* PKRU is separately restored in kvm_x86_ops->run. */ - __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state, - ~XFEATURE_MASK_PKRU); - preempt_enable(); + 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); } /* When vcpu_run ends, restore user space FPU context. */ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { - preempt_disable(); - copy_fpregs_to_fpstate(vcpu->arch.guest_fpu); - copy_kernel_to_fpregs(¤t->thread.fpu.state); - preempt_enable(); + 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); } -int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +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; kvm_load_guest_fpu(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; } + + /* + * 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). + */ + kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_block(vcpu); - kvm_apic_accept_events(vcpu); - kvm_clear_request(KVM_REQ_UNHALT, vcpu); + kvm_vcpu_srcu_read_lock(vcpu); + + if (kvm_apic_accept_events(vcpu) < 0) { + r = 0; + goto out; + } r = -EAGAIN; if (signal_pending(current)) { r = -EINTR; - vcpu->run->exit_reason = KVM_EXIT_INTR; + kvm_run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.signal_exits; } goto out; } - if (vcpu->run->kvm_valid_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; } - if (vcpu->run->kvm_dirty_regs) { + if (kvm_run->kvm_dirty_regs) { r = sync_regs(vcpu); if (r != 0) goto out; @@ -8156,27 +11939,51 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } } + /* + * If userspace set a pending exception and L2 is active, convert it to + * a pending VM-Exit if L1 wants to intercept the exception. + */ + if (vcpu->arch.exception_from_userspace && is_guest_mode(vcpu) && + kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, ex->vector, + ex->error_code)) { + kvm_queue_exception_vmexit(vcpu, ex->vector, + ex->has_error_code, ex->error_code, + ex->has_payload, ex->payload); + ex->injected = false; + ex->pending = false; + } + vcpu->arch.exception_from_userspace = false; + if (unlikely(vcpu->arch.complete_userspace_io)) { int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io; vcpu->arch.complete_userspace_io = NULL; r = cui(vcpu); if (r <= 0) goto out; - } else - WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed); + } else { + WARN_ON_ONCE(vcpu->arch.pio.count); + WARN_ON_ONCE(vcpu->mmio_needed); + } - if (kvm_run->immediate_exit) + if (!vcpu->wants_to_run) { r = -EINTR; - else - r = vcpu_run(vcpu); + goto out; + } + + r = kvm_x86_vcpu_pre_run(vcpu); + if (r <= 0) + goto out; + + r = vcpu_run(vcpu); out: kvm_put_guest_fpu(vcpu); - if (vcpu->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_sigset_deactivate(vcpu); + kvm_vcpu_srcu_read_unlock(vcpu); + kvm_sigset_deactivate(vcpu); vcpu_put(vcpu); return r; } @@ -8191,26 +11998,26 @@ static void __get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) * that usually, but some bad designed PV devices (vmware * backdoor interface) need this to work */ - emulator_writeback_register_cache(&vcpu->arch.emulate_ctxt); + emulator_writeback_register_cache(vcpu->arch.emulate_ctxt); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; } - regs->rax = kvm_register_read(vcpu, VCPU_REGS_RAX); - regs->rbx = kvm_register_read(vcpu, VCPU_REGS_RBX); - regs->rcx = kvm_register_read(vcpu, VCPU_REGS_RCX); - regs->rdx = kvm_register_read(vcpu, VCPU_REGS_RDX); - regs->rsi = kvm_register_read(vcpu, VCPU_REGS_RSI); - regs->rdi = kvm_register_read(vcpu, VCPU_REGS_RDI); - regs->rsp = kvm_register_read(vcpu, VCPU_REGS_RSP); - regs->rbp = kvm_register_read(vcpu, VCPU_REGS_RBP); + regs->rax = kvm_rax_read(vcpu); + regs->rbx = kvm_rbx_read(vcpu); + regs->rcx = kvm_rcx_read(vcpu); + regs->rdx = kvm_rdx_read(vcpu); + regs->rsi = kvm_rsi_read(vcpu); + regs->rdi = kvm_rdi_read(vcpu); + regs->rsp = kvm_rsp_read(vcpu); + regs->rbp = kvm_rbp_read(vcpu); #ifdef CONFIG_X86_64 - regs->r8 = kvm_register_read(vcpu, VCPU_REGS_R8); - regs->r9 = kvm_register_read(vcpu, VCPU_REGS_R9); - regs->r10 = kvm_register_read(vcpu, VCPU_REGS_R10); - regs->r11 = kvm_register_read(vcpu, VCPU_REGS_R11); - regs->r12 = kvm_register_read(vcpu, VCPU_REGS_R12); - regs->r13 = kvm_register_read(vcpu, VCPU_REGS_R13); - regs->r14 = kvm_register_read(vcpu, VCPU_REGS_R14); - regs->r15 = kvm_register_read(vcpu, VCPU_REGS_R15); + regs->r8 = kvm_r8_read(vcpu); + regs->r9 = kvm_r9_read(vcpu); + regs->r10 = kvm_r10_read(vcpu); + regs->r11 = kvm_r11_read(vcpu); + regs->r12 = kvm_r12_read(vcpu); + regs->r13 = kvm_r13_read(vcpu); + regs->r14 = kvm_r14_read(vcpu); + regs->r15 = kvm_r15_read(vcpu); #endif regs->rip = kvm_rip_read(vcpu); @@ -8219,6 +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); @@ -8230,55 +12041,53 @@ static void __set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) vcpu->arch.emulate_regs_need_sync_from_vcpu = true; vcpu->arch.emulate_regs_need_sync_to_vcpu = false; - kvm_register_write(vcpu, VCPU_REGS_RAX, regs->rax); - kvm_register_write(vcpu, VCPU_REGS_RBX, regs->rbx); - kvm_register_write(vcpu, VCPU_REGS_RCX, regs->rcx); - kvm_register_write(vcpu, VCPU_REGS_RDX, regs->rdx); - kvm_register_write(vcpu, VCPU_REGS_RSI, regs->rsi); - kvm_register_write(vcpu, VCPU_REGS_RDI, regs->rdi); - kvm_register_write(vcpu, VCPU_REGS_RSP, regs->rsp); - kvm_register_write(vcpu, VCPU_REGS_RBP, regs->rbp); + kvm_rax_write(vcpu, regs->rax); + kvm_rbx_write(vcpu, regs->rbx); + kvm_rcx_write(vcpu, regs->rcx); + kvm_rdx_write(vcpu, regs->rdx); + kvm_rsi_write(vcpu, regs->rsi); + kvm_rdi_write(vcpu, regs->rdi); + kvm_rsp_write(vcpu, regs->rsp); + kvm_rbp_write(vcpu, regs->rbp); #ifdef CONFIG_X86_64 - kvm_register_write(vcpu, VCPU_REGS_R8, regs->r8); - kvm_register_write(vcpu, VCPU_REGS_R9, regs->r9); - kvm_register_write(vcpu, VCPU_REGS_R10, regs->r10); - kvm_register_write(vcpu, VCPU_REGS_R11, regs->r11); - kvm_register_write(vcpu, VCPU_REGS_R12, regs->r12); - kvm_register_write(vcpu, VCPU_REGS_R13, regs->r13); - kvm_register_write(vcpu, VCPU_REGS_R14, regs->r14); - kvm_register_write(vcpu, VCPU_REGS_R15, regs->r15); + kvm_r8_write(vcpu, regs->r8); + kvm_r9_write(vcpu, regs->r9); + kvm_r10_write(vcpu, regs->r10); + kvm_r11_write(vcpu, regs->r11); + kvm_r12_write(vcpu, regs->r12); + kvm_r13_write(vcpu, regs->r13); + kvm_r14_write(vcpu, regs->r14); + kvm_r15_write(vcpu, regs->r15); #endif kvm_rip_write(vcpu, regs->rip); kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED); vcpu->arch.exception.pending = false; + vcpu->arch.exception_vmexit.pending = false; kvm_make_request(KVM_REQ_EVENT, vcpu); } 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); return 0; } -void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) -{ - struct kvm_segment cs; - - kvm_get_segment(vcpu, &cs, VCPU_SREG_CS); - *db = cs.db; - *l = cs.l; -} -EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits); - -static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static void __get_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { struct desc_ptr dt; + if (vcpu->arch.guest_state_protected) + goto skip_protected_regs; + kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS); kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS); kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES); @@ -8289,31 +12098,59 @@ static void __get_sregs(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); - kvm_x86_ops->get_idt(vcpu, &dt); + kvm_x86_call(get_idt)(vcpu, &dt); sregs->idt.limit = dt.size; sregs->idt.base = dt.address; - kvm_x86_ops->get_gdt(vcpu, &dt); + kvm_x86_call(get_gdt)(vcpu, &dt); sregs->gdt.limit = dt.size; sregs->gdt.base = dt.address; - sregs->cr0 = kvm_read_cr0(vcpu); sregs->cr2 = vcpu->arch.cr2; sregs->cr3 = kvm_read_cr3(vcpu); + +skip_protected_regs: + sregs->cr0 = kvm_read_cr0(vcpu); 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) +{ + __get_sregs_common(vcpu, sregs); - memset(sregs->interrupt_bitmap, 0, sizeof(sregs->interrupt_bitmap)); + if (vcpu->arch.guest_state_protected) + return; if (vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft) set_bit(vcpu->arch.interrupt.nr, (unsigned long *)sregs->interrupt_bitmap); } +static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) +{ + int i; + + __get_sregs_common(vcpu, (struct kvm_sregs *)sregs2); + + if (vcpu->arch.guest_state_protected) + return; + + if (is_pae_paging(vcpu)) { + for (i = 0 ; i < 4 ; i++) + sregs2->pdptrs[i] = kvm_pdptr_read(vcpu, i); + sregs2->flags |= KVM_SREGS2_FLAGS_PDPTRS_VALID; + } +} + 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); @@ -8323,17 +12160,27 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { + int r; + vcpu_load(vcpu); + kvm_vcpu_srcu_read_lock(vcpu); + + r = kvm_apic_accept_events(vcpu); + if (r < 0) + goto out; + r = 0; - kvm_apic_accept_events(vcpu); - if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && - vcpu->arch.pv.pv_unhalted) + if ((vcpu->arch.mp_state == KVM_MP_STATE_HALTED || + vcpu->arch.mp_state == KVM_MP_STATE_AP_RESET_HOLD) && + vcpu->arch.pv.pv_unhalted) mp_state->mp_state = KVM_MP_STATE_RUNNABLE; else mp_state->mp_state = vcpu->arch.mp_state; +out: + kvm_vcpu_srcu_read_unlock(vcpu); vcpu_put(vcpu); - return 0; + return r; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, @@ -8343,21 +12190,34 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, vcpu_load(vcpu); - if (!lapic_in_kernel(vcpu) && - mp_state->mp_state != KVM_MP_STATE_RUNNABLE) - goto out; + switch (mp_state->mp_state) { + case KVM_MP_STATE_UNINITIALIZED: + case KVM_MP_STATE_HALTED: + case KVM_MP_STATE_AP_RESET_HOLD: + case KVM_MP_STATE_INIT_RECEIVED: + case KVM_MP_STATE_SIPI_RECEIVED: + if (!lapic_in_kernel(vcpu)) + goto out; + break; - /* INITs are latched while in SMM */ - if ((is_smm(vcpu) || vcpu->arch.smi_pending) && - (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED || - mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED)) + case KVM_MP_STATE_RUNNABLE: + break; + + default: goto out; + } + /* + * 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 (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; @@ -8369,112 +12229,124 @@ out: int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code) { - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + 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) - return EMULATE_FAIL; + /* + * 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); - kvm_make_request(KVM_REQ_EVENT, vcpu); - return EMULATE_DONE; + 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 int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - (sregs->cr4 & X86_CR4_OSXSAVE)) - return -EINVAL; - if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) { /* * When EFER.LME and CR0.PG are set, the processor is in * 64-bit mode (though maybe in a 32-bit code segment). * CR4.PAE and EFER.LMA must be set. */ - if (!(sregs->cr4 & X86_CR4_PAE) - || !(sregs->efer & EFER_LMA)) - return -EINVAL; + if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) + return false; + if (!kvm_vcpu_is_legal_cr3(vcpu, sregs->cr3)) + return false; } else { /* * Not in 64-bit mode: EFER.LMA is clear and the code * segment cannot be 64-bit. */ if (sregs->efer & EFER_LMA || sregs->cs.l) - return -EINVAL; + return false; } - return 0; + return kvm_is_valid_cr4(vcpu, sregs->cr4) && + kvm_is_valid_cr0(vcpu, sregs->cr0); } -static int __set_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 mmu_reset_needed = 0; - int cpuid_update_needed = 0; - int pending_vec, max_bits, idx; + int idx; struct desc_ptr dt; - int ret = -EINVAL; - if (kvm_valid_sregs(vcpu, sregs)) - goto out; + 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)) - goto out; + if (kvm_apic_set_base(vcpu, sregs->apic_base, true)) + return -EINVAL; + + if (vcpu->arch.guest_state_protected) + return 0; dt.size = sregs->idt.limit; dt.address = sregs->idt.base; - kvm_x86_ops->set_idt(vcpu, &dt); + kvm_x86_call(set_idt)(vcpu, &dt); dt.size = sregs->gdt.limit; dt.address = sregs->gdt.base; - kvm_x86_ops->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; + *mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); + kvm_x86_call(post_set_cr3)(vcpu, sregs->cr3); kvm_set_cr8(vcpu, sregs->cr8); - mmu_reset_needed |= vcpu->arch.efer != sregs->efer; - kvm_x86_ops->set_efer(vcpu, sregs->efer); - - mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; - kvm_x86_ops->set_cr0(vcpu, sregs->cr0); - vcpu->arch.cr0 = sregs->cr0; + *mmu_reset_needed |= vcpu->arch.efer != sregs->efer; + kvm_x86_call(set_efer)(vcpu, sregs->efer); - mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; - cpuid_update_needed |= ((kvm_read_cr4(vcpu) ^ sregs->cr4) & - (X86_CR4_OSXSAVE | X86_CR4_PKE)); - kvm_x86_ops->set_cr4(vcpu, sregs->cr4); - if (cpuid_update_needed) - kvm_update_cpuid(vcpu); - - idx = srcu_read_lock(&vcpu->kvm->srcu); - if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu)) { - load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); - mmu_reset_needed = 1; - } - srcu_read_unlock(&vcpu->kvm->srcu, idx); + *mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; + kvm_x86_call(set_cr0)(vcpu, sregs->cr0); - if (mmu_reset_needed) - kvm_mmu_reset_context(vcpu); + *mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; + kvm_x86_call(set_cr4)(vcpu, sregs->cr4); - max_bits = KVM_NR_INTERRUPTS; - pending_vec = find_first_bit( - (const unsigned long *)sregs->interrupt_bitmap, max_bits); - if (pending_vec < max_bits) { - kvm_queue_interrupt(vcpu, pending_vec, false); - pr_debug("Set back pending irq %d\n", pending_vec); + if (update_pdptrs) { + idx = srcu_read_lock(&vcpu->kvm->srcu); + if (is_pae_paging(vcpu)) { + load_pdptrs(vcpu, kvm_read_cr3(vcpu)); + *mmu_reset_needed = 1; + } + srcu_read_unlock(&vcpu->kvm->srcu, idx); } kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); @@ -8493,13 +12365,69 @@ static int __set_sregs(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); - kvm_make_request(KVM_REQ_EVENT, vcpu); + return 0; +} - ret = 0; -out: - return ret; +static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + int pending_vec, max_bits; + int mmu_reset_needed = 0; + int ret = __set_sregs_common(vcpu, sregs, &mmu_reset_needed, true); + + if (ret) + return ret; + + 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( + (const unsigned long *)sregs->interrupt_bitmap, max_bits); + + if (pending_vec < max_bits) { + kvm_queue_interrupt(vcpu, pending_vec, false); + pr_debug("Set back pending irq %d\n", pending_vec); + kvm_make_request(KVM_REQ_EVENT, vcpu); + } + return 0; +} + +static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) +{ + int mmu_reset_needed = 0; + bool valid_pdptrs = sregs2->flags & KVM_SREGS2_FLAGS_PDPTRS_VALID; + bool pae = (sregs2->cr0 & X86_CR0_PG) && (sregs2->cr4 & X86_CR4_PAE) && + !(sregs2->efer & EFER_LMA); + int i, ret; + + if (sregs2->flags & ~KVM_SREGS2_FLAGS_PDPTRS_VALID) + return -EINVAL; + + if (valid_pdptrs && (!pae || vcpu->arch.guest_state_protected)) + return -EINVAL; + + ret = __set_sregs_common(vcpu, (struct kvm_sregs *)sregs2, + &mmu_reset_needed, !valid_pdptrs); + if (ret) + return ret; + + if (valid_pdptrs) { + for (i = 0; i < 4 ; i++) + kvm_pdptr_write(vcpu, i, sregs2->pdptrs[i]); + + kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + mmu_reset_needed = 1; + vcpu->arch.pdptrs_from_userspace = true; + } + if (mmu_reset_needed) { + kvm_mmu_reset_context(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + } + return 0; } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, @@ -8507,23 +12435,51 @@ 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); return ret; } +static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) +{ + bool set = false; + struct kvm_vcpu *vcpu; + unsigned long i; + + if (!enable_apicv) + return; + + down_write(&kvm->arch.apicv_update_lock); + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ) { + set = true; + break; + } + } + __kvm_set_or_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_BLOCKIRQ, set); + up_write(&kvm->arch.apicv_update_lock); +} + int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { unsigned long rflags; int i, r; + if (vcpu->arch.guest_state_protected) + return -EINVAL; + vcpu_load(vcpu); if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) { r = -EBUSY; - if (vcpu->arch.exception.pending) + if (kvm_is_exception_pending(vcpu)) goto out; if (dbg->control & KVM_GUESTDBG_INJECT_DB) kvm_queue_exception(vcpu, DB_VECTOR); @@ -8552,8 +12508,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, kvm_update_dr7(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) + - get_segment_base(vcpu, VCPU_SREG_CS); + vcpu->arch.singlestep_rip = kvm_get_linear_rip(vcpu); /* * Trigger an rflags update that will inject or remove the trace @@ -8561,7 +12516,9 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, */ kvm_set_rflags(vcpu, rflags); - kvm_x86_ops->update_bp_intercept(vcpu); + kvm_x86_call(update_exception_bitmap)(vcpu); + + kvm_arch_vcpu_guestdbg_update_apicv_inhibit(vcpu->kvm); r = 0; @@ -8586,7 +12543,7 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, gpa = kvm_mmu_gva_to_gpa_system(vcpu, vaddr, NULL); srcu_read_unlock(&vcpu->kvm->srcu, idx); tr->physical_address = gpa; - tr->valid = gpa != UNMAPPED_GVA; + tr->valid = gpa != INVALID_GPA; tr->writeable = 1; tr->usermode = 0; @@ -8598,9 +12555,12 @@ 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 vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; + vcpu_load(vcpu); - fxsave = &vcpu->arch.guest_fpu->state.fxsave; + fxsave = &vcpu->arch.guest_fpu.fpstate->regs.fxsave; memcpy(fpu->fpr, fxsave->st_space, 128); fpu->fcw = fxsave->cwd; fpu->fsw = fxsave->swd; @@ -8618,9 +12578,12 @@ 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 vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; + vcpu_load(vcpu); - fxsave = &vcpu->arch.guest_fpu->state.fxsave; + fxsave = &vcpu->arch.guest_fpu.fpstate->regs.fxsave; memcpy(fxsave->st_space, fpu->fpr, 128); fxsave->cwd = fpu->fcw; @@ -8652,118 +12615,264 @@ static void store_regs(struct kvm_vcpu *vcpu) static int sync_regs(struct kvm_vcpu *vcpu) { - if (vcpu->run->kvm_dirty_regs & ~KVM_SYNC_X86_VALID_FIELDS) - return -EINVAL; - if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_REGS) { __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; } return 0; } -static void fx_init(struct kvm_vcpu *vcpu) +int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { - fpstate_init(&vcpu->arch.guest_fpu->state); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - vcpu->arch.guest_fpu->state.xsave.header.xcomp_bv = - host_xcr0 | XSTATE_COMPACTION_ENABLED; + if (kvm_check_tsc_unstable() && kvm->created_vcpus) + pr_warn_once("SMP vm created on host with unstable TSC; " + "guest TSC will not be reliable\n"); - /* - * Ensure guest xcr0 is valid for loading - */ - vcpu->arch.xcr0 = XFEATURE_MASK_FP; + if (!kvm->arch.max_vcpu_ids) + kvm->arch.max_vcpu_ids = KVM_MAX_VCPU_IDS; + + if (id >= kvm->arch.max_vcpu_ids) + return -EINVAL; - vcpu->arch.cr0 |= X86_CR0_ET; + return kvm_x86_call(vcpu_precreate)(kvm); } -void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) +int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { - void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask; + struct page *page; + int r; - kvmclock_reset(vcpu); + vcpu->arch.last_vmentry_cpu = -1; + vcpu->arch.regs_avail = ~0; + vcpu->arch.regs_dirty = ~0; - kvm_x86_ops->vcpu_free(vcpu); - free_cpumask_var(wbinvd_dirty_mask); -} + kvm_gpc_init(&vcpu->arch.pv_time, vcpu->kvm); -struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, - unsigned int id) -{ - struct kvm_vcpu *vcpu; + if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) + kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); + else + kvm_set_mp_state(vcpu, KVM_MP_STATE_UNINITIALIZED); - if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) - printk_once(KERN_WARNING - "kvm: SMP vm created on host with unstable TSC; " - "guest TSC will not be reliable\n"); + r = kvm_mmu_create(vcpu); + if (r < 0) + return r; - vcpu = kvm_x86_ops->vcpu_create(kvm, id); + r = kvm_create_lapic(vcpu); + if (r < 0) + goto fail_mmu_destroy; - return vcpu; -} + r = -ENOMEM; -int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) -{ - vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; - kvm_vcpu_mtrr_init(vcpu); + page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!page) + goto fail_free_lapic; + vcpu->arch.pio_data = page_address(page); + + vcpu->arch.mce_banks = kcalloc(KVM_MAX_MCE_BANKS * 4, sizeof(u64), + GFP_KERNEL_ACCOUNT); + vcpu->arch.mci_ctl2_banks = kcalloc(KVM_MAX_MCE_BANKS, sizeof(u64), + GFP_KERNEL_ACCOUNT); + if (!vcpu->arch.mce_banks || !vcpu->arch.mci_ctl2_banks) + goto fail_free_mce_banks; + vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; + + if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, + GFP_KERNEL_ACCOUNT)) + goto fail_free_mce_banks; + + if (!alloc_emulate_ctxt(vcpu)) + goto free_wbinvd_dirty_mask; + + if (!fpu_alloc_guest_fpstate(&vcpu->arch.guest_fpu)) { + pr_err("failed to allocate vcpu's fpu\n"); + goto free_emulate_ctxt; + } + + kvm_async_pf_hash_reset(vcpu); + + 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; + vcpu->arch.preempted_in_kernel = false; + +#if IS_ENABLED(CONFIG_HYPERV) + vcpu->arch.hv_root_tdp = INVALID_PAGE; +#endif + + r = kvm_x86_call(vcpu_create)(vcpu); + if (r) + goto free_guest_fpu; + + kvm_xen_init_vcpu(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, false); + kvm_init_mmu(vcpu); vcpu_put(vcpu); return 0; + +free_guest_fpu: + fpu_free_guest_fpstate(&vcpu->arch.guest_fpu); +free_emulate_ctxt: + kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); +free_wbinvd_dirty_mask: + free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); +fail_free_mce_banks: + kfree(vcpu->arch.mce_banks); + kfree(vcpu->arch.mci_ctl2_banks); + free_page((unsigned long)vcpu->arch.pio_data); +fail_free_lapic: + kvm_free_lapic(vcpu); +fail_mmu_destroy: + kvm_mmu_destroy(vcpu); + return r; } void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { - struct msr_data msr; - struct kvm *kvm = vcpu->kvm; - - kvm_hv_vcpu_postcreate(vcpu); - if (mutex_lock_killable(&vcpu->mutex)) return; vcpu_load(vcpu); - msr.data = 0x0; - msr.index = MSR_IA32_TSC; - msr.host_initiated = true; - kvm_write_tsc(vcpu, &msr); + kvm_synchronize_tsc(vcpu, NULL); vcpu_put(vcpu); - mutex_unlock(&vcpu->mutex); - if (!kvmclock_periodic_sync) - return; + /* poll control enabled by default */ + vcpu->arch.msr_kvm_poll_control = 1; - schedule_delayed_work(&kvm->arch.kvmclock_sync_work, - KVMCLOCK_SYNC_PERIOD); + mutex_unlock(&vcpu->mutex); } void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - vcpu->arch.apf.msr_val = 0; + int idx, cpu; - vcpu_load(vcpu); + kvm_clear_async_pf_completion_queue(vcpu); kvm_mmu_unload(vcpu); - vcpu_put(vcpu); - kvm_x86_ops->vcpu_free(vcpu); + kvmclock_reset(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); + fpu_free_guest_fpstate(&vcpu->arch.guest_fpu); + + kvm_xen_destroy_vcpu(vcpu); + kvm_hv_vcpu_uninit(vcpu); + kvm_pmu_destroy(vcpu); + kfree(vcpu->arch.mce_banks); + kfree(vcpu->arch.mci_ctl2_banks); + kvm_free_lapic(vcpu); + idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_mmu_destroy(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + free_page((unsigned long)vcpu->arch.pio_data); + kvfree(vcpu->arch.cpuid_entries); +} + +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) { + struct kvm_cpuid_entry2 *cpuid_0x1; + unsigned long old_cr0 = kvm_read_cr0(vcpu); + unsigned long new_cr0; + + /* + * Several of the "set" flows, e.g. ->set_cr0(), read other registers + * to handle side effects. RESET emulation hits those flows and relies + * on emulated/virtualized registers, including those that are loaded + * into hardware, to be zeroed at vCPU creation. Use CRs as a sentinel + * to detect improper or missing initialization. + */ + WARN_ON_ONCE(!init_event && + (old_cr0 || kvm_read_cr3(vcpu) || kvm_read_cr4(vcpu))); + + /* + * SVM doesn't unconditionally VM-Exit on INIT and SHUTDOWN, thus it's + * possible to INIT the vCPU while L2 is active. Force the vCPU back + * into L1 as EFER.SVME is cleared on INIT (along with all other EFER + * bits), i.e. virtualization is disabled. + */ + if (is_guest_mode(vcpu)) + kvm_leave_nested(vcpu); + kvm_lapic_reset(vcpu, init_event); + WARN_ON_ONCE(is_guest_mode(vcpu) || is_smm(vcpu)); vcpu->arch.hflags = 0; vcpu->arch.smi_pending = 0; @@ -8773,19 +12882,18 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.nmi_injected = false; kvm_clear_interrupt_queue(vcpu); kvm_clear_exception_queue(vcpu); - vcpu->arch.exception.pending = false; memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); kvm_update_dr0123(vcpu); - vcpu->arch.dr6 = DR6_INIT; - kvm_update_dr6(vcpu); + vcpu->arch.dr6 = DR6_ACTIVE_LOW; vcpu->arch.dr7 = DR7_FIXED_1; kvm_update_dr7(vcpu); vcpu->arch.cr2 = 0; kvm_make_request(KVM_REQ_EVENT, vcpu); - vcpu->arch.apf.msr_val = 0; + vcpu->arch.apf.msr_en_val = 0; + vcpu->arch.apf.msr_int_val = 0; vcpu->arch.st.msr_val = 0; kvmclock_reset(vcpu); @@ -8794,44 +12902,85 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; - if (kvm_mpx_supported()) { - void *mpx_state_buffer; - - /* - * To avoid have the INIT path from kvm_apic_has_events() that be - * called with loaded FPU and does not let userspace fix the state. - */ - if (init_event) - kvm_put_guest_fpu(vcpu); - mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave, - XFEATURE_MASK_BNDREGS); - if (mpx_state_buffer) - memset(mpx_state_buffer, 0, sizeof(struct mpx_bndreg_state)); - mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave, - XFEATURE_MASK_BNDCSR); - if (mpx_state_buffer) - memset(mpx_state_buffer, 0, sizeof(struct mpx_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; - vcpu->arch.xcr0 = XFEATURE_MASK_FP; + __kvm_set_xcr(vcpu, 0, XFEATURE_MASK_FP); + kvm_msr_write(vcpu, MSR_IA32_XSS, 0); } + /* All GPRs except RDX (handled below) are zeroed on RESET/INIT. */ memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); - vcpu->arch.regs_avail = ~0; - vcpu->arch.regs_dirty = ~0; + kvm_register_mark_dirty(vcpu, VCPU_REGS_RSP); + + /* + * Fall back to KVM's default Family/Model/Stepping of 0x600 (P6/Athlon) + * if no CPUID match is found. Note, it's impossible to get a match at + * RESET since KVM emulates RESET before exposing the vCPU to userspace, + * i.e. it's impossible for kvm_find_cpuid_entry() to find a valid entry + * on RESET. But, go through the motions in case that's ever remedied. + */ + cpuid_0x1 = kvm_find_cpuid_entry(vcpu, 1); + kvm_rdx_write(vcpu, cpuid_0x1 ? cpuid_0x1->eax : 0x600); - vcpu->arch.ia32_xss = 0; + kvm_x86_call(vcpu_reset)(vcpu, init_event); - kvm_x86_ops->vcpu_reset(vcpu, init_event); + kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); + kvm_rip_write(vcpu, 0xfff0); + + vcpu->arch.cr3 = 0; + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); + + /* + * CR0.CD/NW are set on RESET, preserved on INIT. Note, some versions + * of Intel's SDM list CD/NW as being set on INIT, but they contradict + * (or qualify) that with a footnote stating that CD/NW are preserved. + */ + new_cr0 = X86_CR0_ET; + if (init_event) + new_cr0 |= (old_cr0 & (X86_CR0_NW | X86_CR0_CD)); + else + new_cr0 |= X86_CR0_NW | X86_CR0_CD; + + 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 + * complex conditions determining whether the MMU has to be reset and/or + * which PCIDs have to be flushed. However, CR0.WP and the paging-related + * bits in CR4 and EFER are irrelevant if CR0.PG was '0'; and a reset+flush + * is needed anyway if CR0.PG was '1' (which can only happen for INIT, as + * CR0 will be '0' prior to RESET). So we only need to check CR0.PG here. + */ + if (old_cr0 & X86_CR0_PG) { + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + kvm_mmu_reset_context(vcpu); + } + + /* + * Intel's SDM states that all TLB entries are flushed on INIT. AMD's + * APM states the TLBs are untouched by INIT, but it also states that + * the TLBs are flushed on "External initialization of the processor." + * Flush the guest TLB regardless of vendor, there is no meaningful + * benefit in relying on the guest to flush the TLB immediately after + * INIT. A spurious TLB flush is benign and likely negligible from a + * performance perspective. + */ + if (init_event) + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_reset); void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) { @@ -8843,19 +12992,35 @@ 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_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); +} + +void kvm_arch_disable_virtualization(void) +{ + cpu_emergency_unregister_virt_callback(kvm_x86_ops.emergency_disable_virtualization_cpu); +} -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; int ret; u64 local_tsc; u64 max_tsc = 0; bool stable, backwards_tsc = false; - kvm_shared_msr_cpu_online(); - ret = kvm_x86_ops->hardware_enable(); + kvm_user_return_msr_cpu_online(); + + ret = kvm_x86_check_processor_compatibility(); + if (ret) + return ret; + + ret = kvm_x86_call(enable_virtualization_cpu)(); if (ret != 0) return ret; @@ -8881,7 +13046,7 @@ int kvm_arch_hardware_enable(void) * before any KVM threads can be running. Unfortunately, we can't * bring the TSCs fully up to date with real time, as we aren't yet far * enough into CPU bringup that we know how much real time has actually - * elapsed; our helper function, ktime_get_boot_ns() will be using boot + * elapsed; our helper function, ktime_get_boottime_ns() will be using boot * variables that haven't been updated yet. * * So we simply find the maximum observed TSC above, then record the @@ -8935,250 +13100,156 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) -{ - kvm_x86_ops->hardware_disable(); - drop_user_return_notifiers(); -} - -int kvm_arch_hardware_setup(void) +void kvm_arch_disable_virtualization_cpu(void) { - int r; - - r = kvm_x86_ops->hardware_setup(); - if (r != 0) - return r; - - if (kvm_has_tsc_control) { - /* - * Make sure the user can only configure tsc_khz values that - * fit into a signed integer. - * A min value is not calculated because it will always - * be 1 on all machines. - */ - u64 max = min(0x7fffffffULL, - __scale_tsc(kvm_max_tsc_scaling_ratio, tsc_khz)); - kvm_max_guest_tsc_khz = max; - - kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits; - } - - kvm_init_msr_list(); - return 0; -} + kvm_x86_call(disable_virtualization_cpu)(); -void kvm_arch_hardware_unsetup(void) -{ - kvm_x86_ops->hardware_unsetup(); -} - -void kvm_arch_check_processor_compat(void *rtn) -{ - kvm_x86_ops->check_processor_compatibility(rtn); + /* + * 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_GPL(kvm_vcpu_is_reset_bsp); +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; } -struct static_key kvm_no_apic_vcpu __read_mostly; -EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu); - -int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) +void kvm_arch_free_vm(struct kvm *kvm) { - struct page *page; - int r; - - vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu); - vcpu->arch.emulate_ctxt.ops = &emulate_ops; - if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) - vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; - else - vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; - - page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) { - r = -ENOMEM; - goto fail; - } - vcpu->arch.pio_data = page_address(page); - - kvm_set_tsc_khz(vcpu, max_tsc_khz); - - r = kvm_mmu_create(vcpu); - if (r < 0) - goto fail_free_pio_data; - - if (irqchip_in_kernel(vcpu->kvm)) { - r = kvm_create_lapic(vcpu); - if (r < 0) - goto fail_mmu_destroy; - } else - static_key_slow_inc(&kvm_no_apic_vcpu); - - vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4, - GFP_KERNEL); - if (!vcpu->arch.mce_banks) { - r = -ENOMEM; - goto fail_free_lapic; - } - vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; - - if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL)) { - r = -ENOMEM; - goto fail_free_mce_banks; - } - - fx_init(vcpu); - - vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; - - vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); - - vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; - - kvm_async_pf_hash_reset(vcpu); - kvm_pmu_init(vcpu); - - vcpu->arch.pending_external_vector = -1; - vcpu->arch.preempted_in_kernel = false; +#if IS_ENABLED(CONFIG_HYPERV) + kfree(kvm->arch.hv_pa_pg); +#endif + __kvm_arch_free_vm(kvm); +} - kvm_hv_vcpu_init(vcpu); - return 0; +int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) +{ + int ret; + unsigned long flags; -fail_free_mce_banks: - kfree(vcpu->arch.mce_banks); -fail_free_lapic: - kvm_free_lapic(vcpu); -fail_mmu_destroy: - kvm_mmu_destroy(vcpu); -fail_free_pio_data: - free_page((unsigned long)vcpu->arch.pio_data); -fail: - return r; -} + if (!kvm_is_vm_type_supported(type)) + return -EINVAL; -void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) -{ - int idx; + 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; - kvm_hv_vcpu_uninit(vcpu); - kvm_pmu_destroy(vcpu); - kfree(vcpu->arch.mce_banks); - kvm_free_lapic(vcpu); - idx = srcu_read_lock(&vcpu->kvm->srcu); - kvm_mmu_destroy(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - free_page((unsigned long)vcpu->arch.pio_data); - if (!lapic_in_kernel(vcpu)) - static_key_slow_dec(&kvm_no_apic_vcpu); -} + ret = kvm_page_track_init(kvm); + if (ret) + goto out; -void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) -{ - vcpu->arch.l1tf_flush_l1d = true; - kvm_x86_ops->sched_in(vcpu, cpu); -} + ret = kvm_mmu_init_vm(kvm); + if (ret) + goto out_cleanup_page_track; -int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) -{ - if (type) - return -EINVAL; + 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.active_mmu_pages); - INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); - INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); - /* 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); - spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock); + seqcount_raw_spinlock_init(&kvm->arch.pvclock_sc, &kvm->arch.tsc_write_lock); + kvm->arch.kvmclock_offset = -get_kvmclock_base_ns(); - kvm->arch.kvmclock_offset = -ktime_get_boot_ns(); + raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); pvclock_update_vm_gtod_copy(kvm); + 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; - INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); - INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn); +#if IS_ENABLED(CONFIG_HYPERV) + spin_lock_init(&kvm->arch.hv_root_tdp_lock); + kvm->arch.hv_root_tdp = INVALID_PAGE; +#endif + kvm_apicv_init(kvm); kvm_hv_init_vm(kvm); - kvm_page_track_init(kvm); - kvm_mmu_init_vm(kvm); - - if (kvm_x86_ops->vm_init) - return kvm_x86_ops->vm_init(kvm); + kvm_xen_init_vm(kvm); - return 0; -} - -static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) -{ - vcpu_load(vcpu); - kvm_mmu_unload(vcpu); - vcpu_put(vcpu); -} - -static void kvm_free_vcpus(struct kvm *kvm) -{ - unsigned int i; - struct kvm_vcpu *vcpu; - - /* - * Unpin any mmu pages first. - */ - kvm_for_each_vcpu(i, vcpu, kvm) { - kvm_clear_async_pf_completion_queue(vcpu); - kvm_unload_vcpu_mmu(vcpu); + 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"); } - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_arch_vcpu_free(vcpu); - mutex_lock(&kvm->lock); - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); - mutex_unlock(&kvm->lock); -} + once_init(&kvm->arch.nx_once); + return 0; -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); +out_uninit_mmu: + kvm_mmu_uninit_vm(kvm); +out_cleanup_page_track: + kvm_page_track_cleanup(kvm); +out: + return ret; } -int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) +/** + * __x86_set_memory_region: Setup KVM internal memory slot + * + * @kvm: the kvm pointer to the VM. + * @id: the slot ID to setup. + * @gpa: the GPA to install the slot (unused when @size == 0). + * @size: the size of the slot. Set to zero to uninstall a slot. + * + * This function helps to setup a KVM internal memory slot. Specify + * @size > 0 to install a new slot, while @size == 0 to uninstall a + * slot. The return code can be one of the following: + * + * HVA: on success (uninstall will return a bogus HVA) + * -errno: on error + * + * The caller should always use IS_ERR() to check the return value + * before use. Note, the KVM internal memory slots are guaranteed to + * remain valid and unchanged until the VM is destroyed, i.e., the + * GPA->HVA translation will not change. However, the HVA is a user + * address, i.e. its accessibility is not guaranteed, and must be + * accessed via __copy_{to,from}_user(). + */ +void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, + u32 size) { int i, r; - unsigned long hva; + unsigned long hva, old_npages; struct kvm_memslots *slots = kvm_memslots(kvm); - struct kvm_memory_slot *slot, old; + struct kvm_memory_slot *slot; + + lockdep_assert_held(&kvm->slots_lock); - /* Called with kvm->slots_lock held. */ if (WARN_ON(id >= KVM_MEM_SLOTS_NUM)) - return -EINVAL; + return ERR_PTR_USR(-EINVAL); slot = id_to_memslot(slots, id); if (size) { - if (slot->npages) - return -EEXIST; + if (slot && slot->npages) + return ERR_PTR_USR(-EEXIST); /* * MAP_SHARED to prevent internal slot pages from being moved @@ -9186,117 +13257,157 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) */ hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, 0); - if (IS_ERR((void *)hva)) - return PTR_ERR((void *)hva); + if (IS_ERR_VALUE(hva)) + return (void __user *)hva; } else { - if (!slot->npages) - return 0; + if (!slot || !slot->npages) + return NULL; - hva = 0; + old_npages = slot->npages; + hva = slot->userspace_addr; } - old = *slot; - 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 r; + return ERR_PTR_USR(r); } if (!size) - vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); + vm_munmap(hva, old_npages * PAGE_SIZE); - return 0; + return (void __user *)hva; } -EXPORT_SYMBOL_GPL(__x86_set_memory_region); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(__x86_set_memory_region); -int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) +void kvm_arch_pre_destroy_vm(struct kvm *kvm) { - int r; - - mutex_lock(&kvm->slots_lock); - r = __x86_set_memory_region(kvm, id, gpa, size); - mutex_unlock(&kvm->slots_lock); + /* + * 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 - return r; + kvm_mmu_pre_destroy_vm(kvm); + static_call_cond(kvm_x86_vm_pre_destroy)(kvm); } -EXPORT_SYMBOL_GPL(x86_set_memory_region); void kvm_arch_destroy_vm(struct kvm *kvm) { if (current->mm == kvm->mm) { /* * Free memory regions allocated on behalf of userspace, - * unless the the memory map has changed due to process exit + * unless the memory map has changed due to process exit * or fd copying. */ - x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0); - x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, 0, 0); - x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); - } - if (kvm_x86_ops->vm_destroy) - kvm_x86_ops->vm_destroy(kvm); + mutex_lock(&kvm->slots_lock); + __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + 0, 0); + __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, + 0, 0); + __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); + mutex_unlock(&kvm->slots_lock); + } + 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_free_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); } -void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +static void memslot_rmap_free(struct kvm_memory_slot *slot) { int i; for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { - if (!dont || free->arch.rmap[i] != dont->arch.rmap[i]) { - kvfree(free->arch.rmap[i]); - free->arch.rmap[i] = NULL; - } - if (i == 0) - continue; + vfree(slot->arch.rmap[i]); + slot->arch.rmap[i] = NULL; + } +} - if (!dont || free->arch.lpage_info[i - 1] != - dont->arch.lpage_info[i - 1]) { - kvfree(free->arch.lpage_info[i - 1]); - free->arch.lpage_info[i - 1] = NULL; - } +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) +{ + int i; + + memslot_rmap_free(slot); + + for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { + vfree(slot->arch.lpage_info[i - 1]); + slot->arch.lpage_info[i - 1] = NULL; } - kvm_page_track_free_memslot(free, dont); + kvm_page_track_free_memslot(slot); } -int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, - unsigned long npages) +int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages) { + const int sz = sizeof(*slot->arch.rmap[0]); int i; for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { + int level = i + 1; + int lpages = __kvm_mmu_slot_lpages(slot, npages, level); + + if (slot->arch.rmap[i]) + continue; + + slot->arch.rmap[i] = __vcalloc(lpages, sz, GFP_KERNEL_ACCOUNT); + if (!slot->arch.rmap[i]) { + memslot_rmap_free(slot); + return -ENOMEM; + } + } + + return 0; +} + +static int kvm_alloc_memslot_metadata(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + unsigned long npages = slot->npages; + int i, r; + + /* + * 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 + * the new memslot is successful. + */ + memset(&slot->arch, 0, sizeof(slot->arch)); + + if (kvm_memslots_have_rmaps(kvm)) { + r = memslot_rmap_alloc(slot, npages); + if (r) + return r; + } + + for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { struct kvm_lpage_info *linfo; unsigned long ugfn; int lpages; int level = i + 1; - lpages = gfn_to_index(slot->base_gfn + npages - 1, - slot->base_gfn, level) + 1; + lpages = __kvm_mmu_slot_lpages(slot, npages, level); - slot->arch.rmap[i] = - kvcalloc(lpages, sizeof(*slot->arch.rmap[i]), - GFP_KERNEL); - if (!slot->arch.rmap[i]) - goto out_free; - if (i == 0) - continue; - - linfo = kvcalloc(lpages, sizeof(*linfo), GFP_KERNEL); + linfo = __vcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT); if (!linfo) goto out_free; @@ -9309,11 +13420,9 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, ugfn = slot->userspace_addr >> PAGE_SHIFT; /* * If the gfn and userspace address are not aligned wrt each - * other, or if explicitly asked to, disable large page - * support for this slot + * other, disable large page support for this slot. */ - if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1) || - !kvm_largepages_enabled()) { + if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1)) { unsigned long j; for (j = 0; j < lpages; ++j) @@ -9321,196 +13430,243 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, } } - if (kvm_page_track_create_memslot(slot, npages)) +#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; return 0; out_free: - for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { - kvfree(slot->arch.rmap[i]); - slot->arch.rmap[i] = NULL; - if (i == 0) - continue; + memslot_rmap_free(slot); - kvfree(slot->arch.lpage_info[i - 1]); + for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { + vfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } return -ENOMEM; } -void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) +void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { + struct kvm_vcpu *vcpu; + unsigned long i; + /* * memslots->generation has been incremented. * mmio generation may have reached its maximum value. */ - kvm_mmu_invalidate_mmio_sptes(kvm, slots); + kvm_mmu_invalidate_mmio_sptes(kvm, gen); + + /* Force re-initialization of steal_time cache */ + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_vcpu_kick(vcpu); } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_memory_slot *old, + 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); + } + + if (change == KVM_MR_FLAGS_ONLY) + memcpy(&new->arch, &old->arch, sizeof(old->arch)); + else if (WARN_ON_ONCE(change != KVM_MR_DELETE)) + return -EIO; + return 0; } -static void kvm_mmu_slot_apply_flags(struct kvm *kvm, - struct kvm_memory_slot *new) + +static void kvm_mmu_update_cpu_dirty_logging(struct kvm *kvm, bool enable) { - /* Still write protect RO slot */ - if (new->flags & KVM_MEM_READONLY) { - kvm_mmu_slot_remove_write_access(kvm, new); + int nr_slots; + + if (!kvm->arch.cpu_dirty_log_size) return; - } - /* - * Call kvm_x86_ops dirty logging hooks when they are valid. - * - * kvm_x86_ops->slot_disable_log_dirty is called when: - * - * - KVM_MR_CREATE with dirty logging is disabled - * - KVM_MR_FLAGS_ONLY with dirty logging is disabled in new flag - * - * The reason is, in case of PML, we need to set D-bit for any slots - * with dirty logging disabled in order to eliminate unnecessary GPA - * logging in PML buffer (and potential PML buffer full VMEXT). This - * guarantees leaving PML enabled during guest's lifetime won't have - * any additional overhead from PML when guest is running with dirty - * logging disabled for memory slots. - * - * kvm_x86_ops->slot_enable_log_dirty is called when switching new slot - * to dirty logging mode. - * - * If kvm_x86_ops dirty logging hooks are invalid, use write protect. - * - * In case of write protect: - * - * Write protect all pages for dirty logging. - * - * All the sptes including the large sptes which point to this - * slot are set to readonly. We can not create any new large - * spte on this slot until the end of the logging. - * - * See the comments in fast_page_fault(). - */ - if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { - if (kvm_x86_ops->slot_enable_log_dirty) - kvm_x86_ops->slot_enable_log_dirty(kvm, new); - else - kvm_mmu_slot_remove_write_access(kvm, new); - } else { - if (kvm_x86_ops->slot_disable_log_dirty) - kvm_x86_ops->slot_disable_log_dirty(kvm, new); - } + nr_slots = atomic_read(&kvm->nr_memslots_dirty_logging); + if ((enable && nr_slots == 1) || !nr_slots) + kvm_make_all_cpus_request(kvm, KVM_REQ_UPDATE_CPU_DIRTY_LOGGING); } -void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, - const struct kvm_memory_slot *new, - enum kvm_mr_change change) +static void kvm_mmu_slot_apply_flags(struct kvm *kvm, + struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, + enum kvm_mr_change change) { - int nr_mmu_pages = 0; - - if (!kvm->arch.n_requested_mmu_pages) - nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); - - if (nr_mmu_pages) - kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); + u32 old_flags = old ? old->flags : 0; + u32 new_flags = new ? new->flags : 0; + bool log_dirty_pages = new_flags & KVM_MEM_LOG_DIRTY_PAGES; /* - * Dirty logging tracks sptes in 4k granularity, meaning that large - * sptes have to be split. If live migration is successful, 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. - * - * 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. + * Update CPU dirty logging if dirty logging is being toggled. This + * applies to all operations. */ - if ((change != KVM_MR_DELETE) && - (old->flags & KVM_MEM_LOG_DIRTY_PAGES) && - !(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) - kvm_mmu_zap_collapsible_sptes(kvm, new); + if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) + kvm_mmu_update_cpu_dirty_logging(kvm, log_dirty_pages); /* - * Set up write protection and/or dirty logging for the new slot. + * Nothing more to do for RO slots (which can't be dirtied and can't be + * made writable) or CREATE/MOVE/DELETE of a slot. * - * For KVM_MR_DELETE and KVM_MR_MOVE, the shadow pages of old slot have - * been zapped so no dirty logging staff is needed for old slot. For - * KVM_MR_FLAGS_ONLY, the old slot is essentially the same one as the - * new and it's also covered when dealing with the new slot. + * For a memslot with dirty logging disabled: + * CREATE: No dirty mappings will already exist. + * MOVE/DELETE: The old mappings will already have been cleaned up by + * kvm_arch_flush_shadow_memslot() * - * FIXME: const-ify all uses of struct kvm_memory_slot. + * For a memslot with dirty logging enabled: + * CREATE: No shadow pages exist, thus nothing to write-protect + * and no dirty bits to clear. + * MOVE/DELETE: The old mappings will already have been cleaned up by + * kvm_arch_flush_shadow_memslot(). */ - if (change != KVM_MR_DELETE) - kvm_mmu_slot_apply_flags(kvm, (struct kvm_memory_slot *) new); -} + if ((change != KVM_MR_FLAGS_ONLY) || (new_flags & KVM_MEM_READONLY)) + return; -void kvm_arch_flush_shadow_all(struct kvm *kvm) -{ - kvm_mmu_invalidate_zap_all_pages(kvm); -} + /* + * READONLY and non-flags changes were filtered out above, and the only + * other flag is LOG_DIRTY_PAGES, i.e. something is wrong if dirty + * logging isn't being toggled on or off. + */ + if (WARN_ON_ONCE(!((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES))) + return; -void kvm_arch_flush_shadow_memslot(struct kvm *kvm, - struct kvm_memory_slot *slot) -{ - kvm_page_track_flush_slot(kvm, slot); -} + if (!log_dirty_pages) { + /* + * 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. + * + * 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_recover_huge_pages(kvm, new); + } else { + /* + * Initially-all-set does not require write protecting any page, + * because they're all assumed to be dirty. + */ + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) + return; -static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) -{ - return (is_guest_mode(vcpu) && - kvm_x86_ops->guest_apic_has_interrupt && - kvm_x86_ops->guest_apic_has_interrupt(vcpu)); + if (READ_ONCE(eager_page_split)) + kvm_mmu_slot_try_split_huge_pages(kvm, new, PG_LEVEL_4K); + + 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 { + kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_4K); + } + + /* + * Unconditionally flush the TLBs after enabling dirty logging. + * A flush is almost always going to be necessary (see below), + * and unconditionally flushing allows the helpers to omit + * the subtly complex checks when removing write access. + * + * Do the flush outside of mmu_lock to reduce the amount of + * time mmu_lock is held. Flushing after dropping mmu_lock is + * safe as KVM only needs to guarantee the slot is fully + * write-protected before returning to userspace, i.e. before + * userspace can consume the dirty status. + * + * Flushing outside of mmu_lock requires KVM to be careful when + * making decisions based on writable status of an SPTE, e.g. a + * !writable SPTE doesn't guarantee a CPU can't perform writes. + * + * Specifically, KVM also write-protects guest page tables to + * monitor changes when using shadow paging, and must guarantee + * no CPUs can write to those page before mmu_lock is dropped. + * Because CPUs may have stale TLB entries at this point, a + * !writable SPTE doesn't guarantee CPUs can't perform writes. + * + * KVM also allows making SPTES writable outside of mmu_lock, + * e.g. to allow dirty logging without taking mmu_lock. + * + * To handle these scenarios, KVM uses a separate software-only + * bit (MMU-writable) to track if a SPTE is !writable due to + * a guest page table being write-protected (KVM clears the + * MMU-writable flag when write-protecting for shadow paging). + * + * The use of MMU-writable is also the primary motivation for + * the unconditional flush. Because KVM must guarantee that a + * CPU doesn't contain stale, writable TLB entries for a + * !MMU-writable SPTE, KVM must flush if it encounters any + * MMU-writable SPTE regardless of whether the actual hardware + * writable bit was set. I.e. KVM is almost guaranteed to need + * to flush, while unconditionally flushing allows the "remove + * write access" helpers to ignore MMU-writable entirely. + * + * See is_writable_pte() for more details (the case involving + * access-tracked SPTEs is particularly relevant). + */ + kvm_flush_remote_tlbs_memslot(kvm, new); + } } -static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) +void kvm_arch_commit_memory_region(struct kvm *kvm, + struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, + enum kvm_mr_change change) { - if (!list_empty_careful(&vcpu->async_pf.done)) - return true; + if (change == KVM_MR_DELETE) + kvm_page_track_delete_slot(kvm, old); - if (kvm_apic_has_events(vcpu)) - return true; - - if (vcpu->arch.pv.pv_unhalted) - return true; + if (!kvm->arch.n_requested_mmu_pages && + (change == KVM_MR_CREATE || change == KVM_MR_DELETE)) { + unsigned long nr_mmu_pages; - if (vcpu->arch.exception.pending) - return true; + nr_mmu_pages = kvm->nr_memslot_pages / KVM_MEMSLOT_PAGES_TO_MMU_PAGES_RATIO; + nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES); + kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); + } - if (kvm_test_request(KVM_REQ_NMI, vcpu) || - (vcpu->arch.nmi_pending && - kvm_x86_ops->nmi_allowed(vcpu))) - return true; + kvm_mmu_slot_apply_flags(kvm, old, new, change); - if (kvm_test_request(KVM_REQ_SMI, vcpu) || - (vcpu->arch.smi_pending && !is_smm(vcpu))) - return true; + /* Free the arrays associated with the old memslot. */ + if (change == KVM_MR_MOVE) + kvm_arch_free_memslot(kvm, old); +} - if (kvm_arch_interrupt_allowed(vcpu) && - (kvm_cpu_has_interrupt(vcpu) || - kvm_guest_apic_has_interrupt(vcpu))) - return true; +bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) +{ + WARN_ON_ONCE(!kvm_arch_pmi_in_guest(vcpu)); - if (kvm_hv_has_stimer_pending(vcpu)) + if (vcpu->arch.guest_state_protected) return true; - return false; + return kvm_x86_call(get_cpl)(vcpu) == 0; } -int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) +unsigned long kvm_arch_vcpu_get_ip(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_vcpu_in_kernel(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.preempted_in_kernel; + if (vcpu->arch.guest_state_protected) + return 0; + + return kvm_rip_read(vcpu); } int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) @@ -9520,41 +13676,45 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) { - return kvm_x86_ops->interrupt_allowed(vcpu); + return kvm_x86_call(interrupt_allowed)(vcpu, false); } unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu) { + /* Can't read the RIP when guest state is protected, just return 0 */ + if (vcpu->arch.guest_state_protected) + return 0; + if (is_64_bit_mode(vcpu)) return kvm_rip_read(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 = kvm_x86_ops->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; - kvm_x86_ops->set_rflags(vcpu, rflags); + kvm_x86_call(set_rflags)(vcpu, rflags); } void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) @@ -9562,35 +13722,18 @@ 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); - -void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) -{ - int r; - - if ((vcpu->arch.mmu->direct_map != work->arch.direct_map) || - work->wakeup_all) - return; - - r = kvm_mmu_reload(vcpu); - if (unlikely(r)) - return; - - if (!vcpu->arch.mmu->direct_map && - work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu)) - return; - - vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true); -} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_rflags); static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) { + BUILD_BUG_ON(!is_power_of_2(ASYNC_PF_PER_VCPU)); + return hash_32(gfn & 0xffffffff, order_base_2(ASYNC_PF_PER_VCPU)); } static inline u32 kvm_async_pf_next_probe(u32 key) { - return (key + 1) & (roundup_pow_of_two(ASYNC_PF_PER_VCPU) - 1); + return (key + 1) & (ASYNC_PF_PER_VCPU - 1); } static void kvm_add_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) @@ -9608,7 +13751,7 @@ static u32 kvm_async_pf_gfn_slot(struct kvm_vcpu *vcpu, gfn_t gfn) int i; u32 key = kvm_async_pf_hash_fn(gfn); - for (i = 0; i < roundup_pow_of_two(ASYNC_PF_PER_VCPU) && + for (i = 0; i < ASYNC_PF_PER_VCPU && (vcpu->arch.apf.gfns[key] != gfn && vcpu->arch.apf.gfns[key] != ~0); i++) key = kvm_async_pf_next_probe(key); @@ -9626,6 +13769,10 @@ static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) u32 i, j, k; i = j = kvm_async_pf_gfn_slot(vcpu, gfn); + + if (WARN_ON_ONCE(vcpu->arch.apf.gfns[i] != gfn)) + return; + while (true) { vcpu->arch.apf.gfns[i] = ~0; do { @@ -9644,33 +13791,87 @@ static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) } } -static int apf_put_user(struct kvm_vcpu *vcpu, u32 val) +static inline int apf_put_user_notpresent(struct kvm_vcpu *vcpu) { + u32 reason = KVM_PV_REASON_PAGE_NOT_PRESENT; - return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &val, - sizeof(val)); + return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &reason, + sizeof(reason)); } -static int apf_get_user(struct kvm_vcpu *vcpu, u32 *val) +static inline int apf_put_user_ready(struct kvm_vcpu *vcpu, u32 token) { + unsigned int offset = offsetof(struct kvm_vcpu_pv_apf_data, token); - return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, val, - sizeof(u32)); + return kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.apf.data, + &token, offset, sizeof(token)); } -void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, +static inline bool apf_pageready_slot_free(struct kvm_vcpu *vcpu) +{ + unsigned int offset = offsetof(struct kvm_vcpu_pv_apf_data, token); + u32 val; + + if (kvm_read_guest_offset_cached(vcpu->kvm, &vcpu->arch.apf.data, + &val, offset, sizeof(val))) + return false; + + return !val; +} + +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_always && + (vcpu->arch.guest_state_protected || !kvm_x86_call(get_cpl)(vcpu))) + return false; + + if (is_guest_mode(vcpu)) { + /* + * L1 needs to opt into the special #PF vmexits that are + * used to deliver async page faults. + */ + return vcpu->arch.apf.delivery_as_pf_vmexit; + } else { + /* + * Play it safe in case the guest temporarily disables paging. + * The real mode IDT in particular is unlikely to have a #PF + * exception setup. + */ + return is_paging(vcpu); + } +} + +bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) +{ + if (unlikely(!lapic_in_kernel(vcpu) || + kvm_event_needs_reinjection(vcpu) || + kvm_is_exception_pending(vcpu))) + return false; + + if (kvm_hlt_in_guest(vcpu->kvm) && !kvm_can_deliver_async_pf(vcpu)) + return false; + + /* + * If interrupts are off we cannot even use an artificial + * halt state. + */ + return kvm_arch_interrupt_allowed(vcpu); +} + +bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { struct x86_exception fault; - trace_kvm_async_pf_not_present(work->arch.token, work->gva); + trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa); kvm_add_async_pf_gfn(vcpu, work->arch.gfn); - if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) || - (vcpu->arch.apf.send_user_only && - kvm_x86_ops->get_cpl(vcpu) == 0)) - kvm_make_request(KVM_REQ_APF_HALT, vcpu); - else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_NOT_PRESENT)) { + if (kvm_can_deliver_async_pf(vcpu) && + !apf_put_user_notpresent(vcpu)) { fault.vector = PF_VECTOR; fault.error_code_valid = true; fault.error_code = 0; @@ -9678,162 +13879,527 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, fault.address = work->arch.token; fault.async_page_fault = true; kvm_inject_page_fault(vcpu, &fault); + return true; + } else { + /* + * It is not possible to deliver a paravirtualized asynchronous + * page fault, but putting the guest in an artificial halt state + * can be beneficial nevertheless: if an interrupt arrives, we + * can deliver it timely and perhaps the guest will schedule + * another process. When the instruction that triggered a page + * fault is retried, hopefully the page will be ready in the host. + */ + kvm_make_request(KVM_REQ_APF_HALT, vcpu); + return false; } } void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { - struct x86_exception fault; - u32 val; + struct kvm_lapic_irq irq = { + .delivery_mode = APIC_DM_FIXED, + .vector = vcpu->arch.apf.vec + }; if (work->wakeup_all) work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); - trace_kvm_async_pf_ready(work->arch.token, work->gva); - - if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED && - !apf_get_user(vcpu, &val)) { - if (val == KVM_PV_REASON_PAGE_NOT_PRESENT && - vcpu->arch.exception.pending && - vcpu->arch.exception.nr == PF_VECTOR && - !apf_put_user(vcpu, 0)) { - vcpu->arch.exception.injected = false; - vcpu->arch.exception.pending = false; - vcpu->arch.exception.nr = 0; - vcpu->arch.exception.has_error_code = false; - vcpu->arch.exception.error_code = 0; - vcpu->arch.exception.has_payload = false; - vcpu->arch.exception.payload = 0; - } else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) { - fault.vector = PF_VECTOR; - fault.error_code_valid = true; - fault.error_code = 0; - fault.nested_page_fault = false; - fault.address = work->arch.token; - fault.async_page_fault = true; - kvm_inject_page_fault(vcpu, &fault); - } + trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa); + + if ((work->wakeup_all || work->notpresent_injected) && + kvm_pv_async_pf_enabled(vcpu) && + !apf_put_user_ready(vcpu, work->arch.token)) { + 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); } -bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) +void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu) { - if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED)) - return true; - else - return kvm_can_do_async_pf(vcpu); -} + kvm_make_request(KVM_REQ_APF_READY, vcpu); -void kvm_arch_start_assignment(struct kvm *kvm) -{ - atomic_inc(&kvm->arch.assigned_device_count); + /* 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); } -EXPORT_SYMBOL_GPL(kvm_arch_start_assignment); -void kvm_arch_end_assignment(struct kvm *kvm) +bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) { - atomic_dec(&kvm->arch.assigned_device_count); + if (!kvm_pv_async_pf_enabled(vcpu)) + return true; + else + return kvm_lapic_enabled(vcpu) && apf_pageready_slot_free(vcpu); } -EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); -bool kvm_arch_has_assigned_device(struct kvm *kvm) +static void kvm_noncoherent_dma_assignment_start_or_stop(struct kvm *kvm) { - return 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); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_arch_has_noncoherent_dma); -bool kvm_arch_has_irq_bypass(void) +bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { - return kvm_x86_ops->update_pi_irte != NULL; + return (vcpu->arch.msr_kvm_poll_control & 1) == 0; } -int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, - struct irq_bypass_producer *prod) +#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) { - struct kvm_kernel_irqfd *irqfd = - container_of(cons, struct kvm_kernel_irqfd, consumer); + return !kvm_arch_has_private_mem(kvm); +} - irqfd->producer = prod; +#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 kvm_x86_call(gmem_prepare)(kvm, pfn, gfn, max_order); +} +#endif - return kvm_x86_ops->update_pi_irte(irqfd->kvm, - prod->irq, irqfd->gsi, 1); +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE +void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) +{ + kvm_x86_call(gmem_invalidate)(start, end); } +#endif +#endif -void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, - struct irq_bypass_producer *prod) +int kvm_spec_ctrl_test_value(u64 value) { - int ret; - struct kvm_kernel_irqfd *irqfd = - container_of(cons, struct kvm_kernel_irqfd, consumer); + /* + * test that setting IA32_SPEC_CTRL to given value + * is allowed by the host processor + */ - WARN_ON(irqfd->producer != prod); - irqfd->producer = NULL; + u64 saved_value; + unsigned long flags; + int ret = 0; + + local_irq_save(flags); + + if (rdmsrq_safe(MSR_IA32_SPEC_CTRL, &saved_value)) + ret = 1; + else if (wrmsrq_safe(MSR_IA32_SPEC_CTRL, value)) + ret = 1; + else + wrmsrq(MSR_IA32_SPEC_CTRL, saved_value); + + local_irq_restore(flags); + + return ret; +} +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) +{ + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + struct x86_exception fault; + u64 access = error_code & + (PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK); + + if (!(error_code & PFERR_PRESENT_MASK) || + mmu->gva_to_gpa(vcpu, mmu, gva, access, &fault) != INVALID_GPA) { + /* + * If vcpu->arch.walk_mmu->gva_to_gpa succeeded, the page + * tables probably do not match the TLB. Just proceed + * with the error code that the processor gave. + */ + fault.vector = PF_VECTOR; + fault.error_code_valid = true; + fault.error_code = error_code; + fault.nested_page_fault = false; + fault.address = gva; + fault.async_page_fault = false; + } + vcpu->arch.walk_mmu->inject_page_fault(vcpu, &fault); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_fixup_and_inject_pf_error); + +/* + * Handles kvm_read/write_guest_virt*() result and either injects #PF or returns + * KVM_EXIT_INTERNAL_ERROR for cases not currently handled by KVM. Return value + * indicates whether exit to userspace is needed. + */ +int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, + struct x86_exception *e) +{ + if (r == X86EMUL_PROPAGATE_FAULT) { + if (KVM_BUG_ON(!e, vcpu->kvm)) + return -EIO; + + kvm_inject_emulated_page_fault(vcpu, e); + return 1; + } /* - * 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 = kvm_x86_ops->update_pi_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); + * In case kvm_read/write_guest_virt*() failed with X86EMUL_IO_NEEDED + * while handling a VMX instruction KVM could've handled the request + * correctly by exiting to userspace and performing I/O but there + * doesn't seem to be a real use-case behind such requests, just return + * KVM_EXIT_INTERNAL_ERROR for now. + */ + kvm_prepare_emulation_failure_exit(vcpu); + + return 0; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_handle_memory_failure); + +int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) +{ + bool pcid_enabled; + struct x86_exception e; + struct { + u64 pcid; + u64 gla; + } operand; + int r; + + r = kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e); + if (r != X86EMUL_CONTINUE) + return kvm_handle_memory_failure(vcpu, r, &e); + + if (operand.pcid >> 12 != 0) { + kvm_inject_gp(vcpu, 0); + return 1; + } + + pcid_enabled = kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE); + + 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_invlpg_address(operand.gla, vcpu)) { + kvm_inject_gp(vcpu, 0); + return 1; + } + kvm_mmu_invpcid_gva(vcpu, operand.gla, operand.pcid); + return kvm_skip_emulated_instruction(vcpu); + + case INVPCID_TYPE_SINGLE_CTXT: + if (!pcid_enabled && (operand.pcid != 0)) { + kvm_inject_gp(vcpu, 0); + return 1; + } + + kvm_invalidate_pcid(vcpu, operand.pcid); + return kvm_skip_emulated_instruction(vcpu); + + case INVPCID_TYPE_ALL_NON_GLOBAL: + /* + * Currently, KVM doesn't mark global entries in the shadow + * page tables, so a non-global flush just degenerates to a + * global flush. If needed, we could optimize this later by + * keeping track of global entries in shadow page tables. + */ + + fallthrough; + case INVPCID_TYPE_ALL_INCL_GLOBAL: + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + return kvm_skip_emulated_instruction(vcpu); + + default: + kvm_inject_gp(vcpu, 0); + return 1; + } +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_handle_invpcid); + +static int complete_sev_es_emulated_mmio(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + struct kvm_mmio_fragment *frag; + unsigned int len; + + BUG_ON(!vcpu->mmio_needed); + + /* Complete previous fragment */ + frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment]; + len = min(8u, frag->len); + if (!vcpu->mmio_is_write) + memcpy(frag->data, run->mmio.data, len); + + if (frag->len <= 8) { + /* Switch to the next fragment. */ + frag++; + vcpu->mmio_cur_fragment++; + } else { + /* Go forward to the next mmio piece. */ + frag->data += len; + frag->gpa += len; + frag->len -= len; + } + + if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) { + vcpu->mmio_needed = 0; + + // VMG change, at this point, we're always done + // RIP has already been advanced + return 1; + } + + // More MMIO is needed + run->mmio.phys_addr = frag->gpa; + run->mmio.len = min(8u, frag->len); + run->mmio.is_write = vcpu->mmio_is_write; + if (run->mmio.is_write) + memcpy(run->mmio.data, frag->data, min(8u, frag->len)); + run->exit_reason = KVM_EXIT_MMIO; + + vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio; + + return 0; +} + +int kvm_sev_es_mmio_write(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes, + void *data) +{ + int handled; + struct kvm_mmio_fragment *frag; + + if (!data) + return -EINVAL; + + handled = write_emultor.read_write_mmio(vcpu, gpa, bytes, data); + if (handled == bytes) + return 1; + + bytes -= handled; + gpa += handled; + data += handled; + + /*TODO: Check if need to increment number of frags */ + frag = vcpu->mmio_fragments; + vcpu->mmio_nr_fragments = 1; + frag->len = bytes; + frag->gpa = gpa; + frag->data = data; + + vcpu->mmio_needed = 1; + vcpu->mmio_cur_fragment = 0; + + vcpu->run->mmio.phys_addr = gpa; + vcpu->run->mmio.len = min(8u, frag->len); + vcpu->run->mmio.is_write = 1; + memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len)); + vcpu->run->exit_reason = KVM_EXIT_MMIO; + + vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio; + + return 0; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_sev_es_mmio_write); -int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) +int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes, + void *data) { - if (!kvm_x86_ops->update_pi_irte) + int handled; + struct kvm_mmio_fragment *frag; + + if (!data) return -EINVAL; - return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set); + handled = read_emultor.read_write_mmio(vcpu, gpa, bytes, data); + if (handled == bytes) + return 1; + + bytes -= handled; + gpa += handled; + data += handled; + + /*TODO: Check if need to increment number of frags */ + frag = vcpu->mmio_fragments; + vcpu->mmio_nr_fragments = 1; + frag->len = bytes; + frag->gpa = gpa; + frag->data = data; + + vcpu->mmio_needed = 1; + vcpu->mmio_cur_fragment = 0; + + vcpu->run->mmio.phys_addr = gpa; + vcpu->run->mmio.len = min(8u, frag->len); + vcpu->run->mmio.is_write = 0; + vcpu->run->exit_reason = KVM_EXIT_MMIO; + + vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio; + + return 0; } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_sev_es_mmio_read); -bool kvm_vector_hashing_enabled(void) +static void advance_sev_es_emulated_pio(struct kvm_vcpu *vcpu, unsigned count, int size) { - return vector_hashing; + vcpu->arch.sev_pio_count -= count; + vcpu->arch.sev_pio_data += count * size; } -EXPORT_SYMBOL_GPL(kvm_vector_hashing_enabled); +static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, + unsigned int port); + +static int complete_sev_es_emulated_outs(struct kvm_vcpu *vcpu) +{ + int size = vcpu->arch.pio.size; + int port = vcpu->arch.pio.port; + + vcpu->arch.pio.count = 0; + if (vcpu->arch.sev_pio_count) + return kvm_sev_es_outs(vcpu, size, port); + return 1; +} + +static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, + unsigned int port) +{ + for (;;) { + unsigned int count = + min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count); + int ret = emulator_pio_out(vcpu, size, port, vcpu->arch.sev_pio_data, count); + + /* memcpy done already by emulator_pio_out. */ + advance_sev_es_emulated_pio(vcpu, count, size); + if (!ret) + break; + + /* Emulation done by the kernel. */ + if (!vcpu->arch.sev_pio_count) + return 1; + } + + vcpu->arch.complete_userspace_io = complete_sev_es_emulated_outs; + return 0; +} + +static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size, + unsigned int port); + +static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu) +{ + unsigned count = vcpu->arch.pio.count; + int size = vcpu->arch.pio.size; + int port = vcpu->arch.pio.port; + + complete_emulator_pio_in(vcpu, vcpu->arch.sev_pio_data); + advance_sev_es_emulated_pio(vcpu, count, size); + if (vcpu->arch.sev_pio_count) + return kvm_sev_es_ins(vcpu, size, port); + return 1; +} + +static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size, + unsigned int port) +{ + for (;;) { + unsigned int count = + min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count); + if (!emulator_pio_in(vcpu, size, port, vcpu->arch.sev_pio_data, count)) + break; + + /* Emulation done by the kernel. */ + advance_sev_es_emulated_pio(vcpu, count, size); + if (!vcpu->arch.sev_pio_count) + return 1; + } + + vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins; + return 0; +} + +int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size, + unsigned int port, void *data, unsigned int count, + int in) +{ + vcpu->arch.sev_pio_data = data; + vcpu->arch.sev_pio_count = count; + return in ? kvm_sev_es_ins(vcpu, size, port) + : kvm_sev_es_outs(vcpu, size, port); +} +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); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr); -EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmenter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmenter_failed); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset); -EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window); +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); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_kick_vcpu_slowpath); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_doorbell); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_accept_irq); +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; +} +module_init(kvm_x86_init); + +static void __exit kvm_x86_exit(void) +{ + WARN_ON_ONCE(static_branch_unlikely(&kvm_has_noapic_vcpu)); +} +module_exit(kvm_x86_exit); |