diff options
Diffstat (limited to 'arch/x86/kvm/x86.c')
-rw-r--r-- | arch/x86/kvm/x86.c | 3082 |
1 files changed, 2080 insertions, 1002 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0cf1082455df..ecea83f0da49 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -41,7 +41,6 @@ #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> @@ -87,8 +86,13 @@ #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); + +struct kvm_caps kvm_caps __read_mostly = { + .supported_mce_cap = MCG_CTL_P | MCG_SER_P, +}; +EXPORT_SYMBOL_GPL(kvm_caps); + +#define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e)) #define emul_to_vcpu(ctxt) \ ((struct kvm_vcpu *)(ctxt)->vcpu) @@ -108,6 +112,8 @@ static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; #define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE) +#define KVM_CAP_PMU_VALID_MASK KVM_PMU_CAP_DISABLE + #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) @@ -118,21 +124,21 @@ 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); #define KVM_X86_OP(func) \ DEFINE_STATIC_CALL_NULL(kvm_x86_##func, \ *(((struct kvm_x86_ops *)0)->func)); -#define KVM_X86_OP_NULL KVM_X86_OP +#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); -EXPORT_STATIC_CALL_GPL(kvm_x86_tlb_flush_current); static bool __read_mostly ignore_msrs = 0; module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); @@ -147,19 +153,6 @@ 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); -bool __read_mostly kvm_has_bus_lock_exit; -EXPORT_SYMBOL_GPL(kvm_has_bus_lock_exit); - /* 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); @@ -180,12 +173,25 @@ bool __read_mostly enable_vmware_backdoor = false; module_param(enable_vmware_backdoor, bool, S_IRUGO); EXPORT_SYMBOL_GPL(enable_vmware_backdoor); -static bool __read_mostly force_emulation_prefix = false; -module_param(force_emulation_prefix, 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); int __read_mostly pi_inject_timer = -1; module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR); +/* Enable/disable PMU virtualization */ +bool __read_mostly enable_pmu = true; +EXPORT_SYMBOL_GPL(enable_pmu); +module_param(enable_pmu, bool, 0444); + +bool __read_mostly eager_page_split = true; +module_param(eager_page_split, bool, 0644); + /* * 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 @@ -210,7 +216,7 @@ static struct kvm_user_return_msrs __percpu *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_PKRU | XFEATURE_MASK_XTILE) u64 __read_mostly host_efer; EXPORT_SYMBOL_GPL(host_efer); @@ -223,8 +229,6 @@ EXPORT_SYMBOL_GPL(enable_apicv); u64 __read_mostly host_xss; EXPORT_SYMBOL_GPL(host_xss); -u64 __read_mostly supported_xss; -EXPORT_SYMBOL_GPL(supported_xss); const struct _kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), @@ -254,7 +258,12 @@ const struct kvm_stats_header kvm_vm_stats_header = { 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), @@ -279,7 +288,10 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, nested_run), STATS_DESC_COUNTER(VCPU, directed_yield_attempted), STATS_DESC_COUNTER(VCPU, directed_yield_successful), - STATS_DESC_ICOUNTER(VCPU, guest_mode) + 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 = { @@ -292,8 +304,6 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { }; u64 __read_mostly host_xcr0; -u64 __read_mostly supported_xcr0; -EXPORT_SYMBOL_GPL(supported_xcr0); static struct kmem_cache *x86_emulator_cache; @@ -523,6 +533,7 @@ 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) { @@ -533,8 +544,14 @@ 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))) @@ -544,16 +561,13 @@ 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 @@ -578,8 +592,8 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) * So they need to be flipped for DR6. */ vcpu->arch.dr6 |= DR6_ACTIVE_LOW; - vcpu->arch.dr6 |= payload; - vcpu->arch.dr6 ^= payload & DR6_ACTIVE_LOW; + vcpu->arch.dr6 |= ex->payload; + vcpu->arch.dr6 ^= ex->payload & DR6_ACTIVE_LOW; /* * The #DB payload is defined as compatible with the 'pending @@ -590,15 +604,30 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) 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_GPL(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; +} + 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) @@ -608,18 +637,31 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, kvm_make_request(KVM_REQ_EVENT, vcpu); + /* + * If the exception is destined for L2 and isn't being reinjected, + * morph it to a VM-Exit if L1 wants to intercept the exception. A + * previously injected exception is not checked because it was checked + * when it was original queued, and re-checking is incorrect if _L1_ + * injected the exception, in which case it's exempt from interception. + */ + if (!reinject && 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 (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. + * 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(vcpu->arch.exception.pending); + WARN_ON_ONCE(kvm_is_exception_pending(vcpu)); vcpu->arch.exception.injected = true; if (WARN_ON_ONCE(has_payload)) { /* @@ -634,17 +676,18 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, 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; if (!is_guest_mode(vcpu)) - kvm_deliver_exception_payload(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); @@ -652,25 +695,22 @@ 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) @@ -710,22 +750,36 @@ int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err) } EXPORT_SYMBOL_GPL(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); -bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, +void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { struct kvm_mmu *fault_mmu; @@ -741,10 +795,9 @@ bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, if ((fault->error_code & PFERR_PRESENT_MASK) && !(fault->error_code & PFERR_RSVD_MASK)) kvm_mmu_invalidate_gva(vcpu, fault_mmu, fault->address, - fault_mmu->root_hpa); + fault_mmu->root.hpa); fault_mmu->inject_page_fault(vcpu, fault); - return fault->nested_page_fault; } EXPORT_SYMBOL_GPL(kvm_inject_emulated_page_fault); @@ -798,8 +851,9 @@ static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) /* * 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; gpa_t real_gpa; int i; @@ -810,9 +864,9 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) * If the MMU is nested, CR3 holds an L2 GPA and needs to be translated * to an L1 GPA. */ - real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(pdpt_gfn), - PFERR_USER_MASK | PFERR_WRITE_MASK, NULL); - if (real_gpa == UNMAPPED_GVA) + 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. */ @@ -828,8 +882,16 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) } } + /* + * 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)); kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu); vcpu->arch.pdptrs_from_userspace = false; return 1; @@ -841,6 +903,13 @@ void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned lon if ((cr0 ^ old_cr0) & X86_CR0_PG) { kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu); + + /* + * Clearing CR0.PG is defined to flush the TLB from the guest's + * perspective. + */ + if (!(cr0 & X86_CR0_PG)) + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); } if ((cr0 ^ old_cr0) & KVM_MMU_CR0_ROLE_BITS) @@ -856,7 +925,6 @@ EXPORT_SYMBOL_GPL(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 pdptr_bits = X86_CR0_CD | X86_CR0_NW | X86_CR0_PG; cr0 |= X86_CR0_ET; @@ -886,8 +954,8 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } #endif if (!(vcpu->arch.efer & EFER_LME) && (cr0 & X86_CR0_PG) && - is_pae(vcpu) && ((cr0 ^ old_cr0) & pdptr_bits) && - !load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu))) + is_pae(vcpu) && ((cr0 ^ old_cr0) & X86_CR0_PDPTR_BITS) && + !load_pdptrs(vcpu, kvm_read_cr3(vcpu))) return 1; if (!(cr0 & X86_CR0_PG) && @@ -923,11 +991,13 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss); } +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (static_cpu_has(X86_FEATURE_PKU) && - (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) || - (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU)) && - vcpu->arch.pkru != vcpu->arch.host_pkru) + vcpu->arch.pkru != vcpu->arch.host_pkru && + ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || + kvm_read_cr4_bits(vcpu, X86_CR4_PKE))) write_pkru(vcpu->arch.pkru); +#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */ } EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state); @@ -936,13 +1006,15 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) if (vcpu->arch.guest_state_protected) return; +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (static_cpu_has(X86_FEATURE_PKU) && - (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) || - (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) { + ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || + kvm_read_cr4_bits(vcpu, X86_CR4_PKE))) { vcpu->arch.pkru = rdpkru(); if (vcpu->arch.pkru != vcpu->arch.host_pkru) write_pkru(vcpu->arch.host_pkru); } +#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */ if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) { @@ -957,6 +1029,13 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state); +#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 + static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { u64 xcr0 = xcr; @@ -990,6 +1069,11 @@ 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) @@ -999,6 +1083,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu) { + /* Note, #UD due to CR4.OSXSAVE=0 has priority over the intercept. */ if (static_call(kvm_x86_get_cpl)(vcpu) != 0 || __kvm_set_xcr(vcpu, kvm_rcx_read(vcpu), kvm_read_edx_eax(vcpu))) { kvm_inject_gp(vcpu, 0); @@ -1009,7 +1094,7 @@ int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_xsetbv); -bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +bool __kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { if (cr4 & cr4_reserved_bits) return false; @@ -1017,42 +1102,61 @@ bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (cr4 & vcpu->arch.cr4_guest_rsvd_bits) return false; - return static_call(kvm_x86_is_valid_cr4)(vcpu, cr4); + return true; +} +EXPORT_SYMBOL_GPL(__kvm_is_valid_cr4); + +static bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + return __kvm_is_valid_cr4(vcpu, cr4) && + static_call(kvm_x86_is_valid_cr4)(vcpu, cr4); } -EXPORT_SYMBOL_GPL(kvm_is_valid_cr4); 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 any role bit is changed, the MMU needs to be reset. - * - * If CR4.PCIDE is changed 1 -> 0, the guest TLB must be flushed. * 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. KVM_REQ_MMU_RELOAD is fit for the both cases; it - * is slow, but changing CR4.PCIDE is a rare case. - * - * If CR4.PGE is changed, the guest TLB must be flushed. + * 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); + + /* + * 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 * - * Note: resetting MMU is a superset of KVM_REQ_MMU_RELOAD and - * KVM_REQ_MMU_RELOAD is a superset of KVM_REQ_TLB_FLUSH_GUEST, hence - * the usage of "else if". + * This is a superset of KVM_REQ_TLB_FLUSH_CURRENT. */ - if ((cr4 ^ old_cr4) & KVM_MMU_CR4_ROLE_BITS) - kvm_mmu_reset_context(vcpu); - else if ((cr4 ^ old_cr4) & X86_CR4_PCIDE) - kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); - else if ((cr4 ^ old_cr4) & X86_CR4_PGE) + 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); + + /* + * 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); + } EXPORT_SYMBOL_GPL(kvm_post_set_cr4); int kvm_set_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; if (!kvm_is_valid_cr4(vcpu, cr4)) return 1; @@ -1063,9 +1167,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) 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)) { @@ -1125,7 +1228,7 @@ static void kvm_invalidate_pcid(struct kvm_vcpu *vcpu, unsigned long pcid) if (kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd) == pcid) roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); - kvm_mmu_free_roots(vcpu, mmu, roots_to_free); + kvm_mmu_free_roots(vcpu->kvm, mmu, roots_to_free); } int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) @@ -1154,14 +1257,15 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (kvm_vcpu_is_illegal_gpa(vcpu, cr3)) return 1; - if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) + if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3)) return 1; if (cr3 != kvm_read_cr3(vcpu)) kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); + 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: /* @@ -1331,34 +1435,31 @@ static const u32 msrs_to_save_all[] = { MSR_IA32_UMWAIT_CONTROL, MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, - MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_ARCH_PERFMON_FIXED_CTR0 + 3, + MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL, + MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG, + + /* This part of MSRs should match KVM_INTEL_PMC_MAX_GENERIC. */ MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3, MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5, MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7, - MSR_ARCH_PERFMON_PERFCTR0 + 8, MSR_ARCH_PERFMON_PERFCTR0 + 9, - MSR_ARCH_PERFMON_PERFCTR0 + 10, MSR_ARCH_PERFMON_PERFCTR0 + 11, - MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13, - MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15, - MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17, 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_ARCH_PERFMON_EVENTSEL0 + 8, MSR_ARCH_PERFMON_EVENTSEL0 + 9, - MSR_ARCH_PERFMON_EVENTSEL0 + 10, MSR_ARCH_PERFMON_EVENTSEL0 + 11, - MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13, - MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15, - MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17, MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, + + /* This part of MSRs should match KVM_AMD_PMC_MAX_GENERIC. */ MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, + + MSR_IA32_XFD, MSR_IA32_XFD_ERR, }; static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)]; @@ -1465,12 +1566,32 @@ static const u32 msr_based_features_all[] = { static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)]; static unsigned int num_msr_based_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 + */ + +#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) + static u64 kvm_get_arch_capabilities(void) { u64 data = 0; - if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) { rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data); + data &= KVM_SUPPORTED_ARCH_CAP; + } /* * If nx_huge_pages is enabled, KVM's shadow paging will ensure that @@ -1613,8 +1734,7 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info) 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); return 0; @@ -1680,9 +1800,6 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, { struct msr_data msr; - if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE)) - return KVM_MSR_RET_FILTERED; - switch (index) { case MSR_FS_BASE: case MSR_GS_BASE: @@ -1706,7 +1823,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, * value, and that something deterministic happens if the guest * invokes 64-bit SYSENTER. */ - data = get_canonical(data, vcpu_virt_addr_bits(vcpu)); + data = __canonical_address(data, vcpu_virt_addr_bits(vcpu)); break; case MSR_TSC_AUX: if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) @@ -1764,9 +1881,6 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, struct msr_data msr; int ret; - if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) - return KVM_MSR_RET_FILTERED; - switch (index) { case MSR_TSC_AUX: if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) @@ -1803,6 +1917,20 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, return ret; } +static int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data) +{ + if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) + return KVM_MSR_RET_FILTERED; + return kvm_get_msr_ignored_check(vcpu, index, data, false); +} + +static int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data) +{ + if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE)) + return KVM_MSR_RET_FILTERED; + return kvm_set_msr_ignored_check(vcpu, index, data, false); +} + int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) { return kvm_get_msr_ignored_check(vcpu, index, data, false); @@ -1815,22 +1943,36 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) } EXPORT_SYMBOL_GPL(kvm_set_msr); -static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) +static void complete_userspace_rdmsr(struct kvm_vcpu *vcpu) { - int err = vcpu->run->msr.error; - if (!err) { + 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); +} - return static_call(kvm_x86_complete_emulated_msr)(vcpu, err); +static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) +{ + complete_userspace_rdmsr(vcpu); + return complete_emulated_msr_access(vcpu); } -static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu) +static int complete_fast_msr_access(struct kvm_vcpu *vcpu) { return static_call(kvm_x86_complete_emulated_msr)(vcpu, vcpu->run->msr.error); } +static int complete_fast_rdmsr(struct kvm_vcpu *vcpu) +{ + complete_userspace_rdmsr(vcpu); + return complete_fast_msr_access(vcpu); +} + static u64 kvm_msr_reason(int r) { switch (r) { @@ -1865,31 +2007,13 @@ static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index, return 1; } -static int kvm_get_msr_user_space(struct kvm_vcpu *vcpu, u32 index, int r) -{ - return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_RDMSR, 0, - complete_emulated_rdmsr, r); -} - -static int kvm_set_msr_user_space(struct kvm_vcpu *vcpu, u32 index, u64 data, int r) -{ - return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_WRMSR, data, - complete_emulated_wrmsr, r); -} - int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) { u32 ecx = kvm_rcx_read(vcpu); u64 data; int r; - r = kvm_get_msr(vcpu, ecx, &data); - - /* MSR read failed? See if we should ask user space */ - if (r && kvm_get_msr_user_space(vcpu, ecx, r)) { - /* Bounce to user space */ - return 0; - } + r = kvm_get_msr_with_filter(vcpu, ecx, &data); if (!r) { trace_kvm_msr_read(ecx, data); @@ -1897,6 +2021,10 @@ int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) kvm_rax_write(vcpu, data & -1u); kvm_rdx_write(vcpu, (data >> 32) & -1u); } else { + /* MSR read failed? See if we should ask user space */ + if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_RDMSR, 0, + complete_fast_rdmsr, r)) + return 0; trace_kvm_msr_read_ex(ecx); } @@ -1910,21 +2038,20 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) u64 data = kvm_read_edx_eax(vcpu); int r; - r = kvm_set_msr(vcpu, ecx, data); - - /* MSR write failed? See if we should ask user space */ - if (r && kvm_set_msr_user_space(vcpu, ecx, data, r)) - /* Bounce to user space */ - return 0; + r = kvm_set_msr_with_filter(vcpu, ecx, data); - /* Signal all other negative errors to userspace */ - if (r < 0) - return r; - - if (!r) + if (!r) { trace_kvm_msr_write(ecx, data); - else + } else { + /* MSR write failed? See if we should ask user space */ + if (kvm_msr_user_space(vcpu, ecx, KVM_EXIT_X86_WRMSR, data, + complete_fast_msr_access, r)) + return 0; + /* Signal all other negative errors to userspace */ + if (r < 0) + return r; trace_kvm_msr_write_ex(ecx, data); + } return static_call(kvm_x86_complete_emulated_msr)(vcpu, r); } @@ -1943,13 +2070,6 @@ int kvm_emulate_invd(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_invd); -int kvm_emulate_mwait(struct kvm_vcpu *vcpu) -{ - pr_warn_once("kvm: MWAIT instruction emulated as NOP!\n"); - return kvm_emulate_as_nop(vcpu); -} -EXPORT_SYMBOL_GPL(kvm_emulate_mwait); - int kvm_handle_invalid_op(struct kvm_vcpu *vcpu) { kvm_queue_exception(vcpu, UD_VECTOR); @@ -1957,11 +2077,26 @@ int kvm_handle_invalid_op(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_handle_invalid_op); -int kvm_emulate_monitor(struct kvm_vcpu *vcpu) + +static int kvm_emulate_monitor_mwait(struct kvm_vcpu *vcpu, const char *insn) { - pr_warn_once("kvm: MONITOR instruction emulated as NOP!\n"); + if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS) && + !guest_cpuid_has(vcpu, X86_FEATURE_MWAIT)) + return kvm_handle_invalid_op(vcpu); + + pr_warn_once("kvm: %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_GPL(kvm_emulate_mwait); + +int kvm_emulate_monitor(struct kvm_vcpu *vcpu) +{ + return kvm_emulate_monitor_mwait(vcpu, "MONITOR"); +} EXPORT_SYMBOL_GPL(kvm_emulate_monitor); static inline bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu) @@ -1984,17 +2119,10 @@ static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data return 1; if (((data & APIC_SHORT_MASK) == APIC_DEST_NOSHORT) && - ((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) && - ((data & APIC_MODE_MASK) == APIC_DM_FIXED) && - ((u32)(data >> 32) != X2APIC_BROADCAST)) { - - data &= ~(1 << 12); - kvm_apic_send_ipi(vcpu->arch.apic, (u32)data, (u32)(data >> 32)); - kvm_lapic_set_reg(vcpu->arch.apic, APIC_ICR2, (u32)(data >> 32)); - kvm_lapic_set_reg(vcpu->arch.apic, APIC_ICR, (u32)data); - trace_kvm_apic_write(APIC_ICR, (u32)data); - return 0; - } + ((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) && + ((data & APIC_MODE_MASK) == APIC_DM_FIXED) && + ((u32)(data >> 32) != X2APIC_BROADCAST)) + return kvm_x2apic_icr_write(vcpu->arch.apic, data); return 1; } @@ -2119,7 +2247,7 @@ static s64 get_kvmclock_base_ns(void) } #endif -void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs) +static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs) { int version; int r; @@ -2181,14 +2309,13 @@ static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time, kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); /* we verify if the enable bit is set... */ - vcpu->arch.pv_time_enabled = false; - if (!(system_time & 1)) - return; - - if (!kvm_gfn_to_hva_cache_init(vcpu->kvm, - &vcpu->arch.pv_time, system_time & ~1ULL, - sizeof(struct pvclock_vcpu_time_info))) - vcpu->arch.pv_time_enabled = true; + if (system_time & 1) { + kvm_gpc_activate(vcpu->kvm, &vcpu->arch.pv_time, vcpu, + KVM_HOST_USES_PFN, system_time & ~1ULL, + sizeof(struct pvclock_vcpu_time_info)); + } else { + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time); + } return; } @@ -2249,12 +2376,12 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) /* Guest TSC same frequency as host TSC? */ if (!scale) { - kvm_vcpu_write_tsc_multiplier(vcpu, 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; @@ -2266,10 +2393,10 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) } /* 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) { + 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; @@ -2287,7 +2414,7 @@ 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 */ - kvm_vcpu_write_tsc_multiplier(vcpu, kvm_default_tsc_scaling_ratio); + kvm_vcpu_write_tsc_multiplier(vcpu, kvm_caps.default_tsc_scaling_ratio); return -1; } @@ -2321,10 +2448,12 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) return tsc; } +#ifdef CONFIG_X86_64 static inline int gtod_is_based_on_tsc(int mode) { return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK; } +#endif static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) { @@ -2362,18 +2491,18 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) * (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 ratio) +u64 kvm_scale_tsc(u64 tsc, u64 ratio) { u64 _tsc = tsc; - if (ratio != kvm_default_tsc_scaling_ratio) + if (ratio != kvm_caps.default_tsc_scaling_ratio) _tsc = __scale_tsc(ratio, tsc); return _tsc; @@ -2384,7 +2513,7 @@ static u64 kvm_compute_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) { u64 tsc; - tsc = kvm_scale_tsc(vcpu, rdtsc(), vcpu->arch.l1_tsc_scaling_ratio); + tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio); return target_tsc - tsc; } @@ -2392,7 +2521,7 @@ static u64 kvm_compute_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { return vcpu->arch.l1_tsc_offset + - kvm_scale_tsc(vcpu, host_tsc, vcpu->arch.l1_tsc_scaling_ratio); + kvm_scale_tsc(host_tsc, vcpu->arch.l1_tsc_scaling_ratio); } EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); @@ -2400,11 +2529,11 @@ u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier) { u64 nested_offset; - if (l2_multiplier == kvm_default_tsc_scaling_ratio) + 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_tsc_scaling_ratio_frac_bits); + kvm_caps.tsc_scaling_ratio_frac_bits); nested_offset += l2_offset; return nested_offset; @@ -2413,9 +2542,9 @@ EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_offset); u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier) { - if (l2_multiplier != kvm_default_tsc_scaling_ratio) + if (l2_multiplier != kvm_caps.default_tsc_scaling_ratio) return mul_u64_u64_shr(l1_multiplier, l2_multiplier, - kvm_tsc_scaling_ratio_frac_bits); + kvm_caps.tsc_scaling_ratio_frac_bits); return l1_multiplier; } @@ -2457,7 +2586,7 @@ static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multipli else vcpu->arch.tsc_scaling_ratio = l1_multiplier; - if (kvm_has_tsc_control) + if (kvm_caps.has_tsc_control) static_call(kvm_x86_write_tsc_multiplier)( vcpu, vcpu->arch.tsc_scaling_ratio); } @@ -2593,9 +2722,9 @@ static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) { - if (vcpu->arch.l1_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); } @@ -2817,7 +2946,7 @@ static void kvm_end_pvclock_update(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct kvm_vcpu *vcpu; - int i; + unsigned long i; write_seqcount_end(&ka->pvclock_sc); raw_spin_unlock_irq(&ka->tsc_write_lock); @@ -2831,7 +2960,7 @@ static void kvm_end_pvclock_update(struct kvm *kvm) static void kvm_update_masterclock(struct kvm *kvm) { - kvm_hv_invalidate_tsc_page(kvm); + kvm_hv_request_tsc_page_update(kvm); kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); kvm_end_pvclock_update(kvm); @@ -2891,63 +3020,55 @@ u64 get_kvmclock_ns(struct kvm *kvm) return data.clock; } -static void kvm_setup_pvclock_page(struct kvm_vcpu *v, - struct gfn_to_hva_cache *cache, - unsigned int offset) +static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, + struct gfn_to_pfn_cache *gpc, + unsigned int offset) { struct kvm_vcpu_arch *vcpu = &v->arch; - struct pvclock_vcpu_time_info guest_hv_clock; + struct pvclock_vcpu_time_info *guest_hv_clock; + unsigned long flags; - if (unlikely(kvm_read_guest_offset_cached(v->kvm, cache, - &guest_hv_clock, offset, sizeof(guest_hv_clock)))) - return; + read_lock_irqsave(&gpc->lock, flags); + while (!kvm_gfn_to_pfn_cache_check(v->kvm, gpc, gpc->gpa, + offset + sizeof(*guest_hv_clock))) { + read_unlock_irqrestore(&gpc->lock, flags); + + if (kvm_gfn_to_pfn_cache_refresh(v->kvm, gpc, gpc->gpa, + 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 + /* + * 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_offset_cached(v->kvm, cache, - &vcpu->hv_clock, offset, - sizeof(vcpu->hv_clock.version)); + guest_hv_clock->version = vcpu->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); + vcpu->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; } - trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock); + memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock)); + smp_wmb(); - kvm_write_guest_offset_cached(v->kvm, cache, - &vcpu->hv_clock, offset, - sizeof(vcpu->hv_clock)); + guest_hv_clock->version = ++vcpu->hv_clock.version; - smp_wmb(); + mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT); + read_unlock_irqrestore(&gpc->lock, flags); - vcpu->hv_clock.version++; - kvm_write_guest_offset_cached(v->kvm, cache, - &vcpu->hv_clock, offset, - sizeof(vcpu->hv_clock.version)); + trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock); } static int kvm_guest_time_update(struct kvm_vcpu *v) @@ -3014,8 +3135,8 @@ 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); if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) { @@ -3036,15 +3157,14 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.flags = pvclock_flags; - if (vcpu->pv_time_enabled) - kvm_setup_pvclock_page(v, &vcpu->pv_time, 0); - if (vcpu->xen.vcpu_info_set) - kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_info_cache, - offsetof(struct compat_vcpu_info, time)); - if (vcpu->xen.vcpu_time_info_set) - kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0); - if (!v->vcpu_idx) - kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); + if (vcpu->pv_time.active) + kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0); + if (vcpu->xen.vcpu_info_cache.active) + kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache, + offsetof(struct compat_vcpu_info, time)); + if (vcpu->xen.vcpu_time_info_cache.active) + kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0); + kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; } @@ -3066,7 +3186,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) static void kvmclock_update_fn(struct work_struct *work) { - int i; + unsigned long i; struct delayed_work *dwork = to_delayed_work(work); struct kvm_arch *ka = container_of(dwork, struct kvm_arch, kvmclock_update_work); @@ -3105,6 +3225,16 @@ static void kvmclock_sync_fn(struct work_struct *work) KVMCLOCK_SYNC_PERIOD); } +/* These helpers are safe iff @msr is known to be an MCx bank MSR. */ +static bool is_mci_control_msr(u32 msr) +{ + return (msr & 3) == 0; +} +static bool is_mci_status_msr(u32 msr) +{ + return (msr & 3) == 1; +} + /* * On AMD, HWCR[McStatusWrEn] controls whether setting MCi_STATUS results in #GP. */ @@ -3123,6 +3253,7 @@ 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: @@ -3136,32 +3267,53 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vcpu->arch.mcg_ctl = data; break; - default: - if (msr >= MSR_IA32_MC0_CTL && - msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = array_index_nospec( - msr - MSR_IA32_MC0_CTL, - MSR_IA32_MCx_CTL(bank_num) - 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; - - /* MCi_STATUS */ - if (!msr_info->host_initiated && - (offset & 0x3) == 1 && data != 0) { - if (!can_set_mci_status(vcpu)) - return -1; - } + 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; - vcpu->arch.mce_banks[offset] = data; - break; - } + 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: return 1; } return 0; @@ -3231,14 +3383,14 @@ static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data) static void kvmclock_reset(struct kvm_vcpu *vcpu) { - vcpu->arch.pv_time_enabled = false; + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time); vcpu->arch.time = 0; } static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; - static_call(kvm_x86_tlb_flush_all)(vcpu); + static_call(kvm_x86_flush_tlb_all)(vcpu); } static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) @@ -3256,14 +3408,14 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) kvm_mmu_sync_prev_roots(vcpu); } - static_call(kvm_x86_tlb_flush_guest)(vcpu); + static_call(kvm_x86_flush_tlb_guest)(vcpu); } static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; - static_call(kvm_x86_tlb_flush_current)(vcpu); + static_call(kvm_x86_flush_tlb_current)(vcpu); } /* @@ -3287,6 +3439,7 @@ 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; @@ -3304,13 +3457,12 @@ static void record_steal_time(struct kvm_vcpu *vcpu) slots = kvm_memslots(vcpu->kvm); if (unlikely(slots->generation != ghc->generation || + gpa != ghc->gpa || kvm_is_error_hva(ghc->hva) || !ghc->memslot)) { - gfn_t gfn = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; - /* 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, gfn, sizeof(*st)) || + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gpa, sizeof(*st)) || kvm_is_error_hva(ghc->hva) || !ghc->memslot) return; } @@ -3413,15 +3565,15 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated) return 1; - if (guest_cpuid_has(vcpu, X86_FEATURE_PDCM) && kvm_get_msr_feature(&msr_ent)) + if (kvm_get_msr_feature(&msr_ent)) return 1; if (data & ~msr_ent.data) return 1; vcpu->arch.perf_capabilities = data; - + kvm_pmu_refresh(vcpu); return 0; - } + } case MSR_EFER: return set_efer(vcpu, msr_info); case MSR_K7_HWCR: @@ -3445,7 +3597,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; } break; - case 0x200 ... 0x2ff: + case 0x200 ... MSR_IA32_MC0_CTL2 - 1: + case MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) ... 0x2ff: return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: return kvm_set_apic_base(vcpu, msr_info); @@ -3467,9 +3620,21 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.ia32_tsc_adjust_msr = data; } break; - case MSR_IA32_MISC_ENABLE: + 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) && - ((vcpu->arch.ia32_misc_enable_msr ^ data) & MSR_IA32_MISC_ENABLE_MWAIT)) { + ((old_val ^ data) & MSR_IA32_MISC_ENABLE_MWAIT)) { if (!guest_cpuid_has(vcpu, X86_FEATURE_XMM3)) return 1; vcpu->arch.ia32_misc_enable_msr = data; @@ -3478,6 +3643,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.ia32_misc_enable_msr = data; } break; + } case MSR_IA32_SMBASE: if (!msr_info->host_initiated) return 1; @@ -3504,9 +3670,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * IA32_XSS[bit 8]. Guests have to use RDMSR/WRMSR rather than * XSAVES/XRSTORS to save/restore PT MSRs. */ - if (data & ~supported_xss) + if (data & ~kvm_caps.supported_xss) return 1; vcpu->arch.ia32_xss = data; + kvm_update_cpuid_runtime(vcpu); break; case MSR_SMI_COUNT: if (!msr_info->host_initiated) @@ -3601,6 +3768,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) 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: @@ -3669,6 +3837,39 @@ 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_cpuid_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_cpuid_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_PEBS_ENABLE: + case MSR_IA32_DS_AREA: + case MSR_PEBS_DATA_CFG: + case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: + if (kvm_pmu_is_valid_msr(vcpu, msr)) + return kvm_pmu_set_msr(vcpu, msr_info); + /* + * Userspace is allowed to write '0' to MSRs that KVM reports + * as to-be-saved, even if an MSRs isn't fully supported. + */ + return !msr_info->host_initiated || data; default: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); @@ -3683,6 +3884,7 @@ 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: @@ -3700,16 +3902,27 @@ 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; - default: - if (msr >= MSR_IA32_MC0_CTL && - msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = array_index_nospec( - msr - MSR_IA32_MC0_CTL, - MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL); + 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; - data = vcpu->arch.mce_banks[offset]; - break; - } + 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: return 1; } *pdata = data; @@ -3749,9 +3962,16 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_DRAM_ENERGY_STATUS: /* DRAM controller */ msr_info->data = 0; break; + case MSR_IA32_PEBS_ENABLE: + case MSR_IA32_DS_AREA: + case MSR_PEBS_DATA_CFG: case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info); + /* + * Userspace is allowed to read MSRs that KVM reports as + * to-be-saved, even if an MSR isn't fully supported. + */ if (!msr_info->host_initiated) return 1; msr_info->data = 0; @@ -3802,11 +4022,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) ratio = vcpu->arch.tsc_scaling_ratio; } - msr_info->data = kvm_scale_tsc(vcpu, rdtsc(), ratio) + offset; + msr_info->data = kvm_scale_tsc(rdtsc(), ratio) + offset; break; } case MSR_MTRRcap: - case 0x200 ... 0x2ff: + case 0x200 ... MSR_IA32_MC0_CTL2 - 1: + case MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) ... 0x2ff: return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); case 0xcd: /* fsb frequency */ msr_info->data = 3; @@ -3922,6 +4143,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) 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: @@ -3989,6 +4211,22 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) 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_cpuid_has(vcpu, X86_FEATURE_XFD)) + return 1; + + msr_info->data = vcpu->arch.guest_fpu.fpstate->xfd; + break; + case MSR_IA32_XFD_ERR: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + return 1; + + msr_info->data = vcpu->arch.guest_fpu.xfd_err; + break; +#endif default: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info); @@ -4148,6 +4386,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) 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: @@ -4161,6 +4400,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) 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: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: @@ -4172,7 +4415,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) 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_SHARED_INFO | + KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL | + KVM_XEN_HVM_CONFIG_EVTCHN_SEND; if (sched_info_on()) r |= KVM_XEN_HVM_CONFIG_RUNSTATE; break; @@ -4200,9 +4445,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) */ r = static_call(kvm_x86_has_emulated_msr)(kvm, MSR_IA32_SMBASE); break; - case KVM_CAP_VAPIC: - r = !static_call(kvm_x86_cpu_has_accelerated_tpr)(); - break; case KVM_CAP_NR_VCPUS: r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS); break; @@ -4222,7 +4464,8 @@ 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; @@ -4244,17 +4487,76 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = sched_info_on(); break; case KVM_CAP_X86_BUS_LOCK_EXIT: - if (kvm_has_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: { + u64 guest_perm = xstate_get_guest_group_perm(); + + r = xstate_required_size(kvm_caps.supported_xcr0 & guest_perm, 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_X86_VALID_QUIRKS; + break; + case KVM_CAP_X86_NOTIFY_VMEXIT: + r = kvm_caps.has_notify_vmexit; + break; default: break; } return r; +} + +static inline void __user *kvm_get_attr_addr(struct kvm_device_attr *attr) +{ + void __user *uaddr = (void __user*)(unsigned long)attr->addr; + + if ((u64)(unsigned long)uaddr != attr->addr) + return ERR_PTR_USR(-EFAULT); + return uaddr; +} + +static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr) +{ + u64 __user *uaddr = kvm_get_attr_addr(attr); + + if (attr->group) + return -ENXIO; + + if (IS_ERR(uaddr)) + return PTR_ERR(uaddr); + + switch (attr->attr) { + case KVM_X86_XCOMP_GUEST_SUPP: + if (put_user(kvm_caps.supported_xcr0, uaddr)) + return -EFAULT; + return 0; + default: + return -ENXIO; + break; + } +} +static int kvm_x86_dev_has_attr(struct kvm_device_attr *attr) +{ + if (attr->group) + return -ENXIO; + + switch (attr->attr) { + case KVM_X86_XCOMP_GUEST_SUPP: + return 0; + default: + return -ENXIO; + } } long kvm_arch_dev_ioctl(struct file *filp, @@ -4312,8 +4614,8 @@ long kvm_arch_dev_ioctl(struct file *filp, } 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; @@ -4345,6 +4647,22 @@ long kvm_arch_dev_ioctl(struct file *filp, case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp); break; + 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; @@ -4422,7 +4740,21 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) 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; @@ -4436,6 +4768,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) slots = kvm_memslots(vcpu->kvm); if (unlikely(slots->generation != ghc->generation || + gpa != ghc->gpa || kvm_is_error_hva(ghc->hva) || !ghc->memslot)) return; @@ -4452,19 +4785,21 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { int idx; - if (vcpu->preempted && !vcpu->arch.guest_state_protected) - vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu); + if (vcpu->preempted) { + if (!vcpu->arch.guest_state_protected) + vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(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); + /* + * 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); + } static_call(kvm_x86_vcpu_put)(vcpu); vcpu->arch.last_host_tsc = rdtsc(); @@ -4519,7 +4854,7 @@ static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) return (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_accept_dm_intr(vcpu) && !kvm_event_needs_reinjection(vcpu) && - !vcpu->arch.exception.pending); + !kvm_is_exception_pending(vcpu)); } static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, @@ -4581,22 +4916,63 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, r = -EINVAL; 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); static_call(kvm_x86_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) { @@ -4606,6 +4982,12 @@ 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 @@ -4613,7 +4995,6 @@ 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 @@ -4648,25 +5029,38 @@ 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); if (kvm_check_request(KVM_REQ_SMI, vcpu)) process_smi(vcpu); /* - * 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). Unless the per-VM capability, - * KVM_CAP_EXCEPTION_PAYLOAD, is set, we may not defer the delivery of - * an exception payload and handle after a KVM_GET_VCPU_EVENTS. Since we - * opportunistically defer the exception payload, deliver it if the - * capability hasn't been requested before processing a - * KVM_GET_VCPU_EVENTS. + * 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 && - vcpu->arch.exception.pending && vcpu->arch.exception.has_payload) - kvm_deliver_exception_payload(vcpu); + ex->pending && ex->has_payload) + kvm_deliver_exception_payload(vcpu, ex); /* * The API doesn't provide the instruction length for software @@ -4674,26 +5068,25 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, * isn't advanced, we should expect to encounter the exception * again. */ - if (kvm_exception_is_soft(vcpu->arch.exception.nr)) { + if (kvm_exception_is_soft(ex->vector)) { events->exception.injected = 0; events->exception.pending = 0; } else { - events->exception.injected = vcpu->arch.exception.injected; - events->exception.pending = vcpu->arch.exception.pending; + 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; @@ -4719,6 +5112,10 @@ 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; + 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; + } memset(&events->reserved, 0, sizeof(events->reserved)); } @@ -4732,7 +5129,8 @@ 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) { @@ -4758,9 +5156,22 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, 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; @@ -4783,8 +5194,10 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { - if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) + if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { + kvm_x86_ops.nested_ops->leave_nested(vcpu); kvm_smm_changed(vcpu, events->smi.smm); + } vcpu->arch.smi_pending = events->smi.pending; @@ -4803,6 +5216,15 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, } } + 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); return 0; @@ -4853,6 +5275,16 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, vcpu->arch.pkru); } +static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, + u8 *state, unsigned int size) +{ + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) + return; + + fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, + state, size, vcpu->arch.pkru); +} + static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { @@ -4861,7 +5293,8 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu, guest_xsave->region, - supported_xcr0, &vcpu->arch.pkru); + kvm_caps.supported_xcr0, + &vcpu->arch.pkru); } static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, @@ -4909,7 +5342,7 @@ 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); @@ -4935,11 +5368,11 @@ static int kvm_arch_tsc_has_attr(struct kvm_vcpu *vcpu, static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - u64 __user *uaddr = (u64 __user *)(unsigned long)attr->addr; + u64 __user *uaddr = kvm_get_attr_addr(attr); int r; - if ((u64)(unsigned long)uaddr != attr->addr) - return -EFAULT; + if (IS_ERR(uaddr)) + return PTR_ERR(uaddr); switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: @@ -4958,12 +5391,12 @@ static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - u64 __user *uaddr = (u64 __user *)(unsigned long)attr->addr; + u64 __user *uaddr = kvm_get_attr_addr(attr); struct kvm *kvm = vcpu->kvm; int r; - if ((u64)(unsigned long)uaddr != attr->addr) - return -EFAULT; + if (IS_ERR(uaddr)) + return PTR_ERR(uaddr); switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: { @@ -4981,7 +5414,7 @@ static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, kvm->arch.last_tsc_khz == vcpu->arch.virtual_tsc_khz && kvm->arch.last_tsc_offset == offset); - tsc = kvm_scale_tsc(vcpu, rdtsc(), vcpu->arch.l1_tsc_scaling_ratio) + 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); @@ -5148,17 +5581,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_cpuid __user *cpuid_arg = argp; struct kvm_cpuid cpuid; - /* - * KVM does not correctly handle changing guest CPUID after KVM_RUN, as - * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't - * tracked in kvm_mmu_page_role. As a result, KVM may miss guest page - * faults due to reusing SPs/SPTEs. In practice no sane VMM mucks with - * the core vCPU model on the fly, so fail. - */ - r = -EINVAL; - if (vcpu->arch.last_vmentry_cpu != -1) - goto out; - r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; @@ -5169,14 +5591,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; - /* - * KVM_SET_CPUID{,2} after KVM_RUN is forbidded, see the comment in - * KVM_SET_CPUID case above. - */ - r = -EINVAL; - if (vcpu->arch.last_vmentry_cpu != -1) - goto out; - r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; @@ -5306,6 +5720,10 @@ 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_ACCOUNT); r = -ENOMEM; if (!u.xsave) @@ -5320,7 +5738,9 @@ 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; @@ -5329,6 +5749,25 @@ 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_ACCOUNT); + r = -ENOMEM; + if (!u.xsave) + break; + + kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size); + + 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_ACCOUNT); r = -ENOMEM; @@ -5360,8 +5799,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EINVAL; user_tsc_khz = (u32)arg; - if (kvm_has_tsc_control && - 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) @@ -5693,7 +6132,7 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) * VM-Exit. */ struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) kvm_vcpu_kick(vcpu); @@ -5720,6 +6159,11 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, return -EINVAL; switch (cap->cap) { + case KVM_CAP_DISABLE_QUIRKS2: + r = -EINVAL; + if (cap->args[0] & ~KVM_X86_VALID_QUIRKS) + break; + fallthrough; case KVM_CAP_DISABLE_QUIRKS: kvm->arch.disabled_quirks = cap->args[0]; r = 0; @@ -5741,7 +6185,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT; kvm->arch.nr_reserved_ioapic_pins = cap->args[0]; - kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT); + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_ABSENT); r = 0; split_irqchip_unlock: mutex_unlock(&kvm->lock); @@ -5783,7 +6227,16 @@ split_irqchip_unlock: 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_INVAL | + KVM_MSR_EXIT_REASON_UNKNOWN | + KVM_MSR_EXIT_REASON_FILTER)) + break; kvm->arch.user_space_msr_mask = cap->args[0]; r = 0; break; @@ -5796,7 +6249,7 @@ split_irqchip_unlock: (cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT)) break; - if (kvm_has_bus_lock_exit && + if (kvm_caps.has_bus_lock_exit && cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT) kvm->arch.bus_lock_detection_enabled = true; r = 0; @@ -5820,15 +6273,18 @@ split_irqchip_unlock: #endif case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: r = -EINVAL; - if (kvm_x86_ops.vm_copy_enc_context_from) - r = kvm_x86_ops.vm_copy_enc_context_from(kvm, cap->args[0]); - return r; + if (!kvm_x86_ops.vm_copy_enc_context_from) + break; + + r = static_call(kvm_x86_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) - r = kvm_x86_ops.vm_move_enc_context_from( - kvm, cap->args[0]); - return r; + if (!kvm_x86_ops.vm_move_enc_context_from) + break; + + r = static_call(kvm_x86_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; @@ -5844,6 +6300,77 @@ split_irqchip_unlock: 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.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; default: r = -EINVAL; break; @@ -5910,23 +6437,22 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, return 0; } -static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) +static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, + struct kvm_msr_filter *filter) { - struct kvm_msr_filter __user *user_msr_filter = argp; struct kvm_x86_msr_filter *new_filter, *old_filter; - struct kvm_msr_filter filter; bool default_allow; bool empty = true; int r = 0; u32 i; - if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) - return -EFAULT; + if (filter->flags & ~KVM_MSR_FILTER_DEFAULT_DENY) + return -EINVAL; - for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) - empty &= !filter.ranges[i].nmsrs; + for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) + empty &= !filter->ranges[i].nmsrs; - default_allow = !(filter.flags & KVM_MSR_FILTER_DEFAULT_DENY); + default_allow = !(filter->flags & KVM_MSR_FILTER_DEFAULT_DENY); if (empty && !default_allow) return -EINVAL; @@ -5934,8 +6460,8 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) if (!new_filter) return -ENOMEM; - for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { - r = kvm_add_msr_filter(new_filter, &filter.ranges[i]); + 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; @@ -5958,15 +6484,72 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) return 0; } +#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) +{ + void __user *argp = (void __user *)arg; + struct kvm *kvm = filp->private_data; + long r = -ENOTTY; + + 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, + }; + } + + r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); + break; + } + } + + return r; +} +#endif + #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER static int kvm_arch_suspend_notifier(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i, ret = 0; + unsigned long i; + int ret = 0; mutex_lock(&kvm->lock); kvm_for_each_vcpu(i, vcpu, kvm) { - if (!vcpu->arch.pv_time_enabled) + if (!vcpu->arch.pv_time.active) continue; ret = kvm_set_guest_paused(vcpu); @@ -6020,7 +6603,7 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) if (data.flags & ~KVM_CLOCK_VALID_FLAGS) return -EINVAL; - kvm_hv_invalidate_tsc_page(kvm); + kvm_hv_request_tsc_page_update(kvm); kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); @@ -6122,7 +6705,7 @@ set_identity_unlock: /* Write kvm->irq_routing before enabling irqchip_in_kernel. */ smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL; - kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT); + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_ABSENT); create_irqchip_unlock: mutex_unlock(&kvm->lock); break; @@ -6293,6 +6876,15 @@ set_pit2_out: r = kvm_xen_hvm_set_attr(kvm, &xha); break; } + case KVM_XEN_HVM_EVTCHN_SEND: { + struct kvm_irq_routing_xen_evtchn uxe; + + r = -EFAULT; + if (copy_from_user(&uxe, argp, sizeof(uxe))) + goto out; + r = kvm_xen_hvm_evtchn_send(kvm, &uxe); + break; + } #endif case KVM_SET_CLOCK: r = kvm_vm_ioctl_set_clock(kvm, argp); @@ -6300,10 +6892,34 @@ set_pit2_out: 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; + + WRITE_ONCE(kvm->arch.default_tsc_khz, user_tsc_khz); + r = 0; + + 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_op) - r = static_call(kvm_x86_mem_enc_op)(kvm, argp); + if (!kvm_x86_ops.mem_enc_ioctl) + goto out; + + r = static_call(kvm_x86_mem_enc_ioctl)(kvm, argp); break; } case KVM_MEMORY_ENCRYPT_REG_REGION: { @@ -6314,8 +6930,10 @@ set_pit2_out: goto out; r = -ENOTTY; - if (kvm_x86_ops.mem_enc_reg_region) - r = static_call(kvm_x86_mem_enc_reg_region)(kvm, ®ion); + if (!kvm_x86_ops.mem_enc_register_region) + goto out; + + r = static_call(kvm_x86_mem_enc_register_region)(kvm, ®ion); break; } case KVM_MEMORY_ENCRYPT_UNREG_REGION: { @@ -6326,8 +6944,10 @@ set_pit2_out: goto out; r = -ENOTTY; - if (kvm_x86_ops.mem_enc_unreg_region) - r = static_call(kvm_x86_mem_enc_unreg_region)(kvm, ®ion); + if (!kvm_x86_ops.mem_enc_unregister_region) + goto out; + + r = static_call(kvm_x86_mem_enc_unregister_region)(kvm, ®ion); break; } case KVM_HYPERV_EVENTFD: { @@ -6342,9 +6962,16 @@ set_pit2_out: case KVM_SET_PMU_EVENT_FILTER: r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); break; - case KVM_X86_SET_MSR_FILTER: - r = kvm_vm_ioctl_set_msr_filter(kvm, argp); + 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; } @@ -6354,15 +6981,12 @@ out: static void kvm_init_msr_list(void) { - struct x86_pmu_capability x86_pmu; u32 dummy[2]; unsigned i; - BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4, + BUILD_BUG_ON_MSG(KVM_PMC_MAX_FIXED != 3, "Please update the fixed PMCs in msrs_to_saved_all[]"); - perf_get_x86_pmu_capability(&x86_pmu); - num_msrs_to_save = 0; num_emulated_msrs = 0; num_msr_based_features = 0; @@ -6412,14 +7036,19 @@ static void kvm_init_msr_list(void) intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) continue; break; - case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17: + case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX: if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >= - min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) + min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) continue; break; - case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17: + case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX: if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= - min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) + min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) + continue; + break; + case MSR_IA32_XFD: + case MSR_IA32_XFD_ERR: + if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) continue; break; default: @@ -6502,16 +7131,17 @@ void kvm_get_segment(struct kvm_vcpu *vcpu, static_call(kvm_x86_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; } @@ -6519,25 +7149,31 @@ 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 = (static_call(kvm_x86_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; + + u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; + return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read); gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + + u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_FETCH_MASK; - return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); + return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + + u64 access = (static_call(kvm_x86_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_GPL(kvm_mmu_gva_to_gpa_write); @@ -6545,24 +7181,26 @@ EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_write); 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); @@ -6585,14 +7223,15 @@ 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 = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + u64 access = (static_call(kvm_x86_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); @@ -6610,7 +7249,7 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { - u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; + u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; /* * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED @@ -6629,9 +7268,11 @@ static int emulator_read_std(struct x86_emulate_ctxt *ctxt, struct x86_exception *exception, bool system) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - u32 access = 0; + u64 access = 0; - if (!system && static_call(kvm_x86_get_cpl)(vcpu) == 3) + if (system) + access |= PFERR_IMPLICIT_ACCESS; + else if (static_call(kvm_x86_get_cpl)(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); @@ -6647,21 +7288,20 @@ static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt, } 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) { @@ -6682,9 +7322,11 @@ 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 && static_call(kvm_x86_get_cpl)(vcpu) == 3) + if (system) + access |= PFERR_IMPLICIT_ACCESS; + else if (static_call(kvm_x86_get_cpl)(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, @@ -6702,20 +7344,30 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, } EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); +static int kvm_can_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) +{ + return static_call(kvm_x86_can_emulate_instruction)(vcpu, emul_type, + insn, insn_len); +} + 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; char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; - if (unlikely(!static_call(kvm_x86_can_emulate_instruction)(vcpu, NULL, 0))) + if (unlikely(!kvm_can_emulate_insn(vcpu, emul_type, NULL, 0))) return 1; - if (force_emulation_prefix && + if (fep_flags && kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu), sig, sizeof(sig), &e) == 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 = EMULTYPE_TRAP_UD_FORCED; } @@ -6743,7 +7395,8 @@ 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 = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0) + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + u64 access = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0) | (write ? PFERR_WRITE_MASK : 0); /* @@ -6760,9 +7413,9 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, 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); @@ -6977,15 +7630,8 @@ 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, @@ -6994,12 +7640,11 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, unsigned int bytes, struct x86_exception *exception) { - struct kvm_host_map map; struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u64 page_line_mask; + unsigned long hva; gpa_t gpa; - char *kaddr; - bool exchanged; + int r; /* guests cmpxchg8b have to be emulated atomically */ if (bytes > 8 || (bytes & (bytes - 1))) @@ -7007,7 +7652,7 @@ 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; @@ -7023,31 +7668,32 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (((gpa + bytes - 1) & page_line_mask) != (gpa & page_line_mask)) goto emul_write; - if (kvm_vcpu_map(vcpu, gpa_to_gfn(gpa), &map)) + hva = kvm_vcpu_gfn_to_hva(vcpu, gpa_to_gfn(gpa)); + if (kvm_is_error_hva(hva)) goto emul_write; - kaddr = map.hva + 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(); } - kvm_vcpu_unmap(vcpu, &map, true); - - if (!exchanged) + if (r < 0) + return X86EMUL_UNHANDLEABLE; + if (r) return X86EMUL_CMPXCHG_FAILED; kvm_page_track_write(vcpu, gpa, new, bytes); @@ -7060,36 +7706,47 @@ emul_write: 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, - 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)) - 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; @@ -7097,30 +7754,33 @@ 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, unsigned int count) +static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, + unsigned short port, void *val, unsigned int count) { - WARN_ON(vcpu->arch.pio.count); - memset(vcpu->arch.pio_data, 0, size * count); - return emulator_pio_in_out(vcpu, size, port, count, true); + 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 count = vcpu->arch.pio.count; + 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(struct kvm_vcpu *vcpu, int size, - unsigned short port, void *val, unsigned int count) +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); if (vcpu->arch.pio.count) { /* * Complete a previous iteration that required userspace I/O. @@ -7129,39 +7789,19 @@ static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, * shenanigans as KVM doesn't support modifying the rep count, * and the emulator ensures @count doesn't overflow the buffer. */ - } else { - int r = __emulator_pio_in(vcpu, size, port, count); - if (!r) - return r; - - /* Results already available, fall through. */ + complete_emulator_pio_in(vcpu, val); + return 1; } - complete_emulator_pio_in(vcpu, val); - return 1; -} - -static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, - int size, unsigned short port, void *val, - unsigned int count) -{ - return emulator_pio_in(emul_to_vcpu(ctxt), size, port, val, count); - + 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) { - int ret; - - memcpy(vcpu->arch.pio_data, val, size * count); - trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data); - ret = emulator_pio_in_out(vcpu, size, port, count, false); - if (ret) - vcpu->arch.pio.count = 0; - - return ret; + 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, @@ -7386,36 +8026,62 @@ 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 kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int r; - r = kvm_get_msr(vcpu, msr_index, pdata); + r = kvm_get_msr_with_filter(vcpu, msr_index, pdata); + if (r < 0) + return X86EMUL_UNHANDLEABLE; - if (r && kvm_get_msr_user_space(vcpu, msr_index, r)) { - /* Bounce to user space */ - return X86EMUL_IO_NEEDED; + if (r) { + if (kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0, + complete_emulated_rdmsr, r)) + return X86EMUL_IO_NEEDED; + + trace_kvm_msr_read_ex(msr_index); + return X86EMUL_PROPAGATE_FAULT; } - return r; + trace_kvm_msr_read(msr_index, *pdata); + return X86EMUL_CONTINUE; } -static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, - u32 msr_index, u64 data) +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_set_msr(vcpu, msr_index, data); + r = kvm_set_msr_with_filter(vcpu, msr_index, data); + if (r < 0) + return X86EMUL_UNHANDLEABLE; - if (r && kvm_set_msr_user_space(vcpu, msr_index, data, r)) { - /* Bounce to user space */ - return X86EMUL_IO_NEEDED; + 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 r; + trace_kvm_msr_write(msr_index, data); + return X86EMUL_CONTINUE; +} + +static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, + u32 msr_index, u64 *pdata) +{ + return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); +} + +static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, + u32 msr_index, u64 data) +{ + return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data); } static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt) @@ -7481,6 +8147,11 @@ static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt) return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR); } +static bool emulator_guest_has_rdpid(struct x86_emulate_ctxt *ctxt) +{ + return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID); +} + static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg) { return kvm_register_read_raw(emul_to_vcpu(ctxt), reg); @@ -7524,7 +8195,16 @@ 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 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, @@ -7551,6 +8231,8 @@ static const struct x86_emulate_ops emulate_ops = { .set_dr = emulator_set_dr, .get_smbase = emulator_get_smbase, .set_smbase = emulator_set_smbase, + .set_msr_with_filter = emulator_set_msr_with_filter, + .get_msr_with_filter = emulator_get_msr_with_filter, .set_msr = emulator_set_msr, .get_msr = emulator_get_msr, .check_pmc = emulator_check_pmc, @@ -7563,6 +8245,7 @@ static const struct x86_emulate_ops emulate_ops = { .guest_has_long_mode = emulator_guest_has_long_mode, .guest_has_movbe = emulator_guest_has_movbe, .guest_has_fxsr = emulator_guest_has_fxsr, + .guest_has_rdpid = emulator_guest_has_rdpid, .set_nmi_mask = emulator_set_nmi_mask, .get_hflags = emulator_get_hflags, .exiting_smm = emulator_exiting_smm, @@ -7590,18 +8273,17 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) } } -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_inject_emulated_page_fault(vcpu, &ctxt->exception); - 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) @@ -7787,7 +8469,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF))) return false; - if (!vcpu->arch.mmu->direct_map) { + if (!vcpu->arch.mmu->root_role.direct) { /* * Write permission should be allowed since only * write access need to be emulated. @@ -7798,7 +8480,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * If the mapping is invalid in guest, let cpu retry * it to generate fault. */ - if (gpa == UNMAPPED_GVA) + if (gpa == INVALID_GPA) return true; } @@ -7820,7 +8502,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, kvm_release_pfn_clean(pfn); /* The instructions are well-emulated on direct mmu. */ - if (vcpu->arch.mmu->direct_map) { + if (vcpu->arch.mmu->root_role.direct) { unsigned int indirect_shadow_pages; write_lock(&vcpu->kvm->mmu_lock); @@ -7888,7 +8570,7 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, vcpu->arch.last_retry_eip = ctxt->eip; vcpu->arch.last_retry_addr = cr2_or_gpa; - if (!vcpu->arch.mmu->direct_map) + if (!vcpu->arch.mmu->root_role.direct) gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); @@ -7961,6 +8643,8 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) if (unlikely(!r)) return 0; + kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS); + /* * rflags is the old, "raw" value of the flags. The new value has * not been saved yet. @@ -7975,8 +8659,46 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(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) { + u32 shadow; + + if (kvm_get_rflags(vcpu) & X86_EFLAGS_RF) + return true; + + /* + * Intel CPUs inhibit code #DBs when MOV/POP SS blocking is active, + * but AMD CPUs do not. MOV/POP SS blocking is rare, check that first + * to avoid the relatively expensive CPUID lookup. + */ + shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); + return (shadow & KVM_X86_SHADOW_INT_MOV_SS) && + guest_cpuid_is_intel(vcpu); +} + +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; @@ -7996,7 +8718,7 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) } 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, @@ -8044,25 +8766,23 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) } /* - * Decode to be emulated instruction. Return EMULATION_OK if success. + * 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) { - int r = EMULATION_OK; struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; + int r; init_emulate_ctxt(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. - */ - if (!(emulation_type & EMULTYPE_SKIP) && - kvm_vcpu_check_breakpoint(vcpu, &r)) - return r; - r = x86_decode_insn(ctxt, insn, insn_len, emulation_type); trace_kvm_emulate_insn_start(vcpu); @@ -8080,7 +8800,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, bool writeback = true; bool write_fault_to_spt; - if (unlikely(!static_call(kvm_x86_can_emulate_instruction)(vcpu, insn, insn_len))) + if (unlikely(!kvm_can_emulate_insn(vcpu, emulation_type, insn, insn_len))) return 1; vcpu->arch.l1tf_flush_l1d = true; @@ -8095,6 +8815,14 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, if (!(emulation_type & EMULTYPE_NO_DECODE)) { kvm_clear_exception_queue(vcpu); + /* + * 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 (kvm_vcpu_check_code_breakpoint(vcpu, emulation_type, &r)) + return r; + r = x86_decode_emulated_instruction(vcpu, emulation_type, insn, insn_len); if (r != EMULATION_OK) { @@ -8128,12 +8856,23 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, } /* - * Note, EMULTYPE_SKIP 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. + * 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 (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 1; @@ -8155,7 +8894,7 @@ restart: ctxt->exception.address = cr2_or_gpa; /* With shadow page tables, cr2 contains a GVA or nGPA. */ - if (vcpu->arch.mmu->direct_map) { + if (vcpu->arch.mmu->root_role.direct) { ctxt->gpa_available = true; ctxt->gpa_val = cr2_or_gpa; } @@ -8179,8 +8918,7 @@ restart: if (ctxt->have_exception) { r = 1; - if (inject_emulated_exception(vcpu)) - return r; + inject_emulated_exception(vcpu); } else if (vcpu->arch.pio.count) { if (!vcpu->arch.pio.in) { /* FIXME: return into emulator if single-stepping. */ @@ -8197,22 +8935,34 @@ restart: writeback = false; 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 = 1; +writeback: if (writeback) { unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + + /* + * 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) { + kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS); + if (ctxt->is_branch) + kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); kvm_rip_write(vcpu, ctxt->eip); if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) r = kvm_vcpu_do_singlestep(vcpu); - if (kvm_x86_ops.update_emulated_instruction) - static_call(kvm_x86_update_emulated_instruction)(vcpu); + static_call_cond(kvm_x86_update_emulated_instruction)(vcpu); __kvm_set_rflags(vcpu, ctxt->eflags); } @@ -8299,11 +9049,7 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu) /* For size less than 4 we merge, else we zero extend */ val = (vcpu->arch.pio.size < 4) ? kvm_rax_read(vcpu) : 0; - /* - * Since vcpu->arch.pio.count == 1 let emulator_pio_in perform - * the copy and tracing - */ - emulator_pio_in(vcpu, vcpu->arch.pio.size, vcpu->arch.pio.port, &val, 1); + complete_emulator_pio_in(vcpu, &val); kvm_rax_write(vcpu, val); return kvm_skip_emulated_instruction(vcpu); @@ -8378,7 +9124,7 @@ static void kvm_hyperv_tsc_notifier(void) /* 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; + kvm_caps.max_guest_tsc_khz = tsc_khz; list_for_each_entry(kvm, &vm_list, vm_list) { __kvm_start_pvclock_update(kvm); @@ -8394,7 +9140,8 @@ static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu) { 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, @@ -8495,22 +9242,22 @@ 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; - - 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); + 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(); } - put_cpu(); -#endif cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); } @@ -8519,57 +9266,12 @@ static void kvm_timer_init(void) 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 = static_call(kvm_x86_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 void kvm_handle_intel_pt_intr(void) -{ - struct kvm_vcpu *vcpu = __this_cpu_read(current_vcpu); - - kvm_make_request(KVM_REQ_PMI, vcpu); - __set_bit(MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT, - (unsigned long *)&vcpu->arch.pmu.global_status); -} - -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, - .handle_intel_pt_intr = kvm_handle_intel_pt_intr, -}; - #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; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) @@ -8623,25 +9325,23 @@ static struct notifier_block pvclock_gtod_notifier = { int kvm_arch_init(void *opaque) { struct kvm_x86_init_ops *ops = opaque; + u64 host_pat; int r; if (kvm_x86_ops.hardware_enable) { pr_err("kvm: already loaded vendor module '%s'\n", kvm_x86_ops.name); - r = -EEXIST; - goto out; + return -EEXIST; } if (!ops->cpu_has_kvm_support()) { pr_err_ratelimited("kvm: no hardware support for '%s'\n", ops->runtime_ops->name); - r = -EOPNOTSUPP; - goto out; + return -EOPNOTSUPP; } if (ops->disabled_by_bios()) { pr_err_ratelimited("kvm: support for '%s' disabled by bios\n", ops->runtime_ops->name); - r = -EOPNOTSUPP; - goto out; + return -EOPNOTSUPP; } /* @@ -8651,40 +9351,54 @@ int kvm_arch_init(void *opaque) */ if (!boot_cpu_has(X86_FEATURE_FPU) || !boot_cpu_has(X86_FEATURE_FXSR)) { printk(KERN_ERR "kvm: inadequate fpu\n"); - r = -EOPNOTSUPP; - goto out; + return -EOPNOTSUPP; } - r = -ENOMEM; + if (IS_ENABLED(CONFIG_PREEMPT_RT) && !boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + pr_err("RT requires X86_FEATURE_CONSTANT_TSC\n"); + return -EOPNOTSUPP; + } + + /* + * 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 (rdmsrl_safe(MSR_IA32_CR_PAT, &host_pat) || + (host_pat & GENMASK(2, 0)) != 6) { + pr_err("kvm: host PAT[0] is not WB\n"); + return -EIO; + } x86_emulator_cache = kvm_alloc_emulator_cache(); if (!x86_emulator_cache) { pr_err("kvm: failed to allocate cache for x86 emulator\n"); - goto out; + return -ENOMEM; } user_return_msrs = alloc_percpu(struct kvm_user_return_msrs); if (!user_return_msrs) { printk(KERN_ERR "kvm: failed to allocate percpu kvm_user_return_msrs\n"); + r = -ENOMEM; goto out_free_x86_emulator_cache; } kvm_nr_uret_msrs = 0; - r = kvm_mmu_module_init(); + r = kvm_mmu_vendor_module_init(); if (r) goto out_free_percpu; kvm_timer_init(); - perf_register_guest_info_callbacks(&kvm_guest_cbs); - if (boot_cpu_has(X86_FEATURE_XSAVE)) { host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0; + kvm_caps.supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0; } if (pi_inject_timer == -1) - pi_inject_timer = housekeeping_enabled(HK_FLAG_TIMER); + pi_inject_timer = housekeeping_enabled(HK_TYPE_TIMER); #ifdef CONFIG_X86_64 pvclock_gtod_register_notifier(&pvclock_gtod_notifier); @@ -8698,7 +9412,6 @@ out_free_percpu: free_percpu(user_return_msrs); out_free_x86_emulator_cache: kmem_cache_destroy(x86_emulator_cache); -out: return r; } @@ -8709,7 +9422,6 @@ void kvm_arch_exit(void) clear_hv_tscchange_cb(); #endif kvm_lapic_exit(); - perf_unregister_guest_info_callbacks(&kvm_guest_cbs); if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block, @@ -8721,7 +9433,7 @@ void kvm_arch_exit(void) cancel_work_sync(&pvclock_gtod_work); #endif kvm_x86_ops.hardware_enable = NULL; - kvm_mmu_module_exit(); + kvm_mmu_vendor_module_exit(); free_percpu(user_return_msrs); kmem_cache_destroy(x86_emulator_cache); #ifdef CONFIG_KVM_XEN @@ -8730,8 +9442,15 @@ void kvm_arch_exit(void) #endif } -static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) +static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) { + /* + * The vCPU has halted, e.g. executed HLT. Update the run state if the + * local APIC is in-kernel, the run loop will detect the non-runnable + * state and halt the vCPU. Exit to userspace if the local APIC is + * managed by userspace, in which case userspace is responsible for + * handling wake events. + */ ++vcpu->stat.halt_exits; if (lapic_in_kernel(vcpu)) { vcpu->arch.mp_state = state; @@ -8742,11 +9461,11 @@ static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) } } -int kvm_vcpu_halt(struct kvm_vcpu *vcpu) +int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu) { - return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); } -EXPORT_SYMBOL_GPL(kvm_vcpu_halt); +EXPORT_SYMBOL_GPL(kvm_emulate_halt_noskip); int kvm_emulate_halt(struct kvm_vcpu *vcpu) { @@ -8755,7 +9474,7 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered * KVM_EXIT_DEBUG here. */ - return kvm_vcpu_halt(vcpu) && ret; + return kvm_emulate_halt_noskip(vcpu) && ret; } EXPORT_SYMBOL_GPL(kvm_emulate_halt); @@ -8763,7 +9482,8 @@ int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) { int ret = kvm_skip_emulated_instruction(vcpu); - return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, KVM_EXIT_AP_RESET_HOLD) && ret; + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, + KVM_EXIT_AP_RESET_HOLD) && ret; } EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); @@ -8779,6 +9499,13 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK) return -KVM_EOPNOTSUPP; + /* + * 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; @@ -8802,17 +9529,19 @@ 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 = APIC_DEST_NOSHORT; - lapic_irq.dest_mode = APIC_DEST_PHYSICAL; - 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); } @@ -8822,15 +9551,37 @@ bool kvm_apicv_activated(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_apicv_activated); +bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu) +{ + ulong vm_reasons = READ_ONCE(vcpu->kvm->arch.apicv_inhibit_reasons); + ulong vcpu_reasons = static_call(kvm_x86_vcpu_get_apicv_inhibit_reasons)(vcpu); + + return (vm_reasons | vcpu_reasons) == 0; +} +EXPORT_SYMBOL_GPL(kvm_vcpu_apicv_activated); + +static void set_or_clear_apicv_inhibit(unsigned long *inhibits, + enum kvm_apicv_inhibit reason, bool set) +{ + 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) { + unsigned long *inhibits = &kvm->arch.apicv_inhibit_reasons; + init_rwsem(&kvm->arch.apicv_update_lock); - set_bit(APICV_INHIBIT_REASON_ABSENT, - &kvm->arch.apicv_inhibit_reasons); + set_or_clear_apicv_inhibit(inhibits, APICV_INHIBIT_REASON_ABSENT, true); + if (!enable_apicv) - set_bit(APICV_INHIBIT_REASON_DISABLE, - &kvm->arch.apicv_inhibit_reasons); + set_or_clear_apicv_inhibit(inhibits, + APICV_INHIBIT_REASON_DISABLE, true); } static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) @@ -8921,7 +9672,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) if (!guest_pv_has(vcpu, KVM_FEATURE_PV_UNHALT)) break; - kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1); + kvm_pv_kick_cpu_op(vcpu->kvm, a1); kvm_sched_yield(vcpu, a1); ret = 0; break; @@ -8985,6 +9736,17 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) char instruction[3]; unsigned long rip = kvm_rip_read(vcpu); + /* + * 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; + } + static_call(kvm_x86_patch_hypercall)(vcpu, instruction); return emulator_write_emulated(ctxt, rip, instruction, 3, @@ -8997,31 +9759,18 @@ 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; - /* - * if_flag is obsolete and useless, so do not bother - * setting it for SEV-ES guests. Userspace can just - * use kvm_run->ready_for_interrupt_injection. - */ - kvm_run->if_flag = !vcpu->arch.guest_state_protected - && (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; - + kvm_run->if_flag = static_call(kvm_x86_get_if_flag)(vcpu); kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); - /* - * The call to kvm_ready_for_interrupt_injection() may end up in - * kvm_xen_has_interrupt() which may require the srcu lock to be - * held, to protect against changes in the vcpu_info address. - */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_run->ready_for_interrupt_injection = pic_in_kernel(vcpu->kvm) || kvm_vcpu_ready_for_interrupt_injection(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (is_smm(vcpu)) kvm_run->flags |= KVM_RUN_X86_SMM; @@ -9037,7 +9786,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) if (!lapic_in_kernel(vcpu)) return; - if (vcpu->arch.apicv_active) + if (vcpu->arch.apic->apicv_active) return; if (!vcpu->arch.apic->vapic_addr) @@ -9066,76 +9815,155 @@ int kvm_check_nested_events(struct kvm_vcpu *vcpu) static void kvm_inject_exception(struct kvm_vcpu *vcpu) { + trace_kvm_inj_exception(vcpu->arch.exception.vector, + vcpu->arch.exception.has_error_code, + vcpu->arch.exception.error_code, + vcpu->arch.exception.injected); + if (vcpu->arch.exception.error_code && !is_protmode(vcpu)) vcpu->arch.exception.error_code = false; - static_call(kvm_x86_queue_exception)(vcpu); + static_call(kvm_x86_inject_exception)(vcpu); } -static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) +/* + * 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 + * asynchrounous 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; - bool can_inject = true; - /* try to reinject previous events if any */ + /* + * Process nested events first, as nested VM-Exit supercedes 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; - if (vcpu->arch.exception.injected) { - kvm_inject_exception(vcpu); - can_inject = false; - } /* - * 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. + * 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. */ - else if (!vcpu->arch.exception.pending) { - if (vcpu->arch.nmi_injected) { - static_call(kvm_x86_set_nmi)(vcpu); - can_inject = false; - } else if (vcpu->arch.interrupt.injected) { - static_call(kvm_x86_set_irq)(vcpu); - can_inject = false; - } - } + if (vcpu->arch.exception.injected) + kvm_inject_exception(vcpu); + else if (kvm_is_exception_pending(vcpu)) + ; /* see above */ + else if (vcpu->arch.nmi_injected) + static_call(kvm_x86_inject_nmi)(vcpu); + else if (vcpu->arch.interrupt.injected) + static_call(kvm_x86_inject_irq)(vcpu, true); + /* + * 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); /* - * 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. + * 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 (is_guest_mode(vcpu)) { - r = kvm_check_nested_events(vcpu); - if (r < 0) - goto out; - } + if (r < 0) + goto out; - /* 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); + /* + * 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); - vcpu->arch.exception.pending = false; - vcpu->arch.exception.injected = true; + /* + * 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 (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT) + 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) { - 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); @@ -9143,6 +9971,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) } kvm_inject_exception(vcpu); + + vcpu->arch.exception.pending = false; + vcpu->arch.exception.injected = true; + can_inject = false; } @@ -9181,7 +10013,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) if (r) { --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; - static_call(kvm_x86_set_nmi)(vcpu); + static_call(kvm_x86_inject_nmi)(vcpu); can_inject = false; WARN_ON(static_call(kvm_x86_nmi_allowed)(vcpu, true) < 0); } @@ -9195,7 +10027,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) goto out; if (r) { kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), false); - static_call(kvm_x86_set_irq)(vcpu); + static_call(kvm_x86_inject_irq)(vcpu, false); WARN_ON(static_call(kvm_x86_interrupt_allowed)(vcpu, true) < 0); } if (kvm_cpu_has_injectable_intr(vcpu)) @@ -9203,11 +10035,24 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) } if (is_guest_mode(vcpu) && - kvm_x86_ops.nested_ops->hv_timer_pending && - kvm_x86_ops.nested_ops->hv_timer_pending(vcpu)) + kvm_x86_ops.nested_ops->has_events && + kvm_x86_ops.nested_ops->has_events(vcpu)) *req_immediate_exit = true; - WARN_ON(vcpu->arch.exception.pending); + /* + * 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: @@ -9488,18 +10333,23 @@ void kvm_make_scan_ioapic_request(struct kvm *kvm) void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) { + struct kvm_lapic *apic = vcpu->arch.apic; bool activate; if (!lapic_in_kernel(vcpu)) return; down_read(&vcpu->kvm->arch.apicv_update_lock); + preempt_disable(); - activate = kvm_apicv_activated(vcpu->kvm); - if (vcpu->arch.apicv_active == activate) + /* Do not activate APICV when APIC is disabled */ + activate = kvm_vcpu_apicv_activated(vcpu) && + (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED); + + if (apic->apicv_active == activate) goto out; - vcpu->arch.apicv_active = activate; + apic->apicv_active = activate; kvm_apic_update_apicv(vcpu); static_call(kvm_x86_refresh_apicv_exec_ctrl)(vcpu); @@ -9507,35 +10357,32 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) * 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 - * inject_pending_event() is called to check for that. + * kvm_check_and_inject_events() is called to check for that. */ - if (!vcpu->arch.apicv_active) + if (!apic->apicv_active) kvm_make_request(KVM_REQ_EVENT, vcpu); out: + preempt_enable(); up_read(&vcpu->kvm->arch.apicv_update_lock); } EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); -void __kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) +void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, + enum kvm_apicv_inhibit reason, bool set) { unsigned long old, new; lockdep_assert_held_write(&kvm->arch.apicv_update_lock); - if (!kvm_x86_ops.check_apicv_inhibit_reasons || - !static_call(kvm_x86_check_apicv_inhibit_reasons)(bit)) + if (!static_call(kvm_x86_check_apicv_inhibit_reasons)(reason)) return; old = new = kvm->arch.apicv_inhibit_reasons; - if (activate) - __clear_bit(bit, &new); - else - __set_bit(bit, &new); + set_or_clear_apicv_inhibit(&new, reason, set); if (!!old != !!new) { - trace_kvm_apicv_update_request(activate, bit); /* * Kick all vCPUs before setting apicv_inhibit_reasons to avoid * false positives in the sanity check WARN in svm_vcpu_run(). @@ -9552,20 +10399,27 @@ void __kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) 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 + } else { kvm->arch.apicv_inhibit_reasons = new; + } } -EXPORT_SYMBOL_GPL(__kvm_request_apicv_update); -void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) +void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, + enum kvm_apicv_inhibit reason, bool set) { + if (!enable_apicv) + return; + down_write(&kvm->arch.apicv_update_lock); - __kvm_request_apicv_update(kvm, activate, bit); + __kvm_set_or_clear_apicv_inhibit(kvm, reason, set); up_write(&kvm->arch.apicv_update_lock); } -EXPORT_SYMBOL_GPL(kvm_request_apicv_update); +EXPORT_SYMBOL_GPL(kvm_set_or_clear_apicv_inhibit); static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { @@ -9599,11 +10453,11 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, to_hv_synic(vcpu)->vec_bitmap, 256); - static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); + static_call_cond(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); return; } - static_call(kvm_x86_load_eoi_exitmap)( + static_call_cond(kvm_x86_load_eoi_exitmap)( vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors); } @@ -9621,15 +10475,17 @@ void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); } -void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) +void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) { - if (!lapic_in_kernel(vcpu)) - return; + static_call_cond(kvm_x86_guest_memory_reclaimed)(kvm); +} - if (!kvm_x86_ops.set_apic_access_page_addr) +static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) +{ + if (!lapic_in_kernel(vcpu)) return; - static_call(kvm_x86_set_apic_access_page_addr)(vcpu); + static_call_cond(kvm_x86_set_apic_access_page_addr)(vcpu); } void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) @@ -9639,6 +10495,7 @@ void __kvm_request_immediate_exit(struct kvm_vcpu *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. @@ -9673,8 +10530,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto out; } } - if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) - kvm_mmu_unload(vcpu); + 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)) @@ -9749,12 +10606,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) 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; } @@ -9798,7 +10657,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto out; } - r = inject_pending_event(vcpu, &req_immediate_exit); + r = kvm_check_and_inject_events(vcpu, &req_immediate_exit); if (r < 0) { r = 0; goto out; @@ -9819,7 +10678,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) preempt_disable(); - static_call(kvm_x86_prepare_guest_switch)(vcpu); + static_call(kvm_x86_prepare_switch_to_guest)(vcpu); /* * Disable IRQs before setting IN_GUEST_MODE. Posted interrupt @@ -9827,9 +10686,11 @@ 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 @@ -9846,10 +10707,11 @@ 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. Assigned devices can - * use the POSTED_INTR_VECTOR even if APICv is disabled, - * so do it even if APICv is disabled on this vCPU. + * 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)) static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); @@ -9859,7 +10721,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) 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; } @@ -9873,6 +10735,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (test_thread_flag(TIF_NEED_FPU_LOAD)) switch_fpu_return(); + if (vcpu->arch.guest_fpu.xfd_err) + wrmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); + if (unlikely(vcpu->arch.switch_db_regs)) { set_debugreg(0, 7); set_debugreg(vcpu->arch.eff_db[0], 0); @@ -9883,6 +10748,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(0, 7); } + guest_timing_enter_irqoff(); + for (;;) { /* * Assert that vCPU vs. VM APICv state is consistent. An APICv @@ -9890,9 +10757,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * per-VM state, and responsing vCPUs must wait for the update * to complete before servicing KVM_REQ_APICV_UPDATE. */ - WARN_ON_ONCE(kvm_apicv_activated(vcpu->kvm) != kvm_vcpu_apicv_active(vcpu)); + WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) && + (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED)); - exit_fastpath = static_call(kvm_x86_run)(vcpu); + exit_fastpath = static_call(kvm_x86_vcpu_run)(vcpu); if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; @@ -9934,8 +10802,19 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); + /* + * 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(); + static_call(kvm_x86_handle_exit_irqoff)(vcpu); + if (vcpu->arch.guest_fpu.xfd_err) + wrmsrl(MSR_IA32_XFD_ERR, 0); + /* * Consume any pending interrupts, including the possible source of * VM-Exit on SVM and any ticks that occur between VM-Exit and now. @@ -9943,7 +10822,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * interrupts on processors that implement an interrupt shadow, the * stat.exits increment will do nicely. */ - kvm_before_interrupt(vcpu); + kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); local_irq_enable(); ++vcpu->stat.exits; local_irq_disable(); @@ -9956,20 +10835,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * of accounting via context tracking, but the loss of accuracy is * acceptable for all known use cases. */ - vtime_account_guest_exit(); - - if (lapic_in_kernel(vcpu)) { - s64 delta = vcpu->arch.apic->lapic_timer.advance_expire_delta; - if (delta != S64_MIN) { - trace_kvm_wait_lapic_expire(vcpu->vcpu_id, delta); - vcpu->arch.apic->lapic_timer.advance_expire_delta = S64_MIN; - } - } + guest_timing_exit_irqoff(); local_irq_enable(); preempt_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); /* * Profile KVM exit RIPs: @@ -9998,21 +10869,53 @@ out: return r; } -static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) +/* Called within kvm->srcu read side. */ +static inline int vcpu_block(struct kvm_vcpu *vcpu) { - if (!kvm_arch_vcpu_runnable(vcpu) && - (!kvm_x86_ops.pre_block || static_call(kvm_x86_pre_block)(vcpu) == 0)) { - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - kvm_vcpu_block(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + bool hv_timer; - if (kvm_x86_ops.post_block) - static_call(kvm_x86_post_block)(vcpu); + 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 (!kvm_check_request(KVM_REQ_UNHALT, 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; } + /* + * 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)) { + if (kvm_check_nested_events(vcpu) < 0) + return 0; + } + if (kvm_apic_accept_events(vcpu) < 0) return 0; switch(vcpu->arch.mp_state) { @@ -10028,39 +10931,46 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) 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_check_nested_events(vcpu); - return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted); } +/* Called within kvm->srcu read side. */ static int vcpu_run(struct kvm_vcpu *vcpu) { int r; - struct kvm *kvm = vcpu->kvm; - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); vcpu->arch.l1tf_flush_l1d = true; 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_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); @@ -10073,27 +10983,20 @@ static int vcpu_run(struct kvm_vcpu *vcpu) } if (__xfer_to_guest_mode_work_pending()) { - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); r = xfer_to_guest_mode_handle_work(vcpu); + kvm_vcpu_srcu_read_lock(vcpu); if (r) return r; - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); } } - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - return r; } static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { - 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); - return r; + return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); } static int complete_emulated_pio(struct kvm_vcpu *vcpu) @@ -10169,10 +11072,7 @@ 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) { - /* - * Exclude PKRU from restore as restored separately in - * kvm_x86_ops.run(). - */ + /* Exclude PKRU, it's restored separately immediately after VM-Exit. */ fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, true); trace_kvm_fpu(1); } @@ -10187,6 +11087,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *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; int r; @@ -10195,17 +11096,26 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *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) { r = -EINTR; goto out; } + /* + * It should be impossible for the hypervisor timer to be in + * use before KVM has ever run the vCPU. + */ + WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu)); + + kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_block(vcpu); + kvm_vcpu_srcu_read_lock(vcpu); + if (kvm_apic_accept_events(vcpu) < 0) { r = 0; goto out; } - kvm_clear_request(KVM_REQ_UNHALT, vcpu); r = -EAGAIN; if (signal_pending(current)) { r = -EINTR; @@ -10235,27 +11145,51 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) } } + /* + * 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 (kvm_run->immediate_exit) { r = -EINTR; - else - r = vcpu_run(vcpu); + goto out; + } + + r = static_call(kvm_x86_vcpu_pre_run)(vcpu); + if (r <= 0) + goto out; + + r = vcpu_run(vcpu); out: kvm_put_guest_fpu(vcpu); if (kvm_run->kvm_valid_regs) 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; } @@ -10332,6 +11266,7 @@ static void __set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) 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); } @@ -10344,16 +11279,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) 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_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { struct desc_ptr dt; @@ -10461,16 +11386,30 @@ 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) + 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; + + case KVM_MP_STATE_RUNNABLE: + break; + + default: goto out; + } /* - * KVM_MP_STATE_INIT_RECEIVED means the processor is in - * INIT state; latched init should be reported using - * KVM_SET_VCPU_EVENTS, so reject it here. + * Pending INITs are reported using KVM_SET_VCPU_EVENTS, disallow + * forcing the guest into INIT/SIPI if those events are supposed to be + * blocked. KVM prioritizes SMI over INIT, so reject INIT/SIPI state + * if an SMI is pending as well. */ - if ((kvm_vcpu_latch_init(vcpu) || vcpu->arch.smi_pending) && + if ((!kvm_apic_init_sipi_allowed(vcpu) || vcpu->arch.smi_pending) && (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED || mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED)) goto out; @@ -10563,7 +11502,8 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, vcpu->arch.cr2 = sregs->cr2; *mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); + static_call_cond(kvm_x86_post_set_cr3)(vcpu, sregs->cr3); kvm_set_cr8(vcpu, sregs->cr8); @@ -10580,7 +11520,7 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, if (update_pdptrs) { idx = srcu_read_lock(&vcpu->kvm->srcu); if (is_pae_paging(vcpu)) { - load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + load_pdptrs(vcpu, kvm_read_cr3(vcpu)); *mmu_reset_needed = 1; } srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -10676,19 +11616,22 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) { - bool inhibit = false; + bool set = false; struct kvm_vcpu *vcpu; - int i; + 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) { - inhibit = true; + set = true; break; } } - __kvm_request_apicv_update(kvm, !inhibit, APICV_INHIBIT_REASON_BLOCKIRQ); + __kvm_set_or_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_BLOCKIRQ, set); up_write(&kvm->arch.apicv_update_lock); } @@ -10705,7 +11648,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *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); @@ -10769,7 +11712,7 @@ 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; @@ -10862,11 +11805,17 @@ static int sync_regs(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { - if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) + if (kvm_check_tsc_unstable() && kvm->created_vcpus) pr_warn_once("kvm: SMP vm created on host with unstable TSC; " "guest TSC will not be reliable\n"); - return 0; + if (!kvm->arch.max_vcpu_ids) + kvm->arch.max_vcpu_ids = KVM_MAX_VCPU_IDS; + + if (id >= kvm->arch.max_vcpu_ids) + return -EINVAL; + + return static_call(kvm_x86_vcpu_precreate)(kvm); } int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) @@ -10878,6 +11827,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; + kvm_gpc_init(&vcpu->arch.pv_time); + if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else @@ -10891,8 +11842,21 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); if (r < 0) goto fail_mmu_destroy; - if (kvm_apicv_activated(vcpu->kvm)) - vcpu->arch.apicv_active = true; + + /* + * Defer evaluating inhibits until the vCPU is first run, as + * this vCPU will not get notified of any changes until this + * vCPU is visible to other vCPUs (marked online and added to + * the set of vCPUs). Opportunistically mark APICv active as + * VMX in particularly is highly unlikely to have inhibits. + * Ignore the current per-VM APICv state so that vCPU creation + * is guaranteed to run with a deterministic value, the request + * will ensure the vCPU gets the correct state before VM-Entry. + */ + if (enable_apicv) { + vcpu->arch.apic->apicv_active = true; + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + } } else static_branch_inc(&kvm_has_noapic_vcpu); @@ -10903,10 +11867,12 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) goto fail_free_lapic; vcpu->arch.pio_data = page_address(page); - vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4, + vcpu->arch.mce_banks = kcalloc(KVM_MAX_MCE_BANKS * 4, sizeof(u64), GFP_KERNEL_ACCOUNT); - if (!vcpu->arch.mce_banks) - goto fail_free_pio_data; + 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, @@ -10942,9 +11908,10 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.arch_capabilities = kvm_get_arch_capabilities(); vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; + kvm_xen_init_vcpu(vcpu); kvm_vcpu_mtrr_init(vcpu); vcpu_load(vcpu); - kvm_set_tsc_khz(vcpu, max_tsc_khz); + kvm_set_tsc_khz(vcpu, vcpu->kvm->arch.default_tsc_khz); kvm_vcpu_reset(vcpu, false); kvm_init_mmu(vcpu); vcpu_put(vcpu); @@ -10958,7 +11925,7 @@ free_wbinvd_dirty_mask: free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); fail_free_mce_banks: kfree(vcpu->arch.mce_banks); -fail_free_pio_data: + kfree(vcpu->arch.mci_ctl2_banks); free_page((unsigned long)vcpu->arch.pio_data); fail_free_lapic: kvm_free_lapic(vcpu); @@ -10999,9 +11966,11 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) 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); @@ -11063,8 +12032,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate; /* - * 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. + * All paths that lead to INIT are required to load the guest's + * FPU state (because most paths are buried in KVM_RUN). */ if (init_event) kvm_put_guest_fpu(vcpu); @@ -11081,8 +12050,11 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.smbase = 0x30000; 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_set_msr(vcpu, MSR_IA32_XSS, 0, true); } /* All GPRs except RDX (handled below) are zeroed on RESET/INIT. */ @@ -11096,11 +12068,9 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) * 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, 0); + cpuid_0x1 = kvm_find_cpuid_entry(vcpu, 1); kvm_rdx_write(vcpu, cpuid_0x1 ? cpuid_0x1->eax : 0x600); - vcpu->arch.ia32_xss = 0; - static_call(kvm_x86_vcpu_reset)(vcpu, init_event); kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); @@ -11126,15 +12096,17 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) static_call(kvm_x86_update_exception_bitmap)(vcpu); /* - * Reset the MMU context if paging was enabled prior to INIT (which is - * implied if CR0.PG=1 as CR0 will be '0' prior to RESET). Unlike the - * standard CR0/CR4/EFER modification paths, only CR0.PG needs to be - * checked because it is unconditionally cleared on INIT and all other - * paging related bits are ignored if paging is disabled, i.e. CR0.WP, - * CR4, and EFER changes are all irrelevant if CR0.PG was '0'. + * 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) + 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 @@ -11166,7 +12138,7 @@ int kvm_arch_hardware_enable(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; int ret; u64 local_tsc; u64 max_tsc = 0; @@ -11259,6 +12231,24 @@ void kvm_arch_hardware_disable(void) drop_user_return_notifiers(); } +static inline void kvm_ops_update(struct kvm_x86_init_ops *ops) +{ + memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); + +#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 + + kvm_pmu_ops_update(ops->pmu_ops); +} + int kvm_arch_hardware_setup(void *opaque) { struct kvm_x86_init_ops *ops = opaque; @@ -11269,21 +12259,24 @@ int kvm_arch_hardware_setup(void *opaque) if (boot_cpu_has(X86_FEATURE_XSAVES)) rdmsrl(MSR_IA32_XSS, host_xss); + kvm_init_pmu_capability(); + r = ops->hardware_setup(); if (r != 0) return r; - memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); - kvm_ops_static_call_update(); + kvm_ops_update(ops); + + kvm_register_perf_callbacks(ops->handle_intel_pt_intr); if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) - supported_xss = 0; + kvm_caps.supported_xss = 0; #define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); #undef __kvm_cpu_cap_has - if (kvm_has_tsc_control) { + if (kvm_caps.has_tsc_control) { /* * Make sure the user can only configure tsc_khz values that * fit into a signed integer. @@ -11291,18 +12284,18 @@ int kvm_arch_hardware_setup(void *opaque) * 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; + __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_list(); return 0; } void kvm_arch_hardware_unsetup(void) { + kvm_unregister_perf_callbacks(); + static_call(kvm_x86_hardware_unsetup)(); } @@ -11363,12 +12356,17 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) ret = kvm_page_track_init(kvm); if (ret) - return ret; + goto out; + + ret = kvm_mmu_init_vm(kvm); + if (ret) + goto out_page_track; + + ret = static_call(kvm_x86_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.lpage_disallowed_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); @@ -11387,7 +12385,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) 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.guest_can_read_msr_platform_info = true; + kvm->arch.enable_pmu = enable_pmu; #if IS_ENABLED(CONFIG_HYPERV) spin_lock_init(&kvm->arch.hv_root_tdp_lock); @@ -11399,10 +12399,16 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_apicv_init(kvm); kvm_hv_init_vm(kvm); - kvm_mmu_init_vm(kvm); kvm_xen_init_vm(kvm); - return static_call(kvm_x86_vm_init)(kvm); + return 0; + +out_uninit_mmu: + kvm_mmu_uninit_vm(kvm); +out_page_track: + kvm_page_track_cleanup(kvm); +out: + return ret; } int kvm_arch_post_init_vm(struct kvm *kvm) @@ -11417,27 +12423,15 @@ static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) vcpu_put(vcpu); } -static void kvm_free_vcpus(struct kvm *kvm) +static void kvm_unload_vcpu_mmus(struct kvm *kvm) { - unsigned int i; + unsigned long 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); } - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_destroy(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); } void kvm_arch_sync_events(struct kvm *kvm) @@ -11447,8 +12441,6 @@ void kvm_arch_sync_events(struct kvm *kvm) kvm_free_pit(kvm); } -#define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e)) - /** * __x86_set_memory_region: Setup KVM internal memory slot * @@ -11534,7 +12526,7 @@ 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. */ mutex_lock(&kvm->slots_lock); @@ -11545,11 +12537,12 @@ void kvm_arch_destroy_vm(struct kvm *kvm) __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); mutex_unlock(&kvm->slots_lock); } + kvm_unload_vcpu_mmus(kvm); static_call_cond(kvm_x86_vm_destroy)(kvm); kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1)); kvm_pic_destroy(kvm); kvm_ioapic_destroy(kvm); - kvm_free_vcpus(kvm); + kvm_destroy_vcpus(kvm); 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); @@ -11594,7 +12587,7 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages) if (slot->arch.rmap[i]) continue; - slot->arch.rmap[i] = kvcalloc(lpages, sz, GFP_KERNEL_ACCOUNT); + slot->arch.rmap[i] = __vcalloc(lpages, sz, GFP_KERNEL_ACCOUNT); if (!slot->arch.rmap[i]) { memslot_rmap_free(slot); return -ENOMEM; @@ -11605,9 +12598,9 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages) } static int kvm_alloc_memslot_metadata(struct kvm *kvm, - struct kvm_memory_slot *slot, - unsigned long npages) + struct kvm_memory_slot *slot) { + unsigned long npages = slot->npages; int i, r; /* @@ -11631,7 +12624,7 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm, lpages = __kvm_mmu_slot_lpages(slot, npages, level); - linfo = kvcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT); + linfo = __vcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT); if (!linfo) goto out_free; @@ -11672,7 +12665,7 @@ out_free: void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; /* * memslots->generation has been incremented. @@ -11686,13 +12679,22 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) } 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) { - if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) - return kvm_alloc_memslot_metadata(kvm, memslot, - mem->memory_size >> PAGE_SHIFT); + if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) { + if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn()) + 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; } @@ -11716,13 +12718,15 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - bool log_dirty_pages = new->flags & KVM_MEM_LOG_DIRTY_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; /* * Update CPU dirty logging if dirty logging is being toggled. This * applies to all operations. */ - if ((old->flags ^ new->flags) & KVM_MEM_LOG_DIRTY_PAGES) + if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) kvm_mmu_update_cpu_dirty_logging(kvm, log_dirty_pages); /* @@ -11740,7 +12744,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * MOVE/DELETE: The old mappings will already have been cleaned up by * kvm_arch_flush_shadow_memslot(). */ - if ((change != KVM_MR_FLAGS_ONLY) || (new->flags & KVM_MEM_READONLY)) + if ((change != KVM_MR_FLAGS_ONLY) || (new_flags & KVM_MEM_READONLY)) return; /* @@ -11748,7 +12752,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * 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))) + if (WARN_ON_ONCE(!((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES))) return; if (!log_dirty_pages) { @@ -11774,24 +12778,75 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, if (kvm_dirty_log_manual_protect_and_init_set(kvm)) return; + if (READ_ONCE(eager_page_split)) + kvm_mmu_slot_try_split_huge_pages(kvm, new, PG_LEVEL_4K); + if (kvm_x86_ops.cpu_dirty_log_size) { 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_arch_flush_remote_tlbs_memslot(kvm, new); } } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - if (!kvm->arch.n_requested_mmu_pages) - kvm_mmu_change_mmu_pages(kvm, - kvm_mmu_calculate_default_mmu_pages(kvm)); + if (!kvm->arch.n_requested_mmu_pages && + (change == KVM_MR_CREATE || change == KVM_MR_DELETE)) { + unsigned long nr_mmu_pages; + + 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); + } kvm_mmu_slot_apply_flags(kvm, old, new, change); @@ -11814,8 +12869,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) { return (is_guest_mode(vcpu) && - kvm_x86_ops.guest_apic_has_interrupt && - static_call(kvm_x86_guest_apic_has_interrupt)(vcpu)); + static_call(kvm_x86_guest_apic_has_interrupt)(vcpu)); } static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) @@ -11823,13 +12877,14 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (!list_empty_careful(&vcpu->async_pf.done)) return true; - if (kvm_apic_has_events(vcpu)) + if (kvm_apic_has_pending_init_or_sipi(vcpu) && + kvm_apic_init_sipi_allowed(vcpu)) return true; if (vcpu->arch.pv.pv_unhalted) return true; - if (vcpu->arch.exception.pending) + if (kvm_is_exception_pending(vcpu)) return true; if (kvm_test_request(KVM_REQ_NMI, vcpu) || @@ -11851,8 +12906,11 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) return true; if (is_guest_mode(vcpu) && - kvm_x86_ops.nested_ops->hv_timer_pending && - kvm_x86_ops.nested_ops->hv_timer_pending(vcpu)) + kvm_x86_ops.nested_ops->has_events && + kvm_x86_ops.nested_ops->has_events(vcpu)) + return true; + + if (kvm_xen_has_pending_events(vcpu)) return true; return false; @@ -11865,7 +12923,8 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) { - if (vcpu->arch.apicv_active && static_call(kvm_x86_dy_apicv_has_pending_interrupt)(vcpu)) + if (kvm_vcpu_apicv_active(vcpu) && + static_call(kvm_x86_dy_apicv_has_pending_interrupt)(vcpu)) return true; return false; @@ -11892,6 +12951,11 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) return vcpu->arch.preempted_in_kernel; } +unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu) +{ + return kvm_rip_read(vcpu); +} + int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) { return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; @@ -11947,25 +13011,6 @@ void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) } 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_guest_pgd(vcpu)) - return; - - kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true); -} - static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) { BUILD_BUG_ON(!is_power_of_2(ASYNC_PF_PER_VCPU)); @@ -12063,21 +13108,35 @@ static inline bool apf_pageready_slot_free(struct kvm_vcpu *vcpu) static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu) { - if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu)) + + if (!kvm_pv_async_pf_enabled(vcpu)) return false; - if (!kvm_pv_async_pf_enabled(vcpu) || - (vcpu->arch.apf.send_user_only && static_call(kvm_x86_get_cpl)(vcpu) == 0)) + if (vcpu->arch.apf.send_user_only && + static_call(kvm_x86_get_cpl)(vcpu) == 0) return false; - return true; + 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) || - vcpu->arch.exception.pending)) + kvm_is_exception_pending(vcpu))) return false; if (kvm_hlt_in_guest(vcpu->kvm) && !kvm_can_deliver_async_pf(vcpu)) @@ -12165,7 +13224,7 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) void kvm_arch_start_assignment(struct kvm *kvm) { if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1) - static_call_cond(kvm_x86_start_assignment)(kvm); + static_call_cond(kvm_x86_pi_start_assignment)(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_start_assignment); @@ -12175,9 +13234,9 @@ void kvm_arch_end_assignment(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); -bool kvm_arch_has_assigned_device(struct kvm *kvm) +bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm) { - return atomic_read(&kvm->arch.assigned_device_count); + return arch_atomic_read(&kvm->arch.assigned_device_count); } EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); @@ -12213,7 +13272,7 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, irqfd->producer = prod; kvm_arch_start_assignment(irqfd->kvm); - ret = static_call(kvm_x86_update_pi_irte)(irqfd->kvm, + ret = static_call(kvm_x86_pi_update_irte)(irqfd->kvm, prod->irq, irqfd->gsi, 1); if (ret) @@ -12238,7 +13297,7 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, * when the irq is masked/disabled or the consumer side (KVM * int this case doesn't want to receive the interrupts. */ - ret = static_call(kvm_x86_update_pi_irte)(irqfd->kvm, prod->irq, irqfd->gsi, 0); + ret = static_call(kvm_x86_pi_update_irte)(irqfd->kvm, prod->irq, irqfd->gsi, 0); if (ret) printk(KERN_INFO "irq bypass consumer (token %p) unregistration" " fails: %d\n", irqfd->consumer.token, ret); @@ -12249,7 +13308,7 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set) { - return static_call(kvm_x86_update_pi_irte)(kvm, host_irq, guest_irq, set); + return static_call(kvm_x86_pi_update_irte)(kvm, host_irq, guest_irq, set); } bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old, @@ -12301,12 +13360,13 @@ EXPORT_SYMBOL_GPL(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; - u32 access = error_code & + u64 access = error_code & (PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK); if (!(error_code & PFERR_PRESENT_MASK) || - vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, &fault) != UNMAPPED_GVA) { + 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 @@ -12317,6 +13377,7 @@ void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_c 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); } @@ -12531,6 +13592,12 @@ int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes, } EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_read); +static void advance_sev_es_emulated_pio(struct kvm_vcpu *vcpu, unsigned count, int size) +{ + vcpu->arch.sev_pio_count -= count; + vcpu->arch.sev_pio_data += count * size; +} + static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port); @@ -12554,8 +13621,7 @@ static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, int ret = emulator_pio_out(vcpu, size, port, vcpu->arch.sev_pio_data, count); /* memcpy done already by emulator_pio_out. */ - vcpu->arch.sev_pio_count -= count; - vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size; + advance_sev_es_emulated_pio(vcpu, count, size); if (!ret) break; @@ -12571,20 +13637,14 @@ static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port); -static void advance_sev_es_emulated_ins(struct kvm_vcpu *vcpu) -{ - unsigned count = vcpu->arch.pio.count; - complete_emulator_pio_in(vcpu, vcpu->arch.sev_pio_data); - vcpu->arch.sev_pio_count -= count; - vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size; -} - 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; - advance_sev_es_emulated_ins(vcpu); + 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; @@ -12596,11 +13656,11 @@ static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size, for (;;) { unsigned int count = min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count); - if (!__emulator_pio_in(vcpu, size, port, count)) + if (!emulator_pio_in(vcpu, size, port, vcpu->arch.sev_pio_data, count)) break; /* Emulation done by the kernel. */ - advance_sev_es_emulated_ins(vcpu); + advance_sev_es_emulated_pio(vcpu, count, size); if (!vcpu->arch.sev_pio_count) return 1; } @@ -12627,7 +13687,7 @@ 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); @@ -12642,8 +13702,26 @@ 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_apicv_update_request); +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); + +static int __init kvm_x86_init(void) +{ + kvm_mmu_x86_module_init(); + return 0; +} +module_init(kvm_x86_init); + +static void __exit kvm_x86_exit(void) +{ + /* + * If module_init() is implemented, module_exit() must also be + * implemented to allow module unload. + */ +} +module_exit(kvm_x86_exit); |