diff options
| author | Ingo Molnar <mingo@kernel.org> | 2024-02-14 10:45:07 +0100 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2024-02-14 10:45:07 +0100 |
| commit | 03c11eb3b16dc0058589751dfd91f254be2be613 (patch) | |
| tree | e5f2889212fec0bb0babdce9abd781ab487e246a /arch/x86/kvm | |
| parent | de8c6a352131f642b82474abe0cbb5dd26a7e081 (diff) | |
| parent | 841c35169323cd833294798e58b9bf63fa4fa1de (diff) | |
Merge tag 'v6.8-rc4' into x86/percpu, to resolve conflicts and refresh the branch
Conflicts:
arch/x86/include/asm/percpu.h
arch/x86/include/asm/text-patching.h
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/x86/kvm')
58 files changed, 3585 insertions, 2181 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 89ca7f4c1464..87e3da7b0439 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -23,17 +23,15 @@ config KVM depends on HAVE_KVM depends on HIGH_RES_TIMERS depends on X86_LOCAL_APIC - select PREEMPT_NOTIFIERS - select MMU_NOTIFIER + select KVM_COMMON + select KVM_GENERIC_MMU_NOTIFIER select HAVE_KVM_IRQCHIP select HAVE_KVM_PFNCACHE - select HAVE_KVM_IRQFD select HAVE_KVM_DIRTY_RING_TSO select HAVE_KVM_DIRTY_RING_ACQ_REL select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_IRQ_ROUTING - select HAVE_KVM_EVENTFD select KVM_ASYNC_PF select USER_RETURN_NOTIFIER select KVM_MMIO @@ -46,7 +44,6 @@ config KVM select KVM_XFER_TO_GUEST_WORK select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_VFIO - select INTERVAL_TREE select HAVE_KVM_PM_NOTIFIER if PM select KVM_GENERIC_HARDWARE_ENABLING help @@ -65,18 +62,30 @@ config KVM config KVM_WERROR bool "Compile KVM with -Werror" - # KASAN may cause the build to fail due to larger frames - default y if X86_64 && !KASAN - # We use the dependency on !COMPILE_TEST to not be enabled - # blindly in allmodconfig or allyesconfig configurations - depends on KVM - depends on (X86_64 && !KASAN) || !COMPILE_TEST - depends on EXPERT + # Disallow KVM's -Werror if KASAN is enabled, e.g. to guard against + # randomized configs from selecting KVM_WERROR=y, which doesn't play + # nice with KASAN. KASAN builds generates warnings for the default + # FRAME_WARN, i.e. KVM_WERROR=y with KASAN=y requires special tuning. + # Building KVM with -Werror and KASAN is still doable via enabling + # the kernel-wide WERROR=y. + depends on KVM && EXPERT && !KASAN help Add -Werror to the build flags for KVM. If in doubt, say "N". +config KVM_SW_PROTECTED_VM + bool "Enable support for KVM software-protected VMs" + depends on EXPERT + depends on KVM && X86_64 + select KVM_GENERIC_PRIVATE_MEM + help + Enable support for KVM software-protected VMs. Currently "protected" + means the VM can be backed with memory provided by + KVM_CREATE_GUEST_MEMFD. + + If unsure, say "N". + config KVM_INTEL tristate "KVM for Intel (and compatible) processors support" depends on KVM && IA32_FEAT_CTL @@ -101,7 +110,7 @@ config X86_SGX_KVM config KVM_AMD tristate "KVM for AMD processors support" - depends on KVM + depends on KVM && (CPU_SUP_AMD || CPU_SUP_HYGON) help Provides support for KVM on AMD processors equipped with the AMD-V (SVM) extensions. @@ -129,6 +138,20 @@ config KVM_SMM If unsure, say Y. +config KVM_HYPERV + bool "Support for Microsoft Hyper-V emulation" + depends on KVM + default y + help + Provides KVM support for emulating Microsoft Hyper-V. This allows KVM + to expose a subset of the paravirtualized interfaces defined in the + Hyper-V Hypervisor Top-Level Functional Specification (TLFS): + https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs + These interfaces are required for the correct and performant functioning + of Windows and Hyper-V guests on KVM. + + If unsure, say "Y". + config KVM_XEN bool "Support for Xen hypercall interface" depends on KVM @@ -138,7 +161,31 @@ config KVM_XEN If in doubt, say "N". +config KVM_PROVE_MMU + bool "Prove KVM MMU correctness" + depends on DEBUG_KERNEL + depends on KVM + depends on EXPERT + help + Enables runtime assertions in KVM's MMU that are too costly to enable + in anything remotely resembling a production environment, e.g. this + gates code that verifies a to-be-freed page table doesn't have any + present SPTEs. + + If in doubt, say "N". + config KVM_EXTERNAL_WRITE_TRACKING bool +config KVM_MAX_NR_VCPUS + int "Maximum number of vCPUs per KVM guest" + depends on KVM + range 1024 4096 + default 4096 if MAXSMP + default 1024 + help + Set the maximum number of vCPUs per KVM guest. Larger values will increase + the memory footprint of each KVM guest, regardless of how many vCPUs are + created for a given VM. + endif # VIRTUALIZATION diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 80e3fe184d17..475b5fa917a6 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -11,25 +11,27 @@ include $(srctree)/virt/kvm/Makefile.kvm kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ - hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o \ + debugfs.o mmu/mmu.o mmu/page_track.o \ mmu/spte.o -ifdef CONFIG_HYPERV -kvm-y += kvm_onhyperv.o -endif - kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o +kvm-$(CONFIG_KVM_HYPERV) += hyperv.o kvm-$(CONFIG_KVM_XEN) += xen.o kvm-$(CONFIG_KVM_SMM) += smm.o kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \ - vmx/hyperv.o vmx/nested.o vmx/posted_intr.o + vmx/nested.o vmx/posted_intr.o + kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o +kvm-intel-$(CONFIG_KVM_HYPERV) += vmx/hyperv.o vmx/hyperv_evmcs.o kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \ - svm/sev.o svm/hyperv.o + svm/sev.o +kvm-amd-$(CONFIG_KVM_HYPERV) += svm/hyperv.o ifdef CONFIG_HYPERV +kvm-y += kvm_onhyperv.o +kvm-intel-y += vmx/vmx_onhyperv.o vmx/hyperv_evmcs.o kvm-amd-y += svm/svm_onhyperv.o endif diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index d3432687c9e6..adba49afb5fe 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -11,6 +11,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> +#include "linux/lockdep.h" #include <linux/export.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> @@ -84,6 +85,18 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( struct kvm_cpuid_entry2 *e; int i; + /* + * KVM has a semi-arbitrary rule that querying the guest's CPUID model + * with IRQs disabled is disallowed. The CPUID model can legitimately + * have over one hundred entries, i.e. the lookup is slow, and IRQs are + * typically disabled in KVM only when KVM is in a performance critical + * path, e.g. the core VM-Enter/VM-Exit run loop. Nothing will break + * if this rule is violated, this assertion is purely to flag potential + * performance issues. If this fires, consider moving the lookup out + * of the hotpath, e.g. by caching information during CPUID updates. + */ + lockdep_assert_irqs_enabled(); + for (i = 0; i < nent; i++) { e = &entries[i]; @@ -92,7 +105,7 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( /* * If the index isn't significant, use the first entry with a - * matching function. It's userspace's responsibilty to not + * matching function. It's userspace's responsibility to not * provide "duplicate" entries in all cases. */ if (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index) @@ -301,17 +314,42 @@ EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime); static bool kvm_cpuid_has_hyperv(struct kvm_cpuid_entry2 *entries, int nent) { +#ifdef CONFIG_KVM_HYPERV struct kvm_cpuid_entry2 *entry; entry = cpuid_entry2_find(entries, nent, HYPERV_CPUID_INTERFACE, KVM_CPUID_INDEX_NOT_SIGNIFICANT); return entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX; +#else + return false; +#endif } static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_cpuid_entry2 *best; + bool allow_gbpages; + + BUILD_BUG_ON(KVM_NR_GOVERNED_FEATURES > KVM_MAX_NR_GOVERNED_FEATURES); + bitmap_zero(vcpu->arch.governed_features.enabled, + KVM_MAX_NR_GOVERNED_FEATURES); + + /* + * If TDP is enabled, let the guest use GBPAGES if they're supported in + * hardware. The hardware page walker doesn't let KVM disable GBPAGES, + * i.e. won't treat them as reserved, and KVM doesn't redo the GVA->GPA + * walk for performance and complexity reasons. Not to mention KVM + * _can't_ solve the problem because GVA->GPA walks aren't visible to + * KVM once a TDP translation is installed. Mimic hardware behavior so + * that KVM's is at least consistent, i.e. doesn't randomly inject #PF. + * If TDP is disabled, honor *only* guest CPUID as KVM has full control + * and can install smaller shadow pages if the host lacks 1GiB support. + */ + allow_gbpages = tdp_enabled ? boot_cpu_has(X86_FEATURE_GBPAGES) : + guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES); + if (allow_gbpages) + kvm_governed_feature_set(vcpu, X86_FEATURE_GBPAGES); best = kvm_find_cpuid_entry(vcpu, 1); if (best && apic) { @@ -326,14 +364,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); - /* - * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if - * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't - * supported by the host. - */ - vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0 | - XFEATURE_MASK_FPSSE; - kvm_update_pv_runtime(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); @@ -407,11 +437,13 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, return 0; } +#ifdef CONFIG_KVM_HYPERV if (kvm_cpuid_has_hyperv(e2, nent)) { r = kvm_hv_vcpu_init(vcpu); if (r) return r; } +#endif r = kvm_check_cpuid(vcpu, e2, nent); if (r) @@ -422,7 +454,9 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, vcpu->arch.cpuid_nent = nent; vcpu->arch.kvm_cpuid = kvm_get_hypervisor_cpuid(vcpu, KVM_SIGNATURE); +#ifdef CONFIG_KVM_XEN vcpu->arch.xen.cpuid = kvm_get_hypervisor_cpuid(vcpu, XEN_SIGNATURE); +#endif kvm_vcpu_after_set_cpuid(vcpu); return 0; @@ -441,7 +475,7 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, return -E2BIG; if (cpuid->nent) { - e = vmemdup_user(entries, array_size(sizeof(*e), cpuid->nent)); + e = vmemdup_array_user(entries, cpuid->nent, sizeof(*e)); if (IS_ERR(e)) return PTR_ERR(e); @@ -485,7 +519,7 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, return -E2BIG; if (cpuid->nent) { - e2 = vmemdup_user(entries, array_size(sizeof(*e2), cpuid->nent)); + e2 = vmemdup_array_user(entries, cpuid->nent, sizeof(*e2)); if (IS_ERR(e2)) return PTR_ERR(e2); } @@ -643,11 +677,17 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_mask(CPUID_7_1_EAX, F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) | F(FZRM) | F(FSRS) | F(FSRC) | - F(AMX_FP16) | F(AVX_IFMA) + F(AMX_FP16) | F(AVX_IFMA) | F(LAM) ); kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX, - F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(PREFETCHITI) + F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(PREFETCHITI) | + F(AMX_COMPLEX) + ); + + kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX, + F(INTEL_PSFD) | F(IPRED_CTRL) | F(RRSBA_CTRL) | F(DDPD_U) | + F(BHI_CTRL) | F(MCDT_NO) ); kvm_cpu_cap_mask(CPUID_D_1_EAX, @@ -726,11 +766,13 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_mask(CPUID_8000_0021_EAX, F(NO_NESTED_DATA_BP) | F(LFENCE_RDTSC) | 0 /* SmmPgCfgLock */ | - F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ + F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ | + F(WRMSR_XX_BASE_NS) ); - if (cpu_feature_enabled(X86_FEATURE_SRSO_NO)) - kvm_cpu_cap_set(X86_FEATURE_SRSO_NO); + kvm_cpu_cap_check_and_set(X86_FEATURE_SBPB); + kvm_cpu_cap_check_and_set(X86_FEATURE_IBPB_BRTYPE); + kvm_cpu_cap_check_and_set(X86_FEATURE_SRSO_NO); kvm_cpu_cap_init_kvm_defined(CPUID_8000_0022_EAX, F(PERFMON_V2) @@ -929,13 +971,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) break; /* function 7 has additional index. */ case 7: - entry->eax = min(entry->eax, 1u); + max_idx = entry->eax = min(entry->eax, 2u); cpuid_entry_override(entry, CPUID_7_0_EBX); cpuid_entry_override(entry, CPUID_7_ECX); cpuid_entry_override(entry, CPUID_7_EDX); - /* KVM only supports 0x7.0 and 0x7.1, capped above via min(). */ - if (entry->eax == 1) { + /* KVM only supports up to 0x7.2, capped above via min(). */ + if (max_idx >= 1) { entry = do_host_cpuid(array, function, 1); if (!entry) goto out; @@ -945,6 +987,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ebx = 0; entry->ecx = 0; } + if (max_idx >= 2) { + entry = do_host_cpuid(array, function, 2); + if (!entry) + goto out; + + cpuid_entry_override(entry, CPUID_7_2_EDX); + entry->ecx = 0; + entry->ebx = 0; + entry->eax = 0; + } break; case 0xa: { /* Architectural Performance Monitoring */ union cpuid10_eax eax; @@ -1154,6 +1206,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) cpuid_entry_override(entry, CPUID_8000_0001_EDX); cpuid_entry_override(entry, CPUID_8000_0001_ECX); break; + case 0x80000005: + /* Pass host L1 cache and TLB info. */ + break; case 0x80000006: /* Drop reserved bits, pass host L2 cache and TLB info. */ entry->edx &= ~GENMASK(17, 16); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index b1658c0de847..856e3037e74f 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -47,11 +47,6 @@ static inline bool kvm_vcpu_is_legal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) return !(gpa & vcpu->arch.reserved_gpa_bits); } -static inline bool kvm_vcpu_is_illegal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) -{ - return !kvm_vcpu_is_legal_gpa(vcpu, gpa); -} - static inline bool kvm_vcpu_is_legal_aligned_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, gpa_t alignment) { @@ -174,7 +169,8 @@ static inline bool guest_has_spec_ctrl_msr(struct kvm_vcpu *vcpu) static inline bool guest_has_pred_cmd_msr(struct kvm_vcpu *vcpu) { return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) || - guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)); + guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB) || + guest_cpuid_has(vcpu, X86_FEATURE_SBPB)); } static inline bool supports_cpuid_fault(struct kvm_vcpu *vcpu) @@ -232,4 +228,58 @@ static __always_inline bool guest_pv_has(struct kvm_vcpu *vcpu, return vcpu->arch.pv_cpuid.features & (1u << kvm_feature); } +enum kvm_governed_features { +#define KVM_GOVERNED_FEATURE(x) KVM_GOVERNED_##x, +#include "governed_features.h" + KVM_NR_GOVERNED_FEATURES +}; + +static __always_inline int kvm_governed_feature_index(unsigned int x86_feature) +{ + switch (x86_feature) { +#define KVM_GOVERNED_FEATURE(x) case x: return KVM_GOVERNED_##x; +#include "governed_features.h" + default: + return -1; + } +} + +static __always_inline bool kvm_is_governed_feature(unsigned int x86_feature) +{ + return kvm_governed_feature_index(x86_feature) >= 0; +} + +static __always_inline void kvm_governed_feature_set(struct kvm_vcpu *vcpu, + unsigned int x86_feature) +{ + BUILD_BUG_ON(!kvm_is_governed_feature(x86_feature)); + + __set_bit(kvm_governed_feature_index(x86_feature), + vcpu->arch.governed_features.enabled); +} + +static __always_inline void kvm_governed_feature_check_and_set(struct kvm_vcpu *vcpu, + unsigned int x86_feature) +{ + if (kvm_cpu_cap_has(x86_feature) && guest_cpuid_has(vcpu, x86_feature)) + kvm_governed_feature_set(vcpu, x86_feature); +} + +static __always_inline bool guest_can_use(struct kvm_vcpu *vcpu, + unsigned int x86_feature) +{ + BUILD_BUG_ON(!kvm_is_governed_feature(x86_feature)); + + return test_bit(kvm_governed_feature_index(x86_feature), + vcpu->arch.governed_features.enabled); +} + +static inline bool kvm_vcpu_is_legal_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) +{ + if (guest_can_use(vcpu, X86_FEATURE_LAM)) + cr3 &= ~(X86_CR3_LAM_U48 | X86_CR3_LAM_U57); + + return kvm_vcpu_is_legal_gpa(vcpu, cr3); +} + #endif diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index ee8c4c3496ed..95ea1a1f7403 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -111,7 +111,7 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) mutex_lock(&kvm->slots_lock); write_lock(&kvm->mmu_lock); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { int bkt; slots = __kvm_memslots(kvm, i); @@ -182,6 +182,7 @@ static int kvm_mmu_rmaps_stat_release(struct inode *inode, struct file *file) } static const struct file_operations mmu_rmaps_stat_fops = { + .owner = THIS_MODULE, .open = kvm_mmu_rmaps_stat_open, .read = seq_read, .llseek = seq_lseek, diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 936a397a08cd..e223043ef5b2 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -687,8 +687,8 @@ static unsigned insn_alignment(struct x86_emulate_ctxt *ctxt, unsigned size) static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, struct segmented_address addr, unsigned *max_size, unsigned size, - bool write, bool fetch, - enum x86emul_mode mode, ulong *linear) + enum x86emul_mode mode, ulong *linear, + unsigned int flags) { struct desc_struct desc; bool usable; @@ -701,7 +701,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, *max_size = 0; switch (mode) { case X86EMUL_MODE_PROT64: - *linear = la; + *linear = la = ctxt->ops->get_untagged_addr(ctxt, la, flags); va_bits = ctxt_virt_addr_bits(ctxt); if (!__is_canonical_address(la, va_bits)) goto bad; @@ -717,11 +717,11 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, if (!usable) goto bad; /* code segment in protected mode or read-only data segment */ - if ((((ctxt->mode != X86EMUL_MODE_REAL) && (desc.type & 8)) - || !(desc.type & 2)) && write) + if ((((ctxt->mode != X86EMUL_MODE_REAL) && (desc.type & 8)) || !(desc.type & 2)) && + (flags & X86EMUL_F_WRITE)) goto bad; /* unreadable code segment */ - if (!fetch && (desc.type & 8) && !(desc.type & 2)) + if (!(flags & X86EMUL_F_FETCH) && (desc.type & 8) && !(desc.type & 2)) goto bad; lim = desc_limit_scaled(&desc); if (!(desc.type & 8) && (desc.type & 4)) { @@ -757,8 +757,8 @@ static int linearize(struct x86_emulate_ctxt *ctxt, ulong *linear) { unsigned max_size; - return __linearize(ctxt, addr, &max_size, size, write, false, - ctxt->mode, linear); + return __linearize(ctxt, addr, &max_size, size, ctxt->mode, linear, + write ? X86EMUL_F_WRITE : 0); } static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst) @@ -771,7 +771,8 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst) if (ctxt->op_bytes != sizeof(unsigned long)) addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1); - rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear); + rc = __linearize(ctxt, addr, &max_size, 1, ctxt->mode, &linear, + X86EMUL_F_FETCH); if (rc == X86EMUL_CONTINUE) ctxt->_eip = addr.ea; return rc; @@ -907,8 +908,8 @@ static int __do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, int op_size) * boundary check itself. Instead, we use max_size to check * against op_size. */ - rc = __linearize(ctxt, addr, &max_size, 0, false, true, ctxt->mode, - &linear); + rc = __linearize(ctxt, addr, &max_size, 0, ctxt->mode, &linear, + X86EMUL_F_FETCH); if (unlikely(rc != X86EMUL_CONTINUE)) return rc; @@ -1799,13 +1800,11 @@ static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) op->addr.mem, &op->val, op->bytes); - break; case OP_MEM_STR: return segmented_write(ctxt, op->addr.mem, op->data, op->bytes * op->count); - break; case OP_XMM: kvm_write_sse_reg(op->addr.xmm, &op->vec_val); break; @@ -3441,8 +3440,10 @@ static int em_invlpg(struct x86_emulate_ctxt *ctxt) { int rc; ulong linear; + unsigned int max_size; - rc = linearize(ctxt, ctxt->src.addr.mem, 1, false, &linear); + rc = __linearize(ctxt, ctxt->src.addr.mem, &max_size, 1, ctxt->mode, + &linear, X86EMUL_F_INVLPG); if (rc == X86EMUL_CONTINUE) ctxt->ops->invlpg(ctxt, linear); /* Disable writeback. */ diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h new file mode 100644 index 000000000000..ad463b1ed4e4 --- /dev/null +++ b/arch/x86/kvm/governed_features.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#if !defined(KVM_GOVERNED_FEATURE) || defined(KVM_GOVERNED_X86_FEATURE) +BUILD_BUG() +#endif + +#define KVM_GOVERNED_X86_FEATURE(x) KVM_GOVERNED_FEATURE(X86_FEATURE_##x) + +KVM_GOVERNED_X86_FEATURE(GBPAGES) +KVM_GOVERNED_X86_FEATURE(XSAVES) +KVM_GOVERNED_X86_FEATURE(VMX) +KVM_GOVERNED_X86_FEATURE(NRIPS) +KVM_GOVERNED_X86_FEATURE(TSCRATEMSR) +KVM_GOVERNED_X86_FEATURE(V_VMSAVE_VMLOAD) +KVM_GOVERNED_X86_FEATURE(LBRV) +KVM_GOVERNED_X86_FEATURE(PAUSEFILTER) +KVM_GOVERNED_X86_FEATURE(PFTHRESHOLD) +KVM_GOVERNED_X86_FEATURE(VGIF) +KVM_GOVERNED_X86_FEATURE(VNMI) +KVM_GOVERNED_X86_FEATURE(LAM) + +#undef KVM_GOVERNED_X86_FEATURE +#undef KVM_GOVERNED_FEATURE diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index b28fd020066f..8a47f8541eab 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -727,10 +727,12 @@ static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, stimer_cleanup(stimer); stimer->count = count; - if (stimer->count == 0) - stimer->config.enable = 0; - else if (stimer->config.auto_enable) - stimer->config.enable = 1; + if (!host) { + if (stimer->count == 0) + stimer->config.enable = 0; + else if (stimer->config.auto_enable) + stimer->config.enable = 1; + } if (stimer->config.enable) stimer_mark_pending(stimer, false); @@ -1293,7 +1295,6 @@ static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr) case HV_X64_MSR_VP_ASSIST_PAGE: return hv_vcpu->cpuid_cache.features_eax & HV_MSR_APIC_ACCESS_AVAILABLE; - break; case HV_X64_MSR_TSC_FREQUENCY: case HV_X64_MSR_APIC_FREQUENCY: return hv_vcpu->cpuid_cache.features_eax & @@ -1321,6 +1322,56 @@ static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr) return false; } +#define KVM_HV_WIN2016_GUEST_ID 0x1040a00003839 +#define KVM_HV_WIN2016_GUEST_ID_MASK (~GENMASK_ULL(23, 16)) /* mask out the service version */ + +/* + * Hyper-V enabled Windows Server 2016 SMP VMs fail to boot in !XSAVES && XSAVEC + * configuration. + * Such configuration can result from, for example, AMD Erratum 1386 workaround. + * + * Print a notice so users aren't left wondering what's suddenly gone wrong. + */ +static void __kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_hv *hv = to_kvm_hv(kvm); + + /* Check again under the hv_lock. */ + if (hv->xsaves_xsavec_checked) + return; + + if ((hv->hv_guest_os_id & KVM_HV_WIN2016_GUEST_ID_MASK) != + KVM_HV_WIN2016_GUEST_ID) + return; + + hv->xsaves_xsavec_checked = true; + + /* UP configurations aren't affected */ + if (atomic_read(&kvm->online_vcpus) < 2) + return; + + if (guest_cpuid_has(vcpu, X86_FEATURE_XSAVES) || + !guest_cpuid_has(vcpu, X86_FEATURE_XSAVEC)) + return; + + pr_notice_ratelimited("Booting SMP Windows KVM VM with !XSAVES && XSAVEC. " + "If it fails to boot try disabling XSAVEC in the VM config.\n"); +} + +void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu) +{ + struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); + + if (!vcpu->arch.hyperv_enabled || + hv->xsaves_xsavec_checked) + return; + + mutex_lock(&hv->hv_lock); + __kvm_hv_xsaves_xsavec_maybe_warn(vcpu); + mutex_unlock(&hv->hv_lock); +} + static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { @@ -2387,7 +2438,7 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *h if (!eventfd) return HV_STATUS_INVALID_PORT_ID; - eventfd_signal(eventfd, 1); + eventfd_signal(eventfd); return HV_STATUS_SUCCESS; } diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index f83b8db72b11..923e64903da9 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -24,6 +24,8 @@ #include <linux/kvm_host.h> #include "x86.h" +#ifdef CONFIG_KVM_HYPERV + /* "Hv#1" signature */ #define HYPERV_CPUID_SIGNATURE_EAX 0x31237648 @@ -105,6 +107,17 @@ int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint); void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector); int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages); +static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector) +{ + return to_hv_vcpu(vcpu) && test_bit(vector, to_hv_synic(vcpu)->vec_bitmap); +} + +static inline bool kvm_hv_synic_auto_eoi_set(struct kvm_vcpu *vcpu, int vector) +{ + return to_hv_vcpu(vcpu) && + test_bit(vector, to_hv_synic(vcpu)->auto_eoi_bitmap); +} + void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu); bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu); @@ -169,6 +182,8 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, struct pvclock_vcpu_time_info *hv_clock); void kvm_hv_request_tsc_page_update(struct kvm *kvm); +void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu); + void kvm_hv_init_vm(struct kvm *kvm); void kvm_hv_destroy_vm(struct kvm *kvm); int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu); @@ -236,6 +251,77 @@ static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu) return kvm_hv_get_assist_page(vcpu); } +static inline void kvm_hv_nested_transtion_tlb_flush(struct kvm_vcpu *vcpu, + bool tdp_enabled) +{ + /* + * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or + * L2's VP_ID upon request from the guest. Make sure we check for + * pending entries in the right FIFO upon L1/L2 transition as these + * requests are put by other vCPUs asynchronously. + */ + if (to_hv_vcpu(vcpu) && tdp_enabled) + kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu); +} + int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu); +#else /* CONFIG_KVM_HYPERV */ +static inline void kvm_hv_setup_tsc_page(struct kvm *kvm, + struct pvclock_vcpu_time_info *hv_clock) {} +static inline void kvm_hv_request_tsc_page_update(struct kvm *kvm) {} +static inline void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu) {} +static inline void kvm_hv_init_vm(struct kvm *kvm) {} +static inline void kvm_hv_destroy_vm(struct kvm *kvm) {} +static inline int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) +{ + return 0; +} +static inline void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu) {} +static inline bool kvm_hv_hypercall_enabled(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline int kvm_hv_hypercall(struct kvm_vcpu *vcpu) +{ + return HV_STATUS_ACCESS_DENIED; +} +static inline void kvm_hv_vcpu_purge_flush_tlb(struct kvm_vcpu *vcpu) {} +static inline void kvm_hv_free_pa_page(struct kvm *kvm) {} +static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector) +{ + return false; +} +static inline bool kvm_hv_synic_auto_eoi_set(struct kvm_vcpu *vcpu, int vector) +{ + return false; +} +static inline void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector) {} +static inline bool kvm_hv_invtsc_suppressed(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu, bool hyperv_enabled) {} +static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline bool kvm_hv_is_tlb_flush_hcall(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline bool guest_hv_cpuid_has_l2_tlb_flush(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu) +{ + return 0; +} +static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu) +{ + return vcpu->vcpu_idx; +} +static inline void kvm_hv_nested_transtion_tlb_flush(struct kvm_vcpu *vcpu, bool tdp_enabled) {} +#endif /* CONFIG_KVM_HYPERV */ -#endif +#endif /* __ARCH_X86_KVM_HYPERV_H__ */ diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index b2c397dd2bc6..ad9ca8a60144 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -118,8 +118,10 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v) if (!lapic_in_kernel(v)) return v->arch.interrupt.nr; +#ifdef CONFIG_KVM_XEN if (kvm_xen_has_interrupt(v)) return v->kvm->arch.xen.upcall_vector; +#endif if (irqchip_split(v->kvm)) { int vector = v->arch.pending_external_vector; diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 16d076a1b91a..68f3f6c26046 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -144,7 +144,7 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL); } - +#ifdef CONFIG_KVM_HYPERV static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) @@ -154,6 +154,7 @@ static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e, return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint); } +#endif int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, @@ -163,9 +164,11 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, int r; switch (e->type) { +#ifdef CONFIG_KVM_HYPERV case KVM_IRQ_ROUTING_HV_SINT: return kvm_hv_set_sint(e, kvm, irq_source_id, level, line_status); +#endif case KVM_IRQ_ROUTING_MSI: if (kvm_msi_route_invalid(kvm, e)) @@ -314,11 +317,13 @@ int kvm_set_routing_entry(struct kvm *kvm, if (kvm_msi_route_invalid(kvm, e)) return -EINVAL; break; +#ifdef CONFIG_KVM_HYPERV case KVM_IRQ_ROUTING_HV_SINT: e->set = kvm_hv_set_sint; e->hv_sint.vcpu = ue->u.hv_sint.vcpu; e->hv_sint.sint = ue->u.hv_sint.sint; break; +#endif #ifdef CONFIG_KVM_XEN case KVM_IRQ_ROUTING_XEN_EVTCHN: return kvm_xen_setup_evtchn(kvm, e, ue); @@ -438,5 +443,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, void kvm_arch_irq_routing_update(struct kvm *kvm) { +#ifdef CONFIG_KVM_HYPERV kvm_hv_irq_routing_update(kvm); +#endif } diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index ab65f3a47dfd..e6d149825169 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -88,6 +88,12 @@ struct x86_instruction_info { #define X86EMUL_IO_NEEDED 5 /* IO is needed to complete emulation */ #define X86EMUL_INTERCEPTED 6 /* Intercepted by nested VMCB/VMCS */ +/* x86-specific emulation flags */ +#define X86EMUL_F_WRITE BIT(0) +#define X86EMUL_F_FETCH BIT(1) +#define X86EMUL_F_IMPLICIT BIT(2) +#define X86EMUL_F_INVLPG BIT(3) + struct x86_emulate_ops { void (*vm_bugged)(struct x86_emulate_ctxt *ctxt); /* @@ -213,7 +219,6 @@ struct x86_emulate_ops { bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool exact_only); - bool (*guest_has_long_mode)(struct x86_emulate_ctxt *ctxt); bool (*guest_has_movbe)(struct x86_emulate_ctxt *ctxt); bool (*guest_has_fxsr)(struct x86_emulate_ctxt *ctxt); bool (*guest_has_rdpid)(struct x86_emulate_ctxt *ctxt); @@ -225,6 +230,9 @@ struct x86_emulate_ops { int (*leave_smm)(struct x86_emulate_ctxt *ctxt); void (*triple_fault)(struct x86_emulate_ctxt *ctxt); int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr); + + gva_t (*get_untagged_addr)(struct x86_emulate_ctxt *ctxt, gva_t addr, + unsigned int flags); }; /* Type, address-of, and value of an instruction's operand. */ diff --git a/arch/x86/kvm/kvm_onhyperv.h b/arch/x86/kvm/kvm_onhyperv.h index f9ca3e7432b2..eefab3dc8498 100644 --- a/arch/x86/kvm/kvm_onhyperv.h +++ b/arch/x86/kvm/kvm_onhyperv.h @@ -10,6 +10,26 @@ int hv_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, gfn_t nr_pages); int hv_flush_remote_tlbs(struct kvm *kvm); void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp); +static inline hpa_t hv_get_partition_assist_page(struct kvm_vcpu *vcpu) +{ + /* + * Partition assist page is something which Hyper-V running in L0 + * requires from KVM running in L1 before direct TLB flush for L2 + * guests can be enabled. KVM doesn't currently use the page but to + * comply with TLFS it still needs to be allocated. For now, this + * is a single page shared among all vCPUs. + */ + struct hv_partition_assist_pg **p_hv_pa_pg = + &vcpu->kvm->arch.hv_pa_pg; + + if (!*p_hv_pa_pg) + *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT); + + if (!*p_hv_pa_pg) + return INVALID_PAGE; + + return __pa(*p_hv_pa_pg); +} #else /* !CONFIG_HYPERV */ static inline int hv_flush_remote_tlbs(struct kvm *kvm) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index a983a16163b1..3242f3da2457 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -376,7 +376,8 @@ void kvm_recalculate_apic_map(struct kvm *kvm) struct kvm_vcpu *vcpu; unsigned long i; u32 max_id = 255; /* enough space for any xAPIC ID */ - bool xapic_id_mismatch = false; + bool xapic_id_mismatch; + int r; /* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map. */ if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN) @@ -386,9 +387,14 @@ void kvm_recalculate_apic_map(struct kvm *kvm) "Dirty APIC map without an in-kernel local APIC"); mutex_lock(&kvm->arch.apic_map_lock); + +retry: /* - * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map - * (if clean) or the APIC registers (if dirty). + * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map (if clean) + * or the APIC registers (if dirty). Note, on retry the map may have + * not yet been marked dirty by whatever task changed a vCPU's x2APIC + * ID, i.e. the map may still show up as in-progress. In that case + * this task still needs to retry and complete its calculation. */ if (atomic_cmpxchg_acquire(&kvm->arch.apic_map_dirty, DIRTY, UPDATE_IN_PROGRESS) == CLEAN) { @@ -397,6 +403,15 @@ void kvm_recalculate_apic_map(struct kvm *kvm) return; } + /* + * Reset the mismatch flag between attempts so that KVM does the right + * thing if a vCPU changes its xAPIC ID, but do NOT reset max_id, i.e. + * keep max_id strictly increasing. Disallowing max_id from shrinking + * ensures KVM won't get stuck in an infinite loop, e.g. if the vCPU + * with the highest x2APIC ID is toggling its APIC on and off. + */ + xapic_id_mismatch = false; + kvm_for_each_vcpu(i, vcpu, kvm) if (kvm_apic_present(vcpu)) max_id = max(max_id, kvm_x2apic_id(vcpu->arch.apic)); @@ -415,9 +430,15 @@ void kvm_recalculate_apic_map(struct kvm *kvm) if (!kvm_apic_present(vcpu)) continue; - if (kvm_recalculate_phys_map(new, vcpu, &xapic_id_mismatch)) { + r = kvm_recalculate_phys_map(new, vcpu, &xapic_id_mismatch); + if (r) { kvfree(new); new = NULL; + if (r == -E2BIG) { + cond_resched(); + goto retry; + } + goto out; } @@ -1454,8 +1475,7 @@ static int apic_set_eoi(struct kvm_lapic *apic) apic_clear_isr(vector, apic); apic_update_ppr(apic); - if (to_hv_vcpu(apic->vcpu) && - test_bit(vector, to_hv_synic(apic->vcpu)->vec_bitmap)) + if (kvm_hv_synic_has_vector(apic->vcpu, vector)) kvm_hv_synic_send_eoi(apic->vcpu, vector); kvm_ioapic_send_eoi(apic, vector); @@ -2423,22 +2443,22 @@ EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) { struct kvm_lapic *apic = vcpu->arch.apic; - u64 val; /* - * ICR is a single 64-bit register when x2APIC is enabled. For legacy - * xAPIC, ICR writes need to go down the common (slightly slower) path - * to get the upper half from ICR2. + * ICR is a single 64-bit register when x2APIC is enabled, all others + * registers hold 32-bit values. For legacy xAPIC, ICR writes need to + * go down the common path to get the upper half from ICR2. + * + * Note, using the write helpers may incur an unnecessary write to the + * virtual APIC state, but KVM needs to conditionally modify the value + * in certain cases, e.g. to clear the ICR busy bit. The cost of extra + * conditional branches is likely a wash relative to the cost of the + * maybe-unecessary write, and both are in the noise anyways. */ - if (apic_x2apic_mode(apic) && offset == APIC_ICR) { - val = kvm_lapic_get_reg64(apic, APIC_ICR); - kvm_apic_send_ipi(apic, (u32)val, (u32)(val >> 32)); - trace_kvm_apic_write(APIC_ICR, val); - } else { - /* TODO: optimize to just emulate side effect w/o one more write */ - val = kvm_lapic_get_reg(apic, offset); - kvm_lapic_reg_write(apic, offset, (u32)val); - } + if (apic_x2apic_mode(apic) && offset == APIC_ICR) + kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR)); + else + kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset)); } EXPORT_SYMBOL_GPL(kvm_apic_write_nodecode); @@ -2649,6 +2669,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) u64 msr_val; int i; + static_call_cond(kvm_x86_apicv_pre_state_restore)(vcpu); + if (!init_event) { msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; if (kvm_vcpu_is_reset_bsp(vcpu)) @@ -2738,13 +2760,17 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) { u32 reg = kvm_lapic_get_reg(apic, lvt_type); int vector, mode, trig_mode; + int r; if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) { vector = reg & APIC_VECTOR_MASK; mode = reg & APIC_MODE_MASK; trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; - return __apic_accept_irq(apic, mode, vector, 1, trig_mode, - NULL); + + r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL); + if (r && lvt_type == APIC_LVTPC) + kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED); + return r; } return 0; } @@ -2878,7 +2904,7 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) */ apic_clear_irr(vector, apic); - if (to_hv_vcpu(vcpu) && test_bit(vector, to_hv_synic(vcpu)->auto_eoi_bitmap)) { + if (kvm_hv_synic_auto_eoi_set(vcpu, vector)) { /* * For auto-EOI interrupts, there might be another pending * interrupt above PPR, so check whether to raise another @@ -2956,6 +2982,8 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) struct kvm_lapic *apic = vcpu->arch.apic; int r; + static_call_cond(kvm_x86_apicv_pre_state_restore)(vcpu); + kvm_lapic_set_base(vcpu, vcpu->arch.apic_base); /* set SPIV separately to get count of SW disabled APICs right */ apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV))); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 92d5a1924fc1..60f21bb4c27b 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -121,6 +121,8 @@ void kvm_mmu_unload(struct kvm_vcpu *vcpu); void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu); void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu); void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu); +void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, + int bytes); static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) { @@ -144,6 +146,14 @@ static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu) return kvm_get_pcid(vcpu, kvm_read_cr3(vcpu)); } +static inline unsigned long kvm_get_active_cr3_lam_bits(struct kvm_vcpu *vcpu) +{ + if (!guest_can_use(vcpu, X86_FEATURE_LAM)) + return 0; + + return kvm_read_cr3(vcpu) & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57); +} + static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu) { u64 root_hpa = vcpu->arch.mmu->root.hpa; @@ -235,6 +245,13 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, return -(u32)fault & errcode; } +bool __kvm_mmu_honors_guest_mtrrs(bool vm_has_noncoherent_dma); + +static inline bool kvm_mmu_honors_guest_mtrrs(struct kvm *kvm) +{ + return __kvm_mmu_honors_guest_mtrrs(kvm_arch_has_noncoherent_dma(kvm)); +} + void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end); int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index ec169f5c7dce..2d6cdeab1f8a 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -25,6 +25,7 @@ #include "kvm_cache_regs.h" #include "smm.h" #include "kvm_emulate.h" +#include "page_track.h" #include "cpuid.h" #include "spte.h" @@ -53,7 +54,7 @@ #include <asm/io.h> #include <asm/set_memory.h> #include <asm/vmx.h> -#include <asm/kvm_page_track.h> + #include "trace.h" extern bool itlb_multihit_kvm_mitigation; @@ -115,11 +116,6 @@ static int max_huge_page_level __read_mostly; static int tdp_root_level __read_mostly; static int max_tdp_level __read_mostly; -#ifdef MMU_DEBUG -bool dbg = 0; -module_param(dbg, bool, 0644); -#endif - #define PTE_PREFETCH_NUM 8 #include <trace/events/kvm.h> @@ -275,19 +271,11 @@ static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu, static inline bool kvm_available_flush_remote_tlbs_range(void) { +#if IS_ENABLED(CONFIG_HYPERV) return kvm_x86_ops.flush_remote_tlbs_range; -} - -void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn, - gfn_t nr_pages) -{ - int ret = -EOPNOTSUPP; - - if (kvm_x86_ops.flush_remote_tlbs_range) - ret = static_call(kvm_x86_flush_remote_tlbs_range)(kvm, start_gfn, - nr_pages); - if (ret) - kvm_flush_remote_tlbs(kvm); +#else + return false; +#endif } static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index); @@ -490,7 +478,7 @@ retry: */ static void mmu_spte_set(u64 *sptep, u64 new_spte) { - WARN_ON(is_shadow_present_pte(*sptep)); + WARN_ON_ONCE(is_shadow_present_pte(*sptep)); __set_spte(sptep, new_spte); } @@ -502,7 +490,7 @@ static u64 mmu_spte_update_no_track(u64 *sptep, u64 new_spte) { u64 old_spte = *sptep; - WARN_ON(!is_shadow_present_pte(new_spte)); + WARN_ON_ONCE(!is_shadow_present_pte(new_spte)); check_spte_writable_invariants(new_spte); if (!is_shadow_present_pte(old_spte)) { @@ -515,7 +503,7 @@ static u64 mmu_spte_update_no_track(u64 *sptep, u64 new_spte) else old_spte = __update_clear_spte_slow(sptep, new_spte); - WARN_ON(spte_to_pfn(old_spte) != spte_to_pfn(new_spte)); + WARN_ON_ONCE(spte_to_pfn(old_spte) != spte_to_pfn(new_spte)); return old_spte; } @@ -597,7 +585,7 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) * by a refcounted page, the refcount is elevated. */ page = kvm_pfn_to_refcounted_page(pfn); - WARN_ON(page && !page_count(page)); + WARN_ON_ONCE(page && !page_count(page)); if (is_accessed_spte(old_spte)) kvm_set_pfn_accessed(pfn); @@ -803,16 +791,26 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn, return &slot->arch.lpage_info[level - 2][idx]; } +/* + * The most significant bit in disallow_lpage tracks whether or not memory + * attributes are mixed, i.e. not identical for all gfns at the current level. + * The lower order bits are used to refcount other cases where a hugepage is + * disallowed, e.g. if KVM has shadow a page table at the gfn. + */ +#define KVM_LPAGE_MIXED_FLAG BIT(31) + static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot, gfn_t gfn, int count) { struct kvm_lpage_info *linfo; - int i; + int old, i; for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); + + old = linfo->disallow_lpage; linfo->disallow_lpage += count; - WARN_ON(linfo->disallow_lpage < 0); + WARN_ON_ONCE((old ^ linfo->disallow_lpage) & KVM_LPAGE_MIXED_FLAG); } } @@ -839,8 +837,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) /* the non-leaf shadow pages are keeping readonly. */ if (sp->role.level > PG_LEVEL_4K) - return kvm_slot_page_track_add_page(kvm, slot, gfn, - KVM_PAGE_TRACK_WRITE); + return __kvm_write_track_add_gfn(kvm, slot, gfn); kvm_mmu_gfn_disallow_lpage(slot, gfn); @@ -886,8 +883,7 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, gfn); if (sp->role.level > PG_LEVEL_4K) - return kvm_slot_page_track_remove_page(kvm, slot, gfn, - KVM_PAGE_TRACK_WRITE); + return __kvm_write_track_remove_gfn(kvm, slot, gfn); kvm_mmu_gfn_allow_lpage(slot, gfn); } @@ -941,10 +937,8 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, int count = 0; if (!rmap_head->val) { - rmap_printk("%p %llx 0->1\n", spte, *spte); rmap_head->val = (unsigned long)spte; } else if (!(rmap_head->val & 1)) { - rmap_printk("%p %llx 1->many\n", spte, *spte); desc = kvm_mmu_memory_cache_alloc(cache); desc->sptes[0] = (u64 *)rmap_head->val; desc->sptes[1] = spte; @@ -953,7 +947,6 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, rmap_head->val = (unsigned long)desc | 1; ++count; } else { - rmap_printk("%p %llx many->many\n", spte, *spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); count = desc->tail_count + desc->spte_count; @@ -973,7 +966,8 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, return count; } -static void pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, +static void pte_list_desc_remove_entry(struct kvm *kvm, + struct kvm_rmap_head *rmap_head, struct pte_list_desc *desc, int i) { struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); @@ -984,7 +978,7 @@ static void pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, * when adding an entry and the previous head is full, and heads are * removed (this flow) when they become empty. */ - BUG_ON(j < 0); + KVM_BUG_ON_DATA_CORRUPTION(j < 0, kvm); /* * Replace the to-be-freed SPTE with the last valid entry from the head @@ -999,7 +993,7 @@ static void pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, /* * The head descriptor is empty. If there are no tail descriptors, - * nullify the rmap head to mark the list as emtpy, else point the rmap + * nullify the rmap head to mark the list as empty, else point the rmap * head at the next descriptor, i.e. the new head. */ if (!head_desc->more) @@ -1009,35 +1003,34 @@ static void pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, mmu_free_pte_list_desc(head_desc); } -static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head) +static void pte_list_remove(struct kvm *kvm, u64 *spte, + struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc; int i; - if (!rmap_head->val) { - pr_err("%s: %p 0->BUG\n", __func__, spte); - BUG(); - } else if (!(rmap_head->val & 1)) { - rmap_printk("%p 1->0\n", spte); - if ((u64 *)rmap_head->val != spte) { - pr_err("%s: %p 1->BUG\n", __func__, spte); - BUG(); - } + if (KVM_BUG_ON_DATA_CORRUPTION(!rmap_head->val, kvm)) + return; + + if (!(rmap_head->val & 1)) { + if (KVM_BUG_ON_DATA_CORRUPTION((u64 *)rmap_head->val != spte, kvm)) + return; + rmap_head->val = 0; } else { - rmap_printk("%p many->many\n", spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); while (desc) { for (i = 0; i < desc->spte_count; ++i) { if (desc->sptes[i] == spte) { - pte_list_desc_remove_entry(rmap_head, desc, i); + pte_list_desc_remove_entry(kvm, rmap_head, + desc, i); return; } } desc = desc->more; } - pr_err("%s: %p many->many\n", __func__, spte); - BUG(); + + KVM_BUG_ON_DATA_CORRUPTION(true, kvm); } } @@ -1045,7 +1038,7 @@ static void kvm_zap_one_rmap_spte(struct kvm *kvm, struct kvm_rmap_head *rmap_head, u64 *sptep) { mmu_spte_clear_track_bits(kvm, sptep); - pte_list_remove(sptep, rmap_head); + pte_list_remove(kvm, sptep, rmap_head); } /* Return true if at least one SPTE was zapped, false otherwise */ @@ -1120,7 +1113,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) slot = __gfn_to_memslot(slots, gfn); rmap_head = gfn_to_rmap(gfn, sp->role.level, slot); - pte_list_remove(spte, rmap_head); + pte_list_remove(kvm, spte, rmap_head); } /* @@ -1212,7 +1205,7 @@ static void drop_large_spte(struct kvm *kvm, u64 *sptep, bool flush) struct kvm_mmu_page *sp; sp = sptep_to_sp(sptep); - WARN_ON(sp->role.level == PG_LEVEL_4K); + WARN_ON_ONCE(sp->role.level == PG_LEVEL_4K); drop_spte(kvm, sptep); @@ -1241,8 +1234,6 @@ static bool spte_write_protect(u64 *sptep, bool pt_protect) !(pt_protect && is_mmu_writable_spte(spte))) return false; - rmap_printk("spte %p %llx\n", sptep, *sptep); - if (pt_protect) spte &= ~shadow_mmu_writable_mask; spte = spte & ~PT_WRITABLE_MASK; @@ -1267,9 +1258,7 @@ static bool spte_clear_dirty(u64 *sptep) { u64 spte = *sptep; - rmap_printk("spte %p %llx\n", sptep, *sptep); - - MMU_WARN_ON(!spte_ad_enabled(spte)); + KVM_MMU_WARN_ON(!spte_ad_enabled(spte)); spte &= ~shadow_dirty_mask; return mmu_spte_update(sptep, spte); } @@ -1399,7 +1388,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, gfn_t end = slot->base_gfn + gfn_offset + __fls(mask); if (READ_ONCE(eager_page_split)) - kvm_mmu_try_split_huge_pages(kvm, slot, start, end, PG_LEVEL_4K); + kvm_mmu_try_split_huge_pages(kvm, slot, start, end + 1, PG_LEVEL_4K); kvm_mmu_slot_gfn_write_protect(kvm, slot, start, PG_LEVEL_2M); @@ -1475,14 +1464,11 @@ static bool kvm_set_pte_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, u64 new_spte; kvm_pfn_t new_pfn; - WARN_ON(pte_huge(pte)); + WARN_ON_ONCE(pte_huge(pte)); new_pfn = pte_pfn(pte); restart: for_each_rmap_spte(rmap_head, &iter, sptep) { - rmap_printk("spte %p %llx gfn %llx (%d)\n", - sptep, *sptep, gfn, level); - need_flush = true; if (pte_write(pte)) { @@ -1588,7 +1574,7 @@ static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm, for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, range->start, range->end - 1, &iterator) ret |= handler(kvm, iterator.rmap, range->slot, iterator.gfn, - iterator.level, range->pte); + iterator.level, range->arg.pte); return ret; } @@ -1710,21 +1696,19 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) return young; } -#ifdef MMU_DEBUG -static int is_empty_shadow_page(u64 *spt) +static void kvm_mmu_check_sptes_at_free(struct kvm_mmu_page *sp) { - u64 *pos; - u64 *end; +#ifdef CONFIG_KVM_PROVE_MMU + int i; - for (pos = spt, end = pos + SPTE_ENT_PER_PAGE; pos != end; pos++) - if (is_shadow_present_pte(*pos)) { - printk(KERN_ERR "%s: %p %llx\n", __func__, - pos, *pos); - return 0; - } - return 1; -} + for (i = 0; i < SPTE_ENT_PER_PAGE; i++) { + if (KVM_MMU_WARN_ON(is_shadow_present_pte(sp->spt[i]))) + pr_err_ratelimited("SPTE %llx (@ %p) for gfn %llx shadow-present at free", + sp->spt[i], &sp->spt[i], + kvm_mmu_page_get_gfn(sp, i)); + } #endif +} /* * This value is the sum of all of the kvm instances's @@ -1752,7 +1736,8 @@ static void kvm_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) static void kvm_mmu_free_shadow_page(struct kvm_mmu_page *sp) { - MMU_WARN_ON(!is_empty_shadow_page(sp->spt)); + kvm_mmu_check_sptes_at_free(sp); + hlist_del(&sp->hash_link); list_del(&sp->link); free_page((unsigned long)sp->spt); @@ -1775,16 +1760,16 @@ static void mmu_page_add_parent_pte(struct kvm_mmu_memory_cache *cache, pte_list_add(cache, parent_pte, &sp->parent_ptes); } -static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp, +static void mmu_page_remove_parent_pte(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *parent_pte) { - pte_list_remove(parent_pte, &sp->parent_ptes); + pte_list_remove(kvm, parent_pte, &sp->parent_ptes); } -static void drop_parent_pte(struct kvm_mmu_page *sp, +static void drop_parent_pte(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *parent_pte) { - mmu_page_remove_parent_pte(sp, parent_pte); + mmu_page_remove_parent_pte(kvm, sp, parent_pte); mmu_spte_clear_no_track(parent_pte); } @@ -1840,7 +1825,7 @@ static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp, static inline void clear_unsync_child_bit(struct kvm_mmu_page *sp, int idx) { --sp->unsync_children; - WARN_ON((int)sp->unsync_children < 0); + WARN_ON_ONCE((int)sp->unsync_children < 0); __clear_bit(idx, sp->unsync_child_bitmap); } @@ -1898,7 +1883,7 @@ static int mmu_unsync_walk(struct kvm_mmu_page *sp, static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) { - WARN_ON(!sp->unsync); + WARN_ON_ONCE(!sp->unsync); trace_kvm_mmu_sync_page(sp); sp->unsync = 0; --kvm->stat.mmu_unsync; @@ -2073,11 +2058,11 @@ static int mmu_pages_first(struct kvm_mmu_pages *pvec, if (pvec->nr == 0) return 0; - WARN_ON(pvec->page[0].idx != INVALID_INDEX); + WARN_ON_ONCE(pvec->page[0].idx != INVALID_INDEX); sp = pvec->page[0].sp; level = sp->role.level; - WARN_ON(level == PG_LEVEL_4K); + WARN_ON_ONCE(level == PG_LEVEL_4K); parents->parent[level-2] = sp; @@ -2099,7 +2084,7 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents) if (!sp) return; - WARN_ON(idx == INVALID_INDEX); + WARN_ON_ONCE(idx == INVALID_INDEX); clear_unsync_child_bit(sp, idx); level++; } while (!sp->unsync_children); @@ -2220,7 +2205,7 @@ static struct kvm_mmu_page *kvm_mmu_find_shadow_page(struct kvm *kvm, if (ret < 0) break; - WARN_ON(!list_empty(&invalid_list)); + WARN_ON_ONCE(!list_empty(&invalid_list)); if (ret > 0) kvm_flush_remote_tlbs(kvm); } @@ -2499,7 +2484,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (child->role.access == direct_access) return; - drop_parent_pte(child, sptep); + drop_parent_pte(vcpu->kvm, child, sptep); kvm_flush_remote_tlbs_sptep(vcpu->kvm, sptep); } } @@ -2517,7 +2502,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, drop_spte(kvm, spte); } else { child = spte_to_child_sp(pte); - drop_parent_pte(child, spte); + drop_parent_pte(kvm, child, spte); /* * Recursively zap nested TDP SPs, parentless SPs are @@ -2548,13 +2533,13 @@ static int kvm_mmu_page_unlink_children(struct kvm *kvm, return zapped; } -static void kvm_mmu_unlink_parents(struct kvm_mmu_page *sp) +static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp) { u64 *sptep; struct rmap_iterator iter; while ((sptep = rmap_get_first(&sp->parent_ptes, &iter))) - drop_parent_pte(sp, sptep); + drop_parent_pte(kvm, sp, sptep); } static int mmu_zap_unsync_children(struct kvm *kvm, @@ -2593,7 +2578,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, ++kvm->stat.mmu_shadow_zapped; *nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list); *nr_zapped += kvm_mmu_page_unlink_children(kvm, sp, invalid_list); - kvm_mmu_unlink_parents(sp); + kvm_mmu_unlink_parents(kvm, sp); /* Zapping children means active_mmu_pages has become unstable. */ list_unstable = *nr_zapped; @@ -2675,7 +2660,7 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, kvm_flush_remote_tlbs(kvm); list_for_each_entry_safe(sp, nsp, invalid_list, link) { - WARN_ON(!sp->role.invalid || sp->root_count); + WARN_ON_ONCE(!sp->role.invalid || sp->root_count); kvm_mmu_free_shadow_page(sp); } } @@ -2775,12 +2760,9 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) LIST_HEAD(invalid_list); int r; - pgprintk("%s: looking for gfn %llx\n", __func__, gfn); r = 0; write_lock(&kvm->mmu_lock); for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn) { - pgprintk("%s: gfn %llx role %x\n", __func__, gfn, - sp->role.word); r = 1; kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); } @@ -2831,7 +2813,7 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, * track machinery is used to write-protect upper-level shadow pages, * i.e. this guards the role.level == 4K assertion below! */ - if (kvm_slot_page_track_is_active(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_gfn_is_write_tracked(kvm, slot, gfn)) return -EPERM; /* @@ -2864,16 +2846,16 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, /* * Recheck after taking the spinlock, a different vCPU * may have since marked the page unsync. A false - * positive on the unprotected check above is not + * negative on the unprotected check above is not * possible as clearing sp->unsync _must_ hold mmu_lock - * for write, i.e. unsync cannot transition from 0->1 + * for write, i.e. unsync cannot transition from 1->0 * while this CPU holds mmu_lock for read (or write). */ if (READ_ONCE(sp->unsync)) continue; } - WARN_ON(sp->role.level != PG_LEVEL_4K); + WARN_ON_ONCE(sp->role.level != PG_LEVEL_4K); kvm_unsync_page(kvm, sp); } if (locked) @@ -2938,9 +2920,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, bool prefetch = !fault || fault->prefetch; bool write_fault = fault && fault->write; - pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__, - *sptep, write_fault, gfn); - if (unlikely(is_noslot_pfn(pfn))) { vcpu->stat.pf_mmio_spte_created++; mark_mmio_spte(vcpu, sptep, gfn, pte_access); @@ -2957,11 +2936,9 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, u64 pte = *sptep; child = spte_to_child_sp(pte); - drop_parent_pte(child, sptep); + drop_parent_pte(vcpu->kvm, child, sptep); flush = true; } else if (pfn != spte_to_pfn(*sptep)) { - pgprintk("hfn old %llx new %llx\n", - spte_to_pfn(*sptep), pfn); drop_spte(vcpu->kvm, sptep); flush = true; } else @@ -2986,8 +2963,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, if (flush) kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level); - pgprintk("%s: setting spte %llx\n", __func__, *sptep); - if (!was_rmapped) { WARN_ON_ONCE(ret == RET_PF_SPURIOUS); rmap_add(vcpu, slot, sptep, gfn, pte_access); @@ -3033,7 +3008,7 @@ static void __direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *spte, *start = NULL; int i; - WARN_ON(!sp->role.direct); + WARN_ON_ONCE(!sp->role.direct); i = spte_index(sptep) & ~(PTE_PREFETCH_NUM - 1); spte = sp->spt + i; @@ -3087,7 +3062,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) * * There are several ways to safely use this helper: * - * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before + * - Check mmu_invalidate_retry_gfn() after grabbing the mapping level, before * consuming it. In this case, mmu_lock doesn't need to be held during the * lookup, but it does need to be held while checking the MMU notifier. * @@ -3168,9 +3143,9 @@ out: return level; } -int kvm_mmu_max_mapping_level(struct kvm *kvm, - const struct kvm_memory_slot *slot, gfn_t gfn, - int max_level) +static int __kvm_mmu_max_mapping_level(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t gfn, int max_level, bool is_private) { struct kvm_lpage_info *linfo; int host_level; @@ -3182,6 +3157,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, break; } + if (is_private) + return max_level; + if (max_level == PG_LEVEL_4K) return PG_LEVEL_4K; @@ -3189,6 +3167,16 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, return min(host_level, max_level); } +int kvm_mmu_max_mapping_level(struct kvm *kvm, + const struct kvm_memory_slot *slot, gfn_t gfn, + int max_level) +{ + bool is_private = kvm_slot_can_be_private(slot) && + kvm_mem_is_private(kvm, gfn); + + return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level, is_private); +} + void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; @@ -3209,8 +3197,9 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault * Enforce the iTLB multihit workaround after capturing the requested * level, which will be used to do precise, accurate accounting. */ - fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot, - fault->gfn, fault->max_level); + fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot, + fault->gfn, fault->max_level, + fault->is_private); if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed) return; @@ -3456,8 +3445,8 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_mmu_page *sp; int ret = RET_PF_INVALID; - u64 spte = 0ull; - u64 *sptep = NULL; + u64 spte; + u64 *sptep; uint retry_count = 0; if (!page_fault_can_be_fast(fault)) @@ -3473,6 +3462,14 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) else sptep = fast_pf_get_last_sptep(vcpu, fault->addr, &spte); + /* + * It's entirely possible for the mapping to have been zapped + * by a different task, but the root page should always be + * available as the vCPU holds a reference to its root(s). + */ + if (WARN_ON_ONCE(!sptep)) + spte = REMOVED_SPTE; + if (!is_shadow_present_pte(spte)) break; @@ -3574,16 +3571,12 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, if (!VALID_PAGE(*root_hpa)) return; - /* - * The "root" may be a special root, e.g. a PAE entry, treat it as a - * SPTE to ensure any non-PA bits are dropped. - */ - sp = spte_to_child_sp(*root_hpa); - if (WARN_ON(!sp)) + sp = root_to_sp(*root_hpa); + if (WARN_ON_ONCE(!sp)) return; if (is_tdp_mmu_page(sp)) - kvm_tdp_mmu_put_root(kvm, sp, false); + kvm_tdp_mmu_put_root(kvm, sp); else if (!--sp->root_count && sp->role.invalid) kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); @@ -3624,7 +3617,9 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, &invalid_list); if (free_active_root) { - if (to_shadow_page(mmu->root.hpa)) { + if (kvm_mmu_is_dummy_root(mmu->root.hpa)) { + /* Nothing to cleanup for dummy roots. */ + } else if (root_to_sp(mmu->root.hpa)) { mmu_free_root_page(kvm, &mmu->root.hpa, &invalid_list); } else if (mmu->pae_root) { for (i = 0; i < 4; ++i) { @@ -3648,6 +3643,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_free_roots); void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu) { unsigned long roots_to_free = 0; + struct kvm_mmu_page *sp; hpa_t root_hpa; int i; @@ -3662,8 +3658,8 @@ void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu) if (!VALID_PAGE(root_hpa)) continue; - if (!to_shadow_page(root_hpa) || - to_shadow_page(root_hpa)->role.guest_mode) + sp = root_to_sp(root_hpa); + if (!sp || sp->role.guest_mode) roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); } @@ -3671,19 +3667,6 @@ void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu) } EXPORT_SYMBOL_GPL(kvm_mmu_free_guest_mode_roots); - -static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn) -{ - int ret = 0; - - if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) { - kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); - ret = 1; - } - - return ret; -} - static hpa_t mmu_alloc_root(struct kvm_vcpu *vcpu, gfn_t gfn, int quadrant, u8 level) { @@ -3776,7 +3759,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) kvm_page_track_write_tracking_enabled(kvm)) goto out_success; - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot(slot, bkt, slots) { /* @@ -3819,10 +3802,12 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) hpa_t root; root_pgd = kvm_mmu_get_guest_pgd(vcpu, mmu); - root_gfn = root_pgd >> PAGE_SHIFT; + root_gfn = (root_pgd & __PT_BASE_ADDR_MASK) >> PAGE_SHIFT; - if (mmu_check_root(vcpu, root_gfn)) - return 1; + if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) { + mmu->root.hpa = kvm_mmu_get_dummy_root(); + return 0; + } /* * On SVM, reading PDPTRs might access guest memory, which might fault @@ -3834,8 +3819,8 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) if (!(pdptrs[i] & PT_PRESENT_MASK)) continue; - if (mmu_check_root(vcpu, pdptrs[i] >> PAGE_SHIFT)) - return 1; + if (!kvm_vcpu_is_visible_gfn(vcpu, pdptrs[i] >> PAGE_SHIFT)) + pdptrs[i] = 0; } } @@ -4002,7 +3987,7 @@ static bool is_unsync_root(hpa_t root) { struct kvm_mmu_page *sp; - if (!VALID_PAGE(root)) + if (!VALID_PAGE(root) || kvm_mmu_is_dummy_root(root)) return false; /* @@ -4018,7 +4003,7 @@ static bool is_unsync_root(hpa_t root) * requirement isn't satisfied. */ smp_rmb(); - sp = to_shadow_page(root); + sp = root_to_sp(root); /* * PAE roots (somewhat arbitrarily) aren't backed by shadow pages, the @@ -4048,11 +4033,12 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) if (vcpu->arch.mmu->cpu_role.base.level >= PT64_ROOT_4LEVEL) { hpa_t root = vcpu->arch.mmu->root.hpa; - sp = to_shadow_page(root); if (!is_unsync_root(root)) return; + sp = root_to_sp(root); + write_lock(&vcpu->kvm->mmu_lock); mmu_sync_children(vcpu, sp, true); write_unlock(&vcpu->kvm->mmu_lock); @@ -4194,7 +4180,7 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) return RET_PF_EMULATE; reserved = get_mmio_spte(vcpu, addr, &spte); - if (WARN_ON(reserved)) + if (WARN_ON_ONCE(reserved)) return -EINVAL; if (is_mmio_spte(spte)) { @@ -4232,7 +4218,7 @@ static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu, * guest is writing the page which is write tracked which can * not be fixed by page fault handler. */ - if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_gfn_is_write_tracked(vcpu->kvm, fault->slot, fault->gfn)) return true; return false; @@ -4293,6 +4279,55 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL); } +static inline u8 kvm_max_level_for_order(int order) +{ + BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G); + + KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K)); + + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G)) + return PG_LEVEL_1G; + + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M)) + return PG_LEVEL_2M; + + return PG_LEVEL_4K; +} + +static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, + PAGE_SIZE, fault->write, fault->exec, + fault->is_private); +} + +static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + int max_order, r; + + if (!kvm_slot_can_be_private(fault->slot)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn, + &max_order); + if (r) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return r; + } + + fault->max_level = min(kvm_max_level_for_order(max_order), + fault->max_level); + fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY); + + return RET_PF_CONTINUE; +} + static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; @@ -4325,6 +4360,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault return RET_PF_EMULATE; } + if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + if (fault->is_private) + return kvm_faultin_pfn_private(vcpu, fault); + async = false; fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async, fault->write, &fault->map_writable, @@ -4382,7 +4425,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, static bool is_page_fault_stale(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root.hpa); + struct kvm_mmu_page *sp = root_to_sp(vcpu->arch.mmu->root.hpa); /* Special roots, e.g. pae_root, are not backed by shadow pages. */ if (sp && is_obsolete_sp(vcpu->kvm, sp)) @@ -4400,13 +4443,17 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, return true; return fault->slot && - mmu_invalidate_retry_hva(vcpu->kvm, fault->mmu_seq, fault->hva); + mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn); } static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { int r; + /* Dummy roots are used only for shadowing bad guest roots. */ + if (WARN_ON_ONCE(kvm_mmu_is_dummy_root(vcpu->arch.mmu->root.hpa))) + return RET_PF_RETRY; + if (page_fault_handle_page_track(vcpu, fault)) return RET_PF_EMULATE; @@ -4443,8 +4490,6 @@ out_unlock: static int nonpaging_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - pgprintk("%s: gva %lx error %x\n", __func__, fault->addr, fault->error_code); - /* This path builds a PAE pagetable, we can map 2mb pages at maximum. */ fault->max_level = PG_LEVEL_2M; return direct_page_fault(vcpu, fault); @@ -4519,21 +4564,28 @@ out_unlock: } #endif -int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +bool __kvm_mmu_honors_guest_mtrrs(bool vm_has_noncoherent_dma) { /* - * If the guest's MTRRs may be used to compute the "real" memtype, - * restrict the mapping level to ensure KVM uses a consistent memtype - * across the entire mapping. If the host MTRRs are ignored by TDP - * (shadow_memtype_mask is non-zero), and the VM has non-coherent DMA - * (DMA doesn't snoop CPU caches), KVM's ABI is to honor the memtype - * from the guest's MTRRs so that guest accesses to memory that is - * DMA'd aren't cached against the guest's wishes. + * If host MTRRs are ignored (shadow_memtype_mask is non-zero), and the + * VM has non-coherent DMA (DMA doesn't snoop CPU caches), KVM's ABI is + * to honor the memtype from the guest's MTRRs so that guest accesses + * to memory that is DMA'd aren't cached against the guest's wishes. * * Note, KVM may still ultimately ignore guest MTRRs for certain PFNs, * e.g. KVM will force UC memtype for host MMIO. */ - if (shadow_memtype_mask && kvm_arch_has_noncoherent_dma(vcpu->kvm)) { + return vm_has_noncoherent_dma && shadow_memtype_mask; +} + +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +{ + /* + * If the guest's MTRRs may be used to compute the "real" memtype, + * restrict the mapping level to ensure KVM uses a consistent memtype + * across the entire mapping. + */ + if (kvm_mmu_honors_guest_mtrrs(vcpu->kvm)) { for ( ; fault->max_level > PG_LEVEL_4K; --fault->max_level) { int page_num = KVM_PAGES_PER_HPAGE(fault->max_level); gfn_t base = gfn_round_for_level(fault->gfn, @@ -4562,9 +4614,19 @@ static void nonpaging_init_context(struct kvm_mmu *context) static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t pgd, union kvm_mmu_page_role role) { - return (role.direct || pgd == root->pgd) && - VALID_PAGE(root->hpa) && - role.word == to_shadow_page(root->hpa)->role.word; + struct kvm_mmu_page *sp; + + if (!VALID_PAGE(root->hpa)) + return false; + + if (!role.direct && pgd != root->pgd) + return false; + + sp = root_to_sp(root->hpa); + if (WARN_ON_ONCE(!sp)) + return false; + + return role.word == sp->role.word; } /* @@ -4634,11 +4696,10 @@ static bool fast_pgd_switch(struct kvm *kvm, struct kvm_mmu *mmu, gpa_t new_pgd, union kvm_mmu_page_role new_role) { /* - * For now, limit the caching to 64-bit hosts+VMs in order to avoid - * having to deal with PDPTEs. We may add support for 32-bit hosts/VMs - * later if necessary. + * Limit reuse to 64-bit hosts+VMs without "special" roots in order to + * avoid having to deal with PDPTEs and other complexities. */ - if (VALID_PAGE(mmu->root.hpa) && !to_shadow_page(mmu->root.hpa)) + if (VALID_PAGE(mmu->root.hpa) && !root_to_sp(mmu->root.hpa)) kvm_mmu_free_roots(kvm, mmu, KVM_MMU_ROOT_CURRENT); if (VALID_PAGE(mmu->root.hpa)) @@ -4684,9 +4745,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd) * If this is a direct root page, it doesn't have a write flooding * count. Otherwise, clear the write flooding count. */ - if (!new_role.direct) - __clear_sp_write_flooding_count( - to_shadow_page(vcpu->arch.mmu->root.hpa)); + if (!new_role.direct) { + struct kvm_mmu_page *sp = root_to_sp(vcpu->arch.mmu->root.hpa); + + if (!WARN_ON_ONCE(!sp)) + __clear_sp_write_flooding_count(sp); + } } EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd); @@ -4808,28 +4872,13 @@ static void __reset_rsvds_bits_mask(struct rsvd_bits_validate *rsvd_check, } } -static bool guest_can_use_gbpages(struct kvm_vcpu *vcpu) -{ - /* - * If TDP is enabled, let the guest use GBPAGES if they're supported in - * hardware. The hardware page walker doesn't let KVM disable GBPAGES, - * i.e. won't treat them as reserved, and KVM doesn't redo the GVA->GPA - * walk for performance and complexity reasons. Not to mention KVM - * _can't_ solve the problem because GVA->GPA walks aren't visible to - * KVM once a TDP translation is installed. Mimic hardware behavior so - * that KVM's is at least consistent, i.e. doesn't randomly inject #PF. - */ - return tdp_enabled ? boot_cpu_has(X86_FEATURE_GBPAGES) : - guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES); -} - static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { __reset_rsvds_bits_mask(&context->guest_rsvd_check, vcpu->arch.reserved_gpa_bits, context->cpu_role.base.level, is_efer_nx(context), - guest_can_use_gbpages(vcpu), + guest_can_use(vcpu, X86_FEATURE_GBPAGES), is_cr4_pse(context), guest_cpuid_is_amd_or_hygon(vcpu)); } @@ -4906,7 +4955,8 @@ static void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, __reset_rsvds_bits_mask(shadow_zero_check, reserved_hpa_bits(), context->root_role.level, context->root_role.efer_nx, - guest_can_use_gbpages(vcpu), is_pse, is_amd); + guest_can_use(vcpu, X86_FEATURE_GBPAGES), + is_pse, is_amd); if (!shadow_me_mask) return; @@ -5467,8 +5517,8 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) * physical address properties) in a single VM would require tracking * all relevant CPUID information in kvm_mmu_page_role. That is very * undesirable as it would increase the memory requirements for - * gfn_track (see struct kvm_mmu_page_role comments). For now that - * problem is swept under the rug; KVM's CPUID API is horrific and + * gfn_write_track (see struct kvm_mmu_page_role comments). For now + * that problem is swept under the rug; KVM's CPUID API is horrific and * it's all but impossible to solve it without introducing a new API. */ vcpu->arch.root_mmu.root_role.word = 0; @@ -5531,9 +5581,9 @@ void kvm_mmu_unload(struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; kvm_mmu_free_roots(kvm, &vcpu->arch.root_mmu, KVM_MMU_ROOTS_ALL); - WARN_ON(VALID_PAGE(vcpu->arch.root_mmu.root.hpa)); + WARN_ON_ONCE(VALID_PAGE(vcpu->arch.root_mmu.root.hpa)); kvm_mmu_free_roots(kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL); - WARN_ON(VALID_PAGE(vcpu->arch.guest_mmu.root.hpa)); + WARN_ON_ONCE(VALID_PAGE(vcpu->arch.guest_mmu.root.hpa)); vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY); } @@ -5546,16 +5596,21 @@ static bool is_obsolete_root(struct kvm *kvm, hpa_t root_hpa) /* * When freeing obsolete roots, treat roots as obsolete if they don't - * have an associated shadow page. This does mean KVM will get false + * have an associated shadow page, as it's impossible to determine if + * such roots are fresh or stale. This does mean KVM will get false * positives and free roots that don't strictly need to be freed, but * such false positives are relatively rare: * - * (a) only PAE paging and nested NPT has roots without shadow pages + * (a) only PAE paging and nested NPT have roots without shadow pages + * (or any shadow paging flavor with a dummy root, see note below) * (b) remote reloads due to a memslot update obsoletes _all_ roots * (c) KVM doesn't track previous roots for PAE paging, and the guest * is unlikely to zap an in-use PGD. + * + * Note! Dummy roots are unique in that they are obsoleted by memslot + * _creation_! See also FNAME(fetch). */ - sp = to_shadow_page(root_hpa); + sp = root_to_sp(root_hpa); return !sp || is_obsolete_sp(kvm, sp); } @@ -5634,9 +5689,6 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa, { unsigned offset, pte_size, misaligned; - pgprintk("misaligned: gpa %llx bytes %d role %x\n", - gpa, bytes, sp->role.word); - offset = offset_in_page(gpa); pte_size = sp->role.has_4_byte_gpte ? 4 : 8; @@ -5684,9 +5736,8 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) return spte; } -static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *new, int bytes, - struct kvm_page_track_notifier_node *node) +void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, + int bytes) { gfn_t gfn = gpa >> PAGE_SHIFT; struct kvm_mmu_page *sp; @@ -5702,8 +5753,6 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages)) return; - pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); - write_lock(&vcpu->kvm->mmu_lock); gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, &bytes); @@ -5742,7 +5791,18 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err int r, emulation_type = EMULTYPE_PF; bool direct = vcpu->arch.mmu->root_role.direct; - if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) + /* + * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP + * checks when emulating instructions that triggers implicit access. + * WARN if hardware generates a fault with an error code that collides + * with the KVM-defined value. Clear the flag and continue on, i.e. + * don't terminate the VM, as KVM can't possibly be relying on a flag + * that KVM doesn't know about. + */ + if (WARN_ON_ONCE(error_code & PFERR_IMPLICIT_ACCESS)) + error_code &= ~PFERR_IMPLICIT_ACCESS; + + if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) return RET_PF_RETRY; r = RET_PF_INVALID; @@ -6099,7 +6159,7 @@ restart: * pages. Skip the bogus page, otherwise we'll get stuck in an * infinite loop if the page gets put back on the list (again). */ - if (WARN_ON(sp->role.invalid)) + if (WARN_ON_ONCE(sp->role.invalid)) continue; /* @@ -6199,32 +6259,15 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages)); } -static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm, - struct kvm_memory_slot *slot, - struct kvm_page_track_notifier_node *node) +void kvm_mmu_init_vm(struct kvm *kvm) { - kvm_mmu_zap_all_fast(kvm); -} - -int kvm_mmu_init_vm(struct kvm *kvm) -{ - struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; - int r; - INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages); spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); - if (tdp_mmu_enabled) { - r = kvm_mmu_init_tdp_mmu(kvm); - if (r < 0) - return r; - } - - node->track_write = kvm_mmu_pte_write; - node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot; - kvm_page_track_register_notifier(kvm, node); + if (tdp_mmu_enabled) + kvm_mmu_init_tdp_mmu(kvm); kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache; kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO; @@ -6233,8 +6276,6 @@ int kvm_mmu_init_vm(struct kvm *kvm) kvm->arch.split_desc_cache.kmem_cache = pte_list_desc_cache; kvm->arch.split_desc_cache.gfp_zero = __GFP_ZERO; - - return 0; } static void mmu_free_vm_memory_caches(struct kvm *kvm) @@ -6246,10 +6287,6 @@ static void mmu_free_vm_memory_caches(struct kvm *kvm) void kvm_mmu_uninit_vm(struct kvm *kvm) { - struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; - - kvm_page_track_unregister_notifier(kvm, node); - if (tdp_mmu_enabled) kvm_mmu_uninit_tdp_mmu(kvm); @@ -6268,7 +6305,7 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e if (!kvm_memslots_have_rmaps(kvm)) return flush; - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) { @@ -6294,27 +6331,25 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { bool flush; - int i; if (WARN_ON_ONCE(gfn_end <= gfn_start)) return; write_lock(&kvm->mmu_lock); - kvm_mmu_invalidate_begin(kvm, 0, -1ul); + kvm_mmu_invalidate_begin(kvm); + + kvm_mmu_invalidate_range_add(kvm, gfn_start, gfn_end); flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); - if (tdp_mmu_enabled) { - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start, - gfn_end, true, flush); - } + if (tdp_mmu_enabled) + flush = kvm_tdp_mmu_zap_leafs(kvm, gfn_start, gfn_end, flush); if (flush) kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start); - kvm_mmu_invalidate_end(kvm, 0, -1ul); + kvm_mmu_invalidate_end(kvm); write_unlock(&kvm->mmu_lock); } @@ -6588,7 +6623,7 @@ void kvm_mmu_try_split_huge_pages(struct kvm *kvm, kvm_tdp_mmu_try_split_huge_pages(kvm, memslot, start, end, target_level, false); /* - * A TLB flush is unnecessary at this point for the same resons as in + * A TLB flush is unnecessary at this point for the same reasons as in * kvm_mmu_slot_try_split_huge_pages(). */ } @@ -6670,7 +6705,7 @@ static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm, */ if (walk_slot_rmaps(kvm, slot, kvm_mmu_zap_collapsible_spte, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL - 1, true)) - kvm_arch_flush_remote_tlbs_memslot(kvm, slot); + kvm_flush_remote_tlbs_memslot(kvm, slot); } void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, @@ -6689,20 +6724,6 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, } } -void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, - const struct kvm_memory_slot *memslot) -{ - /* - * All current use cases for flushing the TLBs for a specific memslot - * related to dirty logging, and many do the TLB flush out of mmu_lock. - * The interaction between the various operations on memslot must be - * serialized by slots_locks to ensure the TLB flush from one operation - * is observed by any other operation on the same memslot. - */ - lockdep_assert_held(&kvm->slots_lock); - kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages); -} - void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, const struct kvm_memory_slot *memslot) { @@ -6732,7 +6753,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, */ } -void kvm_mmu_zap_all(struct kvm *kvm) +static void kvm_mmu_zap_all(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; LIST_HEAD(invalid_list); @@ -6741,7 +6762,7 @@ void kvm_mmu_zap_all(struct kvm *kvm) write_lock(&kvm->mmu_lock); restart: list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) { - if (WARN_ON(sp->role.invalid)) + if (WARN_ON_ONCE(sp->role.invalid)) continue; if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign)) goto restart; @@ -6757,9 +6778,20 @@ restart: write_unlock(&kvm->mmu_lock); } +void kvm_arch_flush_shadow_all(struct kvm *kvm) +{ + kvm_mmu_zap_all(kvm); +} + +void kvm_arch_flush_shadow_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + kvm_mmu_zap_all_fast(kvm); +} + void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) { - WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); + WARN_ON_ONCE(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); gen &= MMIO_SPTE_GEN_MASK; @@ -6770,7 +6802,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) * modifier prior to checking for a wrap of the MMIO generation so * that a wrap in any address space is detected. */ - gen &= ~((u64)KVM_ADDRESS_SPACE_NUM - 1); + gen &= ~((u64)kvm_arch_nr_memslot_as_ids(kvm) - 1); /* * The very rare case: if the MMIO generation number has wrapped, @@ -6847,11 +6879,7 @@ static unsigned long mmu_shrink_count(struct shrinker *shrink, return percpu_counter_read_positive(&kvm_total_used_mmu_pages); } -static struct shrinker mmu_shrinker = { - .count_objects = mmu_shrink_count, - .scan_objects = mmu_shrink_scan, - .seeks = DEFAULT_SEEKS * 10, -}; +static struct shrinker *mmu_shrinker; static void mmu_destroy_caches(void) { @@ -6862,7 +6890,7 @@ static void mmu_destroy_caches(void) static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp) { if (nx_hugepage_mitigation_hard_disabled) - return sprintf(buffer, "never\n"); + return sysfs_emit(buffer, "never\n"); return param_get_bool(buffer, kp); } @@ -6984,10 +7012,16 @@ int kvm_mmu_vendor_module_init(void) if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL)) goto out; - ret = register_shrinker(&mmu_shrinker, "x86-mmu"); - if (ret) + mmu_shrinker = shrinker_alloc(0, "x86-mmu"); + if (!mmu_shrinker) goto out_shrinker; + mmu_shrinker->count_objects = mmu_shrink_count; + mmu_shrinker->scan_objects = mmu_shrink_scan; + mmu_shrinker->seeks = DEFAULT_SEEKS * 10; + + shrinker_register(mmu_shrinker); + return 0; out_shrinker: @@ -7009,7 +7043,7 @@ void kvm_mmu_vendor_module_exit(void) { mmu_destroy_caches(); percpu_counter_destroy(&kvm_total_used_mmu_pages); - unregister_shrinker(&mmu_shrinker); + shrinker_free(mmu_shrinker); } /* @@ -7221,3 +7255,163 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm) if (kvm->arch.nx_huge_page_recovery_thread) kthread_stop(kvm->arch.nx_huge_page_recovery_thread); } + +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range) +{ + /* + * Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only + * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM + * can simply ignore such slots. But if userspace is making memory + * PRIVATE, then KVM must prevent the guest from accessing the memory + * as shared. And if userspace is making memory SHARED and this point + * is reached, then at least one page within the range was previously + * PRIVATE, i.e. the slot's possible hugepage ranges are changing. + * Zapping SPTEs in this case ensures KVM will reassess whether or not + * a hugepage can be used for affected ranges. + */ + if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) + return false; + + return kvm_unmap_gfn_range(kvm, range); +} + +static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG; +} + +static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, int level, unsigned long attrs) +{ + const unsigned long start = gfn; + const unsigned long end = start + KVM_PAGES_PER_HPAGE(level); + + if (level == PG_LEVEL_2M) + return kvm_range_has_memory_attributes(kvm, start, end, attrs); + + for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) { + if (hugepage_test_mixed(slot, gfn, level - 1) || + attrs != kvm_get_memory_attributes(kvm, gfn)) + return false; + } + return true; +} + +bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range) +{ + unsigned long attrs = range->arg.attributes; + struct kvm_memory_slot *slot = range->slot; + int level; + + lockdep_assert_held_write(&kvm->mmu_lock); + lockdep_assert_held(&kvm->slots_lock); + + /* + * Calculate which ranges can be mapped with hugepages even if the slot + * can't map memory PRIVATE. KVM mustn't create a SHARED hugepage over + * a range that has PRIVATE GFNs, and conversely converting a range to + * SHARED may now allow hugepages. + */ + if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) + return false; + + /* + * The sequence matters here: upper levels consume the result of lower + * level's scanning. + */ + for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { + gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); + gfn_t gfn = gfn_round_for_level(range->start, level); + + /* Process the head page if it straddles the range. */ + if (gfn != range->start || gfn + nr_pages > range->end) { + /* + * Skip mixed tracking if the aligned gfn isn't covered + * by the memslot, KVM can't use a hugepage due to the + * misaligned address regardless of memory attributes. + */ + if (gfn >= slot->base_gfn) { + if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) + hugepage_clear_mixed(slot, gfn, level); + else + hugepage_set_mixed(slot, gfn, level); + } + gfn += nr_pages; + } + + /* + * Pages entirely covered by the range are guaranteed to have + * only the attributes which were just set. + */ + for ( ; gfn + nr_pages <= range->end; gfn += nr_pages) + hugepage_clear_mixed(slot, gfn, level); + + /* + * Process the last tail page if it straddles the range and is + * contained by the memslot. Like the head page, KVM can't + * create a hugepage if the slot size is misaligned. + */ + if (gfn < range->end && + (gfn + nr_pages) <= (slot->base_gfn + slot->npages)) { + if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) + hugepage_clear_mixed(slot, gfn, level); + else + hugepage_set_mixed(slot, gfn, level); + } + } + return false; +} + +void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + int level; + + if (!kvm_arch_has_private_mem(kvm)) + return; + + for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { + /* + * Don't bother tracking mixed attributes for pages that can't + * be huge due to alignment, i.e. process only pages that are + * entirely contained by the memslot. + */ + gfn_t end = gfn_round_for_level(slot->base_gfn + slot->npages, level); + gfn_t start = gfn_round_for_level(slot->base_gfn, level); + gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); + gfn_t gfn; + + if (start < slot->base_gfn) + start += nr_pages; + + /* + * Unlike setting attributes, every potential hugepage needs to + * be manually checked as the attributes may already be mixed. + */ + for (gfn = start; gfn < end; gfn += nr_pages) { + unsigned long attrs = kvm_get_memory_attributes(kvm, gfn); + + if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) + hugepage_clear_mixed(slot, gfn, level); + else + hugepage_set_mixed(slot, gfn, level); + } + } +} +#endif diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index d39af5639ce9..0669a8a668ca 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -6,21 +6,14 @@ #include <linux/kvm_host.h> #include <asm/kvm_host.h> -#undef MMU_DEBUG - -#ifdef MMU_DEBUG -extern bool dbg; - -#define pgprintk(x...) do { if (dbg) printk(x); } while (0) -#define rmap_printk(fmt, args...) do { if (dbg) printk("%s: " fmt, __func__, ## args); } while (0) -#define MMU_WARN_ON(x) WARN_ON(x) +#ifdef CONFIG_KVM_PROVE_MMU +#define KVM_MMU_WARN_ON(x) WARN_ON_ONCE(x) #else -#define pgprintk(x...) do { } while (0) -#define rmap_printk(x...) do { } while (0) -#define MMU_WARN_ON(x) do { } while (0) +#define KVM_MMU_WARN_ON(x) BUILD_BUG_ON_INVALID(x) #endif /* Page table builder macros common to shadow (host) PTEs and guest PTEs. */ +#define __PT_BASE_ADDR_MASK GENMASK_ULL(51, 12) #define __PT_LEVEL_SHIFT(level, bits_per_level) \ (PAGE_SHIFT + ((level) - 1) * (bits_per_level)) #define __PT_INDEX(address, level, bits_per_level) \ @@ -44,6 +37,16 @@ extern bool dbg; #define INVALID_PAE_ROOT 0 #define IS_VALID_PAE_ROOT(x) (!!(x)) +static inline hpa_t kvm_mmu_get_dummy_root(void) +{ + return my_zero_pfn(0) << PAGE_SHIFT; +} + +static inline bool kvm_mmu_is_dummy_root(hpa_t shadow_page) +{ + return is_zero_pfn(shadow_page >> PAGE_SHIFT); +} + typedef u64 __rcu *tdp_ptep_t; struct kvm_mmu_page { @@ -56,7 +59,12 @@ struct kvm_mmu_page { bool tdp_mmu_page; bool unsync; - u8 mmu_valid_gen; + union { + u8 mmu_valid_gen; + + /* Only accessed under slots_lock. */ + bool tdp_mmu_scheduled_root_to_zap; + }; /* * The shadow page can't be replaced by an equivalent huge page @@ -98,13 +106,7 @@ struct kvm_mmu_page { struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ tdp_ptep_t ptep; }; - union { - DECLARE_BITMAP(unsync_child_bitmap, 512); - struct { - struct work_struct tdp_mmu_async_work; - void *tdp_mmu_async_data; - }; - }; + DECLARE_BITMAP(unsync_child_bitmap, 512); /* * Tracks shadow pages that, if zapped, would allow KVM to create an NX @@ -170,9 +172,6 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn, int min_level); -void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn, - gfn_t nr_pages); - /* Flush the given page (huge or not) of guest memory. */ static inline void kvm_flush_remote_tlbs_gfn(struct kvm *kvm, gfn_t gfn, int level) { @@ -203,6 +202,7 @@ struct kvm_page_fault { /* Derived from mmu and global state. */ const bool is_tdp; + const bool is_private; const bool nx_huge_page_workaround_enabled; /* @@ -298,6 +298,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, .max_level = KVM_MAX_HUGEPAGE_LEVEL, .req_level = PG_LEVEL_4K, .goal_level = PG_LEVEL_4K, + .is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT), }; int r; diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 0a2ac438d647..c87da11f3a04 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -12,13 +12,13 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/lockdep.h> #include <linux/kvm_host.h> #include <linux/rculist.h> -#include <asm/kvm_page_track.h> - #include "mmu.h" #include "mmu_internal.h" +#include "page_track.h" bool kvm_page_track_write_tracking_enabled(struct kvm *kvm) { @@ -28,103 +28,64 @@ bool kvm_page_track_write_tracking_enabled(struct kvm *kvm) void kvm_page_track_free_memslot(struct kvm_memory_slot *slot) { - int i; - - for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) { - kvfree(slot->arch.gfn_track[i]); - slot->arch.gfn_track[i] = NULL; - } + kvfree(slot->arch.gfn_write_track); + slot->arch.gfn_write_track = NULL; } -int kvm_page_track_create_memslot(struct kvm *kvm, - struct kvm_memory_slot *slot, - unsigned long npages) +static int __kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot, + unsigned long npages) { - int i; - - for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) { - if (i == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(kvm)) - continue; - - slot->arch.gfn_track[i] = - __vcalloc(npages, sizeof(*slot->arch.gfn_track[i]), - GFP_KERNEL_ACCOUNT); - if (!slot->arch.gfn_track[i]) - goto track_free; - } + const size_t size = sizeof(*slot->arch.gfn_write_track); - return 0; + if (!slot->arch.gfn_write_track) + slot->arch.gfn_write_track = __vcalloc(npages, size, + GFP_KERNEL_ACCOUNT); -track_free: - kvm_page_track_free_memslot(slot); - return -ENOMEM; + return slot->arch.gfn_write_track ? 0 : -ENOMEM; } -static inline bool page_track_mode_is_valid(enum kvm_page_track_mode mode) +int kvm_page_track_create_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot, + unsigned long npages) { - if (mode < 0 || mode >= KVM_PAGE_TRACK_MAX) - return false; + if (!kvm_page_track_write_tracking_enabled(kvm)) + return 0; - return true; + return __kvm_page_track_write_tracking_alloc(slot, npages); } int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot) { - unsigned short *gfn_track; - - if (slot->arch.gfn_track[KVM_PAGE_TRACK_WRITE]) - return 0; - - gfn_track = __vcalloc(slot->npages, sizeof(*gfn_track), - GFP_KERNEL_ACCOUNT); - if (gfn_track == NULL) - return -ENOMEM; - - slot->arch.gfn_track[KVM_PAGE_TRACK_WRITE] = gfn_track; - return 0; + return __kvm_page_track_write_tracking_alloc(slot, slot->npages); } -static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode, short count) +static void update_gfn_write_track(struct kvm_memory_slot *slot, gfn_t gfn, + short count) { int index, val; index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K); - val = slot->arch.gfn_track[mode][index]; + val = slot->arch.gfn_write_track[index]; - if (WARN_ON(val + count < 0 || val + count > USHRT_MAX)) + if (WARN_ON_ONCE(val + count < 0 || val + count > USHRT_MAX)) return; - slot->arch.gfn_track[mode][index] += count; + slot->arch.gfn_write_track[index] += count; } -/* - * add guest page to the tracking pool so that corresponding access on that - * page will be intercepted. - * - * It should be called under the protection both of mmu-lock and kvm->srcu - * or kvm->slots_lock. - * - * @kvm: the guest instance we are interested in. - * @slot: the @gfn belongs to. - * @gfn: the guest page. - * @mode: tracking mode, currently only write track is supported. - */ -void kvm_slot_page_track_add_page(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode) +void __kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn) { + lockdep_assert_held_write(&kvm->mmu_lock); - if (WARN_ON(!page_track_mode_is_valid(mode))) - return; + lockdep_assert_once(lockdep_is_held(&kvm->slots_lock) || + srcu_read_lock_held(&kvm->srcu)); - if (WARN_ON(mode == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(kvm))) + if (KVM_BUG_ON(!kvm_page_track_write_tracking_enabled(kvm), kvm)) return; - update_gfn_track(slot, gfn, mode, 1); + update_gfn_write_track(slot, gfn, 1); /* * new track stops large page mapping for the @@ -132,37 +93,22 @@ void kvm_slot_page_track_add_page(struct kvm *kvm, */ kvm_mmu_gfn_disallow_lpage(slot, gfn); - if (mode == KVM_PAGE_TRACK_WRITE) - if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K)) - kvm_flush_remote_tlbs(kvm); + if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K)) + kvm_flush_remote_tlbs(kvm); } -EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page); -/* - * remove the guest page from the tracking pool which stops the interception - * of corresponding access on that page. It is the opposed operation of - * kvm_slot_page_track_add_page(). - * - * It should be called under the protection both of mmu-lock and kvm->srcu - * or kvm->slots_lock. - * - * @kvm: the guest instance we are interested in. - * @slot: the @gfn belongs to. - * @gfn: the guest page. - * @mode: tracking mode, currently only write track is supported. - */ -void kvm_slot_page_track_remove_page(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode) +void __kvm_write_track_remove_gfn(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn) { - if (WARN_ON(!page_track_mode_is_valid(mode))) - return; + lockdep_assert_held_write(&kvm->mmu_lock); - if (WARN_ON(mode == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(kvm))) + lockdep_assert_once(lockdep_is_held(&kvm->slots_lock) || + srcu_read_lock_held(&kvm->srcu)); + + if (KVM_BUG_ON(!kvm_page_track_write_tracking_enabled(kvm), kvm)) return; - update_gfn_track(slot, gfn, mode, -1); + update_gfn_write_track(slot, gfn, -1); /* * allow large page mapping for the tracked page @@ -170,31 +116,26 @@ void kvm_slot_page_track_remove_page(struct kvm *kvm, */ kvm_mmu_gfn_allow_lpage(slot, gfn); } -EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page); /* * check if the corresponding access on the specified guest page is tracked. */ -bool kvm_slot_page_track_is_active(struct kvm *kvm, - const struct kvm_memory_slot *slot, - gfn_t gfn, enum kvm_page_track_mode mode) +bool kvm_gfn_is_write_tracked(struct kvm *kvm, + const struct kvm_memory_slot *slot, gfn_t gfn) { int index; - if (WARN_ON(!page_track_mode_is_valid(mode))) - return false; - if (!slot) return false; - if (mode == KVM_PAGE_TRACK_WRITE && - !kvm_page_track_write_tracking_enabled(kvm)) + if (!kvm_page_track_write_tracking_enabled(kvm)) return false; index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K); - return !!READ_ONCE(slot->arch.gfn_track[mode][index]); + return !!READ_ONCE(slot->arch.gfn_write_track[index]); } +#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING void kvm_page_track_cleanup(struct kvm *kvm) { struct kvm_page_track_notifier_head *head; @@ -216,17 +157,22 @@ int kvm_page_track_init(struct kvm *kvm) * register the notifier so that event interception for the tracked guest * pages can be received. */ -void -kvm_page_track_register_notifier(struct kvm *kvm, - struct kvm_page_track_notifier_node *n) +int kvm_page_track_register_notifier(struct kvm *kvm, + struct kvm_page_track_notifier_node *n) { struct kvm_page_track_notifier_head *head; + if (!kvm || kvm->mm != current->mm) + return -ESRCH; + + kvm_get_kvm(kvm); + head = &kvm->arch.track_notifier_head; write_lock(&kvm->mmu_lock); hlist_add_head_rcu(&n->node, &head->track_notifier_list); write_unlock(&kvm->mmu_lock); + return 0; } EXPORT_SYMBOL_GPL(kvm_page_track_register_notifier); @@ -234,9 +180,8 @@ EXPORT_SYMBOL_GPL(kvm_page_track_register_notifier); * stop receiving the event interception. It is the opposed operation of * kvm_page_track_register_notifier(). */ -void -kvm_page_track_unregister_notifier(struct kvm *kvm, - struct kvm_page_track_notifier_node *n) +void kvm_page_track_unregister_notifier(struct kvm *kvm, + struct kvm_page_track_notifier_node *n) { struct kvm_page_track_notifier_head *head; @@ -246,6 +191,8 @@ kvm_page_track_unregister_notifier(struct kvm *kvm, hlist_del_rcu(&n->node); write_unlock(&kvm->mmu_lock); synchronize_srcu(&head->track_srcu); + + kvm_put_kvm(kvm); } EXPORT_SYMBOL_GPL(kvm_page_track_unregister_notifier); @@ -256,34 +203,30 @@ EXPORT_SYMBOL_GPL(kvm_page_track_unregister_notifier); * The node should figure out if the written page is the one that node is * interested in by itself. */ -void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, - int bytes) +void __kvm_page_track_write(struct kvm *kvm, gpa_t gpa, const u8 *new, int bytes) { struct kvm_page_track_notifier_head *head; struct kvm_page_track_notifier_node *n; int idx; - head = &vcpu->kvm->arch.track_notifier_head; + head = &kvm->arch.track_notifier_head; if (hlist_empty(&head->track_notifier_list)) return; idx = srcu_read_lock(&head->track_srcu); hlist_for_each_entry_srcu(n, &head->track_notifier_list, node, - srcu_read_lock_held(&head->track_srcu)) + srcu_read_lock_held(&head->track_srcu)) if (n->track_write) - n->track_write(vcpu, gpa, new, bytes, n); + n->track_write(gpa, new, bytes, n); srcu_read_unlock(&head->track_srcu, idx); } /* - * Notify the node that memory slot is being removed or moved so that it can - * drop write-protection for the pages in the memory slot. - * - * The node should figure out it has any write-protected pages in this slot - * by itself. + * Notify external page track nodes that a memory region is being removed from + * the VM, e.g. so that users can free any associated metadata. */ -void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot) +void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot) { struct kvm_page_track_notifier_head *head; struct kvm_page_track_notifier_node *n; @@ -296,8 +239,69 @@ void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot) idx = srcu_read_lock(&head->track_srcu); hlist_for_each_entry_srcu(n, &head->track_notifier_list, node, - srcu_read_lock_held(&head->track_srcu)) - if (n->track_flush_slot) - n->track_flush_slot(kvm, slot, n); + srcu_read_lock_held(&head->track_srcu)) + if (n->track_remove_region) + n->track_remove_region(slot->base_gfn, slot->npages, n); srcu_read_unlock(&head->track_srcu, idx); } + +/* + * add guest page to the tracking pool so that corresponding access on that + * page will be intercepted. + * + * @kvm: the guest instance we are interested in. + * @gfn: the guest page. + */ +int kvm_write_track_add_gfn(struct kvm *kvm, gfn_t gfn) +{ + struct kvm_memory_slot *slot; + int idx; + + idx = srcu_read_lock(&kvm->srcu); + + slot = gfn_to_memslot(kvm, gfn); + if (!slot) { + srcu_read_unlock(&kvm->srcu, idx); + return -EINVAL; + } + + write_lock(&kvm->mmu_lock); + __kvm_write_track_add_gfn(kvm, slot, gfn); + write_unlock(&kvm->mmu_lock); + + srcu_read_unlock(&kvm->srcu, idx); + + return 0; +} +EXPORT_SYMBOL_GPL(kvm_write_track_add_gfn); + +/* + * remove the guest page from the tracking pool which stops the interception + * of corresponding access on that page. + * + * @kvm: the guest instance we are interested in. + * @gfn: the guest page. + */ +int kvm_write_track_remove_gfn(struct kvm *kvm, gfn_t gfn) +{ + struct kvm_memory_slot *slot; + int idx; + + idx = srcu_read_lock(&kvm->srcu); + + slot = gfn_to_memslot(kvm, gfn); + if (!slot) { + srcu_read_unlock(&kvm->srcu, idx); + return -EINVAL; + } + + write_lock(&kvm->mmu_lock); + __kvm_write_track_remove_gfn(kvm, slot, gfn); + write_unlock(&kvm->mmu_lock); + + srcu_read_unlock(&kvm->srcu, idx); + + return 0; +} +EXPORT_SYMBOL_GPL(kvm_write_track_remove_gfn); +#endif diff --git a/arch/x86/kvm/mmu/page_track.h b/arch/x86/kvm/mmu/page_track.h new file mode 100644 index 000000000000..d4d72ed999b1 --- /dev/null +++ b/arch/x86/kvm/mmu/page_track.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __KVM_X86_PAGE_TRACK_H +#define __KVM_X86_PAGE_TRACK_H + +#include <linux/kvm_host.h> + +#include <asm/kvm_page_track.h> + + +bool kvm_page_track_write_tracking_enabled(struct kvm *kvm); +int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot); + +void kvm_page_track_free_memslot(struct kvm_memory_slot *slot); +int kvm_page_track_create_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot, + unsigned long npages); + +void __kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn); +void __kvm_write_track_remove_gfn(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn); + +bool kvm_gfn_is_write_tracked(struct kvm *kvm, + const struct kvm_memory_slot *slot, gfn_t gfn); + +#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING +int kvm_page_track_init(struct kvm *kvm); +void kvm_page_track_cleanup(struct kvm *kvm); + +void __kvm_page_track_write(struct kvm *kvm, gpa_t gpa, const u8 *new, int bytes); +void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot); + +static inline bool kvm_page_track_has_external_user(struct kvm *kvm) +{ + return !hlist_empty(&kvm->arch.track_notifier_head.track_notifier_list); +} +#else +static inline int kvm_page_track_init(struct kvm *kvm) { return 0; } +static inline void kvm_page_track_cleanup(struct kvm *kvm) { } + +static inline void __kvm_page_track_write(struct kvm *kvm, gpa_t gpa, + const u8 *new, int bytes) { } +static inline void kvm_page_track_delete_slot(struct kvm *kvm, + struct kvm_memory_slot *slot) { } + +static inline bool kvm_page_track_has_external_user(struct kvm *kvm) { return false; } + +#endif /* CONFIG_KVM_EXTERNAL_WRITE_TRACKING */ + +static inline void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, + const u8 *new, int bytes) +{ + __kvm_page_track_write(vcpu->kvm, gpa, new, bytes); + + kvm_mmu_track_write(vcpu, gpa, new, bytes); +} + +#endif /* __KVM_X86_PAGE_TRACK_H */ diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 0662e0278e70..4d4e98fe4f35 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -62,7 +62,7 @@ #endif /* Common logic, but per-type values. These also need to be undefined. */ -#define PT_BASE_ADDR_MASK ((pt_element_t)(((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))) +#define PT_BASE_ADDR_MASK ((pt_element_t)__PT_BASE_ADDR_MASK) #define PT_LVL_ADDR_MASK(lvl) __PT_LVL_ADDR_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS) #define PT_LVL_OFFSET_MASK(lvl) __PT_LVL_OFFSET_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS) #define PT_INDEX(addr, lvl) __PT_INDEX(addr, lvl, PT_LEVEL_BITS) @@ -338,7 +338,6 @@ retry_walk: } #endif walker->max_level = walker->level; - ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu))); /* * FIXME: on Intel processors, loads of the PDPTE registers for PAE paging @@ -348,9 +347,21 @@ retry_walk: nested_access = (have_ad ? PFERR_WRITE_MASK : 0) | PFERR_USER_MASK; pte_access = ~0; + + /* + * Queue a page fault for injection if this assertion fails, as callers + * assume that walker.fault contains sane info on a walk failure. I.e. + * avoid making the situation worse by inducing even worse badness + * between when the assertion fails and when KVM kicks the vCPU out to + * userspace (because the VM is bugged). + */ + if (KVM_BUG_ON(is_long_mode(vcpu) && !is_pae(vcpu), vcpu->kvm)) + goto error; + ++walker->level; do { + struct kvm_memory_slot *slot; unsigned long host_addr; pt_access = pte_access; @@ -381,7 +392,11 @@ retry_walk: if (unlikely(real_gpa == INVALID_GPA)) return 0; - host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gpa_to_gfn(real_gpa), + slot = kvm_vcpu_gfn_to_memslot(vcpu, gpa_to_gfn(real_gpa)); + if (!kvm_is_visible_memslot(slot)) + goto error; + + host_addr = gfn_to_hva_memslot_prot(slot, gpa_to_gfn(real_gpa), &walker->pte_writable[walker->level - 1]); if (unlikely(kvm_is_error_hva(host_addr))) goto error; @@ -456,9 +471,6 @@ retry_walk: goto retry_walk; } - pgprintk("%s: pte %llx pte_access %x pt_access %x\n", - __func__, (u64)pte, walker->pte_access, - walker->pt_access[walker->level - 1]); return 1; error: @@ -529,8 +541,6 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte)) return false; - pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte); - gfn = gpte_to_gfn(gpte); pte_access = sp->role.access & FNAME(gpte_access)(gpte); FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte); @@ -638,8 +648,19 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, if (FNAME(gpte_changed)(vcpu, gw, top_level)) goto out_gpte_changed; - if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) + if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) + goto out_gpte_changed; + + /* + * Load a new root and retry the faulting instruction in the extremely + * unlikely scenario that the guest root gfn became visible between + * loading a dummy root and handling the resulting page fault, e.g. if + * userspace create a memslot in the interim. + */ + if (unlikely(kvm_mmu_is_dummy_root(vcpu->arch.mmu->root.hpa))) { + kvm_make_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu); goto out_gpte_changed; + } for_each_shadow_entry(vcpu, fault->addr, it) { gfn_t table_gfn; @@ -758,7 +779,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault struct guest_walker walker; int r; - pgprintk("%s: addr %lx err %x\n", __func__, fault->addr, fault->error_code); WARN_ON_ONCE(fault->is_tdp); /* @@ -773,7 +793,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault * The page is not mapped by the guest. Let the guest handle it. */ if (!r) { - pgprintk("%s: guest page fault\n", __func__); if (!fault->prefetch) kvm_inject_emulated_page_fault(vcpu, &walker.fault); @@ -837,7 +856,7 @@ static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp) { int offset = 0; - WARN_ON(sp->role.level != PG_LEVEL_4K); + WARN_ON_ONCE(sp->role.level != PG_LEVEL_4K); if (PTTYPE == 32) offset = sp->role.quadrant << SPTE_LEVEL_BITS; diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index cf2c6426a6fc..4a599130e9c9 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -61,7 +61,7 @@ static u64 generation_mmio_spte_mask(u64 gen) { u64 mask; - WARN_ON(gen & ~MMIO_SPTE_GEN_MASK); + WARN_ON_ONCE(gen & ~MMIO_SPTE_GEN_MASK); mask = (gen << MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_SPTE_GEN_LOW_MASK; mask |= (gen << MMIO_SPTE_GEN_HIGH_SHIFT) & MMIO_SPTE_GEN_HIGH_MASK; @@ -221,8 +221,6 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * shadow pages and unsync'ing pages is not allowed. */ if (mmu_try_to_unsync_pages(vcpu->kvm, slot, gfn, can_unsync, prefetch)) { - pgprintk("%s: found shadow page for %llx, marking ro\n", - __func__, gfn); wrprot = true; pte_access &= ~ACC_WRITE_MASK; spte &= ~(PT_WRITABLE_MASK | shadow_mmu_writable_mask); @@ -242,7 +240,7 @@ out: if ((spte & PT_WRITABLE_MASK) && kvm_slot_dirty_track_enabled(slot)) { /* Enforced by kvm_mmu_hugepage_adjust. */ - WARN_ON(level > PG_LEVEL_4K); + WARN_ON_ONCE(level > PG_LEVEL_4K); mark_page_dirty_in_slot(vcpu->kvm, slot, gfn); } diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 1279db2eab44..a129951c9a88 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -3,6 +3,7 @@ #ifndef KVM_X86_MMU_SPTE_H #define KVM_X86_MMU_SPTE_H +#include "mmu.h" #include "mmu_internal.h" /* @@ -236,6 +237,18 @@ static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep) return to_shadow_page(__pa(sptep)); } +static inline struct kvm_mmu_page *root_to_sp(hpa_t root) +{ + if (kvm_mmu_is_dummy_root(root)) + return NULL; + + /* + * The "root" may be a special root, e.g. a PAE entry, treat it as a + * SPTE to ensure any non-PA bits are dropped. + */ + return spte_to_child_sp(root); +} + static inline bool is_mmio_spte(u64 spte) { return (spte & shadow_mmio_mask) == shadow_mmio_value && @@ -265,13 +278,13 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) static inline bool spte_ad_enabled(u64 spte) { - MMU_WARN_ON(!is_shadow_present_pte(spte)); + KVM_MMU_WARN_ON(!is_shadow_present_pte(spte)); return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_DISABLED; } static inline bool spte_ad_need_write_protect(u64 spte) { - MMU_WARN_ON(!is_shadow_present_pte(spte)); + KVM_MMU_WARN_ON(!is_shadow_present_pte(spte)); /* * This is benign for non-TDP SPTEs as SPTE_TDP_AD_ENABLED is '0', * and non-TDP SPTEs will never set these bits. Optimize for 64-bit @@ -282,13 +295,13 @@ static inline bool spte_ad_need_write_protect(u64 spte) static inline u64 spte_shadow_accessed_mask(u64 spte) { - MMU_WARN_ON(!is_shadow_present_pte(spte)); + KVM_MMU_WARN_ON(!is_shadow_present_pte(spte)); return spte_ad_enabled(spte) ? shadow_accessed_mask : 0; } static inline u64 spte_shadow_dirty_mask(u64 spte) { - MMU_WARN_ON(!is_shadow_present_pte(spte)); + KVM_MMU_WARN_ON(!is_shadow_present_pte(spte)); return spte_ad_enabled(spte) ? shadow_dirty_mask : 0; } diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index d2eb0d4f8710..04c247bfe318 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -39,13 +39,14 @@ void tdp_iter_restart(struct tdp_iter *iter) void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root, int min_level, gfn_t next_last_level_gfn) { - int root_level = root->role.level; - - WARN_ON(root_level < 1); - WARN_ON(root_level > PT64_ROOT_MAX_LEVEL); + if (WARN_ON_ONCE(!root || (root->role.level < 1) || + (root->role.level > PT64_ROOT_MAX_LEVEL))) { + iter->valid = false; + return; + } iter->next_last_level_gfn = next_last_level_gfn; - iter->root_level = root_level; + iter->root_level = root->role.level; iter->min_level = min_level; iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root->spt; iter->as_id = kvm_mmu_page_as_id(root); @@ -145,7 +146,7 @@ static bool try_step_up(struct tdp_iter *iter) * Step to the next SPTE in a pre-order traversal of the paging structure. * To get to the next SPTE, the iterator either steps down towards the goal * GFN, if at a present, non-last-level SPTE, or over to a SPTE mapping a - * highter GFN. + * higher GFN. * * The basic algorithm is as follows: * 1. If the current SPTE is a non-last-level SPTE, step down into the page diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 512163d52194..6ae19b4ee5b1 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -12,18 +12,10 @@ #include <trace/events/kvm.h> /* Initializes the TDP MMU for the VM, if enabled. */ -int kvm_mmu_init_tdp_mmu(struct kvm *kvm) +void kvm_mmu_init_tdp_mmu(struct kvm *kvm) { - struct workqueue_struct *wq; - - wq = alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0); - if (!wq) - return -ENOMEM; - INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots); spin_lock_init(&kvm->arch.tdp_mmu_pages_lock); - kvm->arch.tdp_mmu_zap_wq = wq; - return 1; } /* Arbitrarily returns true so that this may be used in if statements. */ @@ -46,20 +38,15 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) * ultimately frees all roots. */ kvm_tdp_mmu_invalidate_all_roots(kvm); - - /* - * Destroying a workqueue also first flushes the workqueue, i.e. no - * need to invoke kvm_tdp_mmu_zap_invalidated_roots(). - */ - destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); + kvm_tdp_mmu_zap_invalidated_roots(kvm); WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages)); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); /* * Ensure that all the outstanding RCU callbacks to free shadow pages - * can run before the VM is torn down. Work items on tdp_mmu_zap_wq - * can call kvm_tdp_mmu_put_root and create new callbacks. + * can run before the VM is torn down. Putting the last reference to + * zapped roots will create new callbacks. */ rcu_barrier(); } @@ -86,51 +73,8 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head) tdp_mmu_free_sp(sp); } -static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, - bool shared); - -static void tdp_mmu_zap_root_work(struct work_struct *work) +void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root) { - struct kvm_mmu_page *root = container_of(work, struct kvm_mmu_page, - tdp_mmu_async_work); - struct kvm *kvm = root->tdp_mmu_async_data; - - read_lock(&kvm->mmu_lock); - - /* - * A TLB flush is not necessary as KVM performs a local TLB flush when - * allocating a new root (see kvm_mmu_load()), and when migrating vCPU - * to a different pCPU. Note, the local TLB flush on reuse also - * invalidates any paging-structure-cache entries, i.e. TLB entries for - * intermediate paging structures, that may be zapped, as such entries - * are associated with the ASID on both VMX and SVM. - */ - tdp_mmu_zap_root(kvm, root, true); - - /* - * Drop the refcount using kvm_tdp_mmu_put_root() to test its logic for - * avoiding an infinite loop. By design, the root is reachable while - * it's being asynchronously zapped, thus a different task can put its - * last reference, i.e. flowing through kvm_tdp_mmu_put_root() for an - * asynchronously zapped root is unavoidable. - */ - kvm_tdp_mmu_put_root(kvm, root, true); - - read_unlock(&kvm->mmu_lock); -} - -static void tdp_mmu_schedule_zap_root(struct kvm *kvm, struct kvm_mmu_page *root) -{ - root->tdp_mmu_async_data = kvm; - INIT_WORK(&root->tdp_mmu_async_work, tdp_mmu_zap_root_work); - queue_work(kvm->arch.tdp_mmu_zap_wq, &root->tdp_mmu_async_work); -} - -void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, - bool shared) -{ - kvm_lockdep_assert_mmu_lock_held(kvm, shared); - if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) return; @@ -159,10 +103,16 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, */ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, struct kvm_mmu_page *prev_root, - bool shared, bool only_valid) + bool only_valid) { struct kvm_mmu_page *next_root; + /* + * While the roots themselves are RCU-protected, fields such as + * role.invalid are protected by mmu_lock. + */ + lockdep_assert_held(&kvm->mmu_lock); + rcu_read_lock(); if (prev_root) @@ -185,7 +135,7 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, rcu_read_unlock(); if (prev_root) - kvm_tdp_mmu_put_root(kvm, prev_root, shared); + kvm_tdp_mmu_put_root(kvm, prev_root); return next_root; } @@ -197,22 +147,22 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * recent root. (Unless keeping a live reference is desirable.) * * If shared is set, this function is operating under the MMU lock in read - * mode. In the unlikely event that this thread must free a root, the lock - * will be temporarily dropped and reacquired in write mode. + * mode. */ -#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, _only_valid)\ - for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, _only_valid); \ - _root; \ - _root = tdp_mmu_next_root(_kvm, _root, _shared, _only_valid)) \ - if (kvm_lockdep_assert_mmu_lock_held(_kvm, _shared) && \ - kvm_mmu_page_as_id(_root) != _as_id) { \ +#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _only_valid)\ + for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid); \ + ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ + _root = tdp_mmu_next_root(_kvm, _root, _only_valid)) \ + if (kvm_mmu_page_as_id(_root) != _as_id) { \ } else -#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared) \ - __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true) +#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \ + __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, true) -#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \ - __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, false, false) +#define for_each_tdp_mmu_root_yield_safe(_kvm, _root) \ + for (_root = tdp_mmu_next_root(_kvm, NULL, false); \ + ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ + _root = tdp_mmu_next_root(_kvm, _root, false)) /* * Iterate over all TDP MMU roots. Requires that mmu_lock be held for write, @@ -292,7 +242,7 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) * by a memslot update or by the destruction of the VM. Initialize the * refcount to two; one reference for the vCPU, and one reference for * the TDP MMU itself, which is held until the root is invalidated and - * is ultimately put by tdp_mmu_zap_root_work(). + * is ultimately put by kvm_tdp_mmu_zap_invalidated_roots(). */ refcount_set(&root->tdp_mmu_root_count, 2); @@ -325,28 +275,18 @@ static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) * * @kvm: kvm instance * @sp: the page to be removed - * @shared: This operation may not be running under the exclusive use of - * the MMU lock and the operation must synchronize with other - * threads that might be adding or removing pages. */ -static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp, - bool shared) +static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp) { tdp_unaccount_mmu_page(kvm, sp); if (!sp->nx_huge_page_disallowed) return; - if (shared) - spin_lock(&kvm->arch.tdp_mmu_pages_lock); - else - lockdep_assert_held_write(&kvm->mmu_lock); - + spin_lock(&kvm->arch.tdp_mmu_pages_lock); sp->nx_huge_page_disallowed = false; untrack_possible_nx_huge_page(kvm, sp); - - if (shared) - spin_unlock(&kvm->arch.tdp_mmu_pages_lock); + spin_unlock(&kvm->arch.tdp_mmu_pages_lock); } /** @@ -375,7 +315,7 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) trace_kvm_mmu_prepare_zap_page(sp); - tdp_mmu_unlink_sp(kvm, sp, shared); + tdp_mmu_unlink_sp(kvm, sp); for (i = 0; i < SPTE_ENT_PER_PAGE; i++) { tdp_ptep_t sptep = pt + i; @@ -475,9 +415,9 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, bool is_leaf = is_present && is_last_spte(new_spte, level); bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte); - WARN_ON(level > PT64_ROOT_MAX_LEVEL); - WARN_ON(level < PG_LEVEL_4K); - WARN_ON(gfn & (KVM_PAGES_PER_HPAGE(level) - 1)); + WARN_ON_ONCE(level > PT64_ROOT_MAX_LEVEL); + WARN_ON_ONCE(level < PG_LEVEL_4K); + WARN_ON_ONCE(gfn & (KVM_PAGES_PER_HPAGE(level) - 1)); /* * If this warning were to trigger it would indicate that there was a @@ -522,9 +462,9 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, * impact the guest since both the former and current SPTEs * are nonpresent. */ - if (WARN_ON(!is_mmio_spte(old_spte) && - !is_mmio_spte(new_spte) && - !is_removed_spte(new_spte))) + if (WARN_ON_ONCE(!is_mmio_spte(old_spte) && + !is_mmio_spte(new_spte) && + !is_removed_spte(new_spte))) pr_err("Unexpected SPTE change! Nonpresent SPTEs\n" "should not be replaced with another,\n" "different nonpresent SPTE, unless one or both\n" @@ -661,7 +601,7 @@ static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, * should be used. If operating under the MMU lock in write mode, the * use of the removed SPTE should not be necessary. */ - WARN_ON(is_removed_spte(old_spte) || is_removed_spte(new_spte)); + WARN_ON_ONCE(is_removed_spte(old_spte) || is_removed_spte(new_spte)); old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level); @@ -689,7 +629,7 @@ static inline void tdp_mmu_iter_set_spte(struct kvm *kvm, struct tdp_iter *iter, else #define tdp_mmu_for_each_pte(_iter, _mmu, _start, _end) \ - for_each_tdp_pte(_iter, to_shadow_page(_mmu->root.hpa), _start, _end) + for_each_tdp_pte(_iter, root_to_sp(_mmu->root.hpa), _start, _end) /* * Yield if the MMU lock is contended or this thread needs to return control @@ -709,7 +649,7 @@ static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm, struct tdp_iter *iter, bool flush, bool shared) { - WARN_ON(iter->yielded); + WARN_ON_ONCE(iter->yielded); /* Ensure forward progress has been made before yielding. */ if (iter->next_last_level_gfn == iter->yielded_gfn) @@ -728,7 +668,7 @@ static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm, rcu_read_lock(); - WARN_ON(iter->gfn > iter->next_last_level_gfn); + WARN_ON_ONCE(iter->gfn > iter->next_last_level_gfn); iter->yielded = true; } @@ -877,13 +817,13 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, * true if a TLB flush is needed before releasing the MMU lock, i.e. if one or * more SPTEs were zapped since the MMU lock was last acquired. */ -bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, - bool can_yield, bool flush) +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush) { struct kvm_mmu_page *root; - for_each_tdp_mmu_root_yield_safe(kvm, root, as_id) - flush = tdp_mmu_zap_leafs(kvm, root, start, end, can_yield, flush); + lockdep_assert_held_write(&kvm->mmu_lock); + for_each_tdp_mmu_root_yield_safe(kvm, root) + flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush); return flush; } @@ -891,7 +831,6 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, void kvm_tdp_mmu_zap_all(struct kvm *kvm) { struct kvm_mmu_page *root; - int i; /* * Zap all roots, including invalid roots, as all SPTEs must be dropped @@ -905,10 +844,9 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) * is being destroyed or the userspace VMM has exited. In both cases, * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request. */ - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - for_each_tdp_mmu_root_yield_safe(kvm, root, i) - tdp_mmu_zap_root(kvm, root, false); - } + lockdep_assert_held_write(&kvm->mmu_lock); + for_each_tdp_mmu_root_yield_safe(kvm, root) + tdp_mmu_zap_root(kvm, root, false); } /* @@ -917,18 +855,47 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) */ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) { - flush_workqueue(kvm->arch.tdp_mmu_zap_wq); + struct kvm_mmu_page *root; + + read_lock(&kvm->mmu_lock); + + for_each_tdp_mmu_root_yield_safe(kvm, root) { + if (!root->tdp_mmu_scheduled_root_to_zap) + continue; + + root->tdp_mmu_scheduled_root_to_zap = false; + KVM_BUG_ON(!root->role.invalid, kvm); + + /* + * A TLB flush is not necessary as KVM performs a local TLB + * flush when allocating a new root (see kvm_mmu_load()), and + * when migrating a vCPU to a different pCPU. Note, the local + * TLB flush on reuse also invalidates paging-structure-cache + * entries, i.e. TLB entries for intermediate paging structures, + * that may be zapped, as such entries are associated with the + * ASID on both VMX and SVM. + */ + tdp_mmu_zap_root(kvm, root, true); + + /* + * The referenced needs to be put *after* zapping the root, as + * the root must be reachable by mmu_notifiers while it's being + * zapped + */ + kvm_tdp_mmu_put_root(kvm, root); + } + + read_unlock(&kvm->mmu_lock); } /* * Mark each TDP MMU root as invalid to prevent vCPUs from reusing a root that * is about to be zapped, e.g. in response to a memslots update. The actual - * zapping is performed asynchronously. Using a separate workqueue makes it - * easy to ensure that the destruction is performed before the "fast zap" - * completes, without keeping a separate list of invalidated roots; the list is - * effectively the list of work items in the workqueue. + * zapping is done separately so that it happens with mmu_lock with read, + * whereas invalidating roots must be done with mmu_lock held for write (unless + * the VM is being destroyed). * - * Note, the asynchronous worker is gifted the TDP MMU's reference. + * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference. * See kvm_tdp_mmu_get_vcpu_root_hpa(). */ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) @@ -953,19 +920,20 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) /* * As above, mmu_lock isn't held when destroying the VM! There can't * be other references to @kvm, i.e. nothing else can invalidate roots - * or be consuming roots, but walking the list of roots does need to be - * guarded against roots being deleted by the asynchronous zap worker. + * or get/put references to roots. */ - rcu_read_lock(); - - list_for_each_entry_rcu(root, &kvm->arch.tdp_mmu_roots, link) { + list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) { + /* + * Note, invalid roots can outlive a memslot update! Invalid + * roots must be *zapped* before the memslot update completes, + * but a different task can acquire a reference and keep the + * root alive after its been zapped. + */ if (!root->role.invalid) { + root->tdp_mmu_scheduled_root_to_zap = true; root->role.invalid = true; - tdp_mmu_schedule_zap_root(kvm, root); } } - - rcu_read_unlock(); } /* @@ -1146,8 +1114,13 @@ retry: bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool flush) { - return kvm_tdp_mmu_zap_leafs(kvm, range->slot->as_id, range->start, - range->end, range->may_block, flush); + struct kvm_mmu_page *root; + + __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false) + flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end, + range->may_block, flush); + + return flush; } typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter, @@ -1241,7 +1214,7 @@ static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte; /* Huge pages aren't expected to be modified without first being zapped. */ - WARN_ON(pte_huge(range->pte) || range->start + 1 != range->end); + WARN_ON_ONCE(pte_huge(range->arg.pte) || range->start + 1 != range->end); if (iter->level != PG_LEVEL_4K || !is_shadow_present_pte(iter->old_spte)) @@ -1255,9 +1228,9 @@ static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter, */ tdp_mmu_iter_set_spte(kvm, iter, 0); - if (!pte_write(range->pte)) { + if (!pte_write(range->arg.pte)) { new_spte = kvm_mmu_changed_pte_notifier_make_spte(iter->old_spte, - pte_pfn(range->pte)); + pte_pfn(range->arg.pte)); tdp_mmu_iter_set_spte(kvm, iter, new_spte); } @@ -1332,7 +1305,7 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, lockdep_assert_held_read(&kvm->mmu_lock); - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages, min_level); @@ -1364,6 +1337,8 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(struct kvm *kvm, { struct kvm_mmu_page *sp; + kvm_lockdep_assert_mmu_lock_held(kvm, shared); + /* * Since we are allocating while under the MMU lock we have to be * careful about GFP flags. Use GFP_NOWAIT to avoid blocking on direct @@ -1514,11 +1489,10 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm, int r = 0; kvm_lockdep_assert_mmu_lock_held(kvm, shared); - - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, shared) { + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) { r = tdp_mmu_split_huge_pages_root(kvm, root, start, end, target_level, shared); if (r) { - kvm_tdp_mmu_put_root(kvm, root, shared); + kvm_tdp_mmu_put_root(kvm, root); break; } } @@ -1540,16 +1514,17 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - tdp_root_for_each_leaf_pte(iter, root, start, end) { + tdp_root_for_each_pte(iter, root, start, end) { retry: - if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) + if (!is_shadow_present_pte(iter.old_spte) || + !is_last_spte(iter.old_spte, iter.level)) continue; - if (!is_shadow_present_pte(iter.old_spte)) + if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; - MMU_WARN_ON(kvm_ad_enabled() && - spte_ad_need_write_protect(iter.old_spte)); + KVM_MMU_WARN_ON(kvm_ad_enabled() && + spte_ad_need_write_protect(iter.old_spte)); if (!(iter.old_spte & dbit)) continue; @@ -1578,8 +1553,7 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, bool spte_set = false; lockdep_assert_held_read(&kvm->mmu_lock); - - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages); @@ -1600,6 +1574,8 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, shadow_dirty_mask; struct tdp_iter iter; + lockdep_assert_held_write(&kvm->mmu_lock); + rcu_read_lock(); tdp_root_for_each_leaf_pte(iter, root, gfn + __ffs(mask), @@ -1607,8 +1583,8 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, if (!mask) break; - MMU_WARN_ON(kvm_ad_enabled() && - spte_ad_need_write_protect(iter.old_spte)); + KVM_MMU_WARN_ON(kvm_ad_enabled() && + spte_ad_need_write_protect(iter.old_spte)); if (iter.level > PG_LEVEL_4K || !(mask & (1UL << (iter.gfn - gfn)))) @@ -1646,7 +1622,6 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, { struct kvm_mmu_page *root; - lockdep_assert_held_write(&kvm->mmu_lock); for_each_tdp_mmu_root(kvm, root, slot->as_id) clear_dirty_pt_masked(kvm, root, gfn, mask, wrprot); } @@ -1712,8 +1687,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, struct kvm_mmu_page *root; lockdep_assert_held_read(&kvm->mmu_lock); - - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) zap_collapsible_spte_range(kvm, root, slot); } diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 0a63b1afabd3..20d97aa46c49 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -7,7 +7,7 @@ #include "spte.h" -int kvm_mmu_init_tdp_mmu(struct kvm *kvm); +void kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); @@ -17,11 +17,9 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) return refcount_inc_not_zero(&root->tdp_mmu_root_count); } -void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, - bool shared); +void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root); -bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, - gfn_t end, bool can_yield, bool flush); +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush); bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp); void kvm_tdp_mmu_zap_all(struct kvm *kvm); void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm); diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 3eb6e7f47e96..a67c28a56417 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -320,7 +320,7 @@ static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; gfn_t start, end; - if (!tdp_enabled || !kvm_arch_has_noncoherent_dma(vcpu->kvm)) + if (!kvm_mmu_honors_guest_mtrrs(vcpu->kvm)) return; if (!mtrr_is_enabled(mtrr_state) && msr != MSR_MTRRdefType) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index bf653df86112..87cc6c8809ad 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -93,14 +93,6 @@ void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops) #undef __KVM_X86_PMU_OP } -static void kvm_pmi_trigger_fn(struct irq_work *irq_work) -{ - struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work); - struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); - - kvm_pmu_deliver_pmi(vcpu); -} - static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); @@ -124,20 +116,7 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); } - if (!pmc->intr || skip_pmi) - return; - - /* - * Inject PMI. If vcpu was in a guest mode during NMI PMI - * can be ejected on a guest mode re-entry. Otherwise we can't - * be sure that vcpu wasn't executing hlt instruction at the - * time of vmexit and is not going to re-enter guest mode until - * woken up. So we should wake it, but this is impossible from - * NMI context. Do it from irq work instead. - */ - if (in_pmi && !kvm_handling_nmi_from_guest(pmc->vcpu)) - irq_work_queue(&pmc_to_pmu(pmc)->irq_work); - else + if (pmc->intr && !skip_pmi) kvm_make_request(KVM_REQ_PMI, pmc->vcpu); } @@ -148,9 +127,9 @@ static void kvm_perf_overflow(struct perf_event *perf_event, struct kvm_pmc *pmc = perf_event->overflow_handler_context; /* - * Ignore overflow events for counters that are scheduled to be - * reprogrammed, e.g. if a PMI for the previous event races with KVM's - * handling of a related guest WRMSR. + * Ignore asynchronous overflow events for counters that are scheduled + * to be reprogrammed, e.g. if a PMI for the previous event races with + * KVM's handling of a related guest WRMSR. */ if (test_and_set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi)) return; @@ -182,6 +161,15 @@ static u64 pmc_get_pebs_precise_level(struct kvm_pmc *pmc) return 1; } +static u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) +{ + u64 sample_period = (-counter_value) & pmc_bitmask(pmc); + + if (!sample_period) + sample_period = pmc_bitmask(pmc) + 1; + return sample_period; +} + static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, bool exclude_user, bool exclude_kernel, bool intr) @@ -236,17 +224,30 @@ static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, return 0; } -static void pmc_pause_counter(struct kvm_pmc *pmc) +static bool pmc_pause_counter(struct kvm_pmc *pmc) { u64 counter = pmc->counter; - - if (!pmc->perf_event || pmc->is_paused) - return; + u64 prev_counter; /* update counter, reset event value to avoid redundant accumulation */ - counter += perf_event_pause(pmc->perf_event, true); + if (pmc->perf_event && !pmc->is_paused) + counter += perf_event_pause(pmc->perf_event, true); + + /* + * Snapshot the previous counter *after* accumulating state from perf. + * If overflow already happened, hardware (via perf) is responsible for + * generating a PMI. KVM just needs to detect overflow on emulated + * counter events that haven't yet been processed. + */ + prev_counter = counter & pmc_bitmask(pmc); + + counter += pmc->emulated_counter; pmc->counter = counter & pmc_bitmask(pmc); + + pmc->emulated_counter = 0; pmc->is_paused = true; + + return pmc->counter < prev_counter; } static bool pmc_resume_counter(struct kvm_pmc *pmc) @@ -271,6 +272,51 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) return true; } +static void pmc_release_perf_event(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + perf_event_release_kernel(pmc->perf_event); + pmc->perf_event = NULL; + pmc->current_config = 0; + pmc_to_pmu(pmc)->event_count--; + } +} + +static void pmc_stop_counter(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + pmc->counter = pmc_read_counter(pmc); + pmc_release_perf_event(pmc); + } +} + +static void pmc_update_sample_period(struct kvm_pmc *pmc) +{ + if (!pmc->perf_event || pmc->is_paused || + !is_sampling_event(pmc->perf_event)) + return; + + perf_event_period(pmc->perf_event, + get_sample_period(pmc, pmc->counter)); +} + +void pmc_write_counter(struct kvm_pmc *pmc, u64 val) +{ + /* + * Drop any unconsumed accumulated counts, the WRMSR is a write, not a + * read-modify-write. Adjust the counter value so that its value is + * relative to the current count, as reading the current count from + * perf is faster than pausing and repgrogramming the event in order to + * reset it to '0'. Note, this very sneakily offsets the accumulated + * emulated count too, by using pmc_read_counter()! + */ + pmc->emulated_counter = 0; + pmc->counter += val - pmc_read_counter(pmc); + pmc->counter &= pmc_bitmask(pmc); + pmc_update_sample_period(pmc); +} +EXPORT_SYMBOL_GPL(pmc_write_counter); + static int filter_cmp(const void *pa, const void *pb, u64 mask) { u64 a = *(u64 *)pa & mask; @@ -382,9 +428,6 @@ static bool check_pmu_event_filter(struct kvm_pmc *pmc) struct kvm_x86_pmu_event_filter *filter; struct kvm *kvm = pmc->vcpu->kvm; - if (!static_call(kvm_x86_pmu_hw_event_available)(pmc)) - return false; - filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu); if (!filter) return true; @@ -398,6 +441,7 @@ static bool check_pmu_event_filter(struct kvm_pmc *pmc) static bool pmc_event_is_allowed(struct kvm_pmc *pmc) { return pmc_is_globally_enabled(pmc) && pmc_speculative_in_use(pmc) && + static_call(kvm_x86_pmu_hw_event_available)(pmc) && check_pmu_event_filter(pmc); } @@ -406,14 +450,15 @@ static void reprogram_counter(struct kvm_pmc *pmc) struct kvm_pmu *pmu = pmc_to_pmu(pmc); u64 eventsel = pmc->eventsel; u64 new_config = eventsel; + bool emulate_overflow; u8 fixed_ctr_ctrl; - pmc_pause_counter(pmc); + emulate_overflow = pmc_pause_counter(pmc); if (!pmc_event_is_allowed(pmc)) goto reprogram_complete; - if (pmc->counter < pmc->prev_counter) + if (emulate_overflow) __kvm_perf_overflow(pmc, false); if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL) @@ -453,7 +498,6 @@ static void reprogram_counter(struct kvm_pmc *pmc) reprogram_complete: clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi); - pmc->prev_counter = 0; } void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) @@ -662,36 +706,60 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 0; } -/* refresh PMU settings. This function generally is called when underlying - * settings are changed (such as changes of PMU CPUID by guest VMs), which - * should rarely happen. +static void kvm_pmu_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + int i; + + pmu->need_cleanup = false; + + bitmap_zero(pmu->reprogram_pmi, X86_PMC_IDX_MAX); + + for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) { + pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i); + if (!pmc) + continue; + + pmc_stop_counter(pmc); + pmc->counter = 0; + pmc->emulated_counter = 0; + + if (pmc_is_gp(pmc)) + pmc->eventsel = 0; + } + + pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0; + + static_call_cond(kvm_x86_pmu_reset)(vcpu); +} + + +/* + * Refresh the PMU configuration for the vCPU, e.g. if userspace changes CPUID + * and/or PERF_CAPABILITIES. */ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) { if (KVM_BUG_ON(kvm_vcpu_has_run(vcpu), vcpu->kvm)) return; + /* + * Stop/release all existing counters/events before realizing the new + * vPMU model. + */ + kvm_pmu_reset(vcpu); + bitmap_zero(vcpu_to_pmu(vcpu)->all_valid_pmc_idx, X86_PMC_IDX_MAX); static_call(kvm_x86_pmu_refresh)(vcpu); } -void kvm_pmu_reset(struct kvm_vcpu *vcpu) -{ - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - - irq_work_sync(&pmu->irq_work); - static_call(kvm_x86_pmu_reset)(vcpu); -} - void kvm_pmu_init(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); memset(pmu, 0, sizeof(*pmu)); static_call(kvm_x86_pmu_init)(vcpu); - init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); - pmu->event_count = 0; - pmu->need_cleanup = false; kvm_pmu_refresh(vcpu); } @@ -727,8 +795,7 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu) static void kvm_pmu_incr_counter(struct kvm_pmc *pmc) { - pmc->prev_counter = pmc->counter; - pmc->counter = (pmc->counter + 1) & pmc_bitmask(pmc); + pmc->emulated_counter++; kvm_pmu_request_counter_reprogram(pmc); } diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 7d9ba301c090..7caeb3d8d4fd 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -66,7 +66,8 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc) { u64 counter, enabled, running; - counter = pmc->counter; + counter = pmc->counter + pmc->emulated_counter; + if (pmc->perf_event && !pmc->is_paused) counter += perf_event_read_value(pmc->perf_event, &enabled, &running); @@ -74,23 +75,7 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc) return counter & pmc_bitmask(pmc); } -static inline void pmc_release_perf_event(struct kvm_pmc *pmc) -{ - if (pmc->perf_event) { - perf_event_release_kernel(pmc->perf_event); - pmc->perf_event = NULL; - pmc->current_config = 0; - pmc_to_pmu(pmc)->event_count--; - } -} - -static inline void pmc_stop_counter(struct kvm_pmc *pmc) -{ - if (pmc->perf_event) { - pmc->counter = pmc_read_counter(pmc); - pmc_release_perf_event(pmc); - } -} +void pmc_write_counter(struct kvm_pmc *pmc, u64 val); static inline bool pmc_is_gp(struct kvm_pmc *pmc) { @@ -140,25 +125,6 @@ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) return NULL; } -static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) -{ - u64 sample_period = (-counter_value) & pmc_bitmask(pmc); - - if (!sample_period) - sample_period = pmc_bitmask(pmc) + 1; - return sample_period; -} - -static inline void pmc_update_sample_period(struct kvm_pmc *pmc) -{ - if (!pmc->perf_event || pmc->is_paused || - !is_sampling_event(pmc->perf_event)) - return; - - perf_event_period(pmc->perf_event, - get_sample_period(pmc, pmc->counter)); -} - static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); @@ -255,7 +221,6 @@ bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); void kvm_pmu_refresh(struct kvm_vcpu *vcpu); -void kvm_pmu_reset(struct kvm_vcpu *vcpu); void kvm_pmu_init(struct kvm_vcpu *vcpu); void kvm_pmu_cleanup(struct kvm_vcpu *vcpu); void kvm_pmu_destroy(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index 56cbdb24400a..aadefcaa9561 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -16,6 +16,7 @@ enum kvm_only_cpuid_leafs { CPUID_7_1_EDX, CPUID_8000_0007_EDX, CPUID_8000_0022_EAX, + CPUID_7_2_EDX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, @@ -43,8 +44,17 @@ enum kvm_only_cpuid_leafs { /* Intel-defined sub-features, CPUID level 0x00000007:1 (EDX) */ #define X86_FEATURE_AVX_VNNI_INT8 KVM_X86_FEATURE(CPUID_7_1_EDX, 4) #define X86_FEATURE_AVX_NE_CONVERT KVM_X86_FEATURE(CPUID_7_1_EDX, 5) +#define X86_FEATURE_AMX_COMPLEX KVM_X86_FEATURE(CPUID_7_1_EDX, 8) #define X86_FEATURE_PREFETCHITI KVM_X86_FEATURE(CPUID_7_1_EDX, 14) +/* Intel-defined sub-features, CPUID level 0x00000007:2 (EDX) */ +#define X86_FEATURE_INTEL_PSFD KVM_X86_FEATURE(CPUID_7_2_EDX, 0) +#define X86_FEATURE_IPRED_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 1) +#define KVM_X86_FEATURE_RRSBA_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 2) +#define X86_FEATURE_DDPD_U KVM_X86_FEATURE(CPUID_7_2_EDX, 3) +#define X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) +#define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5) + /* CPUID level 0x80000007 (EDX). */ #define KVM_X86_FEATURE_CONSTANT_TSC KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8) @@ -79,6 +89,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_0007_EDX] = {0x80000007, 0, CPUID_EDX}, [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, [CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX}, + [CPUID_7_2_EDX] = { 7, 2, CPUID_EDX}, }; /* @@ -105,18 +116,19 @@ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) */ static __always_inline u32 __feature_translate(int x86_feature) { - if (x86_feature == X86_FEATURE_SGX1) - return KVM_X86_FEATURE_SGX1; - else if (x86_feature == X86_FEATURE_SGX2) - return KVM_X86_FEATURE_SGX2; - else if (x86_feature == X86_FEATURE_SGX_EDECCSSA) - return KVM_X86_FEATURE_SGX_EDECCSSA; - else if (x86_feature == X86_FEATURE_CONSTANT_TSC) - return KVM_X86_FEATURE_CONSTANT_TSC; - else if (x86_feature == X86_FEATURE_PERFMON_V2) - return KVM_X86_FEATURE_PERFMON_V2; - - return x86_feature; +#define KVM_X86_TRANSLATE_FEATURE(f) \ + case X86_FEATURE_##f: return KVM_X86_FEATURE_##f + + switch (x86_feature) { + KVM_X86_TRANSLATE_FEATURE(SGX1); + KVM_X86_TRANSLATE_FEATURE(SGX2); + KVM_X86_TRANSLATE_FEATURE(SGX_EDECCSSA); + KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC); + KVM_X86_TRANSLATE_FEATURE(PERFMON_V2); + KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL); + default: + return x86_feature; + } } static __always_inline u32 __feature_leaf(int x86_feature) diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index b42111a24cc2..dc3d95fdca7d 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -324,7 +324,6 @@ void enter_smm(struct kvm_vcpu *vcpu) cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG); static_call(kvm_x86_set_cr0)(vcpu, cr0); - vcpu->arch.cr0 = cr0; static_call(kvm_x86_set_cr4)(vcpu, 0); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index cfc8ab773025..4b74ea91f4e6 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -529,8 +529,11 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: WARN_ONCE(1, "Invalid backing page\n"); break; + case AVIC_IPI_FAILURE_INVALID_IPI_VECTOR: + /* Invalid IPI with vector < 16 */ + break; default: - pr_err("Unknown IPI interception\n"); + vcpu_unimpl(vcpu, "Unknown avic incomplete IPI interception\n"); } return 1; @@ -791,6 +794,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) int ret = 0; unsigned long flags; struct amd_svm_iommu_ir *ir; + u64 entry; /** * In some cases, the existing irte is updated and re-set, @@ -824,6 +828,18 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) ir->data = pi->ir_data; spin_lock_irqsave(&svm->ir_list_lock, flags); + + /* + * Update the target pCPU for IOMMU doorbells if the vCPU is running. + * If the vCPU is NOT running, i.e. is blocking or scheduled out, KVM + * will update the pCPU info when the vCPU awkened and/or scheduled in. + * See also avic_vcpu_load(). + */ + entry = READ_ONCE(*(svm->avic_physical_id_cache)); + if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK) + amd_iommu_update_ga(entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK, + true, pi->ir_data); + list_add(&ir->node, &svm->ir_list); spin_unlock_irqrestore(&svm->ir_list_lock, flags); out: @@ -986,10 +1002,11 @@ static inline int avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) { int ret = 0; - unsigned long flags; struct amd_svm_iommu_ir *ir; struct vcpu_svm *svm = to_svm(vcpu); + lockdep_assert_held(&svm->ir_list_lock); + if (!kvm_arch_has_assigned_device(vcpu->kvm)) return 0; @@ -997,19 +1014,15 @@ avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) * Here, we go through the per-vcpu ir_list to update all existing * interrupt remapping table entry targeting this vcpu. */ - spin_lock_irqsave(&svm->ir_list_lock, flags); - if (list_empty(&svm->ir_list)) - goto out; + return 0; list_for_each_entry(ir, &svm->ir_list, node) { ret = amd_iommu_update_ga(cpu, r, ir->data); if (ret) - break; + return ret; } -out: - spin_unlock_irqrestore(&svm->ir_list_lock, flags); - return ret; + return 0; } void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -1017,6 +1030,7 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) u64 entry; int h_physical_id = kvm_cpu_get_apicid(cpu); struct vcpu_svm *svm = to_svm(vcpu); + unsigned long flags; lockdep_assert_preemption_disabled(); @@ -1033,6 +1047,15 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (kvm_vcpu_is_blocking(vcpu)) return; + /* + * Grab the per-vCPU interrupt remapping lock even if the VM doesn't + * _currently_ have assigned devices, as that can change. Holding + * ir_list_lock ensures that either svm_ir_list_add() will consume + * up-to-date entry information, or that this task will wait until + * svm_ir_list_add() completes to set the new target pCPU. + */ + spin_lock_irqsave(&svm->ir_list_lock, flags); + entry = READ_ONCE(*(svm->avic_physical_id_cache)); WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK); @@ -1042,25 +1065,48 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) WRITE_ONCE(*(svm->avic_physical_id_cache), entry); avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true); + + spin_unlock_irqrestore(&svm->ir_list_lock, flags); } void avic_vcpu_put(struct kvm_vcpu *vcpu) { u64 entry; struct vcpu_svm *svm = to_svm(vcpu); + unsigned long flags; lockdep_assert_preemption_disabled(); + /* + * Note, reading the Physical ID entry outside of ir_list_lock is safe + * as only the pCPU that has loaded (or is loading) the vCPU is allowed + * to modify the entry, and preemption is disabled. I.e. the vCPU + * can't be scheduled out and thus avic_vcpu_{put,load}() can't run + * recursively. + */ entry = READ_ONCE(*(svm->avic_physical_id_cache)); /* Nothing to do if IsRunning == '0' due to vCPU blocking. */ if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)) return; + /* + * Take and hold the per-vCPU interrupt remapping lock while updating + * the Physical ID entry even though the lock doesn't protect against + * multiple writers (see above). Holding ir_list_lock ensures that + * either svm_ir_list_add() will consume up-to-date entry information, + * or that this task will wait until svm_ir_list_add() completes to + * mark the vCPU as not running. + */ + spin_lock_irqsave(&svm->ir_list_lock, flags); + avic_update_iommu_vcpu_affinity(vcpu, -1, 0); entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; WRITE_ONCE(*(svm->avic_physical_id_cache), entry); + + spin_unlock_irqrestore(&svm->ir_list_lock, flags); + } void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/svm/hyperv.h b/arch/x86/kvm/svm/hyperv.h index 02f4784b5d44..d3f8bfc05832 100644 --- a/arch/x86/kvm/svm/hyperv.h +++ b/arch/x86/kvm/svm/hyperv.h @@ -11,6 +11,7 @@ #include "../hyperv.h" #include "svm.h" +#ifdef CONFIG_KVM_HYPERV static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -41,5 +42,13 @@ static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu) } void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); +#else /* CONFIG_KVM_HYPERV */ +static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu) {} +static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu) {} +#endif /* CONFIG_KVM_HYPERV */ #endif /* __ARCH_X86_KVM_SVM_HYPERV_H__ */ diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 96936ddf1b3c..dee62362a360 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -107,7 +107,7 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) static bool nested_vmcb_needs_vls_intercept(struct vcpu_svm *svm) { - if (!svm->v_vmload_vmsave_enabled) + if (!guest_can_use(&svm->vcpu, X86_FEATURE_V_VMSAVE_VMLOAD)) return true; if (!nested_npt_enabled(svm)) @@ -187,7 +187,6 @@ void recalc_intercepts(struct vcpu_svm *svm) */ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) { - struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments; int i; /* @@ -198,11 +197,16 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) * - Nested hypervisor (L1) is using Hyper-V emulation interface and * tells KVM (L0) there were no changes in MSR bitmap for L2. */ - if (!svm->nested.force_msr_bitmap_recalc && - kvm_hv_hypercall_enabled(&svm->vcpu) && - hve->hv_enlightenments_control.msr_bitmap && - (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS))) - goto set_msrpm_base_pa; +#ifdef CONFIG_KVM_HYPERV + if (!svm->nested.force_msr_bitmap_recalc) { + struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments; + + if (kvm_hv_hypercall_enabled(&svm->vcpu) && + hve->hv_enlightenments_control.msr_bitmap && + (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS))) + goto set_msrpm_base_pa; + } +#endif if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) return true; @@ -230,7 +234,9 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) svm->nested.force_msr_bitmap_recalc = false; +#ifdef CONFIG_KVM_HYPERV set_msrpm_base_pa: +#endif svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm)); return true; @@ -247,18 +253,6 @@ static bool nested_svm_check_bitmap_pa(struct kvm_vcpu *vcpu, u64 pa, u32 size) kvm_vcpu_is_legal_gpa(vcpu, addr + size - 1); } -static bool nested_svm_check_tlb_ctl(struct kvm_vcpu *vcpu, u8 tlb_ctl) -{ - /* Nested FLUSHBYASID is not supported yet. */ - switch(tlb_ctl) { - case TLB_CONTROL_DO_NOTHING: - case TLB_CONTROL_FLUSH_ALL_ASID: - return true; - default: - return false; - } -} - static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, struct vmcb_ctrl_area_cached *control) { @@ -278,9 +272,6 @@ static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, IOPM_SIZE))) return false; - if (CC(!nested_svm_check_tlb_ctl(vcpu, control->tlb_ctl))) - return false; - if (CC((control->int_ctl & V_NMI_ENABLE_MASK) && !vmcb12_is_intercept(control, INTERCEPT_NMI))) { return false; @@ -311,7 +302,7 @@ static bool __nested_vmcb_check_save(struct kvm_vcpu *vcpu, if ((save->efer & EFER_LME) && (save->cr0 & X86_CR0_PG)) { if (CC(!(save->cr4 & X86_CR4_PAE)) || CC(!(save->cr0 & X86_CR0_PE)) || - CC(kvm_vcpu_is_illegal_gpa(vcpu, save->cr3))) + CC(!kvm_vcpu_is_legal_cr3(vcpu, save->cr3))) return false; } @@ -378,12 +369,14 @@ void __nested_copy_vmcb_control_to_cache(struct kvm_vcpu *vcpu, to->msrpm_base_pa &= ~0x0fffULL; to->iopm_base_pa &= ~0x0fffULL; +#ifdef CONFIG_KVM_HYPERV /* Hyper-V extensions (Enlightened VMCB) */ if (kvm_hv_hypercall_enabled(vcpu)) { to->clean = from->clean; memcpy(&to->hv_enlightenments, &from->hv_enlightenments, sizeof(to->hv_enlightenments)); } +#endif } void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, @@ -487,14 +480,8 @@ static void nested_save_pending_event_to_vmcb12(struct vcpu_svm *svm, static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu) { - /* - * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or - * L2's VP_ID upon request from the guest. Make sure we check for - * pending entries in the right FIFO upon L1/L2 transition as these - * requests are put by other vCPUs asynchronously. - */ - if (to_hv_vcpu(vcpu) && npt_enabled) - kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu); + /* Handle pending Hyper-V TLB flush requests */ + kvm_hv_nested_transtion_tlb_flush(vcpu, npt_enabled); /* * TODO: optimize unconditional TLB flush/MMU sync. A partial list of @@ -520,7 +507,7 @@ static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu) static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_npt, bool reload_pdptrs) { - if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) + if (CC(!kvm_vcpu_is_legal_cr3(vcpu, cr3))) return -EINVAL; if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) && @@ -552,6 +539,7 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 bool new_vmcb12 = false; struct vmcb *vmcb01 = svm->vmcb01.ptr; struct vmcb *vmcb02 = svm->nested.vmcb02.ptr; + struct kvm_vcpu *vcpu = &svm->vcpu; nested_vmcb02_compute_g_pat(svm); @@ -577,18 +565,18 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 vmcb_mark_dirty(vmcb02, VMCB_DT); } - kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED); + kvm_set_rflags(vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED); - svm_set_efer(&svm->vcpu, svm->nested.save.efer); + svm_set_efer(vcpu, svm->nested.save.efer); - svm_set_cr0(&svm->vcpu, svm->nested.save.cr0); - svm_set_cr4(&svm->vcpu, svm->nested.save.cr4); + svm_set_cr0(vcpu, svm->nested.save.cr0); + svm_set_cr4(vcpu, svm->nested.save.cr4); svm->vcpu.arch.cr2 = vmcb12->save.cr2; - kvm_rax_write(&svm->vcpu, vmcb12->save.rax); - kvm_rsp_write(&svm->vcpu, vmcb12->save.rsp); - kvm_rip_write(&svm->vcpu, vmcb12->save.rip); + kvm_rax_write(vcpu, vmcb12->save.rax); + kvm_rsp_write(vcpu, vmcb12->save.rsp); + kvm_rip_write(vcpu, vmcb12->save.rip); /* In case we don't even reach vcpu_run, the fields are not updated */ vmcb02->save.rax = vmcb12->save.rax; @@ -602,7 +590,8 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 vmcb_mark_dirty(vmcb02, VMCB_DR); } - if (unlikely(svm->lbrv_enabled && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { + if (unlikely(guest_can_use(vcpu, X86_FEATURE_LBRV) && + (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { /* * Reserved bits of DEBUGCTL are ignored. Be consistent with * svm_set_msr's definition of reserved bits. @@ -658,7 +647,8 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, * exit_int_info, exit_int_info_err, next_rip, insn_len, insn_bytes. */ - if (svm->vgif_enabled && (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK)) + if (guest_can_use(vcpu, X86_FEATURE_VGIF) && + (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK)) int_ctl_vmcb12_bits |= (V_GIF_MASK | V_GIF_ENABLE_MASK); else int_ctl_vmcb01_bits |= (V_GIF_MASK | V_GIF_ENABLE_MASK); @@ -695,10 +685,9 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, vmcb02->control.tsc_offset = vcpu->arch.tsc_offset; - if (svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) { - WARN_ON(!svm->tsc_scaling_enabled); + if (guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR) && + svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) nested_svm_update_tsc_ratio_msr(vcpu); - } vmcb02->control.int_ctl = (svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) | @@ -717,7 +706,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, * what a nrips=0 CPU would do (L1 is responsible for advancing RIP * prior to injecting the event). */ - if (svm->nrips_enabled) + if (guest_can_use(vcpu, X86_FEATURE_NRIPS)) vmcb02->control.next_rip = svm->nested.ctl.next_rip; else if (boot_cpu_has(X86_FEATURE_NRIPS)) vmcb02->control.next_rip = vmcb12_rip; @@ -727,7 +716,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, svm->soft_int_injected = true; svm->soft_int_csbase = vmcb12_csbase; svm->soft_int_old_rip = vmcb12_rip; - if (svm->nrips_enabled) + if (guest_can_use(vcpu, X86_FEATURE_NRIPS)) svm->soft_int_next_rip = svm->nested.ctl.next_rip; else svm->soft_int_next_rip = vmcb12_rip; @@ -735,15 +724,21 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, vmcb02->control.virt_ext = vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK; - if (svm->lbrv_enabled) + if (guest_can_use(vcpu, X86_FEATURE_LBRV)) vmcb02->control.virt_ext |= (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK); if (!nested_vmcb_needs_vls_intercept(svm)) vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; - pause_count12 = svm->pause_filter_enabled ? svm->nested.ctl.pause_filter_count : 0; - pause_thresh12 = svm->pause_threshold_enabled ? svm->nested.ctl.pause_filter_thresh : 0; + if (guest_can_use(vcpu, X86_FEATURE_PAUSEFILTER)) + pause_count12 = svm->nested.ctl.pause_filter_count; + else + pause_count12 = 0; + if (guest_can_use(vcpu, X86_FEATURE_PFTHRESHOLD)) + pause_thresh12 = svm->nested.ctl.pause_filter_thresh; + else + pause_thresh12 = 0; if (kvm_pause_in_guest(svm->vcpu.kvm)) { /* use guest values since host doesn't intercept PAUSE */ vmcb02->control.pause_filter_count = pause_count12; @@ -1027,7 +1022,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm) if (vmcb12->control.exit_code != SVM_EXIT_ERR) nested_save_pending_event_to_vmcb12(svm, vmcb12); - if (svm->nrips_enabled) + if (guest_can_use(vcpu, X86_FEATURE_NRIPS)) vmcb12->control.next_rip = vmcb02->control.next_rip; vmcb12->control.int_ctl = svm->nested.ctl.int_ctl; @@ -1066,7 +1061,8 @@ int nested_svm_vmexit(struct vcpu_svm *svm) if (!nested_exit_on_intr(svm)) kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); - if (unlikely(svm->lbrv_enabled && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { + if (unlikely(guest_can_use(vcpu, X86_FEATURE_LBRV) && + (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { svm_copy_lbrs(vmcb12, vmcb02); svm_update_lbrv(vcpu); } else if (unlikely(vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK)) { @@ -1101,10 +1097,10 @@ int nested_svm_vmexit(struct vcpu_svm *svm) vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS); } - if (svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) { - WARN_ON(!svm->tsc_scaling_enabled); + if (kvm_caps.has_tsc_control && + vcpu->arch.tsc_scaling_ratio != vcpu->arch.l1_tsc_scaling_ratio) { vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio; - __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); + svm_write_tsc_multiplier(vcpu); } svm->nested.ctl.nested_cr3 = 0; @@ -1244,6 +1240,9 @@ void svm_leave_nested(struct kvm_vcpu *vcpu) nested_svm_uninit_mmu_context(vcpu); vmcb_mark_all_dirty(svm->vmcb); + + if (kvm_apicv_activated(vcpu->kvm)) + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); } kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); @@ -1537,7 +1536,7 @@ void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu) vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier(vcpu->arch.l1_tsc_scaling_ratio, svm->tsc_ratio_msr); - __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); + svm_write_tsc_multiplier(vcpu); } /* Inverse operation of nested_copy_vmcb_control_to_cache(). asid is copied too. */ diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index cef5a3d0abd0..b6a7ad4d6914 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -160,8 +160,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* MSR_PERFCTRn */ pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); if (pmc) { - pmc->counter += data - pmc_read_counter(pmc); - pmc_update_sample_period(pmc); + pmc_write_counter(pmc, data); return 0; } /* MSR_EVNTSELn */ @@ -233,21 +232,6 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu) } } -static void amd_pmu_reset(struct kvm_vcpu *vcpu) -{ - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - int i; - - for (i = 0; i < KVM_AMD_PMC_MAX_GENERIC; i++) { - struct kvm_pmc *pmc = &pmu->gp_counters[i]; - - pmc_stop_counter(pmc); - pmc->counter = pmc->prev_counter = pmc->eventsel = 0; - } - - pmu->global_ctrl = pmu->global_status = 0; -} - struct kvm_pmu_ops amd_pmu_ops __initdata = { .hw_event_available = amd_hw_event_available, .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, @@ -259,7 +243,6 @@ struct kvm_pmu_ops amd_pmu_ops __initdata = { .set_msr = amd_pmu_set_msr, .refresh = amd_pmu_refresh, .init = amd_pmu_init, - .reset = amd_pmu_reset, .EVENTSEL_EVENT = AMD64_EVENTSEL_EVENT, .MAX_NR_GP_COUNTERS = KVM_AMD_PMC_MAX_GENERIC, .MIN_NR_GP_COUNTERS = AMD64_NUM_COUNTERS, diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index d3aec1f2cad2..f760106c31f8 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -23,6 +23,7 @@ #include <asm/pkru.h> #include <asm/trapnr.h> #include <asm/fpu/xcr.h> +#include <asm/debugreg.h> #include "mmu.h" #include "x86.h" @@ -54,9 +55,14 @@ module_param_named(sev, sev_enabled, bool, 0444); /* enable/disable SEV-ES support */ static bool sev_es_enabled = true; module_param_named(sev_es, sev_es_enabled, bool, 0444); + +/* enable/disable SEV-ES DebugSwap support */ +static bool sev_es_debug_swap_enabled = true; +module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444); #else #define sev_enabled false #define sev_es_enabled false +#define sev_es_debug_swap_enabled false #endif /* CONFIG_KVM_AMD_SEV */ static u8 sev_enc_bit; @@ -606,6 +612,9 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) save->xss = svm->vcpu.arch.ia32_xss; save->dr6 = svm->vcpu.arch.dr6; + if (sev_es_debug_swap_enabled) + save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP; + pr_debug("Virtual Machine Save Area (VMSA):\n"); print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false); @@ -619,6 +628,11 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, struct vcpu_svm *svm = to_svm(vcpu); int ret; + if (vcpu->guest_debug) { + pr_warn_once("KVM_SET_GUEST_DEBUG for SEV-ES guest is not supported"); + return -EINVAL; + } + /* Perform some pre-encryption checks against the VMSA */ ret = sev_es_sync_vmsa(svm); if (ret) @@ -1725,7 +1739,7 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) * Note, the source is not required to have the same number of * vCPUs as the destination when migrating a vanilla SEV VM. */ - src_vcpu = kvm_get_vcpu(dst_kvm, i); + src_vcpu = kvm_get_vcpu(src_kvm, i); src_svm = to_svm(src_vcpu); /* @@ -2171,16 +2185,19 @@ void __init sev_hardware_setup(void) bool sev_es_supported = false; bool sev_supported = false; - if (!sev_enabled || !npt_enabled) + if (!sev_enabled || !npt_enabled || !nrips) goto out; /* * SEV must obviously be supported in hardware. Sanity check that the * CPU supports decode assists, which is mandatory for SEV guests to - * support instruction emulation. + * support instruction emulation. Ditto for flushing by ASID, as SEV + * guests are bound to a single ASID, i.e. KVM can't rotate to a new + * ASID to effect a TLB flush. */ if (!boot_cpu_has(X86_FEATURE_SEV) || - WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS))) + WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS)) || + WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_FLUSHBYASID))) goto out; /* Retrieve SEV CPUID information */ @@ -2256,6 +2273,9 @@ out: sev_enabled = sev_supported; sev_es_enabled = sev_es_supported; + if (!sev_es_enabled || !cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP) || + !cpu_feature_enabled(X86_FEATURE_NO_NESTED_DATA_BP)) + sev_es_debug_swap_enabled = false; #endif } @@ -2881,7 +2901,10 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) svm->sev_es.ghcb_sa); break; case SVM_VMGEXIT_NMI_COMPLETE: - ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_IRET); + ++vcpu->stat.nmi_window_exits; + svm->nmi_masked = false; + kvm_make_request(KVM_REQ_EVENT, vcpu); + ret = 1; break; case SVM_VMGEXIT_AP_HLT_LOOP: ret = kvm_emulate_ap_reset_hold(vcpu); @@ -2942,8 +2965,54 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) count, in); } +static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { + bool v_tsc_aux = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + + set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux); + } + + /* + * For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if + * the host/guest supports its use. + * + * guest_can_use() checks a number of requirements on the host/guest to + * ensure that MSR_IA32_XSS is available, but it might report true even + * if X86_FEATURE_XSAVES isn't configured in the guest to ensure host + * MSR_IA32_XSS is always properly restored. For SEV-ES, it is better + * to further check that the guest CPUID actually supports + * X86_FEATURE_XSAVES so that accesses to MSR_IA32_XSS by misbehaved + * guests will still get intercepted and caught in the normal + * kvm_emulate_rdmsr()/kvm_emulated_wrmsr() paths. + */ + if (guest_can_use(vcpu, X86_FEATURE_XSAVES) && + guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1); + else + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 0, 0); +} + +void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_cpuid_entry2 *best; + + /* For sev guests, the memory encryption bit is not reserved in CR3. */ + best = kvm_find_cpuid_entry(vcpu, 0x8000001F); + if (best) + vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); + + if (sev_es_guest(svm->vcpu.kvm)) + sev_es_vcpu_after_set_cpuid(svm); +} + static void sev_es_init_vmcb(struct vcpu_svm *svm) { + struct vmcb *vmcb = svm->vmcb01.ptr; struct kvm_vcpu *vcpu = &svm->vcpu; svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE; @@ -2952,9 +3021,12 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) /* * An SEV-ES guest requires a VMSA area that is a separate from the * VMCB page. Do not include the encryption mask on the VMSA physical - * address since hardware will access it using the guest key. + * address since hardware will access it using the guest key. Note, + * the VMSA will be NULL if this vCPU is the destination for intrahost + * migration, and will be copied later. */ - svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa); + if (svm->sev_es.vmsa) + svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa); /* Can't intercept CR register access, HV can't modify CR registers */ svm_clr_intercept(svm, INTERCEPT_CR0_READ); @@ -2972,8 +3044,23 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) svm_set_intercept(svm, TRAP_CR4_WRITE); svm_set_intercept(svm, TRAP_CR8_WRITE); - /* No support for enable_vmware_backdoor */ - clr_exception_intercept(svm, GP_VECTOR); + vmcb->control.intercepts[INTERCEPT_DR] = 0; + if (!sev_es_debug_swap_enabled) { + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE); + recalc_intercepts(svm); + } else { + /* + * Disable #DB intercept iff DebugSwap is enabled. KVM doesn't + * allow debugging SEV-ES guests, and enables DebugSwap iff + * NO_NESTED_DATA_BP is supported, so there's no reason to + * intercept #DB when DebugSwap is enabled. For simplicity + * with respect to guest debug, intercept #DB for other VMs + * even if NO_NESTED_DATA_BP is supported, i.e. even if the + * guest can't DoS the CPU with infinite #DB vectoring. + */ + clr_exception_intercept(svm, DB_VECTOR); + } /* Can't intercept XSETBV, HV can't modify XCR0 directly */ svm_clr_intercept(svm, INTERCEPT_XSETBV); @@ -2985,14 +3072,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); - - if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && - (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDPID))) { - set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, 1, 1); - if (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP)) - svm_clr_intercept(svm, INTERCEPT_RDTSCP); - } } void sev_init_vmcb(struct vcpu_svm *svm) @@ -3000,6 +3079,12 @@ void sev_init_vmcb(struct vcpu_svm *svm) svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE; clr_exception_intercept(svm, UD_VECTOR); + /* + * Don't intercept #GP for SEV guests, e.g. for the VMware backdoor, as + * KVM can't decrypt guest memory to decode the faulting instruction. + */ + clr_exception_intercept(svm, GP_VECTOR); + if (sev_es_guest(svm->vcpu.kvm)) sev_es_init_vmcb(svm); } @@ -3018,20 +3103,41 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm) void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) { /* - * As an SEV-ES guest, hardware will restore the host state on VMEXIT, - * of which one step is to perform a VMLOAD. KVM performs the - * corresponding VMSAVE in svm_prepare_guest_switch for both - * traditional and SEV-ES guests. + * All host state for SEV-ES guests is categorized into three swap types + * based on how it is handled by hardware during a world switch: + * + * A: VMRUN: Host state saved in host save area + * VMEXIT: Host state loaded from host save area + * + * B: VMRUN: Host state _NOT_ saved in host save area + * VMEXIT: Host state loaded from host save area + * + * C: VMRUN: Host state _NOT_ saved in host save area + * VMEXIT: Host state initialized to default(reset) values + * + * Manually save type-B state, i.e. state that is loaded by VMEXIT but + * isn't saved by VMRUN, that isn't already saved by VMSAVE (performed + * by common SVM code). */ - - /* XCR0 is restored on VMEXIT, save the current host value */ hostsa->xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - - /* PKRU is restored on VMEXIT, save the current host value */ hostsa->pkru = read_pkru(); - - /* MSR_IA32_XSS is restored on VMEXIT, save the currnet host value */ hostsa->xss = host_xss; + + /* + * If DebugSwap is enabled, debug registers are loaded but NOT saved by + * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU both + * saves and loads debug registers (Type-A). + */ + if (sev_es_debug_swap_enabled) { + hostsa->dr0 = native_get_debugreg(0); + hostsa->dr1 = native_get_debugreg(1); + hostsa->dr2 = native_get_debugreg(2); + hostsa->dr3 = native_get_debugreg(3); + hostsa->dr0_addr_mask = amd_get_dr_addr_mask(0); + hostsa->dr1_addr_mask = amd_get_dr_addr_mask(1); + hostsa->dr2_addr_mask = amd_get_dr_addr_mask(2); + hostsa->dr3_addr_mask = amd_get_dr_addr_mask(3); + } } void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index d4bfdc607fe7..e90b429c84f1 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -39,10 +39,9 @@ #include <asm/spec-ctrl.h> #include <asm/cpu_device_id.h> #include <asm/traps.h> +#include <asm/reboot.h> #include <asm/fpu/api.h> -#include <asm/virtext.h> - #include <trace/events/ipi.h> #include "trace.h" @@ -104,6 +103,7 @@ static const struct svm_direct_access_msrs { { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, { .index = MSR_IA32_LASTINTTOIP, .always = false }, + { .index = MSR_IA32_XSS, .always = false }, { .index = MSR_EFER, .always = false }, { .index = MSR_IA32_CR_PAT, .always = false }, { .index = MSR_AMD64_SEV_ES_GHCB, .always = true }, @@ -200,10 +200,10 @@ module_param_named(npt, npt_enabled, bool, 0444); /* allow nested virtualization in KVM/SVM */ static int nested = true; -module_param(nested, int, S_IRUGO); +module_param(nested, int, 0444); /* enable/disable Next RIP Save */ -static int nrips = true; +int nrips = true; module_param(nrips, int, 0444); /* enable/disable Virtual VMLOAD VMSAVE */ @@ -517,50 +517,79 @@ static void svm_init_osvw(struct kvm_vcpu *vcpu) vcpu->arch.osvw.status |= 1; } -static bool kvm_is_svm_supported(void) +static bool __kvm_is_svm_supported(void) { - int cpu = raw_smp_processor_id(); - const char *msg; - u64 vm_cr; + int cpu = smp_processor_id(); + struct cpuinfo_x86 *c = &cpu_data(cpu); - if (!cpu_has_svm(&msg)) { - pr_err("SVM not supported by CPU %d, %s\n", cpu, msg); + if (c->x86_vendor != X86_VENDOR_AMD && + c->x86_vendor != X86_VENDOR_HYGON) { + pr_err("CPU %d isn't AMD or Hygon\n", cpu); return false; } - if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { - pr_info("KVM is unsupported when running as an SEV guest\n"); + if (!cpu_has(c, X86_FEATURE_SVM)) { + pr_err("SVM not supported by CPU %d\n", cpu); return false; } - rdmsrl(MSR_VM_CR, vm_cr); - if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE)) { - pr_err("SVM disabled (by BIOS) in MSR_VM_CR on CPU %d\n", cpu); + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { + pr_info("KVM is unsupported when running as an SEV guest\n"); return false; } return true; } +static bool kvm_is_svm_supported(void) +{ + bool supported; + + migrate_disable(); + supported = __kvm_is_svm_supported(); + migrate_enable(); + + return supported; +} + static int svm_check_processor_compat(void) { - if (!kvm_is_svm_supported()) + if (!__kvm_is_svm_supported()) return -EIO; return 0; } -void __svm_write_tsc_multiplier(u64 multiplier) +static void __svm_write_tsc_multiplier(u64 multiplier) { - preempt_disable(); - if (multiplier == __this_cpu_read(current_tsc_ratio)) - goto out; + return; wrmsrl(MSR_AMD64_TSC_RATIO, multiplier); __this_cpu_write(current_tsc_ratio, multiplier); -out: - preempt_enable(); +} + +static inline void kvm_cpu_svm_disable(void) +{ + uint64_t efer; + + wrmsrl(MSR_VM_HSAVE_PA, 0); + rdmsrl(MSR_EFER, efer); + if (efer & EFER_SVME) { + /* + * Force GIF=1 prior to disabling SVM, e.g. to ensure INIT and + * NMI aren't blocked. + */ + stgi(); + wrmsrl(MSR_EFER, efer & ~EFER_SVME); + } +} + +static void svm_emergency_disable(void) +{ + kvm_rebooting = true; + + kvm_cpu_svm_disable(); } static void svm_hardware_disable(void) @@ -569,7 +598,7 @@ static void svm_hardware_disable(void) if (tsc_scaling) __svm_write_tsc_multiplier(SVM_TSC_RATIO_DEFAULT); - cpu_svm_disable(); + kvm_cpu_svm_disable(); amd_pmu_disable_virt(); } @@ -637,6 +666,21 @@ static int svm_hardware_enable(void) amd_pmu_enable_virt(); + /* + * If TSC_AUX virtualization is supported, TSC_AUX becomes a swap type + * "B" field (see sev_es_prepare_switch_to_guest()) for SEV-ES guests. + * Since Linux does not change the value of TSC_AUX once set, prime the + * TSC_AUX field now to avoid a RDMSR on every vCPU run. + */ + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { + struct sev_es_save_area *hostsa; + u32 __maybe_unused msr_hi; + + hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); + + rdmsr(MSR_TSC_AUX, hostsa->tsc_aux, msr_hi); + } + return 0; } @@ -677,6 +721,39 @@ free_save_area: } +static void set_dr_intercepts(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = svm->vmcb01.ptr; + + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE); + + recalc_intercepts(svm); +} + +static void clr_dr_intercepts(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = svm->vmcb01.ptr; + + vmcb->control.intercepts[INTERCEPT_DR] = 0; + + recalc_intercepts(svm); +} + static int direct_access_msr_slot(u32 msr) { u32 i; @@ -819,8 +896,7 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept) if (intercept == svm->x2avic_msrs_intercepted) return; - if (!x2avic_enabled || - !apic_x2apic_mode(svm->vcpu.arch.apic)) + if (!x2avic_enabled) return; for (i = 0; i < MAX_DIRECT_ACCESS_MSRS; i++) { @@ -947,50 +1023,24 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu) svm_copy_lbrs(svm->vmcb01.ptr, svm->vmcb); } -static int svm_get_lbr_msr(struct vcpu_svm *svm, u32 index) +static struct vmcb *svm_get_lbr_vmcb(struct vcpu_svm *svm) { /* - * If the LBR virtualization is disabled, the LBR msrs are always - * kept in the vmcb01 to avoid copying them on nested guest entries. - * - * If nested, and the LBR virtualization is enabled/disabled, the msrs - * are moved between the vmcb01 and vmcb02 as needed. + * If LBR virtualization is disabled, the LBR MSRs are always kept in + * vmcb01. If LBR virtualization is enabled and L1 is running VMs of + * its own, the MSRs are moved between vmcb01 and vmcb02 as needed. */ - struct vmcb *vmcb = - (svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) ? - svm->vmcb : svm->vmcb01.ptr; - - switch (index) { - case MSR_IA32_DEBUGCTLMSR: - return vmcb->save.dbgctl; - case MSR_IA32_LASTBRANCHFROMIP: - return vmcb->save.br_from; - case MSR_IA32_LASTBRANCHTOIP: - return vmcb->save.br_to; - case MSR_IA32_LASTINTFROMIP: - return vmcb->save.last_excp_from; - case MSR_IA32_LASTINTTOIP: - return vmcb->save.last_excp_to; - default: - KVM_BUG(false, svm->vcpu.kvm, - "%s: Unknown MSR 0x%x", __func__, index); - return 0; - } + return svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK ? svm->vmcb : + svm->vmcb01.ptr; } void svm_update_lbrv(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - - bool enable_lbrv = svm_get_lbr_msr(svm, MSR_IA32_DEBUGCTLMSR) & - DEBUGCTLMSR_LBR; - - bool current_enable_lbrv = !!(svm->vmcb->control.virt_ext & - LBR_CTL_ENABLE_MASK); - - if (unlikely(is_guest_mode(vcpu) && svm->lbrv_enabled)) - if (unlikely(svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK)) - enable_lbrv = true; + bool current_enable_lbrv = svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK; + bool enable_lbrv = (svm_get_lbr_vmcb(svm)->save.dbgctl & DEBUGCTLMSR_LBR) || + (is_guest_mode(vcpu) && guest_can_use(vcpu, X86_FEATURE_LBRV) && + (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK)); if (enable_lbrv == current_enable_lbrv) return; @@ -1101,21 +1151,23 @@ static u64 svm_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) return svm->tsc_ratio_msr; } -static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +static void svm_write_tsc_offset(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); svm->vmcb01.ptr->control.tsc_offset = vcpu->arch.l1_tsc_offset; - svm->vmcb->control.tsc_offset = offset; + svm->vmcb->control.tsc_offset = vcpu->arch.tsc_offset; vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } -static void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier) +void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu) { - __svm_write_tsc_multiplier(multiplier); + preempt_disable(); + if (to_svm(vcpu)->guest_state_loaded) + __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); + preempt_enable(); } - /* Evaluate instruction intercepts that depend on guest CPUID features. */ static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu, struct vcpu_svm *svm) @@ -1156,8 +1208,6 @@ static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 0, 0); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 0, 0); - - svm->v_vmload_vmsave_enabled = false; } else { /* * If hardware supports Virtual VMLOAD VMSAVE then enable it @@ -1201,10 +1251,9 @@ static void init_vmcb(struct kvm_vcpu *vcpu) * Guest access to VMware backdoor ports could legitimately * trigger #GP because of TSS I/O permission bitmap. * We intercept those #GP and allow access to them anyway - * as VMware does. Don't intercept #GP for SEV guests as KVM can't - * decrypt guest memory to decode the faulting instruction. + * as VMware does. */ - if (enable_vmware_backdoor && !sev_guest(vcpu->kvm)) + if (enable_vmware_backdoor) set_exception_intercept(svm, GP_VECTOR); svm_set_intercept(svm, INTERCEPT_INTR); @@ -1480,7 +1529,14 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) if (tsc_scaling) __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); - if (likely(tsc_aux_uret_slot >= 0)) + /* + * TSC_AUX is always virtualized for SEV-ES guests when the feature is + * available. The user return MSR support is not required in this case + * because TSC_AUX is restored on #VMEXIT from the host save area + * (which has been initialized in svm_hardware_enable()). + */ + if (likely(tsc_aux_uret_slot >= 0) && + (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm))) kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull); svm->guest_state_loaded = true; @@ -1800,15 +1856,17 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) bool old_paging = is_paging(vcpu); #ifdef CONFIG_X86_64 - if (vcpu->arch.efer & EFER_LME && !vcpu->arch.guest_state_protected) { + if (vcpu->arch.efer & EFER_LME) { if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { vcpu->arch.efer |= EFER_LMA; - svm->vmcb->save.efer |= EFER_LMA | EFER_LME; + if (!vcpu->arch.guest_state_protected) + svm->vmcb->save.efer |= EFER_LMA | EFER_LME; } if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) { vcpu->arch.efer &= ~EFER_LMA; - svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME); + if (!vcpu->arch.guest_state_protected) + svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME); } } #endif @@ -1949,7 +2007,7 @@ static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - if (vcpu->arch.guest_state_protected) + if (WARN_ON_ONCE(sev_es_guest(vcpu->kvm))) return; get_debugreg(vcpu->arch.db[0], 0); @@ -2129,12 +2187,6 @@ static int shutdown_interception(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; struct vcpu_svm *svm = to_svm(vcpu); - /* - * The VM save area has already been encrypted so it - * cannot be reinitialized - just terminate. - */ - if (sev_es_guest(vcpu->kvm)) - return -EINVAL; /* * VMCB is undefined after a SHUTDOWN intercept. INIT the vCPU to put @@ -2143,9 +2195,14 @@ static int shutdown_interception(struct kvm_vcpu *vcpu) * userspace. At a platform view, INIT is acceptable behavior as * there exist bare metal platforms that automatically INIT the CPU * in response to shutdown. + * + * The VM save area for SEV-ES guests has already been encrypted so it + * cannot be reinitialized, i.e. synthesizing INIT is futile. */ - clear_page(svm->vmcb); - kvm_vcpu_reset(vcpu, true); + if (!sev_es_guest(vcpu->kvm)) { + clear_page(svm->vmcb); + kvm_vcpu_reset(vcpu, true); + } kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; return 0; @@ -2510,12 +2567,13 @@ static int iret_interception(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + WARN_ON_ONCE(sev_es_guest(vcpu->kvm)); + ++vcpu->stat.nmi_window_exits; svm->awaiting_iret_completion = true; svm_clr_iret_intercept(svm); - if (!sev_es_guest(vcpu->kvm)) - svm->nmi_iret_rip = kvm_rip_read(vcpu); + svm->nmi_iret_rip = kvm_rip_read(vcpu); kvm_make_request(KVM_REQ_EVENT, vcpu); return 1; @@ -2680,6 +2738,13 @@ static int dr_interception(struct kvm_vcpu *vcpu) unsigned long val; int err = 0; + /* + * SEV-ES intercepts DR7 only to disable guest debugging and the guest issues a VMGEXIT + * for DR7 write only. KVM cannot change DR7 (always swapped as type 'A') so return early. + */ + if (sev_es_guest(vcpu->kvm)) + return 1; + if (vcpu->guest_debug == 0) { /* * No more DR vmexits; force a reload of the debug registers @@ -2764,7 +2829,8 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr_info->index) { case MSR_AMD64_TSC_RATIO: - if (!msr_info->host_initiated && !svm->tsc_scaling_enabled) + if (!msr_info->host_initiated && + !guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR)) return 1; msr_info->data = svm->tsc_ratio_msr; break; @@ -2802,11 +2868,19 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = svm->tsc_aux; break; case MSR_IA32_DEBUGCTLMSR: + msr_info->data = svm_get_lbr_vmcb(svm)->save.dbgctl; + break; case MSR_IA32_LASTBRANCHFROMIP: + msr_info->data = svm_get_lbr_vmcb(svm)->save.br_from; + break; case MSR_IA32_LASTBRANCHTOIP: + msr_info->data = svm_get_lbr_vmcb(svm)->save.br_to; + break; case MSR_IA32_LASTINTFROMIP: + msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_from; + break; case MSR_IA32_LASTINTTOIP: - msr_info->data = svm_get_lbr_msr(svm, msr_info->index); + msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_to; break; case MSR_VM_HSAVE_PA: msr_info->data = svm->nested.hsave_msr; @@ -2906,7 +2980,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) switch (ecx) { case MSR_AMD64_TSC_RATIO: - if (!svm->tsc_scaling_enabled) { + if (!guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR)) { if (!msr->host_initiated) return 1; @@ -2928,7 +3002,8 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->tsc_ratio_msr = data; - if (svm->tsc_scaling_enabled && is_guest_mode(vcpu)) + if (guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR) && + is_guest_mode(vcpu)) nested_svm_update_tsc_ratio_msr(vcpu); break; @@ -3017,6 +3092,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_TSC_AUX: /* + * TSC_AUX is always virtualized for SEV-ES guests when the + * feature is available. The user return MSR support is not + * required in this case because TSC_AUX is restored on #VMEXIT + * from the host save area (which has been initialized in + * svm_hardware_enable()). + */ + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm)) + break; + + /* * TSC_AUX is usually changed only during boot and never read * directly. Intercept TSC_AUX instead of exposing it to the * guest via direct_access_msrs, and switch it via user return. @@ -3037,13 +3122,8 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) if (data & DEBUGCTL_RESERVED_BITS) return 1; - if (svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) - svm->vmcb->save.dbgctl = data; - else - svm->vmcb01.ptr->save.dbgctl = data; - + svm_get_lbr_vmcb(svm)->save.dbgctl = data; svm_update_lbrv(vcpu); - break; case MSR_VM_HSAVE_PA: /* @@ -3483,8 +3563,15 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) if (svm->nmi_l1_to_l2) return; - svm->nmi_masked = true; - svm_set_iret_intercept(svm); + /* + * No need to manually track NMI masking when vNMI is enabled, hardware + * automatically sets V_NMI_BLOCKING_MASK as appropriate, including the + * case where software directly injects an NMI. + */ + if (!is_vnmi_enabled(svm)) { + svm->nmi_masked = true; + svm_set_iret_intercept(svm); + } ++vcpu->stat.nmi_injections; } @@ -3769,6 +3856,19 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu) if (svm_get_nmi_mask(vcpu) && !svm->awaiting_iret_completion) return; /* IRET will cause a vm exit */ + /* + * SEV-ES guests are responsible for signaling when a vCPU is ready to + * receive a new NMI, as SEV-ES guests can't be single-stepped, i.e. + * KVM can't intercept and single-step IRET to detect when NMIs are + * unblocked (architecturally speaking). See SVM_VMGEXIT_NMI_COMPLETE. + * + * Note, GIF is guaranteed to be '1' for SEV-ES guests as hardware + * ignores SEV-ES guest writes to EFER.SVME *and* CLGI/STGI are not + * supported NAEs in the GHCB protocol. + */ + if (sev_es_guest(vcpu->kvm)) + return; + if (!gif_set(svm)) { if (vgif) svm_set_intercept(svm, INTERCEPT_STGI); @@ -3918,12 +4018,11 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu) svm->soft_int_injected = false; /* - * If we've made progress since setting HF_IRET_MASK, we've + * If we've made progress since setting awaiting_iret_completion, we've * executed an IRET and can allow NMI injection. */ if (svm->awaiting_iret_completion && - (sev_es_guest(vcpu->kvm) || - kvm_rip_read(vcpu) != svm->nmi_iret_rip)) { + kvm_rip_read(vcpu) != svm->nmi_iret_rip) { svm->awaiting_iret_completion = false; svm->nmi_masked = false; kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -4207,30 +4306,38 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index) static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct kvm_cpuid_entry2 *best; - - vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - boot_cpu_has(X86_FEATURE_XSAVE) && - boot_cpu_has(X86_FEATURE_XSAVES); - - /* Update nrips enabled cache */ - svm->nrips_enabled = kvm_cpu_cap_has(X86_FEATURE_NRIPS) && - guest_cpuid_has(vcpu, X86_FEATURE_NRIPS); - svm->tsc_scaling_enabled = tsc_scaling && guest_cpuid_has(vcpu, X86_FEATURE_TSCRATEMSR); - svm->lbrv_enabled = lbrv && guest_cpuid_has(vcpu, X86_FEATURE_LBRV); - - svm->v_vmload_vmsave_enabled = vls && guest_cpuid_has(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD); - - svm->pause_filter_enabled = kvm_cpu_cap_has(X86_FEATURE_PAUSEFILTER) && - guest_cpuid_has(vcpu, X86_FEATURE_PAUSEFILTER); + /* + * SVM doesn't provide a way to disable just XSAVES in the guest, KVM + * can only disable all variants of by disallowing CR4.OSXSAVE from + * being set. As a result, if the host has XSAVE and XSAVES, and the + * guest has XSAVE enabled, the guest can execute XSAVES without + * faulting. Treat XSAVES as enabled in this case regardless of + * whether it's advertised to the guest so that KVM context switches + * XSS on VM-Enter/VM-Exit. Failure to do so would effectively give + * the guest read/write access to the host's XSS. + */ + if (boot_cpu_has(X86_FEATURE_XSAVE) && + boot_cpu_has(X86_FEATURE_XSAVES) && + guest_cpuid_has(vcpu, X86_FEATURE_XSAVE)) + kvm_governed_feature_set(vcpu, X86_FEATURE_XSAVES); - svm->pause_threshold_enabled = kvm_cpu_cap_has(X86_FEATURE_PFTHRESHOLD) && - guest_cpuid_has(vcpu, X86_FEATURE_PFTHRESHOLD); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_NRIPS); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_TSCRATEMSR); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_LBRV); - svm->vgif_enabled = vgif && guest_cpuid_has(vcpu, X86_FEATURE_VGIF); + /* + * Intercept VMLOAD if the vCPU mode is Intel in order to emulate that + * VMLOAD drops bits 63:32 of SYSENTER (ignoring the fact that exposing + * SVM on Intel is bonkers and extremely unlikely to work). + */ + if (!guest_cpuid_is_intel(vcpu)) + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD); - svm->vnmi_enabled = vnmi && guest_cpuid_has(vcpu, X86_FEATURE_VNMI); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PAUSEFILTER); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PFTHRESHOLD); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VGIF); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VNMI); svm_recalc_instruction_intercepts(vcpu, svm); @@ -4242,12 +4349,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0, !!guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)); - /* For sev guests, the memory encryption bit is not reserved in CR3. */ - if (sev_guest(vcpu->kvm)) { - best = kvm_find_cpuid_entry(vcpu, 0x8000001F); - if (best) - vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); - } + if (sev_guest(vcpu->kvm)) + sev_vcpu_after_set_cpuid(svm); init_vmcb_after_set_cpuid(vcpu); } @@ -4615,15 +4718,15 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu) } #endif -static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +static int svm_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { bool smep, smap, is_user; u64 error_code; /* Emulation is always possible when KVM has access to all guest state. */ if (!sev_guest(vcpu->kvm)) - return true; + return X86EMUL_CONTINUE; /* #UD and #GP should never be intercepted for SEV guests. */ WARN_ON_ONCE(emul_type & (EMULTYPE_TRAP_UD | @@ -4635,33 +4738,44 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * to guest register state. */ if (sev_es_guest(vcpu->kvm)) - return false; + return X86EMUL_RETRY_INSTR; /* * Emulation is possible if the instruction is already decoded, e.g. * when completing I/O after returning from userspace. */ if (emul_type & EMULTYPE_NO_DECODE) - return true; + return X86EMUL_CONTINUE; /* * Emulation is possible for SEV guests if and only if a prefilled * buffer containing the bytes of the intercepted instruction is * available. SEV guest memory is encrypted with a guest specific key - * and cannot be decrypted by KVM, i.e. KVM would read cyphertext and + * and cannot be decrypted by KVM, i.e. KVM would read ciphertext and * decode garbage. * - * Inject #UD if KVM reached this point without an instruction buffer. - * In practice, this path should never be hit by a well-behaved guest, - * e.g. KVM doesn't intercept #UD or #GP for SEV guests, but this path - * is still theoretically reachable, e.g. via unaccelerated fault-like - * AVIC access, and needs to be handled by KVM to avoid putting the - * guest into an infinite loop. Injecting #UD is somewhat arbitrary, - * but its the least awful option given lack of insight into the guest. + * If KVM is NOT trying to simply skip an instruction, inject #UD if + * KVM reached this point without an instruction buffer. In practice, + * this path should never be hit by a well-behaved guest, e.g. KVM + * doesn't intercept #UD or #GP for SEV guests, but this path is still + * theoretically reachable, e.g. via unaccelerated fault-like AVIC + * access, and needs to be handled by KVM to avoid putting the guest + * into an infinite loop. Injecting #UD is somewhat arbitrary, but + * its the least awful option given lack of insight into the guest. + * + * If KVM is trying to skip an instruction, simply resume the guest. + * If a #NPF occurs while the guest is vectoring an INT3/INTO, then KVM + * will attempt to re-inject the INT3/INTO and skip the instruction. + * In that scenario, retrying the INT3/INTO and hoping the guest will + * make forward progress is the only option that has a chance of + * success (and in practice it will work the vast majority of the time). */ if (unlikely(!insn)) { + if (emul_type & EMULTYPE_SKIP) + return X86EMUL_UNHANDLEABLE; + kvm_queue_exception(vcpu, UD_VECTOR); - return false; + return X86EMUL_PROPAGATE_FAULT; } /* @@ -4672,7 +4786,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * table used to translate CS:RIP resides in emulated MMIO. */ if (likely(insn_len)) - return true; + return X86EMUL_CONTINUE; /* * Detect and workaround Errata 1096 Fam_17h_00_0Fh. @@ -4730,6 +4844,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, kvm_inject_gp(vcpu, 0); else kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + return X86EMUL_PROPAGATE_FAULT; } resume_guest: @@ -4747,7 +4862,7 @@ resume_guest: * doesn't explicitly define "ignored", i.e. doing nothing and letting * the guest spin is technically "ignoring" the access. */ - return false; + return X86EMUL_RETRY_INSTR; } static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) @@ -4907,7 +5022,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .vm_copy_enc_context_from = sev_vm_copy_enc_context_from, .vm_move_enc_context_from = sev_vm_move_enc_context_from, - .can_emulate_instruction = svm_can_emulate_instruction, + .check_emulate_instruction = svm_check_emulate_instruction, .apic_init_signal_blocked = svm_apic_init_signal_blocked, @@ -4971,6 +5086,13 @@ static __init void svm_set_cpu_caps(void) kvm_cpu_cap_set(X86_FEATURE_SVM); kvm_cpu_cap_set(X86_FEATURE_VMCBCLEAN); + /* + * KVM currently flushes TLBs on *every* nested SVM transition, + * and so for all intents and purposes KVM supports flushing by + * ASID, i.e. KVM is guaranteed to honor every L1 ASID flush. + */ + kvm_cpu_cap_set(X86_FEATURE_FLUSHBYASID); + if (nrips) kvm_cpu_cap_set(X86_FEATURE_NRIPS); @@ -5112,9 +5234,11 @@ static __init int svm_hardware_setup(void) svm_adjust_mmio_mask(); + nrips = nrips && boot_cpu_has(X86_FEATURE_NRIPS); + /* * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which - * may be modified by svm_adjust_mmio_mask()). + * may be modified by svm_adjust_mmio_mask()), as well as nrips. */ sev_hardware_setup(); @@ -5126,11 +5250,6 @@ static __init int svm_hardware_setup(void) goto err; } - if (nrips) { - if (!boot_cpu_has(X86_FEATURE_NRIPS)) - nrips = false; - } - enable_apicv = avic = avic && avic_hardware_setup(); if (!enable_apicv) { @@ -5213,6 +5332,13 @@ static struct kvm_x86_init_ops svm_init_ops __initdata = { .pmu_ops = &amd_pmu_ops, }; +static void __svm_exit(void) +{ + kvm_x86_vendor_exit(); + + cpu_emergency_unregister_virt_callback(svm_emergency_disable); +} + static int __init svm_init(void) { int r; @@ -5226,6 +5352,8 @@ static int __init svm_init(void) if (r) return r; + cpu_emergency_register_virt_callback(svm_emergency_disable); + /* * Common KVM initialization _must_ come last, after this, /dev/kvm is * exposed to userspace! @@ -5238,14 +5366,14 @@ static int __init svm_init(void) return 0; err_kvm_init: - kvm_x86_vendor_exit(); + __svm_exit(); return r; } static void __exit svm_exit(void) { kvm_exit(); - kvm_x86_vendor_exit(); + __svm_exit(); } module_init(svm_init) diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 8239c8de45ac..8ef95139cd24 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -22,6 +22,7 @@ #include <asm/svm.h> #include <asm/sev-common.h> +#include "cpuid.h" #include "kvm_cache_regs.h" #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) @@ -29,10 +30,11 @@ #define IOPM_SIZE PAGE_SIZE * 3 #define MSRPM_SIZE PAGE_SIZE * 2 -#define MAX_DIRECT_ACCESS_MSRS 46 +#define MAX_DIRECT_ACCESS_MSRS 47 #define MSRPM_OFFSETS 32 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; +extern int nrips; extern int vgif; extern bool intercept_smi; extern bool x2avic_enabled; @@ -146,7 +148,9 @@ struct vmcb_ctrl_area_cached { u64 virt_ext; u32 clean; union { +#if IS_ENABLED(CONFIG_HYPERV) || IS_ENABLED(CONFIG_KVM_HYPERV) struct hv_vmcb_enlightenments hv_enlightenments; +#endif u8 reserved_sw[32]; }; }; @@ -260,16 +264,6 @@ struct vcpu_svm { unsigned long soft_int_next_rip; bool soft_int_injected; - /* optional nested SVM features that are enabled for this guest */ - bool nrips_enabled : 1; - bool tsc_scaling_enabled : 1; - bool v_vmload_vmsave_enabled : 1; - bool lbrv_enabled : 1; - bool pause_filter_enabled : 1; - bool pause_threshold_enabled : 1; - bool vgif_enabled : 1; - bool vnmi_enabled : 1; - u32 ldr_reg; u32 dfr_reg; struct page *avic_backing_page; @@ -406,48 +400,6 @@ static inline bool vmcb12_is_intercept(struct vmcb_ctrl_area_cached *control, u3 return test_bit(bit, (unsigned long *)&control->intercepts); } -static inline void set_dr_intercepts(struct vcpu_svm *svm) -{ - struct vmcb *vmcb = svm->vmcb01.ptr; - - if (!sev_es_guest(svm->vcpu.kvm)) { - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_WRITE); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_WRITE); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_WRITE); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_WRITE); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_WRITE); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_WRITE); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_WRITE); - } - - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE); - - recalc_intercepts(svm); -} - -static inline void clr_dr_intercepts(struct vcpu_svm *svm) -{ - struct vmcb *vmcb = svm->vmcb01.ptr; - - vmcb->control.intercepts[INTERCEPT_DR] = 0; - - /* DR7 access must remain intercepted for an SEV-ES guest */ - if (sev_es_guest(svm->vcpu.kvm)) { - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ); - vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE); - } - - recalc_intercepts(svm); -} - static inline void set_exception_intercept(struct vcpu_svm *svm, u32 bit) { struct vmcb *vmcb = svm->vmcb01.ptr; @@ -493,7 +445,8 @@ static inline bool svm_is_intercept(struct vcpu_svm *svm, int bit) static inline bool nested_vgif_enabled(struct vcpu_svm *svm) { - return svm->vgif_enabled && (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK); + return guest_can_use(&svm->vcpu, X86_FEATURE_VGIF) && + (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK); } static inline struct vmcb *get_vgif_vmcb(struct vcpu_svm *svm) @@ -544,7 +497,7 @@ static inline bool nested_npt_enabled(struct vcpu_svm *svm) static inline bool nested_vnmi_enabled(struct vcpu_svm *svm) { - return svm->vnmi_enabled && + return guest_can_use(&svm->vcpu, X86_FEATURE_VNMI) && (svm->nested.ctl.int_ctl & V_NMI_ENABLE_MASK); } @@ -660,7 +613,7 @@ int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); int nested_svm_exit_special(struct vcpu_svm *svm); void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu); -void __svm_write_tsc_multiplier(u64 multiplier); +void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu); void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, struct vmcb_control_area *control); void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm, @@ -733,6 +686,7 @@ void __init sev_hardware_setup(void); void sev_hardware_unsetup(void); int sev_cpu_init(struct svm_cpu_data *sd); void sev_init_vmcb(struct vcpu_svm *svm); +void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm); void sev_free_vcpu(struct kvm_vcpu *vcpu); int sev_handle_vmgexit(struct kvm_vcpu *vcpu); int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c index 7af8422d3382..3971b3ea5d04 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.c +++ b/arch/x86/kvm/svm/svm_onhyperv.c @@ -18,18 +18,14 @@ int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) { struct hv_vmcb_enlightenments *hve; - struct hv_partition_assist_pg **p_hv_pa_pg = - &to_kvm_hv(vcpu->kvm)->hv_pa_pg; + hpa_t partition_assist_page = hv_get_partition_assist_page(vcpu); - if (!*p_hv_pa_pg) - *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL); - - if (!*p_hv_pa_pg) + if (partition_assist_page == INVALID_PAGE) return -ENOMEM; hve = &to_svm(vcpu)->vmcb->control.hv_enlightenments; - hve->partition_assist_page = __pa(*p_hv_pa_pg); + hve->partition_assist_page = partition_assist_page; hve->hv_vm_id = (unsigned long)vcpu->kvm; if (!hve->hv_enlightenments_control.nested_flush_hypercall) { hve->hv_enlightenments_control.nested_flush_hypercall = 1; diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h index 36c8af87a707..4e725854c63a 100644 --- a/arch/x86/kvm/svm/svm_ops.h +++ b/arch/x86/kvm/svm/svm_ops.h @@ -8,7 +8,7 @@ #define svm_asm(insn, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) "\n\t" \ + asm goto("1: " __stringify(insn) "\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ ::: clobber : fault); \ return; \ @@ -18,7 +18,7 @@ fault: \ #define svm_asm1(insn, op1, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \ + asm goto("1: " __stringify(insn) " %0\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ :: op1 : clobber : fault); \ return; \ @@ -28,7 +28,7 @@ fault: \ #define svm_asm2(insn, op1, op2, clobber...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \ + asm goto("1: " __stringify(insn) " %1, %0\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ :: op1, op2 : clobber : fault); \ return; \ diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index ef2ebabb059c..9499f9c6b077 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -270,16 +270,16 @@ SYM_FUNC_START(__svm_vcpu_run) RESTORE_GUEST_SPEC_CTRL_BODY RESTORE_HOST_SPEC_CTRL_BODY -10: cmpb $0, kvm_rebooting +10: cmpb $0, _ASM_RIP(kvm_rebooting) jne 2b ud2 -30: cmpb $0, kvm_rebooting +30: cmpb $0, _ASM_RIP(kvm_rebooting) jne 4b ud2 -50: cmpb $0, kvm_rebooting +50: cmpb $0, _ASM_RIP(kvm_rebooting) jne 6b ud2 -70: cmpb $0, kvm_rebooting +70: cmpb $0, _ASM_RIP(kvm_rebooting) jne 8b ud2 @@ -381,7 +381,7 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) RESTORE_GUEST_SPEC_CTRL_BODY RESTORE_HOST_SPEC_CTRL_BODY -3: cmpb $0, kvm_rebooting +3: cmpb $0, _ASM_RIP(kvm_rebooting) jne 2b ud2 diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index d0abee35d7ba..41a4533f9989 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -252,7 +252,7 @@ static inline bool cpu_has_vmx_pml(void) static inline bool cpu_has_vmx_xsaves(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & - SECONDARY_EXEC_XSAVES; + SECONDARY_EXEC_ENABLE_XSAVES; } static inline bool cpu_has_vmx_waitpkg(void) diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index 79450e1ed7cf..fab6a1ad98dc 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -13,419 +13,6 @@ #define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK -/* - * Enlightened VMCSv1 doesn't support these: - * - * POSTED_INTR_NV = 0x00000002, - * GUEST_INTR_STATUS = 0x00000810, - * APIC_ACCESS_ADDR = 0x00002014, - * POSTED_INTR_DESC_ADDR = 0x00002016, - * EOI_EXIT_BITMAP0 = 0x0000201c, - * EOI_EXIT_BITMAP1 = 0x0000201e, - * EOI_EXIT_BITMAP2 = 0x00002020, - * EOI_EXIT_BITMAP3 = 0x00002022, - * GUEST_PML_INDEX = 0x00000812, - * PML_ADDRESS = 0x0000200e, - * VM_FUNCTION_CONTROL = 0x00002018, - * EPTP_LIST_ADDRESS = 0x00002024, - * VMREAD_BITMAP = 0x00002026, - * VMWRITE_BITMAP = 0x00002028, - * - * TSC_MULTIPLIER = 0x00002032, - * PLE_GAP = 0x00004020, - * PLE_WINDOW = 0x00004022, - * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, - * - * Currently unsupported in KVM: - * GUEST_IA32_RTIT_CTL = 0x00002814, - */ -#define EVMCS1_SUPPORTED_PINCTRL \ - (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - PIN_BASED_EXT_INTR_MASK | \ - PIN_BASED_NMI_EXITING | \ - PIN_BASED_VIRTUAL_NMIS) - -#define EVMCS1_SUPPORTED_EXEC_CTRL \ - (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - CPU_BASED_HLT_EXITING | \ - CPU_BASED_CR3_LOAD_EXITING | \ - CPU_BASED_CR3_STORE_EXITING | \ - CPU_BASED_UNCOND_IO_EXITING | \ - CPU_BASED_MOV_DR_EXITING | \ - CPU_BASED_USE_TSC_OFFSETTING | \ - CPU_BASED_MWAIT_EXITING | \ - CPU_BASED_MONITOR_EXITING | \ - CPU_BASED_INVLPG_EXITING | \ - CPU_BASED_RDPMC_EXITING | \ - CPU_BASED_INTR_WINDOW_EXITING | \ - CPU_BASED_CR8_LOAD_EXITING | \ - CPU_BASED_CR8_STORE_EXITING | \ - CPU_BASED_RDTSC_EXITING | \ - CPU_BASED_TPR_SHADOW | \ - CPU_BASED_USE_IO_BITMAPS | \ - CPU_BASED_MONITOR_TRAP_FLAG | \ - CPU_BASED_USE_MSR_BITMAPS | \ - CPU_BASED_NMI_WINDOW_EXITING | \ - CPU_BASED_PAUSE_EXITING | \ - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) - -#define EVMCS1_SUPPORTED_2NDEXEC \ - (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ - SECONDARY_EXEC_WBINVD_EXITING | \ - SECONDARY_EXEC_ENABLE_VPID | \ - SECONDARY_EXEC_ENABLE_EPT | \ - SECONDARY_EXEC_UNRESTRICTED_GUEST | \ - SECONDARY_EXEC_DESC | \ - SECONDARY_EXEC_ENABLE_RDTSCP | \ - SECONDARY_EXEC_ENABLE_INVPCID | \ - SECONDARY_EXEC_XSAVES | \ - SECONDARY_EXEC_RDSEED_EXITING | \ - SECONDARY_EXEC_RDRAND_EXITING | \ - SECONDARY_EXEC_TSC_SCALING | \ - SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ - SECONDARY_EXEC_PT_USE_GPA | \ - SECONDARY_EXEC_PT_CONCEAL_VMX | \ - SECONDARY_EXEC_BUS_LOCK_DETECTION | \ - SECONDARY_EXEC_NOTIFY_VM_EXITING | \ - SECONDARY_EXEC_ENCLS_EXITING) - -#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) - -#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ - (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_EXIT_SAVE_DEBUG_CONTROLS | \ - VM_EXIT_ACK_INTR_ON_EXIT | \ - VM_EXIT_HOST_ADDR_SPACE_SIZE | \ - VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_EXIT_SAVE_IA32_PAT | \ - VM_EXIT_LOAD_IA32_PAT | \ - VM_EXIT_SAVE_IA32_EFER | \ - VM_EXIT_LOAD_IA32_EFER | \ - VM_EXIT_CLEAR_BNDCFGS | \ - VM_EXIT_PT_CONCEAL_PIP | \ - VM_EXIT_CLEAR_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ - (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_ENTRY_LOAD_DEBUG_CONTROLS | \ - VM_ENTRY_IA32E_MODE | \ - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_ENTRY_LOAD_IA32_PAT | \ - VM_ENTRY_LOAD_IA32_EFER | \ - VM_ENTRY_LOAD_BNDCFGS | \ - VM_ENTRY_PT_CONCEAL_PIP | \ - VM_ENTRY_LOAD_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMFUNC (0) - -#define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) -#define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ - {EVMCS1_OFFSET(name), clean_field} - -const struct evmcs_field vmcs_field_to_evmcs_1[] = { - /* 64 bit rw */ - EVMCS1_FIELD(GUEST_RIP, guest_rip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(GUEST_RSP, guest_rsp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - EVMCS1_FIELD(GUEST_RFLAGS, guest_rflags, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - EVMCS1_FIELD(HOST_IA32_PAT, host_ia32_pat, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_EFER, host_ia32_efer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CR0, host_cr0, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CR3, host_cr3, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CR4, host_cr4, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_RIP, host_rip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(IO_BITMAP_A, io_bitmap_a, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), - EVMCS1_FIELD(IO_BITMAP_B, io_bitmap_b, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), - EVMCS1_FIELD(MSR_BITMAP, msr_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP), - EVMCS1_FIELD(GUEST_ES_BASE, guest_es_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_BASE, guest_cs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_BASE, guest_ss_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_BASE, guest_ds_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_BASE, guest_fs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_BASE, guest_gs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_BASE, guest_ldtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_BASE, guest_tr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GDTR_BASE, guest_gdtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_IDTR_BASE, guest_idtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(TSC_OFFSET, tsc_offset, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(VMCS_LINK_POINTER, vmcs_link_pointer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_PAT, guest_ia32_pat, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_EFER, guest_ia32_efer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR0, guest_pdptr0, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR1, guest_pdptr1, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR2, guest_pdptr2, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR3, guest_pdptr3, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(CR0_READ_SHADOW, cr0_read_shadow, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(CR4_READ_SHADOW, cr4_read_shadow, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_CR0, guest_cr0, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_CR3, guest_cr3, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_CR4, guest_cr4, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_DR7, guest_dr7, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(HOST_FS_BASE, host_fs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_GS_BASE, host_gs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_TR_BASE, host_tr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_GDTR_BASE, host_gdtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_IDTR_BASE, host_idtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_RSP, host_rsp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(EPT_POINTER, ept_pointer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), - EVMCS1_FIELD(GUEST_BNDCFGS, guest_bndcfgs, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(XSS_EXIT_BITMAP, xss_exit_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(ENCLS_EXITING_BITMAP, encls_exiting_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(TSC_MULTIPLIER, tsc_multiplier, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - /* - * Not used by KVM: - * - * EVMCS1_FIELD(0x00006828, guest_ia32_s_cet, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - * EVMCS1_FIELD(0x0000682A, guest_ssp, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - * EVMCS1_FIELD(0x0000682C, guest_ia32_int_ssp_table_addr, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - * EVMCS1_FIELD(0x00002816, guest_ia32_lbr_ctl, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - * EVMCS1_FIELD(0x00006C18, host_ia32_s_cet, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - * EVMCS1_FIELD(0x00006C1A, host_ssp, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - * EVMCS1_FIELD(0x00006C1C, host_ia32_int_ssp_table_addr, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - */ - - /* 64 bit read only */ - EVMCS1_FIELD(GUEST_PHYSICAL_ADDRESS, guest_physical_address, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(EXIT_QUALIFICATION, exit_qualification, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - /* - * Not defined in KVM: - * - * EVMCS1_FIELD(0x00006402, exit_io_instruction_ecx, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - * EVMCS1_FIELD(0x00006404, exit_io_instruction_esi, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - * EVMCS1_FIELD(0x00006406, exit_io_instruction_esi, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - * EVMCS1_FIELD(0x00006408, exit_io_instruction_eip, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - */ - EVMCS1_FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - - /* - * No mask defined in the spec as Hyper-V doesn't currently support - * these. Future proof by resetting the whole clean field mask on - * access. - */ - EVMCS1_FIELD(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - - /* 32 bit rw */ - EVMCS1_FIELD(TPR_THRESHOLD, tpr_threshold, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - EVMCS1_FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC), - EVMCS1_FIELD(EXCEPTION_BITMAP, exception_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN), - EVMCS1_FIELD(VM_ENTRY_CONTROLS, vm_entry_controls, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY), - EVMCS1_FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), - EVMCS1_FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE, - vm_entry_exception_error_code, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), - EVMCS1_FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), - EVMCS1_FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), - EVMCS1_FIELD(VM_EXIT_CONTROLS, vm_exit_controls, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), - EVMCS1_FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), - EVMCS1_FIELD(GUEST_ES_LIMIT, guest_es_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_LIMIT, guest_cs_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_LIMIT, guest_ss_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_LIMIT, guest_ds_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_LIMIT, guest_fs_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_LIMIT, guest_gs_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_LIMIT, guest_tr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_ACTIVITY_STATE, guest_activity_state, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - - /* 32 bit read only */ - EVMCS1_FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_REASON, vm_exit_reason, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - - /* No mask defined in the spec (not used) */ - EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(CR3_TARGET_COUNT, cr3_target_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - - /* 16 bit rw */ - EVMCS1_FIELD(HOST_ES_SELECTOR, host_es_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CS_SELECTOR, host_cs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_SS_SELECTOR, host_ss_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_DS_SELECTOR, host_ds_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_FS_SELECTOR, host_fs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_GS_SELECTOR, host_gs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_TR_SELECTOR, host_tr_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(GUEST_ES_SELECTOR, guest_es_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_SELECTOR, guest_cs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_SELECTOR, guest_ss_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_SELECTOR, guest_ds_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_SELECTOR, guest_fs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_SELECTOR, guest_gs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_SELECTOR, guest_tr_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), -}; -const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); - u64 nested_get_evmptr(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); @@ -608,40 +195,6 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12) return 0; } -#if IS_ENABLED(CONFIG_HYPERV) -DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); - -/* - * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption - * is: in case a feature has corresponding fields in eVMCS described and it was - * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a - * feature which has no corresponding eVMCS field, this likely means that KVM - * needs to be updated. - */ -#define evmcs_check_vmcs_conf(field, ctrl) \ - do { \ - typeof(vmcs_conf->field) unsupported; \ - \ - unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl; \ - if (unsupported) { \ - pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\ - (u64)unsupported); \ - vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl; \ - } \ - } \ - while (0) - -void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) -{ - evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL); - evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL); - evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC); - evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC); - evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL); - evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL); -} -#endif - int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version) { diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index 9623fe1651c4..a87407412615 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -2,199 +2,89 @@ #ifndef __KVM_X86_VMX_HYPERV_H #define __KVM_X86_VMX_HYPERV_H -#include <linux/jump_label.h> - -#include <asm/hyperv-tlfs.h> -#include <asm/mshyperv.h> -#include <asm/vmx.h> - -#include "../hyperv.h" - -#include "capabilities.h" -#include "vmcs.h" +#include <linux/kvm_host.h> #include "vmcs12.h" +#include "vmx.h" -struct vmcs_config; - -#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs)) - -#define KVM_EVMCS_VERSION 1 +#define EVMPTR_INVALID (-1ULL) +#define EVMPTR_MAP_PENDING (-2ULL) -struct evmcs_field { - u16 offset; - u16 clean_field; +enum nested_evmptrld_status { + EVMPTRLD_DISABLED, + EVMPTRLD_SUCCEEDED, + EVMPTRLD_VMFAIL, + EVMPTRLD_ERROR, }; -extern const struct evmcs_field vmcs_field_to_evmcs_1[]; -extern const unsigned int nr_evmcs_1_fields; - -static __always_inline int evmcs_field_offset(unsigned long field, - u16 *clean_field) -{ - unsigned int index = ROL16(field, 6); - const struct evmcs_field *evmcs_field; - - if (unlikely(index >= nr_evmcs_1_fields)) - return -ENOENT; - - evmcs_field = &vmcs_field_to_evmcs_1[index]; - - /* - * Use offset=0 to detect holes in eVMCS. This offset belongs to - * 'revision_id' but this field has no encoding and is supposed to - * be accessed directly. - */ - if (unlikely(!evmcs_field->offset)) - return -ENOENT; - - if (clean_field) - *clean_field = evmcs_field->clean_field; - - return evmcs_field->offset; -} - -static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, - unsigned long field, u16 offset) +#ifdef CONFIG_KVM_HYPERV +static inline bool evmptr_is_valid(u64 evmptr) { - /* - * vmcs12_read_any() doesn't care whether the supplied structure - * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes - * the exact offset of the required field, use it for convenience - * here. - */ - return vmcs12_read_any((void *)evmcs, field, offset); + return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING; } -#if IS_ENABLED(CONFIG_HYPERV) - -DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); - -static __always_inline bool kvm_is_using_evmcs(void) +static inline bool nested_vmx_is_evmptr12_valid(struct vcpu_vmx *vmx) { - return static_branch_unlikely(&__kvm_is_using_evmcs); + return evmptr_is_valid(vmx->nested.hv_evmcs_vmptr); } -static __always_inline int get_evmcs_offset(unsigned long field, - u16 *clean_field) +static inline bool evmptr_is_set(u64 evmptr) { - int offset = evmcs_field_offset(field, clean_field); - - WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field); - return offset; + return evmptr != EVMPTR_INVALID; } -static __always_inline void evmcs_write64(unsigned long field, u64 value) +static inline bool nested_vmx_is_evmptr12_set(struct vcpu_vmx *vmx) { - u16 clean_field; - int offset = get_evmcs_offset(field, &clean_field); - - if (offset < 0) - return; - - *(u64 *)((char *)current_evmcs + offset) = value; - - current_evmcs->hv_clean_fields &= ~clean_field; + return evmptr_is_set(vmx->nested.hv_evmcs_vmptr); } -static __always_inline void evmcs_write32(unsigned long field, u32 value) +static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx) { - u16 clean_field; - int offset = get_evmcs_offset(field, &clean_field); - - if (offset < 0) - return; - - *(u32 *)((char *)current_evmcs + offset) = value; - current_evmcs->hv_clean_fields &= ~clean_field; + return vmx->nested.hv_evmcs; } -static __always_inline void evmcs_write16(unsigned long field, u16 value) +static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu) { - u16 clean_field; - int offset = get_evmcs_offset(field, &clean_field); - - if (offset < 0) - return; - - *(u16 *)((char *)current_evmcs + offset) = value; - current_evmcs->hv_clean_fields &= ~clean_field; + /* + * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and + * eVMCS has been explicitly enabled by userspace. + */ + return vcpu->arch.hyperv_enabled && + to_vmx(vcpu)->nested.enlightened_vmcs_enabled; } -static __always_inline u64 evmcs_read64(unsigned long field) +u64 nested_get_evmptr(struct kvm_vcpu *vcpu); +uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); +int nested_enable_evmcs(struct kvm_vcpu *vcpu, + uint16_t *vmcs_version); +void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); +int nested_evmcs_check_controls(struct vmcs12 *vmcs12); +bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu); +void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); +#else +static inline bool evmptr_is_valid(u64 evmptr) { - int offset = get_evmcs_offset(field, NULL); - - if (offset < 0) - return 0; - - return *(u64 *)((char *)current_evmcs + offset); + return false; } -static __always_inline u32 evmcs_read32(unsigned long field) +static inline bool nested_vmx_is_evmptr12_valid(struct vcpu_vmx *vmx) { - int offset = get_evmcs_offset(field, NULL); - - if (offset < 0) - return 0; - - return *(u32 *)((char *)current_evmcs + offset); + return false; } -static __always_inline u16 evmcs_read16(unsigned long field) +static inline bool evmptr_is_set(u64 evmptr) { - int offset = get_evmcs_offset(field, NULL); - - if (offset < 0) - return 0; - - return *(u16 *)((char *)current_evmcs + offset); + return false; } -static inline void evmcs_load(u64 phys_addr) +static inline bool nested_vmx_is_evmptr12_set(struct vcpu_vmx *vmx) { - struct hv_vp_assist_page *vp_ap = - hv_get_vp_assist_page(smp_processor_id()); - - if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) - vp_ap->nested_control.features.directhypercall = 1; - vp_ap->current_nested_vmcs = phys_addr; - vp_ap->enlighten_vmentry = 1; + return false; } -void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); -#else /* !IS_ENABLED(CONFIG_HYPERV) */ -static __always_inline bool kvm_is_using_evmcs(void) { return false; } -static __always_inline void evmcs_write64(unsigned long field, u64 value) {} -static __always_inline void evmcs_write32(unsigned long field, u32 value) {} -static __always_inline void evmcs_write16(unsigned long field, u16 value) {} -static __always_inline u64 evmcs_read64(unsigned long field) { return 0; } -static __always_inline u32 evmcs_read32(unsigned long field) { return 0; } -static __always_inline u16 evmcs_read16(unsigned long field) { return 0; } -static inline void evmcs_load(u64 phys_addr) {} -#endif /* IS_ENABLED(CONFIG_HYPERV) */ - -#define EVMPTR_INVALID (-1ULL) -#define EVMPTR_MAP_PENDING (-2ULL) - -static inline bool evmptr_is_valid(u64 evmptr) +static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx) { - return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING; + return NULL; } - -enum nested_evmptrld_status { - EVMPTRLD_DISABLED, - EVMPTRLD_SUCCEEDED, - EVMPTRLD_VMFAIL, - EVMPTRLD_ERROR, -}; - -u64 nested_get_evmptr(struct kvm_vcpu *vcpu); -uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); -int nested_enable_evmcs(struct kvm_vcpu *vcpu, - uint16_t *vmcs_version); -void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); -int nested_evmcs_check_controls(struct vmcs12 *vmcs12); -bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu); -void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); +#endif #endif /* __KVM_X86_VMX_HYPERV_H */ diff --git a/arch/x86/kvm/vmx/hyperv_evmcs.c b/arch/x86/kvm/vmx/hyperv_evmcs.c new file mode 100644 index 000000000000..904bfcd1519b --- /dev/null +++ b/arch/x86/kvm/vmx/hyperv_evmcs.c @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file contains common code for working with Enlightened VMCS which is + * used both by Hyper-V on KVM and KVM on Hyper-V. + */ + +#include "hyperv_evmcs.h" + +#define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) +#define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ + {EVMCS1_OFFSET(name), clean_field} + +const struct evmcs_field vmcs_field_to_evmcs_1[] = { + /* 64 bit rw */ + EVMCS1_FIELD(GUEST_RIP, guest_rip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(GUEST_RSP, guest_rsp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + EVMCS1_FIELD(GUEST_RFLAGS, guest_rflags, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + EVMCS1_FIELD(HOST_IA32_PAT, host_ia32_pat, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_EFER, host_ia32_efer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CR0, host_cr0, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CR3, host_cr3, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CR4, host_cr4, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_RIP, host_rip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(IO_BITMAP_A, io_bitmap_a, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), + EVMCS1_FIELD(IO_BITMAP_B, io_bitmap_b, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), + EVMCS1_FIELD(MSR_BITMAP, msr_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP), + EVMCS1_FIELD(GUEST_ES_BASE, guest_es_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_BASE, guest_cs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_BASE, guest_ss_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_BASE, guest_ds_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_BASE, guest_fs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_BASE, guest_gs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_BASE, guest_ldtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_BASE, guest_tr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GDTR_BASE, guest_gdtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_IDTR_BASE, guest_idtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(TSC_OFFSET, tsc_offset, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(VMCS_LINK_POINTER, vmcs_link_pointer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_PAT, guest_ia32_pat, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_EFER, guest_ia32_efer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR0, guest_pdptr0, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR1, guest_pdptr1, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR2, guest_pdptr2, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR3, guest_pdptr3, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(CR0_READ_SHADOW, cr0_read_shadow, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(CR4_READ_SHADOW, cr4_read_shadow, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_CR0, guest_cr0, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_CR3, guest_cr3, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_CR4, guest_cr4, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_DR7, guest_dr7, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(HOST_FS_BASE, host_fs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_GS_BASE, host_gs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_TR_BASE, host_tr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_GDTR_BASE, host_gdtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_IDTR_BASE, host_idtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_RSP, host_rsp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(EPT_POINTER, ept_pointer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), + EVMCS1_FIELD(GUEST_BNDCFGS, guest_bndcfgs, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(XSS_EXIT_BITMAP, xss_exit_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(ENCLS_EXITING_BITMAP, encls_exiting_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(TSC_MULTIPLIER, tsc_multiplier, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + /* + * Not used by KVM: + * + * EVMCS1_FIELD(0x00006828, guest_ia32_s_cet, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x0000682A, guest_ssp, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + * EVMCS1_FIELD(0x0000682C, guest_ia32_int_ssp_table_addr, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x00002816, guest_ia32_lbr_ctl, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x00006C18, host_ia32_s_cet, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + * EVMCS1_FIELD(0x00006C1A, host_ssp, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + * EVMCS1_FIELD(0x00006C1C, host_ia32_int_ssp_table_addr, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + */ + + /* 64 bit read only */ + EVMCS1_FIELD(GUEST_PHYSICAL_ADDRESS, guest_physical_address, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(EXIT_QUALIFICATION, exit_qualification, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + /* + * Not defined in KVM: + * + * EVMCS1_FIELD(0x00006402, exit_io_instruction_ecx, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + * EVMCS1_FIELD(0x00006404, exit_io_instruction_esi, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + * EVMCS1_FIELD(0x00006406, exit_io_instruction_esi, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + * EVMCS1_FIELD(0x00006408, exit_io_instruction_eip, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + */ + EVMCS1_FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + + /* + * No mask defined in the spec as Hyper-V doesn't currently support + * these. Future proof by resetting the whole clean field mask on + * access. + */ + EVMCS1_FIELD(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + + /* 32 bit rw */ + EVMCS1_FIELD(TPR_THRESHOLD, tpr_threshold, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + EVMCS1_FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC), + EVMCS1_FIELD(EXCEPTION_BITMAP, exception_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN), + EVMCS1_FIELD(VM_ENTRY_CONTROLS, vm_entry_controls, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY), + EVMCS1_FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), + EVMCS1_FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE, + vm_entry_exception_error_code, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), + EVMCS1_FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), + EVMCS1_FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), + EVMCS1_FIELD(VM_EXIT_CONTROLS, vm_exit_controls, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), + EVMCS1_FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), + EVMCS1_FIELD(GUEST_ES_LIMIT, guest_es_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_LIMIT, guest_cs_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_LIMIT, guest_ss_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_LIMIT, guest_ds_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_LIMIT, guest_fs_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_LIMIT, guest_gs_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_LIMIT, guest_tr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_ACTIVITY_STATE, guest_activity_state, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + + /* 32 bit read only */ + EVMCS1_FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_REASON, vm_exit_reason, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + + /* No mask defined in the spec (not used) */ + EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(CR3_TARGET_COUNT, cr3_target_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + + /* 16 bit rw */ + EVMCS1_FIELD(HOST_ES_SELECTOR, host_es_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CS_SELECTOR, host_cs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_SS_SELECTOR, host_ss_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_DS_SELECTOR, host_ds_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_FS_SELECTOR, host_fs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_GS_SELECTOR, host_gs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_TR_SELECTOR, host_tr_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(GUEST_ES_SELECTOR, guest_es_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_SELECTOR, guest_cs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_SELECTOR, guest_ss_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_SELECTOR, guest_ds_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_SELECTOR, guest_fs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_SELECTOR, guest_gs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_SELECTOR, guest_tr_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), +}; +const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); diff --git a/arch/x86/kvm/vmx/hyperv_evmcs.h b/arch/x86/kvm/vmx/hyperv_evmcs.h new file mode 100644 index 000000000000..a543fccfc574 --- /dev/null +++ b/arch/x86/kvm/vmx/hyperv_evmcs.h @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This file contains common definitions for working with Enlightened VMCS which + * are used both by Hyper-V on KVM and KVM on Hyper-V. + */ +#ifndef __KVM_X86_VMX_HYPERV_EVMCS_H +#define __KVM_X86_VMX_HYPERV_EVMCS_H + +#include <asm/hyperv-tlfs.h> + +#include "capabilities.h" +#include "vmcs12.h" + +#define KVM_EVMCS_VERSION 1 + +/* + * Enlightened VMCSv1 doesn't support these: + * + * POSTED_INTR_NV = 0x00000002, + * GUEST_INTR_STATUS = 0x00000810, + * APIC_ACCESS_ADDR = 0x00002014, + * POSTED_INTR_DESC_ADDR = 0x00002016, + * EOI_EXIT_BITMAP0 = 0x0000201c, + * EOI_EXIT_BITMAP1 = 0x0000201e, + * EOI_EXIT_BITMAP2 = 0x00002020, + * EOI_EXIT_BITMAP3 = 0x00002022, + * GUEST_PML_INDEX = 0x00000812, + * PML_ADDRESS = 0x0000200e, + * VM_FUNCTION_CONTROL = 0x00002018, + * EPTP_LIST_ADDRESS = 0x00002024, + * VMREAD_BITMAP = 0x00002026, + * VMWRITE_BITMAP = 0x00002028, + * + * TSC_MULTIPLIER = 0x00002032, + * PLE_GAP = 0x00004020, + * PLE_WINDOW = 0x00004022, + * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, + * + * Currently unsupported in KVM: + * GUEST_IA32_RTIT_CTL = 0x00002814, + */ +#define EVMCS1_SUPPORTED_PINCTRL \ + (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + PIN_BASED_EXT_INTR_MASK | \ + PIN_BASED_NMI_EXITING | \ + PIN_BASED_VIRTUAL_NMIS) + +#define EVMCS1_SUPPORTED_EXEC_CTRL \ + (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + CPU_BASED_HLT_EXITING | \ + CPU_BASED_CR3_LOAD_EXITING | \ + CPU_BASED_CR3_STORE_EXITING | \ + CPU_BASED_UNCOND_IO_EXITING | \ + CPU_BASED_MOV_DR_EXITING | \ + CPU_BASED_USE_TSC_OFFSETTING | \ + CPU_BASED_MWAIT_EXITING | \ + CPU_BASED_MONITOR_EXITING | \ + CPU_BASED_INVLPG_EXITING | \ + CPU_BASED_RDPMC_EXITING | \ + CPU_BASED_INTR_WINDOW_EXITING | \ + CPU_BASED_CR8_LOAD_EXITING | \ + CPU_BASED_CR8_STORE_EXITING | \ + CPU_BASED_RDTSC_EXITING | \ + CPU_BASED_TPR_SHADOW | \ + CPU_BASED_USE_IO_BITMAPS | \ + CPU_BASED_MONITOR_TRAP_FLAG | \ + CPU_BASED_USE_MSR_BITMAPS | \ + CPU_BASED_NMI_WINDOW_EXITING | \ + CPU_BASED_PAUSE_EXITING | \ + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) + +#define EVMCS1_SUPPORTED_2NDEXEC \ + (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ + SECONDARY_EXEC_WBINVD_EXITING | \ + SECONDARY_EXEC_ENABLE_VPID | \ + SECONDARY_EXEC_ENABLE_EPT | \ + SECONDARY_EXEC_UNRESTRICTED_GUEST | \ + SECONDARY_EXEC_DESC | \ + SECONDARY_EXEC_ENABLE_RDTSCP | \ + SECONDARY_EXEC_ENABLE_INVPCID | \ + SECONDARY_EXEC_ENABLE_XSAVES | \ + SECONDARY_EXEC_RDSEED_EXITING | \ + SECONDARY_EXEC_RDRAND_EXITING | \ + SECONDARY_EXEC_TSC_SCALING | \ + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ + SECONDARY_EXEC_PT_USE_GPA | \ + SECONDARY_EXEC_PT_CONCEAL_VMX | \ + SECONDARY_EXEC_BUS_LOCK_DETECTION | \ + SECONDARY_EXEC_NOTIFY_VM_EXITING | \ + SECONDARY_EXEC_ENCLS_EXITING) + +#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) + +#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ + (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_EXIT_SAVE_DEBUG_CONTROLS | \ + VM_EXIT_ACK_INTR_ON_EXIT | \ + VM_EXIT_HOST_ADDR_SPACE_SIZE | \ + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_IA32_PAT | \ + VM_EXIT_LOAD_IA32_PAT | \ + VM_EXIT_SAVE_IA32_EFER | \ + VM_EXIT_LOAD_IA32_EFER | \ + VM_EXIT_CLEAR_BNDCFGS | \ + VM_EXIT_PT_CONCEAL_PIP | \ + VM_EXIT_CLEAR_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ + (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_ENTRY_LOAD_DEBUG_CONTROLS | \ + VM_ENTRY_IA32E_MODE | \ + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_ENTRY_LOAD_IA32_PAT | \ + VM_ENTRY_LOAD_IA32_EFER | \ + VM_ENTRY_LOAD_BNDCFGS | \ + VM_ENTRY_PT_CONCEAL_PIP | \ + VM_ENTRY_LOAD_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMFUNC (0) + +struct evmcs_field { + u16 offset; + u16 clean_field; +}; + +extern const struct evmcs_field vmcs_field_to_evmcs_1[]; +extern const unsigned int nr_evmcs_1_fields; + +static __always_inline int evmcs_field_offset(unsigned long field, + u16 *clean_field) +{ + const struct evmcs_field *evmcs_field; + unsigned int index = ROL16(field, 6); + + if (unlikely(index >= nr_evmcs_1_fields)) + return -ENOENT; + + evmcs_field = &vmcs_field_to_evmcs_1[index]; + + /* + * Use offset=0 to detect holes in eVMCS. This offset belongs to + * 'revision_id' but this field has no encoding and is supposed to + * be accessed directly. + */ + if (unlikely(!evmcs_field->offset)) + return -ENOENT; + + if (clean_field) + *clean_field = evmcs_field->clean_field; + + return evmcs_field->offset; +} + +static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, + unsigned long field, u16 offset) +{ + /* + * vmcs12_read_any() doesn't care whether the supplied structure + * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes + * the exact offset of the required field, use it for convenience + * here. + */ + return vmcs12_read_any((void *)evmcs, field, offset); +} + +#endif /* __KVM_X86_VMX_HYPERV_H */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 516391cc0d64..6329a306856b 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -179,7 +179,7 @@ static int nested_vmx_failValid(struct kvm_vcpu *vcpu, * VM_INSTRUCTION_ERROR is not shadowed. Enlightened VMCS 'shadows' all * fields and thus must be synced. */ - if (to_vmx(vcpu)->nested.hv_evmcs_vmptr != EVMPTR_INVALID) + if (nested_vmx_is_evmptr12_set(to_vmx(vcpu))) to_vmx(vcpu)->nested.need_vmcs12_to_shadow_sync = true; return kvm_skip_emulated_instruction(vcpu); @@ -194,7 +194,7 @@ static int nested_vmx_fail(struct kvm_vcpu *vcpu, u32 vm_instruction_error) * can't be done if there isn't a current VMCS. */ if (vmx->nested.current_vmptr == INVALID_GPA && - !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + !nested_vmx_is_evmptr12_valid(vmx)) return nested_vmx_failInvalid(vcpu); return nested_vmx_failValid(vcpu, vm_instruction_error); @@ -226,10 +226,11 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) { +#ifdef CONFIG_KVM_HYPERV struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + if (nested_vmx_is_evmptr12_valid(vmx)) { kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true); vmx->nested.hv_evmcs = NULL; } @@ -241,6 +242,34 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) hv_vcpu->nested.vm_id = 0; hv_vcpu->nested.vp_id = 0; } +#endif +} + +static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr) +{ +#ifdef CONFIG_KVM_HYPERV + struct vcpu_vmx *vmx = to_vmx(vcpu); + /* + * When Enlightened VMEntry is enabled on the calling CPU we treat + * memory area pointer by vmptr as Enlightened VMCS (as there's no good + * way to distinguish it from VMCS12) and we must not corrupt it by + * writing to the non-existent 'launch_state' field. The area doesn't + * have to be the currently active EVMCS on the calling CPU and there's + * nothing KVM has to do to transition it from 'active' to 'non-active' + * state. It is possible that the area will stay mapped as + * vmx->nested.hv_evmcs but this shouldn't be a problem. + */ + if (!guest_cpuid_has_evmcs(vcpu) || + !evmptr_is_valid(nested_get_evmptr(vcpu))) + return false; + + if (nested_vmx_evmcs(vmx) && vmptr == vmx->nested.hv_evmcs_vmptr) + nested_release_evmcs(vcpu); + + return true; +#else + return false; +#endif } static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, @@ -572,7 +601,6 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, int msr; unsigned long *msr_bitmap_l1; unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap; - struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; struct kvm_host_map *map = &vmx->nested.msr_bitmap_map; /* Nothing to do if the MSR bitmap is not in use. */ @@ -588,10 +616,13 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, * - Nested hypervisor (L1) has enabled 'Enlightened MSR Bitmap' feature * and tells KVM (L0) there were no changes in MSR bitmap for L2. */ - if (!vmx->nested.force_msr_bitmap_recalc && evmcs && - evmcs->hv_enlightenments_control.msr_bitmap && - evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP) - return true; + if (!vmx->nested.force_msr_bitmap_recalc) { + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); + + if (evmcs && evmcs->hv_enlightenments_control.msr_bitmap && + evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP) + return true; + } if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map)) return false; @@ -1085,7 +1116,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, bool reload_pdptrs, enum vm_entry_failure_code *entry_failure_code) { - if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) { + if (CC(!kvm_vcpu_is_legal_cr3(vcpu, cr3))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } @@ -1139,14 +1170,8 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); - /* - * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or - * L2's VP_ID upon request from the guest. Make sure we check for - * pending entries in the right FIFO upon L1/L2 transition as these - * requests are put by other vCPUs asynchronously. - */ - if (to_hv_vcpu(vcpu) && enable_ept) - kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu); + /* Handle pending Hyper-V TLB flush requests */ + kvm_hv_nested_transtion_tlb_flush(vcpu, enable_ept); /* * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings @@ -1578,8 +1603,9 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields) { +#ifdef CONFIG_KVM_HYPERV struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; - struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(&vmx->vcpu); /* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */ @@ -1818,12 +1844,16 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields */ return; +#else /* CONFIG_KVM_HYPERV */ + KVM_BUG_ON(1, vmx->vcpu.kvm); +#endif /* CONFIG_KVM_HYPERV */ } static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) { +#ifdef CONFIG_KVM_HYPERV struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; - struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); /* * Should not be changed by KVM: @@ -1992,6 +2022,9 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) evmcs->guest_bndcfgs = vmcs12->guest_bndcfgs; return; +#else /* CONFIG_KVM_HYPERV */ + KVM_BUG_ON(1, vmx->vcpu.kvm); +#endif /* CONFIG_KVM_HYPERV */ } /* @@ -2001,6 +2034,7 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( struct kvm_vcpu *vcpu, bool from_launch) { +#ifdef CONFIG_KVM_HYPERV struct vcpu_vmx *vmx = to_vmx(vcpu); bool evmcs_gpa_changed = false; u64 evmcs_gpa; @@ -2082,13 +2116,16 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( } return EVMPTRLD_SUCCEEDED; +#else + return EVMPTRLD_DISABLED; +#endif } void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) copy_vmcs12_to_enlightened(vmx); else copy_vmcs12_to_shadow(vmx); @@ -2242,7 +2279,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 u32 exec_control; u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12); - if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx)) prepare_vmcs02_early_rare(vmx, vmcs12); /* @@ -2307,7 +2344,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_ENABLE_RDTSCP | - SECONDARY_EXEC_XSAVES | + SECONDARY_EXEC_ENABLE_XSAVES | SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_APIC_REGISTER_VIRT | @@ -2403,7 +2440,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) { - struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs; + struct hv_enlightened_vmcs *hv_evmcs = nested_vmx_evmcs(vmx); if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) { @@ -2535,15 +2572,15 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, enum vm_entry_failure_code *entry_failure_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); bool load_guest_pdptrs_vmcs12 = false; - if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx)) { prepare_vmcs02_rare(vmx, vmcs12); vmx->nested.dirty_vmcs12 = false; - load_guest_pdptrs_vmcs12 = !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) || - !(vmx->nested.hv_evmcs->hv_clean_fields & - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1); + load_guest_pdptrs_vmcs12 = !nested_vmx_is_evmptr12_valid(vmx) || + !(evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1); } if (vmx->nested.nested_run_pending && @@ -2664,9 +2701,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * bits when it changes a field in eVMCS. Mark all fields as clean * here. */ - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) - vmx->nested.hv_evmcs->hv_clean_fields |= - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; + if (nested_vmx_is_evmptr12_valid(vmx)) + evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; return 0; } @@ -2717,7 +2753,7 @@ static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp) } /* Reserved bits should not be set */ - if (CC(kvm_vcpu_is_illegal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f))) + if (CC(!kvm_vcpu_is_legal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f))) return false; /* AD, if set, should be supported */ @@ -2888,8 +2924,10 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, nested_check_vm_entry_controls(vcpu, vmcs12)) return -EINVAL; +#ifdef CONFIG_KVM_HYPERV if (guest_cpuid_has_evmcs(vcpu)) return nested_evmcs_check_controls(vmcs12); +#endif return 0; } @@ -2912,7 +2950,7 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) || CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) || - CC(kvm_vcpu_is_illegal_gpa(vcpu, vmcs12->host_cr3))) + CC(!kvm_vcpu_is_legal_cr3(vcpu, vmcs12->host_cr3))) return -EINVAL; if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || @@ -3161,6 +3199,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) return 0; } +#ifdef CONFIG_KVM_HYPERV static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3188,6 +3227,7 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) return true; } +#endif static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) { @@ -3279,6 +3319,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) { +#ifdef CONFIG_KVM_HYPERV /* * Note: nested_get_evmcs_page() also updates 'vp_assist_page' copy * in 'struct kvm_vcpu_hv' in case eVMCS is in use, this is mandatory @@ -3295,6 +3336,7 @@ static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) return false; } +#endif if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu)) return false; @@ -3538,7 +3580,7 @@ vmentry_fail_vmexit: load_vmcs12_host_state(vcpu, vmcs12); vmcs12->vm_exit_reason = exit_reason.full; - if (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx)) vmx->nested.need_vmcs12_to_shadow_sync = true; return NVMX_VMENTRY_VMEXIT; } @@ -3569,7 +3611,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (CC(evmptrld_status == EVMPTRLD_VMFAIL)) return nested_vmx_failInvalid(vcpu); - if (CC(!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) && + if (CC(!nested_vmx_is_evmptr12_valid(vmx) && vmx->nested.current_vmptr == INVALID_GPA)) return nested_vmx_failInvalid(vcpu); @@ -3584,8 +3626,10 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (CC(vmcs12->hdr.shadow_vmcs)) return nested_vmx_failInvalid(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { - copy_enlightened_to_vmcs12(vmx, vmx->nested.hv_evmcs->hv_clean_fields); + if (nested_vmx_is_evmptr12_valid(vmx)) { + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); + + copy_enlightened_to_vmcs12(vmx, evmcs->hv_clean_fields); /* Enlightened VMCS doesn't have launch state */ vmcs12->launch_state = !launch; } else if (enable_shadow_vmcs) { @@ -4329,11 +4373,11 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); vmx->nested.need_sync_vmcs02_to_vmcs12_rare = - !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr); + !nested_vmx_is_evmptr12_valid(vmx); vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12); @@ -4732,6 +4776,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, /* trying to cancel vmlaunch/vmresume is a bug */ WARN_ON_ONCE(vmx->nested.nested_run_pending); +#ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { /* * KVM_REQ_GET_NESTED_STATE_PAGES is also used to map @@ -4741,6 +4786,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, */ (void)nested_get_evmcs_page(vcpu); } +#endif /* Service pending TLB flush requests for L2 before switching to L1. */ kvm_service_local_tlb_flush_requests(vcpu); @@ -4854,7 +4900,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, } if ((vm_exit_reason != -1) && - (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))) + (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx))) vmx->nested.need_vmcs12_to_shadow_sync = true; /* in case we halted in L2 */ @@ -4980,6 +5026,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, else *ret = off; + *ret = vmx_get_untagged_addr(vcpu, *ret, 0); /* Long mode: #GP(0)/#SS(0) if the memory address is in a * non-canonical form. This is the only check on the memory * destination for long mode! @@ -5292,18 +5339,7 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) if (vmptr == vmx->nested.vmxon_ptr) return nested_vmx_fail(vcpu, VMXERR_VMCLEAR_VMXON_POINTER); - /* - * When Enlightened VMEntry is enabled on the calling CPU we treat - * memory area pointer by vmptr as Enlightened VMCS (as there's no good - * way to distinguish it from VMCS12) and we must not corrupt it by - * writing to the non-existent 'launch_state' field. The area doesn't - * have to be the currently active EVMCS on the calling CPU and there's - * nothing KVM has to do to transition it from 'active' to 'non-active' - * state. It is possible that the area will stay mapped as - * vmx->nested.hv_evmcs but this shouldn't be a problem. - */ - if (likely(!guest_cpuid_has_evmcs(vcpu) || - !evmptr_is_valid(nested_get_evmptr(vcpu)))) { + if (likely(!nested_evmcs_handle_vmclear(vcpu, vmptr))) { if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vcpu); @@ -5320,8 +5356,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) vmptr + offsetof(struct vmcs12, launch_state), &zero, sizeof(zero)); - } else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) { - nested_release_evmcs(vcpu); } return nested_vmx_succeed(vcpu); @@ -5360,7 +5394,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) /* Decode instruction info and find the field to read */ field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf)); - if (!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + if (!nested_vmx_is_evmptr12_valid(vmx)) { /* * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA, * any VMREAD sets the ALU flags for VMfailInvalid. @@ -5398,7 +5432,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); /* Read the field, zero-extended to a u64 value */ - value = evmcs_read_any(vmx->nested.hv_evmcs, field, offset); + value = evmcs_read_any(nested_vmx_evmcs(vmx), field, offset); } /* @@ -5586,7 +5620,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_VMXON_POINTER); /* Forbid normal VMPTRLD if Enlightened version was used */ - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) return 1; if (vmx->nested.current_vmptr != vmptr) { @@ -5649,7 +5683,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) if (!nested_vmx_check_permission(vcpu)) return 1; - if (unlikely(evmptr_is_valid(to_vmx(vcpu)->nested.hv_evmcs_vmptr))) + if (unlikely(nested_vmx_is_evmptr12_valid(to_vmx(vcpu)))) return 1; if (get_vmx_mem_address(vcpu, exit_qual, instr_info, @@ -5797,6 +5831,10 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) vpid02 = nested_get_vpid02(vcpu); switch (type) { case VMX_VPID_EXTENT_INDIVIDUAL_ADDR: + /* + * LAM doesn't apply to addresses that are inputs to TLB + * invalidation. + */ if (!operand.vpid || is_noncanonical_address(operand.gla, vcpu)) return nested_vmx_fail(vcpu, @@ -6208,11 +6246,13 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, * Handle L2's bus locks in L0 directly. */ return true; +#ifdef CONFIG_KVM_HYPERV case EXIT_REASON_VMCALL: /* Hyper-V L2 TLB flush hypercall is handled by L0 */ return guest_hv_cpuid_has_l2_tlb_flush(vcpu) && nested_evmcs_l2_tlb_flush_enabled(vcpu) && kvm_hv_is_tlb_flush_hcall(vcpu); +#endif default: break; } @@ -6331,7 +6371,7 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, * If if it were, XSS would have to be checked against * the XSS exit bitmap in vmcs12. */ - return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); + return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_XSAVES); case EXIT_REASON_UMWAIT: case EXIT_REASON_TPAUSE: return nested_cpu_has2(vmcs12, @@ -6426,7 +6466,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, vmx = to_vmx(vcpu); vmcs12 = get_vmcs12(vcpu); - if (nested_vmx_allowed(vcpu) && + if (guest_can_use(vcpu, X86_FEATURE_VMX) && (vmx->nested.vmxon || vmx->nested.smm.vmxon)) { kvm_state.hdr.vmx.vmxon_pa = vmx->nested.vmxon_ptr; kvm_state.hdr.vmx.vmcs12_pa = vmx->nested.current_vmptr; @@ -6435,7 +6475,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, kvm_state.size += sizeof(user_vmx_nested_state->vmcs12); /* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */ - if (vmx->nested.hv_evmcs_vmptr != EVMPTR_INVALID) + if (nested_vmx_is_evmptr12_set(vmx)) kvm_state.flags |= KVM_STATE_NESTED_EVMCS; if (is_guest_mode(vcpu) && @@ -6491,7 +6531,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, } else { copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu)); if (!vmx->nested.need_vmcs12_to_shadow_sync) { - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) /* * L1 hypervisor is not obliged to keep eVMCS * clean fields data always up-to-date while @@ -6561,13 +6601,13 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, * code was changed such that flag signals vmcs12 should * be copied into eVMCS in guest memory. * - * To preserve backwards compatability, allow user + * To preserve backwards compatibility, allow user * to set this flag even when there is no VMXON region. */ if (kvm_state->flags & ~KVM_STATE_NESTED_EVMCS) return -EINVAL; } else { - if (!nested_vmx_allowed(vcpu)) + if (!guest_can_use(vcpu, X86_FEATURE_VMX)) return -EINVAL; if (!page_address_valid(vcpu, kvm_state->hdr.vmx.vmxon_pa)) @@ -6601,7 +6641,8 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; if ((kvm_state->flags & KVM_STATE_NESTED_EVMCS) && - (!nested_vmx_allowed(vcpu) || !vmx->nested.enlightened_vmcs_enabled)) + (!guest_can_use(vcpu, X86_FEATURE_VMX) || + !vmx->nested.enlightened_vmcs_enabled)) return -EINVAL; vmx_leave_nested(vcpu); @@ -6631,6 +6672,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; set_current_vmptr(vmx, kvm_state->hdr.vmx.vmcs12_pa); +#ifdef CONFIG_KVM_HYPERV } else if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) { /* * nested_vmx_handle_enlightened_vmptrld() cannot be called @@ -6640,6 +6682,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, */ vmx->nested.hv_evmcs_vmptr = EVMPTR_MAP_PENDING; kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); +#endif } else { return -EINVAL; } @@ -6874,7 +6917,7 @@ static void nested_vmx_setup_secondary_ctls(u32 ept_caps, SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_ENABLE_VMFUNC | SECONDARY_EXEC_RDSEED_EXITING | - SECONDARY_EXEC_XSAVES | + SECONDARY_EXEC_ENABLE_XSAVES | SECONDARY_EXEC_TSC_SCALING | SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; @@ -7095,7 +7138,9 @@ struct kvm_x86_nested_ops vmx_nested_ops = { .set_state = vmx_set_nested_state, .get_nested_state_pages = vmx_get_nested_state_pages, .write_log_dirty = nested_vmx_write_pml_buffer, +#ifdef CONFIG_KVM_HYPERV .enable_evmcs = nested_enable_evmcs, .get_evmcs_version = nested_get_evmcs_version, .hv_inject_synthetic_vmexit_post_tlb_flush = vmx_hv_inject_synthetic_vmexit_post_tlb_flush, +#endif }; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 96952263b029..cce4e2aa30fb 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -3,6 +3,7 @@ #define __KVM_X86_VMX_NESTED_H #include "kvm_cache_regs.h" +#include "hyperv.h" #include "vmcs12.h" #include "vmx.h" @@ -57,7 +58,7 @@ static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu) /* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */ return vmx->nested.current_vmptr != -1ull || - vmx->nested.hv_evmcs_vmptr != EVMPTR_INVALID; + nested_vmx_is_evmptr12_set(vmx); } static inline u16 nested_get_vpid02(struct kvm_vcpu *vcpu) @@ -168,7 +169,7 @@ static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12) static inline bool nested_cpu_has_xsaves(struct vmcs12 *vmcs12) { - return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); + return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_XSAVES); } static inline bool nested_cpu_has_pml(struct vmcs12 *vmcs12) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 80c769c58a87..a6216c874729 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -22,23 +22,51 @@ #define MSR_PMC_FULL_WIDTH_BIT (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0) +enum intel_pmu_architectural_events { + /* + * The order of the architectural events matters as support for each + * event is enumerated via CPUID using the index of the event. + */ + INTEL_ARCH_CPU_CYCLES, + INTEL_ARCH_INSTRUCTIONS_RETIRED, + INTEL_ARCH_REFERENCE_CYCLES, + INTEL_ARCH_LLC_REFERENCES, + INTEL_ARCH_LLC_MISSES, + INTEL_ARCH_BRANCHES_RETIRED, + INTEL_ARCH_BRANCHES_MISPREDICTED, + + NR_REAL_INTEL_ARCH_EVENTS, + + /* + * Pseudo-architectural event used to implement IA32_FIXED_CTR2, a.k.a. + * TSC reference cycles. The architectural reference cycles event may + * or may not actually use the TSC as the reference, e.g. might use the + * core crystal clock or the bus clock (yeah, "architectural"). + */ + PSEUDO_ARCH_REFERENCE_CYCLES = NR_REAL_INTEL_ARCH_EVENTS, + NR_INTEL_ARCH_EVENTS, +}; + static struct { u8 eventsel; u8 unit_mask; } const intel_arch_events[] = { - [0] = { 0x3c, 0x00 }, - [1] = { 0xc0, 0x00 }, - [2] = { 0x3c, 0x01 }, - [3] = { 0x2e, 0x4f }, - [4] = { 0x2e, 0x41 }, - [5] = { 0xc4, 0x00 }, - [6] = { 0xc5, 0x00 }, - /* The above index must match CPUID 0x0A.EBX bit vector */ - [7] = { 0x00, 0x03 }, + [INTEL_ARCH_CPU_CYCLES] = { 0x3c, 0x00 }, + [INTEL_ARCH_INSTRUCTIONS_RETIRED] = { 0xc0, 0x00 }, + [INTEL_ARCH_REFERENCE_CYCLES] = { 0x3c, 0x01 }, + [INTEL_ARCH_LLC_REFERENCES] = { 0x2e, 0x4f }, + [INTEL_ARCH_LLC_MISSES] = { 0x2e, 0x41 }, + [INTEL_ARCH_BRANCHES_RETIRED] = { 0xc4, 0x00 }, + [INTEL_ARCH_BRANCHES_MISPREDICTED] = { 0xc5, 0x00 }, + [PSEUDO_ARCH_REFERENCE_CYCLES] = { 0x00, 0x03 }, }; /* mapping between fixed pmc index and intel_arch_events array */ -static int fixed_pmc_events[] = {1, 0, 7}; +static int fixed_pmc_events[] = { + [0] = INTEL_ARCH_INSTRUCTIONS_RETIRED, + [1] = INTEL_ARCH_CPU_CYCLES, + [2] = PSEUDO_ARCH_REFERENCE_CYCLES, +}; static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) { @@ -80,16 +108,18 @@ static bool intel_hw_event_available(struct kvm_pmc *pmc) u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; int i; - for (i = 0; i < ARRAY_SIZE(intel_arch_events); i++) { + BUILD_BUG_ON(ARRAY_SIZE(intel_arch_events) != NR_INTEL_ARCH_EVENTS); + + /* + * Disallow events reported as unavailable in guest CPUID. Note, this + * doesn't apply to pseudo-architectural events. + */ + for (i = 0; i < NR_REAL_INTEL_ARCH_EVENTS; i++) { if (intel_arch_events[i].eventsel != event_select || intel_arch_events[i].unit_mask != unit_mask) continue; - /* disable event that reported as not present by cpuid */ - if ((i < 7) && !(pmu->available_event_types & (1 << i))) - return false; - - break; + return pmu->available_event_types & BIT(i); } return true; @@ -406,12 +436,10 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated && !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; - pmc->counter += data - pmc_read_counter(pmc); - pmc_update_sample_period(pmc); + pmc_write_counter(pmc, data); break; } else if ((pmc = get_fixed_pmc(pmu, msr))) { - pmc->counter += data - pmc_read_counter(pmc); - pmc_update_sample_period(pmc); + pmc_write_counter(pmc, data); break; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { reserved_bits = pmu->reserved_bits; @@ -438,16 +466,17 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static void setup_fixed_pmc_eventsel(struct kvm_pmu *pmu) { - size_t size = ARRAY_SIZE(fixed_pmc_events); - struct kvm_pmc *pmc; - u32 event; int i; + BUILD_BUG_ON(ARRAY_SIZE(fixed_pmc_events) != KVM_PMC_MAX_FIXED); + for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { - pmc = &pmu->fixed_counters[i]; - event = fixed_pmc_events[array_index_nospec(i, size)]; + int index = array_index_nospec(i, KVM_PMC_MAX_FIXED); + struct kvm_pmc *pmc = &pmu->fixed_counters[index]; + u32 event = fixed_pmc_events[index]; + pmc->eventsel = (intel_arch_events[event].unit_mask << 8) | - intel_arch_events[event].eventsel; + intel_arch_events[event].eventsel; } } @@ -508,10 +537,8 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) if (pmu->version == 1) { pmu->nr_arch_fixed_counters = 0; } else { - pmu->nr_arch_fixed_counters = - min3(ARRAY_SIZE(fixed_pmc_events), - (size_t) edx.split.num_counters_fixed, - (size_t)kvm_pmu_cap.num_counters_fixed); + pmu->nr_arch_fixed_counters = min_t(int, edx.split.num_counters_fixed, + kvm_pmu_cap.num_counters_fixed); edx.split.bit_width_fixed = min_t(int, edx.split.bit_width_fixed, kvm_pmu_cap.bit_width_fixed); pmu->counter_bitmask[KVM_PMC_FIXED] = @@ -603,26 +630,6 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) static void intel_pmu_reset(struct kvm_vcpu *vcpu) { - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - struct kvm_pmc *pmc = NULL; - int i; - - for (i = 0; i < KVM_INTEL_PMC_MAX_GENERIC; i++) { - pmc = &pmu->gp_counters[i]; - - pmc_stop_counter(pmc); - pmc->counter = pmc->prev_counter = pmc->eventsel = 0; - } - - for (i = 0; i < KVM_PMC_MAX_FIXED; i++) { - pmc = &pmu->fixed_counters[i]; - - pmc_stop_counter(pmc); - pmc->counter = pmc->prev_counter = 0; - } - - pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0; - intel_pmu_release_guest_lbr_event(vcpu); } diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index 3e822e582497..6fef01e0536e 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -37,6 +37,7 @@ static int sgx_get_encls_gva(struct kvm_vcpu *vcpu, unsigned long offset, if (!IS_ALIGNED(*gva, alignment)) { fault = true; } else if (likely(is_64_bit_mode(vcpu))) { + *gva = vmx_get_untagged_addr(vcpu, *gva, 0); fault = is_noncanonical_address(*gva, vcpu); } else { *gva &= 0xffffffff; diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index be275a0410a8..906ecd001511 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -289,7 +289,7 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL) RET .Lfixup: - cmpb $0, kvm_rebooting + cmpb $0, _ASM_RIP(kvm_rebooting) jne .Lvmfail ud2 .Lvmfail: diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index b483a8baaacf..1111d9d08903 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -41,13 +41,12 @@ #include <asm/idtentry.h> #include <asm/io.h> #include <asm/irq_remapping.h> -#include <asm/kexec.h> +#include <asm/reboot.h> #include <asm/perf_event.h> #include <asm/mmu_context.h> #include <asm/mshyperv.h> #include <asm/mwait.h> #include <asm/spec-ctrl.h> -#include <asm/virtext.h> #include <asm/vmx.h> #include "capabilities.h" @@ -67,6 +66,7 @@ #include "vmx.h" #include "x86.h" #include "smm.h" +#include "vmx_onhyperv.h" MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); @@ -83,28 +83,28 @@ bool __read_mostly enable_vpid = 1; module_param_named(vpid, enable_vpid, bool, 0444); static bool __read_mostly enable_vnmi = 1; -module_param_named(vnmi, enable_vnmi, bool, S_IRUGO); +module_param_named(vnmi, enable_vnmi, bool, 0444); bool __read_mostly flexpriority_enabled = 1; -module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO); +module_param_named(flexpriority, flexpriority_enabled, bool, 0444); bool __read_mostly enable_ept = 1; -module_param_named(ept, enable_ept, bool, S_IRUGO); +module_param_named(ept, enable_ept, bool, 0444); bool __read_mostly enable_unrestricted_guest = 1; module_param_named(unrestricted_guest, - enable_unrestricted_guest, bool, S_IRUGO); + enable_unrestricted_guest, bool, 0444); bool __read_mostly enable_ept_ad_bits = 1; -module_param_named(eptad, enable_ept_ad_bits, bool, S_IRUGO); +module_param_named(eptad, enable_ept_ad_bits, bool, 0444); static bool __read_mostly emulate_invalid_guest_state = true; -module_param(emulate_invalid_guest_state, bool, S_IRUGO); +module_param(emulate_invalid_guest_state, bool, 0444); static bool __read_mostly fasteoi = 1; -module_param(fasteoi, bool, S_IRUGO); +module_param(fasteoi, bool, 0444); -module_param(enable_apicv, bool, S_IRUGO); +module_param(enable_apicv, bool, 0444); bool __read_mostly enable_ipiv = true; module_param(enable_ipiv, bool, 0444); @@ -115,10 +115,10 @@ module_param(enable_ipiv, bool, 0444); * use VMX instructions. */ static bool __read_mostly nested = 1; -module_param(nested, bool, S_IRUGO); +module_param(nested, bool, 0444); bool __read_mostly enable_pml = 1; -module_param_named(pml, enable_pml, bool, S_IRUGO); +module_param_named(pml, enable_pml, bool, 0444); static bool __read_mostly error_on_inconsistent_vmcs_config = true; module_param(error_on_inconsistent_vmcs_config, bool, 0444); @@ -237,9 +237,6 @@ static const struct { #define L1D_CACHE_ORDER 4 static void *vmx_l1d_flush_pages; -/* Control for disabling CPU Fill buffer clear */ -static bool __read_mostly vmx_fb_clear_ctrl_available; - static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) { struct page *page; @@ -255,14 +252,9 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) return 0; } - if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) { - u64 msr; - - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr); - if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) { - l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; - return 0; - } + if (host_arch_capabilities & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) { + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; + return 0; } /* If set to auto use the default l1tf mitigation method */ @@ -366,22 +358,9 @@ static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp) static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) { if (WARN_ON_ONCE(l1tf_vmx_mitigation >= ARRAY_SIZE(vmentry_l1d_param))) - return sprintf(s, "???\n"); - - return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); -} - -static void vmx_setup_fb_clear_ctrl(void) -{ - u64 msr; + return sysfs_emit(s, "???\n"); - if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES) && - !boot_cpu_has_bug(X86_BUG_MDS) && - !boot_cpu_has_bug(X86_BUG_TAA)) { - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr); - if (msr & ARCH_CAP_FB_CLEAR_CTRL) - vmx_fb_clear_ctrl_available = true; - } + return sysfs_emit(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); } static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) @@ -409,7 +388,9 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - vmx->disable_fb_clear = vmx_fb_clear_ctrl_available; + vmx->disable_fb_clear = (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) && + !boot_cpu_has_bug(X86_BUG_MDS) && + !boot_cpu_has_bug(X86_BUG_TAA); /* * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS @@ -543,22 +524,14 @@ module_param(enlightened_vmcs, bool, 0444); static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) { struct hv_enlightened_vmcs *evmcs; - struct hv_partition_assist_pg **p_hv_pa_pg = - &to_kvm_hv(vcpu->kvm)->hv_pa_pg; - /* - * Synthetic VM-Exit is not enabled in current code and so All - * evmcs in singe VM shares same assist page. - */ - if (!*p_hv_pa_pg) - *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT); + hpa_t partition_assist_page = hv_get_partition_assist_page(vcpu); - if (!*p_hv_pa_pg) + if (partition_assist_page == INVALID_PAGE) return -ENOMEM; evmcs = (struct hv_enlightened_vmcs *)to_vmx(vcpu)->loaded_vmcs->vmcs; - evmcs->partition_assist_page = - __pa(*p_hv_pa_pg); + evmcs->partition_assist_page = partition_assist_page; evmcs->hv_vm_id = (unsigned long)vcpu->kvm; evmcs->hv_enlightenments_control.nested_flush_hypercall = 1; @@ -754,17 +727,51 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, return ret; } -#ifdef CONFIG_KEXEC_CORE -static void crash_vmclear_local_loaded_vmcss(void) +/* + * Disable VMX and clear CR4.VMXE (even if VMXOFF faults) + * + * Note, VMXOFF causes a #UD if the CPU is !post-VMXON, but it's impossible to + * atomically track post-VMXON state, e.g. this may be called in NMI context. + * Eat all faults as all other faults on VMXOFF faults are mode related, i.e. + * faults are guaranteed to be due to the !post-VMXON check unless the CPU is + * magically in RM, VM86, compat mode, or at CPL>0. + */ +static int kvm_cpu_vmxoff(void) +{ + asm goto("1: vmxoff\n\t" + _ASM_EXTABLE(1b, %l[fault]) + ::: "cc", "memory" : fault); + + cr4_clear_bits(X86_CR4_VMXE); + return 0; + +fault: + cr4_clear_bits(X86_CR4_VMXE); + return -EIO; +} + +static void vmx_emergency_disable(void) { int cpu = raw_smp_processor_id(); struct loaded_vmcs *v; + kvm_rebooting = true; + + /* + * Note, CR4.VMXE can be _cleared_ in NMI context, but it can only be + * set in task context. If this races with VMX is disabled by an NMI, + * VMCLEAR and VMXOFF may #UD, but KVM will eat those faults due to + * kvm_rebooting set. + */ + if (!(__read_cr4() & X86_CR4_VMXE)) + return; + list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu), loaded_vmcss_on_cpu_link) vmcs_clear(v->vmcs); + + kvm_cpu_vmxoff(); } -#endif /* CONFIG_KEXEC_CORE */ static void __loaded_vmcs_clear(void *arg) { @@ -1643,8 +1650,8 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) return 0; } -static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +static int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { /* * Emulation of instructions in SGX enclaves is impossible as RIP does @@ -1655,9 +1662,9 @@ static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, */ if (to_vmx(vcpu)->exit_reason.enclave_mode) { kvm_queue_exception(vcpu, UD_VECTOR); - return false; + return X86EMUL_PROPAGATE_FAULT; } - return true; + return X86EMUL_CONTINUE; } static int skip_emulated_instruction(struct kvm_vcpu *vcpu) @@ -1795,7 +1802,7 @@ static void vmx_inject_exception(struct kvm_vcpu *vcpu) * do generate error codes with bits 31:16 set, and so KVM's * ABI lets userspace shove in arbitrary 32-bit values. Drop * the upper bits to avoid VM-Fail, losing information that - * does't really exist is preferable to killing the VM. + * doesn't really exist is preferable to killing the VM. */ vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, (u16)ex->error_code); intr_info |= INTR_INFO_DELIVER_CODE_MASK; @@ -1899,25 +1906,14 @@ u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) return kvm_caps.default_tsc_scaling_ratio; } -static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu) { - vmcs_write64(TSC_OFFSET, offset); + vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); } -static void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier) +static void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu) { - vmcs_write64(TSC_MULTIPLIER, multiplier); -} - -/* - * nested_vmx_allowed() checks whether a guest should be allowed to use VMX - * instructions and MSRs (i.e., nested VMX). Nested VMX is disabled for - * all guests if the "nested" module option is off, and can also be disabled - * for a single guest by disabling its VMX cpuid bit. - */ -bool nested_vmx_allowed(struct kvm_vcpu *vcpu) -{ - return nested && guest_cpuid_has(vcpu, X86_FEATURE_VMX); + vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); } /* @@ -2047,11 +2043,12 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) [msr_info->index - MSR_IA32_SGXLEPUBKEYHASH0]; break; case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: - if (!nested_vmx_allowed(vcpu)) + if (!guest_can_use(vcpu, X86_FEATURE_VMX)) return 1; if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, &msr_info->data)) return 1; +#ifdef CONFIG_KVM_HYPERV /* * Enlightened VMCS v1 doesn't have certain VMCS fields but * instead of just ignoring the features, different Hyper-V @@ -2062,6 +2059,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated && guest_cpuid_has_evmcs(vcpu)) nested_evmcs_filter_control_msr(vcpu, msr_info->index, &msr_info->data); +#endif break; case MSR_IA32_RTIT_CTL: if (!vmx_pt_mode_is_host_guest()) @@ -2355,7 +2353,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!msr_info->host_initiated) return 1; /* they are read-only */ - if (!nested_vmx_allowed(vcpu)) + if (!guest_can_use(vcpu, X86_FEATURE_VMX)) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); case MSR_IA32_RTIT_CTL: @@ -2729,11 +2727,11 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf, return 0; } -static bool kvm_is_vmx_supported(void) +static bool __kvm_is_vmx_supported(void) { - int cpu = raw_smp_processor_id(); + int cpu = smp_processor_id(); - if (!cpu_has_vmx()) { + if (!(cpuid_ecx(1) & feature_bit(VMX))) { pr_err("VMX not supported by CPU %d\n", cpu); return false; } @@ -2747,13 +2745,24 @@ static bool kvm_is_vmx_supported(void) return true; } +static bool kvm_is_vmx_supported(void) +{ + bool supported; + + migrate_disable(); + supported = __kvm_is_vmx_supported(); + migrate_enable(); + + return supported; +} + static int vmx_check_processor_compat(void) { int cpu = raw_smp_processor_id(); struct vmcs_config vmcs_conf; struct vmx_capability vmx_cap; - if (!kvm_is_vmx_supported()) + if (!__kvm_is_vmx_supported()) return -EIO; if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) { @@ -2775,7 +2784,7 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer) cr4_set_bits(X86_CR4_VMXE); - asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" + asm goto("1: vmxon %[vmxon_pointer]\n\t" _ASM_EXTABLE(1b, %l[fault]) : : [vmxon_pointer] "m"(vmxon_pointer) : : fault); @@ -2833,7 +2842,7 @@ static void vmx_hardware_disable(void) { vmclear_local_loaded_vmcss(); - if (cpu_vmxoff()) + if (kvm_cpu_vmxoff()) kvm_spurious_fault(); hv_reset_evmcs(); @@ -3071,13 +3080,6 @@ static void enter_rmode(struct kvm_vcpu *vcpu) vmx->rmode.vm86_active = 1; - /* - * Very old userspace does not call KVM_SET_TSS_ADDR before entering - * vcpu. Warn the user that an update is overdue. - */ - if (!kvm_vmx->tss_addr) - pr_warn_once("KVM_SET_TSS_ADDR needs to be called before running vCPU\n"); - vmx_segment_cache_clear(vmx); vmcs_writel(GUEST_TR_BASE, kvm_vmx->tss_addr); @@ -3350,7 +3352,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) vmx->emulation_required = vmx_emulation_required(vcpu); } -static int vmx_get_max_tdp_level(void) +static int vmx_get_max_ept_level(void) { if (cpu_has_vmx_ept_5levels()) return 5; @@ -3393,7 +3395,8 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, update_guest_cr3 = false; vmx_ept_load_pdptrs(vcpu); } else { - guest_cr3 = root_hpa | kvm_get_active_pcid(vcpu); + guest_cr3 = root_hpa | kvm_get_active_pcid(vcpu) | + kvm_get_active_cr3_lam_bits(vcpu); } if (update_guest_cr3) @@ -4553,16 +4556,19 @@ vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control, * based on a single guest CPUID bit, with a dedicated feature bit. This also * verifies that the control is actually supported by KVM and hardware. */ -#define vmx_adjust_sec_exec_control(vmx, exec_control, name, feat_name, ctrl_name, exiting) \ -({ \ - bool __enabled; \ - \ - if (cpu_has_vmx_##name()) { \ - __enabled = guest_cpuid_has(&(vmx)->vcpu, \ - X86_FEATURE_##feat_name); \ - vmx_adjust_secondary_exec_control(vmx, exec_control, \ - SECONDARY_EXEC_##ctrl_name, __enabled, exiting); \ - } \ +#define vmx_adjust_sec_exec_control(vmx, exec_control, name, feat_name, ctrl_name, exiting) \ +({ \ + struct kvm_vcpu *__vcpu = &(vmx)->vcpu; \ + bool __enabled; \ + \ + if (cpu_has_vmx_##name()) { \ + if (kvm_is_governed_feature(X86_FEATURE_##feat_name)) \ + __enabled = guest_can_use(__vcpu, X86_FEATURE_##feat_name); \ + else \ + __enabled = guest_cpuid_has(__vcpu, X86_FEATURE_##feat_name); \ + vmx_adjust_secondary_exec_control(vmx, exec_control, SECONDARY_EXEC_##ctrl_name,\ + __enabled, exiting); \ + } \ }) /* More macro magic for ENABLE_/opt-in versus _EXITING/opt-out controls. */ @@ -4622,19 +4628,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) if (!enable_pml || !atomic_read(&vcpu->kvm->nr_memslots_dirty_logging)) exec_control &= ~SECONDARY_EXEC_ENABLE_PML; - if (cpu_has_vmx_xsaves()) { - /* Exposing XSAVES only when XSAVE is exposed */ - bool xsaves_enabled = - boot_cpu_has(X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVES); - - vcpu->arch.xsaves_enabled = xsaves_enabled; - - vmx_adjust_secondary_exec_control(vmx, &exec_control, - SECONDARY_EXEC_XSAVES, - xsaves_enabled, false); - } + vmx_adjust_sec_exec_feature(vmx, &exec_control, xsaves, XSAVES); /* * RDPID is also gated by ENABLE_RDTSCP, turn on the control if either @@ -4653,6 +4647,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) SECONDARY_EXEC_ENABLE_RDTSCP, rdpid_or_rdtscp_enabled, false); } + vmx_adjust_sec_exec_feature(vmx, &exec_control, invpcid, INVPCID); vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdrand, RDRAND); @@ -4834,7 +4829,10 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx->nested.posted_intr_nv = -1; vmx->nested.vmxon_ptr = INVALID_GPA; vmx->nested.current_vmptr = INVALID_GPA; + +#ifdef CONFIG_KVM_HYPERV vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; +#endif vcpu->arch.microcode_version = 0x100000000ULL; vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; @@ -5783,7 +5781,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) * would also use advanced VM-exit information for EPT violations to * reconstruct the page fault error code. */ - if (unlikely(allow_smaller_maxphyaddr && kvm_vcpu_is_illegal_gpa(vcpu, gpa))) + if (unlikely(allow_smaller_maxphyaddr && !kvm_vcpu_is_legal_gpa(vcpu, gpa))) return kvm_emulate_instruction(vcpu, 0); return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); @@ -5793,7 +5791,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { gpa_t gpa; - if (!vmx_can_emulate_instruction(vcpu, EMULTYPE_PF, NULL, 0)) + if (vmx_check_emulate_instruction(vcpu, EMULTYPE_PF, NULL, 0)) return 1; /* @@ -6758,10 +6756,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) return; /* - * Grab the memslot so that the hva lookup for the mmu_notifier retry - * is guaranteed to use the same memslot as the pfn lookup, i.e. rely - * on the pfn lookup's validation of the memslot to ensure a valid hva - * is used for the retry check. + * Explicitly grab the memslot using KVM's internal slot ID to ensure + * KVM doesn't unintentionally grab a userspace memslot. It _should_ + * be impossible for userspace to create a memslot for the APIC when + * APICv is enabled, but paranoia won't hurt in this case. */ slot = id_to_memslot(slots, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT); if (!slot || slot->flags & KVM_MEMSLOT_INVALID) @@ -6786,8 +6784,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) return; read_lock(&vcpu->kvm->mmu_lock); - if (mmu_invalidate_retry_hva(kvm, mmu_seq, - gfn_to_hva_memslot(slot, gfn))) { + if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) { kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); read_unlock(&vcpu->kvm->mmu_lock); goto out; @@ -6796,8 +6793,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) vmcs_write64(APIC_ACCESS_ADDR, pfn_to_hpa(pfn)); read_unlock(&vcpu->kvm->mmu_lock); - vmx_flush_tlb_current(vcpu); - + /* + * No need for a manual TLB flush at this point, KVM has already done a + * flush if there were SPTEs pointing at the previous page. + */ out: /* * Do not pin apic access page in memory, the MMU notifier @@ -6911,7 +6910,7 @@ static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } -static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) +static void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7243,13 +7242,20 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, flags); vcpu->arch.cr2 = native_read_cr2(); + vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET; + + vmx->idt_vectoring_info = 0; vmx_enable_fb_clear(vmx); - if (unlikely(vmx->fail)) + if (unlikely(vmx->fail)) { vmx->exit_reason.full = 0xdead; - else - vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON); + goto out; + } + + vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON); + if (likely(!vmx->exit_reason.failed_vmentry)) + vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI && is_nmi(vmx_get_intr_info(vcpu))) { @@ -7258,6 +7264,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, kvm_after_interrupt(vcpu); } +out: guest_state_exit_irqoff(); } @@ -7379,8 +7386,6 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) loadsegment(es, __USER_DS); #endif - vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET; - pt_guest_exit(vmx); kvm_load_host_xsave_state(vcpu); @@ -7397,17 +7402,12 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->nested.nested_run_pending = 0; } - vmx->idt_vectoring_info = 0; - if (unlikely(vmx->fail)) return EXIT_FASTPATH_NONE; if (unlikely((u16)vmx->exit_reason.basic == EXIT_REASON_MCE_DURING_VMENTRY)) kvm_machine_check(); - if (likely(!vmx->exit_reason.failed_vmentry)) - vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); - trace_kvm_exit(vcpu, KVM_ISA_VMX); if (unlikely(vmx->exit_reason.failed_vmentry)) @@ -7577,8 +7577,6 @@ static int vmx_vm_init(struct kvm *kvm) static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { - u8 cache; - /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in * memory aliases with conflicting memory types and sometimes MCEs. * We have to be careful as to what are honored and when. @@ -7605,11 +7603,10 @@ static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) if (kvm_read_cr0_bits(vcpu, X86_CR0_CD)) { if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) - cache = MTRR_TYPE_WRBACK; + return MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT; else - cache = MTRR_TYPE_UNCACHABLE; - - return (cache << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; + return (MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT) | + VMX_EPT_IPAT_BIT; } return kvm_mtrr_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT; @@ -7675,6 +7672,9 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) cr4_fixed1_update(X86_CR4_UMIP, ecx, feature_bit(UMIP)); cr4_fixed1_update(X86_CR4_LA57, ecx, feature_bit(LA57)); + entry = kvm_find_cpuid_entry_index(vcpu, 0x7, 1); + cr4_fixed1_update(X86_CR4_LAM_SUP, eax, feature_bit(LAM)); + #undef cr4_fixed1_update } @@ -7751,8 +7751,17 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - /* xsaves_enabled is recomputed in vmx_compute_secondary_exec_control(). */ - vcpu->arch.xsaves_enabled = false; + /* + * XSAVES is effectively enabled if and only if XSAVE is also exposed + * to the guest. XSAVES depends on CR4.OSXSAVE, and CR4.OSXSAVE can be + * set if and only if XSAVE is supported. + */ + if (boot_cpu_has(X86_FEATURE_XSAVE) && + guest_cpuid_has(vcpu, X86_FEATURE_XSAVE)) + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_XSAVES); + + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VMX); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_LAM); vmx_setup_uret_msrs(vmx); @@ -7760,7 +7769,7 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmcs_set_secondary_exec_control(vmx, vmx_secondary_exec_control(vmx)); - if (nested_vmx_allowed(vcpu)) + if (guest_can_use(vcpu, X86_FEATURE_VMX)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; @@ -7769,7 +7778,7 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) ~(FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX); - if (nested_vmx_allowed(vcpu)) + if (guest_can_use(vcpu, X86_FEATURE_VMX)) nested_vmx_cr_fixed1_bits_update(vcpu); if (boot_cpu_has(X86_FEATURE_INTEL_PT) && @@ -8199,6 +8208,50 @@ static void vmx_vm_destroy(struct kvm *kvm) free_pages((unsigned long)kvm_vmx->pid_table, vmx_get_pid_table_order(kvm)); } +/* + * Note, the SDM states that the linear address is masked *after* the modified + * canonicality check, whereas KVM masks (untags) the address and then performs + * a "normal" canonicality check. Functionally, the two methods are identical, + * and when the masking occurs relative to the canonicality check isn't visible + * to software, i.e. KVM's behavior doesn't violate the SDM. + */ +gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags) +{ + int lam_bit; + unsigned long cr3_bits; + + if (flags & (X86EMUL_F_FETCH | X86EMUL_F_IMPLICIT | X86EMUL_F_INVLPG)) + return gva; + + if (!is_64_bit_mode(vcpu)) + return gva; + + /* + * Bit 63 determines if the address should be treated as user address + * or a supervisor address. + */ + if (!(gva & BIT_ULL(63))) { + cr3_bits = kvm_get_active_cr3_lam_bits(vcpu); + if (!(cr3_bits & (X86_CR3_LAM_U57 | X86_CR3_LAM_U48))) + return gva; + + /* LAM_U48 is ignored if LAM_U57 is set. */ + lam_bit = cr3_bits & X86_CR3_LAM_U57 ? 56 : 47; + } else { + if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_LAM_SUP)) + return gva; + + lam_bit = kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 56 : 47; + } + + /* + * Untag the address by sign-extending the lam_bit, but NOT to bit 63. + * Bit 63 is retained from the raw virtual address so that untagging + * doesn't change a user access to a supervisor access, and vice versa. + */ + return (sign_extend64(gva, lam_bit) & ~BIT_ULL(63)) | (gva & BIT_ULL(63)); +} + static struct kvm_x86_ops vmx_x86_ops __initdata = { .name = KBUILD_MODNAME, @@ -8276,7 +8329,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .set_apic_access_page_addr = vmx_set_apic_access_page_addr, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, - .apicv_post_state_restore = vmx_apicv_post_state_restore, + .apicv_pre_state_restore = vmx_apicv_pre_state_restore, .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, @@ -8331,7 +8384,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .enable_smi_window = vmx_enable_smi_window, #endif - .can_emulate_instruction = vmx_can_emulate_instruction, + .check_emulate_instruction = vmx_check_emulate_instruction, .apic_init_signal_blocked = vmx_apic_init_signal_blocked, .migrate_timers = vmx_migrate_timers, @@ -8339,6 +8392,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .complete_emulated_msr = kvm_complete_insn_gp, .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, + + .get_untagged_addr = vmx_get_untagged_addr, }; static unsigned int vmx_handle_intel_pt_intr(void) @@ -8526,7 +8581,7 @@ static __init int hardware_setup(void) */ vmx_setup_me_spte_mask(); - kvm_configure_mmu(enable_ept, 0, vmx_get_max_tdp_level(), + kvm_configure_mmu(enable_ept, 0, vmx_get_max_ept_level(), ept_caps_to_lpage_level(vmx_capability.ept)); /* @@ -8622,10 +8677,8 @@ static void __vmx_exit(void) { allow_smaller_maxphyaddr = false; -#ifdef CONFIG_KEXEC_CORE - RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); - synchronize_rcu(); -#endif + cpu_emergency_unregister_virt_callback(vmx_emergency_disable); + vmx_cleanup_l1d_flush(); } @@ -8666,18 +8719,14 @@ static int __init vmx_init(void) if (r) goto err_l1d_flush; - vmx_setup_fb_clear_ctrl(); - for_each_possible_cpu(cpu) { INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); pi_init_cpu(cpu); } -#ifdef CONFIG_KEXEC_CORE - rcu_assign_pointer(crash_vmclear_loaded_vmcss, - crash_vmclear_local_loaded_vmcss); -#endif + cpu_emergency_register_virt_callback(vmx_emergency_disable); + vmx_check_vmcs12_offsets(); /* diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 32384ba38499..e3b0985bb74a 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -241,9 +241,11 @@ struct nested_vmx { bool guest_mode; } smm; +#ifdef CONFIG_KVM_HYPERV gpa_t hv_evmcs_vmptr; struct kvm_host_map hv_evmcs_map; struct hv_enlightened_vmcs *hv_evmcs; +#endif }; struct vcpu_vmx { @@ -374,7 +376,6 @@ struct kvm_vmx { u64 *pid_table; }; -bool nested_vmx_allowed(struct kvm_vcpu *vcpu); void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, struct loaded_vmcs *buddy); int allocate_vpid(void); @@ -421,6 +422,8 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type); u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu); u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu); +gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); + static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool value) { @@ -562,7 +565,7 @@ static inline u8 vmx_get_rvi(void) SECONDARY_EXEC_APIC_REGISTER_VIRT | \ SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | \ SECONDARY_EXEC_SHADOW_VMCS | \ - SECONDARY_EXEC_XSAVES | \ + SECONDARY_EXEC_ENABLE_XSAVES | \ SECONDARY_EXEC_RDSEED_EXITING | \ SECONDARY_EXEC_RDRAND_EXITING | \ SECONDARY_EXEC_ENABLE_PML | \ @@ -746,14 +749,4 @@ static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu) return lapic_in_kernel(vcpu) && enable_ipiv; } -static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu) -{ - /* - * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and - * eVMCS has been explicitly enabled by userspace. - */ - return vcpu->arch.hyperv_enabled && - to_vmx(vcpu)->nested.enlightened_vmcs_enabled; -} - #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.c b/arch/x86/kvm/vmx/vmx_onhyperv.c new file mode 100644 index 000000000000..b9a8b91166d0 --- /dev/null +++ b/arch/x86/kvm/vmx/vmx_onhyperv.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "capabilities.h" +#include "vmx_onhyperv.h" + +DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); + +/* + * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption + * is: in case a feature has corresponding fields in eVMCS described and it was + * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a + * feature which has no corresponding eVMCS field, this likely means that KVM + * needs to be updated. + */ +#define evmcs_check_vmcs_conf(field, ctrl) \ + do { \ + typeof(vmcs_conf->field) unsupported; \ + \ + unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl; \ + if (unsupported) { \ + pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\ + (u64)unsupported); \ + vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl; \ + } \ + } \ + while (0) + +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) +{ + evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL); + evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL); + evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC); + evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC); + evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL); + evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL); +} diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.h b/arch/x86/kvm/vmx/vmx_onhyperv.h new file mode 100644 index 000000000000..eb48153bfd73 --- /dev/null +++ b/arch/x86/kvm/vmx/vmx_onhyperv.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ARCH_X86_KVM_VMX_ONHYPERV_H__ +#define __ARCH_X86_KVM_VMX_ONHYPERV_H__ + +#include <asm/hyperv-tlfs.h> +#include <asm/mshyperv.h> + +#include <linux/jump_label.h> + +#include "capabilities.h" +#include "hyperv_evmcs.h" +#include "vmcs12.h" + +#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs)) + +#if IS_ENABLED(CONFIG_HYPERV) + +DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); + +static __always_inline bool kvm_is_using_evmcs(void) +{ + return static_branch_unlikely(&__kvm_is_using_evmcs); +} + +static __always_inline int get_evmcs_offset(unsigned long field, + u16 *clean_field) +{ + int offset = evmcs_field_offset(field, clean_field); + + WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field); + return offset; +} + +static __always_inline void evmcs_write64(unsigned long field, u64 value) +{ + u16 clean_field; + int offset = get_evmcs_offset(field, &clean_field); + + if (offset < 0) + return; + + *(u64 *)((char *)current_evmcs + offset) = value; + + current_evmcs->hv_clean_fields &= ~clean_field; +} + +static __always_inline void evmcs_write32(unsigned long field, u32 value) +{ + u16 clean_field; + int offset = get_evmcs_offset(field, &clean_field); + + if (offset < 0) + return; + + *(u32 *)((char *)current_evmcs + offset) = value; + current_evmcs->hv_clean_fields &= ~clean_field; +} + +static __always_inline void evmcs_write16(unsigned long field, u16 value) +{ + u16 clean_field; + int offset = get_evmcs_offset(field, &clean_field); + + if (offset < 0) + return; + + *(u16 *)((char *)current_evmcs + offset) = value; + current_evmcs->hv_clean_fields &= ~clean_field; +} + +static __always_inline u64 evmcs_read64(unsigned long field) +{ + int offset = get_evmcs_offset(field, NULL); + + if (offset < 0) + return 0; + + return *(u64 *)((char *)current_evmcs + offset); +} + +static __always_inline u32 evmcs_read32(unsigned long field) +{ + int offset = get_evmcs_offset(field, NULL); + + if (offset < 0) + return 0; + + return *(u32 *)((char *)current_evmcs + offset); +} + +static __always_inline u16 evmcs_read16(unsigned long field) +{ + int offset = get_evmcs_offset(field, NULL); + + if (offset < 0) + return 0; + + return *(u16 *)((char *)current_evmcs + offset); +} + +static inline void evmcs_load(u64 phys_addr) +{ + struct hv_vp_assist_page *vp_ap = + hv_get_vp_assist_page(smp_processor_id()); + + if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) + vp_ap->nested_control.features.directhypercall = 1; + vp_ap->current_nested_vmcs = phys_addr; + vp_ap->enlighten_vmentry = 1; +} + +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); +#else /* !IS_ENABLED(CONFIG_HYPERV) */ +static __always_inline bool kvm_is_using_evmcs(void) { return false; } +static __always_inline void evmcs_write64(unsigned long field, u64 value) {} +static __always_inline void evmcs_write32(unsigned long field, u32 value) {} +static __always_inline void evmcs_write16(unsigned long field, u16 value) {} +static __always_inline u64 evmcs_read64(unsigned long field) { return 0; } +static __always_inline u32 evmcs_read32(unsigned long field) { return 0; } +static __always_inline u16 evmcs_read16(unsigned long field) { return 0; } +static inline void evmcs_load(u64 phys_addr) {} +#endif /* IS_ENABLED(CONFIG_HYPERV) */ + +#endif /* __ARCH_X86_KVM_VMX_ONHYPERV_H__ */ diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 33af7b4c6eb4..8060e5fc6dbd 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -6,7 +6,7 @@ #include <asm/vmx.h> -#include "hyperv.h" +#include "vmx_onhyperv.h" #include "vmcs.h" #include "../x86.h" @@ -94,7 +94,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT - asm_volatile_goto("1: vmread %[field], %[output]\n\t" + asm_goto_output("1: vmread %[field], %[output]\n\t" "jna %l[do_fail]\n\t" _ASM_EXTABLE(1b, %l[do_exception]) @@ -188,7 +188,7 @@ static __always_inline unsigned long vmcs_readl(unsigned long field) #define vmx_asm1(insn, op1, error_args...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \ + asm goto("1: " __stringify(insn) " %0\n\t" \ ".byte 0x2e\n\t" /* branch not taken hint */ \ "jna %l[error]\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ @@ -205,7 +205,7 @@ fault: \ #define vmx_asm2(insn, op1, op2, error_args...) \ do { \ - asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \ + asm goto("1: " __stringify(insn) " %1, %0\n\t" \ ".byte 0x2e\n\t" /* branch not taken hint */ \ "jna %l[error]\n\t" \ _ASM_EXTABLE(1b, %l[fault]) \ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c381770bcbf1..bf10a9073a09 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -25,6 +25,7 @@ #include "tss.h" #include "kvm_cache_regs.h" #include "kvm_emulate.h" +#include "mmu/page_track.h" #include "x86.h" #include "cpuid.h" #include "pmu.h" @@ -144,21 +145,21 @@ EXPORT_STATIC_CALL_GPL(kvm_x86_get_cs_db_l_bits); EXPORT_STATIC_CALL_GPL(kvm_x86_cache_reg); static bool __read_mostly ignore_msrs = 0; -module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); +module_param(ignore_msrs, bool, 0644); bool __read_mostly report_ignored_msrs = true; -module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR); +module_param(report_ignored_msrs, bool, 0644); EXPORT_SYMBOL_GPL(report_ignored_msrs); unsigned int min_timer_period_us = 200; -module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); +module_param(min_timer_period_us, uint, 0644); static bool __read_mostly kvmclock_periodic_sync = true; -module_param(kvmclock_periodic_sync, bool, S_IRUGO); +module_param(kvmclock_periodic_sync, bool, 0444); /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ static u32 __read_mostly tsc_tolerance_ppm = 250; -module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); +module_param(tsc_tolerance_ppm, uint, 0644); /* * lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables @@ -167,13 +168,13 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); * tuning, i.e. allows privileged userspace to set an exact advancement time. */ static int __read_mostly lapic_timer_advance_ns = -1; -module_param(lapic_timer_advance_ns, int, S_IRUGO | S_IWUSR); +module_param(lapic_timer_advance_ns, int, 0644); static bool __read_mostly vector_hashing = true; -module_param(vector_hashing, bool, S_IRUGO); +module_param(vector_hashing, bool, 0444); bool __read_mostly enable_vmware_backdoor = false; -module_param(enable_vmware_backdoor, bool, S_IRUGO); +module_param(enable_vmware_backdoor, bool, 0444); EXPORT_SYMBOL_GPL(enable_vmware_backdoor); /* @@ -185,7 +186,7 @@ static int __read_mostly force_emulation_prefix; module_param(force_emulation_prefix, int, 0644); int __read_mostly pi_inject_timer = -1; -module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR); +module_param(pi_inject_timer, bint, 0644); /* Enable/disable PMU virtualization */ bool __read_mostly enable_pmu = true; @@ -237,6 +238,9 @@ EXPORT_SYMBOL_GPL(enable_apicv); u64 __read_mostly host_xss; EXPORT_SYMBOL_GPL(host_xss); +u64 __read_mostly host_arch_capabilities; +EXPORT_SYMBOL_GPL(host_arch_capabilities); + const struct _kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_COUNTER(VM, mmu_shadow_zapped), @@ -958,7 +962,7 @@ void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned lon kvm_mmu_reset_context(vcpu); if (((cr0 ^ old_cr0) & X86_CR0_CD) && - kvm_arch_has_noncoherent_dma(vcpu->kvm) && + kvm_mmu_honors_guest_mtrrs(vcpu->kvm) && !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL); } @@ -1021,7 +1025,7 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); - if (vcpu->arch.xsaves_enabled && + if (guest_can_use(vcpu, X86_FEATURE_XSAVES) && vcpu->arch.ia32_xss != host_xss) wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss); } @@ -1052,7 +1056,7 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); - if (vcpu->arch.xsaves_enabled && + if (guest_can_use(vcpu, X86_FEATURE_XSAVES) && vcpu->arch.ia32_xss != host_xss) wrmsrl(MSR_IA32_XSS, host_xss); } @@ -1280,7 +1284,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) * stuff CR3, e.g. for RSM emulation, and there is no guarantee that * the current vCPU mode is accurate. */ - if (kvm_vcpu_is_illegal_gpa(vcpu, cr3)) + if (!kvm_vcpu_is_legal_cr3(vcpu, cr3)) return 1; if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3)) @@ -1500,6 +1504,8 @@ static unsigned num_msrs_to_save; static const u32 emulated_msrs_all[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, + +#ifdef CONFIG_KVM_HYPERV HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY, @@ -1517,6 +1523,7 @@ static const u32 emulated_msrs_all[] = { HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, HV_X64_MSR_SYNDBG_PENDING_BUFFER, +#endif MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, @@ -1620,12 +1627,7 @@ static bool kvm_is_immutable_feature_msr(u32 msr) static u64 kvm_get_arch_capabilities(void) { - u64 data = 0; - - if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) { - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data); - data &= KVM_SUPPORTED_ARCH_CAP; - } + u64 data = host_arch_capabilities & KVM_SUPPORTED_ARCH_CAP; /* * If nx_huge_pages is enabled, KVM's shadow paging will ensure that @@ -1780,6 +1782,10 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if ((efer ^ old_efer) & KVM_MMU_EFER_ROLE_BITS) kvm_mmu_reset_context(vcpu); + if (!static_cpu_has(X86_FEATURE_XSAVES) && + (efer & EFER_SVME)) + kvm_hv_xsaves_xsavec_maybe_warn(vcpu); + return 0; } @@ -2332,14 +2338,9 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_o if (kvm_write_guest(kvm, wall_clock, &version, sizeof(version))) return; - /* - * The guest calculates current wall clock time by adding - * system time (updated by kvm_guest_time_update below) to the - * wall clock specified here. We do the reverse here. - */ - wall_nsec = ktime_get_real_ns() - get_kvmclock_ns(kvm); + wall_nsec = kvm_get_wall_clock_epoch(kvm); - wc.nsec = do_div(wall_nsec, 1000000000); + wc.nsec = do_div(wall_nsec, NSEC_PER_SEC); wc.sec = (u32)wall_nsec; /* overflow in 2106 guest time */ wc.version = version; @@ -2516,26 +2517,29 @@ static inline int gtod_is_based_on_tsc(int mode) } #endif -static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) +static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool new_generation) { #ifdef CONFIG_X86_64 - bool vcpus_matched; struct kvm_arch *ka = &vcpu->kvm->arch; struct pvclock_gtod_data *gtod = &pvclock_gtod_data; - vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == - atomic_read(&vcpu->kvm->online_vcpus)); + /* + * To use the masterclock, the host clocksource must be based on TSC + * and all vCPUs must have matching TSCs. Note, the count for matching + * vCPUs doesn't include the reference vCPU, hence "+1". + */ + bool use_master_clock = (ka->nr_vcpus_matched_tsc + 1 == + atomic_read(&vcpu->kvm->online_vcpus)) && + gtod_is_based_on_tsc(gtod->clock.vclock_mode); /* - * Once the masterclock is enabled, always perform request in - * order to update it. - * - * In order to enable masterclock, the host clocksource must be TSC - * and the vcpus need to have matched TSCs. When that happens, - * perform request to enable masterclock. + * Request a masterclock update if the masterclock needs to be toggled + * on/off, or when starting a new generation and the masterclock is + * enabled (compute_guest_tsc() requires the masterclock snapshot to be + * taken _after_ the new generation is created). */ - if (ka->use_master_clock || - (gtod_is_based_on_tsc(gtod->clock.vclock_mode) && vcpus_matched)) + if ((ka->use_master_clock && new_generation) || + (ka->use_master_clock != use_master_clock)) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc, @@ -2631,7 +2635,7 @@ static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 l1_offset) else vcpu->arch.tsc_offset = l1_offset; - static_call(kvm_x86_write_tsc_offset)(vcpu, vcpu->arch.tsc_offset); + static_call(kvm_x86_write_tsc_offset)(vcpu); } static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier) @@ -2647,8 +2651,7 @@ static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multipli vcpu->arch.tsc_scaling_ratio = l1_multiplier; if (kvm_caps.has_tsc_control) - static_call(kvm_x86_write_tsc_multiplier)( - vcpu, vcpu->arch.tsc_scaling_ratio); + static_call(kvm_x86_write_tsc_multiplier)(vcpu); } static inline bool kvm_check_tsc_unstable(void) @@ -2713,11 +2716,12 @@ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc, vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec; vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write; - kvm_track_tsc_matching(vcpu); + kvm_track_tsc_matching(vcpu, !matched); } -static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) +static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value) { + u64 data = user_value ? *user_value : 0; struct kvm *kvm = vcpu->kvm; u64 offset, ns, elapsed; unsigned long flags; @@ -2732,25 +2736,37 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) if (vcpu->arch.virtual_tsc_khz) { if (data == 0) { /* - * detection of vcpu initialization -- need to sync - * with other vCPUs. This particularly helps to keep - * kvm_clock stable after CPU hotplug + * Force synchronization when creating a vCPU, or when + * userspace explicitly writes a zero value. */ synchronizing = true; - } else { + } else if (kvm->arch.user_set_tsc) { u64 tsc_exp = kvm->arch.last_tsc_write + nsec_to_cycles(vcpu, elapsed); u64 tsc_hz = vcpu->arch.virtual_tsc_khz * 1000LL; /* - * Special case: TSC write with a small delta (1 second) - * of virtual cycle time against real time is - * interpreted as an attempt to synchronize the CPU. + * Here lies UAPI baggage: when a user-initiated TSC write has + * a small delta (1 second) of virtual cycle time against the + * previously set vCPU, we assume that they were intended to be + * in sync and the delta was only due to the racy nature of the + * legacy API. + * + * This trick falls down when restoring a guest which genuinely + * has been running for less time than the 1 second of imprecision + * which we allow for in the legacy API. In this case, the first + * value written by userspace (on any vCPU) should not be subject + * to this 'correction' to make it sync up with values that only + * come from the kernel's default vCPU creation. Make the 1-second + * slop hack only trigger if the user_set_tsc flag is already set. */ synchronizing = data < tsc_exp + tsc_hz && data + tsc_hz > tsc_exp; } } + if (user_value) + kvm->arch.user_set_tsc = true; + /* * For a reliable TSC, we can match TSC offsets, and for an unstable * TSC, we add elapsed time in this computation. We could let the @@ -3098,7 +3114,8 @@ u64 get_kvmclock_ns(struct kvm *kvm) static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, struct gfn_to_pfn_cache *gpc, - unsigned int offset) + unsigned int offset, + bool force_tsc_unstable) { struct kvm_vcpu_arch *vcpu = &v->arch; struct pvclock_vcpu_time_info *guest_hv_clock; @@ -3135,6 +3152,10 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, } memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock)); + + if (force_tsc_unstable) + guest_hv_clock->flags &= ~PVCLOCK_TSC_STABLE_BIT; + smp_wmb(); guest_hv_clock->version = ++vcpu->hv_clock.version; @@ -3155,6 +3176,16 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) u64 tsc_timestamp, host_tsc; u8 pvclock_flags; bool use_master_clock; +#ifdef CONFIG_KVM_XEN + /* + * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless + * explicitly told to use TSC as its clocksource Xen will not set this bit. + * This default behaviour led to bugs in some guest kernels which cause + * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags. + */ + bool xen_pvclock_tsc_unstable = + ka->xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; +#endif kernel_ns = 0; host_tsc = 0; @@ -3233,17 +3264,97 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.flags = pvclock_flags; if (vcpu->pv_time.active) - kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0); + kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0, false); +#ifdef CONFIG_KVM_XEN if (vcpu->xen.vcpu_info_cache.active) kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache, - offsetof(struct compat_vcpu_info, time)); + offsetof(struct compat_vcpu_info, time), + xen_pvclock_tsc_unstable); if (vcpu->xen.vcpu_time_info_cache.active) - kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0); + kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0, + xen_pvclock_tsc_unstable); +#endif kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; } /* + * The pvclock_wall_clock ABI tells the guest the wall clock time at + * which it started (i.e. its epoch, when its kvmclock was zero). + * + * In fact those clocks are subtly different; wall clock frequency is + * adjusted by NTP and has leap seconds, while the kvmclock is a + * simple function of the TSC without any such adjustment. + * + * Perhaps the ABI should have exposed CLOCK_TAI and a ratio between + * that and kvmclock, but even that would be subject to change over + * time. + * + * Attempt to calculate the epoch at a given moment using the *same* + * TSC reading via kvm_get_walltime_and_clockread() to obtain both + * wallclock and kvmclock times, and subtracting one from the other. + * + * Fall back to using their values at slightly different moments by + * calling ktime_get_real_ns() and get_kvmclock_ns() separately. + */ +uint64_t kvm_get_wall_clock_epoch(struct kvm *kvm) +{ +#ifdef CONFIG_X86_64 + struct pvclock_vcpu_time_info hv_clock; + struct kvm_arch *ka = &kvm->arch; + unsigned long seq, local_tsc_khz; + struct timespec64 ts; + uint64_t host_tsc; + + do { + seq = read_seqcount_begin(&ka->pvclock_sc); + + local_tsc_khz = 0; + if (!ka->use_master_clock) + break; + + /* + * The TSC read and the call to get_cpu_tsc_khz() must happen + * on the same CPU. + */ + get_cpu(); + + local_tsc_khz = get_cpu_tsc_khz(); + + if (local_tsc_khz && + !kvm_get_walltime_and_clockread(&ts, &host_tsc)) + local_tsc_khz = 0; /* Fall back to old method */ + + put_cpu(); + + /* + * These values must be snapshotted within the seqcount loop. + * After that, it's just mathematics which can happen on any + * CPU at any time. + */ + hv_clock.tsc_timestamp = ka->master_cycle_now; + hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; + + } while (read_seqcount_retry(&ka->pvclock_sc, seq)); + + /* + * If the conditions were right, and obtaining the wallclock+TSC was + * successful, calculate the KVM clock at the corresponding time and + * subtract one from the other to get the guest's epoch in nanoseconds + * since 1970-01-01. + */ + if (local_tsc_khz) { + kvm_get_time_scale(NSEC_PER_SEC, local_tsc_khz * NSEC_PER_USEC, + &hv_clock.tsc_shift, + &hv_clock.tsc_to_system_mul); + return ts.tv_nsec + NSEC_PER_SEC * ts.tv_sec - + __pvclock_read_cycles(&hv_clock, host_tsc); + } +#endif + return ktime_get_real_ns() - get_kvmclock_ns(kvm); +} + +/* * kvmclock updates which are isolated to a given vcpu, such as * vcpu->cpu migration, should not allow system_timestamp from * the rest of the vcpus to remain static. Otherwise ntp frequency @@ -3292,9 +3403,6 @@ static void kvmclock_sync_fn(struct work_struct *work) kvmclock_sync_work); struct kvm *kvm = container_of(ka, struct kvm, arch); - if (!kvmclock_periodic_sync) - return; - schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0); schedule_delayed_work(&kvm->arch.kvmclock_sync_work, KVMCLOCK_SYNC_PERIOD); @@ -3643,6 +3751,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_PATCH_LOADER: case MSR_AMD64_BU_CFG2: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: break; @@ -3672,17 +3781,36 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.perf_capabilities = data; kvm_pmu_refresh(vcpu); break; - case MSR_IA32_PRED_CMD: - if (!msr_info->host_initiated && !guest_has_pred_cmd_msr(vcpu)) - return 1; + case MSR_IA32_PRED_CMD: { + u64 reserved_bits = ~(PRED_CMD_IBPB | PRED_CMD_SBPB); + + if (!msr_info->host_initiated) { + if ((!guest_has_pred_cmd_msr(vcpu))) + return 1; + + if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)) + reserved_bits |= PRED_CMD_IBPB; + + if (!guest_cpuid_has(vcpu, X86_FEATURE_SBPB)) + reserved_bits |= PRED_CMD_SBPB; + } + + if (!boot_cpu_has(X86_FEATURE_IBPB)) + reserved_bits |= PRED_CMD_IBPB; - if (!boot_cpu_has(X86_FEATURE_IBPB) || (data & ~PRED_CMD_IBPB)) + if (!boot_cpu_has(X86_FEATURE_SBPB)) + reserved_bits |= PRED_CMD_SBPB; + + if (data & reserved_bits) return 1; + if (!data) break; - wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + wrmsrl(MSR_IA32_PRED_CMD, data); break; + } case MSR_IA32_FLUSH_CMD: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)) @@ -3702,13 +3830,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) data &= ~(u64)0x100; /* ignore ignne emulation enable */ data &= ~(u64)0x8; /* ignore TLB cache disable */ - /* Handle McStatusWrEn */ - if (data == BIT_ULL(18)) { - vcpu->arch.msr_hwcr = data; - } else if (data != 0) { + /* + * Allow McStatusWrEn and TscFreqSel. (Linux guests from v3.2 + * through at least v6.6 whine if TscFreqSel is clear, + * depending on F/M/S. + */ + if (data & ~(BIT_ULL(18) | BIT_ULL(24))) { kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } + vcpu->arch.msr_hwcr = data; break; case MSR_FAM10H_MMIO_CONF_BASE: if (data != 0) { @@ -3779,7 +3910,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_TSC: if (msr_info->host_initiated) { - kvm_synchronize_tsc(vcpu, data); + kvm_synchronize_tsc(vcpu, &data); } else { u64 adj = kvm_compute_l1_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset; adjust_tsc_offset_guest(vcpu, adj); @@ -3916,6 +4047,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * the need to ignore the workaround. */ break; +#ifdef CONFIG_KVM_HYPERV case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: case HV_X64_MSR_SYNDBG_OPTIONS: @@ -3928,6 +4060,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_set_msr_common(vcpu, msr, data, msr_info->host_initiated); +#endif case MSR_IA32_BBL_CR_CTL3: /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. @@ -4067,6 +4200,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_BU_CFG2: case MSR_IA32_PERF_CTL: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: /* * Intel Sandy Bridge CPUs must support the RAPL (running average power @@ -4272,6 +4406,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ msr_info->data = 0x20000000; break; +#ifdef CONFIG_KVM_HYPERV case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: case HV_X64_MSR_SYNDBG_OPTIONS: @@ -4285,6 +4420,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_hv_get_msr_common(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); +#endif case MSR_IA32_BBL_CR_CTL3: /* This legacy MSR exists but isn't fully documented in current * silicon. It is however accessed by winxp in very narrow @@ -4422,6 +4558,7 @@ static inline bool kvm_can_mwait_in_guest(void) boot_cpu_has(X86_FEATURE_ARAT); } +#ifdef CONFIG_KVM_HYPERV static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 __user *cpuid_arg) { @@ -4442,6 +4579,14 @@ static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, return 0; } +#endif + +static bool kvm_is_vm_type_supported(unsigned long type) +{ + return type == KVM_X86_DEFAULT_VM || + (type == KVM_X86_SW_PROTECTED_VM && + IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_enabled); +} int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { @@ -4468,9 +4613,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: case KVM_CAP_VCPU_EVENTS: +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: + case KVM_CAP_HYPERV_TIME: case KVM_CAP_HYPERV_SYNIC: case KVM_CAP_HYPERV_SYNIC2: case KVM_CAP_HYPERV_VP_INDEX: @@ -4480,6 +4627,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_CPUID: case KVM_CAP_HYPERV_ENFORCE_CPUID: case KVM_CAP_SYS_HYPERV_CPUID: +#endif case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: @@ -4489,7 +4637,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_GET_TSC_KHZ: case KVM_CAP_KVMCLOCK_CTRL: case KVM_CAP_READONLY_MEM: - case KVM_CAP_HYPERV_TIME: case KVM_CAP_IOAPIC_POLARITY_IGNORED: case KVM_CAP_TSC_DEADLINE_TIMER: case KVM_CAP_DISABLE_QUIRKS: @@ -4520,6 +4667,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ENABLE_CAP: case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: case KVM_CAP_IRQFD_RESAMPLE: + case KVM_CAP_MEMORY_FAULT_INFO: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: @@ -4533,7 +4681,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | KVM_XEN_HVM_CONFIG_SHARED_INFO | KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL | - KVM_XEN_HVM_CONFIG_EVTCHN_SEND; + KVM_XEN_HVM_CONFIG_EVTCHN_SEND | + KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; if (sched_info_on()) r |= KVM_XEN_HVM_CONFIG_RUNSTATE | KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG; @@ -4599,12 +4748,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = kvm_x86_ops.nested_ops->get_state ? kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0; break; +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: r = kvm_x86_ops.enable_l2_tlb_flush != NULL; break; case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: r = kvm_x86_ops.nested_ops->enable_evmcs != NULL; break; +#endif case KVM_CAP_SMALLER_MAXPHYADDR: r = (int) allow_smaller_maxphyaddr; break; @@ -4633,6 +4784,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_X86_NOTIFY_VMEXIT: r = kvm_caps.has_notify_vmexit; break; + case KVM_CAP_VM_TYPES: + r = BIT(KVM_X86_DEFAULT_VM); + if (kvm_is_vm_type_supported(KVM_X86_SW_PROTECTED_VM)) + r |= BIT(KVM_X86_SW_PROTECTED_VM); + break; default: break; } @@ -4665,7 +4821,6 @@ static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr) return 0; default: return -ENXIO; - break; } } @@ -4767,9 +4922,11 @@ long kvm_arch_dev_ioctl(struct file *filp, case KVM_GET_MSRS: r = msr_io(NULL, argp, do_get_msr_feature, 1); break; +#ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp); break; +#endif case KVM_GET_DEVICE_ATTR: { struct kvm_device_attr attr; r = -EFAULT; @@ -5385,26 +5542,37 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, return 0; } -static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, - struct kvm_xsave *guest_xsave) -{ - if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return; - - fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, - guest_xsave->region, - sizeof(guest_xsave->region), - vcpu->arch.pkru); -} static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, u8 *state, unsigned int size) { + /* + * Only copy state for features that are enabled for the guest. The + * state itself isn't problematic, but setting bits in the header for + * features that are supported in *this* host but not exposed to the + * guest can result in KVM_SET_XSAVE failing when live migrating to a + * compatible host without the features that are NOT exposed to the + * guest. + * + * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if + * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't + * supported by the host. + */ + u64 supported_xcr0 = vcpu->arch.guest_supported_xcr0 | + XFEATURE_MASK_FPSSE; + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return; - fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, - state, size, vcpu->arch.pkru); + fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size, + supported_xcr0, vcpu->arch.pkru); +} + +static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, + struct kvm_xsave *guest_xsave) +{ + kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region, + sizeof(guest_xsave->region)); } static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, @@ -5539,6 +5707,7 @@ static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio) + offset; ns = get_kvmclock_base_ns(); + kvm->arch.user_set_tsc = true; __kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); @@ -5583,14 +5752,11 @@ static int kvm_vcpu_ioctl_device_attr(struct kvm_vcpu *vcpu, static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, struct kvm_enable_cap *cap) { - int r; - uint16_t vmcs_version; - void __user *user_ptr; - if (cap->flags) return -EINVAL; switch (cap->cap) { +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV_SYNIC2: if (cap->args[0]) return -EINVAL; @@ -5602,16 +5768,22 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return kvm_hv_activate_synic(vcpu, cap->cap == KVM_CAP_HYPERV_SYNIC2); case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: - if (!kvm_x86_ops.nested_ops->enable_evmcs) - return -ENOTTY; - r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version); - if (!r) { - user_ptr = (void __user *)(uintptr_t)cap->args[0]; - if (copy_to_user(user_ptr, &vmcs_version, - sizeof(vmcs_version))) - r = -EFAULT; + { + int r; + uint16_t vmcs_version; + void __user *user_ptr; + + if (!kvm_x86_ops.nested_ops->enable_evmcs) + return -ENOTTY; + r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version); + if (!r) { + user_ptr = (void __user *)(uintptr_t)cap->args[0]; + if (copy_to_user(user_ptr, &vmcs_version, + sizeof(vmcs_version))) + r = -EFAULT; + } + return r; } - return r; case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: if (!kvm_x86_ops.enable_l2_tlb_flush) return -ENOTTY; @@ -5620,6 +5792,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, case KVM_CAP_HYPERV_ENFORCE_CPUID: return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]); +#endif case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; @@ -6012,9 +6185,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } +#ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp); break; +#endif #ifdef CONFIG_KVM_XEN case KVM_XEN_VCPU_GET_ATTR: { struct kvm_xen_vcpu_attr xva; @@ -6251,6 +6426,9 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) struct kvm_vcpu *vcpu; unsigned long i; + if (!kvm_x86_ops.cpu_dirty_log_size) + return; + kvm_for_each_vcpu(i, vcpu, kvm) kvm_vcpu_kick(vcpu); } @@ -6532,7 +6710,7 @@ static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter) static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, struct kvm_msr_filter_range *user_range) { - unsigned long *bitmap = NULL; + unsigned long *bitmap; size_t bitmap_size; if (!user_range->nmsrs) @@ -6842,6 +7020,9 @@ set_identity_unlock: r = -EEXIST; if (kvm->arch.vpit) goto create_pit_unlock; + r = -ENOENT; + if (!pic_in_kernel(kvm)) + goto create_pit_unlock; r = -ENOMEM; kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags); if (kvm->arch.vpit) @@ -7069,6 +7250,7 @@ set_pit2_out: r = static_call(kvm_x86_mem_enc_unregister_region)(kvm, ®ion); break; } +#ifdef CONFIG_KVM_HYPERV case KVM_HYPERV_EVENTFD: { struct kvm_hyperv_eventfd hvevfd; @@ -7078,6 +7260,7 @@ set_pit2_out: r = kvm_vm_ioctl_hv_eventfd(kvm, &hvevfd); break; } +#endif case KVM_SET_PMU_EVENT_FILTER: r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); break; @@ -7477,11 +7660,11 @@ 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) +static int kvm_check_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { - return static_call(kvm_x86_can_emulate_instruction)(vcpu, emul_type, - insn, insn_len); + return static_call(kvm_x86_check_emulate_instruction)(vcpu, emul_type, + insn, insn_len); } int handle_ud(struct kvm_vcpu *vcpu) @@ -7491,8 +7674,10 @@ int handle_ud(struct kvm_vcpu *vcpu) int emul_type = EMULTYPE_TRAP_UD; char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; + int r; - if (unlikely(!kvm_can_emulate_insn(vcpu, emul_type, NULL, 0))) + r = kvm_check_emulate_insn(vcpu, emul_type, NULL, 0); + if (r != X86EMUL_CONTINUE) return 1; if (fep_flags && @@ -8245,11 +8430,6 @@ static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, exact_only); } -static bool emulator_guest_has_long_mode(struct x86_emulate_ctxt *ctxt) -{ - return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_LM); -} - static bool emulator_guest_has_movbe(struct x86_emulate_ctxt *ctxt) { return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_MOVBE); @@ -8316,6 +8496,15 @@ static void emulator_vm_bugged(struct x86_emulate_ctxt *ctxt) kvm_vm_bugged(kvm); } +static gva_t emulator_get_untagged_addr(struct x86_emulate_ctxt *ctxt, + gva_t addr, unsigned int flags) +{ + if (!kvm_x86_ops.get_untagged_addr) + return addr; + + return static_call(kvm_x86_get_untagged_addr)(emul_to_vcpu(ctxt), addr, flags); +} + static const struct x86_emulate_ops emulate_ops = { .vm_bugged = emulator_vm_bugged, .read_gpr = emulator_read_gpr, @@ -8351,7 +8540,6 @@ static const struct x86_emulate_ops emulate_ops = { .fix_hypercall = emulator_fix_hypercall, .intercept = emulator_intercept, .get_cpuid = emulator_get_cpuid, - .guest_has_long_mode = emulator_guest_has_long_mode, .guest_has_movbe = emulator_guest_has_movbe, .guest_has_fxsr = emulator_guest_has_fxsr, .guest_has_rdpid = emulator_guest_has_rdpid, @@ -8361,6 +8549,7 @@ static const struct x86_emulate_ops emulate_ops = { .leave_smm = emulator_leave_smm, .triple_fault = emulator_triple_fault, .set_xcr = emulator_set_xcr, + .get_untagged_addr = emulator_get_untagged_addr, }; static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) @@ -8880,8 +9069,14 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; bool writeback = true; - if (unlikely(!kvm_can_emulate_insn(vcpu, emulation_type, insn, insn_len))) - return 1; + r = kvm_check_emulate_insn(vcpu, emulation_type, insn, insn_len); + if (r != X86EMUL_CONTINUE) { + if (r == X86EMUL_RETRY_INSTR || r == X86EMUL_PROPAGATE_FAULT) + return 1; + + WARN_ON_ONCE(r != X86EMUL_UNHANDLEABLE); + return handle_emulation_failure(vcpu, emulation_type); + } vcpu->arch.l1tf_flush_l1d = true; @@ -9172,7 +9367,7 @@ static int kvmclock_cpu_down_prep(unsigned int cpu) static void tsc_khz_changed(void *data) { struct cpufreq_freqs *freq = data; - unsigned long khz = 0; + unsigned long khz; WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_CONSTANT_TSC)); @@ -9512,6 +9707,9 @@ static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) kvm_init_pmu_capability(ops->pmu_ops); + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, host_arch_capabilities); + r = ops->hardware_setup(); if (r != 0) goto out_mmu_exit; @@ -10041,7 +10239,7 @@ static void kvm_inject_exception(struct kvm_vcpu *vcpu) * * But, if a VM-Exit occurs during instruction execution, and KVM does NOT skip * the instruction or inject an exception, then KVM can incorrecty inject a new - * asynchrounous event if the event became pending after the CPU fetched the + * asynchronous event if the event became pending after the CPU fetched the * instruction (in the guest). E.g. if a page fault (#PF, #NPF, EPT violation) * occurs and is resolved by KVM, a coincident NMI, SMI, IRQ, etc... can be * injected on the restarted instruction instead of being deferred until the @@ -10062,7 +10260,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, int r; /* - * Process nested events first, as nested VM-Exit supercedes event + * Process nested events first, as nested VM-Exit supersedes event * re-injection. If there's an event queued for re-injection, it will * be saved into the appropriate vmc{b,s}12 fields on nested VM-Exit. */ @@ -10451,19 +10649,20 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) { - u64 eoi_exit_bitmap[4]; - if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; +#ifdef CONFIG_KVM_HYPERV if (to_hv_vcpu(vcpu)) { + u64 eoi_exit_bitmap[4]; + bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, to_hv_synic(vcpu)->vec_bitmap, 256); static_call_cond(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); return; } - +#endif static_call_cond(kvm_x86_load_eoi_exitmap)( vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors); } @@ -10554,9 +10753,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * the flushes are considered "remote" and not "local" because * the requests can be initiated from other vCPUs. */ +#ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu) && kvm_hv_vcpu_flush_tlb(vcpu)) kvm_vcpu_flush_tlb_guest(vcpu); +#endif if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; @@ -10582,16 +10783,16 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) record_steal_time(vcpu); + if (kvm_check_request(KVM_REQ_PMU, vcpu)) + kvm_pmu_handle_event(vcpu); + if (kvm_check_request(KVM_REQ_PMI, vcpu)) + kvm_pmu_deliver_pmi(vcpu); #ifdef CONFIG_KVM_SMM if (kvm_check_request(KVM_REQ_SMI, vcpu)) process_smi(vcpu); #endif if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); - if (kvm_check_request(KVM_REQ_PMU, vcpu)) - kvm_pmu_handle_event(vcpu); - if (kvm_check_request(KVM_REQ_PMI, vcpu)) - kvm_pmu_deliver_pmi(vcpu); if (kvm_check_request(KVM_REQ_IOAPIC_EOI_EXIT, vcpu)) { BUG_ON(vcpu->arch.pending_ioapic_eoi > 255); if (test_bit(vcpu->arch.pending_ioapic_eoi, @@ -10609,6 +10810,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu_load_eoi_exitmap(vcpu); if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu)) kvm_vcpu_reload_apic_access_page(vcpu); +#ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH; @@ -10639,6 +10841,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) */ if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu)) kvm_hv_process_stimers(vcpu); +#endif if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu)) kvm_vcpu_update_apicv(vcpu); if (kvm_check_request(KVM_REQ_APF_READY, vcpu)) @@ -10760,7 +10963,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* * Assert that vCPU vs. VM APICv state is consistent. An APICv * update must kick and wait for all vCPUs before toggling the - * per-VM state, and responsing vCPUs must wait for the update + * per-VM state, and responding vCPUs must wait for the update * to complete before servicing KVM_REQ_APICV_UPDATE. */ WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) && @@ -10957,6 +11160,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) { int r; + vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; vcpu->arch.l1tf_flush_l1d = true; for (;;) { @@ -11111,12 +11315,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) r = -EINTR; goto out; } + /* - * It should be impossible for the hypervisor timer to be in - * use before KVM has ever run the vCPU. + * Don't bother switching APIC timer emulation from the + * hypervisor timer to the software timer, the only way for the + * APIC timer to be active is if userspace stuffed vCPU state, + * i.e. put the vCPU into a nonsensical state. Only an INIT + * will transition the vCPU out of UNINITIALIZED (without more + * state stuffing from userspace), which will reset the local + * APIC and thus cancel the timer or drop the IRQ (if the timer + * already expired). */ - WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu)); - kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_block(vcpu); kvm_vcpu_srcu_read_lock(vcpu); @@ -11469,7 +11678,7 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) */ if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) return false; - if (kvm_vcpu_is_illegal_gpa(vcpu, sregs->cr3)) + if (!kvm_vcpu_is_legal_cr3(vcpu, sregs->cr3)) return false; } else { /* @@ -11522,7 +11731,6 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, *mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; static_call(kvm_x86_set_cr0)(vcpu, sregs->cr0); - vcpu->arch.cr0 = sregs->cr0; *mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; static_call(kvm_x86_set_cr4)(vcpu, sregs->cr4); @@ -11566,8 +11774,10 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) if (ret) return ret; - if (mmu_reset_needed) + if (mmu_reset_needed) { kvm_mmu_reset_context(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + } max_bits = KVM_NR_INTERRUPTS; pending_vec = find_first_bit( @@ -11608,8 +11818,10 @@ static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) mmu_reset_needed = 1; vcpu->arch.pdptrs_from_userspace = true; } - if (mmu_reset_needed) + if (mmu_reset_needed) { kvm_mmu_reset_context(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + } return 0; } @@ -11798,15 +12010,22 @@ static int sync_regs(struct kvm_vcpu *vcpu) __set_regs(vcpu, &vcpu->run->s.regs.regs); vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_REGS; } + if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_SREGS) { - if (__set_sregs(vcpu, &vcpu->run->s.regs.sregs)) + struct kvm_sregs sregs = vcpu->run->s.regs.sregs; + + if (__set_sregs(vcpu, &sregs)) return -EINVAL; + vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_SREGS; } + if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_EVENTS) { - if (kvm_vcpu_ioctl_x86_set_vcpu_events( - vcpu, &vcpu->run->s.regs.events)) + struct kvm_vcpu_events events = vcpu->run->s.regs.events; + + if (kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events)) return -EINVAL; + vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_EVENTS; } @@ -11953,7 +12172,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) if (mutex_lock_killable(&vcpu->mutex)) return; vcpu_load(vcpu); - kvm_synchronize_tsc(vcpu, 0); + kvm_synchronize_tsc(vcpu, NULL); vcpu_put(vcpu); /* poll control enabled by default */ @@ -12068,7 +12287,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) } if (!init_event) { - kvm_pmu_reset(vcpu); vcpu->arch.smbase = 0x30000; vcpu->arch.msr_misc_features_enables = 0; @@ -12285,7 +12503,9 @@ void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) void kvm_arch_free_vm(struct kvm *kvm) { - kfree(to_kvm_hv(kvm)->hv_pa_pg); +#if IS_ENABLED(CONFIG_HYPERV) + kfree(kvm->arch.hv_pa_pg); +#endif __kvm_arch_free_vm(kvm); } @@ -12295,23 +12515,22 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) int ret; unsigned long flags; - if (type) + if (!kvm_is_vm_type_supported(type)) return -EINVAL; + kvm->arch.vm_type = type; + ret = kvm_page_track_init(kvm); if (ret) goto out; - ret = kvm_mmu_init_vm(kvm); - if (ret) - goto out_page_track; + kvm_mmu_init_vm(kvm); 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.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ @@ -12349,7 +12568,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) out_uninit_mmu: kvm_mmu_uninit_vm(kvm); -out_page_track: kvm_page_track_cleanup(kvm); out: return ret; @@ -12440,8 +12658,8 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, hva = slot->userspace_addr; } - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - struct kvm_userspace_memory_region m; + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { + struct kvm_userspace_memory_region2 m; m.slot = id | (i << 16); m.flags = 0; @@ -12591,6 +12809,10 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm, } } +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + kvm_mmu_init_memslot_memory_attributes(kvm, slot); +#endif + if (kvm_page_track_create_memslot(kvm, slot, npages)) goto out_free; @@ -12627,6 +12849,13 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *new, enum kvm_mr_change change) { + /* + * KVM doesn't support moving memslots when there are external page + * trackers attached to the VM, i.e. if KVMGT is in use. + */ + if (change == KVM_MR_MOVE && kvm_page_track_has_external_user(kvm)) + return -EINVAL; + if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) { if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn()) return -EINVAL; @@ -12772,7 +13001,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * See is_writable_pte() for more details (the case involving * access-tracked SPTEs is particularly relevant). */ - kvm_arch_flush_remote_tlbs_memslot(kvm, new); + kvm_flush_remote_tlbs_memslot(kvm, new); } } @@ -12781,6 +13010,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { + if (change == KVM_MR_DELETE) + kvm_page_track_delete_slot(kvm, old); + if (!kvm->arch.n_requested_mmu_pages && (change == KVM_MR_CREATE || change == KVM_MR_DELETE)) { unsigned long nr_mmu_pages; @@ -12797,17 +13029,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, kvm_arch_free_memslot(kvm, old); } -void kvm_arch_flush_shadow_all(struct kvm *kvm) -{ - kvm_mmu_zap_all(kvm); -} - -void kvm_arch_flush_shadow_memslot(struct kvm *kvm, - struct kvm_memory_slot *slot) -{ - kvm_page_track_flush_slot(kvm, slot); -} - static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) { return (is_guest_mode(vcpu) && @@ -12841,6 +13062,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) return true; #endif + if (kvm_test_request(KVM_REQ_PMI, vcpu)) + return true; + if (kvm_arch_interrupt_allowed(vcpu) && (kvm_cpu_has_interrupt(vcpu) || kvm_guest_apic_has_interrupt(vcpu))) @@ -12894,7 +13118,10 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) if (vcpu->arch.guest_state_protected) return true; - return vcpu->arch.preempted_in_kernel; + if (vcpu != kvm_get_running_vcpu()) + return vcpu->arch.preempted_in_kernel; + + return static_call(kvm_x86_get_cpl)(vcpu) == 0; } unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu) @@ -13186,15 +13413,30 @@ bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); +static void kvm_noncoherent_dma_assignment_start_or_stop(struct kvm *kvm) +{ + /* + * Non-coherent DMA assignment and de-assignment will affect + * whether KVM honors guest MTRRs and cause changes in memtypes + * in TDP. + * So, pass %true unconditionally to indicate non-coherent DMA was, + * or will be involved, and that zapping SPTEs might be necessary. + */ + if (__kvm_mmu_honors_guest_mtrrs(true)) + kvm_zap_gfn_range(kvm, gpa_to_gfn(0), gpa_to_gfn(~0ULL)); +} + void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { - atomic_inc(&kvm->arch.noncoherent_dma_count); + if (atomic_inc_return(&kvm->arch.noncoherent_dma_count) == 1) + kvm_noncoherent_dma_assignment_start_or_stop(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_register_noncoherent_dma); void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm) { - atomic_dec(&kvm->arch.noncoherent_dma_count); + if (!atomic_dec_return(&kvm->arch.noncoherent_dma_count)) + kvm_noncoherent_dma_assignment_start_or_stop(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_unregister_noncoherent_dma); @@ -13381,6 +13623,10 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) switch (type) { case INVPCID_TYPE_INDIV_ADDR: + /* + * LAM doesn't apply to addresses that are inputs to TLB + * invalidation. + */ if ((!pcid_enabled && (operand.pcid != 0)) || is_noncanonical_address(operand.gla, vcpu)) { kvm_inject_gp(vcpu, 0); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 82e3dafc5453..2f7e19166658 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -293,6 +293,7 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); u64 get_kvmclock_ns(struct kvm *kvm); +uint64_t kvm_get_wall_clock_epoch(struct kvm *kvm); int kvm_read_guest_virt(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, @@ -323,6 +324,7 @@ fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu); extern u64 host_xcr0; extern u64 host_xss; +extern u64 host_arch_capabilities; extern struct kvm_caps kvm_caps; @@ -528,6 +530,8 @@ bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type); __reserved_bits |= X86_CR4_VMXE; \ if (!__cpu_has(__c, X86_FEATURE_PCID)) \ __reserved_bits |= X86_CR4_PCIDE; \ + if (!__cpu_has(__c, X86_FEATURE_LAM)) \ + __reserved_bits |= X86_CR4_LAM_SUP; \ __reserved_bits; \ }) diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 40edf4d1974c..4b4e738c6f1b 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -59,7 +59,7 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) * This code mirrors kvm_write_wall_clock() except that it writes * directly through the pfn cache and doesn't mark the page dirty. */ - wall_nsec = ktime_get_real_ns() - get_kvmclock_ns(kvm); + wall_nsec = kvm_get_wall_clock_epoch(kvm); /* It could be invalid again already, so we need to check */ read_lock_irq(&gpc->lock); @@ -98,7 +98,7 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) wc_version = wc->version = (wc->version + 1) | 1; smp_wmb(); - wc->nsec = do_div(wall_nsec, 1000000000); + wc->nsec = do_div(wall_nsec, NSEC_PER_SEC); wc->sec = (u32)wall_nsec; *wc_sec_hi = wall_nsec >> 32; smp_wmb(); @@ -134,9 +134,23 @@ static enum hrtimer_restart xen_timer_callback(struct hrtimer *timer) { struct kvm_vcpu *vcpu = container_of(timer, struct kvm_vcpu, arch.xen.timer); + struct kvm_xen_evtchn e; + int rc; + if (atomic_read(&vcpu->arch.xen.timer_pending)) return HRTIMER_NORESTART; + e.vcpu_id = vcpu->vcpu_id; + e.vcpu_idx = vcpu->vcpu_idx; + e.port = vcpu->arch.xen.timer_virq; + e.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; + + rc = kvm_xen_set_evtchn_fast(&e, vcpu->kvm); + if (rc != -EWOULDBLOCK) { + vcpu->arch.xen.timer_expires = 0; + return HRTIMER_NORESTART; + } + atomic_inc(&vcpu->arch.xen.timer_pending); kvm_make_request(KVM_REQ_UNBLOCK, vcpu); kvm_vcpu_kick(vcpu); @@ -146,6 +160,14 @@ static enum hrtimer_restart xen_timer_callback(struct hrtimer *timer) static void kvm_xen_start_timer(struct kvm_vcpu *vcpu, u64 guest_abs, s64 delta_ns) { + /* + * Avoid races with the old timer firing. Checking timer_expires + * to avoid calling hrtimer_cancel() will only have false positives + * so is fine. + */ + if (vcpu->arch.xen.timer_expires) + hrtimer_cancel(&vcpu->arch.xen.timer); + atomic_set(&vcpu->arch.xen.timer_pending, 0); vcpu->arch.xen.timer_expires = guest_abs; @@ -1019,9 +1041,36 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; case KVM_XEN_VCPU_ATTR_TYPE_TIMER: + /* + * Ensure a consistent snapshot of state is captured, with a + * timer either being pending, or the event channel delivered + * to the corresponding bit in the shared_info. Not still + * lurking in the timer_pending flag for deferred delivery. + * Purely as an optimisation, if the timer_expires field is + * zero, that means the timer isn't active (or even in the + * timer_pending flag) and there is no need to cancel it. + */ + if (vcpu->arch.xen.timer_expires) { + hrtimer_cancel(&vcpu->arch.xen.timer); + kvm_xen_inject_timer_irqs(vcpu); + } + data->u.timer.port = vcpu->arch.xen.timer_virq; data->u.timer.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; data->u.timer.expires_ns = vcpu->arch.xen.timer_expires; + + /* + * The hrtimer may trigger and raise the IRQ immediately, + * while the returned state causes it to be set up and + * raised again on the destination system after migration. + * That's fine, as the guest won't even have had a chance + * to run and handle the interrupt. Asserting an already + * pending event channel is idempotent. + */ + if (vcpu->arch.xen.timer_expires) + hrtimer_start_expires(&vcpu->arch.xen.timer, + HRTIMER_MODE_ABS_HARD); + r = 0; break; @@ -1113,7 +1162,9 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) { /* Only some feature flags need to be *enabled* by userspace */ u32 permitted_flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | - KVM_XEN_HVM_CONFIG_EVTCHN_SEND; + KVM_XEN_HVM_CONFIG_EVTCHN_SEND | + KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; + u32 old_flags; if (xhc->flags & ~permitted_flags) return -EINVAL; @@ -1134,9 +1185,14 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) else if (!xhc->msr && kvm->arch.xen_hvm_config.msr) static_branch_slow_dec_deferred(&kvm_xen_enabled); + old_flags = kvm->arch.xen_hvm_config.flags; memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc)); mutex_unlock(&kvm->arch.xen.xen_lock); + + if ((old_flags ^ xhc->flags) & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE) + kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); + return 0; } @@ -1374,12 +1430,8 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, return true; } + /* A delta <= 0 results in an immediate callback, which is what we want */ delta = oneshot.timeout_abs_ns - get_kvmclock_ns(vcpu->kvm); - if ((oneshot.flags & VCPU_SSHOTTMR_future) && delta < 0) { - *r = -ETIME; - return true; - } - kvm_xen_start_timer(vcpu, oneshot.timeout_abs_ns, delta); *r = 0; return true; @@ -2043,7 +2095,7 @@ static bool kvm_xen_hcall_evtchn_send(struct kvm_vcpu *vcpu, u64 param, u64 *r) if (ret < 0 && ret != -ENOTCONN) return false; } else { - eventfd_signal(evtchnfd->deliver.eventfd.ctx, 1); + eventfd_signal(evtchnfd->deliver.eventfd.ctx); } *r = 0; |