diff options
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/Kconfig | 12 | ||||
-rw-r--r-- | arch/x86/kvm/Makefile | 2 | ||||
-rw-r--r-- | arch/x86/kvm/cpuid.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/emulate.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/irq_comm.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/mmu/mmu.c | 11 | ||||
-rw-r--r-- | arch/x86/kvm/mmu/mmu_internal.h | 2 | ||||
-rw-r--r-- | arch/x86/kvm/mmu/tdp_mmu.c | 32 | ||||
-rw-r--r-- | arch/x86/kvm/mmu/tdp_mmu.h | 24 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.h | 2 | ||||
-rw-r--r-- | arch/x86/kvm/svm/avic.c | 4 | ||||
-rw-r--r-- | arch/x86/kvm/svm/nested.c | 28 | ||||
-rw-r--r-- | arch/x86/kvm/svm/pmu.c | 8 | ||||
-rw-r--r-- | arch/x86/kvm/svm/sev.c | 72 | ||||
-rw-r--r-- | arch/x86/kvm/svm/svm.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/svm/svm.h | 1 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/nested.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/posted_intr.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 16 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 91 | ||||
-rw-r--r-- | arch/x86/kvm/x86.h | 1 |
21 files changed, 222 insertions, 96 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index a788d5120d4d..f6b93a35ce14 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -84,6 +84,18 @@ config KVM_INTEL To compile this as a module, choose M here: the module will be called kvm-intel. +config X86_SGX_KVM + bool "Software Guard eXtensions (SGX) Virtualization" + depends on X86_SGX && KVM_INTEL + help + + Enables KVM guests to create SGX enclaves. + + This includes support to expose "raw" unreclaimable enclave memory to + guests via a device node, e.g. /dev/sgx_vepc. + + If unsure, say N. + config KVM_AMD tristate "KVM for AMD processors support" depends on KVM diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 1b4766fe1de2..eafc4d601f25 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -ccflags-y += -Iarch/x86/kvm +ccflags-y += -I $(srctree)/arch/x86/kvm ccflags-$(CONFIG_KVM_WERROR) += -Werror ifeq ($(CONFIG_FRAME_POINTER),y) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 6bd2f8b830e4..c02466a1410b 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1033,7 +1033,7 @@ EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); * - Centaur: 0xc0000000 - 0xcfffffff * * The Hypervisor class is further subdivided into sub-classes that each act as - * their own indepdent class associated with a 0x100 byte range. E.g. if Qemu + * their own independent class associated with a 0x100 byte range. E.g. if Qemu * is advertising support for both HyperV and KVM, the resulting Hypervisor * CPUID sub-classes are: * diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index f7970ba6219f..cdd2a2b6550e 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3222,7 +3222,7 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, } /* - * Now load segment descriptors. If fault happenes at this stage + * Now load segment descriptors. If fault happens at this stage * it is handled in a context of new task */ ret = __load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR, diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 8a4de3f12820..d5b72a08e566 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -269,7 +269,7 @@ int kvm_set_routing_entry(struct kvm *kvm, const struct kvm_irq_routing_entry *ue) { /* We can't check irqchip_in_kernel() here as some callers are - * currently inititalizing the irqchip. Other callers should therefore + * currently initializing the irqchip. Other callers should therefore * check kvm_arch_can_set_irq_routing() before calling this function. */ switch (ue->type) { diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index d75524bc8423..62b1729277ef 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4961,7 +4961,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, /* * No need to care whether allocation memory is successful - * or not since pte prefetch is skiped if it does not have + * or not since pte prefetch is skipped if it does not have * enough objects in the cache. */ mmu_topup_memory_caches(vcpu, true); @@ -5884,6 +5884,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) struct kvm_mmu_page *sp; unsigned int ratio; LIST_HEAD(invalid_list); + bool flush = false; ulong to_zap; rcu_idx = srcu_read_lock(&kvm->srcu); @@ -5905,19 +5906,19 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) lpage_disallowed_link); WARN_ON_ONCE(!sp->lpage_disallowed); if (is_tdp_mmu_page(sp)) { - kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, - sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level)); + flush |= kvm_tdp_mmu_zap_sp(kvm, sp); } else { kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); WARN_ON_ONCE(sp->lpage_disallowed); } if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { - kvm_mmu_commit_zap_page(kvm, &invalid_list); + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); cond_resched_rwlock_write(&kvm->mmu_lock); + flush = false; } } - kvm_mmu_commit_zap_page(kvm, &invalid_list); + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, rcu_idx); diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 1f6f98c76bdf..360983865398 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -59,7 +59,7 @@ struct kvm_mmu_page { #ifdef CONFIG_X86_64 bool tdp_mmu_page; - /* Used for freeing the page asyncronously if it is a TDP MMU page. */ + /* Used for freeing the page asynchronously if it is a TDP MMU page. */ struct rcu_head rcu_head; #endif }; diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 462b1f71c77f..34207b874886 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -86,7 +86,7 @@ static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t start, gfn_t end, bool can_yield); + gfn_t start, gfn_t end, bool can_yield, bool flush); void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root) { @@ -99,7 +99,7 @@ void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root) list_del(&root->link); - zap_gfn_range(kvm, root, 0, max_gfn, false); + zap_gfn_range(kvm, root, 0, max_gfn, false, false); free_page((unsigned long)root->spt); kmem_cache_free(mmu_page_header_cache, root); @@ -404,7 +404,7 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, * If this warning were to trigger it would indicate that there was a * missing MMU notifier or a race with some notifier handler. * A present, leaf SPTE should never be directly replaced with another - * present leaf SPTE pointing to a differnt PFN. A notifier handler + * present leaf SPTE pointing to a different PFN. A notifier handler * should be zapping the SPTE before the main MM's page table is * changed, or the SPTE should be zeroed, and the TLBs flushed by the * thread before replacement. @@ -418,7 +418,7 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, /* * Crash the host to prevent error propagation and guest data - * courruption. + * corruption. */ BUG(); } @@ -529,7 +529,7 @@ static inline bool tdp_mmu_zap_spte_atomic(struct kvm *kvm, /* * No other thread can overwrite the removed SPTE as they * must either wait on the MMU lock or use - * tdp_mmu_set_spte_atomic which will not overrite the + * tdp_mmu_set_spte_atomic which will not overwrite the * special removed SPTE value. No bookkeeping is needed * here since the SPTE is going from non-present * to non-present. @@ -668,20 +668,21 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm, * scheduler needs the CPU or there is contention on the MMU lock. If this * function cannot yield, it will not release the MMU lock or reschedule and * the caller must ensure it does not supply too large a GFN range, or the - * operation can cause a soft lockup. + * operation can cause a soft lockup. Note, in some use cases a flush may be + * required by prior actions. Ensure the pending flush is performed prior to + * yielding. */ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t start, gfn_t end, bool can_yield) + gfn_t start, gfn_t end, bool can_yield, bool flush) { struct tdp_iter iter; - bool flush_needed = false; rcu_read_lock(); tdp_root_for_each_pte(iter, root, start, end) { if (can_yield && - tdp_mmu_iter_cond_resched(kvm, &iter, flush_needed)) { - flush_needed = false; + tdp_mmu_iter_cond_resched(kvm, &iter, flush)) { + flush = false; continue; } @@ -699,11 +700,11 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, continue; tdp_mmu_set_spte(kvm, &iter, 0); - flush_needed = true; + flush = true; } rcu_read_unlock(); - return flush_needed; + return flush; } /* @@ -712,13 +713,14 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, * SPTEs have been cleared and a TLB flush is needed before releasing the * MMU lock. */ -bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end) +bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end, + bool can_yield) { struct kvm_mmu_page *root; bool flush = false; for_each_tdp_mmu_root_yield_safe(kvm, root) - flush |= zap_gfn_range(kvm, root, start, end, true); + flush = zap_gfn_range(kvm, root, start, end, can_yield, flush); return flush; } @@ -930,7 +932,7 @@ static int zap_gfn_range_hva_wrapper(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end, unsigned long unused) { - return zap_gfn_range(kvm, root, start, end, false); + return zap_gfn_range(kvm, root, start, end, false, false); } int kvm_tdp_mmu_zap_hva_range(struct kvm *kvm, unsigned long start, diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 3b761c111bff..31096ece9b14 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -8,7 +8,29 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root); -bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end); +bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end, + bool can_yield); +static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, + gfn_t end) +{ + return __kvm_tdp_mmu_zap_gfn_range(kvm, start, end, true); +} +static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + gfn_t end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level); + + /* + * Don't allow yielding, as the caller may have a flush pending. Note, + * if mmu_lock is held for write, zapping will never yield in this case, + * but explicitly disallow it for safety. The TDP MMU does not yield + * until it has made forward progress (steps sideways), and when zapping + * a single shadow page that it's guaranteed to see (thus the mmu_lock + * requirement), its "step sideways" will always step beyond the bounds + * of the shadow page's gfn range and stop iterating before yielding. + */ + lockdep_assert_held_write(&kvm->mmu_lock); + return __kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, end, false); +} void kvm_tdp_mmu_zap_all(struct kvm *kvm); int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 7b30bc967af3..67e753edfa22 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -103,7 +103,7 @@ static inline bool kvm_valid_perf_global_ctrl(struct kvm_pmu *pmu, /* returns general purpose PMC with the specified MSR. Note that it can be * used for both PERFCTRn and EVNTSELn; that is why it accepts base as a - * paramenter to tell them apart. + * parameter to tell them apart. */ static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, u32 base) diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 78bdcfac4e40..3e55674098be 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -727,7 +727,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) struct amd_svm_iommu_ir *ir; /** - * In some cases, the existing irte is updaed and re-set, + * In some cases, the existing irte is updated and re-set, * so we need to check here if it's already been * added * to the ir_list. */ @@ -838,7 +838,7 @@ int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, * Here, we setup with legacy mode in the following cases: * 1. When cannot target interrupt to a specific vcpu. * 2. Unsetting posted interrupt. - * 3. APIC virtialization is disabled for the vcpu. + * 3. APIC virtualization is disabled for the vcpu. * 4. IRQ has incompatible delivery mode (SMI, INIT, etc) */ if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set && diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 35891d9a1099..fb204eaa8bb3 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -246,11 +246,18 @@ static bool nested_vmcb_check_controls(struct vmcb_control_area *control) return true; } -static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12) +static bool nested_vmcb_check_save(struct vcpu_svm *svm, struct vmcb *vmcb12) { struct kvm_vcpu *vcpu = &svm->vcpu; bool vmcb12_lma; + /* + * FIXME: these should be done after copying the fields, + * to avoid TOC/TOU races. For these save area checks + * the possible damage is limited since kvm_set_cr0 and + * kvm_set_cr4 handle failure; EFER_SVME is an exception + * so it is force-set later in nested_prepare_vmcb_save. + */ if ((vmcb12->save.efer & EFER_SVME) == 0) return false; @@ -271,7 +278,7 @@ static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12) if (!kvm_is_valid_cr4(&svm->vcpu, vmcb12->save.cr4)) return false; - return nested_vmcb_check_controls(&vmcb12->control); + return true; } static void load_nested_vmcb_control(struct vcpu_svm *svm, @@ -396,7 +403,14 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12) svm->vmcb->save.gdtr = vmcb12->save.gdtr; svm->vmcb->save.idtr = vmcb12->save.idtr; kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED); - svm_set_efer(&svm->vcpu, vmcb12->save.efer); + + /* + * Force-set EFER_SVME even though it is checked earlier on the + * VMCB12, because the guest can flip the bit between the check + * and now. Clearing EFER_SVME would call svm_free_nested. + */ + svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME); + svm_set_cr0(&svm->vcpu, vmcb12->save.cr0); svm_set_cr4(&svm->vcpu, vmcb12->save.cr4); svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = vmcb12->save.cr2; @@ -468,7 +482,6 @@ int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb12_gpa, svm->nested.vmcb12_gpa = vmcb12_gpa; - load_nested_vmcb_control(svm, &vmcb12->control); nested_prepare_vmcb_control(svm); nested_prepare_vmcb_save(svm, vmcb12); @@ -515,7 +528,10 @@ int nested_svm_vmrun(struct vcpu_svm *svm) if (WARN_ON_ONCE(!svm->nested.initialized)) return -EINVAL; - if (!nested_vmcb_checks(svm, vmcb12)) { + load_nested_vmcb_control(svm, &vmcb12->control); + + if (!nested_vmcb_check_save(svm, vmcb12) || + !nested_vmcb_check_controls(&svm->nested.ctl)) { vmcb12->control.exit_code = SVM_EXIT_ERR; vmcb12->control.exit_code_hi = 0; vmcb12->control.exit_info_1 = 0; @@ -1209,6 +1225,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, */ if (!(save->cr0 & X86_CR0_PG)) goto out_free; + if (!(save->efer & EFER_SVME)) + goto out_free; /* * All checks done, we can enter guest mode. L1 control fields diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 035da07500e8..fdf587f19c5f 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -98,6 +98,8 @@ static enum index msr_to_index(u32 msr) static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, enum pmu_type type) { + struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); + switch (msr) { case MSR_F15H_PERF_CTL0: case MSR_F15H_PERF_CTL1: @@ -105,6 +107,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, case MSR_F15H_PERF_CTL3: case MSR_F15H_PERF_CTL4: case MSR_F15H_PERF_CTL5: + if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) + return NULL; + fallthrough; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: if (type != PMU_TYPE_EVNTSEL) return NULL; @@ -115,6 +120,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, case MSR_F15H_PERF_CTR3: case MSR_F15H_PERF_CTR4: case MSR_F15H_PERF_CTR5: + if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) + return NULL; + fallthrough; case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: if (type != PMU_TYPE_COUNTER) return NULL; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 874ea309279f..415a49b8b8f8 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -14,6 +14,7 @@ #include <linux/psp-sev.h> #include <linux/pagemap.h> #include <linux/swap.h> +#include <linux/misc_cgroup.h> #include <linux/processor.h> #include <linux/trace_events.h> #include <asm/fpu/internal.h> @@ -28,6 +29,21 @@ #define __ex(x) __kvm_handle_fault_on_reboot(x) +#ifndef CONFIG_KVM_AMD_SEV +/* + * When this config is not defined, SEV feature is not supported and APIs in + * this file are not used but this file still gets compiled into the KVM AMD + * module. + * + * We will not have MISC_CG_RES_SEV and MISC_CG_RES_SEV_ES entries in the enum + * misc_res_type {} defined in linux/misc_cgroup.h. + * + * Below macros allow compilation to succeed. + */ +#define MISC_CG_RES_SEV MISC_CG_RES_TYPES +#define MISC_CG_RES_SEV_ES MISC_CG_RES_TYPES +#endif + static u8 sev_enc_bit; static int sev_flush_asids(void); static DECLARE_RWSEM(sev_deactivate_lock); @@ -89,8 +105,19 @@ static bool __sev_recycle_asids(int min_asid, int max_asid) static int sev_asid_new(struct kvm_sev_info *sev) { - int pos, min_asid, max_asid; + int pos, min_asid, max_asid, ret; bool retry = true; + enum misc_res_type type; + + type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; + WARN_ON(sev->misc_cg); + sev->misc_cg = get_current_misc_cg(); + ret = misc_cg_try_charge(type, sev->misc_cg, 1); + if (ret) { + put_misc_cg(sev->misc_cg); + sev->misc_cg = NULL; + return ret; + } mutex_lock(&sev_bitmap_lock); @@ -108,7 +135,8 @@ again: goto again; } mutex_unlock(&sev_bitmap_lock); - return -EBUSY; + ret = -EBUSY; + goto e_uncharge; } __set_bit(pos, sev_asid_bitmap); @@ -116,6 +144,11 @@ again: mutex_unlock(&sev_bitmap_lock); return pos + 1; +e_uncharge: + misc_cg_uncharge(type, sev->misc_cg, 1); + put_misc_cg(sev->misc_cg); + sev->misc_cg = NULL; + return ret; } static int sev_get_asid(struct kvm *kvm) @@ -125,14 +158,15 @@ static int sev_get_asid(struct kvm *kvm) return sev->asid; } -static void sev_asid_free(int asid) +static void sev_asid_free(struct kvm_sev_info *sev) { struct svm_cpu_data *sd; int cpu, pos; + enum misc_res_type type; mutex_lock(&sev_bitmap_lock); - pos = asid - 1; + pos = sev->asid - 1; __set_bit(pos, sev_reclaim_asid_bitmap); for_each_possible_cpu(cpu) { @@ -141,6 +175,11 @@ static void sev_asid_free(int asid) } mutex_unlock(&sev_bitmap_lock); + + type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; + misc_cg_uncharge(type, sev->misc_cg, 1); + put_misc_cg(sev->misc_cg); + sev->misc_cg = NULL; } static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) @@ -188,19 +227,20 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) asid = sev_asid_new(sev); if (asid < 0) return ret; + sev->asid = asid; ret = sev_platform_init(&argp->error); if (ret) goto e_free; sev->active = true; - sev->asid = asid; INIT_LIST_HEAD(&sev->regions_list); return 0; e_free: - sev_asid_free(asid); + sev_asid_free(sev); + sev->asid = 0; return ret; } @@ -1315,12 +1355,12 @@ void sev_vm_destroy(struct kvm *kvm) mutex_unlock(&kvm->lock); sev_unbind_asid(kvm, sev->handle); - sev_asid_free(sev->asid); + sev_asid_free(sev); } void __init sev_hardware_setup(void) { - unsigned int eax, ebx, ecx, edx; + unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count; bool sev_es_supported = false; bool sev_supported = false; @@ -1352,7 +1392,11 @@ void __init sev_hardware_setup(void) if (!sev_reclaim_asid_bitmap) goto out; - pr_info("SEV supported: %u ASIDs\n", max_sev_asid - min_sev_asid + 1); + sev_asid_count = max_sev_asid - min_sev_asid + 1; + if (misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)) + goto out; + + pr_info("SEV supported: %u ASIDs\n", sev_asid_count); sev_supported = true; /* SEV-ES support requested? */ @@ -1367,7 +1411,11 @@ void __init sev_hardware_setup(void) if (min_sev_asid == 1) goto out; - pr_info("SEV-ES supported: %u ASIDs\n", min_sev_asid - 1); + sev_es_asid_count = min_sev_asid - 1; + if (misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count)) + goto out; + + pr_info("SEV-ES supported: %u ASIDs\n", sev_es_asid_count); sev_es_supported = true; out: @@ -1382,6 +1430,8 @@ void sev_hardware_teardown(void) bitmap_free(sev_asid_bitmap); bitmap_free(sev_reclaim_asid_bitmap); + misc_cg_set_capacity(MISC_CG_RES_SEV, 0); + misc_cg_set_capacity(MISC_CG_RES_SEV_ES, 0); sev_flush_asids(); } @@ -2082,7 +2132,7 @@ void sev_es_prepare_guest_switch(struct vcpu_svm *svm, unsigned int cpu) hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400); hostsa->xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - /* PKRU is restored on VMEXIT, save the curent host value */ + /* 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 */ diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 58a45bb139f8..6dad89248312 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4400,7 +4400,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int i * * This happens because CPU microcode reading instruction bytes * uses a special opcode which attempts to read data using CPL=0 - * priviledges. The microcode reads CS:RIP and if it hits a SMAP + * privileges. The microcode reads CS:RIP and if it hits a SMAP * fault, it gives up and returns no instruction bytes. * * Detection: diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 39e071fdab0c..9806aaebc37f 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -65,6 +65,7 @@ struct kvm_sev_info { unsigned long pages_locked; /* Number of pages locked */ struct list_head regions_list; /* List of registered regions */ u64 ap_jump_table; /* SEV-ES AP Jump Table address */ + struct misc_cg *misc_cg; /* For misc cgroup accounting */ }; struct kvm_svm { diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index bcca0b80e0d0..1e069aac7410 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3537,7 +3537,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * snapshot restore (migration). * * In this flow, it is assumed that vmcs12 cache was - * trasferred as part of captured nVMX state and should + * transferred as part of captured nVMX state and should * therefore not be read from guest memory (which may not * exist on destination host yet). */ diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 4831bc44ce66..459748680daf 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -10,7 +10,7 @@ #include "vmx.h" /* - * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we + * We maintain a per-CPU linked-list of vCPU, so in wakeup_handler() we * can find which vCPU should be waken up. */ static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 32cf8287d4a7..bcbf0d2139e9 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1529,7 +1529,7 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) /* * MTCFreq, CycThresh and PSBFreq encodings check, any MSR write that - * utilize encodings marked reserved will casue a #GP fault. + * utilize encodings marked reserved will cause a #GP fault. */ value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc_periods); if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc) && @@ -2761,7 +2761,7 @@ static void enter_pmode(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); /* - * Update real mode segment cache. It may be not up-to-date if sement + * Update real mode segment cache. It may be not up-to-date if segment * register was written while vcpu was in a guest mode. */ vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES); @@ -6027,19 +6027,19 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) exit_reason.basic != EXIT_REASON_PML_FULL && exit_reason.basic != EXIT_REASON_APIC_ACCESS && exit_reason.basic != EXIT_REASON_TASK_SWITCH)) { + int ndata = 3; + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; - vcpu->run->internal.ndata = 3; vcpu->run->internal.data[0] = vectoring_info; vcpu->run->internal.data[1] = exit_reason.full; vcpu->run->internal.data[2] = vcpu->arch.exit_qualification; if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) { - vcpu->run->internal.ndata++; - vcpu->run->internal.data[3] = + vcpu->run->internal.data[ndata++] = vmcs_read64(GUEST_PHYSICAL_ADDRESS); } - vcpu->run->internal.data[vcpu->run->internal.ndata++] = - vcpu->arch.last_vmentry_cpu; + vcpu->run->internal.data[ndata++] = vcpu->arch.last_vmentry_cpu; + vcpu->run->internal.ndata = ndata; return 0; } @@ -7252,7 +7252,7 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output)) vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_TOPA; - /* If CPUID.(EAX=14H,ECX=0):ECX[3]=1 FabircEn can be set */ + /* If CPUID.(EAX=14H,ECX=0):ECX[3]=1 FabricEn can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_output_subsys)) vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_FABRIC_EN; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fe806e894212..efc7a82ab140 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -156,9 +156,9 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); /* * lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables - * adaptive tuning starting from default advancment of 1000ns. '0' disables + * adaptive tuning starting from default advancement of 1000ns. '0' disables * advancement entirely. Any other value is used as-is and disables adaptive - * tuning, i.e. allows priveleged userspace to set an exact advancement time. + * 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); @@ -271,8 +271,7 @@ static struct kmem_cache *x86_emulator_cache; * When called, it means the previous get/set msr reached an invalid msr. * Return true if we want to ignore/silent this failed msr access. */ -static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, - u64 data, bool write) +static bool kvm_msr_ignored_check(u32 msr, u64 data, bool write) { const char *op = write ? "wrmsr" : "rdmsr"; @@ -1288,7 +1287,7 @@ static const u32 emulated_msrs_all[] = { MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, MSR_IA32_TSC_ADJUST, - MSR_IA32_TSCDEADLINE, + MSR_IA32_TSC_DEADLINE, MSR_IA32_ARCH_CAPABILITIES, MSR_IA32_PERF_CAPABILITIES, MSR_IA32_MISC_ENABLE, @@ -1373,7 +1372,7 @@ static u64 kvm_get_arch_capabilities(void) /* * If nx_huge_pages is enabled, KVM's shadow paging will ensure that * the nested hypervisor runs with NX huge pages. If it is not, - * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other + * L1 is anyway vulnerable to ITLB_MULTIHIT exploits from other * L1 guests, so it need not worry about its own (L2) guests. */ data |= ARCH_CAP_PSCHANGE_MC_NO; @@ -1445,7 +1444,7 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) if (r == KVM_MSR_RET_INVALID) { /* Unconditionally clear the output for simplicity */ *data = 0; - if (kvm_msr_ignored_check(vcpu, index, 0, false)) + if (kvm_msr_ignored_check(index, 0, false)) r = 0; } @@ -1620,7 +1619,7 @@ static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, int ret = __kvm_set_msr(vcpu, index, data, host_initiated); if (ret == KVM_MSR_RET_INVALID) - if (kvm_msr_ignored_check(vcpu, index, data, true)) + if (kvm_msr_ignored_check(index, data, true)) ret = 0; return ret; @@ -1658,7 +1657,7 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, if (ret == KVM_MSR_RET_INVALID) { /* Unconditionally clear *data for simplicity */ *data = 0; - if (kvm_msr_ignored_check(vcpu, index, 0, false)) + if (kvm_msr_ignored_check(index, 0, false)) ret = 0; } @@ -1850,7 +1849,7 @@ fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) ret = EXIT_FASTPATH_EXIT_HANDLED; } break; - case MSR_IA32_TSCDEADLINE: + case MSR_IA32_TSC_DEADLINE: data = kvm_read_edx_eax(vcpu); if (!handle_fastpath_set_tscdeadline(vcpu, data)) { kvm_skip_emulated_instruction(vcpu); @@ -2329,7 +2328,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) kvm_vcpu_write_tsc_offset(vcpu, offset); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); - spin_lock(&kvm->arch.pvclock_gtod_sync_lock); + spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags); if (!matched) { kvm->arch.nr_vcpus_matched_tsc = 0; } else if (!already_matched) { @@ -2337,7 +2336,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) } kvm_track_tsc_matching(vcpu); - spin_unlock(&kvm->arch.pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags); } static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, @@ -2559,13 +2558,16 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) int i; struct kvm_vcpu *vcpu; struct kvm_arch *ka = &kvm->arch; + unsigned long flags; kvm_hv_invalidate_tsc_page(kvm); - spin_lock(&ka->pvclock_gtod_sync_lock); kvm_make_mclock_inprogress_request(kvm); + /* no guest entries from this point */ + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); pvclock_update_vm_gtod_copy(kvm); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -2573,8 +2575,6 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) /* guest entries allowed */ kvm_for_each_vcpu(i, vcpu, kvm) kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); - - spin_unlock(&ka->pvclock_gtod_sync_lock); #endif } @@ -2582,17 +2582,18 @@ u64 get_kvmclock_ns(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct pvclock_vcpu_time_info hv_clock; + unsigned long flags; u64 ret; - spin_lock(&ka->pvclock_gtod_sync_lock); + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); if (!ka->use_master_clock) { - spin_unlock(&ka->pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); return get_kvmclock_base_ns() + ka->kvmclock_offset; } hv_clock.tsc_timestamp = ka->master_cycle_now; hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; - spin_unlock(&ka->pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); /* both __this_cpu_read() and rdtsc() should be on the same cpu */ get_cpu(); @@ -2686,13 +2687,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) * If the host uses TSC clock, then passthrough TSC as stable * to the guest. */ - spin_lock(&ka->pvclock_gtod_sync_lock); + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); use_master_clock = ka->use_master_clock; if (use_master_clock) { host_tsc = ka->master_cycle_now; kernel_ns = ka->master_kernel_ns; } - spin_unlock(&ka->pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); @@ -3086,7 +3087,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_set_apic_base(vcpu, msr_info); case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_write(vcpu, msr, data); - case MSR_IA32_TSCDEADLINE: + case MSR_IA32_TSC_DEADLINE: kvm_set_lapic_tscdeadline_msr(vcpu, data); break; case MSR_IA32_TSC_ADJUST: @@ -3448,7 +3449,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); - case MSR_IA32_TSCDEADLINE: + case MSR_IA32_TSC_DEADLINE: msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu); break; case MSR_IA32_TSC_ADJUST: @@ -4024,7 +4025,6 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { struct kvm_host_map map; struct kvm_steal_time *st; - int idx; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -4032,15 +4032,9 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) if (vcpu->arch.st.preempted) return; - /* - * Take the srcu lock as memslots will be accessed to check the gfn - * cache generation against the memslots generation. - */ - idx = srcu_read_lock(&vcpu->kvm->srcu); - if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map, &vcpu->arch.st.cache, true)) - goto out; + return; st = map.hva + offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); @@ -4048,20 +4042,25 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true); - -out: - srcu_read_unlock(&vcpu->kvm->srcu, idx); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { + int idx; + if (vcpu->preempted && !vcpu->arch.guest_state_protected) vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu); + /* + * Take the srcu lock as memslots will be accessed to check the gfn + * cache generation against the memslots generation. + */ + idx = srcu_read_lock(&vcpu->kvm->srcu); if (kvm_xen_msr_enabled(vcpu->kvm)) kvm_xen_runstate_set_preempted(vcpu); else kvm_steal_time_set_preempted(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); static_call(kvm_x86_vcpu_put)(vcpu); vcpu->arch.last_host_tsc = rdtsc(); @@ -5726,6 +5725,7 @@ set_pit2_out: } #endif case KVM_SET_CLOCK: { + struct kvm_arch *ka = &kvm->arch; struct kvm_clock_data user_ns; u64 now_ns; @@ -5744,8 +5744,22 @@ set_pit2_out: * pvclock_update_vm_gtod_copy(). */ kvm_gen_update_masterclock(kvm); - now_ns = get_kvmclock_ns(kvm); - kvm->arch.kvmclock_offset += user_ns.clock - now_ns; + + /* + * This pairs with kvm_guest_time_update(): when masterclock is + * in use, we use master_kernel_ns + kvmclock_offset to set + * unsigned 'system_time' so if we use get_kvmclock_ns() (which + * is slightly ahead) here we risk going negative on unsigned + * 'system_time' when 'user_ns.clock' is very small. + */ + spin_lock_irq(&ka->pvclock_gtod_sync_lock); + if (kvm->arch.use_master_clock) + now_ns = ka->master_kernel_ns; + else + now_ns = get_kvmclock_base_ns(); + ka->kvmclock_offset = user_ns.clock - now_ns; + spin_unlock_irq(&ka->pvclock_gtod_sync_lock); + kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); break; } @@ -7724,6 +7738,7 @@ static void kvm_hyperv_tsc_notifier(void) struct kvm *kvm; struct kvm_vcpu *vcpu; int cpu; + unsigned long flags; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) @@ -7739,17 +7754,15 @@ static void kvm_hyperv_tsc_notifier(void) list_for_each_entry(kvm, &vm_list, vm_list) { struct kvm_arch *ka = &kvm->arch; - spin_lock(&ka->pvclock_gtod_sync_lock); - + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); pvclock_update_vm_gtod_copy(kvm); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); kvm_for_each_vcpu(cpu, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); kvm_for_each_vcpu(cpu, vcpu, kvm) kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); - - spin_unlock(&ka->pvclock_gtod_sync_lock); } mutex_unlock(&kvm_lock); } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 39eb04887141..9035e34aa156 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -250,7 +250,6 @@ static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu) void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs); void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); -void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr); u64 get_kvmclock_ns(struct kvm *kvm); int kvm_read_guest_virt(struct kvm_vcpu *vcpu, |