diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-07-04 01:32:22 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-07-04 01:32:22 +0300 |
commit | e8069f5a8e3bdb5fdeeff895780529388592ee7a (patch) | |
tree | ce35ab85db9b66a7e488707fccdb33ce54f696dd /arch/x86/kvm | |
parent | eded37770c9f80ecd5ba842359c4f1058d9812c3 (diff) | |
parent | 255006adb3da71bb75c334453786df781b415f54 (diff) | |
download | linux-e8069f5a8e3bdb5fdeeff895780529388592ee7a.tar.xz |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini:
"ARM64:
- Eager page splitting optimization for dirty logging, optionally
allowing for a VM to avoid the cost of hugepage splitting in the
stage-2 fault path.
- Arm FF-A proxy for pKVM, allowing a pKVM host to safely interact
with services that live in the Secure world. pKVM intervenes on
FF-A calls to guarantee the host doesn't misuse memory donated to
the hyp or a pKVM guest.
- Support for running the split hypervisor with VHE enabled, known as
'hVHE' mode. This is extremely useful for testing the split
hypervisor on VHE-only systems, and paves the way for new use cases
that depend on having two TTBRs available at EL2.
- Generalized framework for configurable ID registers from userspace.
KVM/arm64 currently prevents arbitrary CPU feature set
configuration from userspace, but the intent is to relax this
limitation and allow userspace to select a feature set consistent
with the CPU.
- Enable the use of Branch Target Identification (FEAT_BTI) in the
hypervisor.
- Use a separate set of pointer authentication keys for the
hypervisor when running in protected mode, as the host is untrusted
at runtime.
- Ensure timer IRQs are consistently released in the init failure
paths.
- Avoid trapping CTR_EL0 on systems with Enhanced Virtualization
Traps (FEAT_EVT), as it is a register commonly read from userspace.
- Erratum workaround for the upcoming AmpereOne part, which has
broken hardware A/D state management.
RISC-V:
- Redirect AMO load/store misaligned traps to KVM guest
- Trap-n-emulate AIA in-kernel irqchip for KVM guest
- Svnapot support for KVM Guest
s390:
- New uvdevice secret API
- CMM selftest and fixes
- fix racy access to target CPU for diag 9c
x86:
- Fix missing/incorrect #GP checks on ENCLS
- Use standard mmu_notifier hooks for handling APIC access page
- Drop now unnecessary TR/TSS load after VM-Exit on AMD
- Print more descriptive information about the status of SEV and
SEV-ES during module load
- Add a test for splitting and reconstituting hugepages during and
after dirty logging
- Add support for CPU pinning in demand paging test
- Add support for AMD PerfMonV2, with a variety of cleanups and minor
fixes included along the way
- Add a "nx_huge_pages=never" option to effectively avoid creating NX
hugepage recovery threads (because nx_huge_pages=off can be toggled
at runtime)
- Move handling of PAT out of MTRR code and dedup SVM+VMX code
- Fix output of PIC poll command emulation when there's an interrupt
- Add a maintainer's handbook to document KVM x86 processes,
preferred coding style, testing expectations, etc.
- Misc cleanups, fixes and comments
Generic:
- Miscellaneous bugfixes and cleanups
Selftests:
- Generate dependency files so that partial rebuilds work as
expected"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (153 commits)
Documentation/process: Add a maintainer handbook for KVM x86
Documentation/process: Add a label for the tip tree handbook's coding style
KVM: arm64: Fix misuse of KVM_ARM_VCPU_POWER_OFF bit index
RISC-V: KVM: Remove unneeded semicolon
RISC-V: KVM: Allow Svnapot extension for Guest/VM
riscv: kvm: define vcpu_sbi_ext_pmu in header
RISC-V: KVM: Expose IMSIC registers as attributes of AIA irqchip
RISC-V: KVM: Add in-kernel virtualization of AIA IMSIC
RISC-V: KVM: Expose APLIC registers as attributes of AIA irqchip
RISC-V: KVM: Add in-kernel emulation of AIA APLIC
RISC-V: KVM: Implement device interface for AIA irqchip
RISC-V: KVM: Skeletal in-kernel AIA irqchip support
RISC-V: KVM: Set kvm_riscv_aia_nr_hgei to zero
RISC-V: KVM: Add APLIC related defines
RISC-V: KVM: Add IMSIC related defines
RISC-V: KVM: Implement guest external interrupt line management
KVM: x86: Remove PRIx* definitions as they are solely for user space
s390/uv: Update query for secret-UVCs
s390/uv: replace scnprintf with sysfs_emit
s390/uvdevice: Add 'Lock Secret Store' UVC
...
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/cpuid.c | 43 | ||||
-rw-r--r-- | arch/x86/kvm/i8259.c | 3 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 5 | ||||
-rw-r--r-- | arch/x86/kvm/mmu/mmu.c | 53 | ||||
-rw-r--r-- | arch/x86/kvm/mmu/tdp_mmu.c | 5 | ||||
-rw-r--r-- | arch/x86/kvm/mtrr.c | 64 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.c | 92 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.h | 56 | ||||
-rw-r--r-- | arch/x86/kvm/reverse_cpuid.h | 7 | ||||
-rw-r--r-- | arch/x86/kvm/svm/pmu.c | 68 | ||||
-rw-r--r-- | arch/x86/kvm/svm/sev.c | 19 | ||||
-rw-r--r-- | arch/x86/kvm/svm/svm.c | 56 | ||||
-rw-r--r-- | arch/x86/kvm/svm/svm.h | 1 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/capabilities.h | 4 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/nested.c | 7 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/pmu_intel.c | 79 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/sgx.c | 15 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmenter.S | 2 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 77 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmx.h | 12 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 80 | ||||
-rw-r--r-- | arch/x86/kvm/x86.h | 1 |
22 files changed, 470 insertions, 279 deletions
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 0c9660a07b23..7f4d13383cf2 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -501,20 +501,15 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries) { - int r; - - r = -E2BIG; if (cpuid->nent < vcpu->arch.cpuid_nent) - goto out; - r = -EFAULT; + return -E2BIG; + if (copy_to_user(entries, vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2))) - goto out; - return 0; + return -EFAULT; -out: cpuid->nent = vcpu->arch.cpuid_nent; - return r; + return 0; } /* Mask kvm_cpu_caps for @leaf with the raw CPUID capabilities of this CPU. */ @@ -734,6 +729,10 @@ void kvm_set_cpu_caps(void) F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ ); + kvm_cpu_cap_init_kvm_defined(CPUID_8000_0022_EAX, + F(PERFMON_V2) + ); + /* * Synthesize "LFENCE is serializing" into the AMD-defined entry in * KVM's supported CPUID if the feature is reported as supported by the @@ -948,7 +947,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) union cpuid10_eax eax; union cpuid10_edx edx; - if (!static_cpu_has(X86_FEATURE_ARCH_PERFMON)) { + if (!enable_pmu || !static_cpu_has(X86_FEATURE_ARCH_PERFMON)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; } @@ -1128,7 +1127,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->edx = 0; break; case 0x80000000: - entry->eax = min(entry->eax, 0x80000021); + entry->eax = min(entry->eax, 0x80000022); /* * Serializing LFENCE is reported in a multitude of ways, and * NullSegClearsBase is not reported in CPUID on Zen2; help @@ -1233,6 +1232,28 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ebx = entry->ecx = entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0021_EAX); break; + /* AMD Extended Performance Monitoring and Debug */ + case 0x80000022: { + union cpuid_0x80000022_ebx ebx; + + entry->ecx = entry->edx = 0; + if (!enable_pmu || !kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2)) { + entry->eax = entry->ebx; + break; + } + + cpuid_entry_override(entry, CPUID_8000_0022_EAX); + + if (kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2)) + ebx.split.num_core_pmc = kvm_pmu_cap.num_counters_gp; + else if (kvm_cpu_cap_has(X86_FEATURE_PERFCTR_CORE)) + ebx.split.num_core_pmc = AMD64_NUM_COUNTERS_CORE; + else + ebx.split.num_core_pmc = AMD64_NUM_COUNTERS; + + entry->ebx = ebx.full; + break; + } /*Add support for Centaur's CPUID instruction*/ case 0xC0000000: /*Just support up to 0xC0000004 now*/ diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 4756bcb5724f..8dec646e764b 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -411,7 +411,10 @@ static u32 pic_poll_read(struct kvm_kpic_state *s, u32 addr1) pic_clear_isr(s, ret); if (addr1 >> 7 || ret != 2) pic_update_irq(s->pics_state); + /* Bit 7 is 1, means there's an interrupt */ + ret |= 0x80; } else { + /* Bit 7 is 0, means there's no interrupt */ ret = 0x07; pic_update_irq(s->pics_state); } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 3c300a196bdf..113ca9661ab2 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -51,11 +51,6 @@ #define mod_64(x, y) ((x) % (y)) #endif -#define PRId64 "d" -#define PRIx64 "llx" -#define PRIu64 "u" -#define PRIo64 "o" - /* 14 is the version for Xeon and Pentium 8.4.8*/ #define APIC_VERSION 0x14UL #define LAPIC_MMIO_LENGTH (1 << 12) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 6eaa3d6994ae..ec169f5c7dce 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -58,6 +58,8 @@ extern bool itlb_multihit_kvm_mitigation; +static bool nx_hugepage_mitigation_hard_disabled; + int __read_mostly nx_huge_pages = -1; static uint __read_mostly nx_huge_pages_recovery_period_ms; #ifdef CONFIG_PREEMPT_RT @@ -67,12 +69,13 @@ static uint __read_mostly nx_huge_pages_recovery_ratio = 0; static uint __read_mostly nx_huge_pages_recovery_ratio = 60; #endif +static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp); static int set_nx_huge_pages(const char *val, const struct kernel_param *kp); static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp); static const struct kernel_param_ops nx_huge_pages_ops = { .set = set_nx_huge_pages, - .get = param_get_bool, + .get = get_nx_huge_pages, }; static const struct kernel_param_ops nx_huge_pages_recovery_param_ops = { @@ -1600,6 +1603,10 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) if (tdp_mmu_enabled) flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); + if (kvm_x86_ops.set_apic_access_page_addr && + range->slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT) + kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); + return flush; } @@ -5797,6 +5804,14 @@ static void __kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu vcpu_clear_mmio_info(vcpu, addr); + /* + * Walking and synchronizing SPTEs both assume they are operating in + * the context of the current MMU, and would need to be reworked if + * this is ever used to sync the guest_mmu, e.g. to emulate INVEPT. + */ + if (WARN_ON_ONCE(mmu != vcpu->arch.mmu)) + return; + if (!VALID_PAGE(root_hpa)) return; @@ -6844,6 +6859,14 @@ static void mmu_destroy_caches(void) kmem_cache_destroy(mmu_page_header_cache); } +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 param_get_bool(buffer, kp); +} + static bool get_nx_auto_mode(void) { /* Return true when CPU has the bug, and mitigations are ON */ @@ -6860,15 +6883,29 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) bool old_val = nx_huge_pages; bool new_val; + if (nx_hugepage_mitigation_hard_disabled) + return -EPERM; + /* In "auto" mode deploy workaround only if CPU has the bug. */ - if (sysfs_streq(val, "off")) + if (sysfs_streq(val, "off")) { new_val = 0; - else if (sysfs_streq(val, "force")) + } else if (sysfs_streq(val, "force")) { new_val = 1; - else if (sysfs_streq(val, "auto")) + } else if (sysfs_streq(val, "auto")) { new_val = get_nx_auto_mode(); - else if (kstrtobool(val, &new_val) < 0) + } else if (sysfs_streq(val, "never")) { + new_val = 0; + + mutex_lock(&kvm_lock); + if (!list_empty(&vm_list)) { + mutex_unlock(&kvm_lock); + return -EBUSY; + } + nx_hugepage_mitigation_hard_disabled = true; + mutex_unlock(&kvm_lock); + } else if (kstrtobool(val, &new_val) < 0) { return -EINVAL; + } __set_nx_huge_pages(new_val); @@ -7006,6 +7043,9 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel uint old_period, new_period; int err; + if (nx_hugepage_mitigation_hard_disabled) + return -EPERM; + was_recovery_enabled = calc_nx_huge_pages_recovery_period(&old_period); err = param_set_uint(val, kp); @@ -7164,6 +7204,9 @@ int kvm_mmu_post_init_vm(struct kvm *kvm) { int err; + if (nx_hugepage_mitigation_hard_disabled) + return 0; + err = kvm_vm_create_worker_thread(kvm, kvm_nx_huge_page_recovery_worker, 0, "kvm-nx-lpage-recovery", &kvm->arch.nx_huge_page_recovery_thread); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 08340219c35a..512163d52194 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -592,7 +592,10 @@ static inline int tdp_mmu_set_spte_atomic(struct kvm *kvm, /* * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and - * does not hold the mmu_lock. + * does not hold the mmu_lock. On failure, i.e. if a different logical + * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with + * the current value, so the caller operates on fresh data, e.g. if it + * retries tdp_mmu_set_spte_atomic() */ if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) return -EBUSY; diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 9fac1ec03463..3eb6e7f47e96 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -25,10 +25,24 @@ #define IA32_MTRR_DEF_TYPE_FE (1ULL << 10) #define IA32_MTRR_DEF_TYPE_TYPE_MASK (0xff) +static bool is_mtrr_base_msr(unsigned int msr) +{ + /* MTRR base MSRs use even numbers, masks use odd numbers. */ + return !(msr & 0x1); +} + +static struct kvm_mtrr_range *var_mtrr_msr_to_range(struct kvm_vcpu *vcpu, + unsigned int msr) +{ + int index = (msr - MTRRphysBase_MSR(0)) / 2; + + return &vcpu->arch.mtrr_state.var_ranges[index]; +} + static bool msr_mtrr_valid(unsigned msr) { switch (msr) { - case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1: + case MTRRphysBase_MSR(0) ... MTRRphysMask_MSR(KVM_NR_VAR_MTRR - 1): case MSR_MTRRfix64K_00000: case MSR_MTRRfix16K_80000: case MSR_MTRRfix16K_A0000: @@ -41,7 +55,6 @@ static bool msr_mtrr_valid(unsigned msr) case MSR_MTRRfix4K_F0000: case MSR_MTRRfix4K_F8000: case MSR_MTRRdefType: - case MSR_IA32_CR_PAT: return true; } return false; @@ -52,7 +65,7 @@ static bool valid_mtrr_type(unsigned t) return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */ } -bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) +static bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) { int i; u64 mask; @@ -60,9 +73,7 @@ bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (!msr_mtrr_valid(msr)) return false; - if (msr == MSR_IA32_CR_PAT) { - return kvm_pat_valid(data); - } else if (msr == MSR_MTRRdefType) { + if (msr == MSR_MTRRdefType) { if (data & ~0xcff) return false; return valid_mtrr_type(data & 0xff); @@ -74,7 +85,8 @@ bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) } /* variable MTRRs */ - WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR)); + WARN_ON(!(msr >= MTRRphysBase_MSR(0) && + msr <= MTRRphysMask_MSR(KVM_NR_VAR_MTRR - 1))); mask = kvm_vcpu_reserved_gpa_bits_raw(vcpu); if ((msr & 1) == 0) { @@ -88,7 +100,6 @@ bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) return (data & mask) == 0; } -EXPORT_SYMBOL_GPL(kvm_mtrr_valid); static bool mtrr_is_enabled(struct kvm_mtrr *mtrr_state) { @@ -308,10 +319,8 @@ static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) { struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; gfn_t start, end; - int index; - if (msr == MSR_IA32_CR_PAT || !tdp_enabled || - !kvm_arch_has_noncoherent_dma(vcpu->kvm)) + if (!tdp_enabled || !kvm_arch_has_noncoherent_dma(vcpu->kvm)) return; if (!mtrr_is_enabled(mtrr_state) && msr != MSR_MTRRdefType) @@ -326,8 +335,7 @@ static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) end = ~0ULL; } else { /* variable range MTRRs. */ - index = (msr - 0x200) / 2; - var_mtrr_range(&mtrr_state->var_ranges[index], &start, &end); + var_mtrr_range(var_mtrr_msr_to_range(vcpu, msr), &start, &end); } kvm_zap_gfn_range(vcpu->kvm, gpa_to_gfn(start), gpa_to_gfn(end)); @@ -342,21 +350,18 @@ static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) { struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; struct kvm_mtrr_range *tmp, *cur; - int index, is_mtrr_mask; - index = (msr - 0x200) / 2; - is_mtrr_mask = msr - 0x200 - 2 * index; - cur = &mtrr_state->var_ranges[index]; + cur = var_mtrr_msr_to_range(vcpu, msr); /* remove the entry if it's in the list. */ if (var_mtrr_range_is_valid(cur)) - list_del(&mtrr_state->var_ranges[index].node); + list_del(&cur->node); /* * Set all illegal GPA bits in the mask, since those bits must * implicitly be 0. The bits are then cleared when reading them. */ - if (!is_mtrr_mask) + if (is_mtrr_base_msr(msr)) cur->base = data; else cur->mask = data | kvm_vcpu_reserved_gpa_bits_raw(vcpu); @@ -382,8 +387,6 @@ int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) *(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index] = data; else if (msr == MSR_MTRRdefType) vcpu->arch.mtrr_state.deftype = data; - else if (msr == MSR_IA32_CR_PAT) - vcpu->arch.pat = data; else set_var_mtrr_msr(vcpu, msr, data); @@ -411,21 +414,16 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return 1; index = fixed_msr_to_range_index(msr); - if (index >= 0) + if (index >= 0) { *pdata = *(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index]; - else if (msr == MSR_MTRRdefType) + } else if (msr == MSR_MTRRdefType) { *pdata = vcpu->arch.mtrr_state.deftype; - else if (msr == MSR_IA32_CR_PAT) - *pdata = vcpu->arch.pat; - else { /* Variable MTRRs */ - int is_mtrr_mask; - - index = (msr - 0x200) / 2; - is_mtrr_mask = msr - 0x200 - 2 * index; - if (!is_mtrr_mask) - *pdata = vcpu->arch.mtrr_state.var_ranges[index].base; + } else { + /* Variable MTRRs */ + if (is_mtrr_base_msr(msr)) + *pdata = var_mtrr_msr_to_range(vcpu, msr)->base; else - *pdata = vcpu->arch.mtrr_state.var_ranges[index].mask; + *pdata = var_mtrr_msr_to_range(vcpu, msr)->mask; *pdata &= ~kvm_vcpu_reserved_gpa_bits_raw(vcpu); } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 1690d41c1830..bf653df86112 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -93,11 +93,6 @@ void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops) #undef __KVM_X86_PMU_OP } -static inline bool pmc_is_globally_enabled(struct kvm_pmc *pmc) -{ - return static_call(kvm_x86_pmu_pmc_is_enabled)(pmc); -} - static void kvm_pmi_trigger_fn(struct irq_work *irq_work) { struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work); @@ -562,6 +557,14 @@ void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu) bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { + switch (msr) { + case MSR_CORE_PERF_GLOBAL_STATUS: + case MSR_CORE_PERF_GLOBAL_CTRL: + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + return kvm_pmu_has_perf_global_ctrl(vcpu_to_pmu(vcpu)); + default: + break; + } return static_call(kvm_x86_pmu_msr_idx_to_pmc)(vcpu, msr) || static_call(kvm_x86_pmu_is_valid_msr)(vcpu, msr); } @@ -577,13 +580,86 @@ static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr) int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - return static_call(kvm_x86_pmu_get_msr)(vcpu, msr_info); + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + u32 msr = msr_info->index; + + switch (msr) { + case MSR_CORE_PERF_GLOBAL_STATUS: + case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS: + msr_info->data = pmu->global_status; + break; + case MSR_AMD64_PERF_CNTR_GLOBAL_CTL: + case MSR_CORE_PERF_GLOBAL_CTRL: + msr_info->data = pmu->global_ctrl; + break; + case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR: + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + msr_info->data = 0; + break; + default: + return static_call(kvm_x86_pmu_get_msr)(vcpu, msr_info); + } + + return 0; } int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - kvm_pmu_mark_pmc_in_use(vcpu, msr_info->index); - return static_call(kvm_x86_pmu_set_msr)(vcpu, msr_info); + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + u32 msr = msr_info->index; + u64 data = msr_info->data; + u64 diff; + + /* + * Note, AMD ignores writes to reserved bits and read-only PMU MSRs, + * whereas Intel generates #GP on attempts to write reserved/RO MSRs. + */ + switch (msr) { + case MSR_CORE_PERF_GLOBAL_STATUS: + if (!msr_info->host_initiated) + return 1; /* RO MSR */ + fallthrough; + case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS: + /* Per PPR, Read-only MSR. Writes are ignored. */ + if (!msr_info->host_initiated) + break; + + if (data & pmu->global_status_mask) + return 1; + + pmu->global_status = data; + break; + case MSR_AMD64_PERF_CNTR_GLOBAL_CTL: + data &= ~pmu->global_ctrl_mask; + fallthrough; + case MSR_CORE_PERF_GLOBAL_CTRL: + if (!kvm_valid_perf_global_ctrl(pmu, data)) + return 1; + + if (pmu->global_ctrl != data) { + diff = pmu->global_ctrl ^ data; + pmu->global_ctrl = data; + reprogram_counters(pmu, diff); + } + break; + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + /* + * GLOBAL_OVF_CTRL, a.k.a. GLOBAL STATUS_RESET, clears bits in + * GLOBAL_STATUS, and so the set of reserved bits is the same. + */ + if (data & pmu->global_status_mask) + return 1; + fallthrough; + case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR: + if (!msr_info->host_initiated) + pmu->global_status &= ~data; + break; + default: + kvm_pmu_mark_pmc_in_use(vcpu, msr_info->index); + return static_call(kvm_x86_pmu_set_msr)(vcpu, msr_info); + } + + return 0; } /* refresh PMU settings. This function generally is called when underlying diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 5c7bbf03b599..7d9ba301c090 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -20,7 +20,6 @@ struct kvm_pmu_ops { bool (*hw_event_available)(struct kvm_pmc *pmc); - bool (*pmc_is_enabled)(struct kvm_pmc *pmc); struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx); struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu, unsigned int idx, u64 *mask); @@ -37,10 +36,25 @@ struct kvm_pmu_ops { const u64 EVENTSEL_EVENT; const int MAX_NR_GP_COUNTERS; + const int MIN_NR_GP_COUNTERS; }; void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops); +static inline bool kvm_pmu_has_perf_global_ctrl(struct kvm_pmu *pmu) +{ + /* + * Architecturally, Intel's SDM states that IA32_PERF_GLOBAL_CTRL is + * supported if "CPUID.0AH: EAX[7:0] > 0", i.e. if the PMU version is + * greater than zero. However, KVM only exposes and emulates the MSR + * to/for the guest if the guest PMU supports at least "Architectural + * Performance Monitoring Version 2". + * + * AMD's version of PERF_GLOBAL_CTRL conveniently shows up with v2. + */ + return pmu->version > 1; +} + static inline u64 pmc_bitmask(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); @@ -161,6 +175,7 @@ extern struct x86_pmu_capability kvm_pmu_cap; static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops) { bool is_intel = boot_cpu_data.x86_vendor == X86_VENDOR_INTEL; + int min_nr_gp_ctrs = pmu_ops->MIN_NR_GP_COUNTERS; /* * Hybrid PMUs don't play nice with virtualization without careful @@ -175,11 +190,15 @@ static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops) perf_get_x86_pmu_capability(&kvm_pmu_cap); /* - * For Intel, only support guest architectural pmu - * on a host with architectural pmu. + * WARN if perf did NOT disable hardware PMU if the number of + * architecturally required GP counters aren't present, i.e. if + * there are a non-zero number of counters, but fewer than what + * is architecturally required. */ - if ((is_intel && !kvm_pmu_cap.version) || - !kvm_pmu_cap.num_counters_gp) + if (!kvm_pmu_cap.num_counters_gp || + WARN_ON_ONCE(kvm_pmu_cap.num_counters_gp < min_nr_gp_ctrs)) + enable_pmu = false; + else if (is_intel && !kvm_pmu_cap.version) enable_pmu = false; } @@ -201,6 +220,33 @@ static inline void kvm_pmu_request_counter_reprogram(struct kvm_pmc *pmc) kvm_make_request(KVM_REQ_PMU, pmc->vcpu); } +static inline void reprogram_counters(struct kvm_pmu *pmu, u64 diff) +{ + int bit; + + if (!diff) + return; + + for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) + set_bit(bit, pmu->reprogram_pmi); + kvm_make_request(KVM_REQ_PMU, pmu_to_vcpu(pmu)); +} + +/* + * Check if a PMC is enabled by comparing it against global_ctrl bits. + * + * If the vPMU doesn't have global_ctrl MSR, all vPMCs are enabled. + */ +static inline bool pmc_is_globally_enabled(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + + if (!kvm_pmu_has_perf_global_ctrl(pmu)) + return true; + + return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl); +} + void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index a5717282bb9c..56cbdb24400a 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -15,6 +15,7 @@ enum kvm_only_cpuid_leafs { CPUID_12_EAX = NCAPINTS, CPUID_7_1_EDX, CPUID_8000_0007_EDX, + CPUID_8000_0022_EAX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, @@ -47,6 +48,9 @@ enum kvm_only_cpuid_leafs { /* CPUID level 0x80000007 (EDX). */ #define KVM_X86_FEATURE_CONSTANT_TSC KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8) +/* CPUID level 0x80000022 (EAX) */ +#define KVM_X86_FEATURE_PERFMON_V2 KVM_X86_FEATURE(CPUID_8000_0022_EAX, 0) + struct cpuid_reg { u32 function; u32 index; @@ -74,6 +78,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_7_1_EDX] = { 7, 1, CPUID_EDX}, [CPUID_8000_0007_EDX] = {0x80000007, 0, CPUID_EDX}, [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, + [CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX}, }; /* @@ -108,6 +113,8 @@ static __always_inline u32 __feature_translate(int x86_feature) 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; } diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 5fa939e411d8..cef5a3d0abd0 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -78,14 +78,6 @@ static bool amd_hw_event_available(struct kvm_pmc *pmc) return true; } -/* check if a PMC is enabled by comparing it against global_ctrl bits. Because - * AMD CPU doesn't have global_ctrl MSR, all PMCs are enabled (return TRUE). - */ -static bool amd_pmc_is_enabled(struct kvm_pmc *pmc) -{ - return true; -} - static bool amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -102,12 +94,6 @@ static struct kvm_pmc *amd_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, return amd_pmc_idx_to_pmc(vcpu_to_pmu(vcpu), idx & ~(3u << 30)); } -static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) -{ - /* All MSRs refer to exactly one PMC, so msr_idx_to_pmc is enough. */ - return false; -} - static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -119,6 +105,29 @@ static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr) return pmc; } +static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + + switch (msr) { + case MSR_K7_EVNTSEL0 ... MSR_K7_PERFCTR3: + return pmu->version > 0; + case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: + return guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE); + case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS: + case MSR_AMD64_PERF_CNTR_GLOBAL_CTL: + case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR: + return pmu->version > 1; + default: + if (msr > MSR_F15H_PERF_CTR5 && + msr < MSR_F15H_PERF_CTL0 + 2 * pmu->nr_arch_gp_counters) + return pmu->version > 1; + break; + } + + return amd_msr_idx_to_pmc(vcpu, msr); +} + static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -172,20 +181,39 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static void amd_pmu_refresh(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + union cpuid_0x80000022_ebx ebx; - if (guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) + pmu->version = 1; + if (guest_cpuid_has(vcpu, X86_FEATURE_PERFMON_V2)) { + pmu->version = 2; + /* + * Note, PERFMON_V2 is also in 0x80000022.0x0, i.e. the guest + * CPUID entry is guaranteed to be non-NULL. + */ + BUILD_BUG_ON(x86_feature_cpuid(X86_FEATURE_PERFMON_V2).function != 0x80000022 || + x86_feature_cpuid(X86_FEATURE_PERFMON_V2).index); + ebx.full = kvm_find_cpuid_entry_index(vcpu, 0x80000022, 0)->ebx; + pmu->nr_arch_gp_counters = ebx.split.num_core_pmc; + } else if (guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) { pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS_CORE; - else + } else { pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS; + } + + pmu->nr_arch_gp_counters = min_t(unsigned int, pmu->nr_arch_gp_counters, + kvm_pmu_cap.num_counters_gp); + + if (pmu->version > 1) { + pmu->global_ctrl_mask = ~((1ull << pmu->nr_arch_gp_counters) - 1); + pmu->global_status_mask = pmu->global_ctrl_mask; + } pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1; pmu->reserved_bits = 0xfffffff000280000ull; pmu->raw_event_mask = AMD64_RAW_EVENT_MASK; - pmu->version = 1; /* not applicable to AMD; but clean them to prevent any fall out */ pmu->counter_bitmask[KVM_PMC_FIXED] = 0; pmu->nr_arch_fixed_counters = 0; - pmu->global_status = 0; bitmap_set(pmu->all_valid_pmc_idx, 0, pmu->nr_arch_gp_counters); } @@ -216,11 +244,12 @@ static void amd_pmu_reset(struct kvm_vcpu *vcpu) 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_is_enabled = amd_pmc_is_enabled, .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, .rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc, .msr_idx_to_pmc = amd_msr_idx_to_pmc, @@ -233,4 +262,5 @@ struct kvm_pmu_ops amd_pmu_ops __initdata = { .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 69ae5e1b3120..07756b7348ae 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2216,10 +2216,7 @@ void __init sev_hardware_setup(void) } 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); + WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)); sev_supported = true; /* SEV-ES support requested? */ @@ -2244,13 +2241,19 @@ void __init sev_hardware_setup(void) goto out; 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); + WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count)); sev_es_supported = true; out: + if (boot_cpu_has(X86_FEATURE_SEV)) + pr_info("SEV %s (ASIDs %u - %u)\n", + sev_supported ? "enabled" : "disabled", + min_sev_asid, max_sev_asid); + if (boot_cpu_has(X86_FEATURE_SEV_ES)) + pr_info("SEV-ES %s (ASIDs %u - %u)\n", + sev_es_supported ? "enabled" : "disabled", + min_sev_asid > 1 ? 1 : 0, min_sev_asid - 1); + sev_enabled = sev_supported; sev_es_enabled = sev_es_supported; #endif diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 54089f990c8f..d381ad424554 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -244,15 +244,6 @@ static u8 rsm_ins_bytes[] = "\x0f\xaa"; static unsigned long iopm_base; -struct kvm_ldttss_desc { - u16 limit0; - u16 base0; - unsigned base1:8, type:5, dpl:2, p:1; - unsigned limit1:4, zero0:3, g:1, base2:8; - u32 base3; - u32 zero1; -} __attribute__((packed)); - DEFINE_PER_CPU(struct svm_cpu_data, svm_data); /* @@ -588,7 +579,6 @@ static int svm_hardware_enable(void) struct svm_cpu_data *sd; uint64_t efer; - struct desc_struct *gdt; int me = raw_smp_processor_id(); rdmsrl(MSR_EFER, efer); @@ -601,9 +591,6 @@ static int svm_hardware_enable(void) sd->next_asid = sd->max_asid + 1; sd->min_asid = max_sev_asid + 1; - gdt = get_current_gdt_rw(); - sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); - wrmsrl(MSR_EFER, efer | EFER_SVME); wrmsrl(MSR_VM_HSAVE_PA, sd->save_area_pa); @@ -752,7 +739,7 @@ static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) BUG_ON(offset == MSR_INVALID); - return !!test_bit(bit_write, &tmp); + return test_bit(bit_write, &tmp); } static void set_msr_interception_bitmap(struct kvm_vcpu *vcpu, u32 *msrpm, @@ -2939,9 +2926,10 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_CR_PAT: - if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) - return 1; - vcpu->arch.pat = data; + ret = kvm_set_msr_common(vcpu, msr); + if (ret) + break; + svm->vmcb01.ptr->save.g_pat = data; if (is_guest_mode(vcpu)) nested_vmcb02_compute_g_pat(svm); @@ -3418,8 +3406,6 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; - trace_kvm_exit(vcpu, KVM_ISA_SVM); - /* SEV-ES guests must use the CR write traps to track CR registers. */ if (!sev_es_guest(vcpu->kvm)) { if (!svm_is_intercept(svm, INTERCEPT_CR0_WRITE)) @@ -3457,14 +3443,6 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return svm_invoke_exit_handler(vcpu, exit_code); } -static void reload_tss(struct kvm_vcpu *vcpu) -{ - struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); - - sd->tss_desc->type = 9; /* available 32/64-bit TSS */ - load_TR_desc(); -} - static void pre_svm_run(struct kvm_vcpu *vcpu) { struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); @@ -4099,9 +4077,6 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) svm_vcpu_enter_exit(vcpu, spec_ctrl_intercepted); - if (!sev_es_guest(vcpu->kvm)) - reload_tss(vcpu); - if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL)) x86_spec_ctrl_restore_host(svm->virt_spec_ctrl); @@ -4156,6 +4131,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) SVM_EXIT_EXCP_BASE + MC_VECTOR)) svm_handle_mce(vcpu); + trace_kvm_exit(vcpu, KVM_ISA_SVM); + svm_complete_interrupts(vcpu); if (is_guest_mode(vcpu)) @@ -5025,9 +5002,22 @@ static __init void svm_set_cpu_caps(void) boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); - /* AMD PMU PERFCTR_CORE CPUID */ - if (enable_pmu && boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) - kvm_cpu_cap_set(X86_FEATURE_PERFCTR_CORE); + if (enable_pmu) { + /* + * Enumerate support for PERFCTR_CORE if and only if KVM has + * access to enough counters to virtualize "core" support, + * otherwise limit vPMU support to the legacy number of counters. + */ + if (kvm_pmu_cap.num_counters_gp < AMD64_NUM_COUNTERS_CORE) + kvm_pmu_cap.num_counters_gp = min(AMD64_NUM_COUNTERS, + kvm_pmu_cap.num_counters_gp); + else + kvm_cpu_cap_check_and_set(X86_FEATURE_PERFCTR_CORE); + + if (kvm_pmu_cap.version != 2 || + !kvm_cpu_cap_has(X86_FEATURE_PERFCTR_CORE)) + kvm_cpu_cap_clear(X86_FEATURE_PERFMON_V2); + } /* CPUID 0x8000001F (SME/SEV features) */ sev_set_cpu_caps(); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index f44751dd8d5d..18af7e712a5a 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -303,7 +303,6 @@ struct svm_cpu_data { u32 max_asid; u32 next_asid; u32 min_asid; - struct kvm_ldttss_desc *tss_desc; struct page *save_area; unsigned long save_area_pa; diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 45162c1bcd8f..d0abee35d7ba 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -152,8 +152,8 @@ static inline bool cpu_has_vmx_ept(void) static inline bool vmx_umip_emulated(void) { - return vmcs_config.cpu_based_2nd_exec_ctrl & - SECONDARY_EXEC_DESC; + return !boot_cpu_has(X86_FEATURE_UMIP) && + (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_DESC); } static inline bool cpu_has_vmx_rdtscp(void) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index e35cf0bd0df9..516391cc0d64 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2328,8 +2328,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 * Preset *DT exiting when emulating UMIP, so that vmx_set_cr4() * will not have to rewrite the controls just for this bit. */ - if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated() && - (vmcs12->guest_cr4 & X86_CR4_UMIP)) + if (vmx_umip_emulated() && (vmcs12->guest_cr4 & X86_CR4_UMIP)) exec_control |= SECONDARY_EXEC_DESC; if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) @@ -2649,7 +2648,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) && - intel_pmu_has_perf_global_ctrl(vcpu_to_pmu(vcpu)) && + kvm_pmu_has_perf_global_ctrl(vcpu_to_pmu(vcpu)) && WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, vmcs12->guest_ia32_perf_global_ctrl))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; @@ -4524,7 +4523,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vcpu->arch.pat = vmcs12->host_ia32_pat; } if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) && - intel_pmu_has_perf_global_ctrl(vcpu_to_pmu(vcpu))) + kvm_pmu_has_perf_global_ctrl(vcpu_to_pmu(vcpu))) WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, vmcs12->host_ia32_perf_global_ctrl)); diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 741efe2c497b..80c769c58a87 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -73,18 +73,6 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) } } -static void reprogram_counters(struct kvm_pmu *pmu, u64 diff) -{ - int bit; - - if (!diff) - return; - - for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) - set_bit(bit, pmu->reprogram_pmi); - kvm_make_request(KVM_REQ_PMU, pmu_to_vcpu(pmu)); -} - static bool intel_hw_event_available(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); @@ -107,17 +95,6 @@ static bool intel_hw_event_available(struct kvm_pmc *pmc) return true; } -/* check if a PMC is enabled by comparing it with globl_ctrl bits. */ -static bool intel_pmc_is_enabled(struct kvm_pmc *pmc) -{ - struct kvm_pmu *pmu = pmc_to_pmu(pmc); - - if (!intel_pmu_has_perf_global_ctrl(pmu)) - return true; - - return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl); -} - static bool intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -198,11 +175,7 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) switch (msr) { case MSR_CORE_PERF_FIXED_CTR_CTRL: - case MSR_CORE_PERF_GLOBAL_STATUS: - case MSR_CORE_PERF_GLOBAL_CTRL: - case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - return intel_pmu_has_perf_global_ctrl(pmu); - break; + return kvm_pmu_has_perf_global_ctrl(pmu); case MSR_IA32_PEBS_ENABLE: ret = vcpu_get_perf_capabilities(vcpu) & PERF_CAP_PEBS_FORMAT; break; @@ -352,15 +325,6 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_CORE_PERF_FIXED_CTR_CTRL: msr_info->data = pmu->fixed_ctr_ctrl; break; - case MSR_CORE_PERF_GLOBAL_STATUS: - msr_info->data = pmu->global_status; - break; - case MSR_CORE_PERF_GLOBAL_CTRL: - msr_info->data = pmu->global_ctrl; - break; - case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - msr_info->data = 0; - break; case MSR_IA32_PEBS_ENABLE: msr_info->data = pmu->pebs_enable; break; @@ -410,29 +374,6 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (pmu->fixed_ctr_ctrl != data) reprogram_fixed_counters(pmu, data); break; - case MSR_CORE_PERF_GLOBAL_STATUS: - if (!msr_info->host_initiated) - return 1; /* RO MSR */ - - pmu->global_status = data; - break; - case MSR_CORE_PERF_GLOBAL_CTRL: - if (!kvm_valid_perf_global_ctrl(pmu, data)) - return 1; - - if (pmu->global_ctrl != data) { - diff = pmu->global_ctrl ^ data; - pmu->global_ctrl = data; - reprogram_counters(pmu, diff); - } - break; - case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - if (data & pmu->global_ovf_ctrl_mask) - return 1; - - if (!msr_info->host_initiated) - pmu->global_status &= ~data; - break; case MSR_IA32_PEBS_ENABLE: if (data & pmu->pebs_enable_mask) return 1; @@ -444,8 +385,6 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } break; case MSR_IA32_DS_AREA: - if (msr_info->host_initiated && data && !guest_cpuid_has(vcpu, X86_FEATURE_DS)) - return 1; if (is_noncanonical_address(data, vcpu)) return 1; @@ -531,7 +470,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->reserved_bits = 0xffffffff00200000ull; pmu->raw_event_mask = X86_RAW_EVENT_MASK; pmu->global_ctrl_mask = ~0ull; - pmu->global_ovf_ctrl_mask = ~0ull; + pmu->global_status_mask = ~0ull; pmu->fixed_ctr_ctrl_mask = ~0ull; pmu->pebs_enable_mask = ~0ull; pmu->pebs_data_cfg_mask = ~0ull; @@ -585,11 +524,17 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) counter_mask = ~(((1ull << pmu->nr_arch_gp_counters) - 1) | (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED)); pmu->global_ctrl_mask = counter_mask; - pmu->global_ovf_ctrl_mask = pmu->global_ctrl_mask + + /* + * GLOBAL_STATUS and GLOBAL_OVF_CONTROL (a.k.a. GLOBAL_STATUS_RESET) + * share reserved bit definitions. The kernel just happens to use + * OVF_CTRL for the names. + */ + pmu->global_status_mask = pmu->global_ctrl_mask & ~(MSR_CORE_PERF_GLOBAL_OVF_CTRL_OVF_BUF | MSR_CORE_PERF_GLOBAL_OVF_CTRL_COND_CHGD); if (vmx_pt_mode_is_host_guest()) - pmu->global_ovf_ctrl_mask &= + pmu->global_status_mask &= ~MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI; entry = kvm_find_cpuid_entry_index(vcpu, 7, 0); @@ -801,7 +746,7 @@ void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu) pmc = intel_pmc_idx_to_pmc(pmu, bit); if (!pmc || !pmc_speculative_in_use(pmc) || - !intel_pmc_is_enabled(pmc) || !pmc->perf_event) + !pmc_is_globally_enabled(pmc) || !pmc->perf_event) continue; /* @@ -816,7 +761,6 @@ void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu) struct kvm_pmu_ops intel_pmu_ops __initdata = { .hw_event_available = intel_hw_event_available, - .pmc_is_enabled = intel_pmc_is_enabled, .pmc_idx_to_pmc = intel_pmc_idx_to_pmc, .rdpmc_ecx_to_pmc = intel_rdpmc_ecx_to_pmc, .msr_idx_to_pmc = intel_msr_idx_to_pmc, @@ -831,4 +775,5 @@ struct kvm_pmu_ops intel_pmu_ops __initdata = { .cleanup = intel_pmu_cleanup, .EVENTSEL_EVENT = ARCH_PERFMON_EVENTSEL_EVENT, .MAX_NR_GP_COUNTERS = KVM_INTEL_PMC_MAX_GENERIC, + .MIN_NR_GP_COUNTERS = 1, }; diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index 2261b684a7d4..3e822e582497 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -357,11 +357,12 @@ static int handle_encls_einit(struct kvm_vcpu *vcpu) static inline bool encls_leaf_enabled_in_guest(struct kvm_vcpu *vcpu, u32 leaf) { - if (!enable_sgx || !guest_cpuid_has(vcpu, X86_FEATURE_SGX)) - return false; - + /* + * ENCLS generates a #UD if SGX1 isn't supported, i.e. this point will + * be reached if and only if the SGX1 leafs are enabled. + */ if (leaf >= ECREATE && leaf <= ETRACK) - return guest_cpuid_has(vcpu, X86_FEATURE_SGX1); + return true; if (leaf >= EAUG && leaf <= EMODT) return guest_cpuid_has(vcpu, X86_FEATURE_SGX2); @@ -380,9 +381,11 @@ int handle_encls(struct kvm_vcpu *vcpu) { u32 leaf = (u32)kvm_rax_read(vcpu); - if (!encls_leaf_enabled_in_guest(vcpu, leaf)) { + if (!enable_sgx || !guest_cpuid_has(vcpu, X86_FEATURE_SGX) || + !guest_cpuid_has(vcpu, X86_FEATURE_SGX1)) { kvm_queue_exception(vcpu, UD_VECTOR); - } else if (!sgx_enabled_in_guest_bios(vcpu)) { + } else if (!encls_leaf_enabled_in_guest(vcpu, leaf) || + !sgx_enabled_in_guest_bios(vcpu) || !is_paging(vcpu)) { kvm_inject_gp(vcpu, 0); } else { if (leaf == ECREATE) diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 631fd7da2bc3..07e927d4d099 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -187,7 +187,7 @@ SYM_FUNC_START(__vmx_vcpu_run) _ASM_EXTABLE(.Lvmresume, .Lfixup) _ASM_EXTABLE(.Lvmlaunch, .Lfixup) -SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) +SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL) /* Restore unwind state from before the VMRESUME/VMLAUNCH. */ UNWIND_HINT_RESTORE diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 44fb619803b8..0ecf4be2c6af 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2287,19 +2287,16 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; goto find_uret_msr; case MSR_IA32_CR_PAT: - if (!kvm_pat_valid(data)) - return 1; + ret = kvm_set_msr_common(vcpu, msr_info); + if (ret) + break; if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT) get_vmcs12(vcpu)->guest_ia32_pat = data; - if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { + if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) vmcs_write64(GUEST_IA32_PAT, data); - vcpu->arch.pat = data; - break; - } - ret = kvm_set_msr_common(vcpu, msr_info); break; case MSR_IA32_MCG_EXT_CTL: if ((!msr_info->host_initiated && @@ -3387,15 +3384,15 @@ static bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { - unsigned long old_cr4 = vcpu->arch.cr4; + unsigned long old_cr4 = kvm_read_cr4(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long hw_cr4; + /* * Pass through host's Machine Check Enable value to hw_cr4, which * is in force while we are in guest mode. Do not let guests control * this bit, even if host CR4.MCE == 0. */ - unsigned long hw_cr4; - hw_cr4 = (cr4_read_shadow() & X86_CR4_MCE) | (cr4 & ~X86_CR4_MCE); if (is_unrestricted_guest(vcpu)) hw_cr4 |= KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST; @@ -3404,7 +3401,7 @@ void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) else hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON; - if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) { + if (vmx_umip_emulated()) { if (cr4 & X86_CR4_UMIP) { secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_DESC); hw_cr4 &= ~X86_CR4_UMIP; @@ -5402,7 +5399,13 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) static int handle_desc(struct kvm_vcpu *vcpu) { - WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP)); + /* + * UMIP emulation relies on intercepting writes to CR4.UMIP, i.e. this + * and other code needs to be updated if UMIP can be guest owned. + */ + BUILD_BUG_ON(KVM_POSSIBLE_CR4_GUEST_BITS & X86_CR4_UMIP); + + WARN_ON_ONCE(!kvm_is_cr4_bit_set(vcpu, X86_CR4_UMIP)); return kvm_emulate_instruction(vcpu, 0); } @@ -6708,7 +6711,12 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) { - struct page *page; + const gfn_t gfn = APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT; + struct kvm *kvm = vcpu->kvm; + struct kvm_memslots *slots = kvm_memslots(kvm); + struct kvm_memory_slot *slot; + unsigned long mmu_seq; + kvm_pfn_t pfn; /* Defer reload until vmcs01 is the current VMCS. */ if (is_guest_mode(vcpu)) { @@ -6720,18 +6728,53 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) return; - page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); - if (is_error_page(page)) + /* + * 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. + */ + slot = id_to_memslot(slots, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT); + if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return; - vmcs_write64(APIC_ACCESS_ADDR, page_to_phys(page)); + /* + * Ensure that the mmu_notifier sequence count is read before KVM + * retrieves the pfn from the primary MMU. Note, the memslot is + * protected by SRCU, not the mmu_notifier. Pairs with the smp_wmb() + * in kvm_mmu_invalidate_end(). + */ + mmu_seq = kvm->mmu_invalidate_seq; + smp_rmb(); + + /* + * No need to retry if the memslot does not exist or is invalid. KVM + * controls the APIC-access page memslot, and only deletes the memslot + * if APICv is permanently inhibited, i.e. the memslot won't reappear. + */ + pfn = gfn_to_pfn_memslot(slot, gfn); + if (is_error_noslot_pfn(pfn)) + return; + + read_lock(&vcpu->kvm->mmu_lock); + if (mmu_invalidate_retry_hva(kvm, mmu_seq, + gfn_to_hva_memslot(slot, gfn))) { + kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); + read_unlock(&vcpu->kvm->mmu_lock); + goto out; + } + + vmcs_write64(APIC_ACCESS_ADDR, pfn_to_hpa(pfn)); + read_unlock(&vcpu->kvm->mmu_lock); + vmx_flush_tlb_current(vcpu); +out: /* * Do not pin apic access page in memory, the MMU notifier * will call us again if it is migrated or swapped out. */ - put_page(page); + kvm_release_pfn_clean(pfn); } static void vmx_hwapic_isr_update(int max_isr) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 9e66531861cf..32384ba38499 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -93,18 +93,6 @@ union vmx_exit_reason { u32 full; }; -static inline bool intel_pmu_has_perf_global_ctrl(struct kvm_pmu *pmu) -{ - /* - * Architecturally, Intel's SDM states that IA32_PERF_GLOBAL_CTRL is - * supported if "CPUID.0AH: EAX[7:0] > 0", i.e. if the PMU version is - * greater than zero. However, KVM only exposes and emulates the MSR - * to/for the guest if the guest PMU supports at least "Architectural - * Performance Monitoring Version 2". - */ - return pmu->version > 1; -} - struct lbr_desc { /* Basic info about guest LBR records. */ struct x86_pmu_lbr records; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7f70207e8689..a6b9bea62fb8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1017,13 +1017,11 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss); } -#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS - if (static_cpu_has(X86_FEATURE_PKU) && + if (cpu_feature_enabled(X86_FEATURE_PKU) && vcpu->arch.pkru != vcpu->arch.host_pkru && ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) write_pkru(vcpu->arch.pkru); -#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */ } EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state); @@ -1032,15 +1030,13 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) if (vcpu->arch.guest_state_protected) return; -#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS - if (static_cpu_has(X86_FEATURE_PKU) && + if (cpu_feature_enabled(X86_FEATURE_PKU) && ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) { vcpu->arch.pkru = rdpkru(); if (vcpu->arch.pkru != vcpu->arch.host_pkru) write_pkru(vcpu->arch.host_pkru); } -#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */ if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) { @@ -1427,15 +1423,14 @@ int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu) EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc); /* - * List of msr numbers which we expose to userspace through KVM_GET_MSRS - * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. - * - * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) - * extract the supported MSRs from the related const lists. - * msrs_to_save is selected from the msrs_to_save_all to reflect the - * capabilities of the host cpu. This capabilities test skips MSRs that are - * kvm-specific. Those are put in emulated_msrs_all; filtering of emulated_msrs - * may depend on host virtualization features rather than host cpu features. + * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) track + * the set of MSRs that KVM exposes to userspace through KVM_GET_MSRS, + * KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. msrs_to_save holds MSRs that + * require host support, i.e. should be probed via RDMSR. emulated_msrs holds + * MSRs that KVM emulates without strictly requiring host support. + * msr_based_features holds MSRs that enumerate features, i.e. are effectively + * CPUID leafs. Note, msr_based_features isn't mutually exclusive with + * msrs_to_save and emulated_msrs. */ static const u32 msrs_to_save_base[] = { @@ -1483,6 +1478,10 @@ static const u32 msrs_to_save_pmu[] = { MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, + + MSR_AMD64_PERF_CNTR_GLOBAL_CTL, + MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, + MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, }; static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) + @@ -1531,11 +1530,11 @@ static const u32 emulated_msrs_all[] = { MSR_IA32_UCODE_REV, /* - * The following list leaves out MSRs whose values are determined - * by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs. - * We always support the "true" VMX control MSRs, even if the host - * processor does not, so I am putting these registers here rather - * than in msrs_to_save_all. + * KVM always supports the "true" VMX control MSRs, even if the host + * does not. The VMX MSRs as a whole are considered "emulated" as KVM + * doesn't strictly require them to exist in the host (ignoring that + * KVM would refuse to load in the first place if the core set of MSRs + * aren't supported). */ MSR_IA32_VMX_BASIC, MSR_IA32_VMX_TRUE_PINBASED_CTLS, @@ -1631,7 +1630,7 @@ static u64 kvm_get_arch_capabilities(void) * If we're doing cache flushes (either "always" or "cond") * we will do one whenever the guest does a vmlaunch/vmresume. * If an outer hypervisor is doing the cache flush for us - * (VMENTER_L1D_FLUSH_NESTED_VM), we can safely pass that + * (ARCH_CAP_SKIP_VMENTRY_L1DFLUSH), we can safely pass that * capability to the guest too, and if EPT is disabled we're not * vulnerable. Overall, only VMENTER_L1D_FLUSH_NEVER will * require a nested hypervisor to do a flush of its own. @@ -1809,7 +1808,7 @@ bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type) unsigned long *bitmap = ranges[i].bitmap; if ((index >= start) && (index < end) && (flags & type)) { - allowed = !!test_bit(index - start, bitmap); + allowed = test_bit(index - start, bitmap); break; } } @@ -3701,8 +3700,14 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; } break; - case 0x200 ... MSR_IA32_MC0_CTL2 - 1: - case MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) ... 0x2ff: + case MSR_IA32_CR_PAT: + if (!kvm_pat_valid(data)) + return 1; + + vcpu->arch.pat = data; + break; + case MTRRphysBase_MSR(0) ... MSR_MTRRfix4K_F8000: + case MSR_MTRRdefType: return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: return kvm_set_apic_base(vcpu, msr_info); @@ -4109,9 +4114,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = kvm_scale_tsc(rdtsc(), ratio) + offset; break; } + case MSR_IA32_CR_PAT: + msr_info->data = vcpu->arch.pat; + break; case MSR_MTRRcap: - case 0x200 ... MSR_IA32_MC0_CTL2 - 1: - case MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) ... 0x2ff: + case MTRRphysBase_MSR(0) ... MSR_MTRRfix4K_F8000: + case MSR_MTRRdefType: return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); case 0xcd: /* fsb frequency */ msr_info->data = 3; @@ -7149,6 +7157,12 @@ static void kvm_probe_msr_to_save(u32 msr_index) kvm_pmu_cap.num_counters_fixed) return; break; + case MSR_AMD64_PERF_CNTR_GLOBAL_CTL: + case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS: + case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR: + if (!kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2)) + return; + break; case MSR_IA32_XFD: case MSR_IA32_XFD_ERR: if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) @@ -10434,20 +10448,6 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors); } -void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, - unsigned long start, unsigned long end) -{ - unsigned long apic_address; - - /* - * The physical address of apic access page is stored in the VMCS. - * Update it when it becomes invalid. - */ - apic_address = gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); - if (start <= apic_address && apic_address < end) - kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); -} - void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) { static_call_cond(kvm_x86_guest_memory_reclaimed)(kvm); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index c544602d07a3..82e3dafc5453 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -309,7 +309,6 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu, void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu); u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); -bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data); int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data); int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, |