summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/cpuid.c2
-rw-r--r--arch/x86/kvm/emulate.c2
-rw-r--r--arch/x86/kvm/kvm_cache_regs.h51
-rw-r--r--arch/x86/kvm/mmu.h9
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c6
-rw-r--r--arch/x86/kvm/svm/nested.c16
-rw-r--r--arch/x86/kvm/svm/sev.c32
-rw-r--r--arch/x86/kvm/svm/svm.c7
-rw-r--r--arch/x86/kvm/svm/svm.h3
-rw-r--r--arch/x86/kvm/vmx/nested.c44
-rw-r--r--arch/x86/kvm/vmx/pmu_intel.c6
-rw-r--r--arch/x86/kvm/vmx/vmx.c19
-rw-r--r--arch/x86/kvm/x86.c42
-rw-r--r--arch/x86/kvm/x86.h2
14 files changed, 150 insertions, 91 deletions
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 13036cf0b912..38172ca627d3 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -321,7 +321,7 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
if (cpuid->nent < vcpu->arch.cpuid_nent)
goto out;
r = -EFAULT;
- if (copy_to_user(entries, &vcpu->arch.cpuid_entries,
+ if (copy_to_user(entries, vcpu->arch.cpuid_entries,
vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2)))
goto out;
return 0;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 56cae1ff9e3f..66a08322988f 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2879,6 +2879,8 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data);
*reg_write(ctxt, VCPU_REGS_RSP) = (efer & EFER_LMA) ? msr_data :
(u32)msr_data;
+ if (efer & EFER_LMA)
+ ctxt->mode = X86EMUL_MODE_PROT64;
return X86EMUL_CONTINUE;
}
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index f15bc16de07c..a889563ad02d 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -9,31 +9,6 @@
(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \
| X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE)
-static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu,
- enum kvm_reg reg)
-{
- return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
-}
-
-static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu,
- enum kvm_reg reg)
-{
- return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
-}
-
-static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu,
- enum kvm_reg reg)
-{
- __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
-}
-
-static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu,
- enum kvm_reg reg)
-{
- __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
- __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
-}
-
#define BUILD_KVM_GPR_ACCESSORS(lname, uname) \
static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\
{ \
@@ -43,7 +18,6 @@ static __always_inline void kvm_##lname##_write(struct kvm_vcpu *vcpu, \
unsigned long val) \
{ \
vcpu->arch.regs[VCPU_REGS_##uname] = val; \
- kvm_register_mark_dirty(vcpu, VCPU_REGS_##uname); \
}
BUILD_KVM_GPR_ACCESSORS(rax, RAX)
BUILD_KVM_GPR_ACCESSORS(rbx, RBX)
@@ -63,6 +37,31 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14)
BUILD_KVM_GPR_ACCESSORS(r15, R15)
#endif
+static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu,
+ enum kvm_reg reg)
+{
+ return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+}
+
+static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu,
+ enum kvm_reg reg)
+{
+ return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
+}
+
+static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu,
+ enum kvm_reg reg)
+{
+ __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+}
+
+static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu,
+ enum kvm_reg reg)
+{
+ __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+ __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
+}
+
static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg)
{
if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS))
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 581925e476d6..261be1d2032b 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -44,8 +44,15 @@
#define PT32_ROOT_LEVEL 2
#define PT32E_ROOT_LEVEL 3
-static inline u64 rsvd_bits(int s, int e)
+static __always_inline u64 rsvd_bits(int s, int e)
{
+ BUILD_BUG_ON(__builtin_constant_p(e) && __builtin_constant_p(s) && e < s);
+
+ if (__builtin_constant_p(e))
+ BUILD_BUG_ON(e > 63);
+ else
+ e &= 63;
+
if (e < s)
return 0;
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 2ef8615f9dba..b56d604809b8 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1049,8 +1049,8 @@ bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot)
}
/*
- * Clear non-leaf entries (and free associated page tables) which could
- * be replaced by large mappings, for GFNs within the slot.
+ * Clear leaf entries which could be replaced by large mappings, for
+ * GFNs within the slot.
*/
static void zap_collapsible_spte_range(struct kvm *kvm,
struct kvm_mmu_page *root,
@@ -1062,7 +1062,7 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
tdp_root_for_each_pte(iter, root, start, end) {
if (!is_shadow_present_pte(iter.old_spte) ||
- is_last_spte(iter.old_spte, iter.level))
+ !is_last_spte(iter.old_spte, iter.level))
continue;
pfn = spte_to_pfn(iter.old_spte);
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index cb4c6ee10029..db30670dd8c4 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -200,6 +200,9 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (WARN_ON(!is_guest_mode(vcpu)))
+ return true;
+
if (!nested_svm_vmrun_msrpm(svm)) {
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror =
@@ -228,6 +231,7 @@ static bool nested_vmcb_check_controls(struct vmcb_control_area *control)
static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12)
{
+ struct kvm_vcpu *vcpu = &svm->vcpu;
bool vmcb12_lma;
if ((vmcb12->save.efer & EFER_SVME) == 0)
@@ -241,18 +245,10 @@ static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12)
vmcb12_lma = (vmcb12->save.efer & EFER_LME) && (vmcb12->save.cr0 & X86_CR0_PG);
- if (!vmcb12_lma) {
- if (vmcb12->save.cr4 & X86_CR4_PAE) {
- if (vmcb12->save.cr3 & MSR_CR3_LEGACY_PAE_RESERVED_MASK)
- return false;
- } else {
- if (vmcb12->save.cr3 & MSR_CR3_LEGACY_RESERVED_MASK)
- return false;
- }
- } else {
+ if (vmcb12_lma) {
if (!(vmcb12->save.cr4 & X86_CR4_PAE) ||
!(vmcb12->save.cr0 & X86_CR0_PE) ||
- (vmcb12->save.cr3 & MSR_CR3_LONG_MBZ_MASK))
+ (vmcb12->save.cr3 & vcpu->arch.cr3_lm_rsvd_bits))
return false;
}
if (!kvm_is_valid_cr4(&svm->vcpu, vmcb12->save.cr4))
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index c8ffdbc81709..48017fef1cd9 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -342,6 +342,8 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
unsigned long first, last;
int ret;
+ lockdep_assert_held(&kvm->lock);
+
if (ulen == 0 || uaddr + ulen < uaddr)
return ERR_PTR(-EINVAL);
@@ -1119,12 +1121,20 @@ int svm_register_enc_region(struct kvm *kvm,
if (!region)
return -ENOMEM;
+ mutex_lock(&kvm->lock);
region->pages = sev_pin_memory(kvm, range->addr, range->size, &region->npages, 1);
if (IS_ERR(region->pages)) {
ret = PTR_ERR(region->pages);
+ mutex_unlock(&kvm->lock);
goto e_free;
}
+ region->uaddr = range->addr;
+ region->size = range->size;
+
+ list_add_tail(&region->list, &sev->regions_list);
+ mutex_unlock(&kvm->lock);
+
/*
* The guest may change the memory encryption attribute from C=0 -> C=1
* or vice versa for this memory range. Lets make sure caches are
@@ -1133,13 +1143,6 @@ int svm_register_enc_region(struct kvm *kvm,
*/
sev_clflush_pages(region->pages, region->npages);
- region->uaddr = range->addr;
- region->size = range->size;
-
- mutex_lock(&kvm->lock);
- list_add_tail(&region->list, &sev->regions_list);
- mutex_unlock(&kvm->lock);
-
return ret;
e_free:
@@ -1415,16 +1418,13 @@ static void sev_es_sync_to_ghcb(struct vcpu_svm *svm)
* to be returned:
* GPRs RAX, RBX, RCX, RDX
*
- * Copy their values to the GHCB if they are dirty.
+ * Copy their values, even if they may not have been written during the
+ * VM-Exit. It's the guest's responsibility to not consume random data.
*/
- if (kvm_register_is_dirty(vcpu, VCPU_REGS_RAX))
- ghcb_set_rax(ghcb, vcpu->arch.regs[VCPU_REGS_RAX]);
- if (kvm_register_is_dirty(vcpu, VCPU_REGS_RBX))
- ghcb_set_rbx(ghcb, vcpu->arch.regs[VCPU_REGS_RBX]);
- if (kvm_register_is_dirty(vcpu, VCPU_REGS_RCX))
- ghcb_set_rcx(ghcb, vcpu->arch.regs[VCPU_REGS_RCX]);
- if (kvm_register_is_dirty(vcpu, VCPU_REGS_RDX))
- ghcb_set_rdx(ghcb, vcpu->arch.regs[VCPU_REGS_RDX]);
+ ghcb_set_rax(ghcb, vcpu->arch.regs[VCPU_REGS_RAX]);
+ ghcb_set_rbx(ghcb, vcpu->arch.regs[VCPU_REGS_RBX]);
+ ghcb_set_rcx(ghcb, vcpu->arch.regs[VCPU_REGS_RCX]);
+ ghcb_set_rdx(ghcb, vcpu->arch.regs[VCPU_REGS_RDX]);
}
static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 7ef171790d02..3442d44ca53b 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -454,6 +454,11 @@ static int has_svm(void)
return 0;
}
+ if (sev_active()) {
+ pr_info("KVM is unsupported when running as an SEV guest\n");
+ return 0;
+ }
+
return 1;
}
@@ -3739,6 +3744,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ trace_kvm_entry(vcpu);
+
svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 0fe874ae5498..6e7d070f8b86 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -403,9 +403,6 @@ static inline bool gif_set(struct vcpu_svm *svm)
}
/* svm.c */
-#define MSR_CR3_LEGACY_RESERVED_MASK 0xfe7U
-#define MSR_CR3_LEGACY_PAE_RESERVED_MASK 0x7U
-#define MSR_CR3_LONG_MBZ_MASK 0xfff0000000000000U
#define MSR_INVALID 0xffffffffU
extern int sev;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 0fbb46990dfc..f2b9bfb58206 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -3124,13 +3124,9 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
return 0;
}
-static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
+static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu)
{
- struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
struct vcpu_vmx *vmx = to_vmx(vcpu);
- struct kvm_host_map *map;
- struct page *page;
- u64 hpa;
/*
* hv_evmcs may end up being not mapped after migration (when
@@ -3153,6 +3149,17 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
}
}
+ return true;
+}
+
+static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
+{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct kvm_host_map *map;
+ struct page *page;
+ u64 hpa;
+
if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
/*
* Translate L1 physical address to host physical
@@ -3221,6 +3228,18 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
else
exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
+
+ return true;
+}
+
+static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu)
+{
+ if (!nested_get_evmcs_page(vcpu))
+ return false;
+
+ if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu))
+ return false;
+
return true;
}
@@ -6077,11 +6096,14 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
if (is_guest_mode(vcpu)) {
sync_vmcs02_to_vmcs12(vcpu, vmcs12);
sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
- } else if (!vmx->nested.need_vmcs12_to_shadow_sync) {
- if (vmx->nested.hv_evmcs)
- copy_enlightened_to_vmcs12(vmx);
- else if (enable_shadow_vmcs)
- copy_shadow_to_vmcs12(vmx);
+ } else {
+ copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu));
+ if (!vmx->nested.need_vmcs12_to_shadow_sync) {
+ if (vmx->nested.hv_evmcs)
+ copy_enlightened_to_vmcs12(vmx);
+ else if (enable_shadow_vmcs)
+ copy_shadow_to_vmcs12(vmx);
+ }
}
BUILD_BUG_ON(sizeof(user_vmx_nested_state->vmcs12) < VMCS12_SIZE);
@@ -6602,7 +6624,7 @@ struct kvm_x86_nested_ops vmx_nested_ops = {
.hv_timer_pending = nested_vmx_preemption_timer_pending,
.get_state = vmx_get_nested_state,
.set_state = vmx_set_nested_state,
- .get_nested_state_pages = nested_get_vmcs12_pages,
+ .get_nested_state_pages = vmx_get_nested_state_pages,
.write_log_dirty = nested_vmx_write_pml_buffer,
.enable_evmcs = nested_enable_evmcs,
.get_evmcs_version = nested_get_evmcs_version,
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index a886a47daebd..cdf5f34518f4 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -29,7 +29,7 @@ static struct kvm_event_hw_type_mapping intel_arch_events[] = {
[4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES },
[5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
[6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
- [7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES },
+ [7] = { 0x00, 0x03, PERF_COUNT_HW_REF_CPU_CYCLES },
};
/* mapping between fixed pmc index and intel_arch_events array */
@@ -345,7 +345,9 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
x86_pmu.num_counters_gp);
+ eax.split.bit_width = min_t(int, eax.split.bit_width, x86_pmu.bit_width_gp);
pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1;
+ eax.split.mask_length = min_t(int, eax.split.mask_length, x86_pmu.events_mask_len);
pmu->available_event_types = ~entry->ebx &
((1ull << eax.split.mask_length) - 1);
@@ -355,6 +357,8 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
pmu->nr_arch_fixed_counters =
min_t(int, edx.split.num_counters_fixed,
x86_pmu.num_counters_fixed);
+ edx.split.bit_width_fixed = min_t(int,
+ edx.split.bit_width_fixed, x86_pmu.bit_width_fixed);
pmu->counter_bitmask[KVM_PMC_FIXED] =
((u64)1 << edx.split.bit_width_fixed) - 1;
}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 2af05d3b0590..eb69fef57485 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6653,6 +6653,8 @@ reenter_guest:
if (vmx->emulation_required)
return EXIT_FASTPATH_NONE;
+ trace_kvm_entry(vcpu);
+
if (vmx->ple_window_dirty) {
vmx->ple_window_dirty = false;
vmcs_write32(PLE_WINDOW, vmx->ple_window);
@@ -6858,11 +6860,20 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
switch (index) {
case MSR_IA32_TSX_CTRL:
/*
- * No need to pass TSX_CTRL_CPUID_CLEAR through, so
- * let's avoid changing CPUID bits under the host
- * kernel's feet.
+ * TSX_CTRL_CPUID_CLEAR is handled in the CPUID
+ * interception. Keep the host value unchanged to avoid
+ * changing CPUID bits under the host kernel's feet.
+ *
+ * hle=0, rtm=0, tsx_ctrl=1 can be found with some
+ * combinations of new kernel and old userspace. If
+ * those guests run on a tsx=off host, do allow guests
+ * to use TSX_CTRL, but do not change the value on the
+ * host so that TSX remains always disabled.
*/
- vmx->guest_uret_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
+ if (boot_cpu_has(X86_FEATURE_RTM))
+ vmx->guest_uret_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
+ else
+ vmx->guest_uret_msrs[j].mask = 0;
break;
default:
vmx->guest_uret_msrs[j].mask = -1ull;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9a8969a6dd06..1b404e4d7dd8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -105,6 +105,7 @@ static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;
static void update_cr8_intercept(struct kvm_vcpu *vcpu);
static void process_nmi(struct kvm_vcpu *vcpu);
+static void process_smi(struct kvm_vcpu *vcpu);
static void enter_smm(struct kvm_vcpu *vcpu);
static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
static void store_regs(struct kvm_vcpu *vcpu);
@@ -1393,16 +1394,24 @@ static u64 kvm_get_arch_capabilities(void)
if (!boot_cpu_has_bug(X86_BUG_MDS))
data |= ARCH_CAP_MDS_NO;
- /*
- * On TAA affected systems:
- * - nothing to do if TSX is disabled on the host.
- * - we emulate TSX_CTRL if present on the host.
- * This lets the guest use VERW to clear CPU buffers.
- */
- if (!boot_cpu_has(X86_FEATURE_RTM))
- data &= ~(ARCH_CAP_TAA_NO | ARCH_CAP_TSX_CTRL_MSR);
- else if (!boot_cpu_has_bug(X86_BUG_TAA))
+ if (!boot_cpu_has(X86_FEATURE_RTM)) {
+ /*
+ * If RTM=0 because the kernel has disabled TSX, the host might
+ * have TAA_NO or TSX_CTRL. Clear TAA_NO (the guest sees RTM=0
+ * and therefore knows that there cannot be TAA) but keep
+ * TSX_CTRL: some buggy userspaces leave it set on tsx=on hosts,
+ * and we want to allow migrating those guests to tsx=off hosts.
+ */
+ data &= ~ARCH_CAP_TAA_NO;
+ } else if (!boot_cpu_has_bug(X86_BUG_TAA)) {
data |= ARCH_CAP_TAA_NO;
+ } else {
+ /*
+ * Nothing to do here; we emulate TSX_CTRL if present on the
+ * host so the guest can choose between disabling TSX or
+ * using VERW to clear CPU buffers.
+ */
+ }
return data;
}
@@ -4230,6 +4239,9 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
{
process_nmi(vcpu);
+ if (kvm_check_request(KVM_REQ_SMI, vcpu))
+ process_smi(vcpu);
+
/*
* In guest mode, payload delivery should be deferred,
* so that the L1 hypervisor can intercept #PF before
@@ -8802,9 +8814,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (kvm_request_pending(vcpu)) {
if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
- if (WARN_ON_ONCE(!is_guest_mode(vcpu)))
- ;
- else if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
+ if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
r = 0;
goto out;
}
@@ -8988,8 +8998,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
kvm_x86_ops.request_immediate_exit(vcpu);
}
- trace_kvm_entry(vcpu);
-
fpregs_assert_state_consistent();
if (test_thread_flag(TIF_NEED_FPU_LOAD))
switch_fpu_return();
@@ -9616,6 +9624,8 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
*/
if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA))
return false;
+ if (sregs->cr3 & vcpu->arch.cr3_lm_rsvd_bits)
+ return false;
} else {
/*
* Not in 64-bit mode: EFER.LMA is clear and the code
@@ -9993,6 +10003,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
fx_init(vcpu);
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
+ vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63);
vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT;
@@ -10494,7 +10505,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
return 0;
old_npages = slot->npages;
- hva = 0;
+ hva = slot->userspace_addr;
}
for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
@@ -11556,6 +11567,7 @@ int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size,
}
EXPORT_SYMBOL_GPL(kvm_sev_es_string_io);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_entry);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index c5ee0f5ce0f1..0f727b50bd3d 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -425,6 +425,8 @@ bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type);
__reserved_bits |= X86_CR4_UMIP; \
if (!__cpu_has(__c, X86_FEATURE_VMX)) \
__reserved_bits |= X86_CR4_VMXE; \
+ if (!__cpu_has(__c, X86_FEATURE_PCID)) \
+ __reserved_bits |= X86_CR4_PCIDE; \
__reserved_bits; \
})
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-23 02:29:00 +0000