summaryrefslogtreecommitdiff
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/cpuid.c22
-rw-r--r--arch/x86/kvm/cpuid.h1
-rw-r--r--arch/x86/kvm/emulate.c15
-rw-r--r--arch/x86/kvm/hyperv.c9
-rw-r--r--arch/x86/kvm/kvm_emulate.h5
-rw-r--r--arch/x86/kvm/lapic.c22
-rw-r--r--arch/x86/kvm/lapic.h8
-rw-r--r--arch/x86/kvm/mmu.h1
-rw-r--r--arch/x86/kvm/mmu/mmu.c124
-rw-r--r--arch/x86/kvm/mtrr.c1
-rw-r--r--arch/x86/kvm/reverse_cpuid.h8
-rw-r--r--arch/x86/kvm/smm.c1
-rw-r--r--arch/x86/kvm/svm/avic.c66
-rw-r--r--arch/x86/kvm/svm/nested.c10
-rw-r--r--arch/x86/kvm/svm/sev.c32
-rw-r--r--arch/x86/kvm/svm/svm.c78
-rw-r--r--arch/x86/kvm/svm/svm.h2
-rw-r--r--arch/x86/kvm/svm/vmenter.S16
-rw-r--r--arch/x86/kvm/vmx/hyperv.c1
-rw-r--r--arch/x86/kvm/vmx/main.c2
-rw-r--r--arch/x86/kvm/vmx/nested.c50
-rw-r--r--arch/x86/kvm/vmx/pmu_intel.c10
-rw-r--r--arch/x86/kvm/vmx/posted_intr.c28
-rw-r--r--arch/x86/kvm/vmx/sgx.c5
-rw-r--r--arch/x86/kvm/vmx/vmx.c97
-rw-r--r--arch/x86/kvm/vmx/vmx.h29
-rw-r--r--arch/x86/kvm/vmx/x86_ops.h5
-rw-r--r--arch/x86/kvm/x86.c112
-rw-r--r--arch/x86/kvm/x86.h48
-rw-r--r--arch/x86/kvm/xen.c17
30 files changed, 593 insertions, 232 deletions
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 83bfecd1a6e4..8f587c5bb6bc 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -814,6 +814,7 @@ void kvm_set_cpu_caps(void)
kvm_cpu_cap_mask(CPUID_8000_0021_EAX,
F(NO_NESTED_DATA_BP) | F(LFENCE_RDTSC) | 0 /* SmmPgCfgLock */ |
+ F(VERW_CLEAR) |
F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ |
F(WRMSR_XX_BASE_NS)
);
@@ -821,11 +822,19 @@ void kvm_set_cpu_caps(void)
kvm_cpu_cap_check_and_set(X86_FEATURE_SBPB);
kvm_cpu_cap_check_and_set(X86_FEATURE_IBPB_BRTYPE);
kvm_cpu_cap_check_and_set(X86_FEATURE_SRSO_NO);
+ kvm_cpu_cap_check_and_set(X86_FEATURE_VERW_CLEAR);
kvm_cpu_cap_init_kvm_defined(CPUID_8000_0022_EAX,
F(PERFMON_V2)
);
+ kvm_cpu_cap_init_kvm_defined(CPUID_8000_0021_ECX,
+ F(TSA_SQ_NO) | F(TSA_L1_NO)
+ );
+
+ kvm_cpu_cap_check_and_set(X86_FEATURE_TSA_SQ_NO);
+ kvm_cpu_cap_check_and_set(X86_FEATURE_TSA_L1_NO);
+
/*
* Synthesize "LFENCE is serializing" into the AMD-defined entry in
* KVM's supported CPUID if the feature is reported as supported by the
@@ -1047,8 +1056,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
}
break;
case 0xa: { /* Architectural Performance Monitoring */
- union cpuid10_eax eax;
- union cpuid10_edx edx;
+ union cpuid10_eax eax = { };
+ union cpuid10_edx edx = { };
if (!enable_pmu || !static_cpu_has(X86_FEATURE_ARCH_PERFMON)) {
entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
@@ -1064,8 +1073,6 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
if (kvm_pmu_cap.version)
edx.split.anythread_deprecated = 1;
- edx.split.reserved1 = 0;
- edx.split.reserved2 = 0;
entry->eax = eax.full;
entry->ebx = kvm_pmu_cap.events_mask;
@@ -1378,16 +1385,17 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
break;
case 0x80000021:
- entry->ebx = entry->ecx = entry->edx = 0;
+ entry->ebx = entry->edx = 0;
cpuid_entry_override(entry, CPUID_8000_0021_EAX);
+ cpuid_entry_override(entry, CPUID_8000_0021_ECX);
break;
/* AMD Extended Performance Monitoring and Debug */
case 0x80000022: {
- union cpuid_0x80000022_ebx ebx;
+ 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;
+ entry->eax = entry->ebx = 0;
break;
}
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index ad479cfb91bc..f16a7b2c2adc 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -2,7 +2,6 @@
#ifndef ARCH_X86_KVM_CPUID_H
#define ARCH_X86_KVM_CPUID_H
-#include "x86.h"
#include "reverse_cpuid.h"
#include <asm/cpu.h>
#include <asm/processor.h>
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index e72aed25d721..60986f67c35a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -651,9 +651,10 @@ static inline u8 ctxt_virt_addr_bits(struct x86_emulate_ctxt *ctxt)
}
static inline bool emul_is_noncanonical_address(u64 la,
- struct x86_emulate_ctxt *ctxt)
+ struct x86_emulate_ctxt *ctxt,
+ unsigned int flags)
{
- return !__is_canonical_address(la, ctxt_virt_addr_bits(ctxt));
+ return !ctxt->ops->is_canonical_addr(ctxt, la, flags);
}
/*
@@ -1733,7 +1734,8 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
if (ret != X86EMUL_CONTINUE)
return ret;
if (emul_is_noncanonical_address(get_desc_base(&seg_desc) |
- ((u64)base3 << 32), ctxt))
+ ((u64)base3 << 32), ctxt,
+ X86EMUL_F_DT_LOAD))
return emulate_gp(ctxt, err_code);
}
@@ -2516,8 +2518,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
ss_sel = cs_sel + 8;
cs.d = 0;
cs.l = 1;
- if (emul_is_noncanonical_address(rcx, ctxt) ||
- emul_is_noncanonical_address(rdx, ctxt))
+ if (emul_is_noncanonical_address(rcx, ctxt, 0) ||
+ emul_is_noncanonical_address(rdx, ctxt, 0))
return emulate_gp(ctxt, 0);
break;
}
@@ -3494,7 +3496,8 @@ static int em_lgdt_lidt(struct x86_emulate_ctxt *ctxt, bool lgdt)
if (rc != X86EMUL_CONTINUE)
return rc;
if (ctxt->mode == X86EMUL_MODE_PROT64 &&
- emul_is_noncanonical_address(desc_ptr.address, ctxt))
+ emul_is_noncanonical_address(desc_ptr.address, ctxt,
+ X86EMUL_F_DT_LOAD))
return emulate_gp(ctxt, 0);
if (lgdt)
ctxt->ops->set_gdt(ctxt, &desc_ptr);
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 4f0a94346d00..79d06a8a5b7d 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1980,6 +1980,9 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY)
goto out_flush_all;
+ if (is_noncanonical_invlpg_address(entries[i], vcpu))
+ continue;
+
/*
* Lower 12 bits of 'address' encode the number of additional
* pages to flush.
@@ -2226,6 +2229,9 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
u32 vector;
bool all_cpus;
+ if (!lapic_in_kernel(vcpu))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
if (hc->code == HVCALL_SEND_IPI) {
if (!hc->fast) {
if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi,
@@ -2852,7 +2858,8 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
ent->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED;
ent->eax |= HV_X64_APIC_ACCESS_RECOMMENDED;
ent->eax |= HV_X64_RELAXED_TIMING_RECOMMENDED;
- ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED;
+ if (!vcpu || lapic_in_kernel(vcpu))
+ ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED;
ent->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED;
if (evmcs_ver)
ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 55a18e2f2dcd..10495fffb890 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -94,6 +94,8 @@ struct x86_instruction_info {
#define X86EMUL_F_FETCH BIT(1)
#define X86EMUL_F_IMPLICIT BIT(2)
#define X86EMUL_F_INVLPG BIT(3)
+#define X86EMUL_F_MSR BIT(4)
+#define X86EMUL_F_DT_LOAD BIT(5)
struct x86_emulate_ops {
void (*vm_bugged)(struct x86_emulate_ctxt *ctxt);
@@ -235,6 +237,9 @@ struct x86_emulate_ops {
gva_t (*get_untagged_addr)(struct x86_emulate_ctxt *ctxt, gva_t addr,
unsigned int flags);
+
+ bool (*is_canonical_addr)(struct x86_emulate_ctxt *ctxt, gva_t addr,
+ unsigned int flags);
};
/* Type, address-of, and value of an instruction's operand. */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 95c6beb8ce27..1a8148dec4af 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -763,7 +763,7 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
* just set SVI.
*/
if (unlikely(apic->apicv_active))
- kvm_x86_call(hwapic_isr_update)(vec);
+ kvm_x86_call(hwapic_isr_update)(apic->vcpu, vec);
else {
++apic->isr_count;
BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
@@ -808,7 +808,7 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
* and must be left alone.
*/
if (unlikely(apic->apicv_active))
- kvm_x86_call(hwapic_isr_update)(apic_find_highest_isr(apic));
+ kvm_x86_call(hwapic_isr_update)(apic->vcpu, apic_find_highest_isr(apic));
else {
--apic->isr_count;
BUG_ON(apic->isr_count < 0);
@@ -816,6 +816,17 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
}
}
+void kvm_apic_update_hwapic_isr(struct kvm_vcpu *vcpu)
+{
+ struct kvm_lapic *apic = vcpu->arch.apic;
+
+ if (WARN_ON_ONCE(!lapic_in_kernel(vcpu)) || !apic->apicv_active)
+ return;
+
+ kvm_x86_call(hwapic_isr_update)(vcpu, apic_find_highest_isr(apic));
+}
+EXPORT_SYMBOL_GPL(kvm_apic_update_hwapic_isr);
+
int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
{
/* This may race with setting of irr in __apic_accept_irq() and
@@ -2786,7 +2797,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
if (apic->apicv_active) {
kvm_x86_call(apicv_post_state_restore)(vcpu);
kvm_x86_call(hwapic_irr_update)(vcpu, -1);
- kvm_x86_call(hwapic_isr_update)(-1);
+ kvm_x86_call(hwapic_isr_update)(vcpu, -1);
}
vcpu->arch.apic_arb_prio = 0;
@@ -3102,9 +3113,8 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
kvm_apic_update_apicv(vcpu);
if (apic->apicv_active) {
kvm_x86_call(apicv_post_state_restore)(vcpu);
- kvm_x86_call(hwapic_irr_update)(vcpu,
- apic_find_highest_irr(apic));
- kvm_x86_call(hwapic_isr_update)(apic_find_highest_isr(apic));
+ kvm_x86_call(hwapic_irr_update)(vcpu, apic_find_highest_irr(apic));
+ kvm_x86_call(hwapic_isr_update)(vcpu, apic_find_highest_isr(apic));
}
kvm_make_request(KVM_REQ_EVENT, vcpu);
if (ioapic_in_kernel(vcpu->kvm))
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 1b8ef9856422..3aa599db7796 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -117,11 +117,10 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map);
void kvm_apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high);
-u64 kvm_get_apic_base(struct kvm_vcpu *vcpu);
int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
-enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu);
+void kvm_apic_update_hwapic_isr(struct kvm_vcpu *vcpu);
int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu);
@@ -271,6 +270,11 @@ static inline enum lapic_mode kvm_apic_mode(u64 apic_base)
return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
}
+static inline enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu)
+{
+ return kvm_apic_mode(vcpu->arch.apic_base);
+}
+
static inline u8 kvm_xapic_id(struct kvm_lapic *apic)
{
return kvm_lapic_get_reg(apic, APIC_ID) >> 24;
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 9dc5dd43ae7f..e9322358678b 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -4,6 +4,7 @@
#include <linux/kvm_host.h>
#include "kvm_cache_regs.h"
+#include "x86.h"
#include "cpuid.h"
extern bool __read_mostly enable_mmio_caching;
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 1b4438e24814..8edfb4e4a73d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5591,7 +5591,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0,
union kvm_mmu_page_role root_role;
/* NPT requires CR0.PG=1. */
- WARN_ON_ONCE(cpu_role.base.direct);
+ WARN_ON_ONCE(cpu_role.base.direct || !cpu_role.base.guest_mode);
root_role = cpu_role.base;
root_role.level = kvm_mmu_get_tdp_level(vcpu);
@@ -6234,7 +6234,7 @@ void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
/* It's actually a GPA for vcpu->arch.guest_mmu. */
if (mmu != &vcpu->arch.guest_mmu) {
/* INVLPG on a non-canonical address is a NOP according to the SDM. */
- if (is_noncanonical_address(addr, vcpu))
+ if (is_noncanonical_invlpg_address(addr, vcpu))
return;
kvm_x86_call(flush_tlb_gva)(vcpu, addr);
@@ -7227,6 +7227,19 @@ static void mmu_destroy_caches(void)
kmem_cache_destroy(mmu_page_header_cache);
}
+static void kvm_wake_nx_recovery_thread(struct kvm *kvm)
+{
+ /*
+ * The NX recovery thread is spawned on-demand at the first KVM_RUN and
+ * may not be valid even though the VM is globally visible. Do nothing,
+ * as such a VM can't have any possible NX huge pages.
+ */
+ struct vhost_task *nx_thread = READ_ONCE(kvm->arch.nx_huge_page_recovery_thread);
+
+ if (nx_thread)
+ vhost_task_wake(nx_thread);
+}
+
static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp)
{
if (nx_hugepage_mitigation_hard_disabled)
@@ -7287,7 +7300,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
kvm_mmu_zap_all_fast(kvm);
mutex_unlock(&kvm->slots_lock);
- vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread);
+ kvm_wake_nx_recovery_thread(kvm);
}
mutex_unlock(&kvm_lock);
}
@@ -7433,7 +7446,7 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel
mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list)
- vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread);
+ kvm_wake_nx_recovery_thread(kvm);
mutex_unlock(&kvm_lock);
}
@@ -7565,20 +7578,34 @@ static bool kvm_nx_huge_page_recovery_worker(void *data)
return true;
}
+static void kvm_mmu_start_lpage_recovery(struct once *once)
+{
+ struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once);
+ struct kvm *kvm = container_of(ka, struct kvm, arch);
+ struct vhost_task *nx_thread;
+
+ kvm->arch.nx_huge_page_last = get_jiffies_64();
+ nx_thread = vhost_task_create(kvm_nx_huge_page_recovery_worker,
+ kvm_nx_huge_page_recovery_worker_kill,
+ kvm, "kvm-nx-lpage-recovery");
+
+ if (IS_ERR(nx_thread))
+ return;
+
+ vhost_task_start(nx_thread);
+
+ /* Make the task visible only once it is fully started. */
+ WRITE_ONCE(kvm->arch.nx_huge_page_recovery_thread, nx_thread);
+}
+
int kvm_mmu_post_init_vm(struct kvm *kvm)
{
if (nx_hugepage_mitigation_hard_disabled)
return 0;
- kvm->arch.nx_huge_page_last = get_jiffies_64();
- kvm->arch.nx_huge_page_recovery_thread = vhost_task_create(
- kvm_nx_huge_page_recovery_worker, kvm_nx_huge_page_recovery_worker_kill,
- kvm, "kvm-nx-lpage-recovery");
-
+ call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery);
if (!kvm->arch.nx_huge_page_recovery_thread)
return -ENOMEM;
-
- vhost_task_start(kvm->arch.nx_huge_page_recovery_thread);
return 0;
}
@@ -7589,9 +7616,30 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
}
#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+ int level)
+{
+ return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+ int level)
+{
+ lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+ int level)
+{
+ lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
+}
+
bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
struct kvm_gfn_range *range)
{
+ struct kvm_memory_slot *slot = range->slot;
+ int level;
+
/*
* Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only
* supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM
@@ -7606,27 +7654,49 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
return false;
- return kvm_unmap_gfn_range(kvm, range);
-}
+ if (WARN_ON_ONCE(range->end <= range->start))
+ return false;
-static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
- int level)
-{
- return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG;
-}
+ /*
+ * If the head and tail pages of the range currently allow a hugepage,
+ * i.e. reside fully in the slot and don't have mixed attributes, then
+ * add each corresponding hugepage range to the ongoing invalidation,
+ * e.g. to prevent KVM from creating a hugepage in response to a fault
+ * for a gfn whose attributes aren't changing. Note, only the range
+ * of gfns whose attributes are being modified needs to be explicitly
+ * unmapped, as that will unmap any existing hugepages.
+ */
+ for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+ gfn_t start = gfn_round_for_level(range->start, level);
+ gfn_t end = gfn_round_for_level(range->end - 1, level);
+ gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level);
-static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
- int level)
-{
- lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG;
-}
+ if ((start != range->start || start + nr_pages > range->end) &&
+ start >= slot->base_gfn &&
+ start + nr_pages <= slot->base_gfn + slot->npages &&
+ !hugepage_test_mixed(slot, start, level))
+ kvm_mmu_invalidate_range_add(kvm, start, start + nr_pages);
-static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
- int level)
-{
- lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
+ if (end == start)
+ continue;
+
+ if ((end + nr_pages) > range->end &&
+ (end + nr_pages) <= (slot->base_gfn + slot->npages) &&
+ !hugepage_test_mixed(slot, end, level))
+ kvm_mmu_invalidate_range_add(kvm, end, end + nr_pages);
+ }
+
+ /* Unmap the old attribute page. */
+ if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE)
+ range->attr_filter = KVM_FILTER_SHARED;
+ else
+ range->attr_filter = KVM_FILTER_PRIVATE;
+
+ return kvm_unmap_gfn_range(kvm, range);
}
+
+
static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot,
gfn_t gfn, int level, unsigned long attrs)
{
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index 05490b9d8a43..6f74e2b27c1e 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -19,6 +19,7 @@
#include <asm/mtrr.h>
#include "cpuid.h"
+#include "x86.h"
static u64 *find_mtrr(struct kvm_vcpu *vcpu, unsigned int msr)
{
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index 0d17d6b70639..0ea847b82354 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -18,6 +18,7 @@ enum kvm_only_cpuid_leafs {
CPUID_8000_0022_EAX,
CPUID_7_2_EDX,
CPUID_24_0_EBX,
+ CPUID_8000_0021_ECX,
NR_KVM_CPU_CAPS,
NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,
@@ -68,6 +69,10 @@ enum kvm_only_cpuid_leafs {
/* CPUID level 0x80000022 (EAX) */
#define KVM_X86_FEATURE_PERFMON_V2 KVM_X86_FEATURE(CPUID_8000_0022_EAX, 0)
+/* CPUID level 0x80000021 (ECX) */
+#define KVM_X86_FEATURE_TSA_SQ_NO KVM_X86_FEATURE(CPUID_8000_0021_ECX, 1)
+#define KVM_X86_FEATURE_TSA_L1_NO KVM_X86_FEATURE(CPUID_8000_0021_ECX, 2)
+
struct cpuid_reg {
u32 function;
u32 index;
@@ -98,6 +103,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
[CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX},
[CPUID_7_2_EDX] = { 7, 2, CPUID_EDX},
[CPUID_24_0_EBX] = { 0x24, 0, CPUID_EBX},
+ [CPUID_8000_0021_ECX] = {0x80000021, 0, CPUID_ECX},
};
/*
@@ -137,6 +143,8 @@ static __always_inline u32 __feature_translate(int x86_feature)
KVM_X86_TRANSLATE_FEATURE(PERFMON_V2);
KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL);
KVM_X86_TRANSLATE_FEATURE(BHI_CTRL);
+ KVM_X86_TRANSLATE_FEATURE(TSA_SQ_NO);
+ KVM_X86_TRANSLATE_FEATURE(TSA_L1_NO);
default:
return x86_feature;
}
diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c
index 85241c0c7f56..b0cab215b08f 100644
--- a/arch/x86/kvm/smm.c
+++ b/arch/x86/kvm/smm.c
@@ -131,6 +131,7 @@ void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm)
kvm_mmu_reset_context(vcpu);
}
+EXPORT_SYMBOL_GPL(kvm_smm_changed);
void process_smi(struct kvm_vcpu *vcpu)
{
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 4b74ea91f4e6..63dea8ecd7ef 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -820,7 +820,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
* Allocating new amd_iommu_pi_data, which will get
* add to the per-vcpu ir_list.
*/
- ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT);
+ ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_ATOMIC | __GFP_ACCOUNT);
if (!ir) {
ret = -ENOMEM;
goto out;
@@ -896,6 +896,7 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
{
struct kvm_kernel_irq_routing_entry *e;
struct kvm_irq_routing_table *irq_rt;
+ bool enable_remapped_mode = true;
int idx, ret = 0;
if (!kvm_arch_has_assigned_device(kvm) ||
@@ -933,6 +934,8 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
kvm_vcpu_apicv_active(&svm->vcpu)) {
struct amd_iommu_pi_data pi;
+ enable_remapped_mode = false;
+
/* Try to enable guest_mode in IRTE */
pi.base = __sme_set(page_to_phys(svm->avic_backing_page) &
AVIC_HPA_MASK);
@@ -951,33 +954,6 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
*/
if (!ret && pi.is_guest_mode)
svm_ir_list_add(svm, &pi);
- } else {
- /* Use legacy mode in IRTE */
- struct amd_iommu_pi_data pi;
-
- /**
- * Here, pi is used to:
- * - Tell IOMMU to use legacy mode for this interrupt.
- * - Retrieve ga_tag of prior interrupt remapping data.
- */
- pi.prev_ga_tag = 0;
- pi.is_guest_mode = false;
- ret = irq_set_vcpu_affinity(host_irq, &pi);
-
- /**
- * Check if the posted interrupt was previously
- * setup with the guest_mode by checking if the ga_tag
- * was cached. If so, we need to clean up the per-vcpu
- * ir_list.
- */
- if (!ret && pi.prev_ga_tag) {
- int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
- struct kvm_vcpu *vcpu;
-
- vcpu = kvm_get_vcpu_by_id(kvm, id);
- if (vcpu)
- svm_ir_list_del(to_svm(vcpu), &pi);
- }
}
if (!ret && svm) {
@@ -993,6 +969,34 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
}
ret = 0;
+ if (enable_remapped_mode) {
+ /* Use legacy mode in IRTE */
+ struct amd_iommu_pi_data pi;
+
+ /**
+ * Here, pi is used to:
+ * - Tell IOMMU to use legacy mode for this interrupt.
+ * - Retrieve ga_tag of prior interrupt remapping data.
+ */
+ pi.prev_ga_tag = 0;
+ pi.is_guest_mode = false;
+ ret = irq_set_vcpu_affinity(host_irq, &pi);
+
+ /**
+ * Check if the posted interrupt was previously
+ * setup with the guest_mode by checking if the ga_tag
+ * was cached. If so, we need to clean up the per-vcpu
+ * ir_list.
+ */
+ if (!ret && pi.prev_ga_tag) {
+ int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
+ struct kvm_vcpu *vcpu;
+
+ vcpu = kvm_get_vcpu_by_id(kvm, id);
+ if (vcpu)
+ svm_ir_list_del(to_svm(vcpu), &pi);
+ }
+ }
out:
srcu_read_unlock(&kvm->irq_srcu, idx);
return ret;
@@ -1199,6 +1203,12 @@ bool avic_hardware_setup(void)
return false;
}
+ if (cc_platform_has(CC_ATTR_HOST_SEV_SNP) &&
+ !boot_cpu_has(X86_FEATURE_HV_INUSE_WR_ALLOWED)) {
+ pr_warn("AVIC disabled: missing HvInUseWrAllowed on SNP-enabled system\n");
+ return false;
+ }
+
if (boot_cpu_has(X86_FEATURE_AVIC)) {
pr_info("AVIC enabled\n");
} else if (force_avic) {
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index cf84103ce38b..2dcb9c870d5a 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -646,6 +646,11 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
u32 pause_count12;
u32 pause_thresh12;
+ nested_svm_transition_tlb_flush(vcpu);
+
+ /* Enter Guest-Mode */
+ enter_guest_mode(vcpu);
+
/*
* Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2,
* exit_int_info, exit_int_info_err, next_rip, insn_len, insn_bytes.
@@ -762,11 +767,6 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
}
}
- nested_svm_transition_tlb_flush(vcpu);
-
- /* Enter Guest-Mode */
- enter_guest_mode(vcpu);
-
/*
* Merge guest and host intercepts - must be called with vcpu in
* guest-mode to take effect.
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index fb854cf20ac3..c4ae73541fc5 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2058,6 +2058,10 @@ static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src)
struct kvm_vcpu *src_vcpu;
unsigned long i;
+ if (src->created_vcpus != atomic_read(&src->online_vcpus) ||
+ dst->created_vcpus != atomic_read(&dst->online_vcpus))
+ return -EBUSY;
+
if (!sev_es_guest(src))
return 0;
@@ -3833,7 +3837,7 @@ next_range:
goto next_range;
}
- unreachable();
+ BUG();
}
static int __sev_snp_update_protected_guest_state(struct kvm_vcpu *vcpu)
@@ -3957,16 +3961,12 @@ static int sev_snp_ap_creation(struct vcpu_svm *svm)
/*
* The target vCPU is valid, so the vCPU will be kicked unless the
- * request is for CREATE_ON_INIT. For any errors at this stage, the
- * kick will place the vCPU in an non-runnable state.
+ * request is for CREATE_ON_INIT.
*/
kick = true;
mutex_lock(&target_svm->sev_es.snp_vmsa_mutex);
- target_svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
- target_svm->sev_es.snp_ap_waiting_for_reset = true;
-
/* Interrupt injection mode shouldn't change for AP creation */
if (request < SVM_VMGEXIT_AP_DESTROY) {
u64 sev_features;
@@ -4012,20 +4012,23 @@ static int sev_snp_ap_creation(struct vcpu_svm *svm)
target_svm->sev_es.snp_vmsa_gpa = svm->vmcb->control.exit_info_2;
break;
case SVM_VMGEXIT_AP_DESTROY:
+ target_svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
break;
default:
vcpu_unimpl(vcpu, "vmgexit: invalid AP creation request [%#x] from guest\n",
request);
ret = -EINVAL;
- break;
+ goto out;
}
-out:
+ target_svm->sev_es.snp_ap_waiting_for_reset = true;
+
if (kick) {
kvm_make_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu);
kvm_vcpu_kick(target_vcpu);
}
+out:
mutex_unlock(&target_svm->sev_es.snp_vmsa_mutex);
return ret;
@@ -4579,6 +4582,8 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm)
void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa)
{
+ struct kvm *kvm = svm->vcpu.kvm;
+
/*
* All host state for SEV-ES guests is categorized into three swap types
* based on how it is handled by hardware during a world switch:
@@ -4602,10 +4607,15 @@ void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_are
/*
* If DebugSwap is enabled, debug registers are loaded but NOT saved by
- * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU both
- * saves and loads debug registers (Type-A).
+ * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU does
+ * not save or load debug registers. Sadly, on CPUs without
+ * ALLOWED_SEV_FEATURES, KVM can't prevent SNP guests from enabling
+ * DebugSwap on secondary vCPUs without KVM's knowledge via "AP Create".
+ * Save all registers if DebugSwap is supported to prevent host state
+ * from being clobbered by a misbehaving guest.
*/
- if (sev_vcpu_has_debug_swap(svm)) {
+ if (sev_vcpu_has_debug_swap(svm) ||
+ (sev_snp_guest(kvm) && cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP))) {
hostsa->dr0 = native_get_debugreg(0);
hostsa->dr1 = native_get_debugreg(1);
hostsa->dr2 = native_get_debugreg(2);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 4543dd6bcab2..800f781475c0 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1483,7 +1483,7 @@ static void svm_clear_current_vmcb(struct vmcb *vmcb)
{
int i;
- for_each_online_cpu(i)
+ for_each_possible_cpu(i)
cmpxchg(per_cpu_ptr(&svm_data.current_vmcb, i), vmcb, NULL);
}
@@ -1993,11 +1993,11 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
svm->asid = sd->next_asid++;
}
-static void svm_set_dr6(struct vcpu_svm *svm, unsigned long value)
+static void svm_set_dr6(struct kvm_vcpu *vcpu, unsigned long value)
{
- struct vmcb *vmcb = svm->vmcb;
+ struct vmcb *vmcb = to_svm(vcpu)->vmcb;
- if (svm->vcpu.arch.guest_state_protected)
+ if (vcpu->arch.guest_state_protected)
return;
if (unlikely(value != vmcb->save.dr6)) {
@@ -2222,6 +2222,10 @@ static int shutdown_interception(struct kvm_vcpu *vcpu)
*/
if (!sev_es_guest(vcpu->kvm)) {
clear_page(svm->vmcb);
+#ifdef CONFIG_KVM_SMM
+ if (is_smm(vcpu))
+ kvm_smm_changed(vcpu, false);
+#endif
kvm_vcpu_reset(vcpu, true);
}
@@ -3167,6 +3171,27 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
kvm_pr_unimpl_wrmsr(vcpu, ecx, data);
break;
}
+
+ /*
+ * AMD changed the architectural behavior of bits 5:2. On CPUs
+ * without BusLockTrap, bits 5:2 control "external pins", but
+ * on CPUs that support BusLockDetect, bit 2 enables BusLockTrap
+ * and bits 5:3 are reserved-to-zero. Sadly, old KVM allowed
+ * the guest to set bits 5:2 despite not actually virtualizing
+ * Performance-Monitoring/Breakpoint external pins. Drop bits
+ * 5:2 for backwards compatibility.
+ */
+ data &= ~GENMASK(5, 2);
+
+ /*
+ * Suppress BTF as KVM doesn't virtualize BTF, but there's no
+ * way to communicate lack of support to the guest.
+ */
+ if (data & DEBUGCTLMSR_BTF) {
+ kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data);
+ data &= ~DEBUGCTLMSR_BTF;
+ }
+
if (data & DEBUGCTL_RESERVED_BITS)
return 1;
@@ -4176,6 +4201,18 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
guest_state_enter_irqoff();
+ /*
+ * Set RFLAGS.IF prior to VMRUN, as the host's RFLAGS.IF at the time of
+ * VMRUN controls whether or not physical IRQs are masked (KVM always
+ * runs with V_INTR_MASKING_MASK). Toggle RFLAGS.IF here to avoid the
+ * temptation to do STI+VMRUN+CLI, as AMD CPUs bleed the STI shadow
+ * into guest state if delivery of an event during VMRUN triggers a
+ * #VMEXIT, and the guest_state transitions already tell lockdep that
+ * IRQs are being enabled/disabled. Note! GIF=0 for the entirety of
+ * this path, so IRQs aren't actually unmasked while running host code.
+ */
+ raw_local_irq_enable();
+
amd_clear_divider();
if (sev_es_guest(vcpu->kvm))
@@ -4184,12 +4221,14 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
else
__svm_vcpu_run(svm, spec_ctrl_intercepted);
+ raw_local_irq_disable();
+
guest_state_exit_irqoff();
}
-static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
- bool force_immediate_exit)
+static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
{
+ bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT;
struct vcpu_svm *svm = to_svm(vcpu);
bool spec_ctrl_intercepted = msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL);
@@ -4231,17 +4270,28 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
svm_hv_update_vp_id(svm->vmcb, vcpu);
/*
- * Run with all-zero DR6 unless needed, so that we can get the exact cause
- * of a #DB.
+ * Run with all-zero DR6 unless the guest can write DR6 freely, so that
+ * KVM can get the exact cause of a #DB. Note, loading guest DR6 from
+ * KVM's snapshot is only necessary when DR accesses won't exit.
*/
- if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
- svm_set_dr6(svm, vcpu->arch.dr6);
- else
- svm_set_dr6(svm, DR6_ACTIVE_LOW);
+ if (unlikely(run_flags & KVM_RUN_LOAD_GUEST_DR6))
+ svm_set_dr6(vcpu, vcpu->arch.dr6);
+ else if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)))
+ svm_set_dr6(vcpu, DR6_ACTIVE_LOW);
clgi();
kvm_load_guest_xsave_state(vcpu);
+ /*
+ * Hardware only context switches DEBUGCTL if LBR virtualization is
+ * enabled. Manually load DEBUGCTL if necessary (and restore it after
+ * VM-Exit), as running with the host's DEBUGCTL can negatively affect
+ * guest state and can even be fatal, e.g. due to Bus Lock Detect.
+ */
+ if (!(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) &&
+ vcpu->arch.host_debugctl != svm->vmcb->save.dbgctl)
+ update_debugctlmsr(svm->vmcb->save.dbgctl);
+
kvm_wait_lapic_expire(vcpu);
/*
@@ -4269,6 +4319,10 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
+ if (!(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) &&
+ vcpu->arch.host_debugctl != svm->vmcb->save.dbgctl)
+ update_debugctlmsr(vcpu->arch.host_debugctl);
+
kvm_load_host_xsave_state(vcpu);
stgi();
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 43fa6a16eb19..d114efac7af7 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -591,7 +591,7 @@ static inline bool is_vnmi_enabled(struct vcpu_svm *svm)
/* svm.c */
#define MSR_INVALID 0xffffffffU
-#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
+#define DEBUGCTL_RESERVED_BITS (~DEBUGCTLMSR_LBR)
extern bool dump_invalid_vmcb;
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 2ed80aea3bb1..235c4af6b692 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -169,13 +169,12 @@ SYM_FUNC_START(__svm_vcpu_run)
#endif
mov VCPU_RDI(%_ASM_DI), %_ASM_DI
- /* Enter guest mode */
- sti
+ /* Clobbers EFLAGS.ZF */
+ VM_CLEAR_CPU_BUFFERS
+ /* Enter guest mode */
3: vmrun %_ASM_AX
4:
- cli
-
/* Pop @svm to RAX while it's the only available register. */
pop %_ASM_AX
@@ -339,13 +338,12 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
mov SVM_current_vmcb(%rdi), %rax
mov KVM_VMCB_pa(%rax), %rax
- /* Enter guest mode */
- sti
+ /* Clobbers EFLAGS.ZF */
+ VM_CLEAR_CPU_BUFFERS
+ /* Enter guest mode */
1: vmrun %rax
-
-2: cli
-
+2:
/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT
diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c
index fab6a1ad98dc..fa41d036acd4 100644
--- a/arch/x86/kvm/vmx/hyperv.c
+++ b/arch/x86/kvm/vmx/hyperv.c
@@ -4,6 +4,7 @@
#include <linux/errno.h>
#include <linux/smp.h>
+#include "x86.h"
#include "../cpuid.h"
#include "hyperv.h"
#include "nested.h"
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 7668e2fb8043..3f83e36a657b 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -42,6 +42,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
.vcpu_load = vmx_vcpu_load,
.vcpu_put = vmx_vcpu_put,
+ .HOST_OWNED_DEBUGCTL = DEBUGCTLMSR_FREEZE_IN_SMM,
+
.update_exception_bitmap = vmx_update_exception_bitmap,
.get_feature_msr = vmx_get_feature_msr,
.get_msr = vmx_get_msr,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 931a7361c30f..60bd2791d933 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -7,6 +7,7 @@
#include <asm/debugreg.h>
#include <asm/mmu_context.h>
+#include "x86.h"
#include "cpuid.h"
#include "hyperv.h"
#include "mmu.h"
@@ -16,7 +17,6 @@
#include "sgx.h"
#include "trace.h"
#include "vmx.h"
-#include "x86.h"
#include "smm.h"
static bool __read_mostly enable_shadow_vmcs = 1;
@@ -2653,10 +2653,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
if (vmx->nested.nested_run_pending &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
- vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+ vmx_guest_debugctl_write(vcpu, vmcs12->guest_ia32_debugctl &
+ vmx_get_supported_debugctl(vcpu, false));
} else {
kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
- vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl);
+ vmx_guest_debugctl_write(vcpu, vmx->nested.pre_vmenter_debugctl);
}
if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending ||
!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
@@ -3020,8 +3021,8 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
CC(!kvm_vcpu_is_legal_cr3(vcpu, vmcs12->host_cr3)))
return -EINVAL;
- if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) ||
- CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu)))
+ if (CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_esp, vcpu)) ||
+ CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_eip, vcpu)))
return -EINVAL;
if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) &&
@@ -3055,12 +3056,12 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
CC(vmcs12->host_ss_selector == 0 && !ia32e))
return -EINVAL;
- if (CC(is_noncanonical_address(vmcs12->host_fs_base, vcpu)) ||
- CC(is_noncanonical_address(vmcs12->host_gs_base, vcpu)) ||
- CC(is_noncanonical_address(vmcs12->host_gdtr_base, vcpu)) ||
- CC(is_noncanonical_address(vmcs12->host_idtr_base, vcpu)) ||
- CC(is_noncanonical_address(vmcs12->host_tr_base, vcpu)) ||
- CC(is_noncanonical_address(vmcs12->host_rip, vcpu)))
+ if (CC(is_noncanonical_base_address(vmcs12->host_fs_base, vcpu)) ||
+ CC(is_noncanonical_base_address(vmcs12->host_gs_base, vcpu)) ||
+ CC(is_noncanonical_base_address(vmcs12->host_gdtr_base, vcpu)) ||
+ CC(is_noncanonical_base_address(vmcs12->host_idtr_base, vcpu)) ||
+ CC(is_noncanonical_base_address(vmcs12->host_tr_base, vcpu)) ||
+ CC(is_noncanonical_address(vmcs12->host_rip, vcpu, 0)))
return -EINVAL;
/*
@@ -3135,7 +3136,8 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
- CC(!kvm_dr7_valid(vmcs12->guest_dr7)))
+ (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
+ CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false))))
return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
@@ -3178,7 +3180,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
}
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) &&
- (CC(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) ||
+ (CC(is_noncanonical_msr_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) ||
CC((vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD))))
return -EINVAL;
@@ -3525,7 +3527,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
if (!vmx->nested.nested_run_pending ||
!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
- vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
+ vmx->nested.pre_vmenter_debugctl = vmx_guest_debugctl_read();
if (kvm_mpx_supported() &&
(!vmx->nested.nested_run_pending ||
!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
@@ -4576,6 +4578,12 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
(vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE);
+ /*
+ * Note! Save DR7, but intentionally don't grab DEBUGCTL from vmcs02.
+ * Writes to DEBUGCTL that aren't intercepted by L1 are immediately
+ * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into
+ * vmcs02 doesn't strictly track vmcs12.
+ */
if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS)
vmcs12->guest_dr7 = vcpu->arch.dr7;
@@ -4766,7 +4774,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
__vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR);
kvm_set_dr(vcpu, 7, 0x400);
- vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+ vmx_guest_debugctl_write(vcpu, 0);
if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
vmcs12->vm_exit_msr_load_count))
@@ -4821,6 +4829,9 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7)));
}
+ /* Reload DEBUGCTL to ensure vmcs01 has a fresh FREEZE_IN_SMM value. */
+ vmx_reload_guest_debugctl(vcpu);
+
/*
* Note that calling vmx_set_{efer,cr0,cr4} is important as they
* handle a variety of side effects to KVM's software model.
@@ -5043,6 +5054,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu);
}
+ if (vmx->nested.update_vmcs01_hwapic_isr) {
+ vmx->nested.update_vmcs01_hwapic_isr = false;
+ kvm_apic_update_hwapic_isr(vcpu);
+ }
+
if ((vm_exit_reason != -1) &&
(enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx)))
vmx->nested.need_vmcs12_to_shadow_sync = true;
@@ -5167,7 +5183,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
* non-canonical form. This is the only check on the memory
* destination for long mode!
*/
- exn = is_noncanonical_address(*ret, vcpu);
+ exn = is_noncanonical_address(*ret, vcpu, 0);
} else {
/*
* When not in long mode, the virtual/linear address is
@@ -5978,7 +5994,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
* invalidation.
*/
if (!operand.vpid ||
- is_noncanonical_address(operand.gla, vcpu))
+ is_noncanonical_invlpg_address(operand.gla, vcpu))
return nested_vmx_fail(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
vpid_sync_vcpu_addr(vpid02, operand.gla);
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 83382a4d1d66..a5edc623166a 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -365,7 +365,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
}
break;
case MSR_IA32_DS_AREA:
- if (is_noncanonical_address(data, vcpu))
+ if (is_noncanonical_msr_address(data, vcpu))
return 1;
pmu->ds_area = data;
@@ -605,11 +605,11 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu)
*/
static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu)
{
- u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL);
+ u64 data = vmx_guest_debugctl_read();
if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) {
data &= ~DEBUGCTLMSR_LBR;
- vmcs_write64(GUEST_IA32_DEBUGCTL, data);
+ vmx_guest_debugctl_write(vcpu, data);
}
}
@@ -679,7 +679,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)
if (!lbr_desc->event) {
vmx_disable_lbr_msrs_passthrough(vcpu);
- if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)
+ if (vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR)
goto warn;
if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use))
goto warn;
@@ -701,7 +701,7 @@ warn:
static void intel_pmu_cleanup(struct kvm_vcpu *vcpu)
{
- if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR))
+ if (!(vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR))
intel_pmu_release_guest_lbr_event(vcpu);
}
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index ec08fa3caf43..6b803324a981 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -274,6 +274,7 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
{
struct kvm_kernel_irq_routing_entry *e;
struct kvm_irq_routing_table *irq_rt;
+ bool enable_remapped_mode = true;
struct kvm_lapic_irq irq;
struct kvm_vcpu *vcpu;
struct vcpu_data vcpu_info;
@@ -312,21 +313,8 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
kvm_set_msi_irq(kvm, e, &irq);
if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
- !kvm_irq_is_postable(&irq)) {
- /*
- * Make sure the IRTE is in remapped mode if
- * we don't handle it in posted mode.
- */
- ret = irq_set_vcpu_affinity(host_irq, NULL);
- if (ret < 0) {
- printk(KERN_INFO
- "failed to back to remapped mode, irq: %u\n",
- host_irq);
- goto out;
- }
-
+ !kvm_irq_is_postable(&irq))
continue;
- }
vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
vcpu_info.vector = irq.vector;
@@ -334,11 +322,12 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
vcpu_info.vector, vcpu_info.pi_desc_addr, set);
- if (set)
- ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
- else
- ret = irq_set_vcpu_affinity(host_irq, NULL);
+ if (!set)
+ continue;
+ enable_remapped_mode = false;
+
+ ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
if (ret < 0) {
printk(KERN_INFO "%s: failed to update PI IRTE\n",
__func__);
@@ -346,6 +335,9 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
}
}
+ if (enable_remapped_mode)
+ ret = irq_set_vcpu_affinity(host_irq, NULL);
+
ret = 0;
out:
srcu_read_unlock(&kvm->irq_srcu, idx);
diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c
index a3c3d2a51f47..b352a3ba7354 100644
--- a/arch/x86/kvm/vmx/sgx.c
+++ b/arch/x86/kvm/vmx/sgx.c
@@ -4,12 +4,11 @@
#include <asm/sgx.h>
-#include "cpuid.h"
+#include "x86.h"
#include "kvm_cache_regs.h"
#include "nested.h"
#include "sgx.h"
#include "vmx.h"
-#include "x86.h"
bool __read_mostly enable_sgx = 1;
module_param_named(sgx, enable_sgx, bool, 0444);
@@ -38,7 +37,7 @@ static int sgx_get_encls_gva(struct kvm_vcpu *vcpu, unsigned long offset,
fault = true;
} else if (likely(is_64_bit_mode(vcpu))) {
*gva = vmx_get_untagged_addr(vcpu, *gva, 0);
- fault = is_noncanonical_address(*gva, vcpu);
+ fault = is_noncanonical_address(*gva, vcpu, 0);
} else {
*gva &= 0xffffffff;
fault = (s.unusable) ||
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 92fee5e8a3c7..6c185a260c5b 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -770,8 +770,11 @@ void vmx_emergency_disable_virtualization_cpu(void)
return;
list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
- loaded_vmcss_on_cpu_link)
+ loaded_vmcss_on_cpu_link) {
vmcs_clear(v->vmcs);
+ if (v->shadow_vmcs)
+ vmcs_clear(v->shadow_vmcs);
+ }
kvm_cpu_vmxoff();
}
@@ -1515,16 +1518,12 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
*/
void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
-
if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
shrink_ple_window(vcpu);
vmx_vcpu_load_vmcs(vcpu, cpu, NULL);
vmx_vcpu_pi_load(vcpu, cpu);
-
- vmx->host_debugctlmsr = get_debugctlmsr();
}
void vmx_vcpu_put(struct kvm_vcpu *vcpu)
@@ -2149,7 +2148,7 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = vmx->pt_desc.guest.addr_a[index / 2];
break;
case MSR_IA32_DEBUGCTLMSR:
- msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL);
+ msr_info->data = vmx_guest_debugctl_read();
break;
default:
find_uret_msr:
@@ -2174,7 +2173,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu,
return (unsigned long)data;
}
-static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
{
u64 debugctl = 0;
@@ -2186,9 +2185,25 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
(host_initiated || intel_pmu_lbr_is_enabled(vcpu)))
debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
+ if (boot_cpu_has(X86_FEATURE_RTM) &&
+ (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_RTM)))
+ debugctl |= DEBUGCTLMSR_RTM_DEBUG;
+
return debugctl;
}
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated)
+{
+ u64 invalid;
+
+ invalid = data & ~vmx_get_supported_debugctl(vcpu, host_initiated);
+ if (invalid & (DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR)) {
+ kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data);
+ invalid &= ~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR);
+ }
+ return !invalid;
+}
+
/*
* Writes msr value into the appropriate "register".
* Returns 0 on success, non-0 otherwise.
@@ -2257,35 +2272,28 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
}
vmcs_writel(GUEST_SYSENTER_ESP, data);
break;
- case MSR_IA32_DEBUGCTLMSR: {
- u64 invalid;
-
- invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated);
- if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) {
- kvm_pr_unimpl_wrmsr(vcpu, msr_index, data);
- data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR);
- invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR);
- }
-
- if (invalid)
+ case MSR_IA32_DEBUGCTLMSR:
+ if (!vmx_is_valid_debugctl(vcpu, data, msr_info->host_initiated))
return 1;
+ data &= vmx_get_supported_debugctl(vcpu, msr_info->host_initiated);
+
if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls &
VM_EXIT_SAVE_DEBUG_CONTROLS)
get_vmcs12(vcpu)->guest_ia32_debugctl = data;
- vmcs_write64(GUEST_IA32_DEBUGCTL, data);
+ vmx_guest_debugctl_write(vcpu, data);
+
if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event &&
(data & DEBUGCTLMSR_LBR))
intel_pmu_create_guest_lbr_event(vcpu);
return 0;
- }
case MSR_IA32_BNDCFGS:
if (!kvm_mpx_supported() ||
(!msr_info->host_initiated &&
!guest_cpuid_has(vcpu, X86_FEATURE_MPX)))
return 1;
- if (is_noncanonical_address(data & PAGE_MASK, vcpu) ||
+ if (is_noncanonical_msr_address(data & PAGE_MASK, vcpu) ||
(data & MSR_IA32_BNDCFGS_RSVD))
return 1;
@@ -2450,7 +2458,7 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
index = msr_info->index - MSR_IA32_RTIT_ADDR0_A;
if (index >= 2 * vmx->pt_desc.num_address_ranges)
return 1;
- if (is_noncanonical_address(data, vcpu))
+ if (is_noncanonical_msr_address(data, vcpu))
return 1;
if (index % 2)
vmx->pt_desc.guest.addr_b[index / 2] = data;
@@ -4824,7 +4832,8 @@ static void init_vmcs(struct vcpu_vmx *vmx)
vmcs_write32(GUEST_SYSENTER_CS, 0);
vmcs_writel(GUEST_SYSENTER_ESP, 0);
vmcs_writel(GUEST_SYSENTER_EIP, 0);
- vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+
+ vmx_guest_debugctl_write(&vmx->vcpu, 0);
if (cpu_has_vmx_tpr_shadow()) {
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0);
@@ -6847,11 +6856,32 @@ out:
kvm_release_pfn_clean(pfn);
}
-void vmx_hwapic_isr_update(int max_isr)
+void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
{
u16 status;
u8 old;
+ /*
+ * If L2 is active, defer the SVI update until vmcs01 is loaded, as SVI
+ * is only relevant for if and only if Virtual Interrupt Delivery is
+ * enabled in vmcs12, and if VID is enabled then L2 EOIs affect L2's
+ * vAPIC, not L1's vAPIC. KVM must update vmcs01 on the next nested
+ * VM-Exit, otherwise L1 with run with a stale SVI.
+ */
+ if (is_guest_mode(vcpu)) {
+ /*
+ * KVM is supposed to forward intercepted L2 EOIs to L1 if VID
+ * is enabled in vmcs12; as above, the EOIs affect L2's vAPIC.
+ * Note, userspace can stuff state while L2 is active; assert
+ * that VID is disabled if and only if the vCPU is in KVM_RUN
+ * to avoid false positives if userspace is setting APIC state.
+ */
+ WARN_ON_ONCE(vcpu->wants_to_run &&
+ nested_cpu_has_vid(get_vmcs12(vcpu)));
+ to_vmx(vcpu)->nested.update_vmcs01_hwapic_isr = true;
+ return;
+ }
+
if (max_isr == -1)
max_isr = 0;
@@ -7287,7 +7317,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
vmx_l1d_flush(vcpu);
else if (static_branch_unlikely(&mmio_stale_data_clear) &&
kvm_arch_has_assigned_device(vcpu->kvm))
- mds_clear_cpu_buffers();
+ x86_clear_cpu_buffers();
vmx_disable_fb_clear(vmx);
@@ -7327,8 +7357,9 @@ out:
guest_state_exit_irqoff();
}
-fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
{
+ bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT;
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long cr3, cr4;
@@ -7373,6 +7404,12 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
vcpu->arch.regs_dirty = 0;
+ if (run_flags & KVM_RUN_LOAD_GUEST_DR6)
+ set_debugreg(vcpu->arch.dr6, 6);
+
+ if (run_flags & KVM_RUN_LOAD_DEBUGCTL)
+ vmx_reload_guest_debugctl(vcpu);
+
/*
* Refresh vmcs.HOST_CR3 if necessary. This must be done immediately
* prior to VM-Enter, as the kernel may load a new ASID (PCID) any time
@@ -7392,10 +7429,6 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
vmx->loaded_vmcs->host_state.cr4 = cr4;
}
- /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */
- if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
- set_debugreg(vcpu->arch.dr6, 6);
-
/* When single-stepping over STI and MOV SS, we must clear the
* corresponding interruptibility bits in the guest state. Otherwise
* vmentry fails as it then expects bit 14 (BS) in pending debug
@@ -7431,8 +7464,8 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
}
/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
- if (vmx->host_debugctlmsr)
- update_debugctlmsr(vmx->host_debugctlmsr);
+ if (vcpu->arch.host_debugctl)
+ update_debugctlmsr(vcpu->arch.host_debugctl);
#ifndef CONFIG_X86_64
/*
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 2325f773a20b..a7e2de50d27f 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -176,6 +176,7 @@ struct nested_vmx {
bool reload_vmcs01_apic_access_page;
bool update_vmcs01_cpu_dirty_logging;
bool update_vmcs01_apicv_status;
+ bool update_vmcs01_hwapic_isr;
/*
* Enlightened VMCS has been enabled. It does not mean that L1 has to
@@ -338,8 +339,6 @@ struct vcpu_vmx {
/* apic deadline value in host tsc */
u64 hv_deadline_tsc;
- unsigned long host_debugctlmsr;
-
/*
* Only bits masked by msr_ia32_feature_control_valid_bits can be set in
* msr_ia32_feature_control. FEAT_CTL_LOCKED is always included
@@ -436,6 +435,32 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr,
void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated);
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated);
+
+static inline void vmx_guest_debugctl_write(struct kvm_vcpu *vcpu, u64 val)
+{
+ WARN_ON_ONCE(val & DEBUGCTLMSR_FREEZE_IN_SMM);
+
+ val |= vcpu->arch.host_debugctl & DEBUGCTLMSR_FREEZE_IN_SMM;
+ vmcs_write64(GUEST_IA32_DEBUGCTL, val);
+}
+
+static inline u64 vmx_guest_debugctl_read(void)
+{
+ return vmcs_read64(GUEST_IA32_DEBUGCTL) & ~DEBUGCTLMSR_FREEZE_IN_SMM;
+}
+
+static inline void vmx_reload_guest_debugctl(struct kvm_vcpu *vcpu)
+{
+ u64 val = vmcs_read64(GUEST_IA32_DEBUGCTL);
+
+ if (!((val ^ vcpu->arch.host_debugctl) & DEBUGCTLMSR_FREEZE_IN_SMM))
+ return;
+
+ vmx_guest_debugctl_write(vcpu, val & ~DEBUGCTLMSR_FREEZE_IN_SMM);
+}
+
/*
* Note, early Intel manuals have the write-low and read-high bitmap offsets
* the wrong way round. The bitmaps control MSRs 0x00000000-0x00001fff and
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index a55981c5216e..5e4ce13ab305 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -21,7 +21,7 @@ void vmx_vm_destroy(struct kvm *kvm);
int vmx_vcpu_precreate(struct kvm *kvm);
int vmx_vcpu_create(struct kvm_vcpu *vcpu);
int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu);
-fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit);
+fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags);
void vmx_vcpu_free(struct kvm_vcpu *vcpu);
void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
@@ -48,7 +48,7 @@ void vmx_migrate_timers(struct kvm_vcpu *vcpu);
void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu);
void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr);
-void vmx_hwapic_isr_update(int max_isr);
+void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr);
int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu);
void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
int trig_mode, int vector);
@@ -74,6 +74,7 @@ void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
+void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val);
void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val);
void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu);
void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b49e2eb48930..dbd295ef3eba 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -667,17 +667,6 @@ static void drop_user_return_notifiers(void)
kvm_on_user_return(&msrs->urn);
}
-u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
-{
- return vcpu->arch.apic_base;
-}
-
-enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu)
-{
- return kvm_apic_mode(kvm_get_apic_base(vcpu));
-}
-EXPORT_SYMBOL_GPL(kvm_get_apic_mode);
-
int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
enum lapic_mode old_mode = kvm_get_apic_mode(vcpu);
@@ -1634,7 +1623,7 @@ EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc);
ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \
- ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO)
+ ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO | ARCH_CAP_ITS_NO)
static u64 kvm_get_arch_capabilities(void)
{
@@ -1668,6 +1657,8 @@ static u64 kvm_get_arch_capabilities(void)
data |= ARCH_CAP_MDS_NO;
if (!boot_cpu_has_bug(X86_BUG_RFDS))
data |= ARCH_CAP_RFDS_NO;
+ if (!boot_cpu_has_bug(X86_BUG_ITS))
+ data |= ARCH_CAP_ITS_NO;
if (!boot_cpu_has(X86_FEATURE_RTM)) {
/*
@@ -1854,7 +1845,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
case MSR_KERNEL_GS_BASE:
case MSR_CSTAR:
case MSR_LSTAR:
- if (is_noncanonical_address(data, vcpu))
+ if (is_noncanonical_msr_address(data, vcpu))
return 1;
break;
case MSR_IA32_SYSENTER_EIP:
@@ -1871,7 +1862,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
* value, and that something deterministic happens if the guest
* invokes 64-bit SYSENTER.
*/
- data = __canonical_address(data, vcpu_virt_addr_bits(vcpu));
+ data = __canonical_address(data, max_host_virt_addr_bits());
break;
case MSR_TSC_AUX:
if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX))
@@ -4314,7 +4305,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = 1 << 24;
break;
case MSR_IA32_APICBASE:
- msr_info->data = kvm_get_apic_base(vcpu);
+ msr_info->data = vcpu->arch.apic_base;
break;
case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data);
@@ -4601,6 +4592,11 @@ static bool kvm_is_vm_type_supported(unsigned long type)
return type < 32 && (kvm_caps.supported_vm_types & BIT(type));
}
+static inline u32 kvm_sync_valid_fields(struct kvm *kvm)
+{
+ return kvm && kvm->arch.has_protected_state ? 0 : KVM_SYNC_X86_VALID_FIELDS;
+}
+
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r = 0;
@@ -4709,7 +4705,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
break;
#endif
case KVM_CAP_SYNC_REGS:
- r = KVM_SYNC_X86_VALID_FIELDS;
+ r = kvm_sync_valid_fields(kvm);
break;
case KVM_CAP_ADJUST_CLOCK:
r = KVM_CLOCK_VALID_FLAGS;
@@ -8612,6 +8608,12 @@ static gva_t emulator_get_untagged_addr(struct x86_emulate_ctxt *ctxt,
addr, flags);
}
+static bool emulator_is_canonical_addr(struct x86_emulate_ctxt *ctxt,
+ gva_t addr, unsigned int flags)
+{
+ return !is_noncanonical_address(addr, emul_to_vcpu(ctxt), flags);
+}
+
static const struct x86_emulate_ops emulate_ops = {
.vm_bugged = emulator_vm_bugged,
.read_gpr = emulator_read_gpr,
@@ -8658,6 +8660,7 @@ static const struct x86_emulate_ops emulate_ops = {
.triple_fault = emulator_triple_fault,
.set_xcr = emulator_set_xcr,
.get_untagged_addr = emulator_get_untagged_addr,
+ .is_canonical_addr = emulator_is_canonical_addr,
};
static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
@@ -10159,7 +10162,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
kvm_run->if_flag = kvm_x86_call(get_if_flag)(vcpu);
kvm_run->cr8 = kvm_get_cr8(vcpu);
- kvm_run->apic_base = kvm_get_apic_base(vcpu);
+ kvm_run->apic_base = vcpu->arch.apic_base;
kvm_run->ready_for_interrupt_injection =
pic_in_kernel(vcpu->kvm) ||
@@ -10708,6 +10711,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
dm_request_for_irq_injection(vcpu) &&
kvm_cpu_accept_dm_intr(vcpu);
fastpath_t exit_fastpath;
+ u64 run_flags, debug_ctl;
bool req_immediate_exit = false;
@@ -10952,8 +10956,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
goto cancel_injection;
}
- if (req_immediate_exit)
+ run_flags = 0;
+ if (req_immediate_exit) {
+ run_flags |= KVM_RUN_FORCE_IMMEDIATE_EXIT;
kvm_make_request(KVM_REQ_EVENT, vcpu);
+ }
fpregs_assert_state_consistent();
if (test_thread_flag(TIF_NEED_FPU_LOAD))
@@ -10963,15 +10970,30 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
wrmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
if (unlikely(vcpu->arch.switch_db_regs)) {
- set_debugreg(0, 7);
+ set_debugreg(DR7_FIXED_1, 7);
set_debugreg(vcpu->arch.eff_db[0], 0);
set_debugreg(vcpu->arch.eff_db[1], 1);
set_debugreg(vcpu->arch.eff_db[2], 2);
set_debugreg(vcpu->arch.eff_db[3], 3);
+ /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */
+ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
+ run_flags |= KVM_RUN_LOAD_GUEST_DR6;
} else if (unlikely(hw_breakpoint_active())) {
- set_debugreg(0, 7);
+ set_debugreg(DR7_FIXED_1, 7);
}
+ /*
+ * Refresh the host DEBUGCTL snapshot after disabling IRQs, as DEBUGCTL
+ * can be modified in IRQ context, e.g. via SMP function calls. Inform
+ * vendor code if any host-owned bits were changed, e.g. so that the
+ * value loaded into hardware while running the guest can be updated.
+ */
+ debug_ctl = get_debugctlmsr();
+ if ((debug_ctl ^ vcpu->arch.host_debugctl) & kvm_x86_ops.HOST_OWNED_DEBUGCTL &&
+ !vcpu->arch.guest_state_protected)
+ run_flags |= KVM_RUN_LOAD_DEBUGCTL;
+ vcpu->arch.host_debugctl = debug_ctl;
+
guest_timing_enter_irqoff();
for (;;) {
@@ -10984,8 +11006,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) &&
(kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED));
- exit_fastpath = kvm_x86_call(vcpu_run)(vcpu,
- req_immediate_exit);
+ exit_fastpath = kvm_x86_call(vcpu_run)(vcpu, run_flags);
if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
break;
@@ -10997,6 +11018,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
break;
}
+ run_flags = 0;
+
/* Note, VM-Exits that go down the "slow" path are accounted below. */
++vcpu->stat.exits;
}
@@ -11476,8 +11499,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
struct kvm_queued_exception *ex = &vcpu->arch.exception;
struct kvm_run *kvm_run = vcpu->run;
+ u32 sync_valid_fields;
int r;
+ r = kvm_mmu_post_init_vm(vcpu->kvm);
+ if (r)
+ return r;
+
vcpu_load(vcpu);
kvm_sigset_activate(vcpu);
kvm_run->flags = 0;
@@ -11517,8 +11545,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
goto out;
}
- if ((kvm_run->kvm_valid_regs & ~KVM_SYNC_X86_VALID_FIELDS) ||
- (kvm_run->kvm_dirty_regs & ~KVM_SYNC_X86_VALID_FIELDS)) {
+ sync_valid_fields = kvm_sync_valid_fields(vcpu->kvm);
+ if ((kvm_run->kvm_valid_regs & ~sync_valid_fields) ||
+ (kvm_run->kvm_dirty_regs & ~sync_valid_fields)) {
r = -EINVAL;
goto out;
}
@@ -11576,7 +11605,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
out:
kvm_put_guest_fpu(vcpu);
- if (kvm_run->kvm_valid_regs)
+ if (kvm_run->kvm_valid_regs && likely(!vcpu->arch.guest_state_protected))
store_regs(vcpu);
post_kvm_run_save(vcpu);
kvm_vcpu_srcu_read_unlock(vcpu);
@@ -11711,7 +11740,7 @@ skip_protected_regs:
sregs->cr4 = kvm_read_cr4(vcpu);
sregs->cr8 = kvm_get_cr8(vcpu);
sregs->efer = vcpu->arch.efer;
- sregs->apic_base = kvm_get_apic_base(vcpu);
+ sregs->apic_base = vcpu->arch.apic_base;
}
static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
@@ -11764,6 +11793,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
if (kvm_mpx_supported())
kvm_load_guest_fpu(vcpu);
+ kvm_vcpu_srcu_read_lock(vcpu);
+
r = kvm_apic_accept_events(vcpu);
if (r < 0)
goto out;
@@ -11777,6 +11808,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
mp_state->mp_state = vcpu->arch.mp_state;
out:
+ kvm_vcpu_srcu_read_unlock(vcpu);
+
if (kvm_mpx_supported())
kvm_put_guest_fpu(vcpu);
vcpu_put(vcpu);
@@ -12751,7 +12784,8 @@ out:
int kvm_arch_post_init_vm(struct kvm *kvm)
{
- return kvm_mmu_post_init_vm(kvm);
+ once_init(&kvm->arch.nx_once);
+ return 0;
}
static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
@@ -12876,11 +12910,11 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
mutex_unlock(&kvm->slots_lock);
}
kvm_unload_vcpu_mmus(kvm);
+ kvm_destroy_vcpus(kvm);
kvm_x86_call(vm_destroy)(kvm);
kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
kvm_pic_destroy(kvm);
kvm_ioapic_destroy(kvm);
- kvm_destroy_vcpus(kvm);
kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1));
kvm_mmu_uninit_vm(kvm);
@@ -13545,15 +13579,22 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
{
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
+ struct kvm *kvm = irqfd->kvm;
int ret;
- irqfd->producer = prod;
kvm_arch_start_assignment(irqfd->kvm);
+
+ spin_lock_irq(&kvm->irqfds.lock);
+ irqfd->producer = prod;
+
ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
prod->irq, irqfd->gsi, 1);
if (ret)
kvm_arch_end_assignment(irqfd->kvm);
+ spin_unlock_irq(&kvm->irqfds.lock);
+
+
return ret;
}
@@ -13563,9 +13604,9 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
int ret;
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
+ struct kvm *kvm = irqfd->kvm;
WARN_ON(irqfd->producer != prod);
- irqfd->producer = NULL;
/*
* When producer of consumer is unregistered, we change back to
@@ -13573,12 +13614,18 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
* when the irq is masked/disabled or the consumer side (KVM
* int this case doesn't want to receive the interrupts.
*/
+ spin_lock_irq(&kvm->irqfds.lock);
+ irqfd->producer = NULL;
+
ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
prod->irq, irqfd->gsi, 0);
if (ret)
printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
" fails: %d\n", irqfd->consumer.token, ret);
+ spin_unlock_irq(&kvm->irqfds.lock);
+
+
kvm_arch_end_assignment(irqfd->kvm);
}
@@ -13591,7 +13638,8 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
struct kvm_kernel_irq_routing_entry *new)
{
- if (new->type != KVM_IRQ_ROUTING_MSI)
+ if (old->type != KVM_IRQ_ROUTING_MSI ||
+ new->type != KVM_IRQ_ROUTING_MSI)
return true;
return !!memcmp(&old->msi, &new->msi, sizeof(new->msi));
@@ -13730,7 +13778,7 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva)
* invalidation.
*/
if ((!pcid_enabled && (operand.pcid != 0)) ||
- is_noncanonical_address(operand.gla, vcpu)) {
+ is_noncanonical_invlpg_address(operand.gla, vcpu)) {
kvm_inject_gp(vcpu, 0);
return 1;
}
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index a84c48ef5278..ec623d23d13d 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -8,6 +8,7 @@
#include <asm/pvclock.h>
#include "kvm_cache_regs.h"
#include "kvm_emulate.h"
+#include "cpuid.h"
struct kvm_caps {
/* control of guest tsc rate supported? */
@@ -233,9 +234,52 @@ static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu)
return kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 57 : 48;
}
-static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu)
+static inline u8 max_host_virt_addr_bits(void)
{
- return !__is_canonical_address(la, vcpu_virt_addr_bits(vcpu));
+ return kvm_cpu_cap_has(X86_FEATURE_LA57) ? 57 : 48;
+}
+
+/*
+ * x86 MSRs which contain linear addresses, x86 hidden segment bases, and
+ * IDT/GDT bases have static canonicality checks, the size of which depends
+ * only on the CPU's support for 5-level paging, rather than on the state of
+ * CR4.LA57. This applies to both WRMSR and to other instructions that set
+ * their values, e.g. SGDT.
+ *
+ * KVM passes through most of these MSRS and also doesn't intercept the
+ * instructions that set the hidden segment bases.
+ *
+ * Because of this, to be consistent with hardware, even if the guest doesn't
+ * have LA57 enabled in its CPUID, perform canonicality checks based on *host*
+ * support for 5 level paging.
+ *
+ * Finally, instructions which are related to MMU invalidation of a given
+ * linear address, also have a similar static canonical check on address.
+ * This allows for example to invalidate 5-level addresses of a guest from a
+ * host which uses 4-level paging.
+ */
+static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu,
+ unsigned int flags)
+{
+ if (flags & (X86EMUL_F_INVLPG | X86EMUL_F_MSR | X86EMUL_F_DT_LOAD))
+ return !__is_canonical_address(la, max_host_virt_addr_bits());
+ else
+ return !__is_canonical_address(la, vcpu_virt_addr_bits(vcpu));
+}
+
+static inline bool is_noncanonical_msr_address(u64 la, struct kvm_vcpu *vcpu)
+{
+ return is_noncanonical_address(la, vcpu, X86EMUL_F_MSR);
+}
+
+static inline bool is_noncanonical_base_address(u64 la, struct kvm_vcpu *vcpu)
+{
+ return is_noncanonical_address(la, vcpu, X86EMUL_F_DT_LOAD);
+}
+
+static inline bool is_noncanonical_invlpg_address(u64 la, struct kvm_vcpu *vcpu)
+{
+ return is_noncanonical_address(la, vcpu, X86EMUL_F_INVLPG);
}
static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 622fe24da910..1fc2035df404 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -1472,7 +1472,7 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode,
if (kvm_read_guest_virt(vcpu, (gva_t)sched_poll.ports, ports,
sched_poll.nr_ports * sizeof(*ports), &e)) {
*r = -EFAULT;
- return true;
+ goto out;
}
for (i = 0; i < sched_poll.nr_ports; i++) {
@@ -1916,8 +1916,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm,
{
struct kvm_vcpu *vcpu;
- if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm))
- return -EINVAL;
+ /*
+ * Don't check for the port being within range of max_evtchn_port().
+ * Userspace can configure what ever targets it likes; events just won't
+ * be delivered if/while the target is invalid, just like userspace can
+ * configure MSIs which target non-existent APICs.
+ *
+ * This allow on Live Migration and Live Update, the IRQ routing table
+ * can be restored *independently* of other things like creating vCPUs,
+ * without imposing an ordering dependency on userspace. In this
+ * particular case, the problematic ordering would be with setting the
+ * Xen 'long mode' flag, which changes max_evtchn_port() to allow 4096
+ * instead of 1024 event channels.
+ */
/* We only support 2 level event channels for now */
if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)