aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-01-27 09:21:00 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2019-01-27 09:21:00 -0800
commit1fc7f56db7a7c467e46a5d2e2a009d2f337e0338 (patch)
treed534b5627a7b9317f08bec84c1e8a0dfa0848cd8
parentMerge tag 'dma-mapping-5.0-2' of git://git.infradead.org/users/hch/dma-mapping (diff)
parentKVM: x86: Mark expected switch fall-throughs (diff)
downloadlinux-dev-1fc7f56db7a7c467e46a5d2e2a009d2f337e0338.tar.xz
linux-dev-1fc7f56db7a7c467e46a5d2e2a009d2f337e0338.zip
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM fixes from Paolo Bonzini: "Quite a few fixes for x86: nested virtualization save/restore, AMD nested virtualization and virtual APIC, 32-bit fixes, an important fix to restore operation on older processors, and a bunch of hyper-v bugfixes. Several are marked stable. There are also fixes for GCC warnings and for a GCC/objtool interaction" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: KVM: x86: Mark expected switch fall-throughs KVM: x86: fix TRACE_INCLUDE_PATH and remove -I. header search paths KVM: selftests: check returned evmcs version range x86/kvm/hyper-v: nested_enable_evmcs() sets vmcs_version incorrectly KVM: VMX: Move vmx_vcpu_run()'s VM-Enter asm blob to a helper function kvm: selftests: Fix region overlap check in kvm_util kvm: vmx: fix some -Wmissing-prototypes warnings KVM: nSVM: clear events pending from svm_complete_interrupts() when exiting to L1 svm: Fix AVIC incomplete IPI emulation svm: Add warning message for AVIC IPI invalid target KVM: x86: WARN_ONCE if sending a PV IPI returns a fatal error KVM: x86: Fix PV IPIs for 32-bit KVM host x86/kvm/hyper-v: recommend using eVMCS only when it is enabled x86/kvm/hyper-v: don't recommend doing reset via synthetic MSR kvm: x86/vmx: Use kzalloc for cached_vmcs12 KVM: VMX: Use the correct field var when clearing VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL KVM: x86: Fix single-step debugging x86/kvm/hyper-v: don't announce GUEST IDLE MSR support
-rw-r--r--arch/x86/kernel/kvm.c7
-rw-r--r--arch/x86/kvm/Makefile4
-rw-r--r--arch/x86/kvm/hyperv.c7
-rw-r--r--arch/x86/kvm/lapic.c2
-rw-r--r--arch/x86/kvm/mmu.c1
-rw-r--r--arch/x86/kvm/svm.c31
-rw-r--r--arch/x86/kvm/trace.h2
-rw-r--r--arch/x86/kvm/vmx/evmcs.c7
-rw-r--r--arch/x86/kvm/vmx/nested.c14
-rw-r--r--arch/x86/kvm/vmx/vmx.c147
-rw-r--r--arch/x86/kvm/x86.c8
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c9
-rw-r--r--tools/testing/selftests/kvm/x86_64/evmcs_test.c6
13 files changed, 130 insertions, 115 deletions
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index ba4bfb7f6a36..5c93a65ee1e5 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -457,6 +457,7 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
#else
u64 ipi_bitmap = 0;
#endif
+ long ret;
if (cpumask_empty(mask))
return;
@@ -482,8 +483,9 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
} else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) {
max = apic_id < max ? max : apic_id;
} else {
- kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
+ ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
(unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
+ WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret);
min = max = apic_id;
ipi_bitmap = 0;
}
@@ -491,8 +493,9 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
}
if (ipi_bitmap) {
- kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
+ ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
(unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
+ WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret);
}
local_irq_restore(flags);
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 69b3a7c30013..31ecf7a76d5a 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -2,10 +2,6 @@
ccflags-y += -Iarch/x86/kvm
-CFLAGS_x86.o := -I.
-CFLAGS_svm.o := -I.
-CFLAGS_vmx.o := -I.
-
KVM := ../../../virt/kvm
kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index c90a5352d158..89d20ed1d2e8 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1636,7 +1636,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
ret = kvm_hvcall_signal_event(vcpu, fast, ingpa);
if (ret != HV_STATUS_INVALID_PORT_ID)
break;
- /* maybe userspace knows this conn_id: fall through */
+ /* fall through - maybe userspace knows this conn_id. */
case HVCALL_POST_MESSAGE:
/* don't bother userspace if it has no way to handle it */
if (unlikely(rep || !vcpu_to_synic(vcpu)->active)) {
@@ -1832,7 +1832,6 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
ent->eax |= HV_X64_MSR_VP_INDEX_AVAILABLE;
ent->eax |= HV_X64_MSR_RESET_AVAILABLE;
ent->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE;
- ent->eax |= HV_X64_MSR_GUEST_IDLE_AVAILABLE;
ent->eax |= HV_X64_ACCESS_FREQUENCY_MSRS;
ent->eax |= HV_X64_ACCESS_REENLIGHTENMENT;
@@ -1848,11 +1847,11 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
case HYPERV_CPUID_ENLIGHTMENT_INFO:
ent->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED;
ent->eax |= HV_X64_APIC_ACCESS_RECOMMENDED;
- ent->eax |= HV_X64_SYSTEM_RESET_RECOMMENDED;
ent->eax |= HV_X64_RELAXED_TIMING_RECOMMENDED;
ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED;
ent->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED;
- ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
+ if (evmcs_ver)
+ ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
/*
* Default number of spinlock retry attempts, matches
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 9f089e2e09d0..4b6c2da7265c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1035,6 +1035,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
switch (delivery_mode) {
case APIC_DM_LOWEST:
vcpu->arch.apic_arb_prio++;
+ /* fall through */
case APIC_DM_FIXED:
if (unlikely(trig_mode && !level))
break;
@@ -1874,6 +1875,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
case APIC_LVT0:
apic_manage_nmi_watchdog(apic, val);
+ /* fall through */
case APIC_LVTTHMR:
case APIC_LVTPC:
case APIC_LVT1:
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ce770b446238..da9c42349b1f 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4371,6 +4371,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
rsvd_bits(maxphyaddr, 51);
rsvd_check->rsvd_bits_mask[1][4] =
rsvd_check->rsvd_bits_mask[0][4];
+ /* fall through */
case PT64_ROOT_4LEVEL:
rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd |
nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index a157ca5b6869..f13a3a24d360 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3414,6 +3414,14 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
kvm_mmu_reset_context(&svm->vcpu);
kvm_mmu_load(&svm->vcpu);
+ /*
+ * Drop what we picked up for L2 via svm_complete_interrupts() so it
+ * doesn't end up in L1.
+ */
+ svm->vcpu.arch.nmi_injected = false;
+ kvm_clear_exception_queue(&svm->vcpu);
+ kvm_clear_interrupt_queue(&svm->vcpu);
+
return 0;
}
@@ -4395,7 +4403,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
case MSR_IA32_APICBASE:
if (kvm_vcpu_apicv_active(vcpu))
avic_update_vapic_bar(to_svm(vcpu), data);
- /* Follow through */
+ /* Fall through */
default:
return kvm_set_msr_common(vcpu, msr);
}
@@ -4504,28 +4512,19 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
kvm_lapic_reg_write(apic, APIC_ICR, icrl);
break;
case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: {
- int i;
- struct kvm_vcpu *vcpu;
- struct kvm *kvm = svm->vcpu.kvm;
struct kvm_lapic *apic = svm->vcpu.arch.apic;
/*
- * At this point, we expect that the AVIC HW has already
- * set the appropriate IRR bits on the valid target
- * vcpus. So, we just need to kick the appropriate vcpu.
+ * Update ICR high and low, then emulate sending IPI,
+ * which is handled when writing APIC_ICR.
*/
- kvm_for_each_vcpu(i, vcpu, kvm) {
- bool m = kvm_apic_match_dest(vcpu, apic,
- icrl & KVM_APIC_SHORT_MASK,
- GET_APIC_DEST_FIELD(icrh),
- icrl & KVM_APIC_DEST_MASK);
-
- if (m && !avic_vcpu_is_running(vcpu))
- kvm_vcpu_wake_up(vcpu);
- }
+ kvm_lapic_reg_write(apic, APIC_ICR2, icrh);
+ kvm_lapic_reg_write(apic, APIC_ICR, icrl);
break;
}
case AVIC_IPI_FAILURE_INVALID_TARGET:
+ WARN_ONCE(1, "Invalid IPI target: index=%u, vcpu=%d, icr=%#0x:%#0x\n",
+ index, svm->vcpu.vcpu_id, icrh, icrl);
break;
case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE:
WARN_ONCE(1, "Invalid backing page\n");
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 705f40ae2532..6432d08c7de7 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1465,7 +1465,7 @@ TRACE_EVENT(kvm_hv_send_ipi_ex,
#endif /* _TRACE_KVM_H */
#undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH arch/x86/kvm
+#define TRACE_INCLUDE_PATH ../../arch/x86/kvm
#undef TRACE_INCLUDE_FILE
#define TRACE_INCLUDE_FILE trace
diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c
index 95bc2247478d..5466c6d85cf3 100644
--- a/arch/x86/kvm/vmx/evmcs.c
+++ b/arch/x86/kvm/vmx/evmcs.c
@@ -332,16 +332,17 @@ int nested_enable_evmcs(struct kvm_vcpu *vcpu,
uint16_t *vmcs_version)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ bool evmcs_already_enabled = vmx->nested.enlightened_vmcs_enabled;
+
+ vmx->nested.enlightened_vmcs_enabled = true;
if (vmcs_version)
*vmcs_version = nested_get_evmcs_version(vcpu);
/* We don't support disabling the feature for simplicity. */
- if (vmx->nested.enlightened_vmcs_enabled)
+ if (evmcs_already_enabled)
return 0;
- vmx->nested.enlightened_vmcs_enabled = true;
-
vmx->nested.msrs.pinbased_ctls_high &= ~EVMCS1_UNSUPPORTED_PINCTRL;
vmx->nested.msrs.entry_ctls_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
vmx->nested.msrs.exit_ctls_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 2616bd2c7f2c..8ff20523661b 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -55,7 +55,7 @@ static u16 shadow_read_write_fields[] = {
static int max_shadow_read_write_fields =
ARRAY_SIZE(shadow_read_write_fields);
-void init_vmcs_shadow_fields(void)
+static void init_vmcs_shadow_fields(void)
{
int i, j;
@@ -4140,11 +4140,11 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
if (r < 0)
goto out_vmcs02;
- vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
+ vmx->nested.cached_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL);
if (!vmx->nested.cached_vmcs12)
goto out_cached_vmcs12;
- vmx->nested.cached_shadow_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
+ vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL);
if (!vmx->nested.cached_shadow_vmcs12)
goto out_cached_shadow_vmcs12;
@@ -5263,13 +5263,17 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
copy_shadow_to_vmcs12(vmx);
}
- if (copy_to_user(user_kvm_nested_state->data, vmcs12, sizeof(*vmcs12)))
+ /*
+ * Copy over the full allocated size of vmcs12 rather than just the size
+ * of the struct.
+ */
+ if (copy_to_user(user_kvm_nested_state->data, vmcs12, VMCS12_SIZE))
return -EFAULT;
if (nested_cpu_has_shadow_vmcs(vmcs12) &&
vmcs12->vmcs_link_pointer != -1ull) {
if (copy_to_user(user_kvm_nested_state->data + VMCS12_SIZE,
- get_shadow_vmcs12(vcpu), sizeof(*vmcs12)))
+ get_shadow_vmcs12(vcpu), VMCS12_SIZE))
return -EFAULT;
}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index f6915f10e584..4341175339f3 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -423,7 +423,7 @@ static void check_ept_pointer_match(struct kvm *kvm)
to_kvm_vmx(kvm)->ept_pointers_match = EPT_POINTERS_MATCH;
}
-int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush,
+static int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush,
void *data)
{
struct kvm_tlb_range *range = data;
@@ -1773,7 +1773,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if (!msr_info->host_initiated &&
!guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
return 1;
- /* Otherwise falls through */
+ /* Else, falls through */
default:
msr = find_msr_entry(vmx, msr_info->index);
if (msr) {
@@ -2014,7 +2014,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
/* Check reserved bit, higher 32 bits should be zero */
if ((data >> 32) != 0)
return 1;
- /* Otherwise falls through */
+ /* Else, falls through */
default:
msr = find_msr_entry(vmx, msr_index);
if (msr) {
@@ -2344,7 +2344,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
case 37: /* AAT100 */
case 44: /* BC86,AAY89,BD102 */
case 46: /* BA97 */
- _vmexit_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+ _vmentry_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
_vmexit_control &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL "
"does not work properly. Using workaround\n");
@@ -6362,72 +6362,9 @@ static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
vmx->loaded_vmcs->hv_timer_armed = false;
}
-static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
+static void __vmx_vcpu_run(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- unsigned long cr3, cr4, evmcs_rsp;
-
- /* Record the guest's net vcpu time for enforced NMI injections. */
- if (unlikely(!enable_vnmi &&
- vmx->loaded_vmcs->soft_vnmi_blocked))
- vmx->loaded_vmcs->entry_time = ktime_get();
-
- /* Don't enter VMX if guest state is invalid, let the exit handler
- start emulation until we arrive back to a valid state */
- if (vmx->emulation_required)
- return;
-
- if (vmx->ple_window_dirty) {
- vmx->ple_window_dirty = false;
- vmcs_write32(PLE_WINDOW, vmx->ple_window);
- }
-
- if (vmx->nested.need_vmcs12_sync)
- nested_sync_from_vmcs12(vcpu);
-
- if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
- vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
- if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
- vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
-
- cr3 = __get_current_cr3_fast();
- if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
- vmcs_writel(HOST_CR3, cr3);
- vmx->loaded_vmcs->host_state.cr3 = cr3;
- }
-
- cr4 = cr4_read_shadow();
- if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
- vmcs_writel(HOST_CR4, cr4);
- vmx->loaded_vmcs->host_state.cr4 = cr4;
- }
-
- /* 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
- * exceptions being set, but that's not correct for the guest debugging
- * case. */
- if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
- vmx_set_interrupt_shadow(vcpu, 0);
-
- if (static_cpu_has(X86_FEATURE_PKU) &&
- kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
- vcpu->arch.pkru != vmx->host_pkru)
- __write_pkru(vcpu->arch.pkru);
-
- pt_guest_enter(vmx);
-
- atomic_switch_perf_msrs(vmx);
-
- vmx_update_hv_timer(vcpu);
-
- /*
- * If this vCPU has touched SPEC_CTRL, restore the guest's value if
- * it's non-zero. Since vmentry is serialising on affected CPUs, there
- * is no need to worry about the conditional branch over the wrmsr
- * being speculatively taken.
- */
- x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
+ unsigned long evmcs_rsp;
vmx->__launched = vmx->loaded_vmcs->launched;
@@ -6567,6 +6504,77 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
, "eax", "ebx", "edi"
#endif
);
+}
+STACK_FRAME_NON_STANDARD(__vmx_vcpu_run);
+
+static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned long cr3, cr4;
+
+ /* Record the guest's net vcpu time for enforced NMI injections. */
+ if (unlikely(!enable_vnmi &&
+ vmx->loaded_vmcs->soft_vnmi_blocked))
+ vmx->loaded_vmcs->entry_time = ktime_get();
+
+ /* Don't enter VMX if guest state is invalid, let the exit handler
+ start emulation until we arrive back to a valid state */
+ if (vmx->emulation_required)
+ return;
+
+ if (vmx->ple_window_dirty) {
+ vmx->ple_window_dirty = false;
+ vmcs_write32(PLE_WINDOW, vmx->ple_window);
+ }
+
+ if (vmx->nested.need_vmcs12_sync)
+ nested_sync_from_vmcs12(vcpu);
+
+ if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
+ vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
+ if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
+ vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
+
+ cr3 = __get_current_cr3_fast();
+ if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
+ vmcs_writel(HOST_CR3, cr3);
+ vmx->loaded_vmcs->host_state.cr3 = cr3;
+ }
+
+ cr4 = cr4_read_shadow();
+ if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
+ vmcs_writel(HOST_CR4, cr4);
+ vmx->loaded_vmcs->host_state.cr4 = cr4;
+ }
+
+ /* 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
+ * exceptions being set, but that's not correct for the guest debugging
+ * case. */
+ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+ vmx_set_interrupt_shadow(vcpu, 0);
+
+ if (static_cpu_has(X86_FEATURE_PKU) &&
+ kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
+ vcpu->arch.pkru != vmx->host_pkru)
+ __write_pkru(vcpu->arch.pkru);
+
+ pt_guest_enter(vmx);
+
+ atomic_switch_perf_msrs(vmx);
+
+ vmx_update_hv_timer(vcpu);
+
+ /*
+ * If this vCPU has touched SPEC_CTRL, restore the guest's value if
+ * it's non-zero. Since vmentry is serialising on affected CPUs, there
+ * is no need to worry about the conditional branch over the wrmsr
+ * being speculatively taken.
+ */
+ x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
+
+ __vmx_vcpu_run(vcpu, vmx);
/*
* We do not use IBRS in the kernel. If this vCPU has used the
@@ -6648,7 +6656,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
vmx_recover_nmi_blocking(vmx);
vmx_complete_interrupts(vmx);
}
-STACK_FRAME_NON_STANDARD(vmx_vcpu_run);
static struct kvm *vmx_vm_alloc(void)
{
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02c8e095a239..3d27206f6c01 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3834,6 +3834,8 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
case KVM_CAP_HYPERV_SYNIC2:
if (cap->args[0])
return -EINVAL;
+ /* fall through */
+
case KVM_CAP_HYPERV_SYNIC:
if (!irqchip_in_kernel(vcpu->kvm))
return -EINVAL;
@@ -6480,8 +6482,7 @@ restart:
toggle_interruptibility(vcpu, ctxt->interruptibility);
vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
kvm_rip_write(vcpu, ctxt->eip);
- if (r == EMULATE_DONE &&
- (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
+ if (r == EMULATE_DONE && ctxt->tf)
kvm_vcpu_do_singlestep(vcpu, &r);
if (!ctxt->have_exception ||
exception_type(ctxt->exception.vector) == EXCPT_TRAP)
@@ -7093,10 +7094,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
case KVM_HC_CLOCK_PAIRING:
ret = kvm_pv_clock_pairing(vcpu, a0, a1);
break;
+#endif
case KVM_HC_SEND_IPI:
ret = kvm_pv_send_ipi(vcpu->kvm, a0, a1, a2, a3, op_64_bit);
break;
-#endif
default:
ret = -KVM_ENOSYS;
break;
@@ -7937,6 +7938,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
vcpu->arch.pv.pv_unhalted = false;
vcpu->arch.mp_state =
KVM_MP_STATE_RUNNABLE;
+ /* fall through */
case KVM_MP_STATE_RUNNABLE:
vcpu->arch.apf.halted = false;
break;
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 23022e9d32eb..b52cfdefecbf 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -571,7 +571,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
* already exist.
*/
region = (struct userspace_mem_region *) userspace_mem_region_find(
- vm, guest_paddr, guest_paddr + npages * vm->page_size);
+ vm, guest_paddr, (guest_paddr + npages * vm->page_size) - 1);
if (region != NULL)
TEST_ASSERT(false, "overlapping userspace_mem_region already "
"exists\n"
@@ -587,15 +587,10 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
region = region->next) {
if (region->region.slot == slot)
break;
- if ((guest_paddr <= (region->region.guest_phys_addr
- + region->region.memory_size))
- && ((guest_paddr + npages * vm->page_size)
- >= region->region.guest_phys_addr))
- break;
}
if (region != NULL)
TEST_ASSERT(false, "A mem region with the requested slot "
- "or overlapping physical memory range already exists.\n"
+ "already exists.\n"
" requested slot: %u paddr: 0x%lx npages: 0x%lx\n"
" existing slot: %u paddr: 0x%lx size: 0x%lx",
slot, guest_paddr, npages,
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
index ea3c73e8f4f6..c49c2a28b0eb 100644
--- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -103,6 +103,12 @@ int main(int argc, char *argv[])
vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
+ /* KVM should return supported EVMCS version range */
+ TEST_ASSERT(((evmcs_ver >> 8) >= (evmcs_ver & 0xff)) &&
+ (evmcs_ver & 0xff) > 0,
+ "Incorrect EVMCS version range: %x:%x\n",
+ evmcs_ver & 0xff, evmcs_ver >> 8);
+
run = vcpu_state(vm, VCPU_ID);
vcpu_regs_get(vm, VCPU_ID, &regs1);