From: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/include/asm/kvm_host.h | 6 +++++-
arch/x86/kvm/svm/svm.c | 4 ++--
arch/x86/kvm/vmx/main.c | 6 +++---
arch/x86/kvm/vmx/tdx.c | 3 ++-
arch/x86/kvm/vmx/vmx.c | 3 ++-
arch/x86/kvm/vmx/x86_ops.h | 4 ++--
arch/x86/kvm/x86.c | 11 ++++++++---
7 files changed, 24 insertions(+), 13 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6c06f3d6e081..72e7bb48e7ac 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1671,6 +1671,10 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical)
return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL;
}
+enum kvm_x86_run_flags {
+ KVM_RUN_FORCE_IMMEDIATE_EXIT = BIT(0),
+};
+
struct kvm_x86_ops {
const char *name;
@@ -1752,7 +1756,7 @@ struct kvm_x86_ops {
int (*vcpu_pre_run)(struct kvm_vcpu *vcpu);
enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu,
- bool force_immediate_exit);
+ u64 run_flags);
int (*handle_exit)(struct kvm_vcpu *vcpu,
enum exit_fastpath_completion exit_fastpath);
int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index cc1c721ba067..c8b8a9947057 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4259,9 +4259,9 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
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);
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 94d5d907d37b..a8e80d66e77a 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -176,12 +176,12 @@ static int vt_vcpu_pre_run(struct kvm_vcpu *vcpu)
return vmx_vcpu_pre_run(vcpu);
}
-static fastpath_t vt_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+static fastpath_t vt_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
{
if (is_td_vcpu(vcpu))
- return tdx_vcpu_run(vcpu, force_immediate_exit);
+ return tdx_vcpu_run(vcpu, run_flags);
- return vmx_vcpu_run(vcpu, force_immediate_exit);
+ return vmx_vcpu_run(vcpu, run_flags);
}
static int vt_handle_exit(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index b952bc673271..7dbfad28debc 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1020,8 +1020,9 @@ static void tdx_load_host_xsave_state(struct kvm_vcpu *vcpu)
DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI | \
DEBUGCTLMSR_FREEZE_IN_SMM)
-fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
{
+ bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT;
struct vcpu_tdx *tdx = to_tdx(vcpu);
struct vcpu_vt *vt = to_vt(vcpu);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index ef2d7208dd20..609563da270c 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7324,8 +7324,9 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
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;
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 6bf8be570b2e..e1dfacd6b41f 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);
@@ -132,7 +132,7 @@ void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
void tdx_vcpu_free(struct kvm_vcpu *vcpu);
void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu);
-fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit);
+fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags);
void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
void tdx_vcpu_put(struct kvm_vcpu *vcpu);
bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f6ce044b090a..45e8a9eb438a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10752,6 +10752,7 @@ 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;
bool req_immediate_exit = false;
@@ -10996,8 +10997,11 @@ 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))
@@ -11034,8 +11038,7 @@ 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;
@@ -11047,6 +11050,8 @@ 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;
}
--
2.46.0On Wed, May 21, 2025, Maxim Levitsky wrote:
> ---
> diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
> index b952bc673271..7dbfad28debc 100644
> --- a/arch/x86/kvm/vmx/tdx.c
> +++ b/arch/x86/kvm/vmx/tdx.c
> @@ -1020,8 +1020,9 @@ static void tdx_load_host_xsave_state(struct kvm_vcpu *vcpu)
> DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI | \
> DEBUGCTLMSR_FREEZE_IN_SMM)
>
> -fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
> +fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
> {
> + bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT;
Talking to myself, but I think it makes sense to drop the local force_immediate_exit
entirely, specifically so that the WARN_ON_ONCE() can just yell on run_flags being
non-zero. All immediate usage of run_flags is mutually exclusive with TDX.
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 3cfe89aad68e..9a758d8b38ea 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1018,20 +1018,20 @@ static void tdx_load_host_xsave_state(struct kvm_vcpu *vcpu)
DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI | \
DEBUGCTLMSR_FREEZE_IN_SMM)
-fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
{
struct vcpu_tdx *tdx = to_tdx(vcpu);
struct vcpu_vt *vt = to_vt(vcpu);
/*
- * force_immediate_exit requires vCPU entering for events injection with
- * an immediately exit followed. But The TDX module doesn't guarantee
- * entry, it's already possible for KVM to _think_ it completely entry
- * to the guest without actually having done so.
- * Since KVM never needs to force an immediate exit for TDX, and can't
- * do direct injection, just warn on force_immediate_exit.
+ * WARN if KVM wants to force an immediate exit, as the TDX module does
+ * not guarantee entry into the guest, i.e. it's possible for KVM to
+ * _think_ it completed entry to the guest and forced an immediate exit
+ * without actually having done so. Luckily, KVM never needs to force
+ * an immediate exit for TDX (KVM can't do direct event injection, so
+ * just WARN and continue on.
*/
- WARN_ON_ONCE(force_immediate_exit);
+ WARN_ON_ONCE(run_flags);
/*
* Wait until retry of SEPT-zap-related SEAMCALL completes before
@@ -1041,7 +1041,7 @@ fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
if (unlikely(READ_ONCE(to_kvm_tdx(vcpu->kvm)->wait_for_sept_zap)))
return EXIT_FASTPATH_EXIT_HANDLED;
- trace_kvm_entry(vcpu, force_immediate_exit);
+ trace_kvm_entry(vcpu, run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT);
if (pi_test_on(&vt->pi_desc)) {
apic->send_IPI_self(POSTED_INTR_VECTOR);
© 2016 - 2025 Red Hat, Inc.