[PATCH v3 0/2] KVM: SVM: Fix a bug where TSC_AUX can get clobbered

[PATCH v3 0/2] KVM: SVM: Fix a bug where TSC_AUX can get clobbered

[Sean Christopherson]

Fix a bug where an SEV-ES vCPU running on the same pCPU as a non-SEV-ES vCPU
could clobber TSC_AUX due to loading the host's TSC_AUX on #VMEXIT, as opposed
to restoring whatever was in hardware at the time of VMRUN.

v3:
 - Collect reviews. [Xiaoyao]
 - Make tsc_aux_uret_slot globally visible instead of passing it as a param.
   [Xiaoyao]
 - Mark tsc_aux_uret_slot __ro_after_init.

v2:
 - https://lore.kernel.org/all/20250919213806.1582673-1-seanjc@google.com
 - Drop "cache" from the user_return API.
 - Handle the SEV-ES case in SEV-ES code.
 - Tag everything for stable@.
 - Massage changelog to avoid talking about the host's value and instead
   focus on failing to restore what KVM thinks is in hardware.

v1: https://lore.kernel.org/all/05a018a6997407080b3b7921ba692aa69a720f07.1758166596.git.houwenlong.hwl@antgroup.com

Hou Wenlong (2):
  KVM: x86: Add helper to retrieve current value of user return MSR
  KVM: SVM: Re-load current, not host, TSC_AUX on #VMEXIT from SEV-ES
    guest

 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/svm/sev.c          | 10 ++++++++++
 arch/x86/kvm/svm/svm.c          | 25 ++++++-------------------
 arch/x86/kvm/svm/svm.h          |  2 ++
 arch/x86/kvm/x86.c              |  6 ++++++
 5 files changed, 25 insertions(+), 19 deletions(-)


base-commit: c8fbf7ceb2ae3f64b0c377c8c21f6df577a13eb4
-- 
2.51.0.534.gc79095c0ca-goog

[PATCH v3 1/2] KVM: x86: Add helper to retrieve current value of user return MSR

[Sean Christopherson]

From: Hou Wenlong <houwenlong.hwl@antgroup.com>

In the user return MSR support, the cached value is always the hardware
value of the specific MSR. Therefore, add a helper to retrieve the
cached value, which can replace the need for RDMSR, for example, to
allow SEV-ES guests to restore the correct host hardware value without
using RDMSR.

Cc: stable@vger.kernel.org
Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
[sean: drop "cache" from the name, make it a one-liner, tag for stable]
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h | 1 +
 arch/x86/kvm/x86.c              | 6 ++++++
 2 files changed, 7 insertions(+)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 17772513b9cc..14236006266b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2376,6 +2376,7 @@ int kvm_add_user_return_msr(u32 msr);
 int kvm_find_user_return_msr(u32 msr);
 int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask);
 void kvm_user_return_msr_update_cache(unsigned int index, u64 val);
+u64 kvm_get_user_return_msr(unsigned int slot);
 
 static inline bool kvm_is_supported_user_return_msr(u32 msr)
 {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e07936efacd4..801bf6172a21 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -675,6 +675,12 @@ void kvm_user_return_msr_update_cache(unsigned int slot, u64 value)
 }
 EXPORT_SYMBOL_GPL(kvm_user_return_msr_update_cache);
 
+u64 kvm_get_user_return_msr(unsigned int slot)
+{
+	return this_cpu_ptr(user_return_msrs)->values[slot].curr;
+}
+EXPORT_SYMBOL_GPL(kvm_get_user_return_msr);
+
 static void drop_user_return_notifiers(void)
 {
 	struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
-- 
2.51.0.534.gc79095c0ca-goog

[PATCH v3 2/2] KVM: SVM: Re-load current, not host, TSC_AUX on #VMEXIT from SEV-ES guest

[Sean Christopherson]

From: Hou Wenlong <houwenlong.hwl@antgroup.com>

Prior to running an SEV-ES guest, set TSC_AUX in the host save area to the
current value in hardware, as tracked by the user return infrastructure,
instead of always loading the host's desired value for the CPU.  If the
pCPU is also running a non-SEV-ES vCPU, loading the host's value on #VMEXIT
could clobber the other vCPU's value, e.g. if the SEV-ES vCPU preempted
the non-SEV-ES vCPU, in which case KVM expects the other vCPU's TSC_AUX
value to be resident in hardware.

Note, unlike TDX, which blindly _zeroes_ TSC_AUX on TD-Exit, SEV-ES CPUs
can load an arbitrary value.  Stuff the current value in the host save
area instead of refreshing the user return cache so that KVM doesn't need
to track whether or not the vCPU actually enterred the guest and thus
loaded TSC_AUX from the host save area.

Opportunistically tag tsc_aux_uret_slot as read-only after init to guard
against unexpected modifications, and to make it obvious that using the
variable in sev_es_prepare_switch_to_guest() is safe.

Fixes: 916e3e5f26ab ("KVM: SVM: Do not use user return MSR support for virtualized TSC_AUX")
Cc: stable@vger.kernel.org
Suggested-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
[sean: handle the SEV-ES case in sev_es_prepare_switch_to_guest()]
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c | 10 ++++++++++
 arch/x86/kvm/svm/svm.c | 25 ++++++-------------------
 arch/x86/kvm/svm/svm.h |  2 ++
 3 files changed, 18 insertions(+), 19 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index cce48fff2e6c..887d0d6ad856 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -4712,6 +4712,16 @@ void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_are
 		hostsa->dr2_addr_mask = amd_get_dr_addr_mask(2);
 		hostsa->dr3_addr_mask = amd_get_dr_addr_mask(3);
 	}
+
+	/*
+	 * TSC_AUX is always virtualized for SEV-ES guests when the feature is
+	 * available, i.e. TSC_AUX is loaded on #VMEXIT from the host save area.
+	 * Set the save area to the current hardware value, i.e. the current
+	 * user return value, so that the correct value is restored on #VMEXIT.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_V_TSC_AUX) &&
+	    !WARN_ON_ONCE(tsc_aux_uret_slot < 0))
+		hostsa->tsc_aux = kvm_get_user_return_msr(tsc_aux_uret_slot);
 }
 
 void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 67f4eed01526..0df2e1a5fb77 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -195,7 +195,7 @@ static DEFINE_MUTEX(vmcb_dump_mutex);
  * RDTSCP and RDPID are not used in the kernel, specifically to allow KVM to
  * defer the restoration of TSC_AUX until the CPU returns to userspace.
  */
-static int tsc_aux_uret_slot __read_mostly = -1;
+int tsc_aux_uret_slot __ro_after_init = -1;
 
 static int get_npt_level(void)
 {
@@ -577,18 +577,6 @@ static int svm_enable_virtualization_cpu(void)
 
 	amd_pmu_enable_virt();
 
-	/*
-	 * If TSC_AUX virtualization is supported, TSC_AUX becomes a swap type
-	 * "B" field (see sev_es_prepare_switch_to_guest()) for SEV-ES guests.
-	 * Since Linux does not change the value of TSC_AUX once set, prime the
-	 * TSC_AUX field now to avoid a RDMSR on every vCPU run.
-	 */
-	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
-		u32 __maybe_unused msr_hi;
-
-		rdmsr(MSR_TSC_AUX, sev_es_host_save_area(sd)->tsc_aux, msr_hi);
-	}
-
 	return 0;
 }
 
@@ -1406,10 +1394,10 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 		__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
 
 	/*
-	 * TSC_AUX is always virtualized for SEV-ES guests when the feature is
-	 * available. The user return MSR support is not required in this case
-	 * because TSC_AUX is restored on #VMEXIT from the host save area
-	 * (which has been initialized in svm_enable_virtualization_cpu()).
+	 * TSC_AUX is always virtualized (context switched by hardware) for
+	 * SEV-ES guests when the feature is available.  For non-SEV-ES guests,
+	 * context switch TSC_AUX via the user_return MSR infrastructure (not
+	 * all CPUs support TSC_AUX virtualization).
 	 */
 	if (likely(tsc_aux_uret_slot >= 0) &&
 	    (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm)))
@@ -3004,8 +2992,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		 * TSC_AUX is always virtualized for SEV-ES guests when the
 		 * feature is available. The user return MSR support is not
 		 * required in this case because TSC_AUX is restored on #VMEXIT
-		 * from the host save area (which has been initialized in
-		 * svm_enable_virtualization_cpu()).
+		 * from the host save area.
 		 */
 		if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm))
 			break;
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 5d39c0b17988..bcbd651d04f2 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -52,6 +52,8 @@ extern bool x2avic_enabled;
 extern bool vnmi;
 extern int lbrv;
 
+extern int tsc_aux_uret_slot __ro_after_init;
+
 /*
  * Clean bits in VMCB.
  * VMCB_ALL_CLEAN_MASK might also need to
-- 
2.51.0.534.gc79095c0ca-goog

Re: [PATCH v3 0/2] KVM: SVM: Fix a bug where TSC_AUX can get clobbered

[Sean Christopherson]

On Tue, 23 Sep 2025 08:37:36 -0700, Sean Christopherson wrote:
> Fix a bug where an SEV-ES vCPU running on the same pCPU as a non-SEV-ES vCPU
> could clobber TSC_AUX due to loading the host's TSC_AUX on #VMEXIT, as opposed
> to restoring whatever was in hardware at the time of VMRUN.
> 
> v3:
>  - Collect reviews. [Xiaoyao]
>  - Make tsc_aux_uret_slot globally visible instead of passing it as a param.
>    [Xiaoyao]
>  - Mark tsc_aux_uret_slot __ro_after_init.
> 
> [...]

Applied to kvm-x86 svm, thanks!

[1/2] KVM: x86: Add helper to retrieve current value of user return MSR
      https://github.com/kvm-x86/linux/commit/9bc366350734
[2/2] KVM: SVM: Re-load current, not host, TSC_AUX on #VMEXIT from SEV-ES guest
      https://github.com/kvm-x86/linux/commit/29da8c823abf

--
https://github.com/kvm-x86/linux/tree/next