FAILED: patch "[PATCH] KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested" failed to apply to 6.15-stable tree

FAILED: patch "[PATCH] KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested" failed to apply to 6.15-stable tree

[gregkh]

The patch below does not apply to the 6.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable@vger.kernel.org>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.15.y
git checkout FETCH_HEAD
git cherry-pick -x 095686e6fcb4150f0a55b1a25987fad3d8af58d6
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2025081222-nearness-monogram-75ab@gregkh' --subject-prefix 'PATCH 6.15.y' HEAD^..

Possible dependencies:



thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 095686e6fcb4150f0a55b1a25987fad3d8af58d6 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Tue, 10 Jun 2025 16:20:08 -0700
Subject: [PATCH] KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested
 VM-Enter

Add a consistency check for L2's guest_ia32_debugctl, as KVM only supports
a subset of hardware functionality, i.e. KVM can't rely on hardware to
detect illegal/unsupported values.  Failure to check the vmcs12 value
would allow the guest to load any harware-supported value while running L2.

Take care to exempt BTF and LBR from the validity check in order to match
KVM's behavior for writes via WRMSR, but without clobbering vmcs12.  Even
if VM_EXIT_SAVE_DEBUG_CONTROLS is set in vmcs12, L1 can reasonably expect
that vmcs12->guest_ia32_debugctl will not be modified if writes to the MSR
are being intercepted.

Arguably, KVM _should_ update vmcs12 if VM_EXIT_SAVE_DEBUG_CONTROLS is set
*and* writes to MSR_IA32_DEBUGCTLMSR are not being intercepted by L1, but
that would incur non-trivial complexity and wouldn't change the fact that
KVM's handling of DEBUGCTL is blatantly broken.  I.e. the extra complexity
is not worth carrying.

Cc: stable@vger.kernel.org
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20250610232010.162191-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 7211c71d4241..1b8b0642fc2d 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2663,7 +2663,8 @@ 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);
+		vmcs_write64(GUEST_IA32_DEBUGCTL, 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);
@@ -3156,7 +3157,8 @@ 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) &&
@@ -4608,6 +4610,12 @@ 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;
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4f827a75d980..6a8b78e954cd 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2174,7 +2174,7 @@ 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;
 
@@ -2193,8 +2193,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
 	return debugctl;
 }
 
-static bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data,
-				  bool host_initiated)
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated)
 {
 	u64 invalid;
 
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index b5758c33c60f..392e66c7e5fe 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -414,6 +414,9 @@ 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);
+
 /*
  * Note, early Intel manuals have the write-low and read-high bitmap offsets
  * the wrong way round.  The bitmaps control MSRs 0x00000000-0x00001fff and

[PATCH 6.15.y 1/2] KVM: VMX: Extract checking of guest's DEBUGCTL into helper

[Sasha Levin]

From: Sean Christopherson <seanjc@google.com>

[ Upstream commit 8a4351ac302cd8c19729ba2636acfd0467c22ae8 ]

Move VMX's logic to check DEBUGCTL values into a standalone helper so that
the code can be used by nested VM-Enter to apply the same logic to the
value being loaded from vmcs12.

KVM needs to explicitly check vmcs12->guest_ia32_debugctl on nested
VM-Enter, as hardware may support features that KVM does not, i.e. relying
on hardware to detect invalid guest state will result in false negatives.
Unfortunately, that means applying KVM's funky suppression of BTF and LBR
to vmcs12 so as not to break existing guests.

No functional change intended.

Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://lore.kernel.org/r/20250610232010.162191-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Stable-dep-of: 095686e6fcb4 ("KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested VM-Enter")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/x86/kvm/vmx/vmx.c | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index eec0aa13e002..e812e98b06a8 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2195,6 +2195,19 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
 	return debugctl;
 }
 
+static 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.
@@ -2263,19 +2276,12 @@ 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;
@@ -2285,7 +2291,6 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		    (data & DEBUGCTLMSR_LBR))
 			intel_pmu_create_guest_lbr_event(vcpu);
 		return 0;
-	}
 	case MSR_IA32_BNDCFGS:
 		if (!kvm_mpx_supported() ||
 		    (!msr_info->host_initiated &&
-- 
2.39.5

[PATCH 6.15.y 2/2] KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested VM-Enter

[Sasha Levin]

From: Maxim Levitsky <mlevitsk@redhat.com>

[ Upstream commit 095686e6fcb4150f0a55b1a25987fad3d8af58d6 ]

Add a consistency check for L2's guest_ia32_debugctl, as KVM only supports
a subset of hardware functionality, i.e. KVM can't rely on hardware to
detect illegal/unsupported values.  Failure to check the vmcs12 value
would allow the guest to load any harware-supported value while running L2.

Take care to exempt BTF and LBR from the validity check in order to match
KVM's behavior for writes via WRMSR, but without clobbering vmcs12.  Even
if VM_EXIT_SAVE_DEBUG_CONTROLS is set in vmcs12, L1 can reasonably expect
that vmcs12->guest_ia32_debugctl will not be modified if writes to the MSR
are being intercepted.

Arguably, KVM _should_ update vmcs12 if VM_EXIT_SAVE_DEBUG_CONTROLS is set
*and* writes to MSR_IA32_DEBUGCTLMSR are not being intercepted by L1, but
that would incur non-trivial complexity and wouldn't change the fact that
KVM's handling of DEBUGCTL is blatantly broken.  I.e. the extra complexity
is not worth carrying.

Cc: stable@vger.kernel.org
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20250610232010.162191-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/x86/kvm/vmx/nested.c | 12 ++++++++++--
 arch/x86/kvm/vmx/vmx.c    |  5 ++---
 arch/x86/kvm/vmx/vmx.h    |  3 +++
 3 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 5504d9e9fd32..8c881f6fa6ea 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2653,7 +2653,8 @@ 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);
+		vmcs_write64(GUEST_IA32_DEBUGCTL, 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);
@@ -3146,7 +3147,8 @@ 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) &&
@@ -4598,6 +4600,12 @@ 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;
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e812e98b06a8..5dcd93f9875b 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2180,7 +2180,7 @@ 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;
 
@@ -2195,8 +2195,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
 	return debugctl;
 }
 
-static bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data,
-				  bool host_initiated)
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated)
 {
 	u64 invalid;
 
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 951e44dc9d0e..888d5e9ff547 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -437,6 +437,9 @@ 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);
+
 /*
  * Note, early Intel manuals have the write-low and read-high bitmap offsets
  * the wrong way round.  The bitmaps control MSRs 0x00000000-0x00001fff and
-- 
2.39.5