KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested VM-Enter

[ 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>
Stable-dep-of: 6b1dd26544d0 ("KVM: VMX: Preserve host's DEBUGCTLMSR_FREEZE_IN_SMM while running the guest")
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 7211c71d42413562355e54962a7c01b972985c9d..1b8b0642fc2d63f5a4f9acfcdd0a914cf832c90a 100644 (file)
--- 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 78aa1a7087baaafe122d2853c7f4fb25f1cb717b..c583fae3fdcb710005b82f22092ab0e94c20406c 100644 (file)
--- 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 b5758c33c60f9d69ce0f8459ac4fcacb00267b97..392e66c7e5fe4775f433a0b3f29431675dc0d94f 100644 (file)
--- 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