KVM: nSVM: Triple fault if restore host CR3 fails on nested #VMEXIT

If loading L1's CR3 fails on a nested #VMEXIT, nested_svm_vmexit()
returns an error code that is ignored by most callers, and continues to
run L1 with corrupted state. A sane recovery is not possible in this
case, and HW behavior is to cause a shutdown. Inject a triple fault
instead, and do not return early from nested_svm_vmexit(). Continue
cleaning up the vCPU state (e.g. clear pending exceptions), to handle
the failure as gracefully as possible.

From the APM:

  Upon #VMEXIT, the processor performs the following actions in order to
  return to the host execution context:

  ...

  if (illegal host state loaded, or exception while loading host state)
      shutdown
  else
      execute first host instruction following the VMRUN

Remove the return value of nested_svm_vmexit(), which is mostly
unchecked anyway.

Fixes: d82aaef9c88a ("KVM: nSVM: use nested_svm_load_cr3() on guest->host switch")
CC: stable@vger.kernel.org
Signed-off-by: Yosry Ahmed <yosry@kernel.org>
Link: https://patch.msgid.link/20260303003421.2185681-10-yosry@kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 30c99bbe9927dd2ca46442b587d3cca22eac31df..5e0feeb50ba3264842fe57cbed14eff04e6999c5 100644 (file)
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1192,12 +1192,11 @@ static int nested_svm_vmexit_update_vmcb12(struct kvm_vcpu *vcpu)
        return 0;
 }
 
-int nested_svm_vmexit(struct vcpu_svm *svm)
+void nested_svm_vmexit(struct vcpu_svm *svm)
 {
        struct kvm_vcpu *vcpu = &svm->vcpu;
        struct vmcb *vmcb01 = svm->vmcb01.ptr;
        struct vmcb *vmcb02 = svm->nested.vmcb02.ptr;
-       int rc;
 
        if (nested_svm_vmexit_update_vmcb12(vcpu))
                kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
@@ -1316,9 +1315,8 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 
        nested_svm_uninit_mmu_context(vcpu);
 
-       rc = nested_svm_load_cr3(vcpu, vmcb01->save.cr3, false, true);
-       if (rc)
-               return 1;
+       if (nested_svm_load_cr3(vcpu, vmcb01->save.cr3, false, true))
+               kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 
        /*
         * Drop what we picked up for L2 via svm_complete_interrupts() so it
@@ -1343,8 +1341,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
         */
        if (kvm_apicv_activated(vcpu->kvm))
                __kvm_vcpu_update_apicv(vcpu);
-
-       return 0;
 }
 
 static void nested_svm_triple_fault(struct kvm_vcpu *vcpu)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index e97c56df41f632d1bed755a944c9cda75db8fa92..7efa7170929232f2965febc788fc523a3cea1867 100644 (file)
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2234,13 +2234,9 @@ static int emulate_svm_instr(struct kvm_vcpu *vcpu, int opcode)
                [SVM_INSTR_VMSAVE] = vmsave_interception,
        };
        struct vcpu_svm *svm = to_svm(vcpu);
-       int ret;
 
        if (is_guest_mode(vcpu)) {
-               /* Returns '1' or -errno on failure, '0' on success. */
-               ret = nested_svm_simple_vmexit(svm, guest_mode_exit_codes[opcode]);
-               if (ret)
-                       return ret;
+               nested_svm_simple_vmexit(svm, guest_mode_exit_codes[opcode]);
                return 1;
        }
        return svm_instr_handlers[opcode](vcpu);
@@ -4871,7 +4867,6 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
 {
        struct vcpu_svm *svm = to_svm(vcpu);
        struct kvm_host_map map_save;
-       int ret;
 
        if (!is_guest_mode(vcpu))
                return 0;
@@ -4891,9 +4886,7 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
        svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
        svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
 
-       ret = nested_svm_simple_vmexit(svm, SVM_EXIT_SW);
-       if (ret)
-               return ret;
+       nested_svm_simple_vmexit(svm, SVM_EXIT_SW);
 
        /*
         * KVM uses VMCB01 to store L1 host state while L2 runs but

diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 44d767cd1d25a9b408d70be5fb6041ba62590584..7629cb37c9302d202711ea2558523daf7fd7a600 100644 (file)
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -793,14 +793,14 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu);
 void svm_copy_vmrun_state(struct vmcb_save_area *to_save,
                          struct vmcb_save_area *from_save);
 void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb);
-int nested_svm_vmexit(struct vcpu_svm *svm);
+void nested_svm_vmexit(struct vcpu_svm *svm);
 
-static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code)
+static inline void nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code)
 {
        svm->vmcb->control.exit_code    = exit_code;
        svm->vmcb->control.exit_info_1  = 0;
        svm->vmcb->control.exit_info_2  = 0;
-       return nested_svm_vmexit(svm);
+       nested_svm_vmexit(svm);
 }
 
 int nested_svm_exit_handled(struct vcpu_svm *svm);