linux-kernel - [PATCH v4 06/26] KVM: nSVM: Triple fault if restore host CR3 fails on nested #VMEXIT

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20260115011312.3675857-7-yosry.ahmed@linux.dev>
Date: Thu, 15 Jan 2026 01:12:52 +0000
From: Yosry Ahmed <yosry.ahmed@...ux.dev>
To: Sean Christopherson <seanjc@...gle.com>
Cc: Paolo Bonzini <pbonzini@...hat.com>,
	kvm@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	Yosry Ahmed <yosry.ahmed@...ux.dev>,
	stable@...r.kernel.org
Subject: [PATCH v4 06/26] 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.

>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@...r.kernel.org
Signed-off-by: Yosry Ahmed <yosry.ahmed@...ux.dev>
---
 arch/x86/kvm/svm/nested.c | 12 ++++++------
 arch/x86/kvm/svm/svm.c    | 11 ++---------
 arch/x86/kvm/svm/svm.h    |  6 +++---
 3 files changed, 11 insertions(+), 18 deletions(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 593f7005cdc7..6c4c31d2b30f 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1124,7 +1124,7 @@ void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
 	to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip;
 }
 
-int nested_svm_vmexit(struct vcpu_svm *svm)
+void nested_svm_vmexit(struct vcpu_svm *svm)
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 	gpa_t vmcb12_gpa = svm->nested.vmcb12_gpa;
@@ -1146,7 +1146,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 
 	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map)) {
 		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
-		return 1;
+		return;
 	}
 
 	/* Give the current vmcb to the guest */
@@ -1309,8 +1309,10 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 
 	nested_svm_uninit_mmu_context(vcpu);
 
-	if (nested_svm_load_cr3(vcpu, vmcb01->save.cr3, false, true))
-		return 1;
+	if (nested_svm_load_cr3(vcpu, vmcb01->save.cr3, false, true)) {
+		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+		return;
+	}
 
 	/*
 	 * Drop what we picked up for L2 via svm_complete_interrupts() so it
@@ -1335,8 +1337,6 @@ 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 c6ed59e5f0b8..f3901f9ee487 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2227,13 +2227,9 @@ 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);
@@ -4778,7 +4774,6 @@ 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;
@@ -4798,9 +4793,7 @@ 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 2ce62cc55d7b..3e3dcd671aad 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -785,15 +785,15 @@ 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_code_hi	= 0;
 	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);
-- 
2.52.0.457.g6b5491de43-goog