[PATCH] KVM: Never clear KVM_REQ_VM_DEAD from a vCPU's requests

Use kvm_test_request() instead of kvm_check_request() when querying
KVM_REQ_VM_DEAD, i.e. don't clear KVM_REQ_VM_DEAD, as the entire purpose
of KVM_REQ_VM_DEAD is to prevent the vCPU from enterring the guest ever
again, even if userspace insists on redoing KVM_RUN.

Ensuring KVM_REQ_VM_DEAD is never cleared will allow relaxing KVM's rule
that ioctls can't be invoked on dead VMs, to only disallow ioctls if the
VM is bugged, i.e. if KVM hit a KVM_BUG_ON().

Opportunistically add compile-time assertions to guard against clearing
KVM_REQ_VM_DEAD through the standard APIs.

Signed-off-by: Sean Christopherson <[email protected]>
---

This was previously posted as part of a series to add an ioctl to allow
userspace to terminate a TDX VM.  I'm posting it separately because it fixes
a very real flaw, although the flaw is probably benign in practice?  I don't
want to find out though, i.e. I don't want to wait to get this merged.

This came back on my radar when fixing a bug in x86's pre-fault code, and
looking at that code made it pretty clear that clearing KVM_REQ_VM_DEAD could
make a bad situation worse.

 arch/arm64/kvm/arm.c     | 2 +-
 arch/x86/kvm/mmu/mmu.c   | 2 +-
 arch/x86/kvm/vmx/tdx.c   | 2 +-
 arch/x86/kvm/x86.c       | 2 +-
 include/linux/kvm_host.h | 9 +++++++--
 5 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 50adfff75be8..a56ead423897 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1108,7 +1108,7 @@ static int kvm_vcpu_suspend(struct kvm_vcpu *vcpu)
 static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 {
 	if (kvm_request_pending(vcpu)) {
-		if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu))
+		if (kvm_test_request(KVM_REQ_VM_DEAD, vcpu))
 			return -EIO;
 
 		if (kvm_check_request(KVM_REQ_SLEEP, vcpu))
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index c519e8e8d646..ec34caa06b6a 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5033,7 +5033,7 @@ static int kvm_tdp_page_prefault(struct kvm_vcpu *vcpu, gpa_t gpa,
 		if (signal_pending(current))
 			return -EINTR;
 
-		if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu))
+		if (kvm_test_request(KVM_REQ_VM_DEAD, vcpu))
 			return -EIO;
 
 		cond_resched();
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index b272c20586a7..6c842e9191a5 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1995,7 +1995,7 @@ static int tdx_handle_ept_violation(struct kvm_vcpu *vcpu)
 		if (kvm_vcpu_has_events(vcpu) || signal_pending(current))
 			break;
 
-		if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) {
+		if (kvm_test_request(KVM_REQ_VM_DEAD, vcpu)) {
 			ret = -EIO;
 			break;
 		}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d94b59140c45..0af4b4a95c2d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8060,7 +8060,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	bool req_immediate_exit = false;
 
 	if (kvm_request_pending(vcpu)) {
-		if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) {
+		if (kvm_test_request(KVM_REQ_VM_DEAD, vcpu)) {
 			r = -EIO;
 			goto out;
 		}
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 03bfc92864b6..cf7fe835c4ad 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2324,13 +2324,18 @@ static inline bool kvm_test_request(int req, struct kvm_vcpu *vcpu)
 	return test_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests);
 }
 
-static inline void kvm_clear_request(int req, struct kvm_vcpu *vcpu)
+static __always_inline void kvm_clear_request(int req, struct kvm_vcpu *vcpu)
 {
+	BUILD_BUG_ON(req == KVM_REQ_VM_DEAD);
+
 	clear_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests);
 }
 
-static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
 {
+	/* Once a VM is dead, it needs to stay dead. */
+	BUILD_BUG_ON(req == KVM_REQ_VM_DEAD);
+
 	if (kvm_test_request(req, vcpu)) {
 		kvm_clear_request(req, vcpu);
 

base-commit: a806d364ef288a6443a1337820ea8410a7ccc6b3
-- 
2.55.0.679.g6767b8d81c-goog