KVM: SVM: Don't skip unrelated instruction if INT3/INTO is replaced

When re-injecting a soft interrupt from an INT3, INT0, or (select) INTn
instruction, discard the exception and retry the instruction if the code
stream is changed (e.g. by a different vCPU) between when the CPU
executes the instruction and when KVM decodes the instruction to get the
next RIP.

As effectively predicted by commit 6ef88d6e36c2 ("KVM: SVM: Re-inject
INT3/INTO instead of retrying the instruction"), failure to verify that
the correct INTn instruction was decoded can effectively clobber guest
state due to decoding the wrong instruction and thus specifying the
wrong next RIP.

The bug most often manifests as "Oops: int3" panics on static branch
checks in Linux guests.  Enabling or disabling a static branch in Linux
uses the kernel's "text poke" code patching mechanism.  To modify code
while other CPUs may be executing that code, Linux (temporarily)
replaces the first byte of the original instruction with an int3 (opcode
0xcc), then patches in the new code stream except for the first byte,
and finally replaces the int3 with the first byte of the new code
stream.  If a CPU hits the int3, i.e. executes the code while it's being
modified, then the guest kernel must look up the RIP to determine how to
handle the #BP, e.g. by emulating the new instruction.  If the RIP is
incorrect, then this lookup fails and the guest kernel panics.

The bug reproduces almost instantly by hacking the guest kernel to
repeatedly check a static branch[1] while running a drgn script[2] on
the host to constantly swap out the memory containing the guest's TSS.

[1]: https://gist.github.com/osandov/44d17c51c28c0ac998ea0334edf90b5a
[2]: https://gist.github.com/osandov/10e45e45afa29b11e0c7209247afc00b

Fixes: 6ef88d6e36c2 ("KVM: SVM: Re-inject INT3/INTO instead of retrying the instruction")
Cc: stable@vger.kernel.org
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Link: https://patch.msgid.link/1cc6dcdf36e3add7ee7c8d90ad58414eeb6c3d34.1762278762.git.osandov@fb.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

1 files changed, 13 insertions, 11 deletions

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 1ae7b3c5a7c5..459db8154929 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -272,6 +272,7 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
 }
 
 static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu,
+					   int emul_type,
 					   bool commit_side_effects)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -293,7 +294,7 @@ static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu,
 		if (unlikely(!commit_side_effects))
 			old_rflags = svm->vmcb->save.rflags;
 
-		if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP))
+		if (!kvm_emulate_instruction(vcpu, emul_type))
 			return 0;
 
 		if (unlikely(!commit_side_effects))
@@ -311,11 +312,13 @@ done:
 
 static int svm_skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
-	return __svm_skip_emulated_instruction(vcpu, true);
+	return __svm_skip_emulated_instruction(vcpu, EMULTYPE_SKIP, true);
 }
 
-static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu)
+static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu, u8 vector)
 {
+	const int emul_type = EMULTYPE_SKIP | EMULTYPE_SKIP_SOFT_INT |
+			      EMULTYPE_SET_SOFT_INT_VECTOR(vector);
 	unsigned long rip, old_rip = kvm_rip_read(vcpu);
 	struct vcpu_svm *svm = to_svm(vcpu);
 
@@ -331,7 +334,7 @@ static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu)
 	 * in use, the skip must not commit any side effects such as clearing
 	 * the interrupt shadow or RFLAGS.RF.
 	 */
-	if (!__svm_skip_emulated_instruction(vcpu, !nrips))
+	if (!__svm_skip_emulated_instruction(vcpu, emul_type, !nrips))
 		return -EIO;
 
 	rip = kvm_rip_read(vcpu);
@@ -367,7 +370,7 @@ static void svm_inject_exception(struct kvm_vcpu *vcpu)
 	kvm_deliver_exception_payload(vcpu, ex);
 
 	if (kvm_exception_is_soft(ex->vector) &&
-	    svm_update_soft_interrupt_rip(vcpu))
+	    svm_update_soft_interrupt_rip(vcpu, ex->vector))
 		return;
 
 	svm->vmcb->control.event_inj = ex->vector
@@ -3642,11 +3645,12 @@ static bool svm_set_vnmi_pending(struct kvm_vcpu *vcpu)
 
 static void svm_inject_irq(struct kvm_vcpu *vcpu, bool reinjected)
 {
+	struct kvm_queued_interrupt *intr = &vcpu->arch.interrupt;
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u32 type;
 
-	if (vcpu->arch.interrupt.soft) {
-		if (svm_update_soft_interrupt_rip(vcpu))
+	if (intr->soft) {
+		if (svm_update_soft_interrupt_rip(vcpu, intr->nr))
 			return;
 
 		type = SVM_EVTINJ_TYPE_SOFT;
@@ -3654,12 +3658,10 @@ static void svm_inject_irq(struct kvm_vcpu *vcpu, bool reinjected)
 		type = SVM_EVTINJ_TYPE_INTR;
 	}
 
-	trace_kvm_inj_virq(vcpu->arch.interrupt.nr,
-			   vcpu->arch.interrupt.soft, reinjected);
+	trace_kvm_inj_virq(intr->nr, intr->soft, reinjected);
 	++vcpu->stat.irq_injections;
 
-	svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr |
-				       SVM_EVTINJ_VALID | type;
+	svm->vmcb->control.event_inj = intr->nr | SVM_EVTINJ_VALID | type;
 }
 
 void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode,