linux-kernel - [PATCH v2 06/11] KVM: SVM: Re-inject INTn instead of retrying the insn on "failure"

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: <20220423021411.784383-7-seanjc@google.com>
Date:   Sat, 23 Apr 2022 02:14:06 +0000
From:   Sean Christopherson <seanjc@...gle.com>
To:     Paolo Bonzini <pbonzini@...hat.com>
Cc:     Sean Christopherson <seanjc@...gle.com>,
        Vitaly Kuznetsov <vkuznets@...hat.com>,
        Wanpeng Li <wanpengli@...cent.com>,
        Jim Mattson <jmattson@...gle.com>,
        Joerg Roedel <joro@...tes.org>, kvm@...r.kernel.org,
        linux-kernel@...r.kernel.org, Maxim Levitsky <mlevitsk@...hat.com>,
        "Maciej S . Szmigiero" <maciej.szmigiero@...cle.com>
Subject: [PATCH v2 06/11] KVM: SVM: Re-inject INTn instead of retrying the
 insn on "failure"

Re-inject INTn software interrupts instead of retrying the instruction if
the CPU encountered an intercepted exception while vectoring the INTn,
e.g. if KVM intercepted a #PF when utilizing shadow paging.  Retrying the
instruction is architecturally wrong e.g. will result in a spurious #DB
if there's a code breakpoint on the INT3/O, and lack of re-injection also
breaks nested virtualization, e.g. if L1 injects a software interrupt and
vectoring the injected interrupt encounters an exception that is
intercepted by L0 but not L1.

Signed-off-by: Sean Christopherson <seanjc@...gle.com>
---
 arch/x86/kvm/svm/nested.c |  7 +++----
 arch/x86/kvm/svm/svm.c    | 24 +++++++++++++++++++-----
 2 files changed, 22 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 0163238aa198..a83e367ade54 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -617,10 +617,9 @@ static inline bool is_evtinj_soft(u32 evtinj)
 	if (!(evtinj & SVM_EVTINJ_VALID))
 		return false;
 
-	/*
-	 * Intentionally return false for SOFT events, SVM doesn't yet support
-	 * re-injecting soft interrupts.
-	 */
+	if (type == SVM_EVTINJ_TYPE_SOFT)
+		return true;
+
 	return type == SVM_EVTINJ_TYPE_EXEPT && kvm_exception_is_soft(vector);
 }
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 8321f9ce5e35..b8fb07eeeca5 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3430,14 +3430,23 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu)
 static void svm_inject_irq(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	u32 type;
 
-	WARN_ON(!vcpu->arch.interrupt.soft && !gif_set(svm));
+	if (vcpu->arch.interrupt.soft) {
+		if (svm_update_soft_interrupt_rip(vcpu))
+			return;
+
+		type = SVM_EVTINJ_TYPE_SOFT;
+	} else {
+		WARN_ON(!gif_set(svm));
+		type = SVM_EVTINJ_TYPE_INTR;
+	}
 
 	trace_kvm_inj_virq(vcpu->arch.interrupt.nr);
 	++vcpu->stat.irq_injections;
 
 	svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr |
-		SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR;
+				       SVM_EVTINJ_VALID | type;
 }
 
 void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode,
@@ -3717,6 +3726,8 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu)
 static void svm_complete_soft_interrupt(struct kvm_vcpu *vcpu, u8 vector,
 					int type)
 {
+	bool is_exception = (type == SVM_EXITINTINFO_TYPE_EXEPT);
+	bool is_soft = (type == SVM_EXITINTINFO_TYPE_SOFT);
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	/*
@@ -3728,8 +3739,7 @@ static void svm_complete_soft_interrupt(struct kvm_vcpu *vcpu, u8 vector,
 	 * the same event, i.e. if the event is a soft exception/interrupt,
 	 * otherwise next_rip is unused on VMRUN.
 	 */
-	if (nrips && type == SVM_EXITINTINFO_TYPE_EXEPT &&
-	    kvm_exception_is_soft(vector) &&
+	if (nrips && (is_soft || (is_exception && kvm_exception_is_soft(vector))) &&
 	    kvm_is_linear_rip(vcpu, svm->soft_int_old_rip + svm->soft_int_csbase))
 		svm->vmcb->control.next_rip = svm->soft_int_next_rip;
 	/*
@@ -3740,7 +3750,7 @@ static void svm_complete_soft_interrupt(struct kvm_vcpu *vcpu, u8 vector,
 	 * hit a #NP in the guest, and the #NP encountered a #PF, the #NP will
 	 * be the reported vectored event, but RIP still needs to be unwound.
 	 */
-	else if (!nrips && type == SVM_EXITINTINFO_TYPE_EXEPT &&
+	else if (!nrips && (is_soft || is_exception) &&
 		 kvm_is_linear_rip(vcpu, svm->soft_int_next_rip + svm->soft_int_csbase))
 		kvm_rip_write(vcpu, svm->soft_int_old_rip);
 }
@@ -3802,9 +3812,13 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu)
 	case SVM_EXITINTINFO_TYPE_INTR:
 		kvm_queue_interrupt(vcpu, vector, false);
 		break;
+	case SVM_EXITINTINFO_TYPE_SOFT:
+		kvm_queue_interrupt(vcpu, vector, true);
+		break;
 	default:
 		break;
 	}
+
 }
 
 static void svm_cancel_injection(struct kvm_vcpu *vcpu)
-- 
2.36.0.rc2.479.g8af0fa9b8e-goog