linux-kernel - [PATCH v2 2/4] KVM: SVM: Add emulation support for #GP triggered by SVM instructions

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: <20210121065508.1169585-3-wei.huang2@amd.com>
Date:   Thu, 21 Jan 2021 01:55:06 -0500
From:   Wei Huang <wei.huang2@....com>
To:     kvm@...r.kernel.org
Cc:     linux-kernel@...r.kernel.org, pbonzini@...hat.com,
        vkuznets@...hat.com, mlevitsk@...hat.com, seanjc@...gle.com,
        joro@...tes.org, bp@...en8.de, tglx@...utronix.de,
        mingo@...hat.com, x86@...nel.org, jmattson@...gle.com,
        wanpengli@...cent.com, bsd@...hat.com, dgilbert@...hat.com,
        luto@...capital.net, wei.huang2@....com
Subject: [PATCH v2 2/4] KVM: SVM: Add emulation support for #GP triggered by SVM instructions

From: Bandan Das <bsd@...hat.com>

While running SVM related instructions (VMRUN/VMSAVE/VMLOAD), some AMD
CPUs check EAX against reserved memory regions (e.g. SMM memory on host)
before checking VMCB's instruction intercept. If EAX falls into such
memory areas, #GP is triggered before VMEXIT. This causes problem under
nested virtualization. To solve this problem, KVM needs to trap #GP and
check the instructions triggering #GP. For VM execution instructions,
KVM emulates these instructions.

Co-developed-by: Wei Huang <wei.huang2@....com>
Signed-off-by: Wei Huang <wei.huang2@....com>
Signed-off-by: Bandan Das <bsd@...hat.com>
---
 arch/x86/kvm/svm/svm.c | 99 ++++++++++++++++++++++++++++++++++--------
 1 file changed, 81 insertions(+), 18 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 7ef171790d02..6ed523cab068 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -288,6 +288,9 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 		if (!(efer & EFER_SVME)) {
 			svm_leave_nested(svm);
 			svm_set_gif(svm, true);
+			/* #GP intercept is still needed in vmware_backdoor */
+			if (!enable_vmware_backdoor)
+				clr_exception_intercept(svm, GP_VECTOR);
 
 			/*
 			 * Free the nested guest state, unless we are in SMM.
@@ -309,6 +312,9 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 
 	svm->vmcb->save.efer = efer | EFER_SVME;
 	vmcb_mark_dirty(svm->vmcb, VMCB_CR);
+	/* Enable #GP interception for SVM instructions */
+	set_exception_intercept(svm, GP_VECTOR);
+
 	return 0;
 }
 
@@ -1957,24 +1963,6 @@ static int ac_interception(struct vcpu_svm *svm)
 	return 1;
 }
 
-static int gp_interception(struct vcpu_svm *svm)
-{
-	struct kvm_vcpu *vcpu = &svm->vcpu;
-	u32 error_code = svm->vmcb->control.exit_info_1;
-
-	WARN_ON_ONCE(!enable_vmware_backdoor);
-
-	/*
-	 * VMware backdoor emulation on #GP interception only handles IN{S},
-	 * OUT{S}, and RDPMC, none of which generate a non-zero error code.
-	 */
-	if (error_code) {
-		kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
-		return 1;
-	}
-	return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP);
-}
-
 static bool is_erratum_383(void)
 {
 	int err, i;
@@ -2173,6 +2161,81 @@ static int vmrun_interception(struct vcpu_svm *svm)
 	return nested_svm_vmrun(svm);
 }
 
+enum {
+	NOT_SVM_INSTR,
+	SVM_INSTR_VMRUN,
+	SVM_INSTR_VMLOAD,
+	SVM_INSTR_VMSAVE,
+};
+
+/* Return NOT_SVM_INSTR if not SVM instrs, otherwise return decode result */
+static int svm_instr_opcode(struct kvm_vcpu *vcpu)
+{
+	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
+
+	if (ctxt->b != 0x1 || ctxt->opcode_len != 2)
+		return NOT_SVM_INSTR;
+
+	switch (ctxt->modrm) {
+	case 0xd8: /* VMRUN */
+		return SVM_INSTR_VMRUN;
+	case 0xda: /* VMLOAD */
+		return SVM_INSTR_VMLOAD;
+	case 0xdb: /* VMSAVE */
+		return SVM_INSTR_VMSAVE;
+	default:
+		break;
+	}
+
+	return NOT_SVM_INSTR;
+}
+
+static int emulate_svm_instr(struct kvm_vcpu *vcpu, int opcode)
+{
+	int (*const svm_instr_handlers[])(struct vcpu_svm *svm) = {
+		[SVM_INSTR_VMRUN] = vmrun_interception,
+		[SVM_INSTR_VMLOAD] = vmload_interception,
+		[SVM_INSTR_VMSAVE] = vmsave_interception,
+	};
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	return svm_instr_handlers[opcode](svm);
+}
+
+/*
+ * #GP handling code. Note that #GP can be triggered under the following two
+ * cases:
+ *   1) SVM VM-related instructions (VMRUN/VMSAVE/VMLOAD) that trigger #GP on
+ *      some AMD CPUs when EAX of these instructions are in the reserved memory
+ *      regions (e.g. SMM memory on host).
+ *   2) VMware backdoor
+ */
+static int gp_interception(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	u32 error_code = svm->vmcb->control.exit_info_1;
+	int opcode;
+
+	/* Both #GP cases have zero error_code */
+	if (error_code)
+		goto reinject;
+
+	/* Decode the instruction for usage later */
+	if (x86_emulate_decoded_instruction(vcpu, 0, NULL, 0) != EMULATION_OK)
+		goto reinject;
+
+	opcode = svm_instr_opcode(vcpu);
+	if (opcode)
+		return emulate_svm_instr(vcpu, opcode);
+	else
+		return kvm_emulate_instruction(vcpu,
+				EMULTYPE_VMWARE_GP | EMULTYPE_NO_DECODE);
+
+reinject:
+	kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
+	return 1;
+}
+
 void svm_set_gif(struct vcpu_svm *svm, bool value)
 {
 	if (value) {
-- 
2.27.0