From: Brijesh Singh <brijesh.singh@amd.com>
Date: Mon, 4 Dec 2017 16:57:40 +0000 (-0600)
Subject: KVM: X86: Restart the guest when insn_len is zero and SEV is enabled
X-Git-Tag: v4.15.11~50
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=eff91358798966bc88657ad9ddada93794f8c843;p=thirdparty%2Fkernel%2Fstable.git

KVM: X86: Restart the guest when insn_len is zero and SEV is enabled


[ Upstream commit 00b10fe1046c4b2232097a7ffaa9238c7e479388 ]

On AMD platforms, under certain conditions insn_len may be zero on #NPF.
This can happen if a guest gets a page-fault on data access but the HW
table walker is not able to read the instruction page (e.g instruction
page is not present in memory).

Typically, when insn_len is zero, x86_emulate_instruction() walks the
guest page table and fetches the instruction bytes from guest memory.
When SEV is enabled, the guest memory is encrypted with guest-specific
key hence hypervisor will not able to fetch the instruction bytes.
In those cases we simply restart the guest.

I have encountered this issue when running kernbench inside the guest.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Borislav Petkov <bp@suse.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: x86@kernel.org
Cc: kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e080dbe55360a..fe2cb4cfa75be 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4951,6 +4951,16 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 	if (mmio_info_in_cache(vcpu, cr2, direct))
 		emulation_type = 0;
 emulate:
+	/*
+	 * On AMD platforms, under certain conditions insn_len may be zero on #NPF.
+	 * This can happen if a guest gets a page-fault on data access but the HW
+	 * table walker is not able to read the instruction page (e.g instruction
+	 * page is not present in memory). In those cases we simply restart the
+	 * guest.
+	 */
+	if (unlikely(insn && !insn_len))
+		return 1;
+
 	er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
 
 	switch (er) {
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 3505afabce5d8..76bbca2c8159a 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2178,7 +2178,8 @@ static int pf_interception(struct vcpu_svm *svm)
 	u64 error_code = svm->vmcb->control.exit_info_1;
 
 	return kvm_handle_page_fault(&svm->vcpu, error_code, fault_address,
-			svm->vmcb->control.insn_bytes,
+			static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
+			svm->vmcb->control.insn_bytes : NULL,
 			svm->vmcb->control.insn_len);
 }
 
@@ -2189,7 +2190,8 @@ static int npf_interception(struct vcpu_svm *svm)
 
 	trace_kvm_page_fault(fault_address, error_code);
 	return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code,
-			svm->vmcb->control.insn_bytes,
+			static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
+			svm->vmcb->control.insn_bytes : NULL,
 			svm->vmcb->control.insn_len);
 }