KVM: SVM: copy instruction bytes from VMCB

In case of a nested page fault or an intercepted #PF newer SVM
implementations provide a copy of the faulting instruction bytes
in the VMCB.
Use these bytes to feed the instruction emulator and avoid the costly
guest instruction fetch in this case.

Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

8 files changed, 26 insertions, 15 deletions

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index bf70ece..8e37deb 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -265,7 +265,7 @@ struct x86_emulate_ctxt {
 #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64
 #endif
 
-int x86_decode_insn(struct x86_emulate_ctxt *ctxt);
+int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len);
 #define EMULATION_FAILED -1
 #define EMULATION_OK 0
 #define EMULATION_RESTART 1
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index de00b60..6268f6c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -634,13 +634,13 @@ enum emulation_result {
 #define EMULTYPE_NO_DECODE	    (1 << 0)
 #define EMULTYPE_TRAP_UD	    (1 << 1)
 #define EMULTYPE_SKIP		    (1 << 2)
-int x86_emulate_instruction(struct kvm_vcpu *vcpu,
-			unsigned long cr2, int emulation_type);
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
+			    int emulation_type, void *insn, int insn_len);
 
 static inline int emulate_instruction(struct kvm_vcpu *vcpu,
 			int emulation_type)
 {
-	return x86_emulate_instruction(vcpu, 0, emulation_type);
+	return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0);
 }
 
 void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
@@ -721,7 +721,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
 int kvm_fix_hypercall(struct kvm_vcpu *vcpu);
 
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code);
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code,
+		       void *insn, int insn_len);
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
 
 void kvm_enable_tdp(void);
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index f0ffb81..f2b83bc 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -83,7 +83,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 	u32 clean;
 	u32 reserved_5;
 	u64 next_rip;
-	u8 reserved_6[816];
+	u8 insn_len;
+	u8 insn_bytes[15];
+	u8 reserved_6[800];
 };
 
 
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 36534ec..caf9667 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2610,7 +2610,7 @@ done:
 }
 
 int
-x86_decode_insn(struct x86_emulate_ctxt *ctxt)
+x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 {
 	struct x86_emulate_ops *ops = ctxt->ops;
 	struct decode_cache *c = &ctxt->decode;
@@ -2621,7 +2621,10 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt)
 	struct operand memop = { .type = OP_NONE };
 
 	c->eip = ctxt->eip;
-	c->fetch.start = c->fetch.end = c->eip;
+	c->fetch.start = c->eip;
+	c->fetch.end = c->fetch.start + insn_len;
+	if (insn_len > 0)
+		memcpy(c->fetch.data, insn, insn_len);
 	ctxt->cs_base = seg_base(ctxt, ops, VCPU_SREG_CS);
 
 	switch (mode) {
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 01c5a10..ea6063d 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3330,7 +3330,8 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
 	}
 }
 
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code)
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
+		       void *insn, int insn_len)
 {
 	int r;
 	enum emulation_result er;
@@ -3348,7 +3349,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code)
 	if (r)
 		goto out;
 
-	er = x86_emulate_instruction(vcpu, cr2, 0);
+	er = x86_emulate_instruction(vcpu, cr2, 0, insn, insn_len);
 
 	switch (er) {
 	case EMULATE_DONE:
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index a04c01e..af4b911 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1527,7 +1527,9 @@ static int pf_interception(struct vcpu_svm *svm)
 		trace_kvm_page_fault(fault_address, error_code);
 		if (!npt_enabled && kvm_event_needs_reinjection(&svm->vcpu))
 			kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address);
-		r = kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code);
+		r = kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code,
+			svm->vmcb->control.insn_bytes,
+			svm->vmcb->control.insn_len);
 		break;
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
 		svm->apf_reason = 0;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f3c60fb..736f839 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3055,7 +3055,7 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 
 		if (kvm_event_needs_reinjection(vcpu))
 			kvm_mmu_unprotect_page_virt(vcpu, cr2);
-		return kvm_mmu_page_fault(vcpu, cr2, error_code);
+		return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0);
 	}
 
 	if (vmx->rmode.vm86_active &&
@@ -3502,7 +3502,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
 	trace_kvm_page_fault(gpa, exit_qualification);
-	return kvm_mmu_page_fault(vcpu, gpa, exit_qualification & 0x3);
+	return kvm_mmu_page_fault(vcpu, gpa, exit_qualification & 0x3, NULL, 0);
 }
 
 static u64 ept_rsvd_mask(u64 spte, int level)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a6fcb76..7ad9cda 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4365,7 +4365,9 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
 
 int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 			    unsigned long cr2,
-			    int emulation_type)
+			    int emulation_type,
+			    void *insn,
+			    int insn_len)
 {
 	int r;
 	struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode;
@@ -4386,7 +4388,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		vcpu->arch.emulate_ctxt.have_exception = false;
 		vcpu->arch.emulate_ctxt.perm_ok = false;
 
-		r = x86_decode_insn(&vcpu->arch.emulate_ctxt);
+		r = x86_decode_insn(&vcpu->arch.emulate_ctxt, insn, insn_len);
 		if (r == X86EMUL_PROPAGATE_FAULT)
 			goto done;