KVM: x86 emulator: restart string instruction without going back to a guest.

Currently when string instruction is only partially complete we go back
to a guest mode, guest tries to reexecute instruction and exits again
and at this point emulation continues. Avoid all of this by restarting
instruction without going back to a guest mode, but return to a guest
mode each 1024 iterations to allow interrupt injection. Pending
exception causes immediate guest entry too.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

arch/x86/include/asm/kvm_emulate.h

@@ -193,6 +193,7 @@ struct x86_emulate_ctxt {
 	/* interruptibility state, as a result of execution of STI or MOV SS */
 	int interruptibility;
 
+	bool restart; /* restart string instruction after writeback */
 	/* decode cache */
 	struct decode_cache decode;
 };

arch/x86/kvm/emulate.c

@@ -927,8 +927,11 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	int mode = ctxt->mode;
 	int def_op_bytes, def_ad_bytes, group;
 
-	/* Shadow copy of register state. Committed on successful emulation. */
 
+	/* we cannot decode insn before we complete previous rep insn */
+	WARN_ON(ctxt->restart);
+
+	/* Shadow copy of register state. Committed on successful emulation. */
 	memset(c, 0, sizeof(struct decode_cache));
 	c->eip = ctxt->eip;
 	ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS);
@@ -2426,6 +2429,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	u64 msr_data;
 	struct decode_cache *c = &ctxt->decode;
 	int rc = X86EMUL_CONTINUE;
+	int saved_dst_type = c->dst.type;
 
 	ctxt->interruptibility = 0;
 
@@ -2454,8 +2458,11 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	}
 
 	if (c->rep_prefix && (c->d & String)) {
+		ctxt->restart = true;
 		/* All REP prefixes have the same first termination condition */
 		if (address_mask(c, c->regs[VCPU_REGS_RCX]) == 0) {
+		string_done:
+			ctxt->restart = false;
 			kvm_rip_write(ctxt->vcpu, c->eip);
 			goto done;
 		}
@@ -2467,17 +2474,13 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		 * 	- if REPNE/REPNZ and ZF = 1 then done
 		 */
 		if ((c->b == 0xa6) || (c->b == 0xa7) ||
-				(c->b == 0xae) || (c->b == 0xaf)) {
+		    (c->b == 0xae) || (c->b == 0xaf)) {
 			if ((c->rep_prefix == REPE_PREFIX) &&
-				((ctxt->eflags & EFLG_ZF) == 0)) {
-					kvm_rip_write(ctxt->vcpu, c->eip);
-					goto done;
-			}
+			    ((ctxt->eflags & EFLG_ZF) == 0))
+				goto string_done;
 			if ((c->rep_prefix == REPNE_PREFIX) &&
-				((ctxt->eflags & EFLG_ZF) == EFLG_ZF)) {
-				kvm_rip_write(ctxt->vcpu, c->eip);
-				goto done;
-			}
+			    ((ctxt->eflags & EFLG_ZF) == EFLG_ZF))
+				goto string_done;
 		}
 		c->eip = ctxt->eip;
 	}
@@ -2911,6 +2914,12 @@ writeback:
 	if (rc != X86EMUL_CONTINUE)
 		goto done;
 
+	/*
+	 * restore dst type in case the decoding will be reused
+	 * (happens for string instruction )
+	 */
+	c->dst.type = saved_dst_type;
+
 	if ((c->d & SrcMask) == SrcSI)
 		string_addr_inc(ctxt, seg_override_base(ctxt, c), VCPU_REGS_RSI,
 				&c->src);
@@ -2918,8 +2927,11 @@ writeback:
 	if ((c->d & DstMask) == DstDI)
 		string_addr_inc(ctxt, es_base(ctxt), VCPU_REGS_RDI, &c->dst);
 
-	if (c->rep_prefix && (c->d & String))
+	if (c->rep_prefix && (c->d & String)) {
 		register_address_increment(c, &c->regs[VCPU_REGS_RCX], -1);
+		if (!(c->regs[VCPU_REGS_RCX] & 0x3ff))
+			ctxt->restart = false;
+	}
 
 	/* Commit shadow register state. */
 	memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs);

arch/x86/kvm/x86.c

@@ -3755,6 +3755,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 		return EMULATE_DONE;
 	}
 
+restart:
 	r = x86_emulate_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);
 	shadow_mask = vcpu->arch.emulate_ctxt.interruptibility;
 
@@ -3777,7 +3778,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 
 	if (r) {
 		if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
-			return EMULATE_DONE;
+			goto done;
 		if (!vcpu->mmio_needed) {
 			kvm_report_emulation_failure(vcpu, "mmio");
 			return EMULATE_FAIL;
@@ -3792,6 +3793,13 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 		return EMULATE_DO_MMIO;
 	}
 
+done:
+	if (vcpu->arch.exception.pending)
+		vcpu->arch.emulate_ctxt.restart = false;
+
+	if (vcpu->arch.emulate_ctxt.restart)
+		goto restart;
+
 	return EMULATE_DONE;
 }
 EXPORT_SYMBOL_GPL(emulate_instruction);
@@ -4560,6 +4568,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 			goto out;
 		}
 	}
+	if (vcpu->arch.emulate_ctxt.restart) {
+		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+		r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE);
+		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+		if (r == EMULATE_DO_MMIO) {
+			r = 0;
+			goto out;
+		}
+	}
 	if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL)
 		kvm_register_write(vcpu, VCPU_REGS_RAX,
 				     kvm_run->hypercall.ret);