KVM: x86: retry non-page-table writing instructions

If the emulation is caused by #PF and it is non-page_table writing instruction,
it means the VM-EXIT is caused by shadow page protected, we can zap the shadow
page and retry this instruction directly

The idea is from Avi

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e24edbc..7ba1ab7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4836,6 +4836,50 @@
 	return false;
 }
 
+static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
+			      unsigned long cr2,  int emulation_type)
+{
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+	unsigned long last_retry_eip, last_retry_addr, gpa = cr2;
+
+	last_retry_eip = vcpu->arch.last_retry_eip;
+	last_retry_addr = vcpu->arch.last_retry_addr;
+
+	/*
+	 * If the emulation is caused by #PF and it is non-page_table
+	 * writing instruction, it means the VM-EXIT is caused by shadow
+	 * page protected, we can zap the shadow page and retry this
+	 * instruction directly.
+	 *
+	 * Note: if the guest uses a non-page-table modifying instruction
+	 * on the PDE that points to the instruction, then we will unmap
+	 * the instruction and go to an infinite loop. So, we cache the
+	 * last retried eip and the last fault address, if we meet the eip
+	 * and the address again, we can break out of the potential infinite
+	 * loop.
+	 */
+	vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0;
+
+	if (!(emulation_type & EMULTYPE_RETRY))
+		return false;
+
+	if (x86_page_table_writing_insn(ctxt))
+		return false;
+
+	if (ctxt->eip == last_retry_eip && last_retry_addr == cr2)
+		return false;
+
+	vcpu->arch.last_retry_eip = ctxt->eip;
+	vcpu->arch.last_retry_addr = cr2;
+
+	if (!vcpu->arch.mmu.direct_map)
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
+
+	kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
+
+	return true;
+}
+
 int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 			    unsigned long cr2,
 			    int emulation_type,
@@ -4877,6 +4921,9 @@
 		return EMULATE_DONE;
 	}
 
+	if (retry_instruction(ctxt, cr2, emulation_type))
+		return EMULATE_DONE;
+
 	/* this is needed for vmware backdoor interface to work since it
 	   changes registers values  during IO operation */
 	if (vcpu->arch.emulate_regs_need_sync_from_vcpu) {