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>

arch/x86/include/asm/kvm_emulate.h

@@ -364,6 +364,7 @@ enum x86_intercept {
 #endif
 
 int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len);
+bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt);
 #define EMULATION_FAILED -1
 #define EMULATION_OK 0
 #define EMULATION_RESTART 1

arch/x86/include/asm/kvm_host.h

@@ -444,6 +444,9 @@ struct kvm_vcpu_arch {
 
 	cpumask_var_t wbinvd_dirty_mask;
 
+	unsigned long last_retry_eip;
+	unsigned long last_retry_addr;
+
 	struct {
 		bool halted;
 		gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)];
@@ -692,6 +695,7 @@ enum emulation_result {
 #define EMULTYPE_NO_DECODE	    (1 << 0)
 #define EMULTYPE_TRAP_UD	    (1 << 1)
 #define EMULTYPE_SKIP		    (1 << 2)
+#define EMULTYPE_RETRY		    (1 << 3)
 int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
 			    int emulation_type, void *insn, int insn_len);
 
@@ -756,6 +760,7 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu);
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		       const u8 *new, int bytes,
 		       bool guest_initiated);
+int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
 int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
 void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);

arch/x86/kvm/emulate.c

@@ -3702,6 +3702,11 @@ done:
 	return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK;
 }
 
+bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt)
+{
+	return ctxt->d & PageTable;
+}
+
 static bool string_insn_completed(struct x86_emulate_ctxt *ctxt)
 {
 	/* The second termination condition only applies for REPE

arch/x86/kvm/mmu.c

@@ -1998,7 +1998,7 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
 	kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages;
 }
 
-static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
+int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_mmu_page *sp;
 	struct hlist_node *node;
@@ -2007,7 +2007,7 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 
 	pgprintk("%s: looking for gfn %llx\n", __func__, gfn);
 	r = 0;
-
+	spin_lock(&kvm->mmu_lock);
 	for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) {
 		pgprintk("%s: gfn %llx role %x\n", __func__, gfn,
 			 sp->role.word);
@@ -2015,8 +2015,11 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 		kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
 	}
 	kvm_mmu_commit_zap_page(kvm, &invalid_list);
+	spin_unlock(&kvm->mmu_lock);
+
 	return r;
 }
+EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);
 
 static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
 {
@@ -3698,9 +3701,8 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
 
 	gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
 
-	spin_lock(&vcpu->kvm->mmu_lock);
 	r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
-	spin_unlock(&vcpu->kvm->mmu_lock);
+
 	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt);
@@ -3721,10 +3723,18 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
 	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
 }
 
+static bool is_mmio_page_fault(struct kvm_vcpu *vcpu, gva_t addr)
+{
+	if (vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu))
+		return vcpu_match_mmio_gpa(vcpu, addr);
+
+	return vcpu_match_mmio_gva(vcpu, addr);
+}
+
 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
 		       void *insn, int insn_len)
 {
-	int r;
+	int r, emulation_type = EMULTYPE_RETRY;
 	enum emulation_result er;
 
 	r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false);
@@ -3736,7 +3746,10 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
 		goto out;
 	}
 
-	er = x86_emulate_instruction(vcpu, cr2, 0, insn, insn_len);
+	if (is_mmio_page_fault(vcpu, cr2))
+		emulation_type = 0;
+
+	er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
 
 	switch (er) {
 	case EMULATE_DONE:

arch/x86/kvm/x86.c

@@ -4836,6 +4836,50 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
 	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 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		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) {