KVM: async_pf: Add L1 guest async_pf #PF vmexit handler

This patch adds the L1 guest async page fault #PF vmexit handler, such
by L1 similar to ordinary async page fault.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
[Passed insn parameters to kvm_mmu_page_fault().]
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -650,6 +650,7 @@ struct kvm_vcpu_arch {
 		u64 msr_val;
 		u32 id;
 		bool send_user_only;
+		u32 host_apf_reason;
 	} apf;
 
 	/* OSVW MSRs (AMD only) */

arch/x86/kvm/mmu.c

@@ -46,6 +46,7 @@
 #include <asm/io.h>
 #include <asm/vmx.h>
 #include <asm/kvm_page_track.h>
+#include "trace.h"
 
 /*
  * When setting this variable to true it enables Two-Dimensional-Paging
@@ -3780,6 +3781,38 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 	return false;
 }
 
+int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
+				u64 fault_address, char *insn, int insn_len,
+				bool need_unprotect)
+{
+	int r = 1;
+
+	switch (vcpu->arch.apf.host_apf_reason) {
+	default:
+		trace_kvm_page_fault(fault_address, error_code);
+
+		if (need_unprotect && kvm_event_needs_reinjection(vcpu))
+			kvm_mmu_unprotect_page_virt(vcpu, fault_address);
+		r = kvm_mmu_page_fault(vcpu, fault_address, error_code, insn,
+				insn_len);
+		break;
+	case KVM_PV_REASON_PAGE_NOT_PRESENT:
+		vcpu->arch.apf.host_apf_reason = 0;
+		local_irq_disable();
+		kvm_async_pf_task_wait(fault_address);
+		local_irq_enable();
+		break;
+	case KVM_PV_REASON_PAGE_READY:
+		vcpu->arch.apf.host_apf_reason = 0;
+		local_irq_disable();
+		kvm_async_pf_task_wake(fault_address);
+		local_irq_enable();
+		break;
+	}
+	return r;
+}
+EXPORT_SYMBOL_GPL(kvm_handle_page_fault);
+
 static bool
 check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level)
 {

arch/x86/kvm/mmu.h

@@ -77,6 +77,9 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 			     bool accessed_dirty);
 bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
+int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
+				u64 fault_address, char *insn, int insn_len,
+				bool need_unprotect);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {

arch/x86/kvm/svm.c

@@ -194,7 +194,6 @@ struct vcpu_svm {
 
 	unsigned int3_injected;
 	unsigned long int3_rip;
-	u32 apf_reason;
 
 	/* cached guest cpuid flags for faster access */
 	bool nrips_enabled	: 1;
@@ -2122,34 +2121,11 @@ static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value)
 static int pf_interception(struct vcpu_svm *svm)
 {
 	u64 fault_address = svm->vmcb->control.exit_info_2;
-	u64 error_code;
+	u64 error_code = svm->vmcb->control.exit_info_1;
-	int r = 1;
 
-	switch (svm->apf_reason) {
+	return kvm_handle_page_fault(&svm->vcpu, error_code, fault_address,
-	default:
-		error_code = svm->vmcb->control.exit_info_1;
-
-		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,
 			svm->vmcb->control.insn_bytes,
-			svm->vmcb->control.insn_len);
+			svm->vmcb->control.insn_len, !npt_enabled);
-		break;
-	case KVM_PV_REASON_PAGE_NOT_PRESENT:
-		svm->apf_reason = 0;
-		local_irq_disable();
-		kvm_async_pf_task_wait(fault_address);
-		local_irq_enable();
-		break;
-	case KVM_PV_REASON_PAGE_READY:
-		svm->apf_reason = 0;
-		local_irq_disable();
-		kvm_async_pf_task_wake(fault_address);
-		local_irq_enable();
-		break;
-	}
-	return r;
 }
 
 static int db_interception(struct vcpu_svm *svm)
@@ -2630,7 +2606,7 @@ static int nested_svm_exit_special(struct vcpu_svm *svm)
 		break;
 	case SVM_EXIT_EXCP_BASE + PF_VECTOR:
 		/* When we're shadowing, trap PFs, but not async PF */
-		if (!npt_enabled && svm->apf_reason == 0)
+		if (!npt_enabled && svm->vcpu.arch.apf.host_apf_reason == 0)
 			return NESTED_EXIT_HOST;
 		break;
 	default:
@@ -2677,7 +2653,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm)
 		}
 		/* async page fault always cause vmexit */
 		else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) &&
-			 svm->apf_reason != 0)
+			 svm->vcpu.arch.apf.host_apf_reason != 0)
 			vmexit = NESTED_EXIT_DONE;
 		break;
 	}
@@ -4998,7 +4974,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 
 	/* if exit due to PF check for async PF */
 	if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR)
-		svm->apf_reason = kvm_read_and_reset_pf_reason();
+		svm->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason();
 
 	if (npt_enabled) {
 		vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR);

arch/x86/kvm/vmx.c

@@ -5698,14 +5698,11 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 	}
 
 	if (is_page_fault(intr_info)) {
-		/* EPT won't cause page fault directly */
-		BUG_ON(enable_ept);
 		cr2 = vmcs_readl(EXIT_QUALIFICATION);
-		trace_kvm_page_fault(cr2, error_code);
+		/* EPT won't cause page fault directly */
-
+		WARN_ON_ONCE(!vcpu->arch.apf.host_apf_reason && enable_ept);
-		if (kvm_event_needs_reinjection(vcpu))
+		return kvm_handle_page_fault(vcpu, error_code, cr2, NULL, 0,
-			kvm_mmu_unprotect_page_virt(vcpu, cr2);
+				true);
-		return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0);
 	}
 
 	ex_no = intr_info & INTR_INFO_VECTOR_MASK;
@@ -8643,6 +8640,10 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
 		exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
 	vmx->exit_intr_info = exit_intr_info;
 
+	/* if exit due to PF check for async PF */
+	if (is_page_fault(exit_intr_info))
+		vmx->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason();
+
 	/* Handle machine checks before interrupts are enabled */
 	if (basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY ||
 	    is_machine_check(exit_intr_info))