KVM: MMU: Track page fault data in struct vcpu

This patch introduces a struct with two new fields in
vcpu_arch for x86:

	* fault.address
	* fault.error_code

This will be used to correctly propagate page faults back
into the guest when we could have either an ordinary page
fault or a nested page fault. In the case of a nested page
fault the fault-address is different from the original
address that should be walked. So we need to keep track
about the real fault-address.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

arch/x86/include/asm/kvm_emulate.h

@@ -229,7 +229,6 @@ struct x86_emulate_ctxt {
 	int exception; /* exception that happens during emulation or -1 */
 	u32 error_code; /* error code for exception */
 	bool error_code_valid;
-	unsigned long cr2; /* faulted address in case of #PF */
 
 	/* decode cache */
 	struct decode_cache decode;

arch/x86/include/asm/kvm_host.h

@@ -239,9 +239,7 @@ struct kvm_mmu {
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
 	unsigned long (*get_cr3)(struct kvm_vcpu *vcpu);
 	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
-	void (*inject_page_fault)(struct kvm_vcpu *vcpu,
-				  unsigned long addr,
-				  u32 error_code);
+	void (*inject_page_fault)(struct kvm_vcpu *vcpu);
 	void (*free)(struct kvm_vcpu *vcpu);
 	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
 			    u32 *error);
@@ -288,6 +286,16 @@ struct kvm_vcpu_arch {
 	bool tpr_access_reporting;
 
 	struct kvm_mmu mmu;
+
+	/*
+	 * This struct is filled with the necessary information to propagate a
+	 * page fault into the guest
+	 */
+	struct {
+		u64      address;
+		unsigned error_code;
+	} fault;
+
 	/* only needed in kvm_pv_mmu_op() path, but it's hot so
 	 * put it here to avoid allocation */
 	struct kvm_pv_mmu_op_buffer mmu_op_buffer;
@@ -624,8 +632,7 @@ void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
-void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
-			   u32 error_code);
+void kvm_inject_page_fault(struct kvm_vcpu *vcpu);
 bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
 
 int kvm_pic_set_irq(void *opaque, int irq, int level);

arch/x86/kvm/emulate.c

@@ -487,11 +487,9 @@ static void emulate_gp(struct x86_emulate_ctxt *ctxt, int err)
 	emulate_exception(ctxt, GP_VECTOR, err, true);
 }
 
-static void emulate_pf(struct x86_emulate_ctxt *ctxt, unsigned long addr,
-		       int err)
+static void emulate_pf(struct x86_emulate_ctxt *ctxt)
 {
-	ctxt->cr2 = addr;
-	emulate_exception(ctxt, PF_VECTOR, err, true);
+	emulate_exception(ctxt, PF_VECTOR, 0, true);
 }
 
 static void emulate_ud(struct x86_emulate_ctxt *ctxt)
@@ -834,7 +832,7 @@ static int read_emulated(struct x86_emulate_ctxt *ctxt,
 		rc = ops->read_emulated(addr, mc->data + mc->end, n, &err,
 					ctxt->vcpu);
 		if (rc == X86EMUL_PROPAGATE_FAULT)
-			emulate_pf(ctxt, addr, err);
+			emulate_pf(ctxt);
 		if (rc != X86EMUL_CONTINUE)
 			return rc;
 		mc->end += n;
@@ -921,7 +919,7 @@ static int read_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 	addr = dt.address + index * 8;
 	ret = ops->read_std(addr, desc, sizeof *desc, ctxt->vcpu,  &err);
 	if (ret == X86EMUL_PROPAGATE_FAULT)
-		emulate_pf(ctxt, addr, err);
+		emulate_pf(ctxt);
 
        return ret;
 }
@@ -947,7 +945,7 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 	addr = dt.address + index * 8;
 	ret = ops->write_std(addr, desc, sizeof *desc, ctxt->vcpu, &err);
 	if (ret == X86EMUL_PROPAGATE_FAULT)
-		emulate_pf(ctxt, addr, err);
+		emulate_pf(ctxt);
 
 	return ret;
 }
@@ -1117,7 +1115,7 @@ static inline int writeback(struct x86_emulate_ctxt *ctxt,
 					&err,
 					ctxt->vcpu);
 		if (rc == X86EMUL_PROPAGATE_FAULT)
-			emulate_pf(ctxt, c->dst.addr.mem, err);
+			emulate_pf(ctxt);
 		if (rc != X86EMUL_CONTINUE)
 			return rc;
 		break;
@@ -1939,7 +1937,7 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt,
 			    &err);
 	if (ret == X86EMUL_PROPAGATE_FAULT) {
 		/* FIXME: need to provide precise fault address */
-		emulate_pf(ctxt, old_tss_base, err);
+		emulate_pf(ctxt);
 		return ret;
 	}
 
@@ -1949,7 +1947,7 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt,
 			     &err);
 	if (ret == X86EMUL_PROPAGATE_FAULT) {
 		/* FIXME: need to provide precise fault address */
-		emulate_pf(ctxt, old_tss_base, err);
+		emulate_pf(ctxt);
 		return ret;
 	}
 
@@ -1957,7 +1955,7 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt,
 			    &err);
 	if (ret == X86EMUL_PROPAGATE_FAULT) {
 		/* FIXME: need to provide precise fault address */
-		emulate_pf(ctxt, new_tss_base, err);
+		emulate_pf(ctxt);
 		return ret;
 	}
 
@@ -1970,7 +1968,7 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt,
 				     ctxt->vcpu, &err);
 		if (ret == X86EMUL_PROPAGATE_FAULT) {
 			/* FIXME: need to provide precise fault address */
-			emulate_pf(ctxt, new_tss_base, err);
+			emulate_pf(ctxt);
 			return ret;
 		}
 	}
@@ -2081,7 +2079,7 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt,
 			    &err);
 	if (ret == X86EMUL_PROPAGATE_FAULT) {
 		/* FIXME: need to provide precise fault address */
-		emulate_pf(ctxt, old_tss_base, err);
+		emulate_pf(ctxt);
 		return ret;
 	}
 
@@ -2091,7 +2089,7 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt,
 			     &err);
 	if (ret == X86EMUL_PROPAGATE_FAULT) {
 		/* FIXME: need to provide precise fault address */
-		emulate_pf(ctxt, old_tss_base, err);
+		emulate_pf(ctxt);
 		return ret;
 	}
 
@@ -2099,7 +2097,7 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt,
 			    &err);
 	if (ret == X86EMUL_PROPAGATE_FAULT) {
 		/* FIXME: need to provide precise fault address */
-		emulate_pf(ctxt, new_tss_base, err);
+		emulate_pf(ctxt);
 		return ret;
 	}
 
@@ -2112,7 +2110,7 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt,
 				     ctxt->vcpu, &err);
 		if (ret == X86EMUL_PROPAGATE_FAULT) {
 			/* FIXME: need to provide precise fault address */
-			emulate_pf(ctxt, new_tss_base, err);
+			emulate_pf(ctxt);
 			return ret;
 		}
 	}

arch/x86/kvm/mmu.c

@@ -2566,11 +2566,9 @@ static unsigned long get_cr3(struct kvm_vcpu *vcpu)
 	return vcpu->arch.cr3;
 }
 
-static void inject_page_fault(struct kvm_vcpu *vcpu,
-			      u64 addr,
-			      u32 err_code)
+static void inject_page_fault(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.mmu.inject_page_fault(vcpu, addr, err_code);
+	vcpu->arch.mmu.inject_page_fault(vcpu);
 }
 
 static void paging_free(struct kvm_vcpu *vcpu)

arch/x86/kvm/paging_tmpl.h

@@ -258,6 +258,10 @@ error:
 		walker->error_code |= PFERR_FETCH_MASK;
 	if (rsvd_fault)
 		walker->error_code |= PFERR_RSVD_MASK;
+
+	vcpu->arch.fault.address    = addr;
+	vcpu->arch.fault.error_code = walker->error_code;
+
 	trace_kvm_mmu_walker_error(walker->error_code);
 	return 0;
 }
@@ -521,7 +525,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 	 */
 	if (!r) {
 		pgprintk("%s: guest page fault\n", __func__);
-		inject_page_fault(vcpu, addr, walker.error_code);
+		inject_page_fault(vcpu);
 		vcpu->arch.last_pt_write_count = 0; /* reset fork detector */
 		return 0;
 	}

arch/x86/kvm/x86.c

@@ -329,11 +329,12 @@ void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
 }
 EXPORT_SYMBOL_GPL(kvm_requeue_exception);
 
-void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr,
-			   u32 error_code)
+void kvm_inject_page_fault(struct kvm_vcpu *vcpu)
 {
+	unsigned error_code = vcpu->arch.fault.error_code;
+
 	++vcpu->stat.pf_guest;
-	vcpu->arch.cr2 = addr;
+	vcpu->arch.cr2 = vcpu->arch.fault.address;
 	kvm_queue_exception_e(vcpu, PF_VECTOR, error_code);
 }
 
@@ -4080,7 +4081,7 @@ static void inject_emulated_exception(struct kvm_vcpu *vcpu)
 {
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
 	if (ctxt->exception == PF_VECTOR)
-		kvm_inject_page_fault(vcpu, ctxt->cr2, ctxt->error_code);
+		kvm_inject_page_fault(vcpu);
 	else if (ctxt->error_code_valid)
 		kvm_queue_exception_e(vcpu, ctxt->exception, ctxt->error_code);
 	else