KVM: Inject asynchronous page fault into a PV guest if page is swapped out.

Send async page fault to a PV guest if it accesses swapped out memory.
Guest will choose another task to run upon receiving the fault.

Allow async page fault injection only when guest is in user mode since
otherwise guest may be in non-sleepable context and will not be able
to reschedule.

Vcpu will be halted if guest will fault on the same page again or if
vcpu executes kernel code.

Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

3 files changed, 42 insertions, 5 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 0d7039804b4..167375cc49f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -421,6 +421,7 @@ struct kvm_vcpu_arch {
 		gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)];
 		struct gfn_to_hva_cache data;
 		u64 msr_val;
+		u32 id;
 	} apf;
 };
 
@@ -596,6 +597,7 @@ struct kvm_x86_ops {
 };
 
 struct kvm_arch_async_pf {
+	u32 token;
 	gfn_t gfn;
 };
 
@@ -819,6 +821,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 				 struct kvm_async_pf *work);
 void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
 			       struct kvm_async_pf *work);
+bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu);
 extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index b2c60986a7c..64f90db369f 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2592,6 +2592,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
 int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 {
 	struct kvm_arch_async_pf arch;
+	arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
 	arch.gfn = gfn;
 
 	return kvm_setup_async_pf(vcpu, gva, gfn, &arch);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 063c0729676..ac4c368afd4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6248,20 +6248,53 @@ static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
 	}
 }
 
+static int apf_put_user(struct kvm_vcpu *vcpu, u32 val)
+{
+
+	return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &val,
+				      sizeof(val));
+}
+
 void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 				     struct kvm_async_pf *work)
 {
-	trace_kvm_async_pf_not_present(work->gva);
-
-	kvm_make_request(KVM_REQ_APF_HALT, vcpu);
+	trace_kvm_async_pf_not_present(work->arch.token, work->gva);
 	kvm_add_async_pf_gfn(vcpu, work->arch.gfn);
+
+	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) ||
+	    kvm_x86_ops->get_cpl(vcpu) == 0)
+		kvm_make_request(KVM_REQ_APF_HALT, vcpu);
+	else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_NOT_PRESENT)) {
+		vcpu->arch.fault.error_code = 0;
+		vcpu->arch.fault.address = work->arch.token;
+		kvm_inject_page_fault(vcpu);
+	}
 }
 
 void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 				 struct kvm_async_pf *work)
 {
-	trace_kvm_async_pf_ready(work->gva);
-	kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
+	trace_kvm_async_pf_ready(work->arch.token, work->gva);
+	if (is_error_page(work->page))
+		work->arch.token = ~0; /* broadcast wakeup */
+	else
+		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
+
+	if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) &&
+	    !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
+		vcpu->arch.fault.error_code = 0;
+		vcpu->arch.fault.address = work->arch.token;
+		kvm_inject_page_fault(vcpu);
+	}
+}
+
+bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
+{
+	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED))
+		return true;
+	else
+		return !kvm_event_needs_reinjection(vcpu) &&
+			kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);