KVM: Halt vcpu if page it tries to access is swapped out

If a guest accesses swapped out memory do not swap it in from vcpu thread
context. Schedule work to do swapping and put vcpu into halted state
instead.

Interrupts will still be delivered to the guest and if interrupt will
cause reschedule guest will continue to run another task.

[avi: remove call to get_user_pages_noio(), nacked by Linus; this
      makes everything synchrnous again]

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

2 files changed, 121 insertions, 0 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a0557422715..e56acc7857e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -40,6 +40,7 @@
 #define KVM_REQ_KICK               9
 #define KVM_REQ_DEACTIVATE_FPU    10
 #define KVM_REQ_EVENT             11
+#define KVM_REQ_APF_HALT          12
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID	0
 
@@ -74,6 +75,26 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 			      struct kvm_io_device *dev);
 
+#ifdef CONFIG_KVM_ASYNC_PF
+struct kvm_async_pf {
+	struct work_struct work;
+	struct list_head link;
+	struct list_head queue;
+	struct kvm_vcpu *vcpu;
+	struct mm_struct *mm;
+	gva_t gva;
+	unsigned long addr;
+	struct kvm_arch_async_pf arch;
+	struct page *page;
+	bool done;
+};
+
+void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
+void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
+		       struct kvm_arch_async_pf *arch);
+#endif
+
 struct kvm_vcpu {
 	struct kvm *kvm;
 #ifdef CONFIG_PREEMPT_NOTIFIERS
@@ -104,6 +125,15 @@ struct kvm_vcpu {
 	gpa_t mmio_phys_addr;
 #endif
 
+#ifdef CONFIG_KVM_ASYNC_PF
+	struct {
+		u32 queued;
+		struct list_head queue;
+		struct list_head done;
+		spinlock_t lock;
+	} async_pf;
+#endif
+
 	struct kvm_vcpu_arch arch;
 };
 
@@ -302,6 +332,7 @@ void kvm_set_page_accessed(struct page *page);
 
 pfn_t hva_to_pfn_atomic(struct kvm *kvm, unsigned long addr);
 pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn);
+pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async);
 pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn);
 pfn_t gfn_to_pfn_memslot(struct kvm *kvm,
 			 struct kvm_memory_slot *slot, gfn_t gfn);
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 6dd3a51ab1c..a78a5e57463 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -185,6 +185,96 @@ TRACE_EVENT(kvm_age_page,
 		  __entry->referenced ? "YOUNG" : "OLD")
 );
 
+#ifdef CONFIG_KVM_ASYNC_PF
+TRACE_EVENT(
+	kvm_try_async_get_page,
+	TP_PROTO(bool async, u64 pfn),
+	TP_ARGS(async, pfn),
+
+	TP_STRUCT__entry(
+		__field(__u64, pfn)
+		),
+
+	TP_fast_assign(
+		__entry->pfn = (!async) ? pfn : (u64)-1;
+		),
+
+	TP_printk("pfn %#llx", __entry->pfn)
+);
+
+TRACE_EVENT(
+	kvm_async_pf_not_present,
+	TP_PROTO(u64 gva),
+	TP_ARGS(gva),
+
+	TP_STRUCT__entry(
+		__field(__u64, gva)
+		),
+
+	TP_fast_assign(
+		__entry->gva = gva;
+		),
+
+	TP_printk("gva %#llx not present", __entry->gva)
+);
+
+TRACE_EVENT(
+	kvm_async_pf_ready,
+	TP_PROTO(u64 gva),
+	TP_ARGS(gva),
+
+	TP_STRUCT__entry(
+		__field(__u64, gva)
+		),
+
+	TP_fast_assign(
+		__entry->gva = gva;
+		),
+
+	TP_printk("gva %#llx ready", __entry->gva)
+);
+
+TRACE_EVENT(
+	kvm_async_pf_completed,
+	TP_PROTO(unsigned long address, struct page *page, u64 gva),
+	TP_ARGS(address, page, gva),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, address)
+		__field(pfn_t, pfn)
+		__field(u64, gva)
+		),
+
+	TP_fast_assign(
+		__entry->address = address;
+		__entry->pfn = page ? page_to_pfn(page) : 0;
+		__entry->gva = gva;
+		),
+
+	TP_printk("gva %#llx address %#lx pfn %#llx",  __entry->gva,
+		  __entry->address, __entry->pfn)
+);
+
+TRACE_EVENT(
+	kvm_async_pf_doublefault,
+	TP_PROTO(u64 gva, u64 gfn),
+	TP_ARGS(gva, gfn),
+
+	TP_STRUCT__entry(
+		__field(u64, gva)
+		__field(u64, gfn)
+		),
+
+	TP_fast_assign(
+		__entry->gva = gva;
+		__entry->gfn = gfn;
+		),
+
+	TP_printk("gva = %#llx, gfn = %#llx", __entry->gva, __entry->gfn)
+);
+
+#endif
+
 #endif /* _TRACE_KVM_MAIN_H */
 
 /* This part must be outside protection */