Merge remote branch 'kvm/linux-next'

5 files changed, 220 insertions, 15 deletions

diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 919ae53adc5c..ea2dc1a2e13d 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -540,6 +540,7 @@ struct kvm_ppc_pvinfo {
 #endif
 #define KVM_CAP_PPC_GET_PVINFO 57
 #define KVM_CAP_PPC_IRQ_LEVEL 58
+#define KVM_CAP_ASYNC_PF 59
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a0557422715e..b5021db21858 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -16,6 +16,8 @@
 #include <linux/mm.h>
 #include <linux/preempt.h>
 #include <linux/msi.h>
+#include <linux/slab.h>
+#include <linux/rcupdate.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -40,6 +42,7 @@
 #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 +77,27 @@ 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);
+int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
+#endif
+
 struct kvm_vcpu {
 	struct kvm *kvm;
 #ifdef CONFIG_PREEMPT_NOTIFIERS
@@ -104,6 +128,15 @@ 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;
 };
 
@@ -113,16 +146,19 @@ struct kvm_vcpu {
  */
 #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1)
 
+struct kvm_lpage_info {
+	unsigned long rmap_pde;
+	int write_count;
+};
+
 struct kvm_memory_slot {
 	gfn_t base_gfn;
 	unsigned long npages;
 	unsigned long flags;
 	unsigned long *rmap;
 	unsigned long *dirty_bitmap;
-	struct {
-		unsigned long rmap_pde;
-		int write_count;
-	} *lpage_info[KVM_NR_PAGE_SIZES - 1];
+	unsigned long *dirty_bitmap_head;
+	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
 	unsigned long userspace_addr;
 	int user_alloc;
 	int id;
@@ -169,6 +205,7 @@ struct kvm_irq_routing_table {};
 
 struct kvm_memslots {
 	int nmemslots;
+	u64 generation;
 	struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS +
 					KVM_PRIVATE_MEM_SLOTS];
 };
@@ -206,6 +243,10 @@ struct kvm {
 
 	struct mutex irq_lock;
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
+	/*
+	 * Update side is protected by irq_lock and,
+	 * if configured, irqfds.lock.
+	 */
 	struct kvm_irq_routing_table __rcu *irq_routing;
 	struct hlist_head mask_notifier_list;
 	struct hlist_head irq_ack_notifier_list;
@@ -216,6 +257,7 @@ struct kvm {
 	unsigned long mmu_notifier_seq;
 	long mmu_notifier_count;
 #endif
+	long tlbs_dirty;
 };
 
 /* The guest did something we don't support. */
@@ -302,7 +344,11 @@ 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,
+		       bool write_fault, bool *writable);
 pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn);
+pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
+		      bool *writable);
 pfn_t gfn_to_pfn_memslot(struct kvm *kvm,
 			 struct kvm_memory_slot *slot, gfn_t gfn);
 int memslot_id(struct kvm *kvm, gfn_t gfn);
@@ -321,18 +367,25 @@ int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data,
 			 int offset, int len);
 int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
 		    unsigned long len);
+int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+			   void *data, unsigned long len);
+int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+			      gpa_t gpa);
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
 int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
 unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
+void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot,
+			     gfn_t gfn);
 
 void kvm_vcpu_block(struct kvm_vcpu *vcpu);
 void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
 void kvm_resched(struct kvm_vcpu *vcpu);
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
+
 void kvm_flush_remote_tlbs(struct kvm *kvm);
 void kvm_reload_remote_mmus(struct kvm *kvm);
 
@@ -398,7 +451,19 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
 
 void kvm_free_physmem(struct kvm *kvm);
 
-struct  kvm *kvm_arch_create_vm(void);
+#ifndef __KVM_HAVE_ARCH_VM_ALLOC
+static inline struct kvm *kvm_arch_alloc_vm(void)
+{
+	return kzalloc(sizeof(struct kvm), GFP_KERNEL);
+}
+
+static inline void kvm_arch_free_vm(struct kvm *kvm)
+{
+	kfree(kvm);
+}
+#endif
+
+int kvm_arch_init_vm(struct kvm *kvm);
 void kvm_arch_destroy_vm(struct kvm *kvm);
 void kvm_free_all_assigned_devices(struct kvm *kvm);
 void kvm_arch_sync_events(struct kvm *kvm);
@@ -414,16 +479,8 @@ struct kvm_irq_ack_notifier {
 	void (*irq_acked)(struct kvm_irq_ack_notifier *kian);
 };
 
-#define KVM_ASSIGNED_MSIX_PENDING		0x1
-struct kvm_guest_msix_entry {
-	u32 vector;
-	u16 entry;
-	u16 flags;
-};
-
 struct kvm_assigned_dev_kernel {
 	struct kvm_irq_ack_notifier ack_notifier;
-	struct work_struct interrupt_work;
 	struct list_head list;
 	int assigned_dev_id;
 	int host_segnr;
@@ -434,13 +491,14 @@ struct kvm_assigned_dev_kernel {
 	bool host_irq_disabled;
 	struct msix_entry *host_msix_entries;
 	int guest_irq;
-	struct kvm_guest_msix_entry *guest_msix_entries;
+	struct msix_entry *guest_msix_entries;
 	unsigned long irq_requested_type;
 	int irq_source_id;
 	int flags;
 	struct pci_dev *dev;
 	struct kvm *kvm;
-	spinlock_t assigned_dev_lock;
+	spinlock_t intx_lock;
+	char irq_name[32];
 };
 
 struct kvm_irq_mask_notifier {
@@ -462,6 +520,8 @@ void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic,
 				   unsigned long *deliver_bitmask);
 #endif
 int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level);
+int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm,
+		int irq_source_id, int level);
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin);
 void kvm_register_irq_ack_notifier(struct kvm *kvm,
 				   struct kvm_irq_ack_notifier *kian);
@@ -603,17 +663,28 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {}
 void kvm_eventfd_init(struct kvm *kvm);
 int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags);
 void kvm_irqfd_release(struct kvm *kvm);
+void kvm_irq_routing_update(struct kvm *, struct kvm_irq_routing_table *);
 int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
 
 #else
 
 static inline void kvm_eventfd_init(struct kvm *kvm) {}
+
 static inline int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags)
 {
 	return -EINVAL;
 }
 
 static inline void kvm_irqfd_release(struct kvm *kvm) {}
+
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
+static inline void kvm_irq_routing_update(struct kvm *kvm,
+					  struct kvm_irq_routing_table *irq_rt)
+{
+	rcu_assign_pointer(kvm->irq_routing, irq_rt);
+}
+#endif
+
 static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 {
 	return -ENOSYS;
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 7ac0d4eee430..fa7cc7244cbd 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -67,4 +67,11 @@ struct kvm_lapic_irq {
 	u32 dest_id;
 };
 
+struct gfn_to_hva_cache {
+	u64 generation;
+	gpa_t gpa;
+	unsigned long hva;
+	struct kvm_memory_slot *memslot;
+};
+
 #endif /* __KVM_TYPES_H__ */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 721f451c3029..e097df6c0174 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -145,6 +145,7 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_NONLINEAR	0x02	/* Fault was via a nonlinear mapping */
 #define FAULT_FLAG_MKWRITE	0x04	/* Fault was mkwrite of existing pte */
 #define FAULT_FLAG_ALLOW_RETRY	0x08	/* Retry fault if blocking */
+#define FAULT_FLAG_MINOR	0x10	/* Do only minor fault */
 
 /*
  * This interface is used by x86 PAT code to identify a pfn mapping that is
@@ -858,6 +859,9 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			unsigned long start, int nr_pages, int write, int force,
 			struct page **pages, struct vm_area_struct **vmas);
+int get_user_pages_noio(struct task_struct *tsk, struct mm_struct *mm,
+			unsigned long start, int nr_pages, int write, int force,
+			struct page **pages, struct vm_area_struct **vmas);
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages);
 struct page *get_dump_page(unsigned long addr);
@@ -1415,6 +1419,7 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address,
 #define FOLL_GET	0x04	/* do get_page on page */
 #define FOLL_DUMP	0x08	/* give error on hole if it would be zero */
 #define FOLL_FORCE	0x10	/* get_user_pages read/write w/o permission */
+#define FOLL_MINOR	0x20	/* do only minor page faults */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 6dd3a51ab1cb..46e3cd8e197a 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -6,6 +6,36 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm
 
+#define ERSN(x) { KVM_EXIT_##x, "KVM_EXIT_" #x }
+
+#define kvm_trace_exit_reason						\
+	ERSN(UNKNOWN), ERSN(EXCEPTION), ERSN(IO), ERSN(HYPERCALL),	\
+	ERSN(DEBUG), ERSN(HLT), ERSN(MMIO), ERSN(IRQ_WINDOW_OPEN),	\
+	ERSN(SHUTDOWN), ERSN(FAIL_ENTRY), ERSN(INTR), ERSN(SET_TPR),	\
+	ERSN(TPR_ACCESS), ERSN(S390_SIEIC), ERSN(S390_RESET), ERSN(DCR),\
+	ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI)
+
+TRACE_EVENT(kvm_userspace_exit,
+	    TP_PROTO(__u32 reason, int errno),
+	    TP_ARGS(reason, errno),
+
+	TP_STRUCT__entry(
+		__field(	__u32,		reason		)
+		__field(	int,		errno		)
+	),
+
+	TP_fast_assign(
+		__entry->reason		= reason;
+		__entry->errno		= errno;
+	),
+
+	TP_printk("reason %s (%d)",
+		  __entry->errno < 0 ?
+		  (__entry->errno == -EINTR ? "restart" : "error") :
+		  __print_symbolic(__entry->reason, kvm_trace_exit_reason),
+		  __entry->errno < 0 ? -__entry->errno : __entry->reason)
+);
+
 #if defined(__KVM_HAVE_IOAPIC)
 TRACE_EVENT(kvm_set_irq,
 	TP_PROTO(unsigned int gsi, int level, int irq_source_id),
@@ -185,6 +215,97 @@ TRACE_EVENT(kvm_age_page,
 		  __entry->referenced ? "YOUNG" : "OLD")
 );
 
+#ifdef CONFIG_KVM_ASYNC_PF
+DECLARE_EVENT_CLASS(kvm_async_get_page_class,
+
+	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)
+);
+
+DEFINE_EVENT(kvm_async_get_page_class, kvm_try_async_get_page,
+
+	TP_PROTO(u64 gva, u64 gfn),
+
+	TP_ARGS(gva, gfn)
+);
+
+DEFINE_EVENT(kvm_async_get_page_class, kvm_async_pf_doublefault,
+
+	TP_PROTO(u64 gva, u64 gfn),
+
+	TP_ARGS(gva, gfn)
+);
+
+DECLARE_EVENT_CLASS(kvm_async_pf_nopresent_ready,
+
+	TP_PROTO(u64 token, u64 gva),
+
+	TP_ARGS(token, gva),
+
+	TP_STRUCT__entry(
+		__field(__u64, token)
+		__field(__u64, gva)
+	),
+
+	TP_fast_assign(
+		__entry->token = token;
+		__entry->gva = gva;
+	),
+
+	TP_printk("token %#llx gva %#llx", __entry->token, __entry->gva)
+
+);
+
+DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_not_present,
+
+	TP_PROTO(u64 token, u64 gva),
+
+	TP_ARGS(token, gva)
+);
+
+DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_ready,
+
+	TP_PROTO(u64 token, u64 gva),
+
+	TP_ARGS(token, 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)
+);
+
+#endif
+
 #endif /* _TRACE_KVM_MAIN_H */
 
 /* This part must be outside protection */