exec: memory notifiers

index 5e59564..326513d 100644
@@ -8,6 +8,7 @@
 #endif
 
 #include "bswap.h"
+#include "qemu-queue.h"
 
 /* address in the RAM (different from a physical address) */
 typedef unsigned long ram_addr_t;

@@ -62,6 +63,24 @@ void cpu_physical_memory_unmap(void *buffer, target_phys_addr_t len,
 void *cpu_register_map_client(void *opaque, void (*callback)(void *opaque));
 void cpu_unregister_map_client(void *cookie);
 
+struct CPUPhysMemoryClient;
+typedef struct CPUPhysMemoryClient CPUPhysMemoryClient;
+struct CPUPhysMemoryClient {
+    void (*set_memory)(struct CPUPhysMemoryClient *client,
+                       target_phys_addr_t start_addr,
+                       ram_addr_t size,
+                       ram_addr_t phys_offset);
+    int (*sync_dirty_bitmap)(struct CPUPhysMemoryClient *client,
+                             target_phys_addr_t start_addr,
+                             target_phys_addr_t end_addr);
+    int (*migration_log)(struct CPUPhysMemoryClient *client,
+                         int enable);
+    QLIST_ENTRY(CPUPhysMemoryClient) list;
+};
+
+void cpu_register_phys_memory_client(CPUPhysMemoryClient *);
+void cpu_unregister_phys_memory_client(CPUPhysMemoryClient *);
+
 uint32_t ldub_phys(target_phys_addr_t addr);
 uint32_t lduw_phys(target_phys_addr_t addr);
 uint32_t ldl_phys(target_phys_addr_t addr);

141 lines not on this page · raw message

index 0423fff..0fc6019 100644
@@ -398,6 +398,144 @@ int kvm_check_extension(KVMState *s, unsigned int extension)
 }
 #ifdef KVM_UPSTREAM
 
+void kvm_set_phys_mem(target_phys_addr_t start_addr,
+                      ram_addr_t size,
+                      ram_addr_t phys_offset)
+{
+    KVMState *s = kvm_state;
+    ram_addr_t flags = phys_offset & ~TARGET_PAGE_MASK;
+    KVMSlot *mem, old;
+    int err;
+
+    if (start_addr & ~TARGET_PAGE_MASK) {
+        if (flags >= IO_MEM_UNASSIGNED) {
+            if (!kvm_lookup_overlapping_slot(s, start_addr,
+                                             start_addr + size)) {
+                return;
+            }
+            fprintf(stderr, "Unaligned split of a KVM memory slot\n");
+        } else {
+            fprintf(stderr, "Only page-aligned memory slots supported\n");
+        }
+        abort();
+    }
+
+    /* KVM does not support read-only slots */
+    phys_offset &= ~IO_MEM_ROM;
+
+    while (1) {
+        mem = kvm_lookup_overlapping_slot(s, start_addr, start_addr + size);
+        if (!mem) {
+            break;
+        }
+
+        if (flags < IO_MEM_UNASSIGNED && start_addr >= mem->start_addr &&
+            (start_addr + size <= mem->start_addr + mem->memory_size) &&
+            (phys_offset - start_addr == mem->phys_offset - mem->start_addr)) {
+            /* The new slot fits into the existing one and comes with
+             * identical parameters - nothing to be done. */
+            return;
+        }
+
+        old = *mem;
+
+        /* unregister the overlapping slot */
+        mem->memory_size = 0;
+        err = kvm_set_user_memory_region(s, mem);
+        if (err) {
+            fprintf(stderr, "%s: error unregistering overlapping slot: %s\n",
+                    __func__, strerror(-err));
+            abort();
+        }
+
+        /* Workaround for older KVM versions: we can't join slots, even not by
+         * unregistering the previous ones and then registering the larger
+         * slot. We have to maintain the existing fragmentation. Sigh.
+         *
+         * This workaround assumes that the new slot starts at the same
+         * address as the first existing one. If not or if some overlapping
+         * slot comes around later, we will fail (not seen in practice so far)
+         * - and actually require a recent KVM version. */
+        if (s->broken_set_mem_region &&
+            old.start_addr == start_addr && old.memory_size < size &&
+            flags < IO_MEM_UNASSIGNED) {
+            mem = kvm_alloc_slot(s);
+            mem->memory_size = old.memory_size;
+            mem->start_addr = old.start_addr;
+            mem->phys_offset = old.phys_offset;
+            mem->flags = 0;
+
+            err = kvm_set_user_memory_region(s, mem);
+            if (err) {
+                fprintf(stderr, "%s: error updating slot: %s\n", __func__,
+                        strerror(-err));
+                abort();
+            }
+
+            start_addr += old.memory_size;
+            phys_offset += old.memory_size;
+            size -= old.memory_size;
+            continue;
+        }
+
+        /* register prefix slot */
+        if (old.start_addr < start_addr) {
+            mem = kvm_alloc_slot(s);
+            mem->memory_size = start_addr - old.start_addr;
+            mem->start_addr = old.start_addr;
+            mem->phys_offset = old.phys_offset;
+            mem->flags = 0;
+
+            err = kvm_set_user_memory_region(s, mem);
+            if (err) {
+                fprintf(stderr, "%s: error registering prefix slot: %s\n",
+                        __func__, strerror(-err));
+                abort();
+            }
+        }
+
+        /* register suffix slot */
+        if (old.start_addr + old.memory_size > start_addr + size) {
+            ram_addr_t size_delta;
+
+            mem = kvm_alloc_slot(s);
+            mem->start_addr = start_addr + size;
+            size_delta = mem->start_addr - old.start_addr;
+            mem->memory_size = old.memory_size - size_delta;
+            mem->phys_offset = old.phys_offset + size_delta;
+            mem->flags = 0;
+
+            err = kvm_set_user_memory_region(s, mem);
+            if (err) {
+                fprintf(stderr, "%s: error registering suffix slot: %s\n",
+                        __func__, strerror(-err));
+                abort();
+            }
+        }
+    }
+
+    /* in case the KVM bug workaround already "consumed" the new slot */
+    if (!size)
+        return;
+
+    /* KVM does not need to know about this memory */
+    if (flags >= IO_MEM_UNASSIGNED)
+        return;
+
+    mem = kvm_alloc_slot(s);
+    mem->memory_size = size;
+    mem->start_addr = start_addr;
+    mem->phys_offset = phys_offset;
+    mem->flags = 0;
+
+    err = kvm_set_user_memory_region(s, mem);
+    if (err) {
+        fprintf(stderr, "%s: error registering slot: %s\n", __func__,
+                strerror(-err));
+        abort();
+    }
+}
+
 int kvm_init(int smp_cpus)
 {
     static const char upgrade_note[] =

@@ -680,144 +818,6 @@ int kvm_cpu_exec(CPUState *env)
     return ret;
 }
 
-void kvm_set_phys_mem(target_phys_addr_t start_addr,
-                      ram_addr_t size,
-                      ram_addr_t phys_offset)
-{
-    KVMState *s = kvm_state;
-    ram_addr_t flags = phys_offset & ~TARGET_PAGE_MASK;
-    KVMSlot *mem, old;
-    int err;
-
-    if (start_addr & ~TARGET_PAGE_MASK) {
-        if (flags >= IO_MEM_UNASSIGNED) {
-            if (!kvm_lookup_overlapping_slot(s, start_addr,
-                                             start_addr + size)) {
-                return;
-            }
-            fprintf(stderr, "Unaligned split of a KVM memory slot\n");
-        } else {
-            fprintf(stderr, "Only page-aligned memory slots supported\n");
-        }
-        abort();
-    }
-
-    /* KVM does not support read-only slots */
-    phys_offset &= ~IO_MEM_ROM;
-
-    while (1) {
-        mem = kvm_lookup_overlapping_slot(s, start_addr, start_addr + size);
-        if (!mem) {
-            break;
-        }
-
-        if (flags < IO_MEM_UNASSIGNED && start_addr >= mem->start_addr &&
-            (start_addr + size <= mem->start_addr + mem->memory_size) &&
-            (phys_offset - start_addr == mem->phys_offset - mem->start_addr)) {
-            /* The new slot fits into the existing one and comes with
-             * identical parameters - nothing to be done. */
-            return;
-        }
-
-        old = *mem;
-
-        /* unregister the overlapping slot */
-        mem->memory_size = 0;
-        err = kvm_set_user_memory_region(s, mem);
-        if (err) {
-            fprintf(stderr, "%s: error unregistering overlapping slot: %s\n",
-                    __func__, strerror(-err));
-            abort();
-        }
-
-        /* Workaround for older KVM versions: we can't join slots, even not by
-         * unregistering the previous ones and then registering the larger
-         * slot. We have to maintain the existing fragmentation. Sigh.
-         *
-         * This workaround assumes that the new slot starts at the same
-         * address as the first existing one. If not or if some overlapping
-         * slot comes around later, we will fail (not seen in practice so far)
-         * - and actually require a recent KVM version. */
-        if (s->broken_set_mem_region &&
-            old.start_addr == start_addr && old.memory_size < size &&
-            flags < IO_MEM_UNASSIGNED) {
-            mem = kvm_alloc_slot(s);
-            mem->memory_size = old.memory_size;
-            mem->start_addr = old.start_addr;
-            mem->phys_offset = old.phys_offset;
-            mem->flags = 0;
-
-            err = kvm_set_user_memory_region(s, mem);
-            if (err) {
-                fprintf(stderr, "%s: error updating slot: %s\n", __func__,
-                        strerror(-err));
-                abort();
-            }
-
-            start_addr += old.memory_size;
-            phys_offset += old.memory_size;
-            size -= old.memory_size;
-            continue;
-        }
-
-        /* register prefix slot */
-        if (old.start_addr < start_addr) {
-            mem = kvm_alloc_slot(s);
-            mem->memory_size = start_addr - old.start_addr;
-            mem->start_addr = old.start_addr;
-            mem->phys_offset = old.phys_offset;
-            mem->flags = 0;
-
-            err = kvm_set_user_memory_region(s, mem);
-            if (err) {
-                fprintf(stderr, "%s: error registering prefix slot: %s\n",
-                        __func__, strerror(-err));
-                abort();
-            }
-        }
-
-        /* register suffix slot */
-        if (old.start_addr + old.memory_size > start_addr + size) {
-            ram_addr_t size_delta;
-
-            mem = kvm_alloc_slot(s);
-            mem->start_addr = start_addr + size;
-            size_delta = mem->start_addr - old.start_addr;
-            mem->memory_size = old.memory_size - size_delta;
-            mem->phys_offset = old.phys_offset + size_delta;
-            mem->flags = 0;
-
-            err = kvm_set_user_memory_region(s, mem);
-            if (err) {
-                fprintf(stderr, "%s: error registering suffix slot: %s\n",
-                        __func__, strerror(-err));
-                abort();
-            }
-        }
-    }
-
-    /* in case the KVM bug workaround already "consumed" the new slot */
-    if (!size)
-        return;
-
-    /* KVM does not need to know about this memory */
-    if (flags >= IO_MEM_UNASSIGNED)
-        return;
-
-    mem = kvm_alloc_slot(s);
-    mem->memory_size = size;
-    mem->start_addr = start_addr;
-    mem->phys_offset = phys_offset;
-    mem->flags = 0;
-
-    err = kvm_set_user_memory_region(s, mem);
-    if (err) {
-        fprintf(stderr, "%s: error registering slot: %s\n", __func__,
-                strerror(-err));
-        abort();
-    }
-}
-
 #endif
 int kvm_ioctl(KVMState *s, int type, ...)
 {

index fb3ce3f..8c310d5 100644
@@ -1998,12 +1998,6 @@ int cpu_physical_memory_set_dirty_tracking(int enable)
 {
     int ret = 0;
     in_migration = enable;
-    if (kvm_enabled()) {
-        ret = kvm_set_migration_log(enable);
-    }
-    if (ret < 0) {
-        return ret;
-    }
     ret = cpu_notify_migration_log(!!enable);
     return ret;
 }

@@ -2016,14 +2010,8 @@ int cpu_physical_memory_get_dirty_tracking(void)
 int cpu_physical_sync_dirty_bitmap(target_phys_addr_t start_addr,
                                    target_phys_addr_t end_addr)
 {
-    int ret = 0;
+    int ret;
 
-    if (kvm_enabled()) {
-        ret = kvm_physical_sync_dirty_bitmap(start_addr, end_addr);
-    }
-    if (ret < 0) {
-        return ret;
-    }
     ret = cpu_notify_sync_dirty_bitmap(start_addr, end_addr);
     return ret;
 }

@@ -2436,9 +2424,6 @@ void cpu_register_physical_memory_offset(target_phys_addr_t start_addr,
     ram_addr_t orig_size = size;
     void *subpage;
 
-    if (kvm_enabled())
-        kvm_set_phys_mem(start_addr, size, phys_offset);
-
     cpu_notify_set_memory(start_addr, size, phys_offset);
 
     if (phys_offset == IO_MEM_UNASSIGNED) {

index 0fc6019..f31585e 100644
@@ -259,7 +259,7 @@ int kvm_log_stop(target_phys_addr_t phys_addr, ram_addr_t size)
                                           KVM_MEM_LOG_DIRTY_PAGES);
 }
 
-int kvm_set_migration_log(int enable)
+static int kvm_set_migration_log(int enable)
 {
     KVMState *s = kvm_state;
     KVMSlot *mem;

@@ -294,8 +294,8 @@ static int test_le_bit(unsigned long nr, unsigned char *addr)
  * @start_add: start of logged region.
  * @end_addr: end of logged region.
  */
-int kvm_physical_sync_dirty_bitmap(target_phys_addr_t start_addr,
-                                   target_phys_addr_t end_addr)
+static int kvm_physical_sync_dirty_bitmap(target_phys_addr_t start_addr,
+					  target_phys_addr_t end_addr)
 {
     KVMState *s = kvm_state;
     unsigned long size, allocated_size = 0;

@@ -536,6 +536,33 @@ void kvm_set_phys_mem(target_phys_addr_t start_addr,
     }
 }
 
+static void kvm_client_set_memory(struct CPUPhysMemoryClient *client,
+				  target_phys_addr_t start_addr,
+				  ram_addr_t size,
+				  ram_addr_t phys_offset)
+{
+	kvm_set_phys_mem(start_addr, size, phys_offset);
+}
+
+static int kvm_client_sync_dirty_bitmap(struct CPUPhysMemoryClient *client,
+					target_phys_addr_t start_addr,
+					target_phys_addr_t end_addr)
+{
+	return kvm_physical_sync_dirty_bitmap(start_addr, end_addr);
+}
+
+static int kvm_client_migration_log(struct CPUPhysMemoryClient *client,
+				    int enable)
+{
+	return kvm_set_migration_log(enable);
+}
+
+static CPUPhysMemoryClient kvm_cpu_phys_memory_client = {
+	.set_memory = kvm_client_set_memory,
+	.sync_dirty_bitmap = kvm_client_sync_dirty_bitmap,
+	.migration_log = kvm_client_migration_log,
+};
+
 int kvm_init(int smp_cpus)
 {
     static const char upgrade_note[] =

@@ -632,6 +659,7 @@ int kvm_init(int smp_cpus)
         goto err;
 
     kvm_state = s;
+    cpu_register_phys_memory_client(&kvm_cpu_phys_memory_client);
 
     return 0;
 

index 9fa4e25..7b33177 100644
@@ -38,16 +38,8 @@ int kvm_init_vcpu(CPUState *env);
 
 int kvm_cpu_exec(CPUState *env);
 
-void kvm_set_phys_mem(target_phys_addr_t start_addr,
-                      ram_addr_t size,
-                      ram_addr_t phys_offset);
-
-int kvm_physical_sync_dirty_bitmap(target_phys_addr_t start_addr,
-                                   target_phys_addr_t end_addr);
-
 int kvm_log_start(target_phys_addr_t phys_addr, ram_addr_t size);
 int kvm_log_stop(target_phys_addr_t phys_addr, ram_addr_t size);
-int kvm_set_migration_log(int enable);
 
 int kvm_has_sync_mmu(void);
 #endif /* KVM_UPSTREAM */

index f31585e..51273e4 100644
@@ -536,6 +536,8 @@ void kvm_set_phys_mem(target_phys_addr_t start_addr,
     }
 }
 
+#endif
+
 static void kvm_client_set_memory(struct CPUPhysMemoryClient *client,
 				  target_phys_addr_t start_addr,
 				  ram_addr_t size,

@@ -563,6 +565,8 @@ static CPUPhysMemoryClient kvm_cpu_phys_memory_client = {
 	.migration_log = kvm_client_migration_log,
 };
 
+#ifdef KVM_UPSTREAM
+
 int kvm_init(int smp_cpus)
 {
     static const char upgrade_note[] =

index a305907..f7b2dda 100644
@@ -406,6 +406,7 @@ int kvm_init(int smp_cpus)
         for (i = gsi_count; i < gsi_bits; i++)
             set_gsi(kvm_context, i);
     }
+    cpu_register_phys_memory_client(&kvm_cpu_phys_memory_client);
 
     pthread_mutex_lock(&qemu_mutex);
     return kvm_create_context();

index 51273e4..6dbe480 100644
@@ -1134,4 +1134,24 @@ void kvm_remove_all_breakpoints(CPUState *current_env)
 }
 #endif /* !KVM_CAP_SET_GUEST_DEBUG */
 
+#ifdef KVM_IOEVENTFD
+int kvm_set_ioeventfd(uint16_t addr, uint16_t data, int fd, bool assigned)
+{
+    struct kvm_ioeventfd kick = {
+        .datamatch = data,
+        .addr = addr,
+        .len = 2,
+        .flags = KVM_IOEVENTFD_FLAG_DATAMATCH | KVM_IOEVENTFD_FLAG_PIO,
+        .fd = fd,
+    };
+    int r;
+    if (!assigned)
+        kick.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
+    r = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &kick);
+    if (r < 0)
+        return r;
+    return 0;
+}
+#endif
+
 #include "qemu-kvm.c"

index 7b33177..365d8b1 100644
@@ -14,6 +14,8 @@
 #ifndef QEMU_KVM_H
 #define QEMU_KVM_H
 
+#include <stdbool.h>
+#include <errno.h>
 #include "config.h"
 #include "qemu-queue.h"
 #include "qemu-kvm.h"

@@ -21,6 +23,10 @@
 #ifdef KVM_UPSTREAM
 
 #ifdef CONFIG_KVM
+#include <linux/kvm.h>
+#endif
+
+#ifdef CONFIG_KVM
 extern int kvm_allowed;
 
 #define kvm_enabled() (kvm_allowed)

@@ -143,4 +149,14 @@ static inline void cpu_synchronize_state(CPUState *env)
 
 #endif
 
+#if defined(KVM_IOEVENTFD) && defined(CONFIG_KVM)
+int kvm_set_ioeventfd(uint16_t addr, uint16_t data, int fd, bool assigned);
+#else
+static inline
+int kvm_set_ioeventfd(uint16_t data, uint16_t addr, int fd, bool assigned)
+{
+    return -ENOSYS;
+}
+#endif
+
 #endif

50 lines not on this page · raw message

new file mode 100644
index 0000000..24117ea
@@ -0,0 +1,16 @@
+#ifndef QEMU_EVENT_NOTIFIER_H
+#define QEMU_EVENT_NOTIFIER_H
+
+#include "qemu-common.h"
+
+struct EventNotifier {
+	int fd;
+};
+
+int event_notifier_init(EventNotifier *, int active);
+void event_notifier_cleanup(EventNotifier *);
+int event_notifier_get_fd(EventNotifier *);
+int event_notifier_test_and_clear(EventNotifier *);
+int event_notifier_test(EventNotifier *);
+
+#endif

index bf14a22..5e935d1 100644
@@ -224,6 +224,7 @@ typedef struct uWireSlave uWireSlave;
 typedef struct I2SCodec I2SCodec;
 typedef struct DeviceState DeviceState;
 typedef struct SSIBus SSIBus;
+typedef struct EventNotifier EventNotifier;
 
 /* CPU save/load.  */
 void cpu_save(QEMUFile *f, void *opaque);

index 7c020a3..b9411e9 100644
@@ -592,6 +592,12 @@ VirtQueue *virtio_add_queue(VirtIODevice *vdev, int queue_size,
     return &vdev->vq[i];
 }
 
+void virtio_irq(VirtIODevice *vdev, VirtQueue *vq)
+{
+    vdev->isr |= 0x01;
+    virtio_notify_vector(vdev, vq->vector);
+}
+
 void virtio_notify(VirtIODevice *vdev, VirtQueue *vq)
 {
     /* Always notify when queue is empty (when feature acknowledge) */

@@ -600,8 +606,7 @@ void virtio_notify(VirtIODevice *vdev, VirtQueue *vq)
          (vq->inuse || vring_avail_idx(vq) != vq->last_avail_idx)))
         return;
 
-    vdev->isr |= 0x01;
-    virtio_notify_vector(vdev, vq->vector);
+    virtio_irq(vdev, vq);
 }
 
 void virtio_notify_config(VirtIODevice *vdev)

@@ -714,8 +719,10 @@ VirtIODevice *virtio_common_init(const char *name, uint16_t device_id,
     vdev->queue_sel = 0;
     vdev->config_vector = VIRTIO_NO_VECTOR;
     vdev->vq = qemu_mallocz(sizeof(VirtQueue) * VIRTIO_PCI_QUEUE_MAX);
-    for(i = 0; i < VIRTIO_PCI_QUEUE_MAX; i++)
+    for(i = 0; i < VIRTIO_PCI_QUEUE_MAX; i++) {
         vdev->vq[i].vector = VIRTIO_NO_VECTOR;
+        vdev->vq[i].vdev = vdev;
+    }
 
     vdev->name = name;
     vdev->config_len = config_size;

index 62e882b..2c298a8 100644
@@ -18,6 +18,7 @@
 #include "net.h"
 #include "qdev.h"
 #include "sysemu.h"
+#include "notifier.h"
 
 /* from Linux's linux/virtio_config.h */
 

@@ -88,6 +89,8 @@ typedef struct {
     int (*load_config)(void * opaque, QEMUFile *f);
     int (*load_queue)(void * opaque, int n, QEMUFile *f);
     unsigned (*get_features)(void * opaque);
+    int (*guest_notifier)(void * opaque, int n, bool assigned);
+    int (*host_notifier)(void * opaque, int n, bool assigned);
 } VirtIOBindings;
 
 #define VIRTIO_PCI_QUEUE_MAX 64

@@ -180,5 +183,5 @@ void virtio_net_exit(VirtIODevice *vdev);
 	DEFINE_PROP_BIT("indirect_desc", _state, _field, \
 			VIRTIO_RING_F_INDIRECT_DESC, true)
 
-
+void virtio_irq(VirtIODevice *vdev, VirtQueue *vq);
 #endif

index b9411e9..65e59c1 100644
@@ -73,6 +73,9 @@ struct VirtQueue
     int inuse;
     uint16_t vector;
     void (*handle_output)(VirtIODevice *vdev, VirtQueue *vq);
+    VirtIODevice *vdev;
+    EventNotifier guest_notifier;
+    EventNotifier host_notifier;
 };
 
 /* virt queue functions */

@@ -592,10 +595,10 @@ VirtQueue *virtio_add_queue(VirtIODevice *vdev, int queue_size,
     return &vdev->vq[i];
 }
 
-void virtio_irq(VirtIODevice *vdev, VirtQueue *vq)
+void virtio_irq(VirtQueue *vq)
 {
-    vdev->isr |= 0x01;
-    virtio_notify_vector(vdev, vq->vector);
+    vq->vdev->isr |= 0x01;
+    virtio_notify_vector(vq->vdev, vq->vector);
 }
 
 void virtio_notify(VirtIODevice *vdev, VirtQueue *vq)

@@ -606,7 +609,8 @@ void virtio_notify(VirtIODevice *vdev, VirtQueue *vq)
          (vq->inuse || vring_avail_idx(vq) != vq->last_avail_idx)))
         return;
 
-    virtio_irq(vdev, vq);
+    vdev->isr |= 0x01;
+    virtio_notify_vector(vdev, vq->vector);
 }
 
 void virtio_notify_config(VirtIODevice *vdev)

@@ -740,3 +744,42 @@ void virtio_bind_device(VirtIODevice *vdev, const VirtIOBindings *binding,
     vdev->binding = binding;
     vdev->binding_opaque = opaque;
 }
+
+target_phys_addr_t virtio_queue_get_desc(VirtIODevice *vdev, int n)
+{
+	return vdev->vq[n].vring.desc;
+}
+
+target_phys_addr_t virtio_queue_get_avail(VirtIODevice *vdev, int n)
+{
+	return vdev->vq[n].vring.avail;
+}
+
+target_phys_addr_t virtio_queue_get_used(VirtIODevice *vdev, int n)
+{
+	return vdev->vq[n].vring.used;
+}
+
+uint16_t virtio_queue_last_avail_idx(VirtIODevice *vdev, int n)
+{
+	return vdev->vq[n].last_avail_idx;
+}
+
+void virtio_queue_set_last_avail_idx(VirtIODevice *vdev, int n, uint16_t idx)
+{
+	vdev->vq[n].last_avail_idx = idx;
+}
+
+VirtQueue *virtio_queue(VirtIODevice *vdev, int n)
+{
+	return vdev->vq + n;
+}
+
+EventNotifier *virtio_queue_guest_notifier(VirtQueue *vq)
+{
+	return &vq->guest_notifier;
+}
+EventNotifier *virtio_queue_host_notifier(VirtQueue *vq)
+{
+	return &vq->host_notifier;
+}

index 2c298a8..92ad5d1 100644
@@ -183,5 +183,13 @@ void virtio_net_exit(VirtIODevice *vdev);
 	DEFINE_PROP_BIT("indirect_desc", _state, _field, \
 			VIRTIO_RING_F_INDIRECT_DESC, true)
 
-void virtio_irq(VirtIODevice *vdev, VirtQueue *vq);
+target_phys_addr_t virtio_queue_get_desc(VirtIODevice *vdev, int n);
+target_phys_addr_t virtio_queue_get_avail(VirtIODevice *vdev, int n);
+target_phys_addr_t virtio_queue_get_used(VirtIODevice *vdev, int n);
+uint16_t virtio_queue_last_avail_idx(VirtIODevice *vdev, int n);
+void virtio_queue_set_last_avail_idx(VirtIODevice *vdev, int n, uint16_t idx);
+VirtQueue *virtio_queue(VirtIODevice *vdev, int n);
+EventNotifier *virtio_queue_guest_notifier(VirtQueue *vq);
+EventNotifier *virtio_queue_host_notifier(VirtQueue *vq);
+void virtio_irq(VirtQueue *vq);
 #endif

index 6b6dafc..a4ce734 100644
@@ -243,6 +243,9 @@ void s390_virtio_device_update_status(VirtIOS390Device *dev)
     uint32_t features;
 
     vdev->status = ldub_phys(dev->dev_offs + VIRTIO_DEV_OFFS_STATUS);
+    if (vdev->set_status) {
+        vdev->set_status(vdev);
+    }
 
     /* Update guest supported feature bitmap */
 

index 65239a0..19f6473 100644
@@ -152,6 +152,8 @@ static void syborg_virtio_writel(void *opaque, target_phys_addr_t offset,
         vdev->status = value & 0xFF;
         if (vdev->status == 0)
             virtio_reset(vdev);
+        if (vdev->set_status)
+            vdev->set_status(vdev);
         break;
     case SYBORG_VIRTIO_INT_ENABLE:
         s->int_enable = value;

index 709d13e..dbb0b16 100644
@@ -210,6 +210,9 @@ static void virtio_ioport_write(void *opaque, uint32_t addr, uint32_t val)
             virtio_reset(proxy->vdev);
             msix_unuse_all_vectors(&proxy->pci_dev);
         }
+        if (vdev->set_status) {
+            vdev->set_status(vdev);
+        }
         break;
     case VIRTIO_MSI_CONFIG_VECTOR:
         msix_vector_unuse(&proxy->pci_dev, vdev->config_vector);

@@ -377,6 +380,9 @@ static void virtio_write_config(PCIDevice *pci_dev, uint32_t address,
     if (PCI_COMMAND == address) {
         if (!(val & PCI_COMMAND_MASTER)) {
             proxy->vdev->status &= ~VIRTIO_CONFIG_S_DRIVER_OK;
+            if (proxy->vdev->set_status) {
+                proxy->vdev->set_status(proxy->vdev);
+            }
         }
     }
 

index 92ad5d1..235e7c4 100644
@@ -114,6 +114,7 @@ struct VirtIODevice
     void (*get_config)(VirtIODevice *vdev, uint8_t *config);
     void (*set_config)(VirtIODevice *vdev, const uint8_t *config);
     void (*reset)(VirtIODevice *vdev);
+    void (*set_status)(VirtIODevice *vdev);
     VirtQueue *vq;
     const VirtIOBindings *binding;
     void *binding_opaque;

index 235e7c4..5dae591 100644
@@ -68,7 +68,6 @@ static inline target_phys_addr_t vring_align(target_phys_addr_t addr,
 }
 
 typedef struct VirtQueue VirtQueue;
-typedef struct VirtIODevice VirtIODevice;
 
 #define VIRTQUEUE_MAX_SIZE 1024
 

index 5e935d1..9a31ce0 100644
@@ -225,6 +225,7 @@ typedef struct I2SCodec I2SCodec;
 typedef struct DeviceState DeviceState;
 typedef struct SSIBus SSIBus;
 typedef struct EventNotifier EventNotifier;
+typedef struct VirtIODevice VirtIODevice;
 
 /* CPU save/load.  */
 void cpu_save(QEMUFile *f, void *opaque);

index dbb0b16..02859a7 100644
@@ -23,6 +23,7 @@
 #include "msix.h"
 #include "net.h"
 #include "loader.h"
+#include "kvm.h"
 
 /* from Linux's linux/virtio_pci.h */
 

@@ -396,6 +397,65 @@ static unsigned virtio_pci_get_features(void *opaque)
     return proxy->host_features;
 }
 
+static void virtio_pci_guest_notifier_read(void *opaque)
+{
+    VirtQueue *vq = opaque;
+    EventNotifier *n = virtio_queue_guest_notifier(vq);
+    if (event_notifier_test_and_clear(n)) {
+        virtio_irq(vq);
+    }
+}
+
+static int virtio_pci_guest_notifier(void *opaque, int n, bool assign)
+{
+    VirtIOPCIProxy *proxy = opaque;
+    VirtQueue *vq = virtio_queue(proxy->vdev, n);
+    EventNotifier *notifier = virtio_queue_guest_notifier(vq);
+
+    if (assign) {
+        int r = event_notifier_init(notifier, 0);
+	if (r < 0)
+		return r;
+        qemu_set_fd_handler(event_notifier_get_fd(notifier),
+                            virtio_pci_guest_notifier_read, NULL, vq);
+    } else {
+        qemu_set_fd_handler(event_notifier_get_fd(notifier),
+                            NULL, NULL, vq);
+        event_notifier_cleanup(notifier);
+    }
+
+    return 0;
+}
+
+static int virtio_pci_host_notifier(void *opaque, int n, bool assign)
+{
+    VirtIOPCIProxy *proxy = opaque;
+    VirtQueue *vq = virtio_queue(proxy->vdev, n);
+    EventNotifier *notifier = virtio_queue_host_notifier(vq);
+    int r;
+    if (assign) {
+	r = event_notifier_init(notifier, 1);
+	if (r < 0) {
+		return r;
+        }
+        r = kvm_set_ioeventfd(proxy->addr + VIRTIO_PCI_QUEUE_NOTIFY,
+                              n, event_notifier_get_fd(notifier),
+                              assign);
+        if (r < 0) {
+            event_notifier_cleanup(notifier);
+        }
+    } else {
+        r = kvm_set_ioeventfd(proxy->addr + VIRTIO_PCI_QUEUE_NOTIFY,
+                              n, event_notifier_get_fd(notifier),
+                              assign);
+	if (r < 0) {
+		return r;
+        }
+        event_notifier_cleanup(notifier);
+    }
+    return r;
+}
+
 static const VirtIOBindings virtio_pci_bindings = {
     .notify = virtio_pci_notify,
     .save_config = virtio_pci_save_config,

@@ -403,6 +463,8 @@ static const VirtIOBindings virtio_pci_bindings = {
     .save_queue = virtio_pci_save_queue,
     .load_queue = virtio_pci_load_queue,
     .get_features = virtio_pci_get_features,
+    .host_notifier = virtio_pci_host_notifier,
+    .guest_notifier = virtio_pci_guest_notifier,
 };
 
 static void virtio_init_pci(VirtIOPCIProxy *proxy, VirtIODevice *vdev,

index d3492de..7e9ca79 100644
@@ -269,6 +269,13 @@ static void tap_poll(VLANClientState *nc, bool enable)
     tap_write_poll(s, enable);
 }
 
+int tap_get_fd(VLANClientState *nc)
+{
+    TAPState *s = DO_UPCAST(TAPState, nc, nc);
+    assert(nc->info->type == NET_CLIENT_TYPE_TAP);
+    return s->fd;
+}
+
 /* fd support */
 
 static NetClientInfo net_tap_info = {

index 538a562..a244b28 100644
@@ -48,4 +48,6 @@ int tap_probe_vnet_hdr(int fd);
 int tap_probe_has_ufo(int fd);
 void tap_fd_set_offload(int fd, int csum, int tso4, int tso6, int ecn, int ufo);
 
+int tap_get_fd(VLANClientState *vc);
+
 #endif /* QEMU_NET_TAP_H */

603 lines not on this page · raw message

44 lines not on this page · raw message

147 lines not on this page · raw message

new file mode 100644
index 0000000..21f0277
@@ -0,0 +1,20 @@
+#ifndef VHOST_NET_H
+#define VHOST_NET_H
+
+#include "net.h"
+
+struct vhost_net;
+
+struct vhost_net *vhost_net_init(VLANClientState *backend, int devfd);
+
+int vhost_net_start(struct vhost_net *net,
+		    VirtIODevice *dev);
+void vhost_net_stop(struct vhost_net *net,
+		    VirtIODevice *dev);
+
+void vhost_net_cleanup(struct vhost_net *net);
+
+unsigned vhost_net_get_features(struct vhost_net *net, unsigned features);
+void vhost_net_ack_features(struct vhost_net *net, unsigned features);
+
+#endif

index 6ef93e6..b942d03 100644
@@ -976,6 +976,14 @@ static struct {
                 .name = "vnet_hdr",
                 .type = QEMU_OPT_BOOL,
                 .help = "enable the IFF_VNET_HDR flag on the tap interface"
+            }, {
+                .name = "vhost",
+                .type = QEMU_OPT_BOOL,
+                .help = "enable vhost-net network accelerator",
+            }, {
+                .name = "vhostfd",
+                .type = QEMU_OPT_STRING,
+                .help = "file descriptor of an already opened vhost net device",
             },
 #endif /* _WIN32 */
             { /* end of list */ }

index 7e9ca79..d9f2e41 100644
@@ -41,6 +41,8 @@
 
 #include "net/tap-linux.h"
 
+#include "hw/vhost_net.h"
+
 /* Maximum GSO packet size (64k) plus plenty of room for
  * the ethernet and virtio_net headers
  */

@@ -57,6 +59,7 @@ typedef struct TAPState {
     unsigned int has_vnet_hdr : 1;
     unsigned int using_vnet_hdr : 1;
     unsigned int has_ufo: 1;
+    struct vhost_net *vhost_net;
 } TAPState;
 
 static int launch_script(const char *setup_script, const char *ifname, int fd);

@@ -252,6 +255,10 @@ static void tap_cleanup(VLANClientState *nc)
 {
     TAPState *s = DO_UPCAST(TAPState, nc, nc);
 
+    if (s->vhost_net) {
+        vhost_net_cleanup(s->vhost_net);
+    }
+
     qemu_purge_queued_packets(nc);
 
     if (s->down_script[0])

@@ -307,6 +314,7 @@ static TAPState *net_tap_fd_init(VLANState *vlan,
     s->has_ufo = tap_probe_has_ufo(s->fd);
     tap_set_offload(&s->nc, 0, 0, 0, 0, 0);
     tap_read_poll(s, 1);
+    s->vhost_net = NULL;
     return s;
 }
 

@@ -456,6 +464,27 @@ int net_init_tap(QemuOpts *opts, Monitor *mon, const char *name, VLANState *vlan
         }
     }
 
+    if (qemu_opt_get_bool(opts, "vhost", 0)) {
+        int vhostfd, r;
+        if (qemu_opt_get(opts, "vhostfd")) {
+            r = net_handle_fd_param(mon, qemu_opt_get(opts, "vhostfd"));
+            if (r == -1) {
+                return -1;
+            }
+            vhostfd = r;
+        } else {
+            vhostfd = -1;
+        }
+        s->vhost_net = vhost_net_init(&s->nc, vhostfd);
+        if (!s->vhost_net) {
+            qemu_error("vhost-net requested but could not be initialized\n");
+            return -1;
+        }
+    } else if (qemu_opt_get(opts, "vhostfd")) {
+        qemu_error("vhostfd= is not valid without vhost\n");
+        return -1;
+    }
+
     if (vlan) {
         vlan->nb_host_devs++;
     }

index d9f2e41..166cf05 100644
@@ -491,3 +491,10 @@ int net_init_tap(QemuOpts *opts, Monitor *mon, const char *name, VLANState *vlan
 
     return 0;
 }
+
+struct vhost_net *tap_get_vhost_net(VLANClientState *nc)
+{
+    TAPState *s = DO_UPCAST(TAPState, nc, nc);
+    assert(nc->info->type == NET_CLIENT_TYPE_TAP);
+    return s->vhost_net;
+}

index a244b28..b8cec83 100644
@@ -50,4 +50,7 @@ void tap_fd_set_offload(int fd, int csum, int tso4, int tso6, int ecn, int ufo);
 
 int tap_get_fd(VLANClientState *vc);
 
+struct vhost_net;
+struct vhost_net *tap_get_vhost_net(VLANClientState *vc);
+
 #endif /* QEMU_NET_TAP_H */

index 6e48997..f32c6fa 100644
@@ -17,6 +17,7 @@
 #include "net/tap.h"
 #include "qemu-timer.h"
 #include "virtio-net.h"
+#include "vhost_net.h"
 
 #define VIRTIO_NET_VM_VERSION    11
 

@@ -47,6 +48,8 @@ typedef struct VirtIONet
     uint8_t nomulti;
     uint8_t nouni;
     uint8_t nobcast;
+    uint8_t vhost_started;
+    VMChangeStateEntry *vmstate;
     struct {
         int in_use;
         int first_multi;

@@ -114,6 +117,10 @@ static void virtio_net_reset(VirtIODevice *vdev)
     n->nomulti = 0;
     n->nouni = 0;
     n->nobcast = 0;
+    if (n->vhost_started) {
+        vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), vdev);
+        n->vhost_started = 0;
+    }
 
     /* Flush any MAC and VLAN filter table state */
     n->mac_table.in_use = 0;

@@ -172,7 +179,10 @@ static uint32_t virtio_net_get_features(VirtIODevice *vdev, uint32_t features)
         features &= ~(0x1 << VIRTIO_NET_F_HOST_UFO);
     }
 
-    return features;
+    if (!tap_get_vhost_net(n->nic->nc.peer)) {
+        return features;
+    }
+    return vhost_net_get_features(tap_get_vhost_net(n->nic->nc.peer), features);
 }
 
 static uint32_t virtio_net_bad_features(VirtIODevice *vdev)

@@ -690,6 +700,12 @@ static void virtio_net_save(QEMUFile *f, void *opaque)
 {
     VirtIONet *n = opaque;
 
+    if (n->vhost_started) {
+	/* TODO: should we really stop the backend?
+	 * If we don't, it might keep writing to memory. */
+        vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), &n->vdev);
+	n->vhost_started = 0;
+    }
     virtio_save(&n->vdev, f);
 
     qemu_put_buffer(f, n->mac, ETH_ALEN);

@@ -802,7 +818,6 @@ static int virtio_net_load(QEMUFile *f, void *opaque, int version_id)
         qemu_mod_timer(n->tx_timer,
                        qemu_get_clock(vm_clock) + TX_TIMER_INTERVAL);
     }
-
     return 0;
 }
 

@@ -822,6 +837,47 @@ static NetClientInfo net_virtio_info = {
     .link_status_changed = virtio_net_set_link_status,
 };
 
+static void virtio_net_set_status(struct VirtIODevice *vdev)
+{
+    VirtIONet *n = to_virtio_net(vdev);
+    if (!n->nic->nc.peer) {
+        return;
+    }
+    if (n->nic->nc.peer->info->type != NET_CLIENT_TYPE_TAP) {
+        return;
+    }
+
+    if (!tap_get_vhost_net(n->nic->nc.peer)) {
+        return;
+    }
+    if (!!n->vhost_started == !!(vdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) {
+        return;
+    }
+    if (vdev->status & VIRTIO_CONFIG_S_DRIVER_OK) {
+        int r = vhost_net_start(tap_get_vhost_net(n->nic->nc.peer), vdev);
+        if (r < 0) {
+            fprintf(stderr, "unable to start vhost net: %d: "
+                    "falling back on userspace virtio\n", -r);
+        } else {
+            n->vhost_started = 1;
+        }
+    } else {
+        vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), vdev);
+        n->vhost_started = 0;
+    }
+}
+
+static void virtio_net_vmstate_change(void *opaque, int running, int reason)
+{
+	VirtIONet *n = opaque;
+	if (!running) {
+		return;
+	}
+	/* This is called when vm is started, it will start vhost backend if it
+	 * appropriate e.g. after migration. */
+	virtio_net_set_status(&n->vdev);
+}
+
 VirtIODevice *virtio_net_init(DeviceState *dev, NICConf *conf)
 {
     VirtIONet *n;

@@ -837,6 +893,7 @@ VirtIODevice *virtio_net_init(DeviceState *dev, NICConf *conf)
     n->vdev.set_features = virtio_net_set_features;
     n->vdev.bad_features = virtio_net_bad_features;
     n->vdev.reset = virtio_net_reset;
+    n->vdev.set_status = virtio_net_set_status;
     n->rx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_rx);
     n->tx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_tx);
     n->ctrl_vq = virtio_add_queue(&n->vdev, 64, virtio_net_handle_ctrl);

@@ -859,6 +916,7 @@ VirtIODevice *virtio_net_init(DeviceState *dev, NICConf *conf)
 
     register_savevm("virtio-net", virtio_net_id++, VIRTIO_NET_VM_VERSION,
                     virtio_net_save, virtio_net_load, n);
+    n->vmstate = qemu_add_vm_change_state_handler(virtio_net_vmstate_change, n);
 
     return &n->vdev;
 }

@@ -866,6 +924,11 @@ VirtIODevice *virtio_net_init(DeviceState *dev, NICConf *conf)
 void virtio_net_exit(VirtIODevice *vdev)
 {
     VirtIONet *n = DO_UPCAST(VirtIONet, vdev, vdev);
+    qemu_del_vm_change_state_handler(n->vmstate);
+
+    if (n->vhost_started) {
+        vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer), vdev);
+    }
 
     qemu_purge_queued_packets(&n->nic->nc);
 

new file mode 100644
index 0000000..165a484
@@ -0,0 +1,130 @@
+#ifndef _LINUX_VHOST_H
+#define _LINUX_VHOST_H
+/* Userspace interface for in-kernel virtio accelerators. */
+
+/* vhost is used to reduce the number of system calls involved in virtio.
+ *
+ * Existing virtio net code is used in the guest without modification.
+ *
+ * This header includes interface used by userspace hypervisor for
+ * device configuration.
+ */
+
+#include <linux/types.h>
+
+#include <linux/ioctl.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+
+struct vhost_vring_state {
+	unsigned int index;
+	unsigned int num;
+};
+
+struct vhost_vring_file {
+	unsigned int index;
+	int fd; /* Pass -1 to unbind from file. */
+
+};
+
+struct vhost_vring_addr {
+	unsigned int index;
+	/* Option flags. */
+	unsigned int flags;
+	/* Flag values: */
+	/* Whether log address is valid. If set enables logging. */
+#define VHOST_VRING_F_LOG 0
+
+	/* Start of array of descriptors (virtually contiguous) */
+	__u64 desc_user_addr;
+	/* Used structure address. Must be 32 bit aligned */
+	__u64 used_user_addr;
+	/* Available structure address. Must be 16 bit aligned */
+	__u64 avail_user_addr;
+	/* Logging support. */
+	/* Log writes to used structure, at offset calculated from specified
+	 * address. Address must be 32 bit aligned. */
+	__u64 log_guest_addr;
+};
+
+struct vhost_memory_region {
+	__u64 guest_phys_addr;
+	__u64 memory_size; /* bytes */
+	__u64 userspace_addr;
+	__u64 flags_padding; /* No flags are currently specified. */
+};
+
+/* All region addresses and sizes must be 4K aligned. */
+#define VHOST_PAGE_SIZE 0x1000
+
+struct vhost_memory {
+	__u32 nregions;
+	__u32 padding;
+	struct vhost_memory_region regions[0];
+};
+
+/* ioctls */
+
+#define VHOST_VIRTIO 0xAF
+
+/* Features bitmask for forward compatibility.  Transport bits are used for
+ * vhost specific features. */
+#define VHOST_GET_FEATURES	_IOR(VHOST_VIRTIO, 0x00, __u64)
+#define VHOST_SET_FEATURES	_IOW(VHOST_VIRTIO, 0x00, __u64)
+
+/* Set current process as the (exclusive) owner of this file descriptor.  This
+ * must be called before any other vhost command.  Further calls to
+ * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */
+#define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
+/* Give up ownership, and reset the device to default values.
+ * Allows subsequent call to VHOST_OWNER_SET to succeed. */
+#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
+
+/* Set up/modify memory layout */
+#define VHOST_SET_MEM_TABLE	_IOW(VHOST_VIRTIO, 0x03, struct vhost_memory)
+
+/* Write logging setup. */
+/* Memory writes can optionally be logged by setting bit at an offset
+ * (calculated from the physical address) from specified log base.
+ * The bit is set using an atomic 32 bit operation. */
+/* Set base address for logging. */
+#define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
+/* Specify an eventfd file descriptor to signal on log write. */
+#define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
+
+/* Ring setup. */
+/* Set number of descriptors in ring. This parameter can not
+ * be modified while ring is running (bound to a device). */
+#define VHOST_SET_VRING_NUM _IOW(VHOST_VIRTIO, 0x10, struct vhost_vring_state)
+/* Set addresses for the ring. */
+#define VHOST_SET_VRING_ADDR _IOW(VHOST_VIRTIO, 0x11, struct vhost_vring_addr)
+/* Base value where queue looks for available descriptors */
+#define VHOST_SET_VRING_BASE _IOW(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+/* Get accessor: reads index, writes value in num */
+#define VHOST_GET_VRING_BASE _IOWR(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+
+/* The following ioctls use eventfd file descriptors to signal and poll
+ * for events. */
+
+/* Set eventfd to poll for added buffers */
+#define VHOST_SET_VRING_KICK _IOW(VHOST_VIRTIO, 0x20, struct vhost_vring_file)
+/* Set eventfd to signal when buffers have beed used */
+#define VHOST_SET_VRING_CALL _IOW(VHOST_VIRTIO, 0x21, struct vhost_vring_file)
+/* Set eventfd to signal an error */
+#define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct vhost_vring_file)
+
+/* VHOST_NET specific defines */
+
+/* Attach virtio net ring to a raw socket, or tap device.
+ * The socket must be already bound to an ethernet device, this device will be
+ * used for transmit.  Pass fd -1 to unbind from the socket and the transmit
+ * device.  This can be used to stop the ring (e.g. for migration). */
+#define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file)
+
+/* Feature bits */
+/* Log all write descriptors. Can be changed while device is active. */
+#define VHOST_F_LOG_ALL 26
+/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */
+#define VHOST_NET_F_VIRTIO_NET_HDR 27
+
+#endif

index 6dbe480..3c692f6 100644
@@ -1154,4 +1154,23 @@ int kvm_set_ioeventfd(uint16_t addr, uint16_t data, int fd, bool assigned)
 }
 #endif
 
+#if defined(KVM_IRQFD)
+int kvm_set_irqfd(int gsi, int fd, bool assigned)
+{
+    struct kvm_irqfd irqfd = {
+        .fd = fd,
+        .gsi = gsi,
+        .flags = assigned ? 0 : KVM_IRQFD_FLAG_DEASSIGN,
+    };
+    int r;
+    if (!kvm_irqchip_in_kernel())
+        return -ENOSYS;
+
+    r = kvm_vm_ioctl(kvm_state, KVM_IRQFD, &irqfd);
+    if (r < 0)
+        return r;
+    return 0;
+}
+#endif
+
 #include "qemu-kvm.c"

index 365d8b1..e762a5b 100644
@@ -159,4 +159,14 @@ int kvm_set_ioeventfd(uint16_t data, uint16_t addr, int fd, bool assigned)
 }
 #endif
 
+#if defined(KVM_IRQFD) && defined(CONFIG_KVM)
+int kvm_set_irqfd(int gsi, int fd, bool assigned);
+#else
+static inline
+int kvm_set_irqfd(int gsi, int fd, bool assigned)
+{
+    return -ENOSYS;
+}
+#endif
+
 #endif

index 87f125b..31a61c6 100644
@@ -318,6 +318,13 @@ static void msix_mmio_writel(void *opaque, target_phys_addr_t addr,
     if (kvm_enabled() && kvm_irqchip_in_kernel()) {
         kvm_msix_update(dev, vector, was_masked, msix_is_masked(dev, vector));
     }
+    if (was_masked != msix_is_masked(dev, vector) &&
+        dev->msix_mask_notifier && dev->msix_mask_notifier_opaque[vector]) {
+        int r = dev->msix_mask_notifier(dev, vector,
+					dev->msix_mask_notifier_opaque[vector],
+					msix_is_masked(dev, vector));
+        assert(r >= 0);
+    }
     msix_handle_mask_update(dev, vector);
 }
 

@@ -356,10 +363,18 @@ void msix_mmio_map(PCIDevice *d, int region_num,
 
 static void msix_mask_all(struct PCIDevice *dev, unsigned nentries)
 {
-    int vector;
+    int vector, r;
     for (vector = 0; vector < nentries; ++vector) {
         unsigned offset = vector * MSIX_ENTRY_SIZE + MSIX_VECTOR_CTRL;
+        int was_masked = msix_is_masked(dev, vector);
         dev->msix_table_page[offset] |= MSIX_VECTOR_MASK;
+        if (was_masked != msix_is_masked(dev, vector) &&
+            dev->msix_mask_notifier && dev->msix_mask_notifier_opaque[vector]) {
+            r = dev->msix_mask_notifier(dev, vector,
+                                        dev->msix_mask_notifier_opaque[vector],
+                                        msix_is_masked(dev, vector));
+            assert(r >= 0);
+        }
     }
 }
 

@@ -382,6 +397,9 @@ int msix_init(struct PCIDevice *dev, unsigned short nentries,
                                             sizeof *dev->msix_irq_entries);
     }
 #endif
+    dev->msix_mask_notifier_opaque =
+        qemu_mallocz(nentries * sizeof *dev->msix_mask_notifier_opaque);
+    dev->msix_mask_notifier = NULL;
     dev->msix_entry_used = qemu_mallocz(MSIX_MAX_ENTRIES *
                                         sizeof *dev->msix_entry_used);
 

@@ -444,6 +462,8 @@ int msix_uninit(PCIDevice *dev)
     dev->msix_entry_used = NULL;
     qemu_free(dev->msix_irq_entries);
     dev->msix_irq_entries = NULL;
+    qemu_free(dev->msix_mask_notifier_opaque);
+    dev->msix_mask_notifier_opaque = NULL;
     dev->cap_present &= ~QEMU_PCI_CAP_MSIX;
     return 0;
 }

@@ -587,3 +607,17 @@ void msix_unuse_all_vectors(PCIDevice *dev)
         return;
     msix_free_irq_entries(dev);
 }
+
+int msix_set_mask_notifier(PCIDevice *dev, unsigned vector, void *opaque)
+{
+    int r = 0;
+    if (vector >= dev->msix_entries_nr || !dev->msix_entry_used[vector])
+        return 0;
+
+    if (dev->msix_mask_notifier)
+        r = dev->msix_mask_notifier(dev, vector, opaque,
+                                    msix_is_masked(dev, vector));
+    if (r >= 0)
+        dev->msix_mask_notifier_opaque[vector] = opaque;
+    return r;
+}

index a9f7993..f167231 100644
@@ -33,4 +33,5 @@ void msix_reset(PCIDevice *dev);
 
 extern int msix_supported;
 
+int msix_set_mask_notifier(PCIDevice *dev, unsigned vector, void *opaque);
 #endif

index c9e9d56..a4a0fe9 100644
@@ -137,6 +137,9 @@ enum {
 #define PCI_CAPABILITY_CONFIG_MSI_LENGTH 0x10
 #define PCI_CAPABILITY_CONFIG_MSIX_LENGTH 0x10
 
+typedef int (*msix_mask_notifier_func)(PCIDevice *, unsigned vector,
+				       void *opaque, int masked);
+
 struct PCIDevice {
     DeviceState qdev;
     /* PCI config space */

@@ -202,6 +205,9 @@ struct PCIDevice {
 
     struct kvm_irq_routing_entry *msix_irq_entries;
 
+    void **msix_mask_notifier_opaque;
+    msix_mask_notifier_func msix_mask_notifier;
+
     /* Device capability configuration space */
     struct {
         int supported;

index 02859a7..f3ed939 100644
@@ -406,6 +406,27 @@ static void virtio_pci_guest_notifier_read(void *opaque)
     }
 }
 
+static int virtio_pci_mask_notifier(PCIDevice *dev, unsigned vector,
+                                    void *opaque, int masked)
+{
+    VirtQueue *vq = opaque;
+    EventNotifier *notifier = virtio_queue_guest_notifier(vq);
+    int r = kvm_set_irqfd(dev->msix_irq_entries[vector].gsi,
+                          event_notifier_get_fd(notifier),
+                          !masked);
+    if (r < 0) {
+        return (r == -ENOSYS) ? 0 : r;
+    }
+    if (masked) {
+        qemu_set_fd_handler(event_notifier_get_fd(notifier),
+                            virtio_pci_guest_notifier_read, NULL, vq);
+    } else {
+        qemu_set_fd_handler(event_notifier_get_fd(notifier),
+                            NULL, NULL, vq);
+    }
+    return 0;
+}
+
 static int virtio_pci_guest_notifier(void *opaque, int n, bool assign)
 {
     VirtIOPCIProxy *proxy = opaque;

@@ -414,11 +435,15 @@ static int virtio_pci_guest_notifier(void *opaque, int n, bool assign)
 
     if (assign) {
         int r = event_notifier_init(notifier, 0);
-	if (r < 0)
-		return r;
+        if (r < 0)
+            return r;
         qemu_set_fd_handler(event_notifier_get_fd(notifier),
                             virtio_pci_guest_notifier_read, NULL, vq);
+        msix_set_mask_notifier(&proxy->pci_dev,
+			       virtio_queue_vector(proxy->vdev, n), vq);
     } else {
+        msix_set_mask_notifier(&proxy->pci_dev,
+			       virtio_queue_vector(proxy->vdev, n), NULL);
         qemu_set_fd_handler(event_notifier_get_fd(notifier),
                             NULL, NULL, vq);
         event_notifier_cleanup(notifier);

@@ -503,6 +528,8 @@ static void virtio_init_pci(VirtIOPCIProxy *proxy, VirtIODevice *vdev,
 
     proxy->pci_dev.config_write = virtio_write_config;
 
+    proxy->pci_dev.msix_mask_notifier = virtio_pci_mask_notifier;
+
     size = VIRTIO_PCI_REGION_SIZE(&proxy->pci_dev) + vdev->config_len;
     if (size & (size-1))
         size = 1 << qemu_fls(size);