1 files changed, 163 insertions, 19 deletions

diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index ca554d4ff1..b041343632 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -11,7 +11,9 @@
 #include "qemu/osdep.h"
 #include "qapi/error.h"
 #include "hw/virtio/vhost.h"
+#include "hw/virtio/vhost-user.h"
 #include "hw/virtio/vhost-backend.h"
+#include "hw/virtio/virtio.h"
 #include "hw/virtio/virtio-net.h"
 #include "chardev/char-fe.h"
 #include "sysemu/kvm.h"
@@ -30,6 +32,7 @@
 
 #define VHOST_MEMORY_MAX_NREGIONS    8
 #define VHOST_USER_F_PROTOCOL_FEATURES 30
+#define VHOST_USER_SLAVE_MAX_FDS     8
 
 /*
  * Maximum size of virtio device config space
@@ -47,6 +50,8 @@ enum VhostUserProtocolFeature {
     VHOST_USER_PROTOCOL_F_CRYPTO_SESSION = 7,
     VHOST_USER_PROTOCOL_F_PAGEFAULT = 8,
     VHOST_USER_PROTOCOL_F_CONFIG = 9,
+    VHOST_USER_PROTOCOL_F_SLAVE_SEND_FD = 10,
+    VHOST_USER_PROTOCOL_F_HOST_NOTIFIER = 11,
     VHOST_USER_PROTOCOL_F_MAX
 };
 
@@ -91,6 +96,7 @@ typedef enum VhostUserSlaveRequest {
     VHOST_USER_SLAVE_NONE = 0,
     VHOST_USER_SLAVE_IOTLB_MSG = 1,
     VHOST_USER_SLAVE_CONFIG_CHANGE_MSG = 2,
+    VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG = 3,
     VHOST_USER_SLAVE_MAX
 }  VhostUserSlaveRequest;
 
@@ -135,6 +141,12 @@ static VhostUserConfig c __attribute__ ((unused));
                                    + sizeof(c.size) \
                                    + sizeof(c.flags))
 
+typedef struct VhostUserVringArea {
+    uint64_t u64;
+    uint64_t size;
+    uint64_t offset;
+} VhostUserVringArea;
+
 typedef struct {
     VhostUserRequest request;
 
@@ -156,6 +168,7 @@ typedef union {
         struct vhost_iotlb_msg iotlb;
         VhostUserConfig config;
         VhostUserCryptoSession session;
+        VhostUserVringArea area;
 } VhostUserPayload;
 
 typedef struct VhostUserMsg {
@@ -173,7 +186,8 @@ static VhostUserMsg m __attribute__ ((unused));
 
 struct vhost_user {
     struct vhost_dev *dev;
-    CharBackend *chr;
+    /* Shared between vhost devs of the same virtio device */
+    VhostUserState *user;
     int slave_fd;
     NotifierWithReturn postcopy_notifier;
     struct PostCopyFD  postcopy_fd;
@@ -199,7 +213,7 @@ static bool ioeventfd_enabled(void)
 static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
 {
     struct vhost_user *u = dev->opaque;
-    CharBackend *chr = u->chr;
+    CharBackend *chr = u->user->chr;
     uint8_t *p = (uint8_t *) msg;
     int r, size = VHOST_USER_HDR_SIZE;
 
@@ -285,7 +299,7 @@ static int vhost_user_write(struct vhost_dev *dev, VhostUserMsg *msg,
                             int *fds, int fd_num)
 {
     struct vhost_user *u = dev->opaque;
-    CharBackend *chr = u->chr;
+    CharBackend *chr = u->user->chr;
     int ret, size = VHOST_USER_HDR_SIZE + msg->hdr.size;
 
     /*
@@ -636,9 +650,37 @@ static int vhost_user_set_vring_num(struct vhost_dev *dev,
     return vhost_set_vring(dev, VHOST_USER_SET_VRING_NUM, ring);
 }
 
+static void vhost_user_host_notifier_restore(struct vhost_dev *dev,
+                                             int queue_idx)
+{
+    struct vhost_user *u = dev->opaque;
+    VhostUserHostNotifier *n = &u->user->notifier[queue_idx];
+    VirtIODevice *vdev = dev->vdev;
+
+    if (n->addr && !n->set) {
+        virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, true);
+        n->set = true;
+    }
+}
+
+static void vhost_user_host_notifier_remove(struct vhost_dev *dev,
+                                            int queue_idx)
+{
+    struct vhost_user *u = dev->opaque;
+    VhostUserHostNotifier *n = &u->user->notifier[queue_idx];
+    VirtIODevice *vdev = dev->vdev;
+
+    if (n->addr && n->set) {
+        virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, false);
+        n->set = false;
+    }
+}
+
 static int vhost_user_set_vring_base(struct vhost_dev *dev,
                                      struct vhost_vring_state *ring)
 {
+    vhost_user_host_notifier_restore(dev, ring->index);
+
     return vhost_set_vring(dev, VHOST_USER_SET_VRING_BASE, ring);
 }
 
@@ -672,6 +714,8 @@ static int vhost_user_get_vring_base(struct vhost_dev *dev,
         .hdr.size = sizeof(msg.payload.state),
     };
 
+    vhost_user_host_notifier_remove(dev, ring->index);
+
     if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
         return -1;
     }
@@ -845,6 +889,66 @@ static int vhost_user_slave_handle_config_change(struct vhost_dev *dev)
     return ret;
 }
 
+static int vhost_user_slave_handle_vring_host_notifier(struct vhost_dev *dev,
+                                                       VhostUserVringArea *area,
+                                                       int fd)
+{
+    int queue_idx = area->u64 & VHOST_USER_VRING_IDX_MASK;
+    size_t page_size = qemu_real_host_page_size;
+    struct vhost_user *u = dev->opaque;
+    VhostUserState *user = u->user;
+    VirtIODevice *vdev = dev->vdev;
+    VhostUserHostNotifier *n;
+    void *addr;
+    char *name;
+
+    if (!virtio_has_feature(dev->protocol_features,
+                            VHOST_USER_PROTOCOL_F_HOST_NOTIFIER) ||
+        vdev == NULL || queue_idx >= virtio_get_num_queues(vdev)) {
+        return -1;
+    }
+
+    n = &user->notifier[queue_idx];
+
+    if (n->addr) {
+        virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, false);
+        object_unparent(OBJECT(&n->mr));
+        munmap(n->addr, page_size);
+        n->addr = NULL;
+    }
+
+    if (area->u64 & VHOST_USER_VRING_NOFD_MASK) {
+        return 0;
+    }
+
+    /* Sanity check. */
+    if (area->size != page_size) {
+        return -1;
+    }
+
+    addr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+                fd, area->offset);
+    if (addr == MAP_FAILED) {
+        return -1;
+    }
+
+    name = g_strdup_printf("vhost-user/host-notifier@%p mmaps[%d]",
+                           user, queue_idx);
+    memory_region_init_ram_device_ptr(&n->mr, OBJECT(vdev), name,
+                                      page_size, addr);
+    g_free(name);
+
+    if (virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, true)) {
+        munmap(addr, page_size);
+        return -1;
+    }
+
+    n->addr = addr;
+    n->set = true;
+
+    return 0;
+}
+
 static void slave_read(void *opaque)
 {
     struct vhost_dev *dev = opaque;
@@ -854,10 +958,10 @@ static void slave_read(void *opaque)
     int size, ret = 0;
     struct iovec iov;
     struct msghdr msgh;
-    int fd = -1;
+    int fd[VHOST_USER_SLAVE_MAX_FDS];
     char control[CMSG_SPACE(sizeof(fd))];
     struct cmsghdr *cmsg;
-    size_t fdsize;
+    int i, fdsize = 0;
 
     memset(&msgh, 0, sizeof(msgh));
     msgh.msg_iov = &iov;
@@ -865,6 +969,8 @@ static void slave_read(void *opaque)
     msgh.msg_control = control;
     msgh.msg_controllen = sizeof(control);
 
+    memset(fd, -1, sizeof(fd));
+
     /* Read header */
     iov.iov_base = &hdr;
     iov.iov_len = VHOST_USER_HDR_SIZE;
@@ -885,7 +991,7 @@ static void slave_read(void *opaque)
             if (cmsg->cmsg_level == SOL_SOCKET &&
                 cmsg->cmsg_type == SCM_RIGHTS) {
                     fdsize = cmsg->cmsg_len - CMSG_LEN(0);
-                    memcpy(&fd, CMSG_DATA(cmsg), fdsize);
+                    memcpy(fd, CMSG_DATA(cmsg), fdsize);
                     break;
             }
     }
@@ -911,16 +1017,21 @@ static void slave_read(void *opaque)
     case VHOST_USER_SLAVE_CONFIG_CHANGE_MSG :
         ret = vhost_user_slave_handle_config_change(dev);
         break;
+    case VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG:
+        ret = vhost_user_slave_handle_vring_host_notifier(dev, &payload.area,
+                                                          fd[0]);
+        break;
     default:
         error_report("Received unexpected msg type.");
-        if (fd != -1) {
-            close(fd);
-        }
         ret = -EINVAL;
     }
 
-    /* Message handlers need to make sure that fd will be consumed. */
-    fd = -1;
+    /* Close the remaining file descriptors. */
+    for (i = 0; i < fdsize; i++) {
+        if (fd[i] != -1) {
+            close(fd[i]);
+        }
+    }
 
     /*
      * REPLY_ACK feature handling. Other reply types has to be managed
@@ -954,8 +1065,10 @@ err:
     qemu_set_fd_handler(u->slave_fd, NULL, NULL, NULL);
     close(u->slave_fd);
     u->slave_fd = -1;
-    if (fd != -1) {
-        close(fd);
+    for (i = 0; i < fdsize; i++) {
+        if (fd[i] != -1) {
+            close(fd[i]);
+        }
     }
     return;
 }
@@ -1083,7 +1196,7 @@ static int vhost_user_postcopy_waker(struct PostCopyFD *pcfd, RAMBlock *rb,
 static int vhost_user_postcopy_advise(struct vhost_dev *dev, Error **errp)
 {
     struct vhost_user *u = dev->opaque;
-    CharBackend *chr = u->chr;
+    CharBackend *chr = u->user->chr;
     int ufd;
     VhostUserMsg msg = {
         .hdr.request = VHOST_USER_POSTCOPY_ADVISE,
@@ -1221,7 +1334,7 @@ static int vhost_user_postcopy_notifier(NotifierWithReturn *notifier,
     return 0;
 }
 
-static int vhost_user_init(struct vhost_dev *dev, void *opaque)
+static int vhost_user_backend_init(struct vhost_dev *dev, void *opaque)
 {
     uint64_t features, protocol_features;
     struct vhost_user *u;
@@ -1230,7 +1343,7 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque)
     assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
 
     u = g_new0(struct vhost_user, 1);
-    u->chr = opaque;
+    u->user = opaque;
     u->slave_fd = -1;
     u->dev = dev;
     dev->opaque = u;
@@ -1306,7 +1419,7 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque)
     return 0;
 }
 
-static int vhost_user_cleanup(struct vhost_dev *dev)
+static int vhost_user_backend_cleanup(struct vhost_dev *dev)
 {
     struct vhost_user *u;
 
@@ -1620,10 +1733,40 @@ vhost_user_crypto_close_session(struct vhost_dev *dev, uint64_t session_id)
     return 0;
 }
 
+static bool vhost_user_mem_section_filter(struct vhost_dev *dev,
+                                          MemoryRegionSection *section)
+{
+    bool result;
+
+    result = memory_region_get_fd(section->mr) >= 0;
+
+    return result;
+}
+
+VhostUserState *vhost_user_init(void)
+{
+    VhostUserState *user = g_new0(struct VhostUserState, 1);
+
+    return user;
+}
+
+void vhost_user_cleanup(VhostUserState *user)
+{
+    int i;
+
+    for (i = 0; i < VIRTIO_QUEUE_MAX; i++) {
+        if (user->notifier[i].addr) {
+            object_unparent(OBJECT(&user->notifier[i].mr));
+            munmap(user->notifier[i].addr, qemu_real_host_page_size);
+            user->notifier[i].addr = NULL;
+        }
+    }
+}
+
 const VhostOps user_ops = {
         .backend_type = VHOST_BACKEND_TYPE_USER,
-        .vhost_backend_init = vhost_user_init,
-        .vhost_backend_cleanup = vhost_user_cleanup,
+        .vhost_backend_init = vhost_user_backend_init,
+        .vhost_backend_cleanup = vhost_user_backend_cleanup,
         .vhost_backend_memslots_limit = vhost_user_memslots_limit,
         .vhost_set_log_base = vhost_user_set_log_base,
         .vhost_set_mem_table = vhost_user_set_mem_table,
@@ -1650,4 +1793,5 @@ const VhostOps user_ops = {
         .vhost_set_config = vhost_user_set_config,
         .vhost_crypto_create_session = vhost_user_crypto_create_session,
         .vhost_crypto_close_session = vhost_user_crypto_close_session,
+        .vhost_backend_mem_section_filter = vhost_user_mem_section_filter,
 };