[Qemu-devel] [RFC v2 3/4] vhost-user: add slave-req-fd support

[Maxime Coquelin <maxime.coquelin@redhat.com>]

From: Marc-André Lureau <marcandre.lureau@redhat.com>

Learn to give a socket to the slave to let him make requests to the
master.

Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
 docs/specs/vhost-user.txt |  30 +++++++++++-
 hw/virtio/vhost-user.c    | 117 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 145 insertions(+), 2 deletions(-)

diff --git a/docs/specs/vhost-user.txt b/docs/specs/vhost-user.txt
index 036890f..49c6293 100644
--- a/docs/specs/vhost-user.txt
+++ b/docs/specs/vhost-user.txt
@@ -139,6 +139,7 @@ in the ancillary data:
  * VHOST_USER_SET_VRING_KICK
  * VHOST_USER_SET_VRING_CALL
  * VHOST_USER_SET_VRING_ERR
+ * VHOST_USER_SET_SLAVE_REQ_FD
 
 If Master is unable to send the full message or receives a wrong reply it will
 close the connection. An optional reconnection mechanism can be implemented.
@@ -252,6 +253,18 @@ Once the source has finished migration, rings will be stopped by
 the source. No further update must be done before rings are
 restarted.
 
+Slave communication
+-------------------
+
+An optional communication channel is provided if the slave declares
+VHOST_USER_PROTOCOL_F_SLAVE_REQ protocol feature, to allow the slave to make
+requests to the master.
+
+The fd is provided via VHOST_USER_SET_SLAVE_REQ_FD ancillary data.
+
+A slave may then send VHOST_USER_SLAVE_* messages to the master
+using this fd communication channel.
+
 Protocol features
 -----------------
 
@@ -260,9 +273,10 @@ Protocol features
 #define VHOST_USER_PROTOCOL_F_RARP           2
 #define VHOST_USER_PROTOCOL_F_REPLY_ACK      3
 #define VHOST_USER_PROTOCOL_F_MTU            4
+#define VHOST_USER_PROTOCOL_F_SLAVE_REQ      5
 
-Message types
--------------
+Master message types
+--------------------
 
  * VHOST_USER_GET_FEATURES
 
@@ -486,6 +500,18 @@ Message types
       If VHOST_USER_PROTOCOL_F_REPLY_ACK is negotiated, slave must respond
       with zero in case the specified MTU is valid, or non-zero otherwise.
 
+ * VHOST_USER_SET_SLAVE_REQ_FD
+
+      Id: 21
+      Equivalent ioctl: N/A
+      Master payload: N/A
+
+      Set the socket file descriptor for slave initiated requests. It is passed
+      in the ancillary data.
+      This request should be sent only when VHOST_USER_F_PROTOCOL_FEATURES
+      has been negotiated, and protocol feature bit VHOST_USER_PROTOCOL_F_SLAVE_REQ
+      bit is present in VHOST_USER_GET_PROTOCOL_FEATURES.
+
 VHOST_USER_PROTOCOL_F_REPLY_ACK:
 -------------------------------
 The original vhost-user specification only demands replies for certain
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index f0e10d0..f26f11b 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -33,6 +33,7 @@ enum VhostUserProtocolFeature {
     VHOST_USER_PROTOCOL_F_RARP = 2,
     VHOST_USER_PROTOCOL_F_REPLY_ACK = 3,
     VHOST_USER_PROTOCOL_F_NET_MTU = 4,
+    VHOST_USER_PROTOCOL_F_SLAVE_REQ = 5,
 
     VHOST_USER_PROTOCOL_F_MAX
 };
@@ -61,9 +62,15 @@ typedef enum VhostUserRequest {
     VHOST_USER_SET_VRING_ENABLE = 18,
     VHOST_USER_SEND_RARP = 19,
     VHOST_USER_NET_SET_MTU = 20,
+    VHOST_USER_SET_SLAVE_REQ_FD = 21,
     VHOST_USER_MAX
 } VhostUserRequest;
 
+typedef enum VhostUserSlaveRequest {
+    VHOST_USER_SLAVE_NONE = 0,
+    VHOST_USER_SLAVE_MAX
+}  VhostUserSlaveRequest;
+
 typedef struct VhostUserMemoryRegion {
     uint64_t guest_phys_addr;
     uint64_t memory_size;
@@ -113,6 +120,7 @@ static VhostUserMsg m __attribute__ ((unused));
 
 struct vhost_user {
     CharBackend *chr;
+    int slave_fd;
 };
 
 static bool ioeventfd_enabled(void)
@@ -574,6 +582,104 @@ static int vhost_user_reset_device(struct vhost_dev *dev)
     return 0;
 }
 
+static void slave_read(void *opaque)
+{
+    struct vhost_dev *dev = opaque;
+    struct vhost_user *u = dev->opaque;
+    VhostUserMsg msg = { 0, };
+    int size, ret = 0;
+
+    /* Read header */
+    size = read(u->slave_fd, &msg, VHOST_USER_HDR_SIZE);
+    if (size != VHOST_USER_HDR_SIZE) {
+        error_report("Failed to read from slave.");
+        goto err;
+    }
+
+    if (msg.size > VHOST_USER_PAYLOAD_SIZE) {
+        error_report("Failed to read msg header."
+                " Size %d exceeds the maximum %zu.", msg.size,
+                VHOST_USER_PAYLOAD_SIZE);
+        goto err;
+    }
+
+    /* Read payload */
+    size = read(u->slave_fd, &msg.payload, msg.size);
+    if (size != msg.size) {
+        error_report("Failed to read payload from slave.");
+        goto err;
+    }
+
+    switch (msg.request) {
+    default:
+        error_report("Received unexpected msg type.");
+        ret = -EINVAL;
+    }
+
+    /*
+     * REPLY_ACK feature handling. Other reply types has to be managed
+     * directly in their request handlers.
+     */
+    if (msg.flags & VHOST_USER_NEED_REPLY_MASK) {
+        msg.flags &= ~VHOST_USER_NEED_REPLY_MASK;
+        msg.flags |= VHOST_USER_REPLY_MASK;
+
+        msg.payload.u64 = !!ret;
+        msg.size = sizeof(msg.payload.u64);
+
+        size = write(u->slave_fd, &msg, VHOST_USER_HDR_SIZE + msg.size);
+        if (size != VHOST_USER_HDR_SIZE + msg.size) {
+            error_report("Failed to send msg reply to slave.");
+            goto err;
+        }
+    }
+
+    return;
+
+err:
+    qemu_set_fd_handler(u->slave_fd, NULL, NULL, NULL);
+    close(u->slave_fd);
+    u->slave_fd = -1;
+    return;
+}
+
+static int vhost_setup_slave_channel(struct vhost_dev *dev)
+{
+    VhostUserMsg msg = {
+        .request = VHOST_USER_SET_SLAVE_REQ_FD,
+        .flags = VHOST_USER_VERSION,
+    };
+    struct vhost_user *u = dev->opaque;
+    int sv[2];
+    bool reply_supported = virtio_has_feature(dev->protocol_features,
+                                              VHOST_USER_PROTOCOL_F_REPLY_ACK);
+
+    if (!virtio_has_feature(dev->protocol_features,
+                            VHOST_USER_PROTOCOL_F_SLAVE_REQ)) {
+        return 0;
+    }
+
+    if (socketpair(PF_UNIX, SOCK_STREAM, 0, sv) == -1) {
+        error_report("socketpair() failed");
+        return -1;
+    }
+
+    u->slave_fd = sv[0];
+    qemu_set_fd_handler(u->slave_fd, slave_read, NULL, dev);
+
+    if (reply_supported) {
+        msg.flags |= VHOST_USER_NEED_REPLY_MASK;
+    }
+
+    vhost_user_write(dev, &msg, &sv[1], 1);
+
+    if (reply_supported) {
+        return process_message_reply(dev, msg.request);
+    }
+
+    return 0;
+}
+
 static int vhost_user_init(struct vhost_dev *dev, void *opaque)
 {
     uint64_t features;
@@ -584,6 +690,7 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque)
 
     u = g_new0(struct vhost_user, 1);
     u->chr = opaque;
+    u->slave_fd = -1;
     dev->opaque = u;
 
     err = vhost_user_get_features(dev, &features);
@@ -624,6 +731,12 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque)
                    "VHOST_USER_PROTOCOL_F_LOG_SHMFD feature.");
     }
 
+
+    err = vhost_setup_slave_channel(dev);
+    if (err < 0) {
+        return err;
+    }
+
     return 0;
 }
 
@@ -634,6 +747,10 @@ static int vhost_user_cleanup(struct vhost_dev *dev)
     assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
 
     u = dev->opaque;
+    if (u->slave_fd >= 0) {
+        close(u->slave_fd);
+        u->slave_fd = -1;
+    }
     g_free(u);
     dev->opaque = 0;
 
-- 
2.9.3