virtio, vhost, pc fixes for 2.4

The only notable thing here is vhost-user multiqueue
 revert. We'll work on making it stable in 2.5,
 reverting now means we won't have to maintain
 bug for bug compability forever.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQEcBAABAgAGBQJVrNpQAAoJECgfDbjSjVRp5EwH/jh1iiTG4iXDbSnxPJ/FWwJt
 9hgd+GeNT9K5Dc1A+X6d80OdeaH5bjFNqfUXSrIsLKDWYtj01AU2+dgGS3j0/Uv1
 FRrrWsnN5idcYuqlznk7X9Eu2mb7npGZnjF4PmDU5Hq5eRj/mgJbWvKYqMolLYtv
 cuSHxhbA3dlUTIjfXccMF94kvFQUpfs2A3ip9osmCKE15fDS2zXKT3mIj/itnj3o
 DFRwkmiKYJwwi9cl7F2svzYnqp00mAMaVJ3UrzYFZhPylzWQfIJCgu47PMfGsJAx
 kPvY+IA3WEk0sMTVRNSWj61QNax4G/oM8d4ipnRpt3k0UzWg1XNTZkRIAg40j8A=
 =SW7Q
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

virtio, vhost, pc fixes for 2.4

The only notable thing here is vhost-user multiqueue
revert. We'll work on making it stable in 2.5,
reverting now means we won't have to maintain
bug for bug compability forever.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Mon Jul 20 12:24:00 2015 BST using RSA key ID D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"

* remotes/mst/tags/for_upstream:
  virtio-net: remove virtio queues if the guest doesn't support multiqueue
  virtio-net: Flush incoming queues when DRIVER_OK is being set
  pci_add_capability: remove duplicate comments
  virtio-net: unbreak any layout
  Revert "vhost-user: add multi queue support"
  ich9: fix skipped vmstate_memhp_state subsection

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

docs/specs/vhost-user.txt

@@ -127,11 +127,6 @@ in the ancillary data:
 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.
 
-Multi queue support
--------------------
-The protocol supports multiple queues by setting all index fields in the sent
-messages to a properly calculated value.
-
 Message types
 -------------
 

hw/acpi/ich9.c

@@ -206,9 +206,6 @@ const VMStateDescription vmstate_ich9_pm = {
     },
     .subsections = (const VMStateDescription*[]) {
         &vmstate_memhp_state,
-        NULL
-    },
-    .subsections = (const VMStateDescription*[]) {
         &vmstate_tco_io_state,
         NULL
     }

hw/net/vhost_net.c

@@ -160,7 +160,6 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options)
 
     net->dev.nvqs = 2;
     net->dev.vqs = net->vqs;
-    net->dev.vq_index = net->nc->queue_index;
 
     r = vhost_dev_init(&net->dev, options->opaque,
                        options->backend_type);
@@ -287,7 +286,7 @@ static void vhost_net_stop_one(struct vhost_net *net,
         for (file.index = 0; file.index < net->dev.nvqs; ++file.index) {
             const VhostOps *vhost_ops = net->dev.vhost_ops;
             int r = vhost_ops->vhost_call(&net->dev, VHOST_RESET_OWNER,
-                                          &file);
+                                          NULL);
             assert(r >= 0);
         }
     }

hw/net/virtio-net.c

@@ -162,6 +162,8 @@ static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
     virtio_net_vhost_status(n, status);
 
     for (i = 0; i < n->max_queues; i++) {
+        NetClientState *ncs = qemu_get_subqueue(n->nic, i);
+        bool queue_started;
         q = &n->vqs[i];
 
         if ((!n->multiqueue && i != 0) || i >= n->curr_queues) {
@@ -169,12 +171,18 @@ static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
         } else {
             queue_status = status;
         }
+        queue_started =
+            virtio_net_started(n, queue_status) && !n->vhost_started;
+
+        if (queue_started) {
+            qemu_flush_queued_packets(ncs);
+        }
 
         if (!q->tx_waiting) {
             continue;
         }
 
-        if (virtio_net_started(n, queue_status) && !n->vhost_started) {
+        if (queue_started) {
             if (q->tx_timer) {
                 timer_mod(q->tx_timer,
                                qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + n->tx_timeout);
@@ -1142,7 +1150,8 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
         ssize_t ret, len;
         unsigned int out_num = elem.out_num;
         struct iovec *out_sg = &elem.out_sg[0];
-        struct iovec sg[VIRTQUEUE_MAX_SIZE];
+        struct iovec sg[VIRTQUEUE_MAX_SIZE], sg2[VIRTQUEUE_MAX_SIZE + 1];
+        struct virtio_net_hdr_mrg_rxbuf mhdr;
 
         if (out_num < 1) {
             error_report("virtio-net header not in first element");
@@ -1150,13 +1159,25 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
         }
 
         if (n->has_vnet_hdr) {
-            if (out_sg[0].iov_len < n->guest_hdr_len) {
+            if (iov_to_buf(out_sg, out_num, 0, &mhdr, n->guest_hdr_len) <
+                n->guest_hdr_len) {
                 error_report("virtio-net header incorrect");
                 exit(1);
             }
-            virtio_net_hdr_swap(vdev, (void *) out_sg[0].iov_base);
+            if (virtio_needs_swap(vdev)) {
+                virtio_net_hdr_swap(vdev, (void *) &mhdr);
+                sg2[0].iov_base = &mhdr;
+                sg2[0].iov_len = n->guest_hdr_len;
+                out_num = iov_copy(&sg2[1], ARRAY_SIZE(sg2) - 1,
+                                   out_sg, out_num,
+                                   n->guest_hdr_len, -1);
+                if (out_num == VIRTQUEUE_MAX_SIZE) {
+                    goto drop;
+		}
+                out_num += 1;
+                out_sg = sg2;
+	    }
         }
-
         /*
          * If host wants to see the guest header as is, we can
          * pass it on unchanged. Otherwise, copy just the parts
@@ -1186,7 +1207,7 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
         }
 
         len += ret;
-
+drop:
         virtqueue_push(q->tx_vq, &elem, 0);
         virtio_notify(vdev, q->tx_vq);
 
@@ -1306,9 +1327,86 @@ static void virtio_net_tx_bh(void *opaque)
     }
 }
 
+static void virtio_net_add_queue(VirtIONet *n, int index)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(n);
+
+    n->vqs[index].rx_vq = virtio_add_queue(vdev, 256, virtio_net_handle_rx);
+    if (n->net_conf.tx && !strcmp(n->net_conf.tx, "timer")) {
+        n->vqs[index].tx_vq =
+            virtio_add_queue(vdev, 256, virtio_net_handle_tx_timer);
+        n->vqs[index].tx_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
+                                              virtio_net_tx_timer,
+                                              &n->vqs[index]);
+    } else {
+        n->vqs[index].tx_vq =
+            virtio_add_queue(vdev, 256, virtio_net_handle_tx_bh);
+        n->vqs[index].tx_bh = qemu_bh_new(virtio_net_tx_bh, &n->vqs[index]);
+    }
+
+    n->vqs[index].tx_waiting = 0;
+    n->vqs[index].n = n;
+}
+
+static void virtio_net_del_queue(VirtIONet *n, int index)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(n);
+    VirtIONetQueue *q = &n->vqs[index];
+    NetClientState *nc = qemu_get_subqueue(n->nic, index);
+
+    qemu_purge_queued_packets(nc);
+
+    virtio_del_queue(vdev, index * 2);
+    if (q->tx_timer) {
+        timer_del(q->tx_timer);
+        timer_free(q->tx_timer);
+    } else {
+        qemu_bh_delete(q->tx_bh);
+    }
+    virtio_del_queue(vdev, index * 2 + 1);
+}
+
+static void virtio_net_change_num_queues(VirtIONet *n, int new_max_queues)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(n);
+    int old_num_queues = virtio_get_num_queues(vdev);
+    int new_num_queues = new_max_queues * 2 + 1;
+    int i;
+
+    assert(old_num_queues >= 3);
+    assert(old_num_queues % 2 == 1);
+
+    if (old_num_queues == new_num_queues) {
+        return;
+    }
+
+    /*
+     * We always need to remove and add ctrl vq if
+     * old_num_queues != new_num_queues. Remove ctrl_vq first,
+     * and then we only enter one of the following too loops.
+     */
+    virtio_del_queue(vdev, old_num_queues - 1);
+
+    for (i = new_num_queues - 1; i < old_num_queues - 1; i += 2) {
+        /* new_num_queues < old_num_queues */
+        virtio_net_del_queue(n, i / 2);
+    }
+
+    for (i = old_num_queues - 1; i < new_num_queues - 1; i += 2) {
+        /* new_num_queues > old_num_queues */
+        virtio_net_add_queue(n, i / 2);
+    }
+
+    /* add ctrl_vq last */
+    n->ctrl_vq = virtio_add_queue(vdev, 64, virtio_net_handle_ctrl);
+}
+
 static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue)
 {
+    int max = multiqueue ? n->max_queues : 1;
+
     n->multiqueue = multiqueue;
+    virtio_net_change_num_queues(n, max);
 
     virtio_net_set_queues(n);
 }
@@ -1583,21 +1681,7 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
     }
 
     for (i = 0; i < n->max_queues; i++) {
-        n->vqs[i].rx_vq = virtio_add_queue(vdev, 256, virtio_net_handle_rx);
+        virtio_net_add_queue(n, i);
-        if (n->net_conf.tx && !strcmp(n->net_conf.tx, "timer")) {
-            n->vqs[i].tx_vq =
-                virtio_add_queue(vdev, 256, virtio_net_handle_tx_timer);
-            n->vqs[i].tx_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
-                                              virtio_net_tx_timer,
-                                              &n->vqs[i]);
-        } else {
-            n->vqs[i].tx_vq =
-                virtio_add_queue(vdev, 256, virtio_net_handle_tx_bh);
-            n->vqs[i].tx_bh = qemu_bh_new(virtio_net_tx_bh, &n->vqs[i]);
-        }
-
-        n->vqs[i].tx_waiting = 0;
-        n->vqs[i].n = n;
     }
 
     n->ctrl_vq = virtio_add_queue(vdev, 64, virtio_net_handle_ctrl);
@@ -1651,7 +1735,7 @@ static void virtio_net_device_unrealize(DeviceState *dev, Error **errp)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
     VirtIONet *n = VIRTIO_NET(dev);
-    int i;
+    int i, max_queues;
 
     /* This will stop vhost backend if appropriate. */
     virtio_net_set_status(vdev, 0);
@@ -1666,18 +1750,9 @@ static void virtio_net_device_unrealize(DeviceState *dev, Error **errp)
     g_free(n->mac_table.macs);
     g_free(n->vlans);
 
-    for (i = 0; i < n->max_queues; i++) {
+    max_queues = n->multiqueue ? n->max_queues : 1;
-        VirtIONetQueue *q = &n->vqs[i];
+    for (i = 0; i < max_queues; i++) {
-        NetClientState *nc = qemu_get_subqueue(n->nic, i);
+        virtio_net_del_queue(n, i);
-
-        qemu_purge_queued_packets(nc);
-
-        if (q->tx_timer) {
-            timer_del(q->tx_timer);
-            timer_free(q->tx_timer);
-        } else if (q->tx_bh) {
-            qemu_bh_delete(q->tx_bh);
-        }
     }
 
     timer_del(n->announce_timer);

hw/pci/pci.c

@@ -2101,12 +2101,10 @@ static void pci_del_option_rom(PCIDevice *pdev)
 }
 
 /*
- * if !offset
- * Reserve space and add capability to the linked list in pci config space
- *
  * if offset = 0,
  * Find and reserve space and add capability to the linked list
- * in pci config space */
+ * in pci config space
+ */
 int pci_add_capability(PCIDevice *pdev, uint8_t cap_id,
                        uint8_t offset, uint8_t size)
 {

hw/virtio/vhost-user.c

@@ -210,12 +210,7 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
         break;
 
     case VHOST_SET_OWNER:
-        break;
-
     case VHOST_RESET_OWNER:
-        memcpy(&msg.state, arg, sizeof(struct vhost_vring_state));
-        msg.state.index += dev->vq_index;
-        msg.size = sizeof(m.state);
         break;
 
     case VHOST_SET_MEM_TABLE:
@@ -258,20 +253,17 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
     case VHOST_SET_VRING_NUM:
     case VHOST_SET_VRING_BASE:
         memcpy(&msg.state, arg, sizeof(struct vhost_vring_state));
-        msg.state.index += dev->vq_index;
         msg.size = sizeof(m.state);
         break;
 
     case VHOST_GET_VRING_BASE:
         memcpy(&msg.state, arg, sizeof(struct vhost_vring_state));
-        msg.state.index += dev->vq_index;
         msg.size = sizeof(m.state);
         need_reply = 1;
         break;
 
     case VHOST_SET_VRING_ADDR:
         memcpy(&msg.addr, arg, sizeof(struct vhost_vring_addr));
-        msg.addr.index += dev->vq_index;
         msg.size = sizeof(m.addr);
         break;
 
@@ -279,7 +271,7 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
     case VHOST_SET_VRING_CALL:
     case VHOST_SET_VRING_ERR:
         file = arg;
-        msg.u64 = (file->index + dev->vq_index) & VHOST_USER_VRING_IDX_MASK;
+        msg.u64 = file->index & VHOST_USER_VRING_IDX_MASK;
         msg.size = sizeof(m.u64);
         if (ioeventfd_enabled() && file->fd > 0) {
             fds[fd_num++] = file->fd;
@@ -321,7 +313,6 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
                 error_report("Received bad msg size.");
                 return -1;
             }
-            msg.state.index -= dev->vq_index;
             memcpy(arg, &msg.state, sizeof(struct vhost_vring_state));
             break;
         default:

include/hw/virtio/virtio-access.h

@@ -143,6 +143,15 @@ static inline uint64_t virtio_ldq_p(VirtIODevice *vdev, const void *ptr)
     }
 }
 
+static inline bool virtio_needs_swap(VirtIODevice *vdev)
+{
+#ifdef HOST_WORDS_BIGENDIAN
+    return virtio_access_is_big_endian(vdev) ? false : true;
+#else
+    return virtio_access_is_big_endian(vdev) ? true : false;
+#endif
+}
+
 static inline uint16_t virtio_tswap16(VirtIODevice *vdev, uint16_t s)
 {
 #ifdef HOST_WORDS_BIGENDIAN

net/vhost-user.c

@@ -120,39 +120,35 @@ static void net_vhost_user_event(void *opaque, int event)
     case CHR_EVENT_OPENED:
         vhost_user_start(s);
         net_vhost_link_down(s, false);
-        error_report("chardev \"%s\" went up", s->nc.info_str);
+        error_report("chardev \"%s\" went up", s->chr->label);
         break;
     case CHR_EVENT_CLOSED:
         net_vhost_link_down(s, true);
         vhost_user_stop(s);
-        error_report("chardev \"%s\" went down", s->nc.info_str);
+        error_report("chardev \"%s\" went down", s->chr->label);
         break;
     }
 }
 
 static int net_vhost_user_init(NetClientState *peer, const char *device,
-                               const char *name, CharDriverState *chr,
+                               const char *name, CharDriverState *chr)
-                               uint32_t queues)
 {
     NetClientState *nc;
     VhostUserState *s;
-    int i;
 
-    for (i = 0; i < queues; i++) {
+    nc = qemu_new_net_client(&net_vhost_user_info, peer, device, name);
-        nc = qemu_new_net_client(&net_vhost_user_info, peer, device, name);
 
-        snprintf(nc->info_str, sizeof(nc->info_str), "vhost-user%d to %s",
+    snprintf(nc->info_str, sizeof(nc->info_str), "vhost-user to %s",
-                 i, chr->label);
+             chr->label);
 
-        s = DO_UPCAST(VhostUserState, nc, nc);
+    s = DO_UPCAST(VhostUserState, nc, nc);
 
-        /* We don't provide a receive callback */
+    /* We don't provide a receive callback */
-        s->nc.receive_disabled = 1;
+    s->nc.receive_disabled = 1;
-        s->chr = chr;
+    s->chr = chr;
-        s->nc.queue_index = i;
+
+    qemu_chr_add_handlers(s->chr, NULL, NULL, net_vhost_user_event, s);
 
-        qemu_chr_add_handlers(s->chr, NULL, NULL, net_vhost_user_event, s);
-    }
     return 0;
 }
 
@@ -230,7 +226,6 @@ static int net_vhost_check_net(void *opaque, QemuOpts *opts, Error **errp)
 int net_init_vhost_user(const NetClientOptions *opts, const char *name,
                         NetClientState *peer, Error **errp)
 {
-    uint32_t queues;
     const NetdevVhostUserOptions *vhost_user_opts;
     CharDriverState *chr;
 
@@ -248,12 +243,6 @@ int net_init_vhost_user(const NetClientOptions *opts, const char *name,
         return -1;
     }
 
-    /* number of queues for multiqueue */
-    if (vhost_user_opts->has_queues) {
-        queues = vhost_user_opts->queues;
-    } else {
-        queues = 1;
-    }
 
-    return net_vhost_user_init(peer, "vhost_user", name, chr, queues);
+    return net_vhost_user_init(peer, "vhost_user", name, chr);
 }

qapi-schema.json

@@ -2466,16 +2466,12 @@
 #
 # @vhostforce: #optional vhost on for non-MSIX virtio guests (default: false).
 #
-# @queues: #optional number of queues to be created for multiqueue vhost-user
-#          (default: 1) (Since 2.4)
-#
 # Since 2.1
 ##
 { 'struct': 'NetdevVhostUserOptions',
   'data': {
     'chardev':        'str',
-    '*vhostforce':    'bool',
+    '*vhostforce':    'bool' } }
-    '*queues':        'uint32' } }
 
 ##
 # @NetClientOptions

qemu-options.hx

@@ -1963,14 +1963,13 @@ The hubport netdev lets you connect a NIC to a QEMU "vlan" instead of a single
 netdev.  @code{-net} and @code{-device} with parameter @option{vlan} create the
 required hub automatically.
 
-@item -netdev vhost-user,chardev=@var{id}[,vhostforce=on|off][,queues=n]
+@item -netdev vhost-user,chardev=@var{id}[,vhostforce=on|off]
 
 Establish a vhost-user netdev, backed by a chardev @var{id}. The chardev should
 be a unix domain socket backed one. The vhost-user uses a specifically defined
 protocol to pass vhost ioctl replacement messages to an application on the other
 end of the socket. On non-MSIX guests, the feature can be forced with
-@var{vhostforce}. Use 'queues=@var{n}' to specify the number of queues to
+@var{vhostforce}.
-be created for multiqueue vhost-user.
 
 Example:
 @example