Re: [Qemu-devel] [PATCH v4] vhost-user: add multi queue support

[Michael S. Tsirkin]

On Fri, May 22, 2015 at 01:58:04PM +0800, Ouyang Changchun wrote:
> Based on patch by Nikolay Nikolaev:
> Vhost-user will implement the multi queue support in a similar way
> to what vhost already has - a separate thread for each queue.
> To enable the multi queue functionality - a new command line parameter
> "queues" is introduced for the vhost-user netdev.
> 
> Signed-off-by: Nikolay Nikolaev <address@hidden>
> Signed-off-by: Changchun Ouyang <address@hidden>

Looks good to me, but I have a question, below.


> ---
> Changes since v3:
>  - fix one typo and wrap one long line
> 
> Changes since v2:
>  - fix vq index issue for set_vring_call
>    When it is the case of VHOST_SET_VRING_CALL, The vq_index is not 
> initialized before it is used,
>    thus it could be a random value. The random value leads to crash in vhost 
> after passing down
>    to vhost, as vhost use this random value to index an array index.
>  - fix the typo in the doc and description
>  - address vq index for reset_owner
> 
> Changes since v1:
>  - use s->nc.info_str when bringing up/down the backend
> 
>  docs/specs/vhost-user.txt |  5 +++++
>  hw/net/vhost_net.c        |  3 ++-
>  hw/virtio/vhost-user.c    | 11 ++++++++++-
>  net/vhost-user.c          | 37 ++++++++++++++++++++++++-------------
>  qapi-schema.json          |  6 +++++-
>  qemu-options.hx           |  5 +++--
>  6 files changed, 49 insertions(+), 18 deletions(-)
> 
> diff --git a/docs/specs/vhost-user.txt b/docs/specs/vhost-user.txt
> index 650bb18..2c8e934 100644
> --- a/docs/specs/vhost-user.txt
> +++ b/docs/specs/vhost-user.txt
> @@ -127,6 +127,11 @@ 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
>  -------------
>  
> diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c
> index 47f8b89..426b23e 100644
> --- a/hw/net/vhost_net.c
> +++ b/hw/net/vhost_net.c
> @@ -157,6 +157,7 @@ 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, options->force);
> @@ -267,7 +268,7 @@ 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,
> -                                          NULL);
> +                                          &file);
>              assert(r >= 0);
>          }
>      }
> diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
> index e7ab829..d6f2163 100644
> --- a/hw/virtio/vhost-user.c
> +++ b/hw/virtio/vhost-user.c
> @@ -210,7 +210,12 @@ 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:
> @@ -253,17 +258,20 @@ 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;
>  
> @@ -271,7 +279,7 @@ 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 & VHOST_USER_VRING_IDX_MASK;
> +        msg.u64 = (file->index + dev->vq_index) & VHOST_USER_VRING_IDX_MASK;
>          msg.size = sizeof(m.u64);
>          if (ioeventfd_enabled() && file->fd > 0) {
>              fds[fd_num++] = file->fd;
> @@ -313,6 +321,7 @@ 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:
> diff --git a/net/vhost-user.c b/net/vhost-user.c
> index 1d86a2b..41c8a27 100644
> --- a/net/vhost-user.c
> +++ b/net/vhost-user.c
> @@ -121,35 +121,39 @@ 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->chr->label);
> +        error_report("chardev \"%s\" went up\n", s->nc.info_str);
>          break;
>      case CHR_EVENT_CLOSED:
>          net_vhost_link_down(s, true);
>          vhost_user_stop(s);
> -        error_report("chardev \"%s\" went down", s->chr->label);
> +        error_report("chardev \"%s\" went down\n", s->nc.info_str);
>          break;
>      }
>  }
>  

Hmm should the trailing \n be there?

>  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;
>  
> -    nc = qemu_new_net_client(&net_vhost_user_info, peer, device, name);
> +    for (i = 0; i < queues; i++) {
> +        nc = qemu_new_net_client(&net_vhost_user_info, peer, device, name);
>  
> -    snprintf(nc->info_str, sizeof(nc->info_str), "vhost-user to %s",
> -             chr->label);
> +        snprintf(nc->info_str, sizeof(nc->info_str), "vhost-user%d to %s",
> +                 i, chr->label);
>  
> -    s = DO_UPCAST(VhostUserState, nc, nc);
> +        s = DO_UPCAST(VhostUserState, nc, nc);
>  
> -    /* We don't provide a receive callback */
> -    s->nc.receive_disabled = 1;
> -    s->chr = chr;
> -
> -    qemu_chr_add_handlers(s->chr, NULL, NULL, net_vhost_user_event, s);
> +        /* We don't provide a receive callback */
> +        s->nc.receive_disabled = 1;
> +        s->chr = chr;
> +        s->nc.queue_index = i;
>  
> +        qemu_chr_add_handlers(s->chr, NULL, NULL, net_vhost_user_event, s);
> +    }
>      return 0;
>  }
>  
> @@ -225,6 +229,7 @@ static int net_vhost_check_net(QemuOpts *opts, void 
> *opaque)
>  int net_init_vhost_user(const NetClientOptions *opts, const char *name,
>                          NetClientState *peer)
>  {
> +    uint32_t queues;
>      const NetdevVhostUserOptions *vhost_user_opts;
>      CharDriverState *chr;
>  
> @@ -243,6 +248,12 @@ 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);
> +    return net_vhost_user_init(peer, "vhost_user", name, chr, queues);
>  }
> diff --git a/qapi-schema.json b/qapi-schema.json
> index f97ffa1..00791dd 100644
> --- a/qapi-schema.json
> +++ b/qapi-schema.json
> @@ -2444,12 +2444,16 @@
>  #
>  # @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
> diff --git a/qemu-options.hx b/qemu-options.hx
> index ec356f6..dad035e 100644
> --- a/qemu-options.hx
> +++ b/qemu-options.hx
> @@ -1942,13 +1942,14 @@ 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.
>  
> address@hidden -netdev vhost-user,address@hidden,vhostforce=on|off]
> address@hidden -netdev vhost-user,address@hidden,vhostforce=on|off][,queues=n]
>  
>  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
> address@hidden
> address@hidden Use 'address@hidden' to specify the number of queues to
> +be created for multiqueue vhost-user.
>  
>  Example:
>  @example
> -- 
> 1.8.4.2
>