diff options
Diffstat (limited to 'net/vhost-vdpa.c')
| -rw-r--r-- | net/vhost-vdpa.c | 381 |
1 files changed, 246 insertions, 135 deletions
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c index 939c984d5b..7a226c93bc 100644 --- a/net/vhost-vdpa.c +++ b/net/vhost-vdpa.c @@ -339,7 +339,8 @@ static void vhost_vdpa_net_data_start_first(VhostVDPAState *s) { struct vhost_vdpa *v = &s->vhost_vdpa; - add_migration_state_change_notifier(&s->migration_state); + migration_add_notifier(&s->migration_state, + vdpa_net_migration_state_notifier); if (v->shadow_vqs_enabled) { v->iova_tree = vhost_iova_tree_new(v->iova_range.first, v->iova_range.last); @@ -399,7 +400,7 @@ static void vhost_vdpa_net_client_stop(NetClientState *nc) assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA); if (s->vhost_vdpa.index == 0) { - remove_migration_state_change_notifier(&s->migration_state); + migration_remove_notifier(&s->migration_state); } dev = s->vhost_vdpa.dev; @@ -618,39 +619,77 @@ static void vhost_vdpa_net_cvq_stop(NetClientState *nc) vhost_vdpa_net_client_stop(nc); } -static ssize_t vhost_vdpa_net_cvq_add(VhostVDPAState *s, size_t out_len, - size_t in_len) +static ssize_t vhost_vdpa_net_cvq_add(VhostVDPAState *s, + const struct iovec *out_sg, size_t out_num, + const struct iovec *in_sg, size_t in_num) { - /* Buffers for the device */ - const struct iovec out = { - .iov_base = s->cvq_cmd_out_buffer, - .iov_len = out_len, - }; - const struct iovec in = { - .iov_base = s->status, - .iov_len = sizeof(virtio_net_ctrl_ack), - }; VhostShadowVirtqueue *svq = g_ptr_array_index(s->vhost_vdpa.shadow_vqs, 0); int r; - r = vhost_svq_add(svq, &out, 1, &in, 1, NULL); + r = vhost_svq_add(svq, out_sg, out_num, in_sg, in_num, NULL); if (unlikely(r != 0)) { if (unlikely(r == -ENOSPC)) { qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n", __func__); } - return r; } - /* - * We can poll here since we've had BQL from the time we sent the - * descriptor. Also, we need to take the answer before SVQ pulls by itself, - * when BQL is released - */ - return vhost_svq_poll(svq, 1); + return r; +} + +/* + * Convenience wrapper to poll SVQ for multiple control commands. + * + * Caller should hold the BQL when invoking this function, and should take + * the answer before SVQ pulls by itself when BQL is released. + */ +static ssize_t vhost_vdpa_net_svq_poll(VhostVDPAState *s, size_t cmds_in_flight) +{ + VhostShadowVirtqueue *svq = g_ptr_array_index(s->vhost_vdpa.shadow_vqs, 0); + return vhost_svq_poll(svq, cmds_in_flight); +} + +static void vhost_vdpa_net_load_cursor_reset(VhostVDPAState *s, + struct iovec *out_cursor, + struct iovec *in_cursor) +{ + /* reset the cursor of the output buffer for the device */ + out_cursor->iov_base = s->cvq_cmd_out_buffer; + out_cursor->iov_len = vhost_vdpa_net_cvq_cmd_page_len(); + + /* reset the cursor of the in buffer for the device */ + in_cursor->iov_base = s->status; + in_cursor->iov_len = vhost_vdpa_net_cvq_cmd_page_len(); +} + +/* + * Poll SVQ for multiple pending control commands and check the device's ack. + * + * Caller should hold the BQL when invoking this function. + * + * @s: The VhostVDPAState + * @len: The length of the pending status shadow buffer + */ +static ssize_t vhost_vdpa_net_svq_flush(VhostVDPAState *s, size_t len) +{ + /* device uses a one-byte length ack for each control command */ + ssize_t dev_written = vhost_vdpa_net_svq_poll(s, len); + if (unlikely(dev_written != len)) { + return -EIO; + } + + /* check the device's ack */ + for (int i = 0; i < len; ++i) { + if (s->status[i] != VIRTIO_NET_OK) { + return -EIO; + } + } + return 0; } -static ssize_t vhost_vdpa_net_load_cmd(VhostVDPAState *s, uint8_t class, +static ssize_t vhost_vdpa_net_load_cmd(VhostVDPAState *s, + struct iovec *out_cursor, + struct iovec *in_cursor, uint8_t class, uint8_t cmd, const struct iovec *data_sg, size_t data_num) { @@ -658,36 +697,72 @@ static ssize_t vhost_vdpa_net_load_cmd(VhostVDPAState *s, uint8_t class, .class = class, .cmd = cmd, }; - size_t data_size = iov_size(data_sg, data_num); + size_t data_size = iov_size(data_sg, data_num), cmd_size; + struct iovec out, in; + ssize_t r; + unsigned dummy_cursor_iov_cnt; + VhostShadowVirtqueue *svq = g_ptr_array_index(s->vhost_vdpa.shadow_vqs, 0); assert(data_size < vhost_vdpa_net_cvq_cmd_page_len() - sizeof(ctrl)); + cmd_size = sizeof(ctrl) + data_size; + if (vhost_svq_available_slots(svq) < 2 || + iov_size(out_cursor, 1) < cmd_size) { + /* + * It is time to flush all pending control commands if SVQ is full + * or control commands shadow buffers are full. + * + * We can poll here since we've had BQL from the time + * we sent the descriptor. + */ + r = vhost_vdpa_net_svq_flush(s, in_cursor->iov_base - + (void *)s->status); + if (unlikely(r < 0)) { + return r; + } - /* pack the CVQ command header */ - memcpy(s->cvq_cmd_out_buffer, &ctrl, sizeof(ctrl)); + vhost_vdpa_net_load_cursor_reset(s, out_cursor, in_cursor); + } + /* pack the CVQ command header */ + iov_from_buf(out_cursor, 1, 0, &ctrl, sizeof(ctrl)); /* pack the CVQ command command-specific-data */ iov_to_buf(data_sg, data_num, 0, - s->cvq_cmd_out_buffer + sizeof(ctrl), data_size); + out_cursor->iov_base + sizeof(ctrl), data_size); + + /* extract the required buffer from the cursor for output */ + iov_copy(&out, 1, out_cursor, 1, 0, cmd_size); + /* extract the required buffer from the cursor for input */ + iov_copy(&in, 1, in_cursor, 1, 0, sizeof(*s->status)); + + r = vhost_vdpa_net_cvq_add(s, &out, 1, &in, 1); + if (unlikely(r < 0)) { + return r; + } + + /* iterate the cursors */ + dummy_cursor_iov_cnt = 1; + iov_discard_front(&out_cursor, &dummy_cursor_iov_cnt, cmd_size); + dummy_cursor_iov_cnt = 1; + iov_discard_front(&in_cursor, &dummy_cursor_iov_cnt, sizeof(*s->status)); - return vhost_vdpa_net_cvq_add(s, data_size + sizeof(ctrl), - sizeof(virtio_net_ctrl_ack)); + return 0; } -static int vhost_vdpa_net_load_mac(VhostVDPAState *s, const VirtIONet *n) +static int vhost_vdpa_net_load_mac(VhostVDPAState *s, const VirtIONet *n, + struct iovec *out_cursor, + struct iovec *in_cursor) { if (virtio_vdev_has_feature(&n->parent_obj, VIRTIO_NET_F_CTRL_MAC_ADDR)) { const struct iovec data = { .iov_base = (void *)n->mac, .iov_len = sizeof(n->mac), }; - ssize_t dev_written = vhost_vdpa_net_load_cmd(s, VIRTIO_NET_CTRL_MAC, - VIRTIO_NET_CTRL_MAC_ADDR_SET, - &data, 1); - if (unlikely(dev_written < 0)) { - return dev_written; - } - if (*s->status != VIRTIO_NET_OK) { - return -EIO; + ssize_t r = vhost_vdpa_net_load_cmd(s, out_cursor, in_cursor, + VIRTIO_NET_CTRL_MAC, + VIRTIO_NET_CTRL_MAC_ADDR_SET, + &data, 1); + if (unlikely(r < 0)) { + return r; } } @@ -732,25 +807,24 @@ static int vhost_vdpa_net_load_mac(VhostVDPAState *s, const VirtIONet *n) .iov_len = mul_macs_size, }, }; - ssize_t dev_written = vhost_vdpa_net_load_cmd(s, - VIRTIO_NET_CTRL_MAC, - VIRTIO_NET_CTRL_MAC_TABLE_SET, - data, ARRAY_SIZE(data)); - if (unlikely(dev_written < 0)) { - return dev_written; - } - if (*s->status != VIRTIO_NET_OK) { - return -EIO; + ssize_t r = vhost_vdpa_net_load_cmd(s, out_cursor, in_cursor, + VIRTIO_NET_CTRL_MAC, + VIRTIO_NET_CTRL_MAC_TABLE_SET, + data, ARRAY_SIZE(data)); + if (unlikely(r < 0)) { + return r; } return 0; } static int vhost_vdpa_net_load_mq(VhostVDPAState *s, - const VirtIONet *n) + const VirtIONet *n, + struct iovec *out_cursor, + struct iovec *in_cursor) { struct virtio_net_ctrl_mq mq; - ssize_t dev_written; + ssize_t r; if (!virtio_vdev_has_feature(&n->parent_obj, VIRTIO_NET_F_MQ)) { return 0; @@ -761,24 +835,24 @@ static int vhost_vdpa_net_load_mq(VhostVDPAState *s, .iov_base = &mq, .iov_len = sizeof(mq), }; - dev_written = vhost_vdpa_net_load_cmd(s, VIRTIO_NET_CTRL_MQ, - VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, - &data, 1); - if (unlikely(dev_written < 0)) { - return dev_written; - } - if (*s->status != VIRTIO_NET_OK) { - return -EIO; + r = vhost_vdpa_net_load_cmd(s, out_cursor, in_cursor, + VIRTIO_NET_CTRL_MQ, + VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, + &data, 1); + if (unlikely(r < 0)) { + return r; } return 0; } static int vhost_vdpa_net_load_offloads(VhostVDPAState *s, - const VirtIONet *n) + const VirtIONet *n, + struct iovec *out_cursor, + struct iovec *in_cursor) { uint64_t offloads; - ssize_t dev_written; + ssize_t r; if (!virtio_vdev_has_feature(&n->parent_obj, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) { @@ -806,20 +880,20 @@ static int vhost_vdpa_net_load_offloads(VhostVDPAState *s, .iov_base = &offloads, .iov_len = sizeof(offloads), }; - dev_written = vhost_vdpa_net_load_cmd(s, VIRTIO_NET_CTRL_GUEST_OFFLOADS, - VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET, - &data, 1); - if (unlikely(dev_written < 0)) { - return dev_written; - } - if (*s->status != VIRTIO_NET_OK) { - return -EIO; + r = vhost_vdpa_net_load_cmd(s, out_cursor, in_cursor, + VIRTIO_NET_CTRL_GUEST_OFFLOADS, + VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET, + &data, 1); + if (unlikely(r < 0)) { + return r; } return 0; } static int vhost_vdpa_net_load_rx_mode(VhostVDPAState *s, + struct iovec *out_cursor, + struct iovec *in_cursor, uint8_t cmd, uint8_t on) { @@ -827,14 +901,23 @@ static int vhost_vdpa_net_load_rx_mode(VhostVDPAState *s, .iov_base = &on, .iov_len = sizeof(on), }; - return vhost_vdpa_net_load_cmd(s, VIRTIO_NET_CTRL_RX, - cmd, &data, 1); + ssize_t r; + + r = vhost_vdpa_net_load_cmd(s, out_cursor, in_cursor, + VIRTIO_NET_CTRL_RX, cmd, &data, 1); + if (unlikely(r < 0)) { + return r; + } + + return 0; } static int vhost_vdpa_net_load_rx(VhostVDPAState *s, - const VirtIONet *n) + const VirtIONet *n, + struct iovec *out_cursor, + struct iovec *in_cursor) { - ssize_t dev_written; + ssize_t r; if (!virtio_vdev_has_feature(&n->parent_obj, VIRTIO_NET_F_CTRL_RX)) { return 0; @@ -859,13 +942,10 @@ static int vhost_vdpa_net_load_rx(VhostVDPAState *s, * configuration only at live migration. */ if (!n->mac_table.uni_overflow && !n->promisc) { - dev_written = vhost_vdpa_net_load_rx_mode(s, - VIRTIO_NET_CTRL_RX_PROMISC, 0); - if (unlikely(dev_written < 0)) { - return dev_written; - } - if (*s->status != VIRTIO_NET_OK) { - return -EIO; + r = vhost_vdpa_net_load_rx_mode(s, out_cursor, in_cursor, + VIRTIO_NET_CTRL_RX_PROMISC, 0); + if (unlikely(r < 0)) { + return r; } } @@ -887,13 +967,10 @@ static int vhost_vdpa_net_load_rx(VhostVDPAState *s, * configuration only at live migration. */ if (n->mac_table.multi_overflow || n->allmulti) { - dev_written = vhost_vdpa_net_load_rx_mode(s, - VIRTIO_NET_CTRL_RX_ALLMULTI, 1); - if (unlikely(dev_written < 0)) { - return dev_written; - } - if (*s->status != VIRTIO_NET_OK) { - return -EIO; + r = vhost_vdpa_net_load_rx_mode(s, out_cursor, in_cursor, + VIRTIO_NET_CTRL_RX_ALLMULTI, 1); + if (unlikely(r < 0)) { + return r; } } @@ -912,13 +989,10 @@ static int vhost_vdpa_net_load_rx(VhostVDPAState *s, * configuration only at live migration. */ if (n->alluni) { - dev_written = vhost_vdpa_net_load_rx_mode(s, - VIRTIO_NET_CTRL_RX_ALLUNI, 1); - if (dev_written < 0) { - return dev_written; - } - if (*s->status != VIRTIO_NET_OK) { - return -EIO; + r = vhost_vdpa_net_load_rx_mode(s, out_cursor, in_cursor, + VIRTIO_NET_CTRL_RX_ALLUNI, 1); + if (r < 0) { + return r; } } @@ -933,13 +1007,10 @@ static int vhost_vdpa_net_load_rx(VhostVDPAState *s, * configuration only at live migration. */ if (n->nomulti) { - dev_written = vhost_vdpa_net_load_rx_mode(s, - VIRTIO_NET_CTRL_RX_NOMULTI, 1); - if (dev_written < 0) { - return dev_written; - } - if (*s->status != VIRTIO_NET_OK) { - return -EIO; + r = vhost_vdpa_net_load_rx_mode(s, out_cursor, in_cursor, + VIRTIO_NET_CTRL_RX_NOMULTI, 1); + if (r < 0) { + return r; } } @@ -954,13 +1025,10 @@ static int vhost_vdpa_net_load_rx(VhostVDPAState *s, * configuration only at live migration. */ if (n->nouni) { - dev_written = vhost_vdpa_net_load_rx_mode(s, - VIRTIO_NET_CTRL_RX_NOUNI, 1); - if (dev_written < 0) { - return dev_written; - } - if (*s->status != VIRTIO_NET_OK) { - return -EIO; + r = vhost_vdpa_net_load_rx_mode(s, out_cursor, in_cursor, + VIRTIO_NET_CTRL_RX_NOUNI, 1); + if (r < 0) { + return r; } } @@ -975,13 +1043,10 @@ static int vhost_vdpa_net_load_rx(VhostVDPAState *s, * configuration only at live migration. */ if (n->nobcast) { - dev_written = vhost_vdpa_net_load_rx_mode(s, - VIRTIO_NET_CTRL_RX_NOBCAST, 1); - if (dev_written < 0) { - return dev_written; - } - if (*s->status != VIRTIO_NET_OK) { - return -EIO; + r = vhost_vdpa_net_load_rx_mode(s, out_cursor, in_cursor, + VIRTIO_NET_CTRL_RX_NOBCAST, 1); + if (r < 0) { + return r; } } @@ -990,27 +1055,29 @@ static int vhost_vdpa_net_load_rx(VhostVDPAState *s, static int vhost_vdpa_net_load_single_vlan(VhostVDPAState *s, const VirtIONet *n, + struct iovec *out_cursor, + struct iovec *in_cursor, uint16_t vid) { const struct iovec data = { .iov_base = &vid, .iov_len = sizeof(vid), }; - ssize_t dev_written = vhost_vdpa_net_load_cmd(s, VIRTIO_NET_CTRL_VLAN, - VIRTIO_NET_CTRL_VLAN_ADD, - &data, 1); - if (unlikely(dev_written < 0)) { - return dev_written; - } - if (unlikely(*s->status != VIRTIO_NET_OK)) { - return -EIO; + ssize_t r = vhost_vdpa_net_load_cmd(s, out_cursor, in_cursor, + VIRTIO_NET_CTRL_VLAN, + VIRTIO_NET_CTRL_VLAN_ADD, + &data, 1); + if (unlikely(r < 0)) { + return r; } return 0; } static int vhost_vdpa_net_load_vlan(VhostVDPAState *s, - const VirtIONet *n) + const VirtIONet *n, + struct iovec *out_cursor, + struct iovec *in_cursor) { int r; @@ -1021,7 +1088,8 @@ static int vhost_vdpa_net_load_vlan(VhostVDPAState *s, for (int i = 0; i < MAX_VLAN >> 5; i++) { for (int j = 0; n->vlans[i] && j <= 0x1f; j++) { if (n->vlans[i] & (1U << j)) { - r = vhost_vdpa_net_load_single_vlan(s, n, (i << 5) + j); + r = vhost_vdpa_net_load_single_vlan(s, n, out_cursor, + in_cursor, (i << 5) + j); if (unlikely(r != 0)) { return r; } @@ -1038,6 +1106,7 @@ static int vhost_vdpa_net_cvq_load(NetClientState *nc) struct vhost_vdpa *v = &s->vhost_vdpa; const VirtIONet *n; int r; + struct iovec out_cursor, in_cursor; assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA); @@ -1045,23 +1114,35 @@ static int vhost_vdpa_net_cvq_load(NetClientState *nc) if (v->shadow_vqs_enabled) { n = VIRTIO_NET(v->dev->vdev); - r = vhost_vdpa_net_load_mac(s, n); + vhost_vdpa_net_load_cursor_reset(s, &out_cursor, &in_cursor); + r = vhost_vdpa_net_load_mac(s, n, &out_cursor, &in_cursor); if (unlikely(r < 0)) { return r; } - r = vhost_vdpa_net_load_mq(s, n); + r = vhost_vdpa_net_load_mq(s, n, &out_cursor, &in_cursor); if (unlikely(r)) { return r; } - r = vhost_vdpa_net_load_offloads(s, n); + r = vhost_vdpa_net_load_offloads(s, n, &out_cursor, &in_cursor); if (unlikely(r)) { return r; } - r = vhost_vdpa_net_load_rx(s, n); + r = vhost_vdpa_net_load_rx(s, n, &out_cursor, &in_cursor); if (unlikely(r)) { return r; } - r = vhost_vdpa_net_load_vlan(s, n); + r = vhost_vdpa_net_load_vlan(s, n, &out_cursor, &in_cursor); + if (unlikely(r)) { + return r; + } + + /* + * We need to poll and check all pending device's used buffers. + * + * We can poll here since we've had BQL from the time + * we sent the descriptor. + */ + r = vhost_vdpa_net_svq_flush(s, in_cursor.iov_base - (void *)s->status); if (unlikely(r)) { return r; } @@ -1114,12 +1195,14 @@ static NetClientInfo net_vhost_vdpa_cvq_info = { */ static int vhost_vdpa_net_excessive_mac_filter_cvq_add(VhostVDPAState *s, VirtQueueElement *elem, - struct iovec *out) + struct iovec *out, + const struct iovec *in) { struct virtio_net_ctrl_mac mac_data, *mac_ptr; struct virtio_net_ctrl_hdr *hdr_ptr; uint32_t cursor; ssize_t r; + uint8_t on = 1; /* parse the non-multicast MAC address entries from CVQ command */ cursor = sizeof(*hdr_ptr); @@ -1167,10 +1250,25 @@ static int vhost_vdpa_net_excessive_mac_filter_cvq_add(VhostVDPAState *s, * filter table to the vdpa device, it should send the * VIRTIO_NET_CTRL_RX_PROMISC CVQ command to enable promiscuous mode */ - r = vhost_vdpa_net_load_rx_mode(s, VIRTIO_NET_CTRL_RX_PROMISC, 1); + hdr_ptr = out->iov_base; + out->iov_len = sizeof(*hdr_ptr) + sizeof(on); + + hdr_ptr->class = VIRTIO_NET_CTRL_RX; + hdr_ptr->cmd = VIRTIO_NET_CTRL_RX_PROMISC; + iov_from_buf(out, 1, sizeof(*hdr_ptr), &on, sizeof(on)); + r = vhost_vdpa_net_cvq_add(s, out, 1, in, 1); if (unlikely(r < 0)) { return r; } + + /* + * We can poll here since we've had BQL from the time + * we sent the descriptor. + */ + r = vhost_vdpa_net_svq_poll(s, 1); + if (unlikely(r < sizeof(*s->status))) { + return r; + } if (*s->status != VIRTIO_NET_OK) { return sizeof(*s->status); } @@ -1248,10 +1346,15 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, .iov_base = s->cvq_cmd_out_buffer, }; /* in buffer used for device model */ - const struct iovec in = { + const struct iovec model_in = { .iov_base = &status, .iov_len = sizeof(status), }; + /* in buffer used for vdpa device */ + const struct iovec vdpa_in = { + .iov_base = s->status, + .iov_len = sizeof(*s->status), + }; ssize_t dev_written = -EINVAL; out.iov_len = iov_to_buf(elem->out_sg, elem->out_num, 0, @@ -1280,15 +1383,23 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, * the CVQ command directly. */ dev_written = vhost_vdpa_net_excessive_mac_filter_cvq_add(s, elem, - &out); + &out, &vdpa_in); if (unlikely(dev_written < 0)) { goto out; } } else { - dev_written = vhost_vdpa_net_cvq_add(s, out.iov_len, sizeof(status)); - if (unlikely(dev_written < 0)) { + ssize_t r; + r = vhost_vdpa_net_cvq_add(s, &out, 1, &vdpa_in, 1); + if (unlikely(r < 0)) { + dev_written = r; goto out; } + + /* + * We can poll here since we've had BQL from the time + * we sent the descriptor. + */ + dev_written = vhost_vdpa_net_svq_poll(s, 1); } if (unlikely(dev_written < sizeof(status))) { @@ -1301,7 +1412,7 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, } status = VIRTIO_NET_ERR; - virtio_net_handle_ctrl_iov(svq->vdev, &in, 1, &out, 1); + virtio_net_handle_ctrl_iov(svq->vdev, &model_in, 1, &out, 1); if (status != VIRTIO_NET_OK) { error_report("Bad CVQ processing in model"); } @@ -1456,7 +1567,7 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, s->vhost_vdpa.device_fd = vdpa_device_fd; s->vhost_vdpa.index = queue_pair_index; s->always_svq = svq; - s->migration_state.notify = vdpa_net_migration_state_notifier; + s->migration_state.notify = NULL; s->vhost_vdpa.shadow_vqs_enabled = svq; s->vhost_vdpa.iova_range = iova_range; s->vhost_vdpa.shadow_data = svq; |