diff options
Diffstat (limited to 'net')
-rw-r--r-- | net/colo.c | 25 | ||||
-rw-r--r-- | net/colo.h | 1 | ||||
-rw-r--r-- | net/trace-events | 2 | ||||
-rw-r--r-- | net/vhost-vdpa.c | 228 |
4 files changed, 161 insertions, 95 deletions
@@ -44,21 +44,28 @@ int parse_packet_early(Packet *pkt) { int network_length; static const uint8_t vlan[] = {0x81, 0x00}; - uint8_t *data = pkt->data + pkt->vnet_hdr_len; + uint8_t *data = pkt->data; uint16_t l3_proto; ssize_t l2hdr_len; - if (data == NULL) { - trace_colo_proxy_main_vnet_info("This packet is not parsed correctly, " - "pkt->vnet_hdr_len", pkt->vnet_hdr_len); + assert(data); + + /* Check the received vnet_hdr_len then add the offset */ + if ((pkt->vnet_hdr_len > sizeof(struct virtio_net_hdr_v1_hash)) || + (pkt->size < sizeof(struct eth_header) + sizeof(struct vlan_header) + + pkt->vnet_hdr_len)) { + /* + * The received remote packet maybe misconfiguration here, + * Please enable/disable filter module's the vnet_hdr flag at + * the same time. + */ + trace_colo_proxy_main_vnet_info("This received packet load wrong ", + pkt->vnet_hdr_len, pkt->size); return 1; } - l2hdr_len = eth_get_l2_hdr_length(data); + data += pkt->vnet_hdr_len; - if (pkt->size < ETH_HLEN + pkt->vnet_hdr_len) { - trace_colo_proxy_main("pkt->size < ETH_HLEN"); - return 1; - } + l2hdr_len = eth_get_l2_hdr_length(data); /* * TODO: support vlan. @@ -18,6 +18,7 @@ #include "qemu/jhash.h" #include "qemu/timer.h" #include "net/eth.h" +#include "standard-headers/linux/virtio_net.h" #define HASHTABLE_MAX_SIZE 16384 diff --git a/net/trace-events b/net/trace-events index 6af927b..823a071 100644 --- a/net/trace-events +++ b/net/trace-events @@ -9,7 +9,7 @@ vhost_user_event(const char *chr, int event) "chr: %s got event: %d" # colo.c colo_proxy_main(const char *chr) ": %s" -colo_proxy_main_vnet_info(const char *sta, int size) ": %s = %d" +colo_proxy_main_vnet_info(const char *sta, uint32_t vnet_hdr, int size) ": %s pkt->vnet_hdr_len = %u, pkt->size = %d" # colo-compare.c colo_compare_main(const char *chr) ": %s" diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c index 303447a..6ce68fc 100644 --- a/net/vhost-vdpa.c +++ b/net/vhost-vdpa.c @@ -244,7 +244,7 @@ static void vhost_vdpa_cvq_unmap_buf(struct vhost_vdpa *v, void *addr) error_report("Device cannot unmap: %s(%d)", g_strerror(r), r); } - vhost_iova_tree_remove(tree, map); + vhost_iova_tree_remove(tree, *map); } static size_t vhost_vdpa_net_cvq_cmd_len(void) @@ -263,29 +263,20 @@ static size_t vhost_vdpa_net_cvq_cmd_page_len(void) return ROUND_UP(vhost_vdpa_net_cvq_cmd_len(), qemu_real_host_page_size()); } -/** Copy and map a guest buffer. */ -static bool vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v, - const struct iovec *out_data, - size_t out_num, size_t data_len, void *buf, - size_t *written, bool write) +/** Map CVQ buffer. */ +static int vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v, void *buf, size_t size, + bool write) { DMAMap map = {}; int r; - if (unlikely(!data_len)) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid legnth of %s buffer\n", - __func__, write ? "in" : "out"); - return false; - } - - *written = iov_to_buf(out_data, out_num, 0, buf, data_len); map.translated_addr = (hwaddr)(uintptr_t)buf; - map.size = vhost_vdpa_net_cvq_cmd_page_len() - 1; + map.size = size - 1; map.perm = write ? IOMMU_RW : IOMMU_RO, r = vhost_iova_tree_map_alloc(v->iova_tree, &map); if (unlikely(r != IOVA_OK)) { error_report("Cannot map injected element"); - return false; + return r; } r = vhost_vdpa_dma_map(v, map.iova, vhost_vdpa_net_cvq_cmd_page_len(), buf, @@ -294,63 +285,151 @@ static bool vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v, goto dma_map_err; } - return true; + return 0; dma_map_err: - vhost_iova_tree_remove(v->iova_tree, &map); - return false; + vhost_iova_tree_remove(v->iova_tree, map); + return r; } -/** - * Copy the guest element into a dedicated buffer suitable to be sent to NIC - * - * @iov: [0] is the out buffer, [1] is the in one - */ -static bool vhost_vdpa_net_cvq_map_elem(VhostVDPAState *s, - VirtQueueElement *elem, - struct iovec *iov) +static int vhost_vdpa_net_cvq_start(NetClientState *nc) { - size_t in_copied; - bool ok; + VhostVDPAState *s; + int r; - iov[0].iov_base = s->cvq_cmd_out_buffer; - ok = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, elem->out_sg, elem->out_num, - vhost_vdpa_net_cvq_cmd_len(), iov[0].iov_base, - &iov[0].iov_len, false); - if (unlikely(!ok)) { - return false; + assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA); + + s = DO_UPCAST(VhostVDPAState, nc, nc); + if (!s->vhost_vdpa.shadow_vqs_enabled) { + return 0; } - iov[1].iov_base = s->cvq_cmd_in_buffer; - ok = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, NULL, 0, - sizeof(virtio_net_ctrl_ack), iov[1].iov_base, - &in_copied, true); - if (unlikely(!ok)) { + r = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer, + vhost_vdpa_net_cvq_cmd_page_len(), false); + if (unlikely(r < 0)) { + return r; + } + + r = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, s->cvq_cmd_in_buffer, + vhost_vdpa_net_cvq_cmd_page_len(), true); + if (unlikely(r < 0)) { vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer); - return false; } - iov[1].iov_len = sizeof(virtio_net_ctrl_ack); - return true; + return r; +} + +static void vhost_vdpa_net_cvq_stop(NetClientState *nc) +{ + VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc); + + assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA); + + if (s->vhost_vdpa.shadow_vqs_enabled) { + vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer); + vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_in_buffer); + } +} + +static ssize_t vhost_vdpa_net_cvq_add(VhostVDPAState *s, size_t out_len, + size_t in_len) +{ + /* 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->cvq_cmd_in_buffer, + .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); + 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); } +static int vhost_vdpa_net_load(NetClientState *nc) +{ + VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc); + const struct vhost_vdpa *v = &s->vhost_vdpa; + const VirtIONet *n; + uint64_t features; + + assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA); + + if (!v->shadow_vqs_enabled) { + return 0; + } + + n = VIRTIO_NET(v->dev->vdev); + features = n->parent_obj.guest_features; + if (features & BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR)) { + const struct virtio_net_ctrl_hdr ctrl = { + .class = VIRTIO_NET_CTRL_MAC, + .cmd = VIRTIO_NET_CTRL_MAC_ADDR_SET, + }; + char *cursor = s->cvq_cmd_out_buffer; + ssize_t dev_written; + + memcpy(cursor, &ctrl, sizeof(ctrl)); + cursor += sizeof(ctrl); + memcpy(cursor, n->mac, sizeof(n->mac)); + + dev_written = vhost_vdpa_net_cvq_add(s, sizeof(ctrl) + sizeof(n->mac), + sizeof(virtio_net_ctrl_ack)); + if (unlikely(dev_written < 0)) { + return dev_written; + } + + return *((virtio_net_ctrl_ack *)s->cvq_cmd_in_buffer) != VIRTIO_NET_OK; + } + + return 0; +} + +static NetClientInfo net_vhost_vdpa_cvq_info = { + .type = NET_CLIENT_DRIVER_VHOST_VDPA, + .size = sizeof(VhostVDPAState), + .receive = vhost_vdpa_receive, + .start = vhost_vdpa_net_cvq_start, + .load = vhost_vdpa_net_load, + .stop = vhost_vdpa_net_cvq_stop, + .cleanup = vhost_vdpa_cleanup, + .has_vnet_hdr = vhost_vdpa_has_vnet_hdr, + .has_ufo = vhost_vdpa_has_ufo, + .check_peer_type = vhost_vdpa_check_peer_type, +}; + /** * Do not forward commands not supported by SVQ. Otherwise, the device could * accept it and qemu would not know how to update the device model. */ -static bool vhost_vdpa_net_cvq_validate_cmd(const struct iovec *out, - size_t out_num) +static bool vhost_vdpa_net_cvq_validate_cmd(const void *out_buf, size_t len) { struct virtio_net_ctrl_hdr ctrl; - size_t n; - n = iov_to_buf(out, out_num, 0, &ctrl, sizeof(ctrl)); - if (unlikely(n < sizeof(ctrl))) { + if (unlikely(len < sizeof(ctrl))) { qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid legnth of out buffer %zu\n", __func__, n); + "%s: invalid legnth of out buffer %zu\n", __func__, len); return false; } + memcpy(&ctrl, out_buf, sizeof(ctrl)); switch (ctrl.class) { case VIRTIO_NET_CTRL_MAC: switch (ctrl.cmd) { @@ -380,58 +459,45 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, void *opaque) { VhostVDPAState *s = opaque; - size_t in_len, dev_written; + size_t in_len; virtio_net_ctrl_ack status = VIRTIO_NET_ERR; - /* out and in buffers sent to the device */ - struct iovec dev_buffers[2] = { - { .iov_base = s->cvq_cmd_out_buffer }, - { .iov_base = s->cvq_cmd_in_buffer }, + /* Out buffer sent to both the vdpa device and the device model */ + struct iovec out = { + .iov_base = s->cvq_cmd_out_buffer, }; /* in buffer used for device model */ const struct iovec in = { .iov_base = &status, .iov_len = sizeof(status), }; - int r = -EINVAL; + ssize_t dev_written = -EINVAL; bool ok; - ok = vhost_vdpa_net_cvq_map_elem(s, elem, dev_buffers); + out.iov_len = iov_to_buf(elem->out_sg, elem->out_num, 0, + s->cvq_cmd_out_buffer, + vhost_vdpa_net_cvq_cmd_len()); + ok = vhost_vdpa_net_cvq_validate_cmd(s->cvq_cmd_out_buffer, out.iov_len); if (unlikely(!ok)) { goto out; } - ok = vhost_vdpa_net_cvq_validate_cmd(&dev_buffers[0], 1); - if (unlikely(!ok)) { + dev_written = vhost_vdpa_net_cvq_add(s, out.iov_len, sizeof(status)); + if (unlikely(dev_written < 0)) { goto out; } - r = vhost_svq_add(svq, &dev_buffers[0], 1, &dev_buffers[1], 1, elem); - if (unlikely(r != 0)) { - if (unlikely(r == -ENOSPC)) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n", - __func__); - } - goto out; - } - - /* - * 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 - */ - dev_written = vhost_svq_poll(svq); if (unlikely(dev_written < sizeof(status))) { error_report("Insufficient written data (%zu)", dev_written); goto out; } - memcpy(&status, dev_buffers[1].iov_base, sizeof(status)); + memcpy(&status, s->cvq_cmd_in_buffer, sizeof(status)); if (status != VIRTIO_NET_OK) { - goto out; + return VIRTIO_NET_ERR; } status = VIRTIO_NET_ERR; - virtio_net_handle_ctrl_iov(svq->vdev, &in, 1, dev_buffers, 1); + virtio_net_handle_ctrl_iov(svq->vdev, &in, 1, &out, 1); if (status != VIRTIO_NET_OK) { error_report("Bad CVQ processing in model"); } @@ -444,13 +510,7 @@ out: } vhost_svq_push_elem(svq, elem, MIN(in_len, sizeof(status))); g_free(elem); - if (dev_buffers[0].iov_base) { - vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, dev_buffers[0].iov_base); - } - if (dev_buffers[1].iov_base) { - vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, dev_buffers[1].iov_base); - } - return r; + return dev_written < 0 ? dev_written : 0; } static const VhostShadowVirtqueueOps vhost_vdpa_net_svq_ops = { @@ -475,7 +535,7 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, nc = qemu_new_net_client(&net_vhost_vdpa_info, peer, device, name); } else { - nc = qemu_new_net_control_client(&net_vhost_vdpa_info, peer, + nc = qemu_new_net_control_client(&net_vhost_vdpa_cvq_info, peer, device, name); } snprintf(nc->info_str, sizeof(nc->info_str), TYPE_VHOST_VDPA); @@ -495,8 +555,6 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, s->vhost_vdpa.shadow_vq_ops = &vhost_vdpa_net_svq_ops; s->vhost_vdpa.shadow_vq_ops_opaque = s; - error_setg(&s->vhost_vdpa.migration_blocker, - "Migration disabled: vhost-vdpa uses CVQ."); } ret = vhost_vdpa_add(nc, (void *)&s->vhost_vdpa, queue_pair_index, nvqs); if (ret) { |