Enabling this flag should only be done when the calling application does
not pre-fault the guest shared memory, otherwise migration would fail.
+ - ``RTE_VHOST_USER_LINEARBUF_SUPPORT``
+
+ Enabling this flag forces vhost dequeue function to only provide linear
+ pktmbuf (no multi-segmented pktmbuf).
+
+ The vhost library by default provides a single pktmbuf for given a
+ packet, but if for some reason the data doesn't fit into a single
+ pktmbuf (e.g., TSO is enabled), the library will allocate additional
+ pktmbufs from the same mempool and chain them together to create a
+ multi-segmented pktmbuf.
+
+ However, the vhost application needs to support multi-segmented format.
+ If the vhost application does not support that format and requires large
+ buffers to be dequeue, this flag should be enabled to force only linear
+ buffers (see RTE_VHOST_USER_EXTBUF_SUPPORT) or drop the packet.
+
+ It is disabled by default.
+
+ - ``RTE_VHOST_USER_EXTBUF_SUPPORT``
+
+ Enabling this flag allows vhost dequeue function to allocate and attach
+ an external buffer to a pktmbuf if the pkmbuf doesn't provide enough
+ space to store all data.
+
+ This is useful when the vhost application wants to support large packets
+ but doesn't want to increase the default mempool object size nor to
+ support multi-segmented mbufs (non-linear). In this case, a fresh buffer
+ is allocated using rte_malloc() which gets attached to a pktmbuf using
+ rte_pktmbuf_attach_extbuf().
+
+ See RTE_VHOST_USER_LINEARBUF_SUPPORT as well to disable multi-segmented
+ mbufs for application that doesn't support chained mbufs.
+
+ It is disabled by default.
+
* ``rte_vhost_driver_set_features(path, features)``
This function sets the feature bits the vhost-user driver supports. The
bool dequeue_zero_copy;
bool iommu_support;
bool use_builtin_virtio_net;
+ bool extbuf;
+ bool linearbuf;
/*
* The "supported_features" indicates the feature bits the
if (vsocket->dequeue_zero_copy)
vhost_enable_dequeue_zero_copy(vid);
+ if (vsocket->extbuf)
+ vhost_enable_extbuf(vid);
+
+ if (vsocket->linearbuf)
+ vhost_enable_linearbuf(vid);
+
RTE_LOG(INFO, VHOST_CONFIG, "new device, handle is %d\n", vid);
if (vsocket->notify_ops->new_connection) {
goto out_free;
}
vsocket->dequeue_zero_copy = flags & RTE_VHOST_USER_DEQUEUE_ZERO_COPY;
+ vsocket->extbuf = flags & RTE_VHOST_USER_EXTBUF_SUPPORT;
+ vsocket->linearbuf = flags & RTE_VHOST_USER_LINEARBUF_SUPPORT;
if (vsocket->dequeue_zero_copy &&
(flags & RTE_VHOST_USER_IOMMU_SUPPORT)) {
* not compatible with postcopy.
*/
if (vsocket->dequeue_zero_copy) {
+ if (vsocket->extbuf) {
+ RTE_LOG(ERR, VHOST_CONFIG,
+ "error: zero copy is incompatible with external buffers\n");
+ ret = -1;
+ goto out_mutex;
+ }
+ if (vsocket->linearbuf) {
+ RTE_LOG(ERR, VHOST_CONFIG,
+ "error: zero copy is incompatible with linear buffers\n");
+ ret = -1;
+ goto out_mutex;
+ }
vsocket->supported_features &= ~(1ULL << VIRTIO_F_IN_ORDER);
vsocket->features &= ~(1ULL << VIRTIO_F_IN_ORDER);
return NULL;
}
+static void
+virtio_dev_extbuf_free(void *addr __rte_unused, void *opaque)
+{
+ rte_free(opaque);
+}
+
+static int
+virtio_dev_extbuf_alloc(struct rte_mbuf *pkt, uint32_t size)
+{
+ struct rte_mbuf_ext_shared_info *shinfo = NULL;
+ uint32_t total_len = RTE_PKTMBUF_HEADROOM + size;
+ uint16_t buf_len;
+ rte_iova_t iova;
+ void *buf;
+
+ /* Try to use pkt buffer to store shinfo to reduce the amount of memory
+ * required, otherwise store shinfo in the new buffer.
+ */
+ if (rte_pktmbuf_tailroom(pkt) >= sizeof(*shinfo))
+ shinfo = rte_pktmbuf_mtod(pkt,
+ struct rte_mbuf_ext_shared_info *);
+ else {
+ total_len += sizeof(*shinfo) + sizeof(uintptr_t);
+ total_len = RTE_ALIGN_CEIL(total_len, sizeof(uintptr_t));
+ }
+
+ if (unlikely(total_len > UINT16_MAX))
+ return -ENOSPC;
+
+ buf_len = total_len;
+ buf = rte_malloc(NULL, buf_len, RTE_CACHE_LINE_SIZE);
+ if (unlikely(buf == NULL))
+ return -ENOMEM;
+
+ /* Initialize shinfo */
+ if (shinfo) {
+ shinfo->free_cb = virtio_dev_extbuf_free;
+ shinfo->fcb_opaque = buf;
+ rte_mbuf_ext_refcnt_set(shinfo, 1);
+ } else {
+ shinfo = rte_pktmbuf_ext_shinfo_init_helper(buf, &buf_len,
+ virtio_dev_extbuf_free, buf);
+ if (unlikely(shinfo == NULL)) {
+ rte_free(buf);
+ RTE_LOG(ERR, VHOST_DATA, "Failed to init shinfo\n");
+ return -1;
+ }
+ }
+
+ iova = rte_malloc_virt2iova(buf);
+ rte_pktmbuf_attach_extbuf(pkt, buf, iova, buf_len, shinfo);
+ rte_pktmbuf_reset_headroom(pkt);
+
+ return 0;
+}
+
+/*
+ * Allocate a host supported pktmbuf.
+ */
+static __rte_always_inline struct rte_mbuf *
+virtio_dev_pktmbuf_alloc(struct virtio_net *dev, struct rte_mempool *mp,
+ uint32_t data_len)
+{
+ struct rte_mbuf *pkt = rte_pktmbuf_alloc(mp);
+
+ if (unlikely(pkt == NULL))
+ return NULL;
+
+ if (rte_pktmbuf_tailroom(pkt) >= data_len)
+ return pkt;
+
+ /* attach an external buffer if supported */
+ if (dev->extbuf && !virtio_dev_extbuf_alloc(pkt, data_len))
+ return pkt;
+
+ /* check if chained buffers are allowed */
+ if (!dev->linearbuf)
+ return pkt;
+
+ /* Data doesn't fit into the buffer and the host supports
+ * only linear buffers
+ */
+ rte_pktmbuf_free(pkt);
+
+ return NULL;
+}
+
static __rte_noinline uint16_t
virtio_dev_tx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count)
for (i = 0; i < count; i++) {
struct buf_vector buf_vec[BUF_VECTOR_MAX];
uint16_t head_idx;
- uint32_t dummy_len;
+ uint32_t buf_len;
uint16_t nr_vec = 0;
int err;
if (unlikely(fill_vec_buf_split(dev, vq,
vq->last_avail_idx + i,
&nr_vec, buf_vec,
- &head_idx, &dummy_len,
+ &head_idx, &buf_len,
VHOST_ACCESS_RO) < 0))
break;
if (likely(dev->dequeue_zero_copy == 0))
update_shadow_used_ring_split(vq, head_idx, 0);
- pkts[i] = rte_pktmbuf_alloc(mbuf_pool);
- if (unlikely(pkts[i] == NULL)) {
- RTE_LOG(ERR, VHOST_DATA,
- "Failed to allocate memory for mbuf.\n");
+ pkts[i] = virtio_dev_pktmbuf_alloc(dev, mbuf_pool, buf_len);
+ if (unlikely(pkts[i] == NULL))
break;
- }
err = copy_desc_to_mbuf(dev, vq, buf_vec, nr_vec, pkts[i],
mbuf_pool);
for (i = 0; i < count; i++) {
struct buf_vector buf_vec[BUF_VECTOR_MAX];
uint16_t buf_id;
- uint32_t dummy_len;
+ uint32_t buf_len;
uint16_t desc_count, nr_vec = 0;
int err;
if (unlikely(fill_vec_buf_packed(dev, vq,
vq->last_avail_idx, &desc_count,
buf_vec, &nr_vec,
- &buf_id, &dummy_len,
+ &buf_id, &buf_len,
VHOST_ACCESS_RO) < 0))
break;
update_shadow_used_ring_packed(vq, buf_id, 0,
desc_count);
- pkts[i] = rte_pktmbuf_alloc(mbuf_pool);
- if (unlikely(pkts[i] == NULL)) {
- RTE_LOG(ERR, VHOST_DATA,
- "Failed to allocate memory for mbuf.\n");
+ pkts[i] = virtio_dev_pktmbuf_alloc(dev, mbuf_pool, buf_len);
+ if (unlikely(pkts[i] == NULL))
break;
- }
err = copy_desc_to_mbuf(dev, vq, buf_vec, nr_vec, pkts[i],
mbuf_pool);
git.droids-corp.org / dpdk.git / commitdiff