#include <rte_net.h>
#include <rte_ether.h>
#include <rte_ip.h>
+#include <rte_dmadev.h>
#include <rte_vhost.h>
#include <rte_tcp.h>
#include <rte_udp.h>
#define MAX_BATCH_LEN 256
+/* DMA device copy operation tracking array. */
+struct async_dma_info dma_copy_track[RTE_DMADEV_DEFAULT_MAX];
+
static __rte_always_inline bool
rxvq_is_mergeable(struct virtio_net *dev)
{
return (is_tx ^ (idx & 1)) == 0 && idx < nr_vring;
}
+/*
+ * This function must be called with virtqueue's access_lock taken.
+ */
+static inline void
+vhost_queue_stats_update(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ struct rte_mbuf **pkts, uint16_t count)
+{
+ struct virtqueue_stats *stats = &vq->stats;
+ int i;
+
+ if (!(dev->flags & VIRTIO_DEV_STATS_ENABLED))
+ return;
+
+ for (i = 0; i < count; i++) {
+ struct rte_ether_addr *ea;
+ struct rte_mbuf *pkt = pkts[i];
+ uint32_t pkt_len = rte_pktmbuf_pkt_len(pkt);
+
+ stats->packets++;
+ stats->bytes += pkt_len;
+
+ if (pkt_len == 64) {
+ stats->size_bins[1]++;
+ } else if (pkt_len > 64 && pkt_len < 1024) {
+ uint32_t bin;
+
+ /* count zeros, and offset into correct bin */
+ bin = (sizeof(pkt_len) * 8) - __builtin_clz(pkt_len) - 5;
+ stats->size_bins[bin]++;
+ } else {
+ if (pkt_len < 64)
+ stats->size_bins[0]++;
+ else if (pkt_len < 1519)
+ stats->size_bins[6]++;
+ else
+ stats->size_bins[7]++;
+ }
+
+ ea = rte_pktmbuf_mtod(pkt, struct rte_ether_addr *);
+ if (rte_is_multicast_ether_addr(ea)) {
+ if (rte_is_broadcast_ether_addr(ea))
+ stats->broadcast++;
+ else
+ stats->multicast++;
+ }
+ }
+}
+
+static __rte_always_inline int64_t
+vhost_async_dma_transfer_one(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ int16_t dma_id, uint16_t vchan_id, uint16_t flag_idx,
+ struct vhost_iov_iter *pkt)
+{
+ struct async_dma_vchan_info *dma_info = &dma_copy_track[dma_id].vchans[vchan_id];
+ uint16_t ring_mask = dma_info->ring_mask;
+ static bool vhost_async_dma_copy_log;
+
+
+ struct vhost_iovec *iov = pkt->iov;
+ int copy_idx = 0;
+ uint32_t nr_segs = pkt->nr_segs;
+ uint16_t i;
+
+ if (rte_dma_burst_capacity(dma_id, vchan_id) < nr_segs)
+ return -1;
+
+ for (i = 0; i < nr_segs; i++) {
+ copy_idx = rte_dma_copy(dma_id, vchan_id, (rte_iova_t)iov[i].src_addr,
+ (rte_iova_t)iov[i].dst_addr, iov[i].len, RTE_DMA_OP_FLAG_LLC);
+ /**
+ * Since all memory is pinned and DMA vChannel
+ * ring has enough space, failure should be a
+ * rare case. If failure happens, it means DMA
+ * device encounters serious errors; in this
+ * case, please stop async data-path and check
+ * what has happened to DMA device.
+ */
+ if (unlikely(copy_idx < 0)) {
+ if (!vhost_async_dma_copy_log) {
+ VHOST_LOG_DATA(ERR, "(%s) DMA copy failed for channel %d:%u\n",
+ dev->ifname, dma_id, vchan_id);
+ vhost_async_dma_copy_log = true;
+ }
+ return -1;
+ }
+ }
+
+ /**
+ * Only store packet completion flag address in the last copy's
+ * slot, and other slots are set to NULL.
+ */
+ dma_info->pkts_cmpl_flag_addr[copy_idx & ring_mask] = &vq->async->pkts_cmpl_flag[flag_idx];
+
+ return nr_segs;
+}
+
+static __rte_always_inline uint16_t
+vhost_async_dma_transfer(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ int16_t dma_id, uint16_t vchan_id, uint16_t head_idx,
+ struct vhost_iov_iter *pkts, uint16_t nr_pkts)
+{
+ struct async_dma_vchan_info *dma_info = &dma_copy_track[dma_id].vchans[vchan_id];
+ int64_t ret, nr_copies = 0;
+ uint16_t pkt_idx;
+
+ rte_spinlock_lock(&dma_info->dma_lock);
+
+ for (pkt_idx = 0; pkt_idx < nr_pkts; pkt_idx++) {
+ ret = vhost_async_dma_transfer_one(dev, vq, dma_id, vchan_id, head_idx,
+ &pkts[pkt_idx]);
+ if (unlikely(ret < 0))
+ break;
+
+ nr_copies += ret;
+ head_idx++;
+ if (head_idx >= vq->size)
+ head_idx -= vq->size;
+ }
+
+ if (likely(nr_copies > 0))
+ rte_dma_submit(dma_id, vchan_id);
+
+ rte_spinlock_unlock(&dma_info->dma_lock);
+
+ return pkt_idx;
+}
+
+static __rte_always_inline uint16_t
+vhost_async_dma_check_completed(struct virtio_net *dev, int16_t dma_id, uint16_t vchan_id,
+ uint16_t max_pkts)
+{
+ struct async_dma_vchan_info *dma_info = &dma_copy_track[dma_id].vchans[vchan_id];
+ uint16_t ring_mask = dma_info->ring_mask;
+ uint16_t last_idx = 0;
+ uint16_t nr_copies;
+ uint16_t copy_idx;
+ uint16_t i;
+ bool has_error = false;
+ static bool vhost_async_dma_complete_log;
+
+ rte_spinlock_lock(&dma_info->dma_lock);
+
+ /**
+ * Print error log for debugging, if DMA reports error during
+ * DMA transfer. We do not handle error in vhost level.
+ */
+ nr_copies = rte_dma_completed(dma_id, vchan_id, max_pkts, &last_idx, &has_error);
+ if (unlikely(!vhost_async_dma_complete_log && has_error)) {
+ VHOST_LOG_DATA(ERR, "(%s) DMA completion failure on channel %d:%u\n", dev->ifname,
+ dma_id, vchan_id);
+ vhost_async_dma_complete_log = true;
+ } else if (nr_copies == 0) {
+ goto out;
+ }
+
+ copy_idx = last_idx - nr_copies + 1;
+ for (i = 0; i < nr_copies; i++) {
+ bool *flag;
+
+ flag = dma_info->pkts_cmpl_flag_addr[copy_idx & ring_mask];
+ if (flag) {
+ /**
+ * Mark the packet flag as received. The flag
+ * could belong to another virtqueue but write
+ * is atomic.
+ */
+ *flag = true;
+ dma_info->pkts_cmpl_flag_addr[copy_idx & ring_mask] = NULL;
+ }
+ copy_idx++;
+ }
+
+out:
+ rte_spinlock_unlock(&dma_info->dma_lock);
+ return nr_copies;
+}
+
static inline void
do_data_copy_enqueue(struct virtio_net *dev, struct vhost_virtqueue *vq)
{
}
static __rte_always_inline int
-async_iter_initialize(struct vhost_async *async)
+async_iter_initialize(struct virtio_net *dev, struct vhost_async *async)
{
- struct rte_vhost_iov_iter *iter;
+ struct vhost_iov_iter *iter;
if (unlikely(async->iovec_idx >= VHOST_MAX_ASYNC_VEC)) {
- VHOST_LOG_DATA(ERR, "no more async iovec available\n");
+ VHOST_LOG_DATA(ERR, "(%s) no more async iovec available\n", dev->ifname);
return -1;
}
}
static __rte_always_inline int
-async_iter_add_iovec(struct vhost_async *async, void *src, void *dst, size_t len)
+async_iter_add_iovec(struct virtio_net *dev, struct vhost_async *async,
+ void *src, void *dst, size_t len)
{
- struct rte_vhost_iov_iter *iter;
- struct rte_vhost_iovec *iovec;
+ struct vhost_iov_iter *iter;
+ struct vhost_iovec *iovec;
if (unlikely(async->iovec_idx >= VHOST_MAX_ASYNC_VEC)) {
static bool vhost_max_async_vec_log;
if (!vhost_max_async_vec_log) {
- VHOST_LOG_DATA(ERR, "no more async iovec available\n");
+ VHOST_LOG_DATA(ERR, "(%s) no more async iovec available\n", dev->ifname);
vhost_max_async_vec_log = true;
}
static __rte_always_inline void
async_iter_cancel(struct vhost_async *async)
{
- struct rte_vhost_iov_iter *iter;
+ struct vhost_iov_iter *iter;
iter = async->iov_iter + async->iter_idx;
async->iovec_idx -= iter->nr_segs;
}
static __rte_always_inline int
-async_mbuf_to_desc_seg(struct virtio_net *dev, struct vhost_virtqueue *vq,
+async_fill_seg(struct virtio_net *dev, struct vhost_virtqueue *vq,
struct rte_mbuf *m, uint32_t mbuf_offset,
- uint64_t buf_iova, uint32_t cpy_len)
+ uint64_t buf_iova, uint32_t cpy_len, bool to_desc)
{
struct vhost_async *async = vq->async;
uint64_t mapped_len;
uint32_t buf_offset = 0;
- void *hpa;
+ void *src, *dst;
+ void *host_iova;
while (cpy_len) {
- hpa = (void *)(uintptr_t)gpa_to_first_hpa(dev,
+ host_iova = (void *)(uintptr_t)gpa_to_first_hpa(dev,
buf_iova + buf_offset, cpy_len, &mapped_len);
- if (unlikely(!hpa)) {
- VHOST_LOG_DATA(ERR, "(%d) %s: failed to get hpa.\n", dev->vid, __func__);
+ if (unlikely(!host_iova)) {
+ VHOST_LOG_DATA(ERR, "(%s) %s: failed to get host iova.\n",
+ dev->ifname, __func__);
return -1;
}
- if (unlikely(async_iter_add_iovec(async,
- (void *)(uintptr_t)rte_pktmbuf_iova_offset(m,
- mbuf_offset),
- hpa, (size_t)mapped_len)))
+ if (to_desc) {
+ src = (void *)(uintptr_t)rte_pktmbuf_iova_offset(m, mbuf_offset);
+ dst = host_iova;
+ } else {
+ src = host_iova;
+ dst = (void *)(uintptr_t)rte_pktmbuf_iova_offset(m, mbuf_offset);
+ }
+
+ if (unlikely(async_iter_add_iovec(dev, async, src, dst, (size_t)mapped_len)))
return -1;
cpy_len -= (uint32_t)mapped_len;
}
static __rte_always_inline void
-sync_mbuf_to_desc_seg(struct virtio_net *dev, struct vhost_virtqueue *vq,
+sync_fill_seg(struct virtio_net *dev, struct vhost_virtqueue *vq,
struct rte_mbuf *m, uint32_t mbuf_offset,
- uint64_t buf_addr, uint64_t buf_iova, uint32_t cpy_len)
+ uint64_t buf_addr, uint64_t buf_iova, uint32_t cpy_len, bool to_desc)
{
struct batch_copy_elem *batch_copy = vq->batch_copy_elems;
if (likely(cpy_len > MAX_BATCH_LEN || vq->batch_copy_nb_elems >= vq->size)) {
- rte_memcpy((void *)((uintptr_t)(buf_addr)),
+ if (to_desc) {
+ rte_memcpy((void *)((uintptr_t)(buf_addr)),
rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
cpy_len);
+ } else {
+ rte_memcpy(rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
+ (void *)((uintptr_t)(buf_addr)),
+ cpy_len);
+ }
vhost_log_cache_write_iova(dev, vq, buf_iova, cpy_len);
PRINT_PACKET(dev, (uintptr_t)(buf_addr), cpy_len, 0);
} else {
- batch_copy[vq->batch_copy_nb_elems].dst =
- (void *)((uintptr_t)(buf_addr));
- batch_copy[vq->batch_copy_nb_elems].src =
- rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
+ if (to_desc) {
+ batch_copy[vq->batch_copy_nb_elems].dst =
+ (void *)((uintptr_t)(buf_addr));
+ batch_copy[vq->batch_copy_nb_elems].src =
+ rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
+ } else {
+ batch_copy[vq->batch_copy_nb_elems].dst =
+ rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
+ batch_copy[vq->batch_copy_nb_elems].src =
+ (void *)((uintptr_t)(buf_addr));
+ }
batch_copy[vq->batch_copy_nb_elems].log_addr = buf_iova;
batch_copy[vq->batch_copy_nb_elems].len = cpy_len;
vq->batch_copy_nb_elems++;
} else
hdr = (struct virtio_net_hdr_mrg_rxbuf *)(uintptr_t)hdr_addr;
- VHOST_LOG_DATA(DEBUG, "(%d) RX: num merge buffers %d\n",
- dev->vid, num_buffers);
+ VHOST_LOG_DATA(DEBUG, "(%s) RX: num merge buffers %d\n",
+ dev->ifname, num_buffers);
if (unlikely(buf_len < dev->vhost_hlen)) {
buf_offset = dev->vhost_hlen - buf_len;
mbuf_offset = 0;
if (is_async) {
- if (async_iter_initialize(async))
+ if (async_iter_initialize(dev, async))
return -1;
}
cpy_len = RTE_MIN(buf_avail, mbuf_avail);
if (is_async) {
- if (async_mbuf_to_desc_seg(dev, vq, m, mbuf_offset,
- buf_iova + buf_offset, cpy_len) < 0)
+ if (async_fill_seg(dev, vq, m, mbuf_offset,
+ buf_iova + buf_offset, cpy_len, true) < 0)
goto error;
} else {
- sync_mbuf_to_desc_seg(dev, vq, m, mbuf_offset,
- buf_addr + buf_offset,
- buf_iova + buf_offset, cpy_len);
+ sync_fill_seg(dev, vq, m, mbuf_offset,
+ buf_addr + buf_offset,
+ buf_iova + buf_offset, cpy_len, true);
}
mbuf_avail -= cpy_len;
pkt_len, buf_vec, &num_buffers,
avail_head, &nr_vec) < 0)) {
VHOST_LOG_DATA(DEBUG,
- "(%d) failed to get enough desc from vring\n",
- dev->vid);
+ "(%s) failed to get enough desc from vring\n",
+ dev->ifname);
vq->shadow_used_idx -= num_buffers;
break;
}
- VHOST_LOG_DATA(DEBUG, "(%d) current index %d | end index %d\n",
- dev->vid, vq->last_avail_idx,
+ VHOST_LOG_DATA(DEBUG, "(%s) current index %d | end index %d\n",
+ dev->ifname, vq->last_avail_idx,
vq->last_avail_idx + num_buffers);
if (mbuf_to_desc(dev, vq, pkts[pkt_idx], buf_vec, nr_vec,
if (unlikely(vhost_enqueue_single_packed(dev, vq, pkt, buf_vec,
&nr_descs) < 0)) {
- VHOST_LOG_DATA(DEBUG,
- "(%d) failed to get enough desc from vring\n",
- dev->vid);
+ VHOST_LOG_DATA(DEBUG, "(%s) failed to get enough desc from vring\n",
+ dev->ifname);
return -1;
}
- VHOST_LOG_DATA(DEBUG, "(%d) current index %d | end index %d\n",
- dev->vid, vq->last_avail_idx,
+ VHOST_LOG_DATA(DEBUG, "(%s) current index %d | end index %d\n",
+ dev->ifname, vq->last_avail_idx,
vq->last_avail_idx + nr_descs);
vq_inc_last_avail_packed(vq, nr_descs);
struct vhost_virtqueue *vq;
uint32_t nb_tx = 0;
- VHOST_LOG_DATA(DEBUG, "(%d) %s\n", dev->vid, __func__);
+ VHOST_LOG_DATA(DEBUG, "(%s) %s\n", dev->ifname, __func__);
if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
- VHOST_LOG_DATA(ERR, "(%d) %s: invalid virtqueue idx %d.\n",
- dev->vid, __func__, queue_id);
+ VHOST_LOG_DATA(ERR, "(%s) %s: invalid virtqueue idx %d.\n",
+ dev->ifname, __func__, queue_id);
return 0;
}
else
nb_tx = virtio_dev_rx_split(dev, vq, pkts, count);
+ vhost_queue_stats_update(dev, vq, pkts, nb_tx);
+
out:
if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
vhost_user_iotlb_rd_unlock(vq);
return 0;
if (unlikely(!(dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET))) {
- VHOST_LOG_DATA(ERR,
- "(%d) %s: built-in vhost net backend is disabled.\n",
- dev->vid, __func__);
+ VHOST_LOG_DATA(ERR, "(%s) %s: built-in vhost net backend is disabled.\n",
+ dev->ifname, __func__);
return 0;
}
}
static __rte_noinline uint32_t
-virtio_dev_rx_async_submit_split(struct virtio_net *dev,
- struct vhost_virtqueue *vq, uint16_t queue_id,
- struct rte_mbuf **pkts, uint32_t count)
+virtio_dev_rx_async_submit_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ uint16_t queue_id, struct rte_mbuf **pkts, uint32_t count,
+ int16_t dma_id, uint16_t vchan_id)
{
struct buf_vector buf_vec[BUF_VECTOR_MAX];
uint32_t pkt_idx = 0;
struct vhost_async *async = vq->async;
struct async_inflight_info *pkts_info = async->pkts_info;
uint32_t pkt_err = 0;
- int32_t n_xfer;
+ uint16_t n_xfer;
uint16_t slot_idx = 0;
/*
if (unlikely(reserve_avail_buf_split(dev, vq, pkt_len, buf_vec,
&num_buffers, avail_head, &nr_vec) < 0)) {
- VHOST_LOG_DATA(DEBUG, "(%d) failed to get enough desc from vring\n",
- dev->vid);
+ VHOST_LOG_DATA(DEBUG, "(%s) failed to get enough desc from vring\n",
+ dev->ifname);
vq->shadow_used_idx -= num_buffers;
break;
}
- VHOST_LOG_DATA(DEBUG, "(%d) current index %d | end index %d\n",
- dev->vid, vq->last_avail_idx, vq->last_avail_idx + num_buffers);
+ VHOST_LOG_DATA(DEBUG, "(%s) current index %d | end index %d\n",
+ dev->ifname, vq->last_avail_idx, vq->last_avail_idx + num_buffers);
if (mbuf_to_desc(dev, vq, pkts[pkt_idx], buf_vec, nr_vec, num_buffers, true) < 0) {
vq->shadow_used_idx -= num_buffers;
if (unlikely(pkt_idx == 0))
return 0;
- n_xfer = async->ops.transfer_data(dev->vid, queue_id, async->iov_iter, 0, pkt_idx);
- if (unlikely(n_xfer < 0)) {
- VHOST_LOG_DATA(ERR, "(%d) %s: failed to transfer data for queue id %d.\n",
- dev->vid, __func__, queue_id);
- n_xfer = 0;
- }
+ n_xfer = vhost_async_dma_transfer(dev, vq, dma_id, vchan_id, async->pkts_idx,
+ async->iov_iter, pkt_idx);
pkt_err = pkt_idx - n_xfer;
if (unlikely(pkt_err)) {
uint16_t num_descs = 0;
+ VHOST_LOG_DATA(DEBUG, "(%s) %s: failed to transfer %u packets for queue %u.\n",
+ dev->ifname, __func__, pkt_err, queue_id);
+
/* update number of completed packets */
pkt_idx = n_xfer;
if (unlikely(vhost_enqueue_async_packed(dev, vq, pkt, buf_vec,
nr_descs, nr_buffers) < 0)) {
- VHOST_LOG_DATA(DEBUG, "(%d) failed to get enough desc from vring\n", dev->vid);
+ VHOST_LOG_DATA(DEBUG, "(%s) failed to get enough desc from vring\n", dev->ifname);
return -1;
}
- VHOST_LOG_DATA(DEBUG, "(%d) current index %d | end index %d\n",
- dev->vid, vq->last_avail_idx, vq->last_avail_idx + *nr_descs);
+ VHOST_LOG_DATA(DEBUG, "(%s) current index %d | end index %d\n",
+ dev->ifname, vq->last_avail_idx, vq->last_avail_idx + *nr_descs);
return 0;
}
}
static __rte_noinline uint32_t
-virtio_dev_rx_async_submit_packed(struct virtio_net *dev,
- struct vhost_virtqueue *vq, uint16_t queue_id,
- struct rte_mbuf **pkts, uint32_t count)
+virtio_dev_rx_async_submit_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ uint16_t queue_id, struct rte_mbuf **pkts, uint32_t count,
+ int16_t dma_id, uint16_t vchan_id)
{
uint32_t pkt_idx = 0;
uint32_t remained = count;
- int32_t n_xfer;
+ uint16_t n_xfer;
uint16_t num_buffers;
uint16_t num_descs;
if (unlikely(pkt_idx == 0))
return 0;
- n_xfer = async->ops.transfer_data(dev->vid, queue_id, async->iov_iter, 0, pkt_idx);
- if (unlikely(n_xfer < 0)) {
- VHOST_LOG_DATA(ERR, "(%d) %s: failed to transfer data for queue id %d.\n",
- dev->vid, __func__, queue_id);
- n_xfer = 0;
- }
-
- pkt_err = pkt_idx - n_xfer;
+ n_xfer = vhost_async_dma_transfer(dev, vq, dma_id, vchan_id, async->pkts_idx,
+ async->iov_iter, pkt_idx);
async_iter_reset(async);
- if (unlikely(pkt_err))
+ pkt_err = pkt_idx - n_xfer;
+ if (unlikely(pkt_err)) {
+ VHOST_LOG_DATA(DEBUG, "(%s) %s: failed to transfer %u packets for queue %u.\n",
+ dev->ifname, __func__, pkt_err, queue_id);
dma_error_handler_packed(vq, slot_idx, pkt_err, &pkt_idx);
+ }
if (likely(vq->shadow_used_idx)) {
/* keep used descriptors. */
static __rte_always_inline uint16_t
vhost_poll_enqueue_completed(struct virtio_net *dev, uint16_t queue_id,
- struct rte_mbuf **pkts, uint16_t count)
+ struct rte_mbuf **pkts, uint16_t count, int16_t dma_id,
+ uint16_t vchan_id)
{
struct vhost_virtqueue *vq = dev->virtqueue[queue_id];
struct vhost_async *async = vq->async;
struct async_inflight_info *pkts_info = async->pkts_info;
- int32_t n_cpl;
+ uint16_t nr_cpl_pkts = 0;
uint16_t n_descs = 0, n_buffers = 0;
uint16_t start_idx, from, i;
- n_cpl = async->ops.check_completed_copies(dev->vid, queue_id, 0, count);
- if (unlikely(n_cpl < 0)) {
- VHOST_LOG_DATA(ERR, "(%d) %s: failed to check completed copies for queue id %d.\n",
- dev->vid, __func__, queue_id);
- return 0;
+ /* Check completed copies for the given DMA vChannel */
+ vhost_async_dma_check_completed(dev, dma_id, vchan_id, VHOST_DMA_MAX_COPY_COMPLETE);
+
+ start_idx = async_get_first_inflight_pkt_idx(vq);
+ /**
+ * Calculate the number of copy completed packets.
+ * Note that there may be completed packets even if
+ * no copies are reported done by the given DMA vChannel,
+ * as it's possible that a virtqueue uses multiple DMA
+ * vChannels.
+ */
+ from = start_idx;
+ while (vq->async->pkts_cmpl_flag[from] && count--) {
+ vq->async->pkts_cmpl_flag[from] = false;
+ from++;
+ if (from >= vq->size)
+ from -= vq->size;
+ nr_cpl_pkts++;
}
- if (n_cpl == 0)
+ if (nr_cpl_pkts == 0)
return 0;
- start_idx = async_get_first_inflight_pkt_idx(vq);
-
- for (i = 0; i < n_cpl; i++) {
+ for (i = 0; i < nr_cpl_pkts; i++) {
from = (start_idx + i) % vq->size;
/* Only used with packed ring */
n_buffers += pkts_info[from].nr_buffers;
pkts[i] = pkts_info[from].mbuf;
}
- async->pkts_inflight_n -= n_cpl;
+ async->pkts_inflight_n -= nr_cpl_pkts;
if (likely(vq->enabled && vq->access_ok)) {
if (vq_is_packed(dev)) {
}
}
- return n_cpl;
+ return nr_cpl_pkts;
}
uint16_t
rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
- struct rte_mbuf **pkts, uint16_t count)
+ struct rte_mbuf **pkts, uint16_t count, int16_t dma_id,
+ uint16_t vchan_id)
{
struct virtio_net *dev = get_device(vid);
struct vhost_virtqueue *vq;
if (unlikely(!dev))
return 0;
- VHOST_LOG_DATA(DEBUG, "(%d) %s\n", dev->vid, __func__);
+ VHOST_LOG_DATA(DEBUG, "(%s) %s\n", dev->ifname, __func__);
if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
- VHOST_LOG_DATA(ERR, "(%d) %s: invalid virtqueue idx %d.\n",
- dev->vid, __func__, queue_id);
+ VHOST_LOG_DATA(ERR, "(%s) %s: invalid virtqueue idx %d.\n",
+ dev->ifname, __func__, queue_id);
+ return 0;
+ }
+
+ if (unlikely(!dma_copy_track[dma_id].vchans ||
+ !dma_copy_track[dma_id].vchans[vchan_id].pkts_cmpl_flag_addr)) {
+ VHOST_LOG_DATA(ERR, "(%s) %s: invalid channel %d:%u.\n", dev->ifname, __func__,
+ dma_id, vchan_id);
return 0;
}
vq = dev->virtqueue[queue_id];
- if (unlikely(!vq->async)) {
- VHOST_LOG_DATA(ERR, "(%d) %s: async not registered for queue id %d.\n",
- dev->vid, __func__, queue_id);
+ if (!rte_spinlock_trylock(&vq->access_lock)) {
+ VHOST_LOG_DATA(DEBUG, "(%s) %s: virtqueue %u is busy.\n", dev->ifname, __func__,
+ queue_id);
return 0;
}
- rte_spinlock_lock(&vq->access_lock);
+ if (unlikely(!vq->async)) {
+ VHOST_LOG_DATA(ERR, "(%s) %s: async not registered for virtqueue %d.\n",
+ dev->ifname, __func__, queue_id);
+ goto out;
+ }
- n_pkts_cpl = vhost_poll_enqueue_completed(dev, queue_id, pkts, count);
+ n_pkts_cpl = vhost_poll_enqueue_completed(dev, queue_id, pkts, count, dma_id, vchan_id);
+ vhost_queue_stats_update(dev, vq, pkts, n_pkts_cpl);
+ vq->stats.inflight_completed += n_pkts_cpl;
+
+out:
rte_spinlock_unlock(&vq->access_lock);
return n_pkts_cpl;
uint16_t
rte_vhost_clear_queue_thread_unsafe(int vid, uint16_t queue_id,
- struct rte_mbuf **pkts, uint16_t count)
+ struct rte_mbuf **pkts, uint16_t count, int16_t dma_id,
+ uint16_t vchan_id)
{
struct virtio_net *dev = get_device(vid);
struct vhost_virtqueue *vq;
if (!dev)
return 0;
- VHOST_LOG_DATA(DEBUG, "(%d) %s\n", dev->vid, __func__);
+ VHOST_LOG_DATA(DEBUG, "(%s) %s\n", dev->ifname, __func__);
if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
- VHOST_LOG_DATA(ERR, "(%d) %s: invalid virtqueue idx %d.\n",
- dev->vid, __func__, queue_id);
+ VHOST_LOG_DATA(ERR, "(%s) %s: invalid virtqueue idx %d.\n",
+ dev->ifname, __func__, queue_id);
return 0;
}
vq = dev->virtqueue[queue_id];
+ if (unlikely(!rte_spinlock_is_locked(&vq->access_lock))) {
+ VHOST_LOG_DATA(ERR, "(%s) %s() called without access lock taken.\n",
+ dev->ifname, __func__);
+ return -1;
+ }
+
if (unlikely(!vq->async)) {
- VHOST_LOG_DATA(ERR, "(%d) %s: async not registered for queue id %d.\n",
- dev->vid, __func__, queue_id);
+ VHOST_LOG_DATA(ERR, "(%s) %s: async not registered for queue id %d.\n",
+ dev->ifname, __func__, queue_id);
+ return 0;
+ }
+
+ if (unlikely(!dma_copy_track[dma_id].vchans ||
+ !dma_copy_track[dma_id].vchans[vchan_id].pkts_cmpl_flag_addr)) {
+ VHOST_LOG_DATA(ERR, "(%s) %s: invalid channel %d:%u.\n", dev->ifname, __func__,
+ dma_id, vchan_id);
return 0;
}
- n_pkts_cpl = vhost_poll_enqueue_completed(dev, queue_id, pkts, count);
+ n_pkts_cpl = vhost_poll_enqueue_completed(dev, queue_id, pkts, count, dma_id, vchan_id);
+
+ vhost_queue_stats_update(dev, vq, pkts, n_pkts_cpl);
+ vq->stats.inflight_completed += n_pkts_cpl;
return n_pkts_cpl;
}
static __rte_always_inline uint32_t
virtio_dev_rx_async_submit(struct virtio_net *dev, uint16_t queue_id,
- struct rte_mbuf **pkts, uint32_t count)
+ struct rte_mbuf **pkts, uint32_t count, int16_t dma_id, uint16_t vchan_id)
{
struct vhost_virtqueue *vq;
uint32_t nb_tx = 0;
- VHOST_LOG_DATA(DEBUG, "(%d) %s\n", dev->vid, __func__);
+ VHOST_LOG_DATA(DEBUG, "(%s) %s\n", dev->ifname, __func__);
if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
- VHOST_LOG_DATA(ERR, "(%d) %s: invalid virtqueue idx %d.\n",
- dev->vid, __func__, queue_id);
+ VHOST_LOG_DATA(ERR, "(%s) %s: invalid virtqueue idx %d.\n",
+ dev->ifname, __func__, queue_id);
+ return 0;
+ }
+
+ if (unlikely(!dma_copy_track[dma_id].vchans ||
+ !dma_copy_track[dma_id].vchans[vchan_id].pkts_cmpl_flag_addr)) {
+ VHOST_LOG_DATA(ERR, "(%s) %s: invalid channel %d:%u.\n", dev->ifname, __func__,
+ dma_id, vchan_id);
return 0;
}
if (vq_is_packed(dev))
nb_tx = virtio_dev_rx_async_submit_packed(dev, vq, queue_id,
- pkts, count);
+ pkts, count, dma_id, vchan_id);
else
nb_tx = virtio_dev_rx_async_submit_split(dev, vq, queue_id,
- pkts, count);
+ pkts, count, dma_id, vchan_id);
+
+ vq->stats.inflight_submitted += nb_tx;
out:
if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
uint16_t
rte_vhost_submit_enqueue_burst(int vid, uint16_t queue_id,
- struct rte_mbuf **pkts, uint16_t count)
+ struct rte_mbuf **pkts, uint16_t count, int16_t dma_id,
+ uint16_t vchan_id)
{
struct virtio_net *dev = get_device(vid);
return 0;
if (unlikely(!(dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET))) {
- VHOST_LOG_DATA(ERR,
- "(%d) %s: built-in vhost net backend is disabled.\n",
- dev->vid, __func__);
+ VHOST_LOG_DATA(ERR, "(%s) %s: built-in vhost net backend is disabled.\n",
+ dev->ifname, __func__);
return 0;
}
- return virtio_dev_rx_async_submit(dev, queue_id, pkts, count);
+ return virtio_dev_rx_async_submit(dev, queue_id, pkts, count, dma_id, vchan_id);
}
static inline bool
}
static __rte_always_inline void
-vhost_dequeue_offload_legacy(struct virtio_net_hdr *hdr, struct rte_mbuf *m)
+vhost_dequeue_offload_legacy(struct virtio_net *dev, struct virtio_net_hdr *hdr,
+ struct rte_mbuf *m)
{
uint8_t l4_proto = 0;
struct rte_tcp_hdr *tcp_hdr = NULL;
m->l4_len = sizeof(struct rte_udp_hdr);
break;
default:
- VHOST_LOG_DATA(WARNING,
- "unsupported gso type %u.\n", hdr->gso_type);
+ VHOST_LOG_DATA(WARNING, "(%s) unsupported gso type %u.\n",
+ dev->ifname, hdr->gso_type);
goto error;
}
}
}
static __rte_always_inline void
-vhost_dequeue_offload(struct virtio_net_hdr *hdr, struct rte_mbuf *m,
- bool legacy_ol_flags)
+vhost_dequeue_offload(struct virtio_net *dev, struct virtio_net_hdr *hdr,
+ struct rte_mbuf *m, bool legacy_ol_flags)
{
struct rte_net_hdr_lens hdr_lens;
int l4_supported = 0;
return;
if (legacy_ol_flags) {
- vhost_dequeue_offload_legacy(hdr, m);
+ vhost_dequeue_offload_legacy(dev, hdr, m);
return;
}
}
static __rte_always_inline int
-copy_desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
+desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
struct buf_vector *buf_vec, uint16_t nr_vec,
struct rte_mbuf *m, struct rte_mempool *mbuf_pool,
- bool legacy_ol_flags)
+ bool legacy_ol_flags, uint16_t slot_idx, bool is_async)
{
- uint32_t buf_avail, buf_offset;
- uint64_t buf_addr, buf_len;
+ uint32_t buf_avail, buf_offset, buf_len;
+ uint64_t buf_addr, buf_iova;
uint32_t mbuf_avail, mbuf_offset;
uint32_t cpy_len;
struct rte_mbuf *cur = m, *prev = m;
struct virtio_net_hdr *hdr = NULL;
/* A counter to avoid desc dead loop chain */
uint16_t vec_idx = 0;
- struct batch_copy_elem *batch_copy = vq->batch_copy_elems;
- int error = 0;
+ struct vhost_async *async = vq->async;
+ struct async_inflight_info *pkts_info;
buf_addr = buf_vec[vec_idx].buf_addr;
+ buf_iova = buf_vec[vec_idx].buf_iova;
buf_len = buf_vec[vec_idx].buf_len;
- if (unlikely(buf_len < dev->vhost_hlen && nr_vec <= 1)) {
- error = -1;
- goto out;
- }
+ if (unlikely(buf_len < dev->vhost_hlen && nr_vec <= 1))
+ return -1;
if (virtio_net_with_host_offload(dev)) {
if (unlikely(buf_len < sizeof(struct virtio_net_hdr))) {
buf_offset = dev->vhost_hlen - buf_len;
vec_idx++;
buf_addr = buf_vec[vec_idx].buf_addr;
+ buf_iova = buf_vec[vec_idx].buf_iova;
buf_len = buf_vec[vec_idx].buf_len;
buf_avail = buf_len - buf_offset;
} else if (buf_len == dev->vhost_hlen) {
if (unlikely(++vec_idx >= nr_vec))
- goto out;
+ goto error;
buf_addr = buf_vec[vec_idx].buf_addr;
+ buf_iova = buf_vec[vec_idx].buf_iova;
buf_len = buf_vec[vec_idx].buf_len;
buf_offset = 0;
mbuf_offset = 0;
mbuf_avail = m->buf_len - RTE_PKTMBUF_HEADROOM;
+
+ if (is_async) {
+ pkts_info = async->pkts_info;
+ if (async_iter_initialize(dev, async))
+ return -1;
+ }
+
while (1) {
cpy_len = RTE_MIN(buf_avail, mbuf_avail);
- if (likely(cpy_len > MAX_BATCH_LEN ||
- vq->batch_copy_nb_elems >= vq->size ||
- (hdr && cur == m))) {
- rte_memcpy(rte_pktmbuf_mtod_offset(cur, void *,
- mbuf_offset),
- (void *)((uintptr_t)(buf_addr +
- buf_offset)), cpy_len);
+ if (is_async) {
+ if (async_fill_seg(dev, vq, cur, mbuf_offset,
+ buf_iova + buf_offset, cpy_len, false) < 0)
+ goto error;
} else {
- batch_copy[vq->batch_copy_nb_elems].dst =
- rte_pktmbuf_mtod_offset(cur, void *,
- mbuf_offset);
- batch_copy[vq->batch_copy_nb_elems].src =
- (void *)((uintptr_t)(buf_addr + buf_offset));
- batch_copy[vq->batch_copy_nb_elems].len = cpy_len;
- vq->batch_copy_nb_elems++;
+ sync_fill_seg(dev, vq, cur, mbuf_offset,
+ buf_addr + buf_offset,
+ buf_iova + buf_offset, cpy_len, false);
}
mbuf_avail -= cpy_len;
break;
buf_addr = buf_vec[vec_idx].buf_addr;
+ buf_iova = buf_vec[vec_idx].buf_iova;
buf_len = buf_vec[vec_idx].buf_len;
buf_offset = 0;
if (mbuf_avail == 0) {
cur = rte_pktmbuf_alloc(mbuf_pool);
if (unlikely(cur == NULL)) {
- VHOST_LOG_DATA(ERR, "Failed to "
- "allocate memory for mbuf.\n");
- error = -1;
- goto out;
+ VHOST_LOG_DATA(ERR, "(%s) failed to allocate memory for mbuf.\n",
+ dev->ifname);
+ goto error;
}
prev->next = cur;
prev->data_len = mbuf_offset;
m->pkt_len += mbuf_offset;
- if (hdr)
- vhost_dequeue_offload(hdr, m, legacy_ol_flags);
+ if (is_async) {
+ async_iter_finalize(async);
+ if (hdr)
+ pkts_info[slot_idx].nethdr = *hdr;
+ } else {
+ if (hdr)
+ vhost_dequeue_offload(dev, hdr, m, legacy_ol_flags);
+ }
-out:
+ return 0;
+error:
+ if (is_async)
+ async_iter_cancel(async);
- return error;
+ return -1;
}
static void
}
static int
-virtio_dev_extbuf_alloc(struct rte_mbuf *pkt, uint32_t size)
+virtio_dev_extbuf_alloc(struct virtio_net *dev, struct rte_mbuf *pkt, uint32_t size)
{
struct rte_mbuf_ext_shared_info *shinfo = NULL;
uint32_t total_len = RTE_PKTMBUF_HEADROOM + size;
virtio_dev_extbuf_free, buf);
if (unlikely(shinfo == NULL)) {
rte_free(buf);
- VHOST_LOG_DATA(ERR, "Failed to init shinfo\n");
+ VHOST_LOG_DATA(ERR, "(%s) failed to init shinfo\n", dev->ifname);
return -1;
}
return 0;
/* attach an external buffer if supported */
- if (dev->extbuf && !virtio_dev_extbuf_alloc(pkt, data_len))
+ if (dev->extbuf && !virtio_dev_extbuf_alloc(dev, pkt, data_len))
return 0;
/* check if chained buffers are allowed */
rte_prefetch0(&vq->avail->ring[vq->last_avail_idx & (vq->size - 1)]);
- VHOST_LOG_DATA(DEBUG, "(%d) %s\n", dev->vid, __func__);
+ VHOST_LOG_DATA(DEBUG, "(%s) %s\n", dev->ifname, __func__);
count = RTE_MIN(count, MAX_PKT_BURST);
count = RTE_MIN(count, free_entries);
- VHOST_LOG_DATA(DEBUG, "(%d) about to dequeue %u buffers\n",
- dev->vid, count);
+ VHOST_LOG_DATA(DEBUG, "(%s) about to dequeue %u buffers\n",
+ dev->ifname, count);
if (rte_pktmbuf_alloc_bulk(mbuf_pool, pkts, count))
return 0;
* is required. Drop this packet.
*/
if (!allocerr_warned) {
- VHOST_LOG_DATA(ERR,
- "Failed mbuf alloc of size %d from %s on %s.\n",
- buf_len, mbuf_pool->name, dev->ifname);
+ VHOST_LOG_DATA(ERR, "(%s) failed mbuf alloc of size %d from %s.\n",
+ dev->ifname, buf_len, mbuf_pool->name);
allocerr_warned = true;
}
dropped += 1;
break;
}
- err = copy_desc_to_mbuf(dev, vq, buf_vec, nr_vec, pkts[i],
- mbuf_pool, legacy_ol_flags);
+ err = desc_to_mbuf(dev, vq, buf_vec, nr_vec, pkts[i],
+ mbuf_pool, legacy_ol_flags, 0, false);
if (unlikely(err)) {
if (!allocerr_warned) {
- VHOST_LOG_DATA(ERR,
- "Failed to copy desc to mbuf on %s.\n",
+ VHOST_LOG_DATA(ERR, "(%s) failed to copy desc to mbuf.\n",
dev->ifname);
allocerr_warned = true;
}
i++;
break;
}
+
}
if (dropped)
if (virtio_net_with_host_offload(dev)) {
vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
hdr = (struct virtio_net_hdr *)(desc_addrs[i]);
- vhost_dequeue_offload(hdr, pkts[i], legacy_ol_flags);
+ vhost_dequeue_offload(dev, hdr, pkts[i], legacy_ol_flags);
}
}
if (unlikely(virtio_dev_pktmbuf_prep(dev, pkts, buf_len))) {
if (!allocerr_warned) {
- VHOST_LOG_DATA(ERR,
- "Failed mbuf alloc of size %d from %s on %s.\n",
- buf_len, mbuf_pool->name, dev->ifname);
+ VHOST_LOG_DATA(ERR, "(%s) failed mbuf alloc of size %d from %s.\n",
+ dev->ifname, buf_len, mbuf_pool->name);
allocerr_warned = true;
}
return -1;
}
- err = copy_desc_to_mbuf(dev, vq, buf_vec, nr_vec, pkts,
- mbuf_pool, legacy_ol_flags);
+ err = desc_to_mbuf(dev, vq, buf_vec, nr_vec, pkts,
+ mbuf_pool, legacy_ol_flags, 0, false);
if (unlikely(err)) {
if (!allocerr_warned) {
- VHOST_LOG_DATA(ERR,
- "Failed to copy desc to mbuf on %s.\n",
+ VHOST_LOG_DATA(ERR, "(%s) failed to copy desc to mbuf.\n",
dev->ifname);
allocerr_warned = true;
}
return 0;
if (unlikely(!(dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET))) {
- VHOST_LOG_DATA(ERR,
- "(%d) %s: built-in vhost net backend is disabled.\n",
- dev->vid, __func__);
+ VHOST_LOG_DATA(ERR, "(%s) %s: built-in vhost net backend is disabled.\n",
+ dev->ifname, __func__);
return 0;
}
if (unlikely(!is_valid_virt_queue_idx(queue_id, 1, dev->nr_vring))) {
- VHOST_LOG_DATA(ERR,
- "(%d) %s: invalid virtqueue idx %d.\n",
- dev->vid, __func__, queue_id);
+ VHOST_LOG_DATA(ERR, "(%s) %s: invalid virtqueue idx %d.\n",
+ dev->ifname, __func__, queue_id);
return 0;
}
rarp_mbuf = rte_net_make_rarp_packet(mbuf_pool, &dev->mac);
if (rarp_mbuf == NULL) {
- VHOST_LOG_DATA(ERR, "Failed to make RARP packet.\n");
+ VHOST_LOG_DATA(ERR, "(%s) failed to make RARP packet.\n", dev->ifname);
count = 0;
goto out;
}
* learning table will get updated first.
*/
pkts[0] = rarp_mbuf;
+ vhost_queue_stats_update(dev, vq, pkts, 1);
pkts++;
count -= 1;
}
count = virtio_dev_tx_split_compliant(dev, vq, mbuf_pool, pkts, count);
}
+ vhost_queue_stats_update(dev, vq, pkts, count);
+
+out:
+ if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+ vhost_user_iotlb_rd_unlock(vq);
+
+out_access_unlock:
+ rte_spinlock_unlock(&vq->access_lock);
+
+ if (unlikely(rarp_mbuf != NULL))
+ count += 1;
+
+ return count;
+}
+
+static __rte_always_inline uint16_t
+async_poll_dequeue_completed_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ struct rte_mbuf **pkts, uint16_t count, int16_t dma_id,
+ uint16_t vchan_id, bool legacy_ol_flags)
+{
+ uint16_t start_idx, from, i;
+ uint16_t nr_cpl_pkts = 0;
+ struct async_inflight_info *pkts_info = vq->async->pkts_info;
+
+ vhost_async_dma_check_completed(dev, dma_id, vchan_id, VHOST_DMA_MAX_COPY_COMPLETE);
+
+ start_idx = async_get_first_inflight_pkt_idx(vq);
+
+ from = start_idx;
+ while (vq->async->pkts_cmpl_flag[from] && count--) {
+ vq->async->pkts_cmpl_flag[from] = false;
+ from = (from + 1) & (vq->size - 1);
+ nr_cpl_pkts++;
+ }
+
+ if (nr_cpl_pkts == 0)
+ return 0;
+
+ for (i = 0; i < nr_cpl_pkts; i++) {
+ from = (start_idx + i) & (vq->size - 1);
+ pkts[i] = pkts_info[from].mbuf;
+
+ if (virtio_net_with_host_offload(dev))
+ vhost_dequeue_offload(dev, &pkts_info[from].nethdr, pkts[i],
+ legacy_ol_flags);
+ }
+
+ /* write back completed descs to used ring and update used idx */
+ write_back_completed_descs_split(vq, nr_cpl_pkts);
+ __atomic_add_fetch(&vq->used->idx, nr_cpl_pkts, __ATOMIC_RELEASE);
+ vhost_vring_call_split(dev, vq);
+
+ vq->async->pkts_inflight_n -= nr_cpl_pkts;
+
+ return nr_cpl_pkts;
+}
+
+static __rte_always_inline uint16_t
+virtio_dev_tx_async_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count,
+ int16_t dma_id, uint16_t vchan_id, bool legacy_ol_flags)
+{
+ static bool allocerr_warned;
+ bool dropped = false;
+ uint16_t free_entries;
+ uint16_t pkt_idx, slot_idx = 0;
+ uint16_t nr_done_pkts = 0;
+ uint16_t pkt_err = 0;
+ uint16_t n_xfer;
+ struct vhost_async *async = vq->async;
+ struct async_inflight_info *pkts_info = async->pkts_info;
+ struct rte_mbuf *pkts_prealloc[MAX_PKT_BURST];
+ uint16_t pkts_size = count;
+
+ /**
+ * The ordering between avail index and
+ * desc reads needs to be enforced.
+ */
+ free_entries = __atomic_load_n(&vq->avail->idx, __ATOMIC_ACQUIRE) -
+ vq->last_avail_idx;
+ if (free_entries == 0)
+ goto out;
+
+ rte_prefetch0(&vq->avail->ring[vq->last_avail_idx & (vq->size - 1)]);
+
+ async_iter_reset(async);
+
+ count = RTE_MIN(count, MAX_PKT_BURST);
+ count = RTE_MIN(count, free_entries);
+ VHOST_LOG_DATA(DEBUG, "(%s) about to dequeue %u buffers\n",
+ dev->ifname, count);
+
+ if (rte_pktmbuf_alloc_bulk(mbuf_pool, pkts_prealloc, count))
+ goto out;
+
+ for (pkt_idx = 0; pkt_idx < count; pkt_idx++) {
+ uint16_t head_idx = 0;
+ uint16_t nr_vec = 0;
+ uint16_t to;
+ uint32_t buf_len;
+ int err;
+ struct buf_vector buf_vec[BUF_VECTOR_MAX];
+ struct rte_mbuf *pkt = pkts_prealloc[pkt_idx];
+
+ if (unlikely(fill_vec_buf_split(dev, vq, vq->last_avail_idx,
+ &nr_vec, buf_vec,
+ &head_idx, &buf_len,
+ VHOST_ACCESS_RO) < 0)) {
+ dropped = true;
+ break;
+ }
+
+ err = virtio_dev_pktmbuf_prep(dev, pkt, buf_len);
+ if (unlikely(err)) {
+ /**
+ * mbuf allocation fails for jumbo packets when external
+ * buffer allocation is not allowed and linear buffer
+ * is required. Drop this packet.
+ */
+ if (!allocerr_warned) {
+ VHOST_LOG_DATA(ERR,
+ "(%s) %s: Failed mbuf alloc of size %d from %s\n",
+ dev->ifname, __func__, buf_len, mbuf_pool->name);
+ allocerr_warned = true;
+ }
+ dropped = true;
+ break;
+ }
+
+ slot_idx = (async->pkts_idx + pkt_idx) & (vq->size - 1);
+ err = desc_to_mbuf(dev, vq, buf_vec, nr_vec, pkt, mbuf_pool,
+ legacy_ol_flags, slot_idx, true);
+ if (unlikely(err)) {
+ if (!allocerr_warned) {
+ VHOST_LOG_DATA(ERR,
+ "(%s) %s: Failed to offload copies to async channel.\n",
+ dev->ifname, __func__);
+ allocerr_warned = true;
+ }
+ dropped = true;
+ break;
+ }
+
+ pkts_info[slot_idx].mbuf = pkt;
+
+ /* store used descs */
+ to = async->desc_idx_split & (vq->size - 1);
+ async->descs_split[to].id = head_idx;
+ async->descs_split[to].len = 0;
+ async->desc_idx_split++;
+
+ vq->last_avail_idx++;
+ }
+
+ if (unlikely(dropped))
+ rte_pktmbuf_free_bulk(&pkts_prealloc[pkt_idx], count - pkt_idx);
+
+ n_xfer = vhost_async_dma_transfer(dev, vq, dma_id, vchan_id, async->pkts_idx,
+ async->iov_iter, pkt_idx);
+
+ async->pkts_inflight_n += n_xfer;
+
+ pkt_err = pkt_idx - n_xfer;
+ if (unlikely(pkt_err)) {
+ VHOST_LOG_DATA(DEBUG, "(%s) %s: failed to transfer data.\n",
+ dev->ifname, __func__);
+
+ pkt_idx = n_xfer;
+ /* recover available ring */
+ vq->last_avail_idx -= pkt_err;
+
+ /**
+ * recover async channel copy related structures and free pktmbufs
+ * for error pkts.
+ */
+ async->desc_idx_split -= pkt_err;
+ while (pkt_err-- > 0) {
+ rte_pktmbuf_free(pkts_info[slot_idx & (vq->size - 1)].mbuf);
+ slot_idx--;
+ }
+ }
+
+ async->pkts_idx += pkt_idx;
+ if (async->pkts_idx >= vq->size)
+ async->pkts_idx -= vq->size;
+
+out:
+ /* DMA device may serve other queues, unconditionally check completed. */
+ nr_done_pkts = async_poll_dequeue_completed_split(dev, vq, pkts, pkts_size,
+ dma_id, vchan_id, legacy_ol_flags);
+
+ return nr_done_pkts;
+}
+
+__rte_noinline
+static uint16_t
+virtio_dev_tx_async_split_legacy(struct virtio_net *dev,
+ struct vhost_virtqueue *vq, struct rte_mempool *mbuf_pool,
+ struct rte_mbuf **pkts, uint16_t count,
+ int16_t dma_id, uint16_t vchan_id)
+{
+ return virtio_dev_tx_async_split(dev, vq, mbuf_pool,
+ pkts, count, dma_id, vchan_id, true);
+}
+
+__rte_noinline
+static uint16_t
+virtio_dev_tx_async_split_compliant(struct virtio_net *dev,
+ struct vhost_virtqueue *vq, struct rte_mempool *mbuf_pool,
+ struct rte_mbuf **pkts, uint16_t count,
+ int16_t dma_id, uint16_t vchan_id)
+{
+ return virtio_dev_tx_async_split(dev, vq, mbuf_pool,
+ pkts, count, dma_id, vchan_id, false);
+}
+
+uint16_t
+rte_vhost_async_try_dequeue_burst(int vid, uint16_t queue_id,
+ struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count,
+ int *nr_inflight, int16_t dma_id, uint16_t vchan_id)
+{
+ struct virtio_net *dev;
+ struct rte_mbuf *rarp_mbuf = NULL;
+ struct vhost_virtqueue *vq;
+ int16_t success = 1;
+
+ dev = get_device(vid);
+ if (!dev || !nr_inflight)
+ return 0;
+
+ *nr_inflight = -1;
+
+ if (unlikely(!(dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET))) {
+ VHOST_LOG_DATA(ERR, "(%s) %s: built-in vhost net backend is disabled.\n",
+ dev->ifname, __func__);
+ return 0;
+ }
+
+ if (unlikely(!is_valid_virt_queue_idx(queue_id, 1, dev->nr_vring))) {
+ VHOST_LOG_DATA(ERR, "(%s) %s: invalid virtqueue idx %d.\n",
+ dev->ifname, __func__, queue_id);
+ return 0;
+ }
+
+ if (unlikely(dma_id < 0 || dma_id >= RTE_DMADEV_DEFAULT_MAX)) {
+ VHOST_LOG_DATA(ERR, "(%s) %s: invalid dma id %d.\n",
+ dev->ifname, __func__, dma_id);
+ return 0;
+ }
+
+ if (unlikely(!dma_copy_track[dma_id].vchans ||
+ !dma_copy_track[dma_id].vchans[vchan_id].pkts_cmpl_flag_addr)) {
+ VHOST_LOG_DATA(ERR, "(%s) %s: invalid channel %d:%u.\n", dev->ifname, __func__,
+ dma_id, vchan_id);
+ return 0;
+ }
+
+ vq = dev->virtqueue[queue_id];
+
+ if (unlikely(rte_spinlock_trylock(&vq->access_lock) == 0))
+ return 0;
+
+ if (unlikely(vq->enabled == 0)) {
+ count = 0;
+ goto out_access_unlock;
+ }
+
+ if (unlikely(!vq->async)) {
+ VHOST_LOG_DATA(ERR, "(%s) %s: async not registered for queue id %d.\n",
+ dev->ifname, __func__, queue_id);
+ count = 0;
+ goto out_access_unlock;
+ }
+
+ if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+ vhost_user_iotlb_rd_lock(vq);
+
+ if (unlikely(vq->access_ok == 0))
+ if (unlikely(vring_translate(dev, vq) < 0)) {
+ count = 0;
+ goto out;
+ }
+
+ /*
+ * Construct a RARP broadcast packet, and inject it to the "pkts"
+ * array, to looks like that guest actually send such packet.
+ *
+ * Check user_send_rarp() for more information.
+ *
+ * broadcast_rarp shares a cacheline in the virtio_net structure
+ * with some fields that are accessed during enqueue and
+ * __atomic_compare_exchange_n causes a write if performed compare
+ * and exchange. This could result in false sharing between enqueue
+ * and dequeue.
+ *
+ * Prevent unnecessary false sharing by reading broadcast_rarp first
+ * and only performing compare and exchange if the read indicates it
+ * is likely to be set.
+ */
+ if (unlikely(__atomic_load_n(&dev->broadcast_rarp, __ATOMIC_ACQUIRE) &&
+ __atomic_compare_exchange_n(&dev->broadcast_rarp,
+ &success, 0, 0, __ATOMIC_RELEASE, __ATOMIC_RELAXED))) {
+
+ rarp_mbuf = rte_net_make_rarp_packet(mbuf_pool, &dev->mac);
+ if (rarp_mbuf == NULL) {
+ VHOST_LOG_DATA(ERR, "Failed to make RARP packet.\n");
+ count = 0;
+ goto out;
+ }
+ /*
+ * Inject it to the head of "pkts" array, so that switch's mac
+ * learning table will get updated first.
+ */
+ pkts[0] = rarp_mbuf;
+ pkts++;
+ count -= 1;
+ }
+
+ if (unlikely(vq_is_packed(dev))) {
+ static bool not_support_pack_log;
+ if (!not_support_pack_log) {
+ VHOST_LOG_DATA(ERR,
+ "(%s) %s: async dequeue does not support packed ring.\n",
+ dev->ifname, __func__);
+ not_support_pack_log = true;
+ }
+ count = 0;
+ goto out;
+ }
+
+ if (dev->flags & VIRTIO_DEV_LEGACY_OL_FLAGS)
+ count = virtio_dev_tx_async_split_legacy(dev, vq, mbuf_pool, pkts,
+ count, dma_id, vchan_id);
+ else
+ count = virtio_dev_tx_async_split_compliant(dev, vq, mbuf_pool, pkts,
+ count, dma_id, vchan_id);
+
+ *nr_inflight = vq->async->pkts_inflight_n;
+
out:
if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
vhost_user_iotlb_rd_unlock(vq);
git.droids-corp.org / dpdk.git / blobdiff