@@ -2060,6 +2060,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
struct virtnet_sq *sq = container_of(napi, struct virtnet_sq, napi);
struct virtnet_info *vi = sq->vq->vdev->priv;
unsigned int index = vq2txq(sq->vq);
+ struct xsk_buff_pool *pool;
struct netdev_queue *txq;
int busy = 0;
int opaque;
@@ -2074,7 +2075,16 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
txq = netdev_get_tx_queue(vi->dev, index);
__netif_tx_lock(txq, raw_smp_processor_id());
virtqueue_disable_cb(sq->vq);
- free_old_xmit(sq, true);
+
+ rcu_read_lock();
+ pool = rcu_dereference(sq->xsk.pool);
+ if (pool) {
+ busy |= virtnet_xsk_xmit(sq, pool, budget);
+ rcu_read_unlock();
+ } else {
+ rcu_read_unlock();
+ free_old_xmit(sq, true);
+ }
if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
netif_tx_wake_queue(txq);
@@ -9,7 +9,8 @@
#include <net/xdp_sock_drv.h>
#define VIRTIO_XDP_FLAG BIT(0)
-#define VIRTIO_XMIT_DATA_MASK (VIRTIO_XDP_FLAG)
+#define VIRTIO_XSK_FLAG BIT(1)
+#define VIRTIO_XMIT_DATA_MASK (VIRTIO_XDP_FLAG | VIRTIO_XSK_FLAG)
/* RX packet size EWMA. The average packet size is used to determine the packet
* buffer size when refilling RX rings. As the entire RX ring may be refilled
@@ -7,6 +7,114 @@
static struct virtio_net_hdr_mrg_rxbuf xsk_hdr;
+static void sg_fill_dma(struct scatterlist *sg, dma_addr_t addr, u32 len)
+{
+ sg->dma_address = addr;
+ sg->length = len;
+}
+
+static void virtnet_xsk_check_queue(struct virtnet_sq *sq)
+{
+ struct virtnet_info *vi = sq->vq->vdev->priv;
+ struct net_device *dev = vi->dev;
+ int qnum = sq - vi->sq;
+
+ /* If it is a raw buffer queue, it does not check whether the status
+ * of the queue is stopped when sending. So there is no need to check
+ * the situation of the raw buffer queue.
+ */
+ if (virtnet_is_xdp_raw_buffer_queue(vi, qnum))
+ return;
+
+ /* If this sq is not the exclusive queue of the current cpu,
+ * then it may be called by start_xmit, so check it running out
+ * of space.
+ *
+ * Stop the queue to avoid getting packets that we are
+ * then unable to transmit. Then wait the tx interrupt.
+ */
+ if (sq->vq->num_free < 2 + MAX_SKB_FRAGS)
+ netif_stop_subqueue(dev, qnum);
+}
+
+static int virtnet_xsk_xmit_one(struct virtnet_sq *sq,
+ struct xsk_buff_pool *pool,
+ struct xdp_desc *desc)
+{
+ struct virtnet_info *vi;
+ dma_addr_t addr;
+
+ vi = sq->vq->vdev->priv;
+
+ addr = xsk_buff_raw_get_dma(pool, desc->addr);
+ xsk_buff_raw_dma_sync_for_device(pool, addr, desc->len);
+
+ sg_init_table(sq->sg, 2);
+
+ sg_fill_dma(sq->sg, sq->xsk.hdr_dma_address, vi->hdr_len);
+ sg_fill_dma(sq->sg + 1, addr, desc->len);
+
+ return virtqueue_add_outbuf(sq->vq, sq->sg, 2,
+ virtnet_xsk_to_ptr(desc->len), GFP_ATOMIC);
+}
+
+static int virtnet_xsk_xmit_batch(struct virtnet_sq *sq,
+ struct xsk_buff_pool *pool,
+ unsigned int budget,
+ struct virtnet_sq_stats *stats)
+{
+ struct xdp_desc *descs = pool->tx_descs;
+ u32 nb_pkts, max_pkts, i;
+ bool kick = false;
+ int err;
+
+ max_pkts = min_t(u32, budget, sq->vq->num_free / 2);
+
+ nb_pkts = xsk_tx_peek_release_desc_batch(pool, max_pkts);
+ if (!nb_pkts)
+ return 0;
+
+ for (i = 0; i < nb_pkts; i++) {
+ err = virtnet_xsk_xmit_one(sq, pool, &descs[i]);
+ if (unlikely(err))
+ break;
+
+ kick = true;
+ }
+
+ if (kick && virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq))
+ ++stats->kicks;
+
+ stats->xdp_tx += i;
+
+ return i;
+}
+
+bool virtnet_xsk_xmit(struct virtnet_sq *sq, struct xsk_buff_pool *pool,
+ int budget)
+{
+ struct virtnet_sq_stats stats = {};
+ int sent;
+
+ virtnet_free_old_xmit(sq, true, &stats);
+
+ sent = virtnet_xsk_xmit_batch(sq, pool, budget, &stats);
+
+ virtnet_xsk_check_queue(sq);
+
+ u64_stats_update_begin(&sq->stats.syncp);
+ sq->stats.packets += stats.packets;
+ sq->stats.bytes += stats.bytes;
+ sq->stats.kicks += stats.kicks;
+ sq->stats.xdp_tx += stats.xdp_tx;
+ u64_stats_update_end(&sq->stats.syncp);
+
+ if (xsk_uses_need_wakeup(pool))
+ xsk_set_tx_need_wakeup(pool);
+
+ return sent == budget;
+}
+
static int virtnet_rq_bind_xsk_pool(struct virtnet_info *vi, struct virtnet_rq *rq,
struct xsk_buff_pool *pool)
{
@@ -3,5 +3,18 @@
#ifndef __XSK_H__
#define __XSK_H__
+#define VIRTIO_XSK_FLAG_OFFSET 4
+
+static inline void *virtnet_xsk_to_ptr(u32 len)
+{
+ unsigned long p;
+
+ p = len << VIRTIO_XSK_FLAG_OFFSET;
+
+ return (void *)(p | VIRTIO_XSK_FLAG);
+}
+
int virtnet_xsk_pool_setup(struct net_device *dev, struct netdev_bpf *xdp);
+bool virtnet_xsk_xmit(struct virtnet_sq *sq, struct xsk_buff_pool *pool,
+ int budget);
#endif
The driver's tx napi is very important for XSK. It is responsible for obtaining data from the XSK queue and sending it out. At the beginning, we need to trigger tx napi. Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com> --- drivers/net/virtio/main.c | 12 +++- drivers/net/virtio/virtio_net.h | 3 +- drivers/net/virtio/xsk.c | 108 ++++++++++++++++++++++++++++++++ drivers/net/virtio/xsk.h | 13 ++++ 4 files changed, 134 insertions(+), 2 deletions(-)