diff options
| -rw-r--r-- | drivers/net/virtio_net.c | 81 |
1 files changed, 57 insertions, 24 deletions
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 61a57d134544..9f9b86874173 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -47,7 +47,8 @@ module_param(napi_tx, bool, 0644); #define VIRTIO_XDP_TX BIT(0) #define VIRTIO_XDP_REDIR BIT(1) -#define VIRTIO_XDP_FLAG BIT(0) +#define VIRTIO_XDP_FLAG BIT(0) +#define VIRTIO_ORPHAN_FLAG BIT(1) /* 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 @@ -85,6 +86,8 @@ struct virtnet_stat_desc { struct virtnet_sq_free_stats { u64 packets; u64 bytes; + u64 napi_packets; + u64 napi_bytes; }; struct virtnet_sq_stats { @@ -506,29 +509,50 @@ static struct xdp_frame *ptr_to_xdp(void *ptr) return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG); } -static void __free_old_xmit(struct send_queue *sq, bool in_napi, - struct virtnet_sq_free_stats *stats) +static bool is_orphan_skb(void *ptr) +{ + return (unsigned long)ptr & VIRTIO_ORPHAN_FLAG; +} + +static void *skb_to_ptr(struct sk_buff *skb, bool orphan) +{ + return (void *)((unsigned long)skb | (orphan ? VIRTIO_ORPHAN_FLAG : 0)); +} + +static struct sk_buff *ptr_to_skb(void *ptr) +{ + return (struct sk_buff *)((unsigned long)ptr & ~VIRTIO_ORPHAN_FLAG); +} + +static void __free_old_xmit(struct send_queue *sq, struct netdev_queue *txq, + bool in_napi, struct virtnet_sq_free_stats *stats) { unsigned int len; void *ptr; while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { - ++stats->packets; - if (!is_xdp_frame(ptr)) { - struct sk_buff *skb = ptr; + struct sk_buff *skb = ptr_to_skb(ptr); pr_debug("Sent skb %p\n", skb); - stats->bytes += skb->len; + if (is_orphan_skb(ptr)) { + stats->packets++; + stats->bytes += skb->len; + } else { + stats->napi_packets++; + stats->napi_bytes += skb->len; + } napi_consume_skb(skb, in_napi); } else { struct xdp_frame *frame = ptr_to_xdp(ptr); + stats->packets++; stats->bytes += xdp_get_frame_len(frame); xdp_return_frame(frame); } } + netdev_tx_completed_queue(txq, stats->napi_packets, stats->napi_bytes); } /* Converting between virtqueue no. and kernel tx/rx queue no. @@ -955,21 +979,22 @@ static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf) virtnet_rq_free_buf(vi, rq, buf); } -static void free_old_xmit(struct send_queue *sq, bool in_napi) +static void free_old_xmit(struct send_queue *sq, struct netdev_queue *txq, + bool in_napi) { struct virtnet_sq_free_stats stats = {0}; - __free_old_xmit(sq, in_napi, &stats); + __free_old_xmit(sq, txq, in_napi, &stats); /* Avoid overhead when no packets have been processed * happens when called speculatively from start_xmit. */ - if (!stats.packets) + if (!stats.packets && !stats.napi_packets) return; u64_stats_update_begin(&sq->stats.syncp); - u64_stats_add(&sq->stats.bytes, stats.bytes); - u64_stats_add(&sq->stats.packets, stats.packets); + u64_stats_add(&sq->stats.bytes, stats.bytes + stats.napi_bytes); + u64_stats_add(&sq->stats.packets, stats.packets + stats.napi_packets); u64_stats_update_end(&sq->stats.syncp); } @@ -1003,7 +1028,9 @@ static void check_sq_full_and_disable(struct virtnet_info *vi, * early means 16 slots are typically wasted. */ if (sq->vq->num_free < 2+MAX_SKB_FRAGS) { - netif_stop_subqueue(dev, qnum); + struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum); + + netif_tx_stop_queue(txq); u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.stop); u64_stats_update_end(&sq->stats.syncp); @@ -1012,7 +1039,7 @@ static void check_sq_full_and_disable(struct virtnet_info *vi, virtqueue_napi_schedule(&sq->napi, sq->vq); } else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) { /* More just got used, free them then recheck. */ - free_old_xmit(sq, false); + free_old_xmit(sq, txq, false); if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) { netif_start_subqueue(dev, qnum); u64_stats_update_begin(&sq->stats.syncp); @@ -1138,7 +1165,8 @@ static int virtnet_xdp_xmit(struct net_device *dev, } /* Free up any pending old buffers before queueing new ones. */ - __free_old_xmit(sq, false, &stats); + __free_old_xmit(sq, netdev_get_tx_queue(dev, sq - vi->sq), + false, &stats); for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; @@ -2313,7 +2341,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq) do { virtqueue_disable_cb(sq->vq); - free_old_xmit(sq, true); + free_old_xmit(sq, txq, true); } while (unlikely(!virtqueue_enable_cb_delayed(sq->vq))); if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) { @@ -2412,6 +2440,7 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) goto err_xdp_reg_mem_model; virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); + netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, qp_index)); virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi); return 0; @@ -2471,7 +2500,7 @@ 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); + free_old_xmit(sq, txq, true); if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) { if (netif_tx_queue_stopped(txq)) { @@ -2505,7 +2534,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget) return 0; } -static int xmit_skb(struct send_queue *sq, struct sk_buff *skb) +static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan) { struct virtio_net_hdr_mrg_rxbuf *hdr; const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest; @@ -2549,7 +2578,8 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb) return num_sg; num_sg++; } - return virtqueue_add_outbuf(sq->vq, sq->sg, num_sg, skb, GFP_ATOMIC); + return virtqueue_add_outbuf(sq->vq, sq->sg, num_sg, + skb_to_ptr(skb, orphan), GFP_ATOMIC); } static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) @@ -2559,24 +2589,25 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) struct send_queue *sq = &vi->sq[qnum]; int err; struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum); - bool kick = !netdev_xmit_more(); + bool xmit_more = netdev_xmit_more(); bool use_napi = sq->napi.weight; + bool kick; /* Free up any pending old buffers before queueing new ones. */ do { if (use_napi) virtqueue_disable_cb(sq->vq); - free_old_xmit(sq, false); + free_old_xmit(sq, txq, false); - } while (use_napi && kick && + } while (use_napi && !xmit_more && unlikely(!virtqueue_enable_cb_delayed(sq->vq))); /* timestamp packet in software */ skb_tx_timestamp(skb); /* Try to transmit */ - err = xmit_skb(sq, skb); + err = xmit_skb(sq, skb, !use_napi); /* This should not happen! */ if (unlikely(err)) { @@ -2598,7 +2629,9 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) check_sq_full_and_disable(vi, dev, sq); - if (kick || netif_xmit_stopped(txq)) { + kick = use_napi ? __netdev_tx_sent_queue(txq, skb->len, xmit_more) : + !xmit_more || netif_xmit_stopped(txq); + if (kick) { if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) { u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.kicks); |