From 07e1a9408b6c2f9d0cfb757b67dabb52da7a32b2 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 18 Sep 2026 20:47:28 -0400 Subject: [PATCH] virtio_net: copy zerocopy frags in start_xmit without NAPI Virtio-net without NAPI frees completed skbs lazily on the next start_xmit. Senders waiting for in-flight zerocopy buffers can deadlock if they cannot transmit more packets, as then no completed packets will be freed. When !use_napi, virtio-net already calls skb_orphan to avoid waiting up for transmitted skbs to be freed. For zerocopy packets that require deep copying on orphan (i.e. those that do not set SKBFL_DONT_ORPHAN, such as PACKET_TX_RING), call skb_orphan_frags before orphaning to release the buffers. This fixes the tpacket_snd slot reuse bug on skb_orphan for virtio-net, and prevents PACKET_TX_RING from running out of slots. This fix also touches vhost_net zerocopy packets, which also do not set SKBFL_DONT_ORPHAN. This is fine: vhost_net packets only encounter virtio-net in nested virtualization, and only if napi_tx is explicitly disabled (it has been default-enabled since Linux 4.12). In that rare case, copying the frags is desirable anyway to prevent holding guest descriptors pinned across unbounded intervals. This is a prerequisite for the next patch, which converts PACKET_TX_RING to standard zerocopy completion. Without this patch first, a bounded ring sender can stall indefinitely behind a virtio-net virtqueue that cannot reclaim. Fixes: 5cd8d46ea156 ("packet: copy user buffers before orphan or clone") Cc: stable@vger.kernel.org Cc: mst@redhat.com Cc: jasowangio@gmail.com Signed-off-by: Willem de Bruijn Link: https://patch.msgid.link/20260919004748.1463985-2-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/virtio_net.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index e34c52d059d3..bf82ef9874ab 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3349,6 +3349,14 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) else virtqueue_disable_cb(sq->vq); + if (!use_napi && + unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) { + DEV_STATS_INC(dev, tx_dropped); + dev_kfree_skb_any(skb); + kick = !xmit_more || netif_xmit_stopped(txq); + goto kick_vq; + } + /* timestamp packet in software */ skb_tx_timestamp(skb); @@ -3381,6 +3389,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) kick = use_napi ? __netdev_tx_sent_queue(txq, skb->len, xmit_more) : !xmit_more || netif_xmit_stopped(txq); +kick_vq: if (kick) { if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) { u64_stats_update_begin(&sq->stats.syncp);