From: Ben Hutchings <ben@decadent.org.uk>
To: Jakub Kicinski <kuba@kernel.org>, davem@davemloft.net
Cc: netdev@vger.kernel.org, edumazet@google.com, pabeni@redhat.com,
andrew+netdev@lunn.ch, horms@kernel.org, sdf@fomichev.me,
hawk@kernel.org, alexander.h.duyck@intel.com
Subject: Re: [PATCH net v2] net: consume xmit errors of GSO frames
Date: Wed, 25 Mar 2026 13:01:59 +0100 [thread overview]
Message-ID: <cfbb231e80caceb4138e37d036de7dca39ec7e7b.camel@decadent.org.uk> (raw)
In-Reply-To: <20260223235100.108939-1-kuba@kernel.org>
[-- Attachment #1: Type: text/plain, Size: 2108 bytes --]
On Mon, 2026-02-23 at 15:51 -0800, Jakub Kicinski wrote:
[...]
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -4822,6 +4822,8 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
> * to -1 or to their cpu id, but not to our id.
> */
> if (READ_ONCE(txq->xmit_lock_owner) != cpu) {
> + bool is_list = false;
> +
> if (dev_xmit_recursion())
> goto recursion_alert;
>
> @@ -4832,17 +4834,28 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
> HARD_TX_LOCK(dev, txq, cpu);
>
> if (!netif_xmit_stopped(txq)) {
> + is_list = !!skb->next;
> +
> dev_xmit_recursion_inc();
> skb = dev_hard_start_xmit(skb, dev, txq, &rc);
> dev_xmit_recursion_dec();
> - if (dev_xmit_complete(rc)) {
> - HARD_TX_UNLOCK(dev, txq);
> - goto out;
> - }
> +
> + /* GSO segments a single SKB into
> + * a list of frames. TCP expects error
> + * to mean none of the data was sent.
> + */
> + if (is_list)
> + rc = NETDEV_TX_OK;
> }
> HARD_TX_UNLOCK(dev, txq);
> + if (!skb) /* xmit completed */
> + goto out;
> +
> net_crit_ratelimited("Virtual device %s asks to queue packet!\n",
> dev->name);
> + /* NETDEV_TX_BUSY or queue was stopped */
> + if (!is_list)
> + rc = -ENETDOWN;
> } else {
> /* Recursion is detected! It is possible,
> * unfortunately
> @@ -4850,10 +4863,10 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
> recursion_alert:
> net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
> dev->name);
> + rc = -ENETDOWN;
> }
> }
>
> - rc = -ENETDOWN;
After removing this assignment, rc is not set properly in case the
device is down or TX is stopped.
Perhaps this assignment should be restored before the check for
(dev->flags & IFF_UP)?
Ben.
> rcu_read_unlock_bh();
>
> dev_core_stats_tx_dropped_inc(dev);
--
Ben Hutchings
Theory and practice are closer in theory than in practice - John Levine
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
prev parent reply other threads:[~2026-03-25 12:02 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-23 23:51 [PATCH net v2] net: consume xmit errors of GSO frames Jakub Kicinski
2026-02-24 9:00 ` Eric Dumazet
2026-02-26 10:40 ` patchwork-bot+netdevbpf
2026-03-25 12:01 ` Ben Hutchings [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=cfbb231e80caceb4138e37d036de7dca39ec7e7b.camel@decadent.org.uk \
--to=ben@decadent.org.uk \
--cc=alexander.h.duyck@intel.com \
--cc=andrew+netdev@lunn.ch \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=hawk@kernel.org \
--cc=horms@kernel.org \
--cc=kuba@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=sdf@fomichev.me \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox