[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20251114174300.19e9e2a1@kernel.org>
Date: Fri, 14 Nov 2025 17:43:00 -0800
From: Jakub Kicinski <kuba@...nel.org>
To: Eric Dumazet <edumazet@...gle.com>
Cc: "David S . Miller" <davem@...emloft.net>, Paolo Abeni
<pabeni@...hat.com>, Simon Horman <horms@...nel.org>, Neal Cardwell
<ncardwell@...gle.com>, Kuniyuki Iwashima <kuniyu@...gle.com>,
netdev@...r.kernel.org, eric.dumazet@...il.com
Subject: Re: [PATCH net] tcp: reduce tcp_comp_sack_slack_ns default value to
10 usec
On Fri, 14 Nov 2025 11:35:12 -0800 Eric Dumazet wrote:
> > Makes sense, or expedite/force the IPI if these skbs are 'deferred'
> >
> > I did not complete the series to call skb_data_unref() from
> > skb_attempt_defer_free().
> > I hope to finish this soon.
>
> In the meantime we could add this fix:
>
> diff --git a/net/core/skbuff.c b/net/core/skbuff.c
> index f34372666e67cee5329d3ba1d3c86f8622facac3..12d65357fc7f83cfa9f8714227c7b69035441644
> 100644
> --- a/net/core/skbuff.c
> +++ b/net/core/skbuff.c
> @@ -1480,6 +1480,9 @@ void napi_consume_skb(struct sk_buff *skb, int budget)
> DEBUG_NET_WARN_ON_ONCE(!in_softirq());
>
> if (skb->alloc_cpu != smp_processor_id() && !skb_shared(skb)) {
> + if (skb_zcopy(skb))
> + return consume_skb(skb);
> +
> skb_release_head_state(skb);
> return skb_attempt_defer_free(skb);
> }
Queued locally in the CI for now.
Powered by blists - more mailing lists