[PATCH AUTOSEL 6.18] net: napi: Skip last poll when arming gro timer in busy poll
From: Sasha Levin <sashal@kernel.org>
Date: 2026-08-31 13:41:27
Also in:
linux-patches, lkml, stable
Subsystem:
networking [general], the rest · Maintainers:
"David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Linus Torvalds
From: Martin Karsten <redacted>
[ Upstream commit 7599c13dbe7a2dc49e33f4c6581c6f1287d9410e ]
Skip the extra call to napi->poll(), if the gro timer is armed at the
end of busy polling. This removes the need for having a separate
__busy_poll_stop() routine and its code is moved directly into the
relevant places in busy_poll_stop(). Remove obsolete comment about
ndo_busy_poll_stop().
This is a follow-up to commit 58e2330bd455 ("net: napi: Avoid gro timer
misfiring at end of busypoll"), which has deferred arming the gro timer
to the end of __busy_poll_stop() to eliminate a race condition between
a short timer and long poll that could leave the queue stuck with
interrupts disabled and no timer armed.
Co-developed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Martin Karsten <redacted>
Link: https://patch.msgid.link/20260523012247.1574691-1-mkarsten@uwaterloo.ca
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
LLM Generated explanations, may be completely bogus:
Connection lost, reconnecting to https://agentn.us.api5.cursor.sh
(attempt 1)...
Retry attempt 1...
That background search on `linus-next` finished with no matches (it ran
~25 minutes and returned empty). The commit is already identified on
`origin/master` as `7599c13dbe7a2` — it went through the netdev tree,
not `linus-next`. That doesn’t change the **YES** backport
recommendation for 6.18.44.
net/core/dev.c | 62 ++++++++++++++++++++++----------------------------
1 file changed, 27 insertions(+), 35 deletions(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index a83083e8761b1..e61cf0b7487fb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c@@ -6787,22 +6787,6 @@ static void skb_defer_free_flush(void) #if defined(CONFIG_NET_RX_BUSY_POLL) -static void __busy_poll_stop(struct napi_struct *napi, unsigned long timeout) -{ - if (!timeout) { - gro_normal_list(&napi->gro); - __napi_schedule(napi); - return; - } - - /* Flush too old packets. If HZ < 1000, flush all packets */ - gro_flush_normal(&napi->gro, HZ >= 1000); - - clear_bit(NAPI_STATE_SCHED, &napi->state); - hrtimer_start(&napi->timer, ns_to_ktime(timeout), - HRTIMER_MODE_REL_PINNED); -} - enum { NAPI_F_PREFER_BUSY_POLL = 1, NAPI_F_END_ON_RESCHED = 2,
@@ -6818,8 +6802,8 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, /* Busy polling means there is a high chance device driver hard irq * could not grab NAPI_STATE_SCHED, and that NAPI_STATE_MISSED was * set in napi_schedule_prep(). - * Since we are about to call napi->poll() once more, we can safely - * clear NAPI_STATE_MISSED. + * Since we either call napi->poll() once more or start the timer, + * we can safely clear NAPI_STATE_MISSED. * * Note: x86 could use a single "lock and ..." instruction * to perform these two clear_bit()
@@ -6832,27 +6816,35 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, if (flags & NAPI_F_PREFER_BUSY_POLL) { napi->defer_hard_irqs_count = napi_get_defer_hard_irqs(napi); - if (napi->defer_hard_irqs_count) { - /* A short enough gro flush timeout and long enough - * poll can result in timer firing too early. - * Timer will be armed later if necessary. - */ + if (napi->defer_hard_irqs_count) timeout = napi_get_gro_flush_timeout(napi); + } + if (timeout) { + netpoll_poll_unlock(have_poll_lock); + + /* Drain aged GRO packets before clearing SCHED since the NAPI + * won't run again until after the timer fires. When HZ < 1000, + * GRO age comparison is too coarse, so flush everything. + */ + gro_flush_normal(&napi->gro, HZ >= 1000); + + clear_bit(NAPI_STATE_SCHED, &napi->state); + hrtimer_start(&napi->timer, ns_to_ktime(timeout), + HRTIMER_MODE_REL_PINNED); + } else { + /* Use driver poll to re-enable device interrupts. */ + rc = napi->poll(napi, budget); + /* Unless rc == budget we no longer own the NAPI instance, + * IRQ may fire on another CPU, poll this NAPI, and enter GRO. + */ + trace_napi_poll(napi, rc, budget); + netpoll_poll_unlock(have_poll_lock); + if (rc == budget) { + gro_normal_list(&napi->gro); + __napi_schedule(napi); } } - /* All we really want here is to re-enable device interrupts. - * Ideally, a new ndo_busy_poll_stop() could avoid another round. - */ - rc = napi->poll(napi, budget); - /* We can't gro_normal_list() here, because napi->poll() might have - * rearmed the napi (napi_complete_done()) in which case it could - * already be running on another CPU. - */ - trace_napi_poll(napi, rc, budget); - netpoll_poll_unlock(have_poll_lock); - if (rc == budget) - __busy_poll_stop(napi, timeout); bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); }
--
2.53.0