[PATCH AUTOSEL 6.18] net: napi: Skip last poll when arming gro timer in busy poll

[Sasha Levin <sashal@kernel.org>]

From: Martin Karsten <mkarsten@uwaterloo.ca>

[ 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 <mkarsten@uwaterloo.ca>
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