[PATCH net-next v3] net: napi: Skip last poll when arming gro timer in busy poll

[Martin Karsten <mkarsten@uwaterloo.ca>]

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>
---
Changes since v2 [1]:
- Fix patch formatting problems.
- Leave STATE_PREFER_BUSY_POLL bit set when timer is armed.
  Don't want interrupts anyway until timer clears STATE_PREFER_BUSY_POLL.

Changes since RFC [2]:
- Sending only the cleanup/improvement patch to net-next.
- Expand commit message to summarize original issue.
- Streamline control flow.
- Improve comments.

[1] https://lore.kernel.org/all/f0ecdde3-de16-47ba-b795-fe0042114e96@uwaterloo.c/
[2] https://lore.kernel.org/all/20260428175134.1197036-4-dtatulea@nvidia.com/
---
 net/core/dev.c | 63 ++++++++++++++++++++++----------------------------
 1 file changed, 28 insertions(+), 35 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 267cf3854395..a7b8f9a3588a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6862,22 +6862,6 @@ 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,
@@ -6893,8 +6877,8 @@ 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()
@@ -6907,27 +6891,36 @@ 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 {
+		/* All we really want here is to re-enable device interrupts. */
+		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) {
+			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();
 }

base-commit: 627ac78f2741e2ebd2225e2e953b6964a8a9182f
-- 
2.54.0