[PATCH net-next 4/4] net: call skb_defer_free_flush() before each napi_poll()

[Eric Dumazet <eric.dumazet@gmail.com>]

From: Eric Dumazet <edumazet@google.com>

skb_defer_free_flush() can consume cpu cycles,
it seems better to call it in the inner loop:

- Potentially frees page/skb that will be reallocated while hot.

- Account for the cpu cycles in the @time_limit determination.

- Keep softnet_data.defer_count small to reduce chances for
  skb_attempt_defer_free() to send an IPI.

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/core/dev.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index ac22fedfeaf72dc0d46f4793bbd9b2d5dd301730..aabb695e25f35402bbc85602e1bb9c86d2fa209e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6654,6 +6654,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 	for (;;) {
 		struct napi_struct *n;
 
+		skb_defer_free_flush(sd);
+
 		if (list_empty(&list)) {
 			if (!sd_has_rps_ipi_waiting(sd) && list_empty(&repoll))
 				goto end;
@@ -6683,8 +6685,7 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
 
 	net_rps_action_and_irq_enable(sd);
-end:
-	skb_defer_free_flush(sd);
+end:;
 }
 
 struct netdev_adjacent {
-- 
2.36.0.550.gb090851708-goog