From: Eric Dumazet <edumazet@google.com>
Date: Mon, 16 May 2022 04:24:56 +0000 (-0700)
Subject: net: call skb_defer_free_flush() before each napi_poll()
X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=909876500251b3b48480a840bbf9053588254eee;p=linux.git

net: call skb_defer_free_flush() before each napi_poll()

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>
Signed-off-by: David S. Miller <davem@davemloft.net>
---

diff --git a/net/core/dev.c b/net/core/dev.c
index 6359f8953269c..04fd056f7f74d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6655,6 +6655,8 @@ 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;
@@ -6684,8 +6686,7 @@ 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 {