[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20251116202717.1542829-4-edumazet@google.com>
Date: Sun, 16 Nov 2025 20:27:17 +0000
From: Eric Dumazet <edumazet@...gle.com>
To: "David S . Miller" <davem@...emloft.net>, Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>
Cc: Simon Horman <horms@...nel.org>, Kuniyuki Iwashima <kuniyu@...gle.com>,
Jason Xing <kerneljasonxing@...il.com>, netdev@...r.kernel.org, eric.dumazet@...il.com,
Eric Dumazet <edumazet@...gle.com>
Subject: [PATCH v3 net-next 3/3] net: use napi_skb_cache even in process context
This is a followup of commit e20dfbad8aab ("net: fix napi_consume_skb()
with alien skbs").
Now the per-cpu napi_skb_cache is populated from TX completion path,
we can make use of this cache, especially for cpus not used
from a driver NAPI poll (primary user of napi_cache).
We can use the napi_skb_cache only if current context is not from hard irq.
With this patch, I consistently reach 130 Mpps on my UDP tx stress test
and reduce SLUB spinlock contention to smaller values.
Note there is still some SLUB contention for skb->head allocations.
I had to tune /sys/kernel/slab/skbuff_small_head/cpu_partial
and /sys/kernel/slab/skbuff_small_head/min_partial depending
on the platform taxonomy.
Signed-off-by: Eric Dumazet <edumazet@...gle.com>
---
net/core/skbuff.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8a0a4ca7fa5dbb2fa3044ee45bb0b9c8c3ca85ea..9feea830a4dbb61c1c661e802ed315eaeebcc809 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -666,7 +666,12 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
skb = napi_skb_cache_get(true);
if (unlikely(!skb))
return NULL;
+ } else if (!in_hardirq() && !irqs_disabled()) {
+ local_bh_disable();
+ skb = napi_skb_cache_get(false);
+ local_bh_enable();
}
+
if (!skb) {
fallback:
skb = kmem_cache_alloc_node(cache, gfp_mask & ~GFP_DMA, node);
--
2.52.0.rc1.455.g30608eb744-goog
Powered by blists - more mailing lists