[PATCH net-next] tcp: tcp_make_synack() can use alloc_skb()

Subsystems: networking [general], networking [tcp], the rest

STALE5208d

2 messages, 2 authors, 2012-06-04 · open the first message on its own page

[PATCH net-next] tcp: tcp_make_synack() can use alloc_skb()

From: Eric Dumazet <hidden>
Date: 2012-06-04 05:50:47

From: Eric Dumazet <edumazet@google.com>

There is no value using sock_wmalloc() in tcp_make_synack().

A listener socket only sends SYNACK packets, they are not queued in a
socket queue, only in Qdisc and device layers, so the number of in
flight packets is limited in these layers. We used sock_wmalloc() with
the %force parameter set to 1 to ignore socket limits anyway.

This patch removes two atomic operations per SYNACK packet.

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/ipv4/tcp_output.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 803cbfe..f0b0e44 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2461,7 +2461,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 
 	if (cvp != NULL && cvp->s_data_constant && cvp->s_data_desired)
 		s_data_desired = cvp->s_data_desired;
-	skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15 + s_data_desired, 1, GFP_ATOMIC);
+	skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired, GFP_ATOMIC);
 	if (skb == NULL)
 		return NULL;
 

Re: [PATCH net-next] tcp: tcp_make_synack() can use alloc_skb()

From: David Miller <davem@davemloft.net>
Date: 2012-06-04 15:33:19

From: Eric Dumazet <redacted>
Date: Mon, 04 Jun 2012 07:50:43 +0200
From: Eric Dumazet <edumazet@google.com>

There is no value using sock_wmalloc() in tcp_make_synack().

A listener socket only sends SYNACK packets, they are not queued in a
socket queue, only in Qdisc and device layers, so the number of in
flight packets is limited in these layers. We used sock_wmalloc() with
the %force parameter set to 1 to ignore socket limits anyway.

This patch removes two atomic operations per SYNACK packet.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Looks good, applied.
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help