From: Krishna Kumar <krkumar2@in.ibm.com>
To: davem@davemloft.net
Cc: netdev@vger.kernel.org, Krishna Kumar <krkumar2@in.ibm.com>
Subject: [PATCH 3/3 Ver2] tcp: Slightly optimize tcp_sendmsg
Date: Thu, 10 Dec 2009 22:46:59 +0530 [thread overview]
Message-ID: <20091210171659.20777.67516.sendpatchset@localhost.localdomain> (raw)
In-Reply-To: <20091210171652.20777.79982.sendpatchset@localhost.localdomain>
From: Krishna Kumar <krkumar2@in.ibm.com>
Slightly optimize tcp_sendmsg since NETIF_F_SG is used many
times iteratively in the loop. The only other modification is
to change:
} else if (i == MAX_SKB_FRAGS ||
(!i &&
!(sk->sk_route_caps & NETIF_F_SG))) {
to:
} else if (i == MAX_SKB_FRAGS || !sg) {
The reason why this change is correct: this code (other than
the MAX_SKB_FRAGS case) executes only due to the else part
of: "if (skb_tailroom(skb) > 0) {" - i.e. there was no space
in the skb to put the data inline. Hence SG is false is a
sufficient condition, and there is no way a fragment can be
added to the skb.
Changelog:
- Added the above explanation for the change
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Acked-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
---
net/ipv4/tcp.c | 17 +++++++++--------
1 file changed, 9 insertions(+), 8 deletions(-)
diff -ruNp org/net/ipv4/tcp.c new/net/ipv4/tcp.c
--- org/net/ipv4/tcp.c 2009-12-10 21:22:41.000000000 +0530
+++ new/net/ipv4/tcp.c 2009-12-10 21:32:06.000000000 +0530
@@ -876,12 +876,12 @@ ssize_t tcp_sendpage(struct socket *sock
#define TCP_PAGE(sk) (sk->sk_sndmsg_page)
#define TCP_OFF(sk) (sk->sk_sndmsg_off)
-static inline int select_size(struct sock *sk)
+static inline int select_size(struct sock *sk, int sg)
{
struct tcp_sock *tp = tcp_sk(sk);
int tmp = tp->mss_cache;
- if (sk->sk_route_caps & NETIF_F_SG) {
+ if (sg) {
if (sk_can_gso(sk))
tmp = 0;
else {
@@ -905,7 +905,7 @@ int tcp_sendmsg(struct kiocb *iocb, stru
struct sk_buff *skb;
int iovlen, flags;
int mss_now, size_goal;
- int err, copied;
+ int sg, err, copied;
long timeo;
lock_sock(sk);
@@ -933,6 +933,8 @@ int tcp_sendmsg(struct kiocb *iocb, stru
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
goto out_err;
+ sg = sk->sk_route_caps & NETIF_F_SG;
+
while (--iovlen >= 0) {
int seglen = iov->iov_len;
unsigned char __user *from = iov->iov_base;
@@ -958,8 +960,9 @@ new_segment:
if (!sk_stream_memory_free(sk))
goto wait_for_sndbuf;
- skb = sk_stream_alloc_skb(sk, select_size(sk),
- sk->sk_allocation);
+ skb = sk_stream_alloc_skb(sk,
+ select_size(sk, sg),
+ sk->sk_allocation);
if (!skb)
goto wait_for_memory;
@@ -996,9 +999,7 @@ new_segment:
/* We can extend the last page
* fragment. */
merge = 1;
- } else if (i == MAX_SKB_FRAGS ||
- (!i &&
- !(sk->sk_route_caps & NETIF_F_SG))) {
+ } else if (i == MAX_SKB_FRAGS || !sg) {
/* Need to add new fragment and cannot
* do this because interface is non-SG,
* or because all the page slots are
next prev parent reply other threads:[~2009-12-10 17:16 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-12-10 17:16 [PATCH 2/3 Ver2] tcp: Remove unrequired operations in tcp_push() Krishna Kumar
2009-12-10 17:16 ` Krishna Kumar [this message]
2009-12-23 22:16 ` [PATCH 3/3 Ver2] tcp: Slightly optimize tcp_sendmsg David Miller
2009-12-23 22:15 ` [PATCH 2/3 Ver2] tcp: Remove unrequired operations in tcp_push() David Miller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20091210171659.20777.67516.sendpatchset@localhost.localdomain \
--to=krkumar2@in.ibm.com \
--cc=davem@davemloft.net \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox