Netdev List
 help / color / mirror / Atom feed
From: Vakul Garg <vakul.garg@nxp.com>
To: davem@davemloft.net
Cc: netdev@vger.kernel.org, tom@quantonium.net, borisp@mellanox.com,
	ebiggers@google.com, davejwatson@fb.com, doronrk@fb.com,
	Vakul Garg <vakul.garg@nxp.com>
Subject: [PATCH net-next] strparser: Call skb_unclone conditionally
Date: Sat, 30 Jun 2018 00:45:55 +0530	[thread overview]
Message-ID: <20180629191555.19874-1-vakul.garg@nxp.com> (raw)

Calling skb_unclone() is expensive as it triggers a memcpy operation.
Instead of calling skb_unclone() unconditionally, call it only when skb
has a shared frag_list. This improves tls rx throughout significantly.

Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Suggested-by: Boris Pismenny <borisp@mellanox.com>
---
 net/strparser/strparser.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 373836615c57..4f40a90ca016 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -155,11 +155,13 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 			/* We are going to append to the frags_list of head.
 			 * Need to unshare the frag_list.
 			 */
-			err = skb_unclone(head, GFP_ATOMIC);
-			if (err) {
-				STRP_STATS_INCR(strp->stats.mem_fail);
-				desc->error = err;
-				return 0;
+			if (skb_has_frag_list(head)) {
+				err = skb_unclone(head, GFP_ATOMIC);
+				if (err) {
+					STRP_STATS_INCR(strp->stats.mem_fail);
+					desc->error = err;
+					return 0;
+				}
 			}
 
 			if (unlikely(skb_shinfo(head)->frag_list)) {
@@ -216,14 +218,16 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 			memset(stm, 0, sizeof(*stm));
 			stm->strp.offset = orig_offset + eaten;
 		} else {
-			/* Unclone since we may be appending to an skb that we
+			/* Unclone if we are appending to an skb that we
 			 * already share a frag_list with.
 			 */
-			err = skb_unclone(skb, GFP_ATOMIC);
-			if (err) {
-				STRP_STATS_INCR(strp->stats.mem_fail);
-				desc->error = err;
-				break;
+			if (skb_has_frag_list(skb)) {
+				err = skb_unclone(skb, GFP_ATOMIC);
+				if (err) {
+					STRP_STATS_INCR(strp->stats.mem_fail);
+					desc->error = err;
+					break;
+				}
 			}
 
 			stm = _strp_msg(head);
-- 
2.13.6

             reply	other threads:[~2018-06-29 13:55 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-06-29 19:15 Vakul Garg [this message]
2018-06-30 12:25 ` [PATCH net-next] strparser: Call skb_unclone conditionally 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=20180629191555.19874-1-vakul.garg@nxp.com \
    --to=vakul.garg@nxp.com \
    --cc=borisp@mellanox.com \
    --cc=davejwatson@fb.com \
    --cc=davem@davemloft.net \
    --cc=doronrk@fb.com \
    --cc=ebiggers@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=tom@quantonium.net \
    /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