[3.19.y-ckt stable] Patch "net:Add sysctl_max_skb_frags" has been added to the 3.19.y-ckt tree

[Kamal Mostafa]

This is a note to let you know that I have just added a patch titled

    net:Add sysctl_max_skb_frags

to the linux-3.19.y-queue branch of the 3.19.y-ckt extended stable tree 
which can be found at:

    http://kernel.ubuntu.com/git/ubuntu/linux.git/log/?h=linux-3.19.y-queue

This patch is scheduled to be released in version 3.19.8-ckt16.

If you, or anyone else, feels it should not be added to this tree, please 
reply to this email.

For more information about the 3.19.y-ckt tree, see
https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable

Thanks.
-Kamal

---8<------------------------------------------------------------

>From 7967dbf3aacedc547099bc4b3d6eed5a2a601b91 Mon Sep 17 00:00:00 2001
From: Hans Westgaard Ry <hans.westgaard.ry at oracle.com>
Date: Wed, 3 Feb 2016 09:26:57 +0100
Subject: net:Add sysctl_max_skb_frags
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 5f74f82ea34c0da80ea0b49192bb5ea06e063593 ]

Devices may have limits on the number of fragments in an skb they support.
Current codebase uses a constant as maximum for number of fragments one
skb can hold and use.
When enabling scatter/gather and running traffic with many small messages
the codebase uses the maximum number of fragments and may thereby violate
the max for certain devices.
The patch introduces a global variable as max number of fragments.

Signed-off-by: Hans Westgaard Ry <hans.westgaard.ry at oracle.com>
Reviewed-by: Håkon Bugge <haakon.bugge at oracle.com>
Acked-by: Eric Dumazet <edumazet at google.com>
Signed-off-by: David S. Miller <davem at davemloft.net>
Signed-off-by: Kamal Mostafa <kamal at canonical.com>
---
 include/linux/skbuff.h     |  1 +
 net/core/skbuff.c          |  2 ++
 net/core/sysctl_net_core.c | 10 ++++++++++
 net/ipv4/tcp.c             |  4 ++--
 4 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 85b1df30..31a9eab 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -192,6 +192,7 @@ struct sk_buff;
 #else
 #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1)
 #endif
+extern int sysctl_max_skb_frags;

 typedef struct skb_frag_struct skb_frag_t;

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 35012ad..f7e9722 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -77,6 +77,8 @@

 struct kmem_cache *skbuff_head_cache __read_mostly;
 static struct kmem_cache *skbuff_fclone_cache __read_mostly;
+int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
+EXPORT_SYMBOL(sysctl_max_skb_frags);

 /**
  *	skb_panic - private function for out-of-line support
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index bbb1d5a..f15cda4 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -27,6 +27,7 @@ static int one = 1;
 static int ushort_max = USHRT_MAX;
 static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
+static int max_skb_frags = MAX_SKB_FRAGS;

 static int net_msg_warn;	/* Unused, but still a sysctl */

@@ -384,6 +385,15 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "max_skb_frags",
+		.data		= &sysctl_max_skb_frags,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+		.extra2		= &max_skb_frags,
+	},
 	{ }
 };

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 48e9bb6..4181016 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -921,7 +921,7 @@ new_segment:

 		i = skb_shinfo(skb)->nr_frags;
 		can_coalesce = skb_can_coalesce(skb, i, page, offset);
-		if (!can_coalesce && i >= MAX_SKB_FRAGS) {
+		if (!can_coalesce && i >= sysctl_max_skb_frags) {
 			tcp_mark_push(tp, skb);
 			goto new_segment;
 		}
@@ -1207,7 +1207,7 @@ new_segment:

 				if (!skb_can_coalesce(skb, i, pfrag->page,
 						      pfrag->offset)) {
-					if (i == MAX_SKB_FRAGS || !sg) {
+					if (i == sysctl_max_skb_frags || !sg) {
 						tcp_mark_push(tp, skb);
 						goto new_segment;
 					}
--
2.7.0