From: Greg Kroah-Hartman <gregkh@suse.de>
Date: Fri, 16 Nov 2007 00:57:35 +0000 (-0800)
Subject: another tcp patch added to 2.6.23 review cycle
X-Git-Tag: v2.6.23.2~1
X-Git-Url: http://git.ipfire.org/gitweb/?a=commitdiff_plain;h=fab7fdb0b8a68f7ae422654f9c7d39e0f5433970;p=thirdparty%2Fkernel%2Fstable-queue.git

another tcp patch added to 2.6.23 review cycle
---

diff --git a/review-2.6.23-3/series b/review-2.6.23-3/series
index 709fb910271..8c1365fe446 100644
--- a/review-2.6.23-3/series
+++ b/review-2.6.23-3/series
@@ -5,6 +5,7 @@ add-get_unaligned-to-ieee80211_get_radiotap_len.patch
 fix-advertised-packet-scheduler-timer-resolution.patch
 fix-9p-protocol-build.patch
 fix-skb_with_overhead-calculations.patch
+tcp-fix-size-calculation-in-sk_stream_alloc_pskb.patch
 fix-kernel_accept-return-handling.patch
 softmac-fix-wext-mlme-request-reason-code-endianness.patch
 fix-error-returns-in-sys_socketpair.patch
diff --git a/review-2.6.23-3/tcp-fix-size-calculation-in-sk_stream_alloc_pskb.patch b/review-2.6.23-3/tcp-fix-size-calculation-in-sk_stream_alloc_pskb.patch
new file mode 100644
index 00000000000..a9e299ac143
--- /dev/null
+++ b/review-2.6.23-3/tcp-fix-size-calculation-in-sk_stream_alloc_pskb.patch
@@ -0,0 +1,60 @@
+From fb93134dfc2a6e6fbedc7c270a31da03fce88db9 Mon Sep 17 00:00:00 2001
+From: Herbert Xu <herbert@gondor.apana.org.au>
+Date: Wed, 14 Nov 2007 15:45:21 -0800
+To: Greg KH <greg@kroah.com>
+Subject: TCP: Fix size calculation in sk_stream_alloc_pskb
+
+From: Herbert Xu <herbert@gondor.apana.org.au>
+
+[TCP]: Fix size calculation in sk_stream_alloc_pskb
+
+[ Upstream commit: fb93134dfc2a6e6fbedc7c270a31da03fce88db9 ]
+
+We round up the header size in sk_stream_alloc_pskb so that
+TSO packets get zero tail room.  Unfortunately this rounding
+up is not coordinated with the select_size() function used by
+TCP to calculate the second parameter of sk_stream_alloc_pskb.
+
+As a result, we may allocate more than a page of data in the
+non-TSO case when exactly one page is desired.
+
+In fact, rounding up the head room is detrimental in the non-TSO
+case because it makes memory that would otherwise be available to
+the payload head room.  TSO doesn't need this either, all it wants
+is the guarantee that there is no tail room.
+
+So this patch fixes this by adjusting the skb_reserve call so that
+exactly the requested amount (which all callers have calculated in
+a precise way) is made available as tail room.
+
+Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
+
+---
+ include/net/sock.h |   10 ++++++----
+ 1 file changed, 6 insertions(+), 4 deletions(-)
+
+--- a/include/net/sock.h
++++ b/include/net/sock.h
+@@ -1199,14 +1199,16 @@ static inline struct sk_buff *sk_stream_
+ 						   gfp_t gfp)
+ {
+ 	struct sk_buff *skb;
+-	int hdr_len;
+ 
+-	hdr_len = SKB_DATA_ALIGN(sk->sk_prot->max_header);
+-	skb = alloc_skb_fclone(size + hdr_len, gfp);
++	skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp);
+ 	if (skb) {
+ 		skb->truesize += mem;
+ 		if (sk_stream_wmem_schedule(sk, skb->truesize)) {
+-			skb_reserve(skb, hdr_len);
++			/*
++			 * Make sure that we have exactly size bytes
++			 * available to the caller, no more, no less.
++			 */
++			skb_reserve(skb, skb_tailroom(skb) - size);
+ 			return skb;
+ 		}
+ 		__kfree_skb(skb);