svn commit: r279281 - head/sys/netinet

[Hans Petter Selasky]

Author: hselasky
Date: Wed Feb 25 13:58:43 2015
New Revision: 279281
URL: https://svnweb.freebsd.org/changeset/base/279281

Log:
  Fix a special case in ip_fragment() to produce a more sensible chain
  of packets. When the data payload length excluding any headers, of an
  outgoing IPv4 packet exceeds PAGE_SIZE bytes, a special case in
  ip_fragment() can kick in to optimise the outgoing payload(s). The
  code which was added in r98849 as part of zero copy socket support
  assumes that the beginning of any MTU sized payload is aligned to
  where a MBUF's "m_data" pointer points. This is not always the case
  and can sometimes cause large IPv4 packets, as part of ping replies,
  to be split more than needed.
  
  Instead of iterating the MBUFs to figure out how much data is in the
  current chain, use the value already in the "m_pkthdr.len" field of
  the first MBUF in the chain.
  
  Reviewed by:		ken @
  Differential Revision:	https://reviews.freebsd.org/D1893
  MFC after:		2 weeks
  Sponsored by:		Mellanox Technologies

Modified:
  head/sys/netinet/ip_output.c

Modified: head/sys/netinet/ip_output.c
==============================================================================
--- head/sys/netinet/ip_output.c	Wed Feb 25 12:26:45 2015	(r279280)
+++ head/sys/netinet/ip_output.c	Wed Feb 25 13:58:43 2015	(r279281)
@@ -743,10 +743,8 @@ ip_fragment(struct ip *ip, struct mbuf *
 		 * be less than the receiver's page size ?
 		 */
 		int newlen;
-		struct mbuf *m;
 
-		for (m = m0, off = 0; m && (off+m->m_len) <= mtu; m = m->m_next)
-			off += m->m_len;
+		off = MIN(mtu, m0->m_pkthdr.len);
 
 		/*
 		 * firstlen (off - hlen) must be aligned on an