Commit graph

159 commits

Author SHA1 Message Date
Harald Welte
bf3a46aa9b [NETFILTER]: convert nfmark and conntrack mark to 32bit
As discussed at netconf'05, we convert nfmark and conntrack-mark to be
32bits even on 64bit architectures.

Signed-off-by: Harald Welte <laforge@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-29 15:29:31 -07:00
Patrick McHardy
06c7427021 [FIB_TRIE]: Don't ignore negative results from fib_semantic_match
When a semantic match occurs either success, not found or an error
(for matching unreachable routes/blackholes) is returned. fib_trie
ignores the errors and looks for a different matching route. Treat
results other than "no match" as success and end lookup.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-23 22:06:09 -07:00
David S. Miller
d5d283751e [TCP]: Document non-trivial locking path in tcp_v{4,6}_get_port().
This trips up a lot of folks reading this code.
Put an unlikely() around the port-exhaustion test
for good measure.

Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-23 10:49:54 -07:00
David S. Miller
89ebd197eb [TCP]: Unconditionally clear TCP_NAGLE_PUSH in skb_entail().
Intention of this bit is to force pushing of the existing
send queue when TCP_CORK or TCP_NODELAY state changes via
setsockopt().

But it's easy to create a situation where the bit never
clears.  For example, if the send queue starts empty:

1) set TCP_NODELAY
2) clear TCP_NODELAY
3) set TCP_CORK
4) do small write()

The current code will leave TCP_NAGLE_PUSH set after that
sequence.  Unconditionally clearing the bit when new data
is added via skb_entail() solves the problem.

Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-23 10:13:06 -07:00
Patrick McHardy
66a79a19a7 [NETFILTER]: Fix HW checksum handling in ip_queue/ip6_queue
The checksum needs to be filled in on output, after mangling a packet
ip_summed needs to be reset.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-23 10:10:35 -07:00
Dave Johnson
1344a41637 [IPV4]: Fix negative timer loop with lots of ipv4 peers.
From: Dave Johnson <djohnson+linux-kernel@sw.starentnetworks.com>

Found this bug while doing some scaling testing that created 500K inet
peers.

peer_check_expire() in net/ipv4/inetpeer.c isn't using inet_peer_gc_mintime
correctly and will end up creating an expire timer with less than the
minimum duration, and even zero/negative if enough active peers are
present.

If >65K peers, the timer will be less than inet_peer_gc_mintime, and with
>70K peers, the timer duration will reach zero and go negative.

The timer handler will continue to schedule another zero/negative timer in
a loop until peers can be aged.  This can continue for at least a few
minutes or even longer if the peers remain active due to arriving packets
while the loop is occurring.

Bug is present in both 2.4 and 2.6.  Same patch will apply to both just
fine.

Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-23 10:10:15 -07:00
Dmitry Yusupov
14869c3886 [TCP]: Do TSO deferral even if tail SKB can go out now.
If the tail SKB fits into the window, it is still
benefitical to defer until the goal percentage of
the window is available.  This give the application
time to feed more data into the send queue and thus
results in larger TSO frames going out.

Patch from Dmitry Yusupov <dima@neterion.com>.

Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-23 10:09:27 -07:00
Patrick McHardy
7e71af49d4 [NETFILTER]: Fix HW checksum handling in TCPMSS target
Most importantly, remove bogus BUG() in receive path.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-20 17:40:41 -07:00
Patrick McHardy
f93592ff4f [NETFILTER]: Fix HW checksum handling in ECN target
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-20 17:39:15 -07:00
Patrick McHardy
fd841326d7 [NETFILTER]: Fix ECN target TCP marking
An incorrect check made it bail out before doing anything.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-20 17:38:40 -07:00
Herbert Xu
6fc8b9e7c6 [IPCOMP]: Fix false smp_processor_id warning
This patch fixes a false-positive from debug_smp_processor_id().

The processor ID is only used to look up crypto_tfm objects.
Any processor ID is acceptable here as long as it is one that is
iterated on by for_each_cpu().

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-18 14:36:59 -07:00
Patrick McHardy
cb94c62c25 [IPV4]: Fix DST leak in icmp_push_reply()
Based upon a bug report and initial patch by
Ollie Wild.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-18 14:05:44 -07:00
Herbert Xu
c8ac377464 [TCP]: Fix bug #5070: kernel BUG at net/ipv4/tcp_output.c:864
1) We send out a normal sized packet with TSO on to start off.
2) ICMP is received indicating a smaller MTU.
3) We send the current sk_send_head which needs to be fragmented
since it was created before the ICMP event.  The first fragment
is then sent out.

At this point the remaining fragment is allocated by tcp_fragment.
However, its size is padded to fit the L1 cache-line size therefore
creating tail-room up to 124 bytes long.

This fragment will also be sitting at sk_send_head.

4) tcp_sendmsg is called again and it stores data in the tail-room of
of the fragment.
5) tcp_push_one is called by tcp_sendmsg which then calls tso_fragment
since the packet as a whole exceeds the MTU.

At this point we have a packet that has data in the head area being
fed to tso_fragment which bombs out.

My take on this is that we shouldn't ever call tcp_fragment on a TSO
socket for a packet that is yet to be transmitted since this creates
a packet on sk_send_head that cannot be extended.

So here is a patch to change it so that tso_fragment is always used
in this case.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-16 20:43:40 -07:00
Herbert Xu
b5da623ae9 [TCP]: Adjust {p,f}ackets_out correctly in tcp_retransmit_skb()
Well I've only found one potential cause for the assertion
failure in tcp_mark_head_lost.  First of all, this can only
occur if cnt > 1 since tp->packets_out is never zero here.
If it did hit zero we'd have much bigger problems.

So cnt is equal to fackets_out - reordering.  Normally
fackets_out is less than packets_out.  The only reason
I've found that might cause fackets_out to exceed packets_out
is if tcp_fragment is called from tcp_retransmit_skb with a
TSO skb and the current MSS is greater than the MSS stored
in the TSO skb.  This might occur as the result of an expiring
dst entry.

In that case, packets_out may decrease (line 1380-1381 in
tcp_output.c).  However, fackets_out is unchanged which means
that it may in fact exceed packets_out.

Previously tcp_retrans_try_collapse was the only place where
packets_out can go down and it takes care of this by decrementing
fackets_out.

So we should make sure that fackets_out is reduced by an appropriate
amount here as well.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-10 18:32:36 -07:00
Linus Torvalds
92e52b2e82 Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 2005-08-08 16:06:01 -07:00
Heikki Orsila
ca9334523c [IPV4]: Debug cleanup
Here's a small patch to cleanup NETDEBUG() use in net/ipv4/ for Linux 
kernel 2.6.13-rc5. Also weird use of indentation is changed in some
places.

Signed-off-by: Heikki Orsila <heikki.orsila@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-08 14:26:52 -07:00
Harald Welte
8b83bc77bf [PATCH] don't try to do any NAT on untracked connections
With the introduction of 'rustynat' in 2.6.11, the old tricks of preventing
NAT of 'untracked' connections (e.g. NOTRACK target in 'raw' table) are no
longer sufficient.

The ip_conntrack_untracked.status |= IPS_NAT_DONE_MASK effectively
prevents iteration of the 'nat' table, but doesn't prevent nat_packet()
to be executed.  Since nr_manips is gone in 'rustynat', nat_packet() now
implicitly thinks that it has to do NAT on the packet.

This patch fixes that problem by explicitly checking for
ip_conntrack_untracked in ip_nat_fn().

Signed-off-by: Harald Welte <laforge@netfilter.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-08-08 11:48:28 -07:00
Herbert Xu
6fc0b4a7a7 [IPSEC]: Restrict socket policy loading to CAP_NET_ADMIN.
The interface needs much redesigning if we wish to allow
normal users to do this in some way.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-06 06:33:15 -07:00
David S. Miller
b7656e7f29 [IPV4]: Fix memory leak during fib_info hash expansion.
When we grow the tables, we forget to free the olds ones
up.

Noticed by Yan Zheng.

Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-05 04:12:48 -07:00
Herbert Xu
b68e9f8572 [PATCH] tcp: fix TSO cwnd caching bug
tcp_write_xmit caches the cwnd value indirectly in cwnd_quota.  When
tcp_transmit_skb reduces the cwnd because of tcp_enter_cwr, the cached
value becomes invalid.

This patch ensures that the cwnd value is always reread after each
tcp_transmit_skb call.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-08-04 21:43:14 -07:00
David S. Miller
846998ae87 [PATCH] tcp: fix TSO sizing bugs
MSS changes can be lost since we preemptively initialize the tso_segs count
for an SKB before we %100 commit to sending it out.

So, by the time we send it out, the tso_size information can be stale due
to PMTU events.  This mucks up all of the logic in our send engine, and can
even result in the BUG() triggering in tcp_tso_should_defer().

Another problem we have is that we're storing the tp->mss_cache, not the
SACK block normalized MSS, as the tso_size.  That's wrong too.

Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-08-04 21:43:14 -07:00
Alexey Kuznetsov
db44575f6f [NET]: fix oops after tunnel module unload
Tunnel modules used to obtain module refcount each time when
some tunnel was created, which meaned that tunnel could be unloaded
only after all the tunnels are deleted.

Since killing old MOD_*_USE_COUNT macros this protection has gone.
It is possible to return it back as module_get/put, but it looks
more natural and practically useful to force destruction of all
the child tunnels on module unload.

Signed-off-by: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-30 17:46:44 -07:00
Harald Welte
1f494c0e04 [NETFILTER] Inherit masq_index to slave connections
masq_index is used for cleanup in case the interface address changes
(such as a dialup ppp link with dynamic addreses).  Without this patch,
slave connections are not evicted in such a case, since they don't inherit
masq_index.

Signed-off-by: Harald Welte <laforge@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-30 17:44:07 -07:00
Baruch Even
d1b04c081e [NET]: Spelling mistakes threshoulds -> thresholds
Just simple spelling mistake fixes.

Signed-Off-By: Baruch Even <baruch@ev-en.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-30 17:41:59 -07:00
Matt Mackall
5e43db7730 [NET]: Move in_aton from net/ipv4/utils.c to net/core/utils.c
Move in_aton to allow netpoll and pktgen to work without the rest of
the IPv4 stack. Fix whitespace and add comment for the odd placement.

Delete now-empty net/ipv4/utils.c

Re-enable netpoll/netconsole without CONFIG_INET

Signed-off-by: Matt Mackall <mpm@selenic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-27 15:24:42 -07:00
Nick Sillik
7cee432a22 [NETFILTER]: Fix -Wunder error in ip_conntrack_core.c
Signed-off-by: Nick Sillik <n.sillik@temple.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-27 14:46:03 -07:00
Hans-Juergen Tappe (SYSGO AG)
eaa1c5d059 [IPV4]: Fix Kconfig syntax error
From: "Hans-Juergen Tappe (SYSGO AG)" <hjt@sysgo.com>

Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-27 13:00:04 -07:00
Patrick McHardy
74bb421da7 [NETFILTER]: Use correct byteorder in ICMP NAT
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-22 12:51:38 -07:00
Patrick McHardy
21f930e4ab [NETFILTER]: Wait until all references to ip_conntrack_untracked are dropped on unload
Fixes a crash when unloading ip_conntrack.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-22 12:51:03 -07:00
Patrick McHardy
d04b4f8c1c [NETFILTER]: Fix potential memory corruption in NAT code (aka memory NAT)
The portptr pointing to the port in the conntrack tuple is declared static,
which could result in memory corruption when two packets of the same
protocol are NATed at the same time and one conntrack goes away.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-22 12:50:29 -07:00
Rusty Russell
4acdbdbe50 [NETFILTER]: ip_conntrack_expect_related must not free expectation
If a connection tracking helper tells us to expect a connection, and
we're already expecting that connection, we simply free the one they
gave us and return success.

The problem is that NAT helpers (eg. FTP) have to allocate the
expectation first (to see what port is available) then rewrite the
packet.  If that rewrite fails, they try to remove the expectation,
but it was freed in ip_conntrack_expect_related.

This is one example of a larger problem: having registered the
expectation, the pointer is no longer ours to use.  Reference counting
is needed for ctnetlink anyway, so introduce it now.

To have a single "put" path, we need to grab the reference to the
connection on creation, rather than open-coding it in the caller.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-21 13:14:46 -07:00
Patrick McHardy
0303770deb [NET]: Make ipip/ip6_tunnel independant of XFRM
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-19 14:03:34 -07:00
Stephen Hemminger
c877efb207 [IPV4]: Fix up lots of little whitespace indentation stuff in fib_trie.
Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-19 14:01:51 -07:00
Patrick McHardy
abaacad9bc [IPV4]: Don't select XFRM for ip_gre
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-19 13:59:17 -07:00
Adrian Bunk
6876f95f20 [IPV4]: fix IP_FIB_HASH kconfig warning
This patch fixes the following kconfig warning:
  net/ipv4/Kconfig:92:warning: defaults for choice values not supported

Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-18 13:55:19 -07:00
Phil Oester
84531c24f2 [NETFILTER]: Revert nf_reset change
Revert the nf_reset change that caused so much trouble, drop conntrack
references manually before packets are queued to packet sockets.

Signed-off-by: Phil Oester <kernel@linuxace.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-12 11:57:52 -07:00
Sam Ravnborg
6a2e9b738c [NET]: move config options out to individual protocols
Move the protocol specific config options out to the specific protocols.
With this change net/Kconfig now starts to become readable and serve as a
good basis for further re-structuring.

The menu structure is left almost intact, except that indention is
fixed in most cases. Most visible are the INET changes where several
"depends on INET" are replaced with a single ifdef INET / endif pair.

Several new files were created to accomplish this change - they are
small but serve the purpose that config options are now distributed
out where they belongs.

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-11 21:13:56 -07:00
Olaf Kirch
0b7f22aab4 [IPV4]: Prevent oops when printing martian source
In some cases, we may be generating packets with a source address that
qualifies as martian. This can happen when we're in the middle of setting
up the network, and netfilter decides to reject a packet with an RST.
The IPv4 routing code would try to print a warning and oops, because
locally generated packets do not have a valid skb->mac.raw pointer
at this point.

Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-11 21:01:42 -07:00
Julian Anastasov
af9debd461 [IPVS]: Add and reorder bh locks after moving to keventd.
An addition to the last ipvs changes that move
update_defense_level/si_meminfo to keventd:

- ip_vs_random_dropentry now runs in process context and should use _bh
  locks to protect from softirqs

- update_defense_level still needs _bh locks after si_meminfo is called,
  for the same purpose

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-11 20:59:57 -07:00
David L Stevens
84b42baef7 [IPV4]: fix IPv4 leave-group group matching
This patch fixes the multicast group matching for 
IP_DROP_MEMBERSHIP, similar to the IP_ADD_MEMBERSHIP fix in a prior
patch. Groups are identifiedby <group address,interface> and including
the interface address in the match will fail if a leave-group is done
by address when the join was done by index, or if different addresses
on the same interface are used in the join and leave.

Signed-off-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-08 17:48:38 -07:00
David L Stevens
9951f036fe [IPV4]: (INCLUDE,empty)/leave-group equivalence for full-state MSF APIs & errno fix
1) Adds (INCLUDE, empty)/leave-group equivalence to the full-state 
   multicast source filter APIs (IPv4 and IPv6)

2) Fixes an incorrect errno in the IPv6 leave-group (ENOENT should be
   EADDRNOTAVAIL)

Signed-off-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-08 17:47:28 -07:00
David L Stevens
917f2f105e [IPV4]: multicast API "join" issues
1) In the full-state API when imsf_numsrc == 0
   errno should be "0", but returns EADDRNOTAVAIL

2) An illegal filter mode change
   errno should be EINVAL, but returns EADDRNOTAVAIL

3) Trying to do an any-source option without IP_ADD_MEMBERSHIP
   errno should be EINVAL, but returns EADDRNOTAVAIL

4) Adds comments for the less obvious error return values

Signed-off-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-08 17:45:16 -07:00
David L Stevens
8cdaaa15da [IPV4]: multicast API "join" issues
1) Changes IP_ADD_SOURCE_MEMBERSHIP and MCAST_JOIN_SOURCE_GROUP to ignore
   EADDRINUSE errors on a "courtesy join" -- prior membership or not
   is ok for these.

2) Adds "leave group" equivalence of (INCLUDE, empty) filters in the 
   delta-based API. Without this, mixing delta-based API calls that
   end in an (INCLUDE, empty) filter would not allow a subsequent
   regular IP_ADD_MEMBERSHIP. It also frees socket buffer memory that
   isn't needed for both the multicast group record and source filter.

Signed-off-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-08 17:39:23 -07:00
David L Stevens
ca9b907d14 [IPV4]: multicast API "join" issues
This patch corrects a few problems with the IP_ADD_MEMBERSHIP
socket option:

1) The existing code makes an attempt at reference counting joins when
   using the ip_mreqn/imr_ifindex interface. Joining the same group
   on the same socket is an error, whatever the API. This leads to
   unexpected results when mixing ip_mreqn by index with ip_mreqn by
   address, ip_mreq, or other API's. For example, ip_mreq followed by
   ip_mreqn of the same group will "work" while the same two reversed
   will not.
           Fixed to always return EADDRINUSE on a duplicate join and
   removed the (now unused) reference count in ip_mc_socklist.

2) The group-search list in ip_mc_join_group() is comparing a full 
   ip_mreqn structure and all of it must match for it to find the
   group. This doesn't correctly match a group that was joined with
   ip_mreq or ip_mreqn with an address (with or without an index). It
   also doesn't match groups that are joined by different addresses on
   the same interface. All of these are the same multicast group,
   which is identified by group address and interface index.
           Fixed the check to correctly match groups so we don't get
   duplicate group entries on the ip_mc_socklist.

3) The old code allocates a multicast address before searching for
   duplicates requiring it to free in various error cases. This
   patch moves the allocate until after the search and
   igmp_max_memberships check, so never a need to allocate, then free
   an entry.

Signed-off-by: David L Stevens <dlstevens@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-08 17:38:07 -07:00
Alexey Kuznetsov
4c866aa798 [IPV4]: Apply sysctl_icmp_echo_ignore_broadcasts to ICMP_TIMESTAMP as well.
This was the full intention of the original code.

Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-08 17:34:46 -07:00
Victor Fusco
86a76caf87 [NET]: Fix sparse warnings
From: Victor Fusco <victor@cetuc.puc-rio.br>

Fix the sparse warning "implicit cast to nocast type"

Signed-off-by: Victor Fusco <victor@cetuc.puc-rio.br>
Signed-off-by: Domen Puncer <domen@coderock.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-08 14:57:47 -07:00
David S. Miller
b03efcfb21 [NET]: Transform skb_queue_len() binary tests into skb_queue_empty()
This is part of the grand scheme to eliminate the qlen
member of skb_queue_head, and subsequently remove the
'list' member of sk_buff.

Most users of skb_queue_len() want to know if the queue is
empty or not, and that's trivially done with skb_queue_empty()
which doesn't use the skb_queue_head->qlen member and instead
uses the queue list emptyness as the test.

Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-08 14:57:23 -07:00
David S. Miller
908a75c17a [TCP]: Never TSO defer under periods of congestion.
Congestion window recover after loss depends upon the fact
that if we have a full MSS sized frame at the head of the
send queue, we will send it.  TSO deferral can defeat the
ACK clocking necessary to exit cleanly from recovery.

Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-05 15:43:58 -07:00
David S. Miller
c1b4a7e695 [TCP]: Move to new TSO segmenting scheme.
Make TSO segment transmit size decisions at send time not earlier.

The basic scheme is that we try to build as large a TSO frame as
possible when pulling in the user data, but the size of the TSO frame
output to the card is determined at transmit time.

This is guided by tp->xmit_size_goal.  It is always set to a multiple
of MSS and tells sendmsg/sendpage how large an SKB to try and build.

Later, tcp_write_xmit() and tcp_push_one() chop up the packet if
necessary and conditions warrant.  These routines can also decide to
"defer" in order to wait for more ACKs to arrive and thus allow larger
TSO frames to be emitted.

A general observation is that TSO elongates the pipe, thus requiring a
larger congestion window and larger buffering especially at the sender
side.  Therefore, it is important that applications 1) get a large
enough socket send buffer (this is accomplished by our dynamic send
buffer expansion code) 2) do large enough writes.

Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-05 15:24:38 -07:00
David S. Miller
0d9901df62 [TCP]: Break out send buffer expansion test.
This makes it easier to understand, and allows easier
tweaking of the heuristic later on.

Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-05 15:21:10 -07:00