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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
In tcp_clean_rtx_queue(), if the TSO packet is not even partially
acked, do not waste time calling tcp_tso_acked().
Signed-off-by: David S. Miller <davem@davemloft.net>
Everything stated there is out of data. tcp_trim_skb()
does adjust the available socket send buffer space and
skb->truesize now.
Signed-off-by: David S. Miller <davem@davemloft.net>
Only put user data purely to pages when doing TSO.
The extra page allocations cause two problems:
1) Add the overhead of the page allocations themselves.
2) Make us do small user copies when we get to the end
of the TCP socket cache page.
It is still beneficial to purely use pages for TSO,
so we will do it for that case.
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp_snd_test() is run for every packet output by a single
call to tcp_write_xmit(), but this is not necessary.
For one, the congestion window space needs to only be
calculated one time, then used throughout the duration
of the loop.
This cleanup also makes experimenting with different TSO
packetization schemes much easier.
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp_snd_test() does several different things, use inline
functions to express this more clearly.
1) It initializes the TSO count of SKB, if necessary.
2) It performs the Nagle test.
3) It makes sure the congestion window is adhered to.
4) It makes sure SKB fits into the send window.
This cleanup also sets things up so that things like the
available packets in the congestion window does not need
to be calculated multiple times by packet sending loops
such as tcp_write_xmit().
Signed-off-by: David S. Miller <davem@davemloft.net>
'nonagle' should be passed to the tcp_snd_test() function
as 'TCP_NAGLE_PUSH' if we are checking an SKB not at the
tail of the write_queue. This is because Nagle does not
apply to such frames since we cannot possibly tack more
data onto them.
However, while doing this __tcp_push_pending_frames() makes
all of the packets in the write_queue use this modified
'nonagle' value.
Fix the bug and simplify this function by just calling
tcp_write_xmit() directly if sk_send_head is non-NULL.
As a result, we can now make tcp_data_snd_check() just call
tcp_push_pending_frames() instead of the specialized
__tcp_data_snd_check().
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp_write_xmit() uses tcp_current_mss(), but some of it's callers,
namely __tcp_push_pending_frames(), already has this value available
already.
While we're here, fix the "cur_mss" argument to be "unsigned int"
instead of plain "unsigned".
Signed-off-by: David S. Miller <davem@davemloft.net>
Put the main basic block of work at the top-level of
tabbing, and mark the TCP_CLOSE test with unlikely().
Signed-off-by: David S. Miller <davem@davemloft.net>
The tcp_cwnd_validate() function should only be invoked
if we actually send some frames, yet __tcp_push_pending_frames()
will always invoke it. tcp_write_xmit() does the call for us,
so the call here can simply be removed.
Also, tcp_write_xmit() can be marked static.
Signed-off-by: David S. Miller <davem@davemloft.net>
When we add any new packet to the TCP socket write queue,
we must call skb_header_release() on it in order for the
TSO sharing checks in the drivers to work.
Signed-off-by: David S. Miller <davem@davemloft.net>
It reimplements portions of tcp_snd_check(), so it
we move it to tcp_output.c we can consolidate it's
logic much easier in a later change.
Signed-off-by: David S. Miller <davem@davemloft.net>
This just moves the code into tcp_output.c, no code logic changes are
made by this patch.
Using this as a baseline, we can begin to untangle the mess of
comparisons for the Nagle test et al. We will also be able to reduce
all of the redundant computation that occurs when outputting data
packets.
Signed-off-by: David S. Miller <davem@davemloft.net>
Herbert Xu
Linus Torvalds
Heikki Orsila
Harald Welte
David S. Miller
Alexey Kuznetsov
Baruch Even
Matt Mackall
Nick Sillik
Hans-Juergen Tappe (SYSGO AG)
Patrick McHardy
Rusty Russell
Stephen Hemminger
Adrian Bunk
Phil Oester
Sam Ravnborg
Olaf Kirch
Julian Anastasov
David L Stevens
Victor Fusco