21 May, 2010
2 commits
-
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1674 commits)
qlcnic: adding co maintainer
ixgbe: add support for active DA cables
ixgbe: dcb, do not tag tc_prio_control frames
ixgbe: fix ixgbe_tx_is_paused logic
ixgbe: always enable vlan strip/insert when DCB is enabled
ixgbe: remove some redundant code in setting FCoE FIP filter
ixgbe: fix wrong offset to fc_frame_header in ixgbe_fcoe_ddp
ixgbe: fix header len when unsplit packet overflows to data buffer
ipv6: Never schedule DAD timer on dead address
ipv6: Use POSTDAD state
ipv6: Use state_lock to protect ifa state
ipv6: Replace inet6_ifaddr->dead with state
cxgb4: notify upper drivers if the device is already up when they load
cxgb4: keep interrupts available when the ports are brought down
cxgb4: fix initial addition of MAC address
cnic: Return SPQ credit to bnx2x after ring setup and shutdown.
cnic: Convert cnic_local_flags to atomic ops.
can: Fix SJA1000 command register writes on SMP systems
bridge: fix build for CONFIG_SYSFS disabled
ARCNET: Limit com20020 PCI ID matches for SOHARD cards
...Fix up various conflicts with pcmcia tree drivers/net/
{pcmcia/3c589_cs.c, wireless/orinoco/orinoco_cs.c and
wireless/orinoco/spectrum_cs.c} and feature removal
(Documentation/feature-removal-schedule.txt).Also fix a non-content conflict due to pm_qos_requirement getting
renamed in the PM tree (now pm_qos_request) in net/mac80211/scan.c -
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial: (44 commits)
vlynq: make whole Kconfig-menu dependant on architecture
add descriptive comment for TIF_MEMDIE task flag declaration.
EEPROM: max6875: Header file cleanup
EEPROM: 93cx6: Header file cleanup
EEPROM: Header file cleanup
agp: use NULL instead of 0 when pointer is needed
rtc-v3020: make bitfield unsigned
PCI: make bitfield unsigned
jbd2: use NULL instead of 0 when pointer is needed
cciss: fix shadows sparse warning
doc: inode uses a mutex instead of a semaphore.
uml: i386: Avoid redefinition of NR_syscalls
fix "seperate" typos in comments
cocbalt_lcdfb: correct sections
doc: Change urls for sparse
Powerpc: wii: Fix typo in comment
i2o: cleanup some exit paths
Documentation/: it's -> its where appropriate
UML: Fix compiler warning due to missing task_struct declaration
UML: add kernel.h include to signal.c
...
18 May, 2010
8 commits
-
This patch removes from net/ (but not any netfilter files)
all the unnecessary return; statements that precede the
last closing brace of void functions.It does not remove the returns that are immediately
preceded by a label as gcc doesn't like that.Done via:
$ grep -rP --include=*.[ch] -l "return;\n}" net/ | \
xargs perl -i -e 'local $/ ; while (<>) { s/\n[ \t\n]+return;\n}/\n}/g; print; }'Signed-off-by: Joe Perches
Signed-off-by: David S. Miller -
skb rxhash should be cleared when a skb is handled by a tunnel before
being delivered again, so that correct packet steering can take place.There are other cleanups and accounting that we can factorize in a new
helper, skb_tunnel_rx()Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller -
Commit 33ad798c924b4a (tcp: options clean up) introduced a problem
if MD5+SACK+timestamps were used in initial SYN message.Some stacks (old linux for example) try to negotiate MD5+SACK+TSTAMP
sessions, but since 40 bytes of tcp options space are not enough to
store all the bits needed, we chose to disable timestamps in this case.We send a SYN-ACK _without_ timestamp option, but socket has timestamps
enabled and all further outgoing messages contain a TS block, all with
the initial timestamp of the remote peer.Fix is to really disable timestamps option for the whole session.
Reported-by: Bijay Singh
Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller -
Also added an explicit break; to avoid
a fallthrough in net/ipv4/tcp_input.cSigned-off-by: Joe Perches
Signed-off-by: David S. Miller -
TCP outgoing packets can avoid two atomic ops, and dirtying
of previously higly contended cache line using new refdst
infrastructure.Note 1: loopback device excluded because of !IFF_XMIT_DST_RELEASE
Note 2: UDP packets dsts are built before ip_queue_xmit().Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller -
Use ip_route_input_noref() in ip fast path, to avoid two atomic ops per
incoming packet.Note: loopback is excluded from this optimization in ip_rcv_finish()
Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller -
ip_route_input() is the version returning a refcounted dst, while
ip_route_input_noref() returns a non refcounted one.Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller -
Use low order bit of skb->_skb_dst to tell dst is not refcounted.
Change _skb_dst to _skb_refdst to make sure all uses are catched.
skb_dst() returns the dst, regardless of noref bit set or not, but
with a lockdep check to make sure a noref dst is not given if current
user is not rcu protected.New skb_dst_set_noref() helper to set an notrefcounted dst on a skb.
(with lockdep check)skb_dst_drop() drops a reference only if skb dst was refcounted.
skb_dst_force() helper is used to force a refcount on dst, when skb
is queued and not anymore RCU protected.Use skb_dst_force() in __sk_add_backlog(), __dev_xmit_skb() if
!IFF_XMIT_DST_RELEASE or skb enqueued on qdisc queue, in
sock_queue_rcv_skb(), in __nf_queue().Use skb_dst_force() in dev_requeue_skb().
Note: dst_use_noref() still dirties dst, we might transform it
later to do one dirtying per jiffies.Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller
17 May, 2010
1 commit
-
Conflicts:
include/linux/if_link.h
16 May, 2010
3 commits
-
TCP-MD5 sessions have intermittent failures, when route cache is
invalidated. ip_queue_xmit() has to find a new route, calls
sk_setup_caps(sk, &rt->u.dst), destroying thesk->sk_route_caps &= ~NETIF_F_GSO_MASK
that MD5 desperately try to make all over its way (from
tcp_transmit_skb() for example)So we send few bad packets, and everything is fine when
tcp_transmit_skb() is called again for this socket.Since ip_queue_xmit() is at a lower level than TCP-MD5, I chose to use a
socket field, sk_route_nocaps, containing bits to mask on sk_route_caps.Reported-by: Bhaskar Dutta
Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller -
TCP MD5 support uses percpu data for temporary storage. It currently
disables preemption so that same storage cannot be reclaimed by another
thread on same cpu.We also have to make sure a softirq handler wont try to use also same
context. Various bug reports demonstrated corruptions.Fix is to disable preemption and BH.
Reported-by: Bhaskar Dutta
Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller -
(Dropped the infiniband part, because Tetsuo modified the related code,
I will send a separate patch for it once this is accepted.)This patch introduces /proc/sys/net/ipv4/ip_local_reserved_ports which
allows users to reserve ports for third-party applications.The reserved ports will not be used by automatic port assignments
(e.g. when calling connect() or bind() with port number 0). Explicit
port allocation behavior is unchanged.Signed-off-by: Octavian Purdila
Signed-off-by: WANG Cong
Cc: Neil Horman
Cc: Eric Dumazet
Cc: Eric W. Biederman
Signed-off-by: David S. Miller
14 May, 2010
1 commit
13 May, 2010
3 commits
-
This patch removes from net/ netfilter files
all the unnecessary return; statements that precede the
last closing brace of void functions.It does not remove the returns that are immediately
preceded by a label as gcc doesn't like that.Done via:
$ grep -rP --include=*.[ch] -l "return;\n}" net/ | \
xargs perl -i -e 'local $/ ; while (<>) { s/\n[ \t\n]+return;\n}/\n}/g; print; }'Signed-off-by: Joe Perches
[Patrick: changed to keep return statements in otherwise empty function bodies]
Signed-off-by: Patrick McHardy -
Make sure all printk messages have a severity level.
Signed-off-by: Stephen Hemminger
Signed-off-by: Patrick McHardy -
Change netfilter asserts to standard WARN_ON. This has the
benefit of backtrace info and also causes netfilter errors
to show up on kerneloops.org.Signed-off-by: Stephen Hemminger
Signed-off-by: Patrick McHardy
12 May, 2010
7 commits
-
Conflicts:
Documentation/feature-removal-schedule.txt
drivers/net/wireless/ath/ar9170/usb.c
drivers/scsi/iscsi_tcp.c
net/ipv4/ipmr.c -
Prepare the arrays for use with the multiregister function. The
future layer-3 xt matches can then be easily added to it without
needing more (un)register code.Signed-off-by: Jan Engelhardt
-
Since xt_action_param is writable, let's use it. The pointer to
'bool hotdrop' always worried (8 bytes (64-bit) to write 1 byte!).
Surprisingly results in a reduction in size:text data bss filename
5457066 692730 357892 vmlinux.o-prev
5456554 692730 357892 vmlinux.oSigned-off-by: Jan Engelhardt
-
In future, layer-3 matches will be an xt module of their own, and
need to set the fragoff and thoff fields. Adding more pointers would
needlessy increase memory requirements (esp. so for 64-bit, where
pointers are wider).Signed-off-by: Jan Engelhardt
-
Signed-off-by: Jan Engelhardt
-
The structures carried - besides match/target - almost the same data.
It is possible to combine them, as extensions are evaluated serially,
and so, the callers end up a little smaller.text data bss filename
-15318 740 104 net/ipv4/netfilter/ip_tables.o
+15286 740 104 net/ipv4/netfilter/ip_tables.o
-15333 540 152 net/ipv6/netfilter/ip6_tables.o
+15269 540 152 net/ipv6/netfilter/ip6_tables.oSigned-off-by: Jan Engelhardt
11 May, 2010
1 commit
-
Conflicts:
net/bridge/br_device.c
net/bridge/br_forward.cSigned-off-by: Patrick McHardy
10 May, 2010
2 commits
-
Need to check both CONFIG_FOO and CONFIG_FOO_MODULE
Signed-off-by: David S. Miller
-
Fixes the expiration timer for unresolved multicast route entries.
In case new multicast routing requests come in faster than the
expiration timeout occurs (e.g. zap through multicast TV streams), the
timer is prevented from being called at time for already existing entries.As the single timer is resetted to default whenever a new entry is made,
the timeout for existing unresolved entires are missed and/or not
updated. As a consequence new requests are denied when the limit of
unresolved entries has been reached because old entries live longer than
they are supposed to.The solution is to reset the timer only for the first unresolved entry
in the multicast routing cache. All other timers are already set and
updated correctly within the timer function itself by now.Signed-off by: Andreas Meissner
Signed-off-by: David S. Miller
08 May, 2010
1 commit
-
A while back there was a discussion regarding the rt_secret_interval timer.
Given that we've had the ability to do emergency route cache rebuilds for awhile
now, based on a statistical analysis of the various hash chain lengths in the
cache, the use of the flush timer is somewhat redundant. This patch removes the
rt_secret_interval sysctl, allowing us to rely solely on the statistical
analysis mechanism to determine the need for route cache flushes.Signed-off-by: Neil Horman
Acked-by: Eric Dumazet
Signed-off-by: David S. Miller
07 May, 2010
1 commit
-
commit 2783ef23 moved the initialisation of saddr and daddr after
pskb_may_pull() to avoid a potential data corruption. Unfortunately
also placing it after the short packet and bad checksum error paths,
where these variables are used for logging. The result is bogus
output like[92238.389505] UDP: short packet: From 2.0.0.0:65535 23715/178 to 0.0.0.0:65535
Moving the saddr and daddr initialisation above the error paths, while still
keeping it after the pskb_may_pull() to keep the fix from commit 2783ef23.Signed-off-by: Bjørn Mork
Cc: stable@kernel.org
Acked-by: Eric Dumazet
Signed-off-by: David S. Miller
03 May, 2010
1 commit
02 May, 2010
2 commits
-
Signed-off-by: Jan Engelhardt
-
Signed-off-by: Jan Engelhardt
29 Apr, 2010
3 commits
-
When queueing a skb to socket, we can immediately release its dst if
target socket do not use IP_CMSG_PKTINFO.tcp_data_queue() can drop dst too.
This to benefit from a hot cache line and avoid the receiver, possibly
on another cpu, to dirty this cache line himself.Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller -
Since commit 95766fff ([UDP]: Add memory accounting.),
each received packet needs one extra sock_lock()/sock_release() pair.This added latency because of possible backlog handling. Then later,
ticket spinlocks added yet another latency source in case of DDOS.This patch introduces lock_sock_bh() and unlock_sock_bh()
synchronization primitives, avoiding one atomic operation and backlog
processing.skb_free_datagram_locked() uses them instead of full blown
lock_sock()/release_sock(). skb is orphaned inside locked section for
proper socket memory reclaim, and finally freed outside of it.UDP receive path now take the socket spinlock only once.
Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller -
This reverts two commits:
fda48a0d7a8412cedacda46a9c0bf8ef9cd13559
tcp: bind() fix when many ports are boundand a follow-on fix for it:
6443bb1fc2050ca2b6585a3fa77f7833b55329ed
ipv6: Fix inet6_csk_bind_conflict()It causes problems with binding listening sockets when time-wait
sockets from a previous instance still are alive.It's too late to keep fiddling with this so late in the -rc
series, and we'll deal with it in net-next-2.6 instead.Signed-off-by: David S. Miller
28 Apr, 2010
4 commits
-
Current socket backlog limit is not enough to really stop DDOS attacks,
because user thread spend many time to process a full backlog each
round, and user might crazy spin on socket lock.We should add backlog size and receive_queue size (aka rmem_alloc) to
pace writers, and let user run without being slow down too much.Introduce a sk_rcvqueues_full() helper, to avoid taking socket lock in
stress situations.Under huge stress from a multiqueue/RPS enabled NIC, a single flow udp
receiver can now process ~200.000 pps (instead of ~100 pps before the
patch) on a 8 core machine.Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller -
Idea from Eric Dumazet.
As for placement inside of struct sock, I tried to choose a place
that otherwise has a 32-bit hole on 64-bit systems.Signed-off-by: David S. Miller
Acked-by: Eric Dumazet -
RFC 1122 says the following:
...
Keep-alive packets MUST only be sent when no data or
acknowledgement packets have been received for the
connection within an interval.
...The acknowledgement packet is reseting the keepalive
timer but the data packet isn't. This patch fixes it by
checking the timestamp of the last received data packet
too when the keepalive timer expires.Signed-off-by: Flavio Leitner
Signed-off-by: Eric Dumazet
Acked-by: Ilpo Järvinen
Signed-off-by: David S. Miller
