Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Fix merge between commit 3adadc08 ("net ax25: Reorder ax25_exit to
remove races") and commit 0ca7a4c8 ("net ax25: Simplify and
cleanup the ax25 sysctl handling")

The former moved around the sysctl register/unregister calls, the
later simply removed them.

With help from Stephen Rothwell.
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: David S. Miller <davem@davemloft.net>

Commit 35f3d14d (pipe: add support for shrinking and growing pipes)
added a slowdown for splice(socket -> pipe), as we might grow the spd
used in skb_splice_bits() for each skb we process in splice() syscall.

Its not needed since skb lengths are capped. The default on-stack arrays
are more than enough.

Use MAX_SKB_FRAGS instead of PIPE_DEF_BUFFERS to describe the reasonable
limit per skb.

Add coalescing support to help splicing of GRO skbs built from linear
skbs (linked into frag_list)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Pull build system failure fix from Michal Marek:
 "This fixes build failure with newer gcc that adds some internal
  symbols that end in "__mod_*_device_table", but are not actually the
  tables themselves."

* 'rc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild:
  Fix modpost failures in fedora 17

commit c8628155 (tcp: reduce out_of_order memory use) took care of
coalescing tcp segments provided by legacy devices (linear skbs)

We extend this idea to fragged skbs, as their truesize can be heavy.

ixgbe for example uses 256+1024+PAGE_SIZE/2 = 3328 bytes per segment.

Use this coalescing strategy for receive queue too.

This contributes to reduce number of tcp collapses, at minimal cost, and
reduces memory overhead and packets drops.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Barak Witkowski <barak@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Removes GRO workaround, as issue is fixed in FW 7.2.51.
Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
Signed-off-by: Barak Witkowski <barak@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Following patch adds afex multifunction support to the driver (afex
multifunction is based on vntag header) and updates FW version used to 7.2.51.

Support includes the following:

1. Configure vif parameters in firmware (default vlan, vif id, default
   priority, allowed priorities) according to values received from NIC.
2. Configure FW to strip/add default vlan according to afex vlan mode.
3. Notify link up to OS only after vif is fully initialized.
4. Support vif list set/get requests and configure FW accordingly.
5. Supply afex statistics upon request from NIC.
6. Special handling to L2 interface in case of FCoE vif.
Signed-off-by: Barak Witkowski <barak@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>

Moving to interrupts instead of polling fpr TX completions
Avoiding situations where skb can be held in by the driver for
a long time (till timer expires).
The change is also necessary for supporting BQL.

Removing comp_lock that was required because we could handle TX
completions from several contexts: Interrupts, timer, polling.
Now there is only interrupts
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>

While investigating TCP performance problems on 10Gb+ links, we found a
tcp sender was dropping lot of incoming ACKS because of sk_rcvbuf limit
in sk_add_backlog(), especially if receiver doesnt use GRO/LRO and sends
one ACK every two MSS segments.

A sender usually tweaks sk_sndbuf, but sk_rcvbuf stays at its default
value (87380), allowing a too small backlog.

A TCP ACK, even being small, can consume nearly same truesize space than
outgoing packets. Using sk_rcvbuf + sk_sndbuf as a limit makes sense and
is fast to compute.

Performance results on netperf, single flow, receiver with disabled
GRO/LRO : 7500 Mbits instead of 6050 Mbits, no more TCPBacklogDrop
increments at sender.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Cc: Rick Jones <rick.jones2@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

sk_add_backlog() & sk_rcvqueues_full() hard coded sk_rcvbuf as the
memory limit. We need to make this limit a parameter for TCP use.

No functional change expected in this patch, all callers still using the
old sk_rcvbuf limit.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Cc: Rick Jones <rick.jones2@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Randy Dunlap <rdunlap@xenotime.net> reported:

> On 04/23/2012 12:07 AM, Stephen Rothwell wrote:
>
>> Hi all,
>>
>> Changes since 20120420:
>
>
> include/net/ax25.h:447:75: error: expected ';' before '}' token
>
> static inline int ax25_register_dev_sysctl(ax25_dev *ax25_dev) { return 0 };
> static inline void ax25_unregister_dev_sysctl(ax25_dev *ax25_dev) {};
>
> First function:  move ';' inside braces.
> Second function:  drop the ';'.

Put the semicolons where it makes sense.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Acked-by: Randy Dunlap <rdunlap@xenotime.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

Pull a few more md bug fixes from NeilBrown:
 "2 are tagged for -stable, one being for a fairly serious bug that can
  corrupt metadata and make it hard to recovery an array.  The other is
  for a more recent regression since 3.3"

* tag 'md-3.4-fixes' of git://neil.brown.name/md:
  md: fix possible corruption of array metadata on shutdown.
  md: don't call ->add_disk unless there is good reason.
  DM RAID: Use safe version of rdev_for_each

Pull dlm fixes from David Teigland:
 "This includes one short patch fixing the behavior of the QUECVT flag,
  which the gfs2 folks are waiting on."

* tag 'dlm-fixes-3.4' of git://git.kernel.org/pub/scm/linux/kernel/git/teigland/linux-dlm:
  dlm: fix QUECVT when convert queue is empty

Mel reports a BUG_ON(slot == NULL) in radix_tree_tag_set() on s390
3.0.13: called from __set_page_dirty_nobuffers() when page_remove_rmap()
tries to transfer dirty flag from s390 storage key to struct page and
radix_tree.

That would be because of reclaim's shrink_page_list() calling
add_to_swap() on this page at the same time: first PageSwapCache is set
(causing page_mapping(page) to appear as &swapper_space), then
page->private set, then tree_lock taken, then page inserted into
radix_tree - so there's an interval before taking the lock when the
radix_tree slot is empty.

We could fix this by moving __add_to_swap_cache()'s spin_lock_irq up
before the SetPageSwapCache.  But a better fix is simply to do what's
five years overdue: Ken Chen introduced __set_page_dirty_no_writeback()
(if !PageDirty TestSetPageDirty) for tmpfs to skip all the radix_tree
overhead, and swap is just the same - it ignores the radix_tree tag, and
does not participate in dirty page accounting, so should be using
__set_page_dirty_no_writeback() too.

s390 testing now confirms that this does indeed fix the problem.
Reported-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Ken Chen <kenchen@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

commit c744a65c
  md: don't set md arrays to readonly on shutdown.

removed the possibility of a 'BUG' when data is written to an array
that has just been switched to read-only, but also introduced the
possibility that the array metadata could be corrupted.

If, when md_notify_reboot gets the mddev lock, the array is
in a state where it is assembled but hasn't been started (as can
happen if the personality module is not available, or in other unusual
situations), then incorrect metadata will be written out making it
impossible to re-assemble the array.

So only call __md_stop_writes() if the array has actually been
activated.

This patch is needed for any stable kernel which has had the above
commit applied.

Cc: stable@vger.kernel.org
Reported-by: Christoph Nelles <evilazrael@evilazrael.de>
Signed-off-by: NeilBrown <neilb@suse.de>

Commit 7bfec5f3

   md/raid5: If there is a spare and a want_replacement device, start replacement.

cause md_check_recovery to call ->add_disk much more often.
Instead of only when the array is degraded, it is now called whenever
md_check_recovery finds anything useful to do, which includes
updating the metadata for clean<->dirty transition.
This causes unnecessary work, and causes info messages from ->add_disk
to be reported much too often.

So refine md_check_recovery to only do any actual recovery checking
(including ->add_disk) if MD_RECOVERY_NEEDED is set.

This fix is suitable for 3.3.y:

Cc: stable@vger.kernel.org
Reported-by: Jan Ceuleers <jan.ceuleers@computer.org>
Signed-off-by: NeilBrown <neilb@suse.de>

Fix segfault caused by using rdev_for_each instead of rdev_for_each_safe

Commit dafb20fa mistakenly replaced a safe
iterator with an unsafe one when making some macro changes.
Signed-off-by: Jonathan Brassow <jbrassow@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>

Randy Dunlap <rdunlap@xenotime.net> reported:
> On 04/23/2012 12:07 AM, Stephen Rothwell wrote:
>
>> Hi all,
>>
>> Changes since 20120420:
>
>
>
> ERROR: "unregister_net_sysctl_table" [net/phonet/phonet.ko] undefined!
> ERROR: "register_net_sysctl" [net/phonet/phonet.ko] undefined!
>
> when CONFIG_SYSCTL is not enabled.

Add static inline stub functions to gracefully handle the case when sysctl
support is not present.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Acked-by: Randy Dunlap <rdunlap@xenotime.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

ethtool get settings was not displaying all the settings correctly.
use the get_phy_info to get more information about the PHY to fix this.
Signed-off-by: Ajit Khaparde <ajit.khaparde@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The QUECVT flag should not prevent conversions from
being granted immediately when the convert queue is
empty.
Signed-off-by: David Teigland <teigland@redhat.com>

net/ipv4/tcp_ipv4.c: In function 'tcp_v4_init_sock':
net/ipv4/tcp_ipv4.c:1891:19: warning: unused variable 'tp' [-Wunused-variable]
net/ipv6/tcp_ipv6.c: In function 'tcp_v6_init_sock':
net/ipv6/tcp_ipv6.c:1836:19: warning: unused variable 'tp' [-Wunused-variable]
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

Pull ARM fixes from Russell King:
 "Here's my usual Sunday push, just for one revert which PeterZ hollered
  about after last weeks push.  Other than that, all seems strangely
  quiet as far as fixes go in non-platform ARM land at the moment."

* 'fixes' of git://git.linaro.org/people/rmk/linux-arm:
  Revert "ARM: 7359/2: smp_twd: Only wait for reprogramming on active cpus"

Pull powerpc fixes from Benjamin Herrenschmidt:
 "Here are a few fixes for powerpc.  Note the addition to the generic
  irq.h.  This is part of a 3-patches regression fix for mpic due to
  changes in how IRQ_TYPE_NONE is being handled.  Thomas agreed to the
  addition of the new IRQ_TYPE_DEFAULT contant, however he hasn't
  replied with an Ack to the actual patch yet.  I don't to wait much
  longer with these patches tho."

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
  powerpc/mpic: Properly set default triggers
  irq: Add IRQ_TYPE_DEFAULT for use by PIC drivers
  powerpc/mpic: Fix confusion between hw_irq and virq
  powerpc/pmac: Don't add_timer() twice
  powerpc/eeh: Fix crash caused by null eeh_dev
  powerpc/mpc85xx: add MPIC message dts node
  powerpc/mpic_msgr: fix offset error when setting mer register
  powerpc/mpic_msgr: add lock for MPIC message global variable
  powerpc/mpic_msgr: fix compile error when SMP disabled
  powerpc: fix build when CONFIG_BOOKE_WDT is enabled
  powerpc/85xx: don't call of_platform_bus_probe() twice

Pull networking fixes from David Miller:

 1) Fix namespace init and cleanup in phonet to fix some oopses, from
    Eric W. Biederman.

 2) Missing kfree_skb() in AF_KEY, from Julia Lawall.

 3) Refcount leak and source address handling fix in l2tp from James
    Chapman.

 4) Memory leak fix in CAIF from Tomasz Gregorek.

 5) When routes are cloned from ipv6 addrconf routes, we don't process
    expirations properly.  Fix from Gao Feng.

 6) Fix panic on DMA errors in atl1 driver, from Tony Zelenoff.

 7) Only enable interrupts in 8139cp driver after we've registered the
    IRQ handler.  From Jason Wang.

 8) Fix too many reads of KS_CIDER register in ks8851 during probe,
    fixing crashes on spurious interrupts.  From Matt Renzelmann.

 9) Missing include in ath5k driver and missing iounmap on probe
    failure, from Jonathan Bither.

10) Fix RX packet handling in smsc911x driver, from Will Deacon.

11) Fix ixgbe WoL on fiber by leaving the laser on during shutdown.

12) ks8851 needs MAX_RECV_FRAMES increased otherwise the internal MAC
    buffers are easily overflown.  Fix from Davide Cimingahi.

13) Fix memory leaks in peak_usb CAN driver, from Jesper Juhl.

14) gred packet scheduler can dump in WRED more when doing a netlink
    dump.  Fix from David Ward.

15) Fix MTU in USB smsc75xx driver, from Stephane Fillod.

16) Dummy device needs ->ndo_uninit handler to properly handle
    ->ndo_init failures.  From Hiroaki SHIMODA.

17) Fix TX fragmentation in ath9k driver, from Sujith Manoharan.

18) Missing RTNL lock in ixgbe PM resume, from Benjamin Poirier.

19) Missing iounmap in farsync WAN driver, from Julia Lawall.

20) With LRO/GRO, tcp_grow_window() is easily tricked into not growing
    the receive window properly, and this hurts performance.  Fix from
    Eric Dumazet.

21) Network namespace init failure can leak net_generic data, fix from
    Julian Anastasov.

22) Fix skb_over_panic due to mis-accounting in TCP for partially ACK'd
    SKBs.  From Eric Dumazet.

23) New IDs for qmi_wwan driver, from Bjørn Mork.

24) Fix races in ax25_exit(), from Eric W. Biederman.

25) IPV6 TCP doesn't handle TCP_MAXSEG socket option properly, copy over
    logic from the IPV4 side.  From Neal Cardwell.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (59 commits)
  tcp: fix TCP_MAXSEG for established IPv6 passive sockets
  drivers/net: Do not free an IRQ if its request failed
  drop_monitor: allow more events per second
  ks8851: Fix request_irq/free_irq mismatch
  net/hyperv: Adding cancellation to ensure rndis filter is closed
  ks8851: Fix mutex deadlock in ks8851_net_stop()
  net ax25: Reorder ax25_exit to remove races.
  icplus: fix interrupt for IC+ 101A/G and 1001LF
  net: qmi_wwan: support Sierra Wireless MC77xx devices in QMI mode
  bnx2x: off by one in bnx2x_ets_e3b0_sp_pri_to_cos_set()
  ksz884x: don't copy too much in netdev_set_mac_address()
  tcp: fix retransmit of partially acked frames
  netns: do not leak net_generic data on failed init
  net/sock.h: fix sk_peek_off kernel-doc warning
  tcp: fix tcp_grow_window() for large incoming frames
  drivers/net/wan/farsync.c: add missing iounmap
  davinci_mdio: Fix MDIO timeout check
  ipv6: clean up rt6_clean_expires
  ipv6: fix rt6_update_expires
  arcnet: rimi: Fix device name in debug output
  ...

This gets rid of the unused default senses array, and replaces the
incorrect use of IRQ_TYPE_NONE with the new IRQ_TYPE_DEFAULT for
the initial set_trigger() call when mapping an interrupt.

This in turn makes us read the HW state and update the irq desc
accordingly.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

This is meant typically to allow a PIC driver's irq domain map() callback
to establish sane defaults for the interrupt (and make sure that the HW
and the irq_desc are in sync as far as the trigger is concerned).

The irq core may not call the set_trigger callback if it thinks the
trigger is already set to the right setting, so we need to ensure new
descriptors are properly synchronized with the hardware.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

mpic_is_ipi() takes a virq and immediately converts it to a hw_irq.

However, one of the two call sites calls it with a ... hw_irq. The
other call site also happens to have the hw_irq at hand, so let's
change it to just take that as an argument. Also change mpic_is_tm()
for consistency.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

If the interrupt and the timeout happen roughly at the same
time, we can get into a situation where the timer function
is run while the interrupt has already been processed. In
this case, the timer function might end up doing an add_timer
on an already pending timer, causing a BUG_ON() to trigger.

Instead, just skip the whole timeout operation if we see that
the timer is pending. The spinlock ensures that the only way
that happens is if we already started a new operation and thus
the timeout can be ignored.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

The problem was reported by Anton Blanchard. While EEH error
happened to the PCI device without the corresponding device
driver, kernel crash was seen. Eventually, I successfully
reproduced the problem on Firebird-L machine with utility
"errinjct". Initially, the device driver for Emulex ethernet
MAC has been disabled from .config and force data parity on
the Emulex ethernet MAC with help of "errinjct". Eventually,
I saw the kernel crash after issueing couple of "lspci -v"
command.

The root cause behind is that the PCI device, including the
reference to the corresponding eeh device, will be removed
from the system while EEH does recovery. Afterwards, the
PCI device will be probed again and added into the system
accordingly. So it's not safe to retrieve the eeh device from
the corresponding PCI device after the PCI device has been removed
and not added again.

The patch fixes the issue and retrieve the eeh device from OF node
instead of PCI device after the PCI device has been removed.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Tested-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

Commit f5fff5dc forgot to fix TCP_MAXSEG behavior IPv6 sockets, so IPv6
TCP server sockets that used TCP_MAXSEG would find that the advmss of
child sockets would be incorrect. This commit mirrors the advmss logic
from tcp_v4_syn_recv_sock in tcp_v6_syn_recv_sock. Eventually this
logic should probably be shared between IPv4 and IPv6, but this at
least fixes this issue.
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Replace netif_receive_skb with napi_gro_receive.
Signed-off-by: Jiajun Wu <b06378@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Refrain from attempting to free an interrupt line if the request
fails and hence, there is no IRQ to free.

CC: netdev@vger.kernel.org
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Factorize code, since most fetched values are int type.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This commit moves the (substantial) common code shared between
tcp_v4_init_sock() and tcp_v6_init_sock() to a new address-family
independent function, tcp_init_sock().

Centralizing this functionality should help avoid drift issues,
e.g. where the IPv4 side is updated without a corresponding update to
IPv6. There was already some drift: IPv4 initialized snd_cwnd to
TCP_INIT_CWND, while the IPv6 side was still initializing snd_cwnd to
2 (in this case it should not matter, since snd_cwnd is also
initialized in tcp_init_metrics(), but the general risks and
maintenance overhead remain).

When diffing the old and new code, note that new tcp_init_sock()
function uses the order of steps from the tcp_v4_init_sock()
implementation (the order is slightly different in
tcp_v6_init_sock()).
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>