as reported by Alexander Beregalov <a.beregalov@gmail.com>

ioatdma 0000:00:08.0: DMA-API: device driver frees DMA memory with
wrong function [device address=0x000000007f76f800] [size=2000 bytes]
[map
ped as single] [unmapped as page]

The ioatdma driver was unmapping all regions
(either allocated as page or single) using unmap_page.
This patch lets dma driver recognize if unmap_single or unmap_page should be used.
It introduces two new dma control flags:
DMA_COMPL_SRC_UNMAP_SINGLE and DMA_COMPL_DEST_UNMAP_SINGLE.
They should be set to indicate dma driver to do dma-unmapping as single
(first one for the source, tha latter for the destination).
If respective flag is not set, the driver assumes dma-unmapping as page.
Signed-off-by: NMaciej Sosnowski <maciej.sosnowski@intel.com>
Reported-by: NAlexander Beregalov <a.beregalov@gmail.com>
Tested-by: NAlexander Beregalov <a.beregalov@gmail.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

In order to build the generic syscall table, we need a declaration for
every system call.  sys_pipe2 was added without a proper declaration, so
add this to syscalls.h now.
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Cc: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Put generic_show_options read access to s_options under rcu_read_lock,
split save_mount_options() into "we are setting it the first time"
(uses in foo_fill_super()) and "we are relacing and freeing the old one",
synchronize_rcu() before kfree() in the latter.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

... and make path_lookup_open() static
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

There's no kernel-only content in it anymore, so move it to header-y
and remove the superflous #ifdef __KERNEL__.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Does equivalent of up_write(&s->s_umount); deactivate_super(s);
However, it does not does not unlock it until it's all over.
As the result, it's safe to use to dispose of new superblock on ->get_sb()
failure exits - nobody will see the sucker until it's all over.
Equivalent using up_write/deactivate_super is safe for that purpose
if superblock is either	safe to use or has NULL ->s_root when we unlock.
Normally filesystems take the required precautions, but
	a) we do have bugs in that area in some of them.
	b) up_write/deactivate_super sequence is extremely common,
so the helper makes sense anyway.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

 With Al Viro's patch to move privroot lookup to fs mount, there's no need
 to have special code to hide the privroot in reiserfs_lookup.

 I've also cleaned up the privroot hiding in reiserfs_readdir_dentry and
 removed the last user of reiserfs_xattrs().
Signed-off-by: NJeff Mahoney <jeffm@suse.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

 The xattr_root caching was broken from my previous patch set. It wouldn't
 cause corruption, but could cause decreased performance due to allocating
 a larger chunk of the journal (~ 27 blocks) than it would actually use.

 This patch loads the xattr root dentry at xattr initialization and creates
 it on-demand. Since we're using the cached dentry, there's no point
 in keeping lookup_or_create_dir around, so that's removed.
Signed-off-by: NJeff Mahoney <jeffm@suse.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

... even if it's a negative dentry.  That way we can set ->d_op on
root before anyone could race with us.  Simplify d_compare(), while
we are at it.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

This reverts commit 006f4571:

	This patch moves platform_data from struct device into
	struct platform_device, based on the two ideas:

	1. Now all platform_driver is registered by platform_driver_register,
	   which makes probe()/release()/... of platform_driver passed parameter
	   of platform_device *, so platform driver can get platform_data from
	   platform_device;

	2. Other kind of devices do not need to use platform_data, we can
	   decrease size of device if moving it to platform_device.

	Taking into consideration of thousands of files to be fixed and they
	can't be finished in one night(maybe it will take a long time), so we
	keep platform_data in device to allow two kind of cases coexist until
	all platform devices pass its platfrom data from
	platform_device->platform_data.

	All patches to do this kind of conversion are welcome.

As we don't really want to do it, it was a bad idea.

Cc: David Brownell <david-b@pacbell.net>
Cc: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

When building with gcc 3.2 I get thousands of warnings such as

include/linux/gfp.h: In function `allocflags_to_migratetype':
include/linux/gfp.h:105: warning: null format string

due to passing a NULL format string to warn_slowpath() in

#define __WARN()		warn_slowpath(__FILE__, __LINE__, NULL)

Split this case out into a separate call.  This also shrinks the kernel
slightly:

          text    data     bss     dec     hex filename
       4802274  707668  712704 6222646  5ef336 vmlinux
          text    data     bss     dec     hex filename
       4799027  703572  712704 6215303  5ed687 vmlinux

due to removeing one argument from the commonly-called __WARN().

[akpm@linux-foundation.org: reduce scope of `empty']
Acked-by: NJesper Nilsson <jesper.nilsson@axis.com>
Acked-by: NJohannes Weiner <hannes@cmpxchg.org>
Acked-by: NArjan van de Ven <arjan@linux.intel.com>
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Cc: Hugh Dickins <hugh@veritas.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NJaroslav Kysela <perex@perex.cz>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This patch fixes a problem when you use 32 nodes in the cluster
match:

% iptables -I PREROUTING -t mangle -i eth0 -m cluster \
  --cluster-total-nodes  32  --cluster-local-node  32 \
  --cluster-hash-seed 0xdeadbeef -j MARK --set-mark 0xffff
iptables: Invalid argument. Run `dmesg' for more information.
% dmesg | tail -1
xt_cluster: this node mask cannot be higher than the total number of nodes

The problem is related to this checking:

if (info->node_mask >= (1 << info->total_nodes)) {
	printk(KERN_ERR "xt_cluster: this node mask cannot be "
			"higher than the total number of nodes\n");
	return false;
}

(1 << 32) is 1. Thus, the checking fails.

BTW, I said this before but I insist: I have only tested the cluster
match with 2 nodes getting ~45% extra performance in an active-active setup.
The maximum limit of 32 nodes is still completely arbitrary. I'd really
appreciate if people that have more nodes in their setups let me know.
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: NPatrick McHardy <kaber@trash.net>

Pointed out by Dave Miller:

  CHECK   include/linux/netfilter (57 files)
/home/davem/src/GIT/net-2.6/usr/include/linux/netfilter/xt_LED.h:6: found __[us]{8,16,32,64} type without #include <linux/types.h>
Signed-off-by: NPatrick McHardy <kaber@trash.net>

Due to a semantic changes in flush_workqueue() the current approach of
synchronizing the sysfs handling for connections doesn't work anymore. The
whole approach is actually fully broken and based on assumptions that are
no longer valid.

With the introduction of Simple Pairing support, the creation of low-level
ACL links got changed. This change invalidates the reason why in the past
two independent work queues have been used for adding/removing sysfs
devices. The adding of the actual sysfs device is now postponed until the
host controller successfully assigns an unique handle to that link. So
the real synchronization happens inside the controller and not the host.

The only left-over problem is that some internals of the sysfs device
handling are not initialized ahead of time. This leaves potential access
to invalid data and can cause various NULL pointer dereferences. To fix
this a new function makes sure that all sysfs details are initialized
when an connection attempt is made. The actual sysfs device is only
registered when the connection has been successfully established. To
avoid a race condition with the registration, the check if a device is
registered has been moved into the removal work.

As an extra protection two flush_work() calls are left in place to
make sure a previous add/del work has been completed first.

Based on a report by Marc Pignat <marc.pignat@hevs.ch>
Signed-off-by: NMarcel Holtmann <marcel@holtmann.org>
Tested-by: NJustin P. Mattock <justinmattock@gmail.com>
Tested-by: NRoger Quadros <ext-roger.quadros@nokia.com>
Tested-by: NMarc Pignat <marc.pignat@hevs.ch>

This introduces a CDC Ethernet Emulation Model (EEM) host side
driver to support USB EEM devices.

EEM is different from the Ethernet Control Model (ECM) currently
supported by the "CDC Ethernet" driver.  One key difference is
that it doesn't require of USB interface alternate settings to
manage interface state; some maldesigned hardware can't handle
that part of USB.  It also avoids a separate USB interface for
control and status updates.

[ dbrownell@users.sourceforge.net: fix skb leaks, add rx packet
checks, improve fault handling, EEM conformance updates, cleanup ]
Signed-off-by: NOmar Laazimani <omar.oberthur@gmail.com>
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

tcp_prequeue() refers to the constant value (TCP_RTO_MIN) regardless of
the actual value might be tuned. The following patches fix this and make
tcp_prequeue get the actual value returns from tcp_rto_min().
Signed-off-by: NSatoru SATOH <satoru.satoh@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

See http://bugzilla.kernel.org/show_bug.cgi?id=13034

If the port gets into a TIME_WAIT state, then we cannot reconnect without
binding to a new port.
Tested-by: NPetr Vandrovec <petr@vandrovec.name>
Tested-by: NJean Delvare <khali@linux-fr.org>
Signed-off-by: NTrond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The Committed_AS field can underflow in certain situations:

>         # while true; do cat /proc/meminfo  | grep _AS; sleep 1; done | uniq -c
>               1 Committed_AS: 18446744073709323392 kB
>              11 Committed_AS: 18446744073709455488 kB
>               6 Committed_AS:    35136 kB
>               5 Committed_AS: 18446744073709454400 kB
>               7 Committed_AS:    35904 kB
>               3 Committed_AS: 18446744073709453248 kB
>               2 Committed_AS:    34752 kB
>               9 Committed_AS: 18446744073709453248 kB
>               8 Committed_AS:    34752 kB
>               3 Committed_AS: 18446744073709320960 kB
>               7 Committed_AS: 18446744073709454080 kB
>               3 Committed_AS: 18446744073709320960 kB
>               5 Committed_AS: 18446744073709454080 kB
>               6 Committed_AS: 18446744073709320960 kB

Because NR_CPUS can be greater than 1000 and meminfo_proc_show() does
not check for underflow.

But NR_CPUS proportional isn't good calculation.  In general,
possibility of lock contention is proportional to the number of online
cpus, not theorical maximum cpus (NR_CPUS).

The current kernel has generic percpu-counter stuff.  using it is right
way.  it makes code simplify and percpu_counter_read_positive() don't
make underflow issue.
Reported-by: NDave Hansen <dave@linux.vnet.ibm.com>
Signed-off-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Eric B Munson <ebmunson@us.ibm.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: <stable@kernel.org>		[All kernel versions]
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Some drivers using of_register_platform_driver() wrapper break on sparc
because the wrapper isn't in the header file.  This patch moves it from
Microblaze and PowerPC implementations and makes it common code.

Fixes this sparc64 allmodconfig build error (at least):

drivers/leds/leds-gpio.c: In function `gpio_led_init':
drivers/leds/leds-gpio.c:295: error: implicit declaration of function `of_register_platform_driver'
drivers/leds/leds-gpio.c: In function `gpio_led_exit':
drivers/leds/leds-gpio.c:311: error: implicit declaration of function `of_unregister_platform_driver'
Signed-off-by: NGrant Likely <grant.likely@secretlab.ca>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Richard Purdie <rpurdie@rpsys.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This fixes the problem introduced by commit 3bfacef4 (get rid of
special-casing the /sbin/loader on alpha): osf/1 ecoff binary segfaults
when binfmt_aout built as module.  That happens because aout binary
handler gets on the top of the binfmt list due to late registration, and
kernel attempts to execute the binary without preparatory work that must
be done by binfmt_loader.

Fixed by changing the registration order of the default binfmt handlers
using list_add_tail() and introducing insert_binfmt() function which
places new handler on the top of the binfmt list.  This might be generally
useful for installing arch-specific frontends for default handlers or just
for overriding them.
Signed-off-by: NIvan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Richard Henderson <rth@twiddle.net
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Current mem_cgroup_shrink_usage() has two problems.

1. It doesn't call mem_cgroup_out_of_memory and doesn't update
   last_oom_jiffies, so pagefault_out_of_memory invokes global OOM.

2. Considering hierarchy, shrinking has to be done from the
   mem_over_limit, not from the memcg which the page would be charged to.

mem_cgroup_try_charge_swapin() does all of these things properly, so we
use it and call cancel_charge_swapin when it succeeded.

The name of "shrink_usage" is not appropriate for this behavior, so we
change it too.
Signed-off-by: NDaisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Acked-by: NKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.cn>
Cc: Paul Menage <menage@google.com>
Cc: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

On a linux-next allyesconfig build:

kernel/trace/ring_buffer.c:1726:
	warning: passing argument 1 of 'atomic_cmpxchg' from incompatible pointer type
linux-next/arch/s390/include/asm/atomic.h:112:
	note: expected 'struct atomic_t *' but argument is of type 'struct atomic64_t *'

atomic_long_cmpxchg and atomic_long_xchg are incorrectly defined for 64
bit architectures.  They should be mapped to the atomic64_* variants.
Acked-by: NMathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Acked-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

virtio_net.h uses the macro ETH_ALEN which is defined in linux/if_ether.h.
Discovered when hacking on virtio-over-pci patches.
Signed-off-by: NGrant Likely <grant.likely@secretlab.ca>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NEric Dumazet <dada1@cosmosbay.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Original patch (dfa4411c) was buggy.
This is a more proper fix which introduces blk_rq_quiet() macro
alleviating the need for dumb, too short caching variables.

Thanks to Helge Deller and Bart for debugging this.
Signed-off-by: NBorislav Petkov <petkovbb@gmail.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Reported-and-tested-by: NHelge Deller <deller@gmx.de>
Signed-off-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>

It's possible for character sets to require a multi-byte null
string terminator. Add a helper function that determines the size
of the null terminator at runtime.
Signed-off-by: NJeff Layton <jlayton@redhat.com>
Acked-by: NSuresh Jayaraman <sjayaraman@suse.de>
Signed-off-by: NSteve French <sfrench@us.ibm.com>

The x_tables are organized with a table structure and a per-cpu copies
of the counters and rules. On older kernels there was a reader/writer 
lock per table which was a performance bottleneck. In 2.6.30-rc, this
was converted to use RCU and the counters/rules which solved the performance
problems for do_table but made replacing rules much slower because of
the necessary RCU grace period.

This version uses a per-cpu set of spinlocks and counters to allow to
table processing to proceed without the cache thrashing of a global
reader lock and keeps the same performance for table updates.
Signed-off-by: NStephen Hemminger <shemminger@vyatta.com>
Acked-by: NLinus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add regulator header file missing kernel-doc:

Warning(include/linux/regulator/driver.h:117): No description found for parameter 'set_mode'
Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
cc:	Liam Girdwood <lrg@slimlogic.co.uk>
cc:	Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: NLiam Girdwood <lrg@slimlogic.co.uk>

In order to utilize the full power of the new multi-touch devices, a
way to report detailed finger data to user space is needed. This patch
adds a multi-touch (MT) protocol which allows drivers to report details
for an arbitrary number of fingers.

The driver sends a SYN_MT_REPORT event via the input_mt_sync() function
when a complete finger has been reported.

In order to stay compatible with existing applications, the data
reported in a finger packet must not be recognized as single-touch
events. In addition, all finger data must bypass input filtering,
since subsequent events of the same type refer to different fingers.

A set of ABS_MT events with the desired properties are defined. The
events are divided into categories, to allow for partial implementation.
The minimum set consists of ABS_MT_TOUCH_MAJOR, ABS_MT_POSITION_X and
ABS_MT_POSITION_Y, which allows for multiple fingers to be tracked.
If the device supports it, the ABS_MT_WIDTH_MAJOR may be used to provide
the size of the approaching finger. Anisotropy and direction may be
specified with ABS_MT_TOUCH_MINOR, ABS_MT_WIDTH_MINOR and
ABS_MT_ORIENTATION. Devices with more granular information may specify
general shapes as blobs, i.e., as a sequence of rectangular shapes
grouped together by a ABS_MT_BLOB_ID. Finally, the ABS_MT_TOOL_TYPE
may be used to specify whether the touching tool is a finger or a pen.
Signed-off-by: NHenrik Rydberg <rydberg@euromail.se>
Signed-off-by: NDmitry Torokhov <dtor@mail.ru>

The integrated button on the new unibody Macbooks presents a need to
report explicit four-finger actions. Evidently, the finger pressing
the button is also touching the trackpad, so in order to fully support
three-finger actions, the driver must be able to report four-finger
actions. This patch adds a new button, BTN_TOOL_QUADTAP, which
achieves this.
Signed-off-by: NHenrik Rydberg <rydberg@euromail.se>
Signed-off-by: NDmitry Torokhov <dtor@mail.ru>

The Bluetooth stack uses a reference counting for all established ACL
links and if no user (L2CAP connection) is present, the link will be
terminated to save power. The problem part is the dedicated pairing
when using Legacy Pairing (Bluetooth 2.0 and before). At that point
no user is present and pairing attempts will be disconnected within
10 seconds or less. In previous kernel version this was not a problem
since the disconnect timeout wasn't triggered on incoming connections
for the first time. However this caused issues with broken host stacks
that kept the connections around after dedicated pairing. When the
support for Simple Pairing got added, the link establishment procedure
needed to be changed and now causes issues when using Legacy Pairing

When using Simple Pairing it is possible to do a proper reference
counting of ACL link users. With Legacy Pairing this is not possible
since the specification is unclear in some areas and too many broken
Bluetooth devices have already been deployed. So instead of trying to
deal with all the broken devices, a special pairing timeout will be
introduced that increases the timeout to 60 seconds when pairing is
triggered.

If a broken devices now puts the stack into an unforeseen state, the
worst that happens is the disconnect timeout triggers after 120 seconds
instead of 4 seconds. This allows successful pairings with legacy and
broken devices now.

Based on a report by Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: NMarcel Holtmann <marcel@holtmann.org>

Use a different work_struct variables for add_conn() and del_conn() and
use single work queue instead of two for adding and deleting connections.

It eliminates the following error on a preemptible kernel:

[  204.358032] Unable to handle kernel NULL pointer dereference at virtual address 0000000c
[  204.370697] pgd = c0004000
[  204.373443] [0000000c] *pgd=00000000
[  204.378601] Internal error: Oops: 17 [#1] PREEMPT
[  204.383361] Modules linked in: vfat fat rfcomm sco l2cap sd_mod scsi_mod iphb pvr2d drm omaplfb ps
[  204.438537] CPU: 0    Not tainted  (2.6.28-maemo2 #1)
[  204.443664] PC is at klist_put+0x2c/0xb4
[  204.447601] LR is at klist_put+0x18/0xb4
[  204.451568] pc : [<c0270f08>]    lr : [<c0270ef4>]    psr: a0000113
[  204.451568] sp : cf1b3f10  ip : cf1b3f10  fp : cf1b3f2c
[  204.463104] r10: 00000000  r9 : 00000000  r8 : bf08029c
[  204.468353] r7 : c7869200  r6 : cfbe2690  r5 : c78692c8  r4 : 00000001
[  204.474945] r3 : 00000001  r2 : cf1b2000  r1 : 00000001  r0 : 00000000
[  204.481506] Flags: NzCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM Segment kernel
[  204.488861] Control: 10c5387d  Table: 887fc018  DAC: 00000017
[  204.494628] Process btdelconn (pid: 515, stack limit = 0xcf1b22e0)
Signed-off-by: NRoger Quadros <ext-roger.quadros@nokia.com>
Signed-off-by: NMarcel Holtmann <marcel@holtmann.org>

In 2.6.25 we added UDP mem accounting.

This unfortunatly added a penalty when a frame is transmitted, since
we have at TX completion time to call sock_wfree() to perform necessary
memory accounting. This calls sock_def_write_space() and utimately
scheduler if any thread is waiting on the socket.
Thread(s) waiting for an incoming frame was scheduled, then had to sleep
again as event was meaningless.

(All threads waiting on a socket are using same sk_sleep anchor)

This adds lot of extra wakeups and increases latencies, as noted
by Christoph Lameter, and slows down softirq handler.

Reference : http://marc.info/?l=linux-netdev&m=124060437012283&w=2 

Fortunatly, Davide Libenzi recently added concept of keyed wakeups
into kernel, and particularly for sockets (see commit
37e5540b 
epoll keyed wakeups: make sockets use keyed wakeups)

Davide goal was to optimize epoll, but this new wakeup infrastructure
can help non epoll users as well, if they care to setup an appropriate
handler.

This patch introduces new DEFINE_WAIT_FUNC() helper and uses it
in wait_for_packet(), so that only relevant event can wakeup a thread
blocked in this function.

Trace of function calls from bnx2 TX completion bnx2_poll_work() is :
__kfree_skb()
 skb_release_head_state()
  sock_wfree()
   sock_def_write_space()
    __wake_up_sync_key()
     __wake_up_common()
      receiver_wake_function() : Stops here since thread is waiting for an INPUT
Reported-by: NChristoph Lameter <cl@linux.com>
Signed-off-by: NEric Dumazet <dada1@cosmosbay.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The old refok sections

  .text.init.refok
  .data.init.refok
  .exit.text.refok

have been deprecated since commit
312b1485.  After the other patches in
this patch series nothing is put in these sections, so clean things up
by eliminating all the remaining references to them.
Signed-off-by: NTim Abbott <tabbott@mit.edu>
Acked-by: NSam Ravnborg <sam@ravnborg.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

OSC's OSD2 target: [git clone git://git.open-osd.org/osc-osd/ master]
(Initiator code prior to this patch must use: "git checkout CDB_VER_OSD2r01"
 in the target tree above)

This is a summery of the wire changes:

 * OSDv2_ADDITIONAL_CDB_LENGTH == 192 => 228 (Total CDB is now 236 bytes)
 * Attributes List Element Header grew, so attribute values are 8 bytes
   aligned.
 * Cryptographic keys and signatures are 20 => 32
 * Few new definitions.

(Still missing new standard definitions attribute values, these do not change
 wire format and will be added later when needed)
Signed-off-by: NBoaz Harrosh <bharrosh@panasas.com>
Signed-off-by: NJames Bottomley <James.Bottomley@HansenPartnership.com>

In OSD2r04 draft, cryptographic key size changed to 32 bytes from
OSD1's 20 bytes. This causes a couple of on-the-wire structures
to change, including the CDB.

In this patch the OSD1/OSD2 handling is separated out in regard
to affected structures, but on-the-wire is still the same. All
on the wire changes will be submitted in one patch for bisect-ability.
Signed-off-by: NBoaz Harrosh <bharrosh@panasas.com>
Signed-off-by: NJames Bottomley <James.Bottomley@HansenPartnership.com>

In OSD2r05 draft each attribute list element header was changed
so attribute-value would be 8 bytes aligned. In OSD2r01-r04
it was aligned on 2 bytes. (This is because in OSD2r01 the complete
element was 8 bytes padded at end but the header was not adjusted
and caused permanent miss-alignment.)

OSD1 elements are not padded and might be or might not be aligned.
OSD1 is still supported.

In this code we do all the code re-factoring to separate OSD1/OSD2
differences but do not change actual wire format. All wire format
changes will happen in one patch later, for bisect-ability.
Signed-off-by: NBoaz Harrosh <bharrosh@panasas.com>
Signed-off-by: NJames Bottomley <James.Bottomley@HansenPartnership.com>

When building with a .config generated from 'make allmodconfig'
some build warnings are generated. This patch corrects the warnings,
adds a FC_FID_NONE (= 0) enumeration for FC-IDs and cleans up one
variable naming to meet our variable naming conventions. For example,
fc_lport's should be named "lport," not "lp."
Signed-off-by: NRobert Love <robert.w.love@intel.com>
Signed-off-by: NJames Bottomley <James.Bottomley@HansenPartnership.com>

Rogue ports are currently not tracked on any list. The only reference
to them is through any outstanding exchanges pending on the rogue ports.
If the module is removed while a retry is set on a rogue port
(say a Plogi retry for instance), this retry is not cancelled because there
is no reference to the rogue port in the discovery rports list. Thus the
local port can clean itself up, delete the exchange pool, and then the
rogue port timeout can fire and try to start up another exchange.

This patch tracks the rogue ports in a new list disc->rogue_rports. Creating
a new list instead of using the disc->rports list keeps remote port code
change to a minimum.

1)  Whenever a rogue port is created, it is immediately added to the
disc->rogue_rports list.

2) When the rogues port goes to ready, it is removed from the rogue list
and the real remote port is added to the disc->rports list

3) The removal of the rogue from the disc->rogue_rports list is done in
the context of the fc_rport_work() workQ thread in discovery callback.

4) Real rports are removed from the disc->rports list like before. Lookup
is done only in the real rports list. This avoids making large changes
to the remote port code.

5) In fc_disc_stop_rports, the rogues list is traversed in addition to the
real list to stop the rogue ports and issue logoffs on them. This way, rogue
ports get cleaned up when the local port goes away.

6) rogue remote ports are not removed from the list right away, but
removed late in fc_rport_work() context, multiple threads can find the same
remote port in the list and call rport_logoff(). Rport_logoff() only
continues with the logoff if port is not in NONE state, thus preventing
multiple logoffs and multiple list deletions.

7) Since the rport is removed from the disc list at a later stage
(in the disc callback), incoming frames can find the rport even if
rport_logoff() has been called on the rport. When rport_logoff() is called,
the rport state is set to NONE, and we are trying to cancel all exchanges
and retries on that port. While in this state, if an incoming
Plogi/Prli/Logo or other frames match the rport, we should not reply
because the rport is in the NONE state. Just drop the frame, since the
rport will be deleted soon in the disc callback (fc_rport_work)

8)  In fc_disc_single(), remove rport lookup and call to fc_disc_del_target.
fc_disc_single() is called from recv_rscn_req() where rport lookup
and rport_logoff is already done.
Signed-off-by: NAbhijeet Joglekar <abjoglek@cisco.com>
Signed-off-by: NRobert Love <robert.w.love@intel.com>
Signed-off-by: NJames Bottomley <James.Bottomley@HansenPartnership.com>