Pass the work_struct pointer to the work function rather than context data.
The work function can use container_of() to work out the data.

For the cases where the container of the work_struct may go away the moment the
pending bit is cleared, it is made possible to defer the release of the
structure by deferring the clearing of the pending bit.

To make this work, an extra flag is introduced into the management side of the
work_struct.  This governs auto-release of the structure upon execution.

Ordinarily, the work queue executor would release the work_struct for further
scheduling or deallocation by clearing the pending bit prior to jumping to the
work function.  This means that, unless the driver makes some guarantee itself
that the work_struct won't go away, the work function may not access anything
else in the work_struct or its container lest they be deallocated..  This is a
problem if the auxiliary data is taken away (as done by the last patch).

However, if the pending bit is *not* cleared before jumping to the work
function, then the work function *may* access the work_struct and its container
with no problems.  But then the work function must itself release the
work_struct by calling work_release().

In most cases, automatic release is fine, so this is the default.  Special
initiators exist for the non-auto-release case (ending in _NAR).
Signed-Off-By: NDavid Howells <dhowells@redhat.com>

Reclaim a word from the size of the work_struct by folding the pending bit and
the wq_data pointer together.  This shouldn't cause misalignment problems as
all pointers should be at least 4-byte aligned.
Signed-Off-By: NDavid Howells <dhowells@redhat.com>

Define a type for the work function prototype.  It's not only kept in the
work_struct struct, it's also passed as an argument to several functions.

This makes it easier to change it.
Signed-Off-By: NDavid Howells <dhowells@redhat.com>

Separate delayable work items from non-delayable work items be splitting them
into a separate structure (delayed_work), which incorporates a work_struct and
the timer_list removed from work_struct.

The work_struct struct is huge, and this limits it's usefulness.  On a 64-bit
architecture it's nearly 100 bytes in size.  This reduces that by half for the
non-delayable type of event.
Signed-Off-By: NDavid Howells <dhowells@redhat.com>

* 'merge' of master.kernel.org:/pub/scm/linux/kernel/git/paulus/powerpc:
  [POWERPC] Fix ucc_geth of_device discovery on mpc832x
  [POWERPC] Revert "[POWERPC] Add powerpc get/set_rtc_time interface to new generic rtc class"
  [POWERPC] Revert "[POWERPC] Enable generic rtc hook for the MPC8349 mITX"

* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6:
  [TG3]: Add missing unlock in tg3_open() error path.
  [IPV6]: Fix address/interface handling in UDP and DCCP, according to the scoping architecture.
  [IRDA]: Lockdep fix.
  [BLUETOOTH]: Fix unaligned access in hci_send_to_sock.
  [XFRM]: nlmsg length not computed correctly in the presence of subpolicies
  [XFRM]: Sub-policies broke policy events
  [IGMP]: Fix IGMPV3_EXP() normalization bit shift value.
  [Bluetooth] Ignore L2CAP config requests on disconnect
  [Bluetooth] Always include MTU in L2CAP config responses
  [Bluetooth] Check if RFCOMM session is still attached to the TTY
  [Bluetooth] Handling pending connect attempts after inquiry
  [Bluetooth] Attach low-level connections to the Bluetooth bus
  [IPV6] IP6TUNNEL: Add missing nf_reset() on input path.
  [IPV6] IP6TUNNEL: Delete all tunnel device when unloading module.
  [IPV6] ROUTE: Do not enable router reachability probing in router mode.
  [IPV6] ROUTE: Prefer reachable nexthop only if the caller requests.
  [IPV6] ROUTE: Try to use router which is not known unreachable.

mpc832x, as in mpc8360, needs to explicitly find and create the
platform device for ucc_geth in 2.6.19.  This code will likely be
readapted to Benh's new of_ methods for 2.6.20.
Signed-off-by: NKim Phillips <kim.phillips@freescale.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

Sparse noticed a locking imbalance in tg3_open(). This patch adds an
unlock to one of the error paths, so that tg3_open() always exits
without the lock held.
Signed-off-by: NIra W. Snyder <kernel@irasnyder.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TCP and RAW do not have this issue.  Closes Bug #7432.
Signed-off-by: NYOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

On Sat, 2006-11-18 at 16:12 +0300, Andrey Borzenkov wrote:

> =============================================
> [ INFO: possible recursive locking detected ]
> 2.6.19-rc5-2avb #2
> - ---------------------------------------------
> pppd/26425 is trying to acquire lock:
>  (&hashbin->hb_spinlock){....}, at: [<dfdea87a>] irlmp_slsap_inuse+0x5a/0x170
> [irda]
>
> but task is already holding lock:
>  (&hashbin->hb_spinlock){....}, at: [<dfdea857>] irlmp_slsap_inuse+0x37/0x170
> [irda]
>
> other info that might help us debug this:
> 1 lock held by pppd/26425:
>  #0:  (&hashbin->hb_spinlock){....}, at: [<dfdea857>]
> irlmp_slsap_inuse+0x37/0x170 [irda]
>
> stack backtrace:
>  [<c010413c>] dump_trace+0x1cc/0x200
>  [<c010418a>] show_trace_log_lvl+0x1a/0x30
>  [<c01047f2>] show_trace+0x12/0x20
>  [<c01048c9>] dump_stack+0x19/0x20
>  [<c01346ca>] __lock_acquire+0x8fa/0xc20
>  [<c0134d2d>] lock_acquire+0x5d/0x80
>  [<c02a851c>] _spin_lock+0x2c/0x40
>  [<dfdea87a>] irlmp_slsap_inuse+0x5a/0x170 [irda]
>  [<dfdebab2>] irlmp_open_lsap+0x62/0x180 [irda]
>  [<dfdf35d1>] irttp_open_tsap+0x181/0x230 [irda]
>  [<dfdc0c3d>] ircomm_open_tsap+0x5d/0xa0 [ircomm]
>  [<dfdc05d8>] ircomm_open+0xb8/0xd0 [ircomm]
>  [<dfdd0477>] ircomm_tty_open+0x4f7/0x570 [ircomm_tty]
>  [<c020bbe4>] tty_open+0x174/0x340
>  [<c016bd69>] chrdev_open+0x89/0x170
>  [<c0167bd6>] __dentry_open+0xa6/0x1d0
>  [<c0167da5>] nameidata_to_filp+0x35/0x40
>  [<c0167df9>] do_filp_open+0x49/0x50
>  [<c0167e47>] do_sys_open+0x47/0xd0
>  [<c0167f0c>] sys_open+0x1c/0x20
>  [<c010307d>] sysenter_past_esp+0x56/0x8d
>  [<b7f86410>] 0xb7f86410
>  =======================

The comment at the nesting lock says:

	/* Careful for priority inversions here !
	 * irlmp->links is never taken while another IrDA
	 * spinlock is held, so we are safe. Jean II */

So, under the assumption the author was right, it just needs a lockdep
annotation.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This reverts commit 7a69af63.

As advised by David Brownell:

http://marc.theaimsgroup.com/?l=linux-kernel&m=116387226902131&w=2Signed-off-by: NKim Phillips <kim.phillips@freescale.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

This reverts commit a8ed4f7e.

As advised by David Brownell:

http://marc.theaimsgroup.com/?l=linux-kernel&m=116387226902131&w=2Signed-off-by: NKim Phillips <kim.phillips@freescale.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

The "u16 *" derefs of skb->data need to be wrapped inside of
a get_unaligned().

Thanks to Gustavo Zacarias for the bug report.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

I actually dont have a test case for these; i just found them by
inspection. Refer to patch "[XFRM]: Sub-policies broke policy events"
for more info
Signed-off-by: NJamal Hadi Salim <hadi@cyberus.ca>
Acked-by: NMasahide NAKAMURA <nakam@linux-ipv6.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

XFRM policy events are broken when sub-policy feature is turned on.
A simple test to verify this:
run ip xfrm mon on one window and add then delete a policy on another
window ..
Signed-off-by: NJamal Hadi Salim <hadi@cyberus.ca>
Acked-by: NMasahide NAKAMURA <nakam@linux-ipv6.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The IGMPV3_EXP() macro doesn't correctly shift the normalization bit, so
time-out values are longer than they should be.

Thanks to Dirk Ooms for finding the problem in IGMPv3 - MLDv2 had a
similar problem that was already fixed a year ago. :-(
Signed-off-by: NDavid L Stevens <dlstevens@us.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Any L2CAP connection in disconnecting state shall not response
to any further config requests from the remote side. So in case
such a request is received, ignore it.
Signed-off-by: NVille Tervo <ville.tervo@nokia.com>
Signed-off-by: NMarcel Holtmann <marcel@holtmann.org>

When sending a positive config response it shall include the actual
MTU to be used on this channel. This differs from the Bluetooth 1.1
specification where it was enough to acknowledge the config request.
Signed-off-by: NMarcel Holtmann <marcel@holtmann.org>

If the RFCOMM session is no longer attached to the TTY device, then it
makes no sense to go through with changing the termios settings.
Signed-off-by: NMarcel Holtmann <marcel@holtmann.org>

After an inquiry completed or got canceled the Bluetooth core should
check for any pending connect attempts.
Signed-off-by: NMarcel Holtmann <marcel@holtmann.org>

To receive uvents for the low-level ACL and SCO links, they must be
assigned to a subsystem. It is enough to attach them to the already
established Bluetooth bus.
Signed-off-by: NMarcel Holtmann <marcel@holtmann.org>

Signed-off-by: NYasuyuki Kozakai <yasuyuki.kozakai@toshiba.co.jp>
Signed-off-by: NYOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>

Signed-off-by: NYasuyuki Kozakai <yasuyuki.kozakai@toshiba.co.jp>
Signed-off-by: NYOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>

RFC4191 explicitly states that the procedures are applicable to
hosts only.  We should not have changed behavior of routers.
Signed-off-by: NYOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>

Signed-off-by: NYOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>

Only routers in "FAILED" state should be considered unreachable.
Otherwise, we do not try to use speicific routes unless all least specific
routers are considered unreachable.
Signed-off-by: NYOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>

The ONDEMAND governor needs FREQ_TABLE
Signed-off-by: NMattia Dongili <malattia@linux.it>
Signed-off-by: NDave Jones <davej@redhat.com>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

* 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6:
  [PATCH] x86_64: Align data segment to PAGE_SIZE boundary
  [PATCH] x86-64: increase PHB1 split transaction timeout
  [PATCH] x86-64: Fix C3 timer test

o Explicitly align data segment to PAGE_SIZE boundary otherwise depending on
  config options and tool chain it might be placed on a non PAGE_SIZE aligned
  boundary and vmlinux loaders like kexec fail when they encounter a
  PT_LOAD type segment which is not aligned to PAGE_SIZE boundary.
Signed-off-by: NVivek Goyal <vgoyal@in.ibm.com>
Signed-off-by: NAndi Kleen <ak@suse.de>

SGI-PV: 958376
SGI-Modid: xfs-linux-melb:xfs-kern:27503a
Signed-off-by: NDavid Chinner <dgc@sgi.com>
Signed-off-by: NTim Shimmin <tes@sgi.com>

xfs_bmap_add_extent_delay_real()

SGI-PV: 957008
SGI-Modid: xfs-linux-melb:xfs-kern:27457a
Signed-off-by: NLachlan McIlroy <lachlan@sgi.com>
Signed-off-by: NShailendra Tripathi <stripathi@agami.com>
Signed-off-by: NTim Shimmin <tes@sgi.com>

ipath uses skb functions and won't build without CONFIG_NET.

Spotted by Randy Dunlap.
Signed-off-by: NBryan O'Sullivan <bryan.osullivan@qlogic.com>
Acked-by: NRandy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: NRoland Dreier <rolandd@cisco.com>

This is a quick hack to overcome the fact that SRCU currently does not
allow static initializers, and we need to sometimes initialize those
things before any other initializers (even "core" ones) can do so.

Currently we don't allow this at all for modules, and the only user that
needs is right now is cpufreq. As reported by Thomas Gleixner:

   "Commit b4dfdbb3 ("[PATCH] cpufreq:
    make the transition_notifier chain use SRCU breaks cpu frequency
    notification users, which register the callback > on core_init
    level."

Cc: Thomas Gleixner <tglx@timesys.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Andrew Morton <akpm@osdl.org>,
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

* 'for-linus' of master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband:
  IPoIB: Clear high octet in QP number

Switch to using irq_handler_t for interrupt function handler pointers.

Change name of m68knommu's irq_hanlder_t data structure so it doesn't
clash with the common type (include/linux/interrupt.h).
Signed-off-by: NGreg Ungerer <gerg@uclinux.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Fix a build error for the  enter:now PCI card.
Signed-off-by: NToralf Foerster <toralf.foerster@gmx.de>
Acked-by: NKarsten Keil <kkeil@suse.de>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Fix printk format warnings:
drivers/char/ftape/zftape/zftape-buffers.c:87: warning: format '%d' expects type
'int', but argument 3 has type 'size_t'
drivers/char/ftape/zftape/zftape-buffers.c:104: warning: format '%d' expects type
 'int', but argument 3 has type 'size_t'
Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

This is to fix compile error of x86-64 memory hotplug without any NUMA
option.

  CC      arch/x86_64/mm/init.o
arch/x86_64/mm/init.c:501: error: redefinition of 'memory_add_physaddr_to_nid'
include/linux/memory_hotplug.h:71: error: previous definition of 'memory_add_phys
addr_to_nid' was here
arch/x86_64/mm/init.c:509: error: redefinition of 'memory_add_physaddr_to_nid'
arch/x86_64/mm/init.c:501: error: previous definition of 'memory_add_physaddr_to_
nid' was here

I confirmed compile completion with !NUMA, (NUMA & !ACPI_NUMA),
or (NUMA & ACPI_NUMA).
Signed-off-by: NYasunori Goto <y-goto@jp.fujitsu.com>
Acked-by: NAndi Kleen <ak@suse.de>
Cc: "Randy.Dunlap" <rdunlap@xenotime.net>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Signed-off-by: NJeff Garzik <jeff@garzik.org>
Signed-off-by: NJean Delvare <khali@linux-fr.org>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>