try_one_irq() contains redundant code and lots of useless checks for
shared interrupts. Check for shared before setting IRQ_INPROGRESS and
then call handle_IRQ_event() while pending. Shorter version with the
same functionality.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

We run all handlers with interrupts disabled and expect them not to
enable them. Warn when we catch one who does.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

We cannot walk the action chain unlocked. Even if IRQ_INPROGRESS is
set an action can be removed and we follow a null pointer. It's safe
to take the lock there, because the code which removes the action will
call synchronize_irq() which waits unlocked for IRQ_INPROGRESS going
away.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

Thread affinity is already set by setup_affinity().

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

While rumaging through arch code I found that there are a few
workarounds which deal with the fact that the initial affinity setting
from request_irq() copies the mask into irq_data->affinity before the
chip code is called. In the normal path we unconditionally copy the
mask when the chip code returns 0.

Copy after the code is called and add a return code
IRQ_SET_MASK_OK_NOCOPY for the chip functions, which prevents the
copy. That way we see the real mask when the chip function decided to
truncate it further as some arches do. IRQ_SET_MASK_OK is 0, which is
the current behaviour.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

If the affinity had been set by the user, then a later request_irq()
will honour that setting. But online cpus can have changed. So apply
the online mask and for this case as well.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

IRQ_NO_BALANCING is already checked in irq_can_set_affinity() above,
no need to check it again.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

There is lot of #ifdef CONFIG_GENERIC_PENDING_IRQ along with
duplicated code in the irq core. Move the #ifdeffery into one place
and cleanup the code so it's readable. No functional change.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

The irq namespace has become quite convoluted. My bad.  Clean it up
and deprecate the old functions. All new functions follow the scheme:

irq number based:
    irq_set/get/xxx/_xxx(unsigned int irq, ...)

irq_data based:
	 irq_data_set/get/xxx/_xxx(struct irq_data *d, ....)

irq_desc based:
	 irq_desc_get_xxx(struct irq_desc *desc)

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

chips behind a slow bus cannot update the chip under desc->lock, but
we miss the chip_buslock/chip_bus_sync_unlock() calls around the set
type and set wake functions.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

We face more and more the requirement to expand nr_irqs at
runtime. The reason are irq expanders which can not be detected in the
early boot stage. So we speculate nr_irqs to have enough room. Further
Xen needs extra irq numbers and we really want to avoid adding more
"detection" code into the early boot. There is no real good reason why
we need to limit nr_irqs at early boot.

Allow the allocation code to expand nr_irqs. We have already 8k extra
number space in the allocation bitmap, so lets use it.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

Reason: Further patches are conflicting with mainline fixes

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

With CONFIG_SHIRQ_DEBUG=y we call a newly installed interrupt handler
in request_threaded_irq().

The original implementation (commit a304e1b8) called the handler
_BEFORE_ it was installed, but that caused problems with handlers
calling disable_irq_nosync(). See commit 377bf1e4

.

It's braindead in the first place to call disable_irq_nosync in shared
handlers, but ....

Moving this call after we installed the handler looks innocent, but it
is very subtle broken on SMP.

Interrupt handlers rely on the fact, that the irq core prevents
reentrancy.

Now this debug call violates that promise because we run the handler
w/o the IRQ_INPROGRESS protection - which we cannot apply here because
that would result in a possibly forever masked interrupt line.

A concurrent real hardware interrupt on a different CPU results in
handler reentrancy and can lead to complete wreckage, which was
unfortunately observed in reality and took a fricking long time to
debug.

Leave the code here for now. We want this debug feature, but that's
not easy to fix. We really should get rid of those
disable_irq_nosync() abusers and remove that function completely.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Anton Vorontsov <avorontsov@ru.mvista.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: stable@kernel.org # .28 -> .37

Lars-Peter Clausen pointed out:

   I stumbled upon this while looking through the existing archs using
   SPARSE_IRQ.  Even with SPARSE_IRQ the NR_IRQS is still the upper
   limit for the number of IRQs.

   Both PXA and MMP set NR_IRQS to IRQ_BOARD_START, with
   IRQ_BOARD_START being the number of IRQs used by the core.

   In various machine files the nr_irqs field of the ARM machine
   defintion struct is then set to "IRQ_BOARD_START + NR_BOARD_IRQS".

   As a result "nr_irqs" will greater then NR_IRQS which then again
   causes the "allocated_irqs" bitmap in the core irq code to be
   accessed beyond its size overwriting unrelated data.

The core code really misses a sanity check there.

This went unnoticed so far as by chance the compiler/linker places
data behind that bitmap which gets initialized later on those affected
platforms.

So the obvious fix would be to add a sanity check in early_irq_init()
and break all affected platforms. Though that check wants to be
backported to stable as well, which will require to fix all known
problematic platforms and probably some more yet not known ones as
well. Lots of churn.

A way simpler solution is to allocate a slightly larger bitmap and
avoid the whole churn w/o breaking anything. Add a few warnings when
an arch returns utter crap.

Reported-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@kernel.org # .37
Cc: Haojian Zhuang <haojian.zhuang@marvell.com>
Cc: Eric Miao <eric.y.miao@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>

* 'rtc-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  RTC: Re-enable UIE timer/polling emulation
  RTC: Revert UIE emulation removal
  RTC: Release mutex in error path of rtc_alarm_irq_enable

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (37 commits)
  net: deinit automatic LIST_HEAD
  net: dont leave active on stack LIST_HEAD
  net: provide default_advmss() methods to blackhole dst_ops
  tg3: Restrict phy ioctl access
  drivers/net: Call netif_carrier_off at the end of the probe
  ixgbe: work around for DDP last buffer size
  ixgbe: fix panic due to uninitialised pointer
  e1000e: flush all writebacks before unload
  e1000e: check down flag in tasks
  isdn: hisax: Use l2headersize() instead of dup (and buggy) func.
  arp_notify: unconditionally send gratuitous ARP for NETDEV_NOTIFY_PEERS.
  cxgb4vf: Use defined Mailbox Timeout
  cxgb4vf: Quiesce Virtual Interfaces on shutdown ...
  cxgb4vf: Behave properly when CONFIG_DEBUG_FS isn't defined ...
  cxgb4vf: Check driver parameters in the right place ...
  pch_gbe: Fix the MAC Address load issue.
  iwlwifi: Delete iwl3945_good_plcp_health.
  net/can/softing: make CAN_SOFTING_CS depend on CAN_SOFTING
  netfilter: nf_iterate: fix incorrect RCU usage
  pch_gbe: Fix the issue that the receiving data is not normal.
  ...

* 'for-linus/bugfixes' of git://xenbits.xen.org/people/ianc/linux-2.6:
  xen: suspend and resume system devices when running PVHVM

* 'fixes-2.6.38' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
  workqueue: make sure MAYDAY_INITIAL_TIMEOUT is at least 2 jiffies long
  workqueue, freezer: unify spelling of 'freeze' + 'able' to 'freezable'
  workqueue: wake up a worker when a rescuer is leaving a gcwq

commit 9b5e383c

 (net: Introduce
unregister_netdevice_many()) left an active LIST_HEAD() in
rollback_registered(), with possible memory corruption.

Even if device is freed without touching its unreg_list (and therefore
touching the previous memory location holding LISTE_HEAD(single), better
close the bug for good, since its really subtle.

(Same fix for default_device_exit_batch() for completeness)

Reported-by: Michal Hocko <mhocko@suse.cz>
Tested-by: Michal Hocko <mhocko@suse.cz>
Reported-by: Eric W. Biderman <ebiderman@xmission.com>
Tested-by: Eric W. Biderman <ebiderman@xmission.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Ingo Molnar <mingo@elte.hu>
CC: Octavian Purdila <opurdila@ixiacom.com>
CC: stable <stable@kernel.org> [.33+]
Signed-off-by: David S. Miller <davem@davemloft.net>

Eric W. Biderman and Michal Hocko reported various memory corruptions
that we suspected to be related to a LIST head located on stack, that
was manipulated after thread left function frame (and eventually exited,
so its stack was freed and reused).

Eric Dumazet suggested the problem was probably coming from commit
44345724

 (net: factorize
sync-rcu call in unregister_netdevice_many)

This patch fixes __dev_close() and dev_close() to properly deinit their
respective LIST_HEAD(single) before exiting.

References: https://lkml.org/lkml/2011/2/16/304
References: https://lkml.org/lkml/2011/2/14/223

Reported-by: Michal Hocko <mhocko@suse.cz>
Tested-by: Michal Hocko <mhocko@suse.cz>
Reported-by: Eric W. Biderman <ebiderman@xmission.com>
Tested-by: Eric W. Biderman <ebiderman@xmission.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Ingo Molnar <mingo@elte.hu>
CC: Octavian Purdila <opurdila@ixiacom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Commit 0dbaee3b

 (net: Abstract default ADVMSS behind an
accessor.) introduced a possible crash in tcp_connect_init(), when
dst->default_advmss() is called from dst_metric_advmss()

Reported-by: George Spelvin <linux@horizon.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

When list debugging is enabled, we aim to readably show list corruption
errors, and the basic list_add/list_del operations end up having extra
debugging code in them to do some basic validation of the list entries.

However, "list_del_init()" and "list_move[_tail]()" ended up avoiding
the debug code due to how they were written. This fixes that.

So the _next_ time we have list_move() problems with stale list entries,
we'll hopefully have an easier time finding them..

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

* 'pm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6:
  PM / Hibernate: Return error code when alloc_image_page() fails

* 'drm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6:
  drm/radeon/kms: add missing frac fb div flag for dce4+
  drm/radeon/kms: do not reject X16 and Y16X16 floating-point formats on r300
  drm/nouveau: fix suspend/resume on GPUs that don't have PM support
  drm/nouveau: flips/flipd need to always set 'evict' for move_accel_cleanup()
  drm/nv40: fix tiling-related setup for a number of chipsets
  drm/nouveau: fix non-EDIDful native mode selection
  drm/nouveau: Fix detection of DDC-based LVDS on DCB15 boards.
  drm/nv04-nv40: Fix NULL dereference when we fail to find an LVDS native mode.
  drm/nv10: Fix crash when allocating a BO larger than half the available VRAM.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
  IB/qib: Prevent double completions after a timeout or RNR error
  IB/qib: Fix double add_timer()
  RDMA/nes: Don't generate async events for unregistered devices

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc-2.6:
  sparc64: Fix NMI startup bug which also breaks perf.
  sparc: fix size argument to find_next_zero_bit()
  sparc: use bitmap_set()
  sparc32: unaligned memory access (MNA) trap handler bug

Validate number of blocks in map and remove redundant variable.

Signed-off-by: Timo Warns <warns@pre-sense.de>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

This patch re-enables UIE timer/polling emulation for rtc devices
that do not support alarm irqs.

CC: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
CC: Thomas Gleixner <tglx@linutronix.de>
Reported-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: John Stultz <john.stultz@linaro.org>

Uwe pointed out that my alarm based UIE emulation is not sufficient
to replace the older timer/polling based UIE emulation on devices
where there is no alarm irq. This causes rtc devices without alarms
to return -EINVAL to UIE ioctls. The fix is to re-instate the old
timer/polling method for devices without alarm irqs.

This patch reverts the following commits:
042620a0 - Remove UIE emulation
1daeddd5 - Cleanup removed UIE emulation declaration
b5cc8ca1

 - Remove Kconfig symbol for UIE emulation

The emulation mode will still need to be wired-in with a following
patch before it will work.

CC: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
CC: Thomas Gleixner <tglx@linutronix.de>
Reported-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: John Stultz <john.stultz@linaro.org>

On hardware that doesn't support alarm interrupts, rtc_alarm_irq_enable
could return without releasing the ops_lock mutex.

This was introduced in
	aa0be0f4

 (RTC: Propagate error handling via rtc_timer_enqueue properly)

This patch corrects the issue by only returning once the mutex is
released.

[john.stultz: Reworded the commit log]

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: John Stultz <john.stultz@linaro.org>

If management firmware is present and the device is down, the firmware
will assume control of the phy.  If a phy access were allowed from the
host, it will collide with firmware phy accesses, resulting in
unpredictable behavior.  This patch fixes the problem by disallowing phy
accesses during the problematic condition.

Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Without calling of netif_carrier_off at the end of the probe the operstate
is unknown when the device is initially opened. By default the carrier is
on so when the device is opened and netif_carrier_on is called the link
watch event is not fired and operstate remains zero (unknown).

This patch fixes this behavior in forcedeth and r8169.

Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Acked-by: Francois Romieu <romieu@fr.zoreil.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

There is a double completion associated with error handling for RC QPs.

The sequence is:

 - The do_rc_ack() routine fields an RNR nack and there are 0
   rnr_retries configured on the QP.
 - qib_error_qp() stops the pending timer
 - qib_rc_send_complete() is called from sdma_complete()
 - qib_rc_send_complete() starts the timer because the msb of the psn
   just completed says an ack is needed.
 - a bunch of flushes occur as ipoib posts WQEs to an error'ed QP
 - rc_timeout() calls qib_restart_rc()
 - qib_restart_rc() calls qib_send_complete() with a
   IB_WC_RETRY_EXC_ERR on a wqe that has already been completed in the
   past

The fix avoids starting the timer since another packet will never
arrive.

Signed-off-by: Mike Marciniszyn <mike.marciniszyn@qlogic.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

Otherwise we fail to properly suspend/resume all of the emulated devices.

Something between 2.6.38-rc2 and rc3 appears to have exposed this
issue, but it's always been wrong not to do this.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Jeremy Fitzhardinge <jeremy@goop.org>

A HW limitation was recently discovered where the last buffer in a DDP offload
cannot be a full buffer size in length. Fix the issue with a work around by
adding another buffer with size = 1.

Signed-off-by: Amir Hanania <amir.hanania@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

Systems containing an 82599EB and running a backported driver from
upstream were panicing on boot.  It turns out hw->mac.ops.setup_sfp is
only set for 82599, so one should check to be sure that pointer is set
before continuing in ixgbe_sfp_config_module_task.  I verified by
inspection that the upstream driver has the same issue and also added a
check before the call in ixgbe_sfp_link_config.

Signed-off-by: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

The driver was not flushing all writebacks before unloading, possibly
causing memory to be written by the hardware after the driver had
reinitialized the rings.

This adds missing functionality to flush any pending writebacks and is
called in all spots where descriptors should be completed before the driver
begins processing.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Reviewed-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

This change is part of a fix to avoid any tasks running while the driver is
exiting and deinitializing resources.

Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

* 'for-2.6.38' of git://linux-nfs.org/~bfields/linux:
  nfsd: correctly handle return value from nfsd_map_name_to_*