Stale entries in the CQ being destroyed causes hardware to generate
EQEs indefinitely for a given CQ.  Thus causing uncontrolled execution
of irq_handler.  This patch fixes this using following sementics:

    * irq_handler will ring EQ doorbell atleast once and implement budgeting scheme.
    * cq_destroy will count number of valid entires during destroy and ring
      cq-db so that hardware does not generate uncontrolled EQE.
    * cq_destroy will synchronize with last running irq_handler instance.
    * arm_cq will always defer arming CQ till poll_cq, except for the first arm_cq call.
    * poll_cq will always ring cq-db with arm=SET if arm_cq was called prior to enter poll_cq.
    * poll_cq will always ring cq-db with arm=UNSET if arm_cq was not called prior to enter poll_cq.
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

drivers/infiniband/hw/ocrdma/ocrdma_verbs.c: In function ‘_ocrdma_modify_qp’:
drivers/infiniband/hw/ocrdma/ocrdma_verbs.c:1299:31: error: ‘old_qps’ may be used uninitialized in this function [-Werror=maybe-uninitialized]
  status = ocrdma_mbx_modify_qp(dev, qp, attr, attr_mask, old_qps);

ocrdma_mbx_modify_qp() (and subsequent calls) doesn't appear to use old_qps
so it doesn't need to be passed on.  Removing the variable results in the
warning going away.
Signed-off-by: NPrarit Bhargava <prarit@redhat.com>
Acked-by: Devesh Sharma (Devesh.sharma@emulex.com)
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Pull ARM SoC fixes from Olof Johansson:
 "A collection of fixes for ARM platforms.  Most are fixes for DTS
  files, mostly from DT conversion on OMAP which is still finding a few
  issues here and there.

  There's a couple of small stale code removal patches that we usually
  queue for the next release instead, but they seemed harmless enough to
  bring in now.

  Also, a fix for backlight on some PXA platforms, and a cache
  configuration fix for Tegra, etc"

* tag 'fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc: (25 commits)
  MAINTAINERS: add additional ARM BCM281xx/BCM11xxx maintainer
  ARM: tegra: only run PL310 init on systems with one
  ARM: tegra: Add head numbers to display controllers
  ARM: imx6: build pm-imx6q.c independently of CONFIG_PM
  ARM: tegra: fix RTC0 alias for Cardhu
  ARM: dove: dt: revert PMU interrupt controller node
  Documentation: dt: OMAP: Update Overo/Tobi
  ARM: dts: Add support for both OMAP35xx and OMAP36xx Overo/Tobi
  ARM: dts: omap3-tobi: Use the correct vendor prefix
  ARM: dts: omap3-tobi: Fix boot with OMAP36xx-based Overo
  ARM: OMAP2+: Remove legacy macros for zoom platforms
  ARM: OMAP2+: Remove MACH_NOKIA_N800
  ARM: dts: N900: add missing compatible property
  ARM: dts: N9/N950: fix boot hang with 3.14-rc1
  ARM: OMAP1: nokia770: enable tahvo-usb
  ARM: OMAP2+: gpmc: fix: DT ONENAND child nodes not probed when MTD_ONENAND is built as module
  ARM: OMAP2+: gpmc: fix: DT NAND child nodes not probed when MTD_NAND is built as module
  ARM: dts: omap3-gta04: Fix mmc1 properties.
  ARM: dts: omap3-gta04: Fix 'aux' gpio key flags.
  ARM: OMAP2+: add missing ARCH_HAS_OPP
  ...

Pull regulator fixes from Mark Brown:
 "Mostly unexciting driver fixes, plus one fix to lower the severity of
  the log message when we don't use an optional regulator - the fixes
  for ACPI system made this come up more often and it was correctly
  observed that it was causing undue concern for users"

* tag 'regulator-v3.14-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator:
  regulator: max14577: Fix invalid return value on DT parse success
  regulator: core: Change dummy supplies error message to a warning
  regulator: s5m8767: Add missing of_node_put
  regulator: s5m8767: Use of_get_child_by_name
  regulator: da9063: Bug fix when setting max voltage on LDOs 5-11

Pull timer fix from Thomas Gleixner:
 "Serialize the registration of a new sched_clock in the currently ARM
  only generic sched_clock facilty to avoid sched_clock havoc"

* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched_clock: Prevent callers from seeing half-updated data

Pull x86 fixes from Thomas Gleixner:

 - a bugfix which prevents a divide by 0 panic when the newly introduced
   try_msr_calibrate_tsc() fails

 - enablement of the Baytrail platform to utilize the newfangled msr
   based calibration

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86: tsc: Add missing Baytrail frequency to the table
  x86, tsc: Fallback to normal calibration if fast MSR calibration fails

Pull irq fixes from Thomas Gleixner:
 "Another four fixlets to tame the ARM orion irq chip"

* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  irqchip: orion: Fix getting generic chip pointer.
  irqchip: orion: clear stale interrupts in irq_startup
  irqchip: orion: use handle_edge_irq on bridge irqs
  irqchip: orion: clear bridge cause register on init

Pull USB fixes from Greg KH:
 "Here are a number of USB fixes for reported issues for 3.14-rc4

  The majority of these are for USB gadget, phy, and musb driver issues.
  And there's a few new device ids thrown in for good measure"

* tag 'usb-3.14-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb:
  usb: chipidea: need to mask when writting endptflush and endptprime
  usb: musb: correct use of schedule_delayed_work()
  usb: phy: msm: fix compilation errors when !CONFIG_PM_SLEEP
  usb: gadget: fix NULL pointer dereference
  usb: gadget: printer: using gadget_is_otg to check otg support at runtime
  phy: let phy_provider_register be the last step in registering PHY
  phy-core: Don't allow building phy-core as a module
  phy-core: Don't propagate -ENOSUPP from phy_pm_runtime_get_sync to caller
  phy-core: phy_get: Leave error logging to the caller
  phy,phy-bcm-kona-usb2.c: Add dependency on HAS_IOMEM
  usb: musb: correct use of schedule_delayed_work()
  usb: musb: do not sleep in atomic context
  USB: serial: option: blacklist interface 4 for Cinterion PHS8 and PXS8
  USB: EHCI: add delay during suspend to prevent erroneous wakeups
  usb: gadget: bcm63xx_udc: fix build failure on DMA channel code
  usb: musb: do not sleep in atomic context
  usb: gadget: s3c2410_udc: Fix build error
  usb: musb: core: Fix remote-wakeup resume
  usb: musb: host: Fix SuperSpeed hub enumeration
  usb: musb: fix obex in g_nokia.ko causing kernel panic

Pull TTY revert from Greg KH:
 "Here is a single commit, a revert of a sysfs file change that ended up
  breaking a userspace tool"

* tag 'tty-3.14-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty:
  Revert "tty: Set correct tty name in 'active' sysfs attribute"

Pull staging tree fix from Greg KH:
 "Here is a single android driver fix for 3.14-rc4 that fixes a reported
  problem in the binder driver"

* tag 'staging-3.14-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging:
  staging: binder: Fix death notifications

Pull char/misc fix from Greg KH:
 "Here is a single commit, to fix a reported problem in the mei driver"

* tag 'char-misc-3.14-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc:
  mei: set client's read_cb to NULL when flow control fails

Add myself as an additional maintainer for the Broadcom mobile
SoCs.
Signed-off-by: NMatt Porter <mporter@linaro.org>
Acked-by: NChristian Daudt <bcm@fixthebug.org>
Signed-off-by: NOlof Johansson <olof@lixom.net>

Merge remote-tracking branches 'regulator/fix/da9063', 'regulator/fix/max14577' and 'regulator/fix/s5m8767' into regulator-linus

This reverts commit d8a5dc30.

This breaks plymouth installs, either because plymouth is using the file
"incorrectly" or because the patch is incorrect.  Either way, this needs
to be reverted until it is all figured out.
Reported-by: NJosh Boyer <jwboyer@fedoraproject.org>
Reported-by: NRay Strode <halfline@gmail.com>
Cc: Lennart Poettering <lennart@poettering.net>
Cc: Kay Sievers <kay@vrfy.org>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: David Herrmann <dh.herrmann@gmail.com>
Cc: Werner Fink <werner@suse.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Pull scheduler fixes from Ingo Molnar:
 "Misc fixlets: a fair number of them resulting from the new
  SCHED_DEADLINE code"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/deadline: Remove useless dl_nr_total
  sched/deadline: Test for CPU's presence explicitly
  sched: Add 'flags' argument to sched_{set,get}attr() syscalls
  sched: Fix information leak in sys_sched_getattr()
  sched,numa: add cond_resched to task_numa_work
  sched/core: Make dl_b->lock IRQ safe
  sched/core: Fix sched_rt_global_validate
  sched/deadline: Fix overflow to handle period==0 and deadline!=0
  sched/deadline: Fix bad accounting of nr_running

Pull perf fixes from Ingo Molnar:
 "Misc fixlets from all around the place"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/uncore: Fix IVT/SNB-EP uncore CBOX NID filter table
  perf/x86: Correctly use FEATURE_PDCM
  perf, nmi: Fix unknown NMI warning
  perf trace: Fix ioctl 'request' beautifier build problems on !(i386 || x86_64) arches
  perf trace: Add fallback definition of EFD_SEMAPHORE
  perf list: Fix checking for supported events on older kernels
  perf tools: Handle PERF_RECORD_HEADER_EVENT_TYPE properly
  perf probe: Do not add offset twice to uprobe address
  perf/x86: Fix Userspace RDPMC switch
  perf/x86/intel/p6: Add userspace RDPMC quirk for PPro

Pull hwmon fix from Guenter Roeck:
 "Fix writing the minimum temperature in max1668 driver"

* tag 'hwmon-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging:
  hwmon: (max1668) Fix writing the minimum temperature

Pull xfs fixes from Dave Chinner:
 "This is the first pull request I've had to do for you, so I'm still
  sorting things out.  The reason I'm sending this and not Ben should be
  obvious from the first commit below - SGI has stepped down from the
  XFS maintainership role.  As such, I'd like to take another
  opportunity to thank them for their many years of effort maintaining
  XFS and supporting the XFS community that they developed from the
  ground up.

  So I haven't had time to work things like signed tags into my
  workflows yet, so this is just a repo branch I'm asking you to pull
  from.  And yes, I named the branch -rc4 because I wanted the fixes in
  rc4, not because the branch was for merging into -rc3.  Probably not
  right, either.

  Anyway, I should have everything sorted out by the time the next merge
  window comes around.  If there's anything that you don't like in the
  pull req, feel free to flame me unmercifully.

  The changes are fixes for recent regressions and important thinkos in
  verification code:

        - a log vector buffer alignment issue on ia32
        - timestamps on truncate got mangled
        - primary superblock CRC validation fixes and error message
          sanitisation"

* 'xfs-fixes-for-3.14-rc4' of git://oss.sgi.com/xfs/xfs:
  xfs: limit superblock corruption errors to actual corruption
  xfs: skip verification on initial "guess" superblock read
  MAINTAINERS: SGI no longer maintaining XFS
  xfs: xfs_sb_read_verify() doesn't flag bad crcs on primary sb
  xfs: ensure correct log item buffer alignment
  xfs: ensure correct timestamp updates from truncate

Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/urgent fixes from Arnaldo Carvalho de Melo:

  * Handle PERF_RECORD_HEADER_EVENT_TYPE properly. (Jiri Olsa)

  * Fix checking for supported events on older kernels in
    'perf list' (Vince Weaver)

  * Do not add offset twice to uprobe address in
    'perf probe' (Masami Hiramatsu)

  * Fix perf trace's ioctl 'request' beautifier build problems
    on !(i386 || x86_64) arches (Arnaldo Carvalho de Melo)

  * Fix 'perf trace' build by adding a fallback definition for
    EFD_SEMAPHORE (Ben Hutchings)
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NIngo Molnar <mingo@kernel.org>

This fixes bug introduced in 667a6b7a (regulator: max14577: Add missing
of_node_put). The DTS parsing function returned number of matched
regulators as success status which then was compared against 0 in probe.

Result was a probe fail after successful parsing the DTS:
max14577-regulator: probe of max14577-regulator failed with error 2
Signed-off-by: NKrzysztof Kozlowski <k.kozlowski@samsung.com>
Reviwed-by: NSachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: NMark Brown <broonie@linaro.org>

irqchip mvebu fixes for v3.14

 - orion:
    - fixes for clearing bridge cause register, and clearing stale interrupts
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Pull devicetree fixes from Grant Likely:
 "Device tree compatible match order bug fix

  This branch contains a bug fix for the way devicetree code identifies
  the type of device.  Device drivers can contain a list of
  of_device_ids, but it more than one entry will match, then the device
  driver may choose the wrong one.  Commit 10535314, "match each node
  compatible against all given matches first", was queued for v3.14 but
  ended up causing other bugs.  Commit 06b29e76 attempted to fix it
  but it had other bugs.  Merely reverting the fix and waiting until
  v3.15 isn't a good option because there is code in v3.14 that depends
  on the revised behaviour to boot.

  This branch should finally fixes the problem correctly.  This time
  instead of just hoping that the patch is correct, this branch also
  adds new testcases that validate the behaviour.

  The changes in this branch are larger than I would like for a -rc
  pull, but moving the test case data out of out of arch/arm so that it
  could be validated on other architectures was important"

* tag 'dt-for-linus' of git://git.secretlab.ca/git/linux:
  of: Add self test for of_match_node()
  of: Move testcase FDT data into drivers/of
  of: reimplement the matching method for __of_match_node()
  Revert "of: search the best compatible match first in __of_match_node()"

Pull watchdog fix from Wim Van Sebroeck:
 "It corrects the error code when no device was found for w83697hf_wdt"

* git://www.linux-watchdog.org/linux-watchdog:
  watchdog: w83697hf_wdt: return ENODEV if no device was found

Enabling SPARSE_IRQ shows up a bug in the irq-orion bridge interrupt
handler. The bridge interrupt is implemented using a single generic
chip. Thus the parameter passed to irq_get_domain_generic_chip()
should always be zero.
Signed-off-by: NAndrew Lunn <andrew@lunn.ch>
Acked-by: NSebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Fixes: 9dbd90f1 ("irqchip: Add support for Marvell Orion SoCs")
Cc: <stable@vger.kernel.org> # v3.11+
Signed-off-by: NJason Cooper <jason@lakedaemon.net>

This patch updates the CBOX PMU filters mapping tables for SNB-EP
and IVT (model 45 and 62 respectively).

The NID umask always comes in addition to another umask.
When set, the NID filter is applied.

The current mapping tables were missing some code/umask
combinations to account for the NID umask. This patch
fixes that.

Cc: mingo@elte.hu
Cc: ak@linux.intel.com
Reviewed-by: NYan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: NStephane Eranian <eranian@google.com>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140219131018.GA24475@quadSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

The current code simply assumes Intel Arch PerfMon v2+ to have
the IA32_PERF_CAPABILITIES MSR; the SDM specifies that we should check
CPUID[1].ECX[15] (aka, FEATURE_PDCM) instead.

This was found by KVM which implements v2+ but didn't provide the
capabilities MSR. Change the code to DTRT; KVM will also implement the
MSR and return 0.

Cc: pbonzini@redhat.com
Reported-by: N"Michael S. Tsirkin" <mst@redhat.com>
Suggested-by: NEduardo Habkost <ehabkost@redhat.com>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140203132903.GI8874@twins.programming.kicks-ass.netSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

When using BTS on Core i7-4*, I get the below kernel warning.

$ perf record -c 1 -e branches:u ls
Message from syslogd@labpc1501 at Nov 11 15:49:25 ...
 kernel:[  438.317893] Uhhuh. NMI received for unknown reason 31 on CPU 2.

Message from syslogd@labpc1501 at Nov 11 15:49:25 ...
 kernel:[  438.317920] Do you have a strange power saving mode enabled?

Message from syslogd@labpc1501 at Nov 11 15:49:25 ...
 kernel:[  438.317945] Dazed and confused, but trying to continue

Make intel_pmu_handle_irq() take the full exit path when returning early.

Cc: eranian@google.com
Cc: peterz@infradead.org
Cc: mingo@kernel.org
Signed-off-by: NMarkus Metzger <markus.t.metzger@intel.com>
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1392425048-5309-1-git-send-email-andi@firstfloor.orgSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

ENDPTFLUSH and ENDPTPRIME registers are set by software and clear
by hardware. There is a bit for each endpoint. When we are setting
a bit for an endpoint we should make sure we do not touch other
endpoint bit. There is a race condition if the hardware clear the
bit between the read and the write in hw_write.

Cc: stable <stable@vger.kernel.org> # 3.11+
Signed-off-by: NPeter Chen <peter.chen@freescale.com>
Signed-off-by: NMatthieu CASTET <matthieu.castet@parrot.com>
Tested-by: NMichael Grzeschik <mgrzeschik@pengutronix.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

The change (008fa749) that moved the
node release code to a separate function broke death notifications in
some cases. When it encountered a reference without a death
notification request, it would skip looking at the remaining
references, and therefore fail to send death notifications for them.

Cc: Colin Cross <ccross@android.com>
Cc: Android Kernel Team <kernel-team@android.com>
Cc: stable <stable@vger.kernel.org> # 3.10
Signed-off-by: NArve Hjønnevåg <arve@android.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Signed-off-by: NJeremy Compostella <jeremy.compostella@intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

In deadline class we do not have group scheduling like in RT.

dl_nr_total is the same as dl_nr_running. So, one of them should
be removed.

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: NKirill Tkhai <tkhai@yandex.ru>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/368631392675853@web20h.yandex.ruSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

A hot-removed CPU may have ID that is numerically larger than the number of
existing CPUs in the system (e.g. we can unplug CPU 4 from a system that
has CPUs 0, 1 and 4).

Thus the WARN_ONs should check whether the CPU in question is currently
present, not whether its ID value is less than num_present_cpus().

Cc: Ingo Molnar <mingo@kernel.org>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Reported-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1392646353-1874-1-git-send-email-boris.ostrovsky@oracle.comSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

Because of a recent syscall design debate; its deemed appropriate for
each syscall to have a flags argument for future extension; without
immediately requiring new syscalls.

Cc: juri.lelli@gmail.com
Cc: Ingo Molnar <mingo@redhat.com>
Suggested-by: NMichael Kerrisk <mtk.manpages@gmail.com>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140214161929.GL27965@twins.programming.kicks-ass.netSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

We're copying the on-stack structure to userspace, but forgot to give
the right number of bytes to copy. This allows the calling process to
obtain up to PAGE_SIZE bytes from the stack (and possibly adjacent
kernel memory).

This fix copies only as much as we actually have on the stack
(attr->size defaults to the size of the struct) and leaves the rest of
the userspace-provided buffer untouched.

Found using kmemcheck + trinity.

Fixes: d50dde5a ("sched: Add new scheduler syscalls to support an extended scheduling parameters ABI")
Cc: Dario Faggioli <raistlin@linux.it>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: NVegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1392585857-10725-1-git-send-email-vegard.nossum@oracle.comSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

Normally task_numa_work scans over a fairly small amount of memory,
but it is possible to run into a large unpopulated part of virtual
memory, with no pages mapped. In that case, task_numa_work can run
for a while, and it may make sense to reschedule as required.

Cc: akpm@linux-foundation.org
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: NRik van Riel <riel@redhat.com>
Reported-by: NXing Gang <gang.xing@hp.com>
Tested-by: NChegu Vinod <chegu_vinod@hp.com>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1392761566-24834-2-git-send-email-riel@redhat.comSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

Fix this lockdep warning:

[   44.804600] =========================================================
[   44.805746] [ INFO: possible irq lock inversion dependency detected ]
[   44.805746] 3.14.0-rc2-test+ #14 Not tainted
[   44.805746] ---------------------------------------------------------
[   44.805746] bash/3674 just changed the state of lock:
[   44.805746]  (&dl_b->lock){+.....}, at: [<ffffffff8106ad15>] sched_rt_handler+0x132/0x248
[   44.805746] but this lock was taken by another, HARDIRQ-safe lock in the past:
[   44.805746]  (&rq->lock){-.-.-.}

and interrupts could create inverse lock ordering between them.

[   44.805746]
[   44.805746] other info that might help us debug this:
[   44.805746]  Possible interrupt unsafe locking scenario:
[   44.805746]
[   44.805746]        CPU0                    CPU1
[   44.805746]        ----                    ----
[   44.805746]   lock(&dl_b->lock);
[   44.805746]                                local_irq_disable();
[   44.805746]                                lock(&rq->lock);
[   44.805746]                                lock(&dl_b->lock);
[   44.805746]   <Interrupt>
[   44.805746]     lock(&rq->lock);

by making dl_b->lock acquiring always IRQ safe.

Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: NJuri Lelli <juri.lelli@gmail.com>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1392107067-19907-3-git-send-email-juri.lelli@gmail.comSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

Don't compare sysctl_sched_rt_runtime against sysctl_sched_rt_period if
the former is equal to RUNTIME_INF, otherwise disabling -rt bandwidth
management (with CONFIG_RT_GROUP_SCHED=n) fails.

Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: NJuri Lelli <juri.lelli@gmail.com>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1392107067-19907-2-git-send-email-juri.lelli@gmail.comSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

While debugging the crash with the bad nr_running accounting, I hit
another bug where, after running my sched deadline test, I was getting
failures to take a CPU offline. It was giving me a -EBUSY error.

Adding a bunch of trace_printk()s around, I found that the cpu
notifier that called sched_cpu_inactive() was returning a failure. The
overflow value was coming up negative?

Talking this over with Juri, the problem is that the total_bw update was
suppose to be made by dl_overflow() which, during my tests, seemed to
not be called. Adding more trace_printk()s, it wasn't that it wasn't
called, but it exited out right away with the check of new_bw being
equal to p->dl.dl_bw. The new_bw calculates the ratio between period and
runtime. The bug is that if you set a deadline, you do not need to set
a period if you plan on the period being equal to the deadline. That
is, if period is zero and deadline is not, then the system call should
set the period to be equal to the deadline. This is done elsewhere in
the code.

The fix is easy, check if period is set, and if it is not, then use the
deadline.

Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140219135335.7e74abd4@gandalf.local.homeSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

Rostedt writes:

My test suite was locking up hard when enabling mmiotracer. This was due
to the mmiotracer placing all but one CPU offline. I found this out
when I was able to reproduce the bug with just my stress-cpu-hotplug
test. This bug baffled me because it would not always trigger, and
would only trigger on the first run after boot up. The
stress-cpu-hotplug test would crash hard the first run, or never crash
at all. But a new reboot may cause it to crash on the first run again.

I spent all week bisecting this, as I couldn't find a consistent
reproducer. I finally narrowed it down to the sched deadline patches,
and even more peculiar, to the commit that added the sched
deadline boot up self test to the latency tracer. Then it dawned on me
to what the bug was.

All it took was to run a task under sched deadline to screw up the CPU
hot plugging. This explained why it would lock up only on the first run
of the stress-cpu-hotplug test. The bug happened when the boot up self
test of the schedule latency tracer would test a deadline task. The
deadline task would corrupt something that would cause CPU hotplug to
fail. If it didn't corrupt it, the stress test would always work
(there's no other sched deadline tasks that would run to cause
problems). If it did corrupt on boot up, the first test would lockup
hard.

I proved this theory by running my deadline test program on another box,
and then run the stress-cpu-hotplug test, and it would now consistently
lock up. I could run stress-cpu-hotplug over and over with no problem,
but once I ran the deadline test, the next run of the
stress-cpu-hotplug would lock hard.

After adding lots of tracing to the code, I found the cause. The
function tracer showed that migrate_tasks() was stuck in an infinite
loop, where rq->nr_running never equaled 1 to break out of it. When I
added a trace_printk() to see what that number was, it was 335 and
never decrementing!

Looking at the deadline code I found:

static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) {
	dequeue_dl_entity(&p->dl);
	dequeue_pushable_dl_task(rq, p);
}

static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) {
	update_curr_dl(rq);
	__dequeue_task_dl(rq, p, flags);

	dec_nr_running(rq);
}

And this:

	if (dl_runtime_exceeded(rq, dl_se)) {
		__dequeue_task_dl(rq, curr, 0);
		if (likely(start_dl_timer(dl_se, curr->dl.dl_boosted)))
			dl_se->dl_throttled = 1;
		else
			enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);

		if (!is_leftmost(curr, &rq->dl))
			resched_task(curr);
	}

Notice how we call __dequeue_task_dl() and in the else case we
call enqueue_task_dl()? Also notice that dequeue_task_dl() has
underscores where enqueue_task_dl() does not. The enqueue_task_dl()
calls inc_nr_running(rq), but __dequeue_task_dl() does not. This is
where we get nr_running out of sync.

[snip]

Another point where nr_running can get out of sync is when the dl_timer
fires:

	dl_se->dl_throttled = 0;
	if (p->on_rq) {
		enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
		if (task_has_dl_policy(rq->curr))
			check_preempt_curr_dl(rq, p, 0);
		else
			resched_task(rq->curr);

This patch does two things:

 - correctly accounts for throttled tasks (that are now considered
   !running);

 - fixes the bug, updating nr_running from {inc,dec}_dl_tasks(),
   since we risk to update it twice in some situations (e.g., a
   task is dequeued while it has exceeded its budget).

Cc: mingo@redhat.com
Cc: torvalds@linux-foundation.org
Cc: akpm@linux-foundation.org
Reported-by: NSteven Rostedt <rostedt@goodmis.org>
Reviewed-by: NSteven Rostedt <rostedt@goodmis.org>
Tested-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NJuri Lelli <juri.lelli@gmail.com>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1392884379-13744-1-git-send-email-juri.lelli@gmail.comSigned-off-by: NThomas Gleixner <tglx@linutronix.de>