When @gfp is specified, the percpu allocator is interested in whether
it contains all of GFP_KERNEL or not.  If it does, the normal
allocation path is taken; otherwise, the atomic allocation path.
Unfortunately, pcpu_alloc() was incorrectly testing for whether @gfp
contains any part of GFP_KERNEL.

Fix it by testing "(gfp & GFP_KERNEL) != GFP_KERNEL" instead of
"!(gfp & GFP_KERNEL)" to decide whether the allocation should be
atomic or not.
Signed-off-by: Tejun Heo <tj@kernel.org>

blk-mq uses percpu_ref for its usage counter which tracks the number
of in-flight commands and used to synchronously drain the queue on
freeze.  percpu_ref shutdown takes measureable wallclock time as it
involves a sched RCU grace period.  This means that draining a blk-mq
takes measureable wallclock time.  One would think that this shouldn't
matter as queue shutdown should be a rare event which takes place
asynchronously w.r.t. userland.

Unfortunately, SCSI probing involves synchronously setting up and then
tearing down a lot of request_queues back-to-back for non-existent
LUNs.  This means that SCSI probing may take above ten seconds when
scsi-mq is used.

  [    0.949892] scsi host0: Virtio SCSI HBA
  [    1.007864] scsi 0:0:0:0: Direct-Access     QEMU     QEMU HARDDISK    1.1. PQ: 0 ANSI: 5
  [    1.021299] scsi 0:0:1:0: Direct-Access     QEMU     QEMU HARDDISK    1.1. PQ: 0 ANSI: 5
  [    1.520356] tsc: Refined TSC clocksource calibration: 2491.910 MHz

  <stall>

  [   16.186549] sd 0:0:0:0: Attached scsi generic sg0 type 0
  [   16.190478] sd 0:0:1:0: Attached scsi generic sg1 type 0
  [   16.194099] osd: LOADED open-osd 0.2.1
  [   16.203202] sd 0:0:0:0: [sda] 31457280 512-byte logical blocks: (16.1 GB/15.0 GiB)
  [   16.208478] sd 0:0:0:0: [sda] Write Protect is off
  [   16.211439] sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
  [   16.218771] sd 0:0:1:0: [sdb] 31457280 512-byte logical blocks: (16.1 GB/15.0 GiB)
  [   16.223264] sd 0:0:1:0: [sdb] Write Protect is off
  [   16.225682] sd 0:0:1:0: [sdb] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA

This is also the reason why request_queues start in bypass mode which
is ended on blk_register_queue() as shutting down a fully functional
queue also involves a RCU grace period and the queues for non-existent
SCSI devices never reach registration.

blk-mq basically needs to do the same thing - start the mq in a
degraded mode which is faster to shut down and then make it fully
functional only after the queue reaches registration.  percpu_ref
recently grew facilities to force atomic operation until explicitly
switched to percpu mode, which can be used for this purpose.  This
patch makes blk-mq initialize q->mq_usage_counter in atomic mode and
switch it to percpu mode only once blk_register_queue() is reached.

Note that this issue was previously worked around by 0a30288d
("blk-mq, percpu_ref: implement a kludge for SCSI blk-mq stall during
probe") for v3.17.  The temp fix was reverted in preparation of adding
persistent atomic mode to percpu_ref by 9eca8046 ("Revert "blk-mq,
percpu_ref: implement a kludge for SCSI blk-mq stall during probe"").
This patch and the prerequisite percpu_ref changes will be merged
during v3.18 devel cycle.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Christoph Hellwig <hch@infradead.org>
Link: http://lkml.kernel.org/g/20140919113815.GA10791@lst.de
Fixes: add703fd ("blk-mq: use percpu_ref for mq usage count")
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Johannes Weiner <hannes@cmpxchg.org>

Currently, a percpu_ref which is initialized with
PERPCU_REF_INIT_ATOMIC or switched to atomic mode via
switch_to_atomic() automatically reverts to percpu mode on the first
percpu_ref_reinit().  This makes the atomic mode difficult to use for
cases where a percpu_ref is used as a persistent on/off switch which
may be cycled multiple times.

This patch makes such atomic state sticky so that it survives through
kill/reinit cycles.  After this patch, atomic state is cleared only by
an explicit percpu_ref_switch_to_percpu() call.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>

With the recent addition of percpu_ref_reinit(), percpu_ref now can be
used as a persistent switch which can be turned on and off repeatedly
where turning off maps to killing the ref and waiting for it to drain;
however, there currently isn't a way to initialize a percpu_ref in its
off (killed and drained) state, which can be inconvenient for certain
persistent switch use cases.

Similarly, percpu_ref_switch_to_atomic/percpu() allow dynamic
selection of operation mode; however, currently a newly initialized
percpu_ref is always in percpu mode making it impossible to avoid the
latency overhead of switching to atomic mode.

This patch adds @flags to percpu_ref_init() and implements the
following flags.

* PERCPU_REF_INIT_ATOMIC	: start ref in atomic mode
* PERCPU_REF_INIT_DEAD		: start ref killed and drained

These flags should be able to serve the above two use cases.

v2: target_core_tpg.c conversion was missing.  Fixed.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>

percpu_ref has treated the dropping of the base reference and
switching to atomic mode as an integral operation; however, there's
nothing inherent tying the two together.

The use cases for percpu_ref have been expanding continuously.  While
the current init/kill/reinit/exit model can cover a lot, the coupling
of kill/reinit with atomic/percpu mode switching is turning out to be
too restrictive for use cases where many percpu_refs are created and
destroyed back-to-back with only some of them reaching extended
operation.  The coupling also makes implementing always-atomic debug
mode difficult.

This patch separates out percpu mode switching into
percpu_ref_switch_to_percpu() and reimplements percpu_ref_reinit() on
top of it.

* DEAD still requires ATOMIC.  A dead ref can't be switched to percpu
  mode w/o going through reinit.

v2: __percpu_ref_switch_to_percpu() was missing static.  Fixed.
    Reported by Fengguang aka kbuild test robot.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: kbuild test robot <fengguang.wu@intel.com>

percpu_ref has treated the dropping of the base reference and
switching to atomic mode as an integral operation; however, there's
nothing inherent tying the two together.

The use cases for percpu_ref have been expanding continuously.  While
the current init/kill/reinit/exit model can cover a lot, the coupling
of kill/reinit with atomic/percpu mode switching is turning out to be
too restrictive for use cases where many percpu_refs are created and
destroyed back-to-back with only some of them reaching extended
operation.  The coupling also makes implementing always-atomic debug
mode difficult.

This patch separates out atomic mode switching into
percpu_ref_switch_to_atomic() and reimplements
percpu_ref_kill_and_confirm() on top of it.

* The handling of __PERCPU_REF_ATOMIC and __PERCPU_REF_DEAD is now
  differentiated.  Among get/put operations, percpu_ref_tryget_live()
  is the only one which cares about DEAD.

* percpu_ref_switch_to_atomic() can be called multiple times on the
  same ref.  This means that multiple @confirm_switch may get queued
  up which we can't do reliably without extra memory area.  This is
  handled by making the later invocation synchronously wait for the
  completion of the previous one.  This isn't particularly desirable
  but such synchronous waits shouldn't happen in most cases.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>

percpu_ref will be restructured so that percpu/atomic mode switching
and reference killing are dedoupled.  In preparation, add
PCPU_REF_DEAD and PCPU_REF_ATOMIC_DEAD which is OR of ATOMIC and DEAD.
For now, ATOMIC and DEAD are changed together and all PCPU_REF_ATOMIC
uses are converted to PCPU_REF_ATOMIC_DEAD without causing any
behavior changes.

percpu_ref_init() now specifies an explicit alignment when allocating
the percpu counters so that the pointer has enough unused low bits to
accomodate the flags.  Note that one flag was fine as min alignment
for percpu memory is 2 bytes but two flags are already too many for
the natural alignment of unsigned longs on archs like cris and m68k.

v2: The original patch had BUILD_BUG_ON() which triggers if unsigned
    long's alignment isn't enough to accomodate the flags, which
    triggered on cris and m64k.  percpu_ref_init() updated to specify
    the required alignment explicitly.  Reported by Fengguang.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
Cc: kbuild test robot <fengguang.wu@intel.com>

percpu_ref will be restructured so that percpu/atomic mode switching
and reference killing are dedoupled.  In preparation, do the following
renames.

* percpu_ref->confirm_kill	-> percpu_ref->confirm_switch
* __PERCPU_REF_DEAD		-> __PERCPU_REF_ATOMIC
* __percpu_ref_alive()		-> __ref_is_percpu()

This patch is pure rename and doesn't introduce any functional
changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>

percpu_ref uses pcpu_ prefix for internal stuff and percpu_ for
externally visible ones.  This is the same convention used in the
percpu allocator implementation.  It works fine there but percpu_ref
doesn't have too much internal-only stuff and scattered usages of
pcpu_ prefix are confusing than helpful.

This patch replaces all pcpu_ prefixes with percpu_.  This is pure
rename and there's no functional change.  Note that PCPU_REF_DEAD is
renamed to __PERCPU_REF_DEAD to signify that the flag is internal.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>

* Some comments became stale.  Updated.
* percpu_ref_tryget() unnecessarily initializes @ret.  Removed.
* A blank line removed from percpu_ref_kill_rcu().
* Explicit function name in a WARN format string replaced with __func__.
* WARN_ON() in percpu_ref_reinit() converted to WARN_ON_ONCE().
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>

percpu_ref is gonna go through restructuring.  Move
percpu_ref_reinit() after percpu_ref_kill_and_confirm().  This will
make later changes easier to follow and result in cleaner
organization.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>

This reverts commit 0a30288d, which
was a temporary fix for SCSI blk-mq stall issue.  The following
patches will fix the issue properly by introducing atomic mode to
percpu_ref.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@lst.de>

Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block into for-3.18

This is to receive 0a30288d ("blk-mq, percpu_ref: implement a
kludge for SCSI blk-mq stall during probe") which implements
__percpu_ref_kill_expedited() to work around SCSI blk-mq stall.  The
commit reverted and patches to implement proper fix will be added.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@lst.de>

blk-mq uses percpu_ref for its usage counter which tracks the number
of in-flight commands and used to synchronously drain the queue on
freeze.  percpu_ref shutdown takes measureable wallclock time as it
involves a sched RCU grace period.  This means that draining a blk-mq
takes measureable wallclock time.  One would think that this shouldn't
matter as queue shutdown should be a rare event which takes place
asynchronously w.r.t. userland.

Unfortunately, SCSI probing involves synchronously setting up and then
tearing down a lot of request_queues back-to-back for non-existent
LUNs.  This means that SCSI probing may take more than ten seconds
when scsi-mq is used.

This will be properly fixed by implementing a mechanism to keep
q->mq_usage_counter in atomic mode till genhd registration; however,
that involves rather big updates to percpu_ref which is difficult to
apply late in the devel cycle (v3.17-rc6 at the moment).  As a
stop-gap measure till the proper fix can be implemented in the next
cycle, this patch introduces __percpu_ref_kill_expedited() and makes
blk_mq_freeze_queue() use it.  This is heavy-handed but should work
for testing the experimental SCSI blk-mq implementation.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Christoph Hellwig <hch@infradead.org>
Link: http://lkml.kernel.org/g/20140919113815.GA10791@lst.de
Fixes: add703fd ("blk-mq: use percpu_ref for mq usage count")
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Tested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

Pull infiniband/rdma fixes from Roland Dreier:
 "Last late set of InfiniBand/RDMA fixes for 3.17:

   - fixes for the new memory region re-registration support
   - iSER initiator error path fixes
   - grab bag of small fixes for the qib and ocrdma hardware drivers
   - larger set of fixes for mlx4, especially in RoCE mode"

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (26 commits)
  IB/mlx4: Fix VF mac handling in RoCE
  IB/mlx4: Do not allow APM under RoCE
  IB/mlx4: Don't update QP1 in native mode
  IB/mlx4: Avoid accessing netdevice when building RoCE qp1 header
  mlx4: Fix mlx4 reg/unreg mac to work properly with 0-mac addresses
  IB/core: When marshaling uverbs path, clear unused fields
  IB/mlx4: Avoid executing gid task when device is being removed
  IB/mlx4: Fix lockdep splat for the iboe lock
  IB/mlx4: Get upper dev addresses as RoCE GIDs when port comes up
  IB/mlx4: Reorder steps in RoCE GID table initialization
  IB/mlx4: Don't duplicate the default RoCE GID
  IB/mlx4: Avoid null pointer dereference in mlx4_ib_scan_netdevs()
  IB/iser: Bump version to 1.4.1
  IB/iser: Allow bind only when connection state is UP
  IB/iser: Fix RX/TX CQ resource leak on error flow
  RDMA/ocrdma: Use right macro in query AH
  RDMA/ocrdma: Resolve L2 address when creating user AH
  mlx4: Correct error flows in rereg_mr
  IB/qib: Correct reference counting in debugfs qp_stats
  IPoIB: Remove unnecessary port query
  ...

Pull sound fixes from Takashi Iwai:
 "One fix is about a buggy computation in PCM API function Clemens
  spotted out, but the impact must be really small as no one really uses
  it in user-space side.

  The rest are a trivial fix for a HD-audio model and a USB-audio
  device-specific regression fix, so all look fairly safe to apply"

* tag 'sound-3.17-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound:
  ALSA: snd-usb-caiaq: Fix LED commands for Kore controller
  ALSA: pcm: fix fifo_size frame calculation
  ALSA: hda - Add fixup model name lookup for Lemote A1205

Pull final block fixes from Jens Axboe:
 "This week and last we've been fixing some corner cases related to
  blk-mq, mostly.  I ended up pulling most of that out of for-linus
  yesterday, which is why the branch looks fresh.  The rest were
  postponed for 3.18.

  This pull request contains:

   - Fix from Christoph, avoiding a stack overflow when FUA insertion
     would recursive infinitely.

   - Fix from David Hildenbrand on races between the timeout handler and
     uninitialized requests.  Fixes a real issue that virtio_blk has run
     into.

   - A few fixes from me:

        - Ensure that request deadline/timeout is ordered before the
          request is marked as started.

        - A potential oops on out-of-memory, when we scale the queue
          depth of the device and retry.

        - A hang fix on requeue from SCSI, where the hardware queue
          would be stopped when we attempt to re-run it (and hence
          nothing would happen, stalling progress).

        - A fix for commit 2da78092, where the cleanup path was moved
          to RCU, but a debug might_sleep() was inadvertently left in
          the code.  This causes warnings for people"

* 'for-linus' of git://git.kernel.dk/linux-block:
  genhd: fix leftover might_sleep() in blk_free_devt()
  blk-mq: use blk_mq_start_hw_queues() when running requeue work
  blk-mq: fix potential oops on out-of-memory in __blk_mq_alloc_rq_maps()
  blk-mq: avoid infinite recursion with the FUA flag
  blk-mq: Avoid race condition with uninitialized requests
  blk-mq: request deadline must be visible before marking rq as started

Pull parisc fixes from Helge Deller:
 "We avoid using -mfast-indirect-calls for 64bit kernel builds to
  prevent building an unbootable kernel due to latest gcc changes.

  In the pdc_stable/firmware-access driver we fix a few possible stack
  overflows and we now call secure_computing_strict() instead of
  secure_computing() which fixes upcoming SECCOMP patches in the
  for-next trees"

* 'parisc-3.17-7' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux:
  parisc: Only use -mfast-indirect-calls option for 32-bit kernel builds
  parisc: pdc_stable.c: Avoid potential stack overflows
  parisc: pdc_stable.c: Cleaning up unnecessary use of memset in conjunction with strncpy
  parisc: ptrace: use secure_computing_strict()

In spite of what the GCC manual says, the -mfast-indirect-calls has
never been supported in the 64-bit parisc compiler. Indirect calls have
always been done using function descriptors irrespective of the
-mfast-indirect-calls option.

Recently, it was noticed that a function descriptor was always requested
when the -mfast-indirect-calls option was specified. This caused
problems when the option was used in  application code and doesn't make
any sense because the whole point of the option is to avoid using a
function descriptor for indirect calls.

Fixing this broke 64-bit kernel builds.

I will fix GCC but for now we need the attached change. This results in
the same kernel code as before.
Signed-off-by: John David Anglin <dave.anglin@bell.net>
Cc: stable@vger.kernel.org  # v3.0+
Signed-off-by: Helge Deller <deller@gmx.de>

Pull ia64 defconfig update from Tony Luck:
 "Need to rebuild defconfig files to cope with removal of "select NET"
  in drivers/scsi/Kconfig"

* tag 'please-pull-defconfig' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux:
  [IA64] refresh arch/ia64/configs/* using "make savedefconfig"

Pull hwmon fixes from Guenter Roeck:
 - Fix a resource leak in tmp103 driver
 - Add support for two more processors to fam15h_power driver
 - Also fix a bug in the same driver to only report the power level on
   chips which actually support reporting it

* tag 'hwmon-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging:
  hwmon: (tmp103) Fix resource leak bug in tmp103 temperature sensor driver
  hwmon: (fam15h_power) Add support for two more processors
  hwmon: (fam15h_power) Make actual power reporting conditional

Prompted by a change to drivers/scsi/Kconfig which used to do a
"select NET" but now does a "depends on NET". This meant that some
configurations ended up without CONFIG_NET=y

Signed-off-by Tony Luck <tony.luck@intel.com>

Pull another kvm fix from Paolo Bonzini:
 "Another fix for 3.17 arrived at just the wrong time, after I had sent
  yesterday's pull request.  Normally I would have waited for some other
  patches to pile up, but since 3.17 might be short here it is"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  arm/arm64: KVM: Fix unaligned access bug on gicv2 access

Pull cgroup fix from Tejun Heo:
 "One late fix for cgroup.

  I was waiting for another set of fixes for a long-standing obscure
   cpuset bug but am not sure whether they'll be ready before v3.17
  release.  This one is a simple fix for a mutex unlock balance bug in
  an allocation failure path in pidlist_array_load().

  The bug was introduced in v3.14 and the fix is tagged for -stable"

* 'for-3.17-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: fix unbalanced locking

Merge tag 'kvm-arm-for-v3.17-rc7-or-final' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into kvm-master

Fixes unaligned access to the gicv2 virtual cpu status.

This reverts commit 9cb0e394.

It causes my Sony Vaio Pro 11 to immediately reboot at startup.
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Peter Anvin <hpa@zytor.com>
Cc: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Matt Fleming <matt.fleming@intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Pull networking fixes from David Miller:

 1) If the user gives us a msg_namelen of 0, don't try to interpret
    anything pointed to by msg_name.  From Ani Sinha.

 2) Fix some bnx2i/bnx2fc randconfig compilation errors.

    The gist of the issue is that we firstly have drivers that span both
    SCSI and networking.  And at the top of that chain of dependencies
    we have things like SCSI_FC_ATTRS and SCSI_NETLINK which are
    selected.

    But since select is a sledgehammer and ignores dependencies,
    everything to select's SCSI_FC_ATTRS and/or SCSI_NETLINK has to also
    explicitly select their dependencies and so on and so forth.

    Generally speaking 'select' is supposed to only be used for child
    nodes, those which have no dependencies of their own.  And this
    whole chain of dependencies in the scsi layer violates that rather
    strongly.

    So just make SCSI_NETLINK depend upon it's dependencies, and so on
    and so forth for the things selecting it (either directly or
    indirectly).

    From Anish Bhatt and Randy Dunlap.

 3) Fix generation of blackhole routes in IPSEC, from Steffen Klassert.

 4) Actually notice netdev feature changes in rtl_open() code, from
    Hayes Wang.

 5) Fix divide by zero in bond enslaving, from Nikolay Aleksandrov.

 6) Missing memory barrier in sunvnet driver, from David Stevens.

 7) Don't leave anycast addresses around when ipv6 interface is
    destroyed, from Sabrina Dubroca.

 8) Don't call efx_{arch}_filter_sync_rx_mode before addr_list_lock is
    initialized in SFC driver, from Edward Cree.

 9) Fix missing DMA error checking in 3c59x, from Neal Horman.

10) Openvswitch doesn't emit OVS_FLOW_CMD_NEW notifications accidently,
    fix from Samuel Gauthier.

11) pch_gbe needs to select NET_PTP_CLASSIFY otherwise we can get a
    build error.

12) Fix macvlan regression wherein we stopped emitting
    broadcast/multicast frames over software devices.  From Nicolas
    Dichtel.

13) Fix infiniband bug due to unintended overflow of skb->cb[], from
    Eric Dumazet.  And add an assertion so this doesn't happen again.

14) dm9000_parse_dt() should return error pointers, not NULL.  From
    Tobias Klauser.

15) IP tunneling code uses this_cpu_ptr() in preemptible contexts, fix
    from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (87 commits)
  net: bcmgenet: call bcmgenet_dma_teardown in bcmgenet_fini_dma
  net: bcmgenet: fix TX reclaim accounting for fragments
  ipv4: do not use this_cpu_ptr() in preemptible context
  dm9000: Return an ERR_PTR() in all error conditions of dm9000_parse_dt()
  r8169: fix an if condition
  r8152: disable ALDPS
  ipoib: validate struct ipoib_cb size
  net: sched: shrink struct qdisc_skb_cb to 28 bytes
  tg3: Work around HW/FW limitations with vlan encapsulated frames
  macvlan: allow to enqueue broadcast pkt on virtual device
  pch_gbe: 'select' NET_PTP_CLASSIFY.
  scsi: Use 'depends' with LIBFC instead of 'select'.
  openvswitch: restore OVS_FLOW_CMD_NEW notifications
  genetlink: add function genl_has_listeners()
  lib: rhashtable: remove second linux/log2.h inclusion
  net: allow macvlans to move to net namespace
  3c59x: Fix bad offset spec in skb_frag_dma_map
  3c59x: Add dma error checking and recovery
  sparc: bpf_jit: fix support for ldx/stx mem and SKF_AD_VLAN_TAG
  can: at91_can: add missing prepare and unprepare of the clock
  ...

Pull clock layer fixes from Mike Turquette:
 "The fixes for the clock tree are mostly run-time bugs in clock
  drivers.

  The fixes for TI DRA7 remove divide-by-zero errors.  The recently
  merged AT91 clock driver fixes some bad error checking and the QCOM
  driver fix restores audio for that platform, a clear regression.  A
  list iteration bug in the framework core was hit recently and is fixed
  up here.  Finally a compilation warning is fixed for efm32gg, which is
  also a regression fix"

* tag 'clk-fixes-for-linus' of git://git.linaro.org/people/mike.turquette/linux:
  clk/efm32gg: fix dt init prototype
  clk: prevent erronous parsing of children during rate change
  clk: rockchip: Fix the clocks for i2c1 and i2c2
  clk: qcom: Fix sdc 144kHz frequency entry
  clk: at91: fix num_parents test in at91sam9260 slow clk implementation
  clk: ti: dra7-atl: Provide error check for incoming parameters in set_rate
  clk: ti: divider: Provide error check for incoming parameters in set_rate

Merge tag 'fscache-fixes-20140917' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs

Pull fs-cache fixes from David Howells:

 - Put a timeout in releasepage() to deal with a recursive hang between
   the memory allocator, writeback, ext4 and fscache under memory
   pressure.

 - Fix a pair of refcount bugs in the fscache error handling.

 - Remove a couple of unused pagevecs.

 - The cachefiles requirement that the base directory support rename
   should permit rename2 as an alternative - otherwise certain
   filesystems cannot now be used as backing stores (such as ext4).

* tag 'fscache-fixes-20140917' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs:
  CacheFiles: Handle rename2
  cachefiles: remove two unused pagevecs.
  FS-Cache: refcount becomes corrupt under vma pressure.
  FS-Cache: Reduce cookie ref count if submit fails.
  FS-Cache: Timeout for releasepage()

Florian Fainelli says:

====================
net: bcmgenet: TX reclaim and DMA fixes

This patch set contains one fix for an accounting problem while reclaiming
transmitted buffers having fragments, and the second fix is to make sure
that the DMA shutdown is properly controlled.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

We should not be manipulaging the DMA_CTRL registers directly by writing
0 to them to disable DMA. This is an operation that needs to be timed to
make sure the DMA engines have been properly stopped since their state
machine stops on a packet boundary, not immediately.

Make sure that tha bcmgenet_fini_dma() calls bcmgenet_dma_teardown() to
ensure a proper DMA engine state. As a result, we need to reorder the
function bodies to resolve the use dependency.

Fixes: 1c1008c7 ("net: bcmgenet: add main driver file")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The GENET driver supports SKB fragments, and succeeds in transmitting
them properly, but when reclaiming these transmitted fragments, we will
only update the count of free buffer descriptors by 1, even for SKBs
with fragments. This leads to the networking stack thinking it has more
room than the hardware has when pushing new SKBs, and backing off
consequently because we return NETDEV_TX_BUSY.

Fix this by accounting for the SKB nr_frags plus one (itself) and update
ring->free_bds accordingly with that value for each iteration loop in
__bcmgenet_tx_reclaim().

Fixes: 1c1008c7 ("net: bcmgenet: add main driver file")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

this_cpu_ptr() in preemptible context is generally bad

Sep 22 05:05:55 br kernel: [   94.608310] BUG: using smp_processor_id()
in
preemptible [00000000] code: ip/2261
Sep 22 05:05:55 br kernel: [   94.608316] caller is
tunnel_dst_set.isra.28+0x20/0x60 [ip_tunnel]
Sep 22 05:05:55 br kernel: [   94.608319] CPU: 3 PID: 2261 Comm: ip Not
tainted
3.17.0-rc5 #82

We can simply use raw_cpu_ptr(), as preemption is safe in these
contexts.

Should fix https://bugzilla.kernel.org/show_bug.cgi?id=84991Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Joe <joe9mail@gmail.com>
Fixes: 9a4aa9af ("ipv4: Use percpu Cache route in IP tunnels")
Acked-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

We were using an atomic bitop on the vgic_v2.vgic_elrsr field which was
not aligned to the natural size on 64-bit platforms.  This bug showed up
after QEMU correctly identifies the pl011 line as being level-triggered,
and not edge-triggered.

These data structures are protected by a spinlock so simply use a
non-atomic version of the accessor instead.
Tested-by: Joel Schopp <joel.schopp@amd.com>
Reported-by: Riku Voipio <riku.voipio@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

Commit 2da78092 changed the locking from a mutex to a spinlock,
so we now longer sleep in this context. But there was a leftover
might_sleep() in there, which now triggers since we do the final
free from an RCU callback. Get rid of it.
Reported-by: Pontus Fuchs <pontus.fuchs@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

Steffen Klassert says:

====================
pull request (net): ipsec 2014-09-22

We generate a blackhole or queueing route if a packet
matches an IPsec policy but a state can't be resolved.
Here we assume that dst_output() is called to kill
these packets. Unfortunately this assumption is not
true in all cases, so it is possible that these packets
leave the system without the necessary transformations.

This pull request contains two patches to fix this issue:

1) Fix for blackhole routed packets.

2) Fix for queue routed packets.

Both patches are serious stable candidates.

Please pull or let me know if there are problems.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

In one error condition dm9000_parse_dt() returns NULL, however the
return value is checked using IS_ERR() in dm9000_probe(), leading to the
error not being properly propagated if CONFIG_OF is not enabled or the
device tree data is not available. Fix this by also returning an
ERR_PTR() in this case.

Fixes: 0b8bf1ba (net: dm9000: Allow instantiation using device tree)
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

There is an extra semi-colon so __rtl8169_set_features() is called every
time.

Fixes: 929a031d ('r8169: adjust __rtl8169_set_features')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Hayes Wang <hayeswang@realtek.com>--
Signed-off-by: David S. Miller <davem@davemloft.net>

Pull KVM fixes from Paolo Bonzini:
 "Two very simple bugfixes, affecting all supported architectures"

[ Two? There's three commits in here.  Oh well, I guess Paolo didn't
  count the preparatory symbol export ]

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: correct null pid check in kvm_vcpu_yield_to()
  KVM: check for !is_zero_pfn() in kvm_is_mmio_pfn()
  mm: export symbol dependencies of is_zero_pfn()

If the hw is in ALDPS mode, the hw may have no response for accessing
the most registers. Therefore, the ALDPS should be disabled before
accessing the hw in rtl_ops.init(), rtl_ops.disable(), rtl_ops.up(),
and rtl_ops.down(). Regardless of rtl_ops.enable(), because the hw
wouldn't enter ALDPS mode when linking on. The hw would enter the
ALDPS mode after several seconds when link down occurs and the ALDPS
is enabled.
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>