Fireworks has a quirk to transmit empty packets with TAG0. This commit
adds handling this quirk for full duplex stream synchronization.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Fireworks manages connections by CMP and can transmit/receive AMDTP streams
with a few quirks. This commit adds functionality to start/stop the streams.

Major Fireworks products don't support 'SYT-Match' clock source mode, except
for AudioFire12/8(till 2009 July) with firmware version 1.0. Already in
previous commit, this driver don't support such old firmwares. So this commit
adds support for non 'SYT-Match' clock source modes.

I note that this driver has a short gap for MIDI streams when starting PCM
stream. When AMDTP streams are running only for MIDI data and PCM data is
going to be joined at different sampling rate, then AMDTP streams are
stopped once and started again after changing sampling rate.

Unfortunately, Fireworks is not fully compliant to IEC 61883-1/6. Some commits
following to this commit add these quirks.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Fireworks uses own command and response. This commit adds functionality to
transact and adds some commands required for sound card instance and kernel
streaming.

There are two ways to deliver substance of this transaction:
1.AV/C vendor dependent command for command/response
2.Async transaction to specific addresses for command/response

By way 1, I confirm AudioFire12 cannot correctly response to some commands with
firmware version 5.0 or later. This is also confirmed by FFADO. So this driver
implement way 2.

The address for response gives an issue. When this driver allocate own callback
function into the address, then no one can allocate its own callback function.
This situation is not good for applications in user-land. This issue is solved
in later commit.

I note there is a command to change the address for response if the device
supports. But this driver uses default value. So users should not execute this
command as long as hoping this driver works correctly.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

This commit adds a new driver for devices based on Fireworks. This driver
just creates/removes card instance according to callbacks.

Fireworks is a board module which Echo Audio produced. This module
consists of three chipsets:
 - Communication chipset for IEEE1394 PHY/Link and IEC 61883-1/6
 - DSP or/and FPGA for signal processing
 - Flash Memory to store firmwares

Current supported devices:
 - Mackie Onyx 400F/1200F
 - Echo AudioFire12/8(until 2009 July)
 - Echo AudioFire2/4/Pre8/8(since 2009 July)
 - Echo Fireworks 8/HDMI
 - Gibson Robot Interface pack/GoldTop
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

This commit adds three commands, which may be used by some firewire device
drivers. These commands are defined in 'AV/C Digital Interface Command Set
General Specification Version 4.2 (2004006, 1394TA)'.

1. PLUG INFO command (clause 10.1)
2. INPUT PLUG SIGNAL FORMAT command (clause 10.10)
3. OUTPUT PLUG SIGNAL FORMAT command (clause 10.11)

By the command 1, the drivers can get the number of plugs for AV/C unit or
subunit.
By the command 2 and 3, the drivers can get/set sampling frequency.

The 'firewire-speakers' already uses INPUT PLUG SIGNAL FORMAT command to set
sampling rate. So this commit also affects the driver.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Some devices based on BeBoB use this type of AV/C transaction.

'Deferred Transaction' is defined in 'AV/C Digital Interface Command Set
General Specification' and is used by targets to make a response deferred
during processing it.

If a target may not be able to complete a command within 100msec since
receiving the command, then the target shall return INTERIM response,
to which final response will follow later. CONTROL/NOTIFY commands are
allowed for deferred transaction.

In the specification, devices allow to send INTERIM response just one time.
But this commit allows to handle several INTERIM response with two reasons.
One reason is to simplify codes, and another reason is to prepare for
devices which is out of specification.

There is an issue. In the specification, the interval between INTERIM
response and final response is 'Unspecified interval'. The specification
depends on each subunit specification for this interval.

But we promise to finish this function for caller. In this reason, I use
FCP_TIMEOUT_MS for this interval. Currently it's 125msec. When we find
devices which needs more time for this interval, then let us add some codes
to apply more interval for 'Unspecified interval'.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Plug Control Registers have two fields related to the number of established
connections, one is 'Broadcast connection counter' and another is
'Point-to-point connection counter'. The driver can know there are established
connections or not to check these fields.

This commit is for considering about JACK/FFADO streaming. Currently, when
JACK/FFADO starts its streaming to the device, cmp_connection_establish() is
failed expectedly. This seems to be enough but there are some devices which
needs to change sampling frequency before trying to establish connections.
For such devices, this functionality is needed.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

This patch adds some macros, codes with condition of direction and new functions
to handle output connection. Once cmp_connection_init() is executed with its
direction, CMP input and output connection can be handled by the same way.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

This patch adds 'direction' member to 'cmp_connection' structure to indicate
the direction of connection. This patch also adds 'direction' argument to
cmp_connection_init() function to determine the direction.

The cmp_connection_init() function is exported and used in snd-firewire-speakers
so this patch also affect it.

This patch just add them. Actual implementation will be done by followed
patches.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Referring to IEC 61883-1, oMPR and iMPR, oPCR and iPCR have some fields with
the same role in the same position. This patch renames some macros, variables
and function arguments with "i" in its prefix to reuse them between oMPR and
iMPR, oPCR and iPCR.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Currently, drivers can bring XRUN state for PCM substreams when error to
queue packets or detecting discontinuity of packet. The application may try to
recover this state by calling snd_pcm_prepare().

Depending on each driver, .prepare() includes restart streaming. Then there
is a state that PCM substreams are running but isochronous contexts are
stopped. In this case, when .pointer() is called, it refers to error pointer.

This commit is for a prevention of this bug.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

This commit adds common PCM constraints according to current firewire-lib
implementation.

1.Maximum width for each sample is limited by 24.
AM824 in IEC 61883-6 can deliver 24bit data.

2. Minimum time for period is 5msec.
Apply the old value. For shorter latency, further works are needed.

3. In blocking mode, frames per period/buffer is aligned to 32.
Each packet can include some frames depending on its sampling rate. In
blocking mode, the number equals to SYT_INTERVAL. Currently firewire-lib
can schedule snd_pcm_period_elapsed() for each packet. So, for accurate
PCM interrupt, the number of frames per period/buffer should be aligned
to SYT_INTERVAL.
Currently firewire-lib is lack of better rules to achieve this. So LCM of
each value of SYT_INTERVALs (=32) is applied. This can be improved for
further work.

[Fixed the compile error due to the missing "&" by tiwai]
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

In previous commit, AMDTP functionality in firewire-lib supports mapping
for PCM data channels. With this mapping, firewire-lib can obsolete
a flag, CIP_HI_DUALWIRE, but Dice driver still keeps dual wire mode.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Some devices arrange the position of PCM/MIDI data channel in AMDTP packet.
This commit allows drivers to set channel mapping.

To be simple, the mapping table is an array with fixed length. Then the number
of channels for PCM is restricted by 64 channels.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Generally, the devices can synchronize to handle 'presentation timestamp'
in CIP packets. This commit adds functionality to pick up this timestamp from
in-packets transmitted by the device, then use it for out packets.

In current implementation, this module generated the timestamp by itself. This
is 'SYT Match' mode. Then drivers with this module acts as synchronization
master. This commit allows this module to act as synchronization slave.

This commit restricts this mechanism is only available in blocking mode because
handling the timestamp in non-blocking mode is more complicated than in
blocking mode.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

For duplex streams with synchronization, drivers should pick up
'presentation timestamp' from in-packets and use the timestamp for
out-packets. This commit is preparation for this.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

For capturing/playbacking MIDI messages, this commit adds one MIDI conformant
data channel. This data channel has multiplexed 8 MIDI data streams. So this
data channel can transfer messages from/to 8 MIDI ports.

And this commit allows to set PCM format even if AMDTP streams already start.
I suppose the case that PCM substreams are going to be joined into AMDTP
streams when AMDTP streams are already started for MIDI substreams. Each
driver must count how many PCM/MIDI substreams use AMDTP streams to stop
AMDTP streams.

There are differences between specifications about MIDI conformant data.

About the multiplexing, IEC 61883-6:2002, itself, has no information. It
describes labels and bytes for MIDI messages and refers to MMA/AMEI RP-027
for 'successfull implementation'. MMA/AMEI RP-027 describes 8 MPX-MIDI data
streams for one MIDI conformant data channel. IEC 61883-6:2005 adds
'sequence multiplexing' and apply this way and describe incompatibility
between 2002 and 2005.

So this commit applies IEC 61883-6:2005. When we find some devices compliant
to IEC 61883-6:2002, then this difference should be handles as device quirk
in additional work.

About the number of bytes in an MIDI conformant data, IEC 61883-6:2002 describe
0,1,2,3 bytes. MMA/AMEI RP-027 describes 'MIDI1.0-1x-SPEED', 'MIDI1.0-2x-SPEED',
'MIDI1.0-3x-SPEED' modes and the maximum bytes for each mode corresponds to 1,
2, 3 bytes. The 'MIDI1.0-2x/3x-SPEED' modes are accompanied with 'negotiation
procedure' and 'encapsulation details' but there is no specifications for them.

So this commit implements 'MIDI1.0-1x-SPEED' mode for playback, but allows
to pick up 1-3 bytes for capturing.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

For capturing PCM, this commit adds the functionality to handle in-stream.
This is also applied for dual-wire mode.

Currently, capturing 32bit samples are supported.

When the sequence of in-packet has discontinuity of dbc, in-stream isn't handled
and amdtp_streaming_error() returns true.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Some codes can be reused to handle in-stream. This commit adds new functions.
This commit also renames some functions to keep naming consistency.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

This patch adds 'direction' member to amdtp_stream structure to indicate its
direction. This patch also adds 'direction' argument to amdtp_stream_init()
function to determine its direction.

The amdtp_stream_init() function is exported and used by firewire-speakers and
dice so this patch also affects them.

This patch just add them. Actual implementation will be done by followed
patches.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

This patch adds some macros instead of fixed value for AMDTP according to
IEC 61883-1/6. These macros will also be used by followed patches.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

This patch renames some functions, a structure and its member to reuse them
in both AMDTP in/out stream.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Pull two powerpc fixes from Ben Herrenschmidt:
 "Here are a couple of fixes for 3.15.  One from Anton fixes a nasty
  regression I introduced when trying to fix a loss of irq_work whose
  consequences is that we can completely lose timer interrupts on a
  CPU... not pretty.

  The other one is a change to our PCIe reset hook to use a firmware
  call instead of direct config space accesses to trigger a fundamental
  reset on the root port.  This is necessary so that the FW gets a
  chance to disable the link down error monitoring, which would
  otherwise trip and cause subsequent fatal EEH error"

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
  powerpc: irq work racing with timer interrupt can result in timer interrupt hang
  powerpc/powernv: Reset root port in firmware

Pull two btrfs fixes from Chris Mason:
 "This has two fixes that we've been testing for 3.16, but since both
  are safe and fix real bugs, it makes sense to send for 3.15 instead"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
  Btrfs: send, fix incorrect ref access when using extrefs
  Btrfs: fix EIO on reading file after ioctl clone works on it

Pull two ceph fixes from Sage Weil:
 "The first patch fixes a problem when we have a page count of 0 for
  sendpage which is triggered by zfs.  The second fixes a bug in CRUSH
  that was resolved in the userland code a while back but fell through
  the cracks on the kernel side"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client:
  crush: decode and initialize chooseleaf_vary_r
  libceph: fix corruption when using page_count 0 page in rbd

Pull xfs fixes from Dave Chinner:
 "Code inspection of the XFS error number sign translations found a
  bunch of issues, including returning incorrectly signed errors for
  some data integrity operations.

  These leak to userspace and result in applications not getting the
  errors correctly reported.  Hence they need fixing sooner rather than
  later.

  A couple of the bugs are in data integrity operations, a couple more
  are in the new COLLAPSE_RANGE code.  One of these came in through a
  recent ext4 merge and so I had to update the base tree to 3.15-rc5
  before fixing the issues"

* tag 'xfs-for-linus-3.15-rc6' of git://oss.sgi.com/xfs/xfs:
  xfs: list_lru_init returns a negative error
  xfs: negate xfs_icsb_init_counters error value
  xfs: negate mount workqueue init error value
  xfs: fix wrong err sign on xfs_set_acl()
  xfs: fix wrong errno from xfs_initxattrs
  xfs: correct error sign on COLLAPSE_RANGE errors
  xfs: xfs_commit_metadata returns wrong errno
  xfs: fix incorrect error sign in xfs_file_aio_read
  xfs: xfs_dir_fsync() returns positive errno

Pull renameat2 arch support from Miklos Szeredi:
 "I've collected architecture patches for the renameat2 syscall that
  maintainers acked and/or asked me to queue.

  This adds architecture support for the renameat2 syscall to m68k,
  parisc, ia64 and through asm-generic to arc, arm64, c6x, hexagon,
  metag, openrisc, score, tile, unicore32"

* 'renameat2' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs:
  scripts/checksyscalls.sh: Make renameat optional
  asm-generic: Add renameat2 syscall
  ia64: add renameat2 syscall
  parisc: add renameat2 syscall
  m68k: add renameat2 syscall

Pull iommu fixes from Joerg Roedel:
 "Three fixes for the AMD IOMMU driver:
   - fix a locking issue around get_user_pages()
   - fix two issues with device aliasing and exclusion range handling"

* tag 'iommu-fixes-v3.15-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  iommu/amd: fix enabling exclusion range for an exact device
  iommu/amd: Take mmap_sem when calling get_user_pages
  iommu/amd: Fix interrupt remapping for aliased devices

Merge tag 'stable/for-linus-3.15-rc5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/ibft

Pull iscsi_ibft fix from Konrad Rzeszutek Wilk:
 "Fix iBFT regression on Broadcom NICs introduced in 3.2"

* tag 'stable/for-linus-3.15-rc5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/ibft:
  iscsi_ibft: Fix finding Broadcom specific ibft sign

Merge tag 'renesas-sh-drivers-for-v3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas

Pull SH driver fix from Simon Horman:
 "Compile drivers/sh/pm_runtime.c if ARCH_SHMOBILE_MULTI

  This resolves a regression introduced in v3.14 by commit bf98c1ea
  ("ARM: Rename ARCH_SHMOBILE to ARCH_SHMOBILE_LEGACY")"

* tag 'renesas-sh-drivers-for-v3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas:
  drivers: sh: compile drivers/sh/pm_runtime.c if ARCH_SHMOBILE_MULTI

Pull media fixes from Mauro Carvalho Chehab:
 "Most of the changes are drivers fixes (rtl28xuu, fc2580, ov7670,
  davinci, gspca, s5p-fimc and s5c73m3).

  There is also a compat32 fix and one infoleak fixup at the media
  controller"

* 'v4l_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-media:
  [media] V4L2: fix VIDIOC_CREATE_BUFS in 64- / 32-bit compatibility mode
  [media] V4L2: ov7670: fix a wrong index, potentially Oopsing the kernel from user-space
  [media] media-device: fix infoleak in ioctl media_enum_entities()
  [media] fc2580: fix tuning failure on 32-bit arch
  [media] Prefer gspca_sonixb over sn9c102 for all devices
  [media] media: davinci: vpfe: make sure all the buffers unmapped and released
  [media] staging: media: davinci: vpfe: make sure all the buffers are released
  [media] media: davinci: vpbe_display: fix releasing of active buffers
  [media] media: davinci: vpif_display: fix releasing of active buffers
  [media] media: davinci: vpif_capture: fix releasing of active buffers
  [media] s5p-fimc: Fix YUV422P depth
  [media] s5c73m3: Add missing rename of v4l2_of_get_next_endpoint() function
  [media] rtl28xxu: silence error log about disabled rtl2832_sdr module
  [media] rtl28xxu: do not hard depend on staging SDR module

Pull staging driver fixes from Greg KH:
 "Here are five staging driver fixes for 3.15-rc6 that resolve some
  reported issues.  They are for the imx and rtl8723au drivers"

* tag 'staging-3.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging:
  staging: rtl8723au: Do not reset wdev->iftype in netdev_close()
  staging: rtl8723au: Use correct pipe type for USB interrupts
  imx-drm: imx-tve: correct DDC property name to 'ddc-i2c-bus'
  imx-drm: imx-drm-core: skip components whose parent device is disabled
  imx-drm: imx-drm-core: fix imx_drm_encoder_get_mux_id

Merge tag 'driver-core-3.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core

Pull driver core fixes from Greg KH:
 "Here are two driver core (well, sysfs) fixes for 3.15-rc6 that resolve
  some reported issues and a regression from 3.13"

* tag 'driver-core-3.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core:
  sysfs: make sure read buffer is zeroed
  kernfs, sysfs, cgroup: restrict extra perm check on open to sysfs

Pull PCI fixes from Bjorn Helgaas:
 "These are fixes for an SHPCHP hotplug regression, a "wait for pending
  transaction" problem (used in device reset paths), and an email
  address update.

  PCI device hotplug:
    - Fix SHPCHP bus speed mismatch issue (Marcel Apfelbaum)

  Miscellaneous:
    - Fix pci_wait_for_pending_transaction() (Gavin Shan)
    - Update email address (Ben Hutchings)"

* tag 'pci-v3.15-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci:
  PCI: Wrong register used to check pending traffic
  PCI: shpchp: Check bridge's secondary (not primary) bus speed
  PCI: Update my email address

Pull /dev/random fix from Ted Ts'o:
 "This fixes a BUG_ON-causing regression that was introduced during the
  last merge window"

* tag 'random_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/random:
  random: fix BUG_ON caused by accounting simplification

Pull clock framework fixes from Mike Turquette:
 "Clock framework and driver fixes, all of which fix user-visible
  regressions.

  As usual most fixes are for platform-specific clock drivers, but there
  are also two fixes to the clk core after recent changes to the way
  that clock unregistration is handled"

* tag 'clk-fixes-for-linus' of git://git.linaro.org/people/mike.turquette/linux:
  clk: tegra: Fix wrong value written to PLLE_AUX
  clk: shmobile: clk-mstp: change to using clock-indices
  clk: Fix slab corruption in clk_unregister()
  clk: Fix double free due to devm_clk_register()
  clk: socfpga: fix clock driver for 3.15
  clk: divider: Fix best div calculation for power-of-two and table dividers
  clk: bcm281xx: don't use unnamed structs or unions

Pull spi fixes from Mark Brown:
 "A few core fixes around outlying cases here, nothing that should
  affect most users but useful fixes.  The diffstat is rather larger
  than one might hope due some simple code motion in the fix for
  !CONFIG_DMA, the actual meaningful change is much smaller.

   - Fix handling of unsupported dual and quad mode support on slave
     registration so that drivers that can degrade gracefully do so,
     preventing regressions for drivers this is added.
   - Fix build in !CONFIG_DMA cases following addition of generic DMA
     mapping support.
   - Fix error handling for queue creation which due to wider kernel
     changes can be triggered more easily.
   - A couple of driver specific fixes"

* tag 'spi-v3.15-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi:
  spi/pxa2xx: Prevent DMA from transferring too many bytes
  spi: core: Don't destroy master queue if we fail to create it
  spi: qup: Fix return value checking for pm_runtime_get_sync()
  spi: core: Protect DMA code by #ifdef CONFIG_HAS_DMA
  spi: core: Ignore unsupported Dual/Quad Transfer Mode bits

Pull GPIO fixes from Linus Walleij:
 - fix a null pointer bug in the ICH6 chipset driver
 - fix device tree registration for the mcp23s08 driver

* tag 'gpio-v3.15-3' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio:
  gpio: mcp23s08: Bug fix of SPI device tree registration.
  gpio: ich: set regs and reglen for i3100 and ich6 chipset

Pull more cgroup fixes from Tejun Heo:
 "Three more patches to fix cgroup_freezer breakage due to the recent
  cgroup internal locking changes - an operation cgroup_freezer was
  using now requires sleepable context and cgroup_freezer was invoking
  that while holding a spin lock.  cgroup_freezer was using an overly
  elaborate hierarchical locking scheme.

  While it's possible to convert the hierarchical spinlocks directly to
  mutexes, this patch simplifies the overall locking so that it uses a
  global mutex.  This has the added benefit of avoiding iterating
  potentially huge number of tasks under a spinlock.  While the patch is
  on the larger side in the devel cycle, the changes made are mostly
  straight-forward and the locking logic is a lot simpler afterwards"

* 'for-3.15-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: fix rcu_read_lock() leak in update_if_frozen()
  cgroup_freezer: replace freezer->lock with freezer_mutex
  cgroup: introduce task_css_is_root()