This device-mapper target creates a read-only device that transparently
validates the data on one underlying device against a pre-generated tree
of cryptographic checksums stored on a second device.

Two checksum device formats are supported: version 0 which is already
shipping in Chromium OS and version 1 which incorporates some
improvements.
Signed-off-by: NMikulas Patocka <mpatocka@redhat.com>
Signed-off-by: NMandeep Singh Baines <msb@chromium.org>
Signed-off-by: NWill Drewry <wad@chromium.org>
Signed-off-by: NElly Jones <ellyjones@chromium.org>
Cc: Milan Broz <mbroz@redhat.com>
Cc: Olof Johansson <olofj@chromium.org>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

This patch introduces a new function dm_bufio_prefetch. It prefetches
the specified range of blocks into dm-bufio cache without waiting
for i/o completion.
Signed-off-by: NMikulas Patocka <mpatocka@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Add dm thin target arguments to control discard support.

ignore_discard: Disables discard support

no_discard_passdown: Don't pass discards down to the underlying data
device, but just remove the mapping within the thin provisioning target.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Support discards in the thin target.

On discard the corresponding mapping(s) are removed from the thin
device.  If the associated block(s) are no longer shared the discard
is passed to the underlying device.

All bios other than discards now have an associated deferred_entry
that is saved to the 'all_io_entry' in endio_hook.  When non-discard
IO completes and associated mappings are quiesced any discards that
were deferred, via ds_add_work() in process_discard(), will be queued
for processing by the worker thread.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

drivers/md/dm-thin.c |  173 ++++++++++++++++++++++++++++++++++++++++++++++----
 drivers/md/dm-thin.c |  172 ++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 158 insertions(+), 14 deletions(-)

This patch contains the ground work needed for dm-thin to support discard.

  - Adds endio function that replaces shared_read_endio.

  - Introduce an explicit 'quiesced' flag into the new_mapping structure.
    Before, this was implicitly indicated by m->list being empty.

  - The map_info->ptr remains constant for the duration of a bio's trip
    through the thin target.  Make it easier to reason about it.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Use dm_target_offset wrapper instead of referencing the awkward ti->begin
explicitly.
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Support the use of an external _read only_ device as an origin for a thin
device.

Any read to an unprovisioned area of the thin device will be passed
through to the origin.  Writes trigger allocation of new blocks as
usual.

One possible use case for this would be VM hosts that want to run
guests on thinly-provisioned volumes but have the base image on another
device (possibly shared between many VMs).
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

The thin metadata format can only make use of a device that is <=
THIN_METADATA_MAX_SECTORS (currently 15.9375 GB).  Therefore, there is no
practical benefit to using a larger device.

However, it may be that other factors impose a certain granularity for
the space that is allocated to a device (E.g. lvm2 can impose a coarse
granularity through the use of large, >= 1 GB, physical extents).

Rather than reject a larger metadata device, during thin-pool device
construction, switch to allowing it but issue a warning if a device
larger than THIN_METADATA_MAX_SECTORS_WARNING (16 GB) is
provided.  Any space over 15.9375 GB will not be used.
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Save space by removing entries from the space map ref_count tree if
they're no longer needed.

Ref counts are stored in two places: a bitmap if the ref_count is
below 3, or a btree of uint32_t if 3 or above.

When a ref_count that was above 3 drops below we can remove it from
the tree and save some metadata space.  This removal was commented out
before because I was unsure why this was causing under-populated btree
nodes.  Earlier patches have fixed this issue.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Commit unwritten data every second to prevent too much building up.

Released blocks don't become available until after the next commit
(for crash resilience).  Prior to this patch commits were only
triggered by a message to the target or a REQ_{FLUSH,FUA} bio.  This
allowed far too big a position to build up.

The interval is hard-coded to 1 second.  This is a sensible setting.
I'm not making this user configurable, since there isn't much to be
gained by tweaking this - and a lot lost by setting it far too high.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Device mapper uses sscanf to convert arguments to numbers. The problem is that
the way we use it ignores additional unmatched characters in the scanned string.

For example, this `if (sscanf(string, "%d", &number) == 1)' will match a number,
but also it will match number with some garbage appended, like "123abc".

As a result, device mapper accepts garbage after some numbers. For example
the command `dmsetup create vg1-new --table "0 16384 linear 254:1bla 34816bla"'
will pass without an error.

This patch fixes all sscanf uses in device mapper. It appends "%c" with
a pointer to a dummy character variable to every sscanf statement.

The construct `if (sscanf(string, "%d%c", &number, &dummy) == 1)' succeeds
only if string is a null-terminated number (optionally preceded by some
whitespace characters). If there is some character appended after the number,
sscanf matches "%c", writes the character to the dummy variable and returns 2.
We check the return value for 1 and consequently reject numbers with some
garbage appended.
Signed-off-by: NMikulas Patocka <mpatocka@redhat.com>
Acked-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

The dm-raid code currently fails to create a RAID array if any of the
superblocks cannot be read.  This was an oversight as there is already
code to handle this case if the values ('- -') were provided for the
failed array position.

With this patch, if a superblock cannot be read, the array position's
fields are initialized as though '- -' was set in the table.  That is,
the device is failed and the position should not be used, but if there
is sufficient redundancy, the array should still be activated.
Signed-off-by: NJonathan Brassow <jbrassow@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Fix a harmless typo.

The root is a chunk of data that gets written to the superblock.  This
data is used to recreate the space map when opening a metadata area.
We have two space maps; one tracking space on the metadata device and
one of the data device.  Both of these use the same format for their
root, so this typo was harmless.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Now that the value_size is held within every node of the btrees we can
remove this argument from value_ptr().

For the last few months a BUG_ON has been checking this argument is
the same as that held in the node.  No issues were reported.  So this
is a safe change.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

The map_context pointer should always be set. However, we have reports
that upon requeuing it is not set correctly.  So add set and clear
functions with a BUG_ON() to track the issue properly.
Signed-off-by: NJun'ichi Nomura <j-nomura@ce.jp.nec.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Acked-by: NHannes Reinecke <hare@suse.de>
Tested-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Acked-by: NDave Wysochanski <dwysocha@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

As a precaution, set bi_end_io to NULL when failing to remap.
Signed-off-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

free_devices in dm_table.c already uses list_for_each(), so we don't
need to check if the list is empty.
Signed-off-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Remove documentation for unimplemented 'trim' message.

I'd planned a 'trim' target message for shrinking thin devices, but
this is better handled via the discard ioctl.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

The dm raid module (using md) is becoming the preferred way of creating long-lived
mirrors through userspace LVM so remove the EXPERIMENTAL tag.
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Drop EXPERIMENTAL tag from dm-uevent.

It's not changed for a while and some userspace tools are relying upon it.
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Update device-mapper MAINTAINERS entry to mention quilt working tree location
and persistent-data subdirectory.
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Describe attributes provided by device-mapper in /sys/block.
Signed-off-by: NMilan Broz <mbroz@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

When we remove an entry from a node we sometimes rebalance with it's
two neighbours.  This wasn't being done correctly; in some cases
entries have to move all the way from the right neighbour to the left
neighbour, or vice versa.  This patch pretty much re-writes the
balancing code to fix it.

This code is barely used currently; only when you delete a thin
device, and then only if you have hundreds of them in the same pool.
Once we have discard support, which removes mappings, this will be used
much more heavily.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Cc: stable@kernel.org
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Avoid using the bi_next field for the holder of a cell when deferring
bios because a stacked device below might change it.  Store the
holder in a new field in struct cell instead.

When a cell is created, the bio that triggered creation (the holder) was
added to the same bio list as subsequent bios.  In some cases we pass
this holder bio directly to devices underneath.  If those devices use
the bi_next field there will be trouble...

This also simplifies some code that had to work out which bio was the
holder.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Cc: stable@kernel.org
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Always set io->error to -EIO when an error is detected in dm-crypt.

There were cases where an error code would be set only if we finish
processing the last sector. If there were other encryption operations in
flight, the error would be ignored and bio would be returned with
success as if no error happened.

This bug is present in kcryptd_crypt_write_convert, kcryptd_crypt_read_convert
and kcryptd_async_done.
Signed-off-by: NMikulas Patocka <mpatocka@redhat.com>
Cc: stable@kernel.org
Reviewed-by: NMilan Broz <mbroz@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

This patch fixes a possible deadlock in dm-crypt's mempool use.

Currently, dm-crypt reserves a mempool of MIN_BIO_PAGES reserved pages.
It allocates first MIN_BIO_PAGES with non-failing allocation (the allocation
cannot fail and waits until the mempool is refilled). Further pages are
allocated with different gfp flags that allow failing.

Because allocations may be done in parallel, this code can deadlock. Example:
There are two processes, each tries to allocate MIN_BIO_PAGES and the processes
run simultaneously.
It may end up in a situation where each process allocates (MIN_BIO_PAGES / 2)
pages. The mempool is exhausted. Each process waits for more pages to be freed
to the mempool, which never happens.

To avoid this deadlock scenario, this patch changes the code so that only
the first page is allocated with non-failing gfp mask. Allocation of further
pages may fail.
Signed-off-by: NMikulas Patocka <mpatocka@redhat.com>
Cc: stable@kernel.org
Signed-off-by: NMilan Broz <mbroz@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Call the correct exit function on failure in dm_exception_store_init.
Signed-off-by: NAndrei Warkentin <andrey.warkentin@gmail.com>
Acked-by: NMike Snitzer <snitzer@redhat.com>
Cc: stable@kernel.org
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Pull fbdev updates for 3.4 from Florian Tobias Schandinat:
 - drivers for Samsung Exynos MIPI DSI and display port
 - i740fb to support those old Intel chips
 - large updates to OMAP, viafb and sh_mobile_lcdcfb
 - some updates to s3c-fb and udlfb, few patches to others

Fix up conflicts in drivers/video/udlfb.c due to Key Sievers' fix making
it in twice.

* tag 'fbdev-updates-for-3.4' of git://github.com/schandinat/linux-2.6: (156 commits)
  Revert "video:uvesafb: Fix oops that uvesafb try to execute NX-protected page"
  OMAPDSS: register dss drivers in module init
  video: pxafb: add clk_prepare/clk_unprepare calls
  fbdev: bfin_adv7393fb: Drop needless include
  fbdev: sh_mipi_dsi: add extra phyctrl for sh_mipi_dsi_info
  fbdev: remove dependency of FB_SH_MOBILE_MERAM from FB_SH_MOBILE_LCDC
  Revert "MAINTAINERS: add entry for exynos mipi display drivers"
  fbdev: da8xx: add support for SP10Q010 display
  fbdev: da8xx:: fix reporting of the display timing info
  drivers/video/pvr2fb.c: ensure arguments to request_irq and free_irq are compatible
  OMAPDSS: APPLY: fix clearing shadow dirty flag with manual update
  fbdev: sh_mobile_meram: Implement system suspend/resume
  fbdev: sh_mobile_meram: Remove unneeded sanity checks
  fbdev: sh_mobile_meram: Don't perform update in register operation
  arm: mach-shmobile: Constify sh_mobile_meram_cfg structures
  fbdev: sh_mobile_lcdc: Don't store copy of platform data
  fbdev: sh_mobile_meram: Remove unused sh_mobile_meram_icb_cfg fields
  arm: mach-shmobile: Don't set MERAM ICB numbers in platform data
  fbdev: sh_mobile_meram: Allocate ICBs automatically
  fbdev: sh_mobile_meram: Use genalloc to manage MERAM allocation
  ...

Pull regmap updates from Mark Brown:
 "Things are really quieting down with the regmap API, while we're still
  seeing a trickle of new features coming in they're getting much
  smaller than they were.  It's also nice to have some features which
  support other subsystems building infrastructure on top of regmap.
  Highlights include:

  - Support for padding between the register and the value when
    interacting with the device, sometimes needed for fast interfaces.
  - Support for applying register updates to the device when restoring
    the register state.  This is intended to be used to apply updates
    supplied by manufacturers for tuning the performance of the device
    (many of which are to undocumented registers which aren't otherwise
    covered).
  - Support for multi-register operations on cached registers.
  - Support for syncing only part of the register cache.
  - Stubs and parameter query functions intended to make it easier for
    other subsystems to build infrastructure on top of the regmap API.

  plus a few driver updates making use of the new features which it was
  easier to merge via this tree."

* tag 'regmap-3.4' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regmap: (41 commits)
  regmap: Fix future missing prototype of devres_alloc() and friends
  regmap: Rejig struct declarations for stubbed API
  regmap: Fix rbtree block base in sync
  regcache: Make sure we sync register 0 in an rbtree cache
  regmap: delete unused module.h from drivers/base/regmap files
  regmap: Add stub for regcache_sync_region()
  mfd: Improve performance of later WM1811 revisions
  regmap: Fix x86_64 breakage
  regmap: Allow drivers to sync only part of the register cache
  regmap: Supply ranges to the sync operations
  regmap: Add tracepoints for cache only and cache bypass
  regmap: Mark the cache as clean after a successful sync
  regmap: Remove default cache sync implementation
  regmap: Skip hardware defaults for LZO caches
  regmap: Expose the driver name in debugfs
  mfd: wm8400: Convert to devm_regmap_init_i2c()
  mfd: wm831x: Convert to devm_regmap_init()
  mfd: wm8994: Convert to devm_regmap_init()
  mfd/ASoC: Convert WM8994 driver to use regmap patches
  mfd: Add __devinit and __devexit annotations in wm8994
  ...

Pull IEEE 1394 (FireWire) subsystem updates post v3.3 from Stefan Richter:

 - Some SBP-2 initiator fixes, side product from ongoing work on a target.

 - Reintroduction of an isochronous I/O feature of the older ieee1394 driver
   stack (flush buffer completions); it was evidently rarely used but not
   actually unused.  Matching libraw1394 code is already available.

 - Be sure to prefix all kernel log messages with device name or card name,
   and other logging related cleanups.

 - Misc other small cleanups, among them a small API change that affects
   sound/firewire/ too. Clemens Ladisch is aware of it.

* tag 'firewire-updates' of git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394/linux1394: (26 commits)
  firewire: allow explicit flushing of iso packet completions
  firewire: prevent dropping of completed iso packet header data
  firewire: ohci: factor out iso completion flushing code
  firewire: ohci: simplify iso header pointer arithmetic
  firewire: ohci: optimize control bit checks
  firewire: ohci: remove unused excess_bytes field
  firewire: ohci: copy_iso_headers(): make comment match the code
  firewire: cdev: fix IR multichannel event documentation
  firewire: ohci: fix too-early completion of IR multichannel buffers
  firewire: ohci: move runtime debug facility out of #ifdef
  firewire: tone down some diagnostic log messages
  firewire: sbp2: replace a GFP_ATOMIC allocation
  firewire: sbp2: Fix SCSI sense data mangling
  firewire: sbp2: Ignore SBP-2 targets on the local node
  firewire: sbp2: Take into account Unit_Unique_ID
  firewire: nosy: Use the macro DMA_BIT_MASK().
  firewire: core: convert AR-req handler lock from _irqsave to _bh
  firewire: core: fix race at address_handler unregistration
  firewire: core: remove obsolete comment
  firewire: core: prefix log messages with card name
  ...

Pull pinctrl updates for v3.4 from Linus Walleij (*):
 - Switches the PXA 168, 910 and MMP over to use pinctrl
 - Locking revamped
 - Massive refactorings...
 - Reform the driver API to use multiple states
 - Support pin config in the mapping tables
 - Pinctrl drivers for the nVidia Tegra series
 - Generic pin config support lib for simple pin controllers
 - Implement pin config for the U300

* tag 'pinctrl-for-3.4' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl: (48 commits)
  ARM: u300: configure some pins as an example
  pinctrl: support pinconfig on the U300
  pinctrl/coh901: use generic pinconf enums and parameters
  pinctrl: introduce generic pin config
  pinctrl: fix error path in pinconf_map_to_setting()
  pinctrl: allow concurrent gpio and mux function ownership of pins
  pinctrl: forward-declare struct device
  pinctrl: split pincontrol states into its own header
  pinctrl: include machine header to core.h
  ARM: tegra: Select PINCTRL Kconfig variables
  pinctrl: add a driver for NVIDIA Tegra
  pinctrl: Show selected function and group in pinmux-pins debugfs
  pinctrl: enhance mapping table to support pin config operations
  pinctrl: API changes to support multiple states per device
  pinctrl: add usecount to pins for muxing
  pinctrl: refactor struct pinctrl handling in core.c vs pinmux.c
  pinctrl: fix and simplify locking
  pinctrl: fix the pin descriptor kerneldoc
  pinctrl: assume map table entries can't have a NULL name field
  pinctrl: introduce PINCTRL_STATE_DEFAULT, define hogs as that state
  ...

(*) What is it with all these Linuses these days? There's a Linus at
    google too.  Some day I will get myself my own broadsword, and run
    around screaming "There can be only one".

    I used to be _special_ dammit. Snif.

Pull libata updates from Jeff Garzik:

 1) AHCI regression fix.  A recent "make driver conform to spec" change
    broke on deployed hardware.  Make new behavior optional, rather than
    default, turning it on only for specific embedded platforms that
    need this.

    Everybody else runs in the famous "non conformant but working" mode.

 2) pata_cmd64x, pata_legacy cleanups

 3) new Intel SATA PCI IDs

 4) misc minor vendor feature additions

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jgarzik/libata-dev:
  pata_cmd64x: implement sff_irq_check() method
  pata_cmd64x: implement sff_irq_clear() method
  pata_cmd64x: use interrupt status from MRDMODE register
  pata_cmd64x: turn string of *if* statements into *switch*
  drivers/ata/pata_mpc52xx.c: clean up error handling code
  ahci_platform: add STRICT_AHCI platform type
  ahci: move AHCI_HFLAGS() macro to ahci.h
  ahci: add AHCI_HFLAG_DELAY_ENGINE host flag
  sata_fsl: add support for interrupt coalsecing feature
  ata/pata_arasan_cf: Add Hibernation support
  pata_legacy: correctly mask recovery field for HT6560B
  ata_piix: IDE-mode SATA patch for Intel Lynx Point DeviceIDs
  ahci: AHCI-mode SATA patch for Intel Lynx Point DeviceIDs

Pull input subsystem updates from Dmitry Torokhov:
 "- we finally merged driver for USB version of Synaptics touchpads
    (I guess most commonly found in IBM/Lenovo keyboard/touchpad combo);

   - a bunch of new drivers for embedded platforms (Cypress
     touchscreens, DA9052 OnKey, MAX8997-haptic, Ilitek ILI210x
     touchscreens, TI touchscreen);

   - input core allows clients to specify desired clock source for
     timestamps on input events (EVIOCSCLOCKID ioctl);

   - input core allows querying state of all MT slots for given event
     code via EVIOCGMTSLOTS ioctl;

   - various driver fixes and improvements."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input: (45 commits)
  Input: ili210x - add support for Ilitek ILI210x based touchscreens
  Input: altera_ps2 - use of_match_ptr()
  Input: synaptics_usb - switch to module_usb_driver()
  Input: convert I2C drivers to use module_i2c_driver()
  Input: convert SPI drivers to use module_spi_driver()
  Input: omap4-keypad - move platform_data to <linux/platform_data>
  Input: kxtj9 - who_am_i check value and initial data rate fixes
  Input: add driver support for MAX8997-haptic
  Input: tegra-kbc - revise device tree support
  Input: of_keymap - add device tree bindings for simple key matrices
  Input: wacom - fix physical size calculation for 3rd-gen Bamboo
  Input: twl4030-vibra - really switch from #if to #ifdef
  Input: hp680_ts_input - ensure arguments to request_irq and free_irq are compatible
  Input: max8925_onkey - avoid accessing input device too early
  Input: max8925_onkey - allow to be used as a wakeup source
  Input: atmel-wm97xx - convert to dev_pm_ops
  Input: atmel-wm97xx - set driver owner
  Input: add cyttsp touchscreen maintainer entry
  Input: cyttsp - remove useless checks in cyttsp_probe()
  Input: usbtouchscreen - add support for Data Modul EasyTouch TP 72037
  ...

Pull crypto fixes from Herbert Xu:
 "This fixes a build problem where two crypto modules both try to export
  the same symbols (which shouldn't have been exported in the first
  place)."

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6:
  crypto: twofish-x86_64-3way - module init/exit functions should be static
  crypto: camellia-x86_64 - module init/exit functions should be static

Pull xen updates from Konrad Rzeszutek Wilk:
 "which has three neat features:

   - PV multiconsole support, so that there can be hvc1, hvc2, etc; This
     can be used in HVM and in PV mode.

   - P-state and C-state power management driver that uploads said power
     management data to the hypervisor.  It also inhibits cpufreq
     scaling drivers to load so that only the hypervisor can make power
     management decisions - fixing a weird perf bug.

     There is one thing in the Kconfig that you won't like: "default y
     if (X86_ACPI_CPUFREQ = y || X86_POWERNOW_K8 = y)" (note, that it
     all depends on CONFIG_XEN which depends on CONFIG_PARAVIRT which by
     default is off).  I've a fix to convert that boolean expression
     into "default m" which I am going to post after the cpufreq git
     pull - as the two patches to make this work depend on a fix in Dave
     Jones's tree.

   - Function Level Reset (FLR) support in the Xen PCI backend.

  Fixes:

   - Kconfig dependencies for Xen PV keyboard and video
   - Compile warnings and constify fixes
   - Change over to use percpu_xxx instead of this_cpu_xxx"

Fix up trivial conflicts in drivers/tty/hvc/hvc_xen.c due to changes to
a removed commit.

* tag 'stable/for-linus-3.4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
  xen kconfig: relax INPUT_XEN_KBDDEV_FRONTEND deps
  xen/acpi-processor: C and P-state driver that uploads said data to hypervisor.
  xen: constify all instances of "struct attribute_group"
  xen/xenbus: ignore console/0
  hvc_xen: introduce HVC_XEN_FRONTEND
  hvc_xen: implement multiconsole support
  hvc_xen: support PV on HVM consoles
  xenbus: don't free other end details too early
  xen/enlighten: Expose MWAIT and MWAIT_LEAF if hypervisor OKs it.
  xen/setup/pm/acpi: Remove the call to boot_option_idle_override.
  xenbus: address compiler warnings
  xen: use this_cpu_xxx replace percpu_xxx funcs
  xen/pciback: Support pci_reset_function, aka FLR or D3 support.
  pci: Introduce __pci_reset_function_locked to be used when holding device_lock.
  xen: Utilize the restore_msi_irqs hook.

Pull cleancache changes from Konrad Rzeszutek Wilk:
 "This has some patches for the cleancache API that should have been
  submitted a _long_ time ago.  They are basically cleanups:

   - rename of flush to invalidate

   - moving reporting of statistics into debugfs

   - use __read_mostly as necessary.

  Oh, and also the MAINTAINERS file change.  The files (except the
  MAINTAINERS file) have been in #linux-next for months now.  The late
  addition of MAINTAINERS file is a brain-fart on my side - didn't
  realize I needed that just until I was typing this up - and I based
  that patch on v3.3 - so the tree is on top of v3.3."

* tag 'stable/for-linus-3.4' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/mm:
  MAINTAINERS: Adding cleancache API to the list.
  mm: cleancache: Use __read_mostly as appropiate.
  mm: cleancache: report statistics via debugfs instead of sysfs.
  mm: zcache/tmem/cleancache: s/flush/invalidate/
  mm: cleancache: s/flush/invalidate/

Pull blackfin updates from Bob Liu

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/lliubbo/blackfin: (24 commits)
  blackfin: clean up string bfin_dma_5xx after rename.
  blackfin:dma: rename bfin_dma_5xx.c to bfin_dma.c
  bf548: ssm2602: Add ssm2602 platform data into bf548 ezkit board file.
  Blackfin: s/#if CONFIG/#ifdef CONFIG/
  Blackfin: pnav: delete duplicate linux/export.h include
  bf561: add ppi DLEN macro for 10bits to 16bits
  arch: blackfin: udpate defconfig
  Disintegrate asm/system.h for Blackfin [ver #2]
  arch/blackfin: don't generate random mac in bfin_get_ether_addr()
  Blackfin: wire up new process_vm syscalls
  blackfin: cleanup anomaly workarounds
  blackfin: update default defconfig
  blackfin: thread_info: add suspend flag
  bfin: add bfin_ad73311_machine platform device
  blackfin: bf537: stamp: update board file for 193x
  blackfin: kgdb: skip hardware watchpoint test
  bf548: add ppi interrupt mask and blanking clocks
  blackfin: bf561: forgot CSYNC in get_core_lock_noflush
  spi/bfin_spi: drop bits_per_word from client data
  blackfin: cplb-mpu: fix page mask table overflow
  ...

Pull s390 patches from Martin Schwidefsky:
 "The biggest patch is the rework of the smp code, something I wanted to
  do for some time.  There are some patches for our various dump methods
  and one new thing: z/VM LGR detection.  LGR stands for linux-guest-
  relocation and is the guest migration feature of z/VM.  For debugging
  purposes we keep a log of the systems where a specific guest has lived."

Fix up trivial conflict in arch/s390/kernel/smp.c due to the scheduler
cleanup having removed some code next to removed s390 code.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
  [S390] kernel: Pass correct stack for smp_call_ipl_cpu()
  [S390] Ensure that vmcore_info pointer is never accessed directly
  [S390] dasd: prevent validate server for offline devices
  [S390] Remove monolithic build option for zcrypt driver.
  [S390] stack dump: fix indentation in output
  [S390] kernel: Add OS info memory interface
  [S390] Use block_sigmask()
  [S390] kernel: Add z/VM LGR detection
  [S390] irq: external interrupt code passing
  [S390] irq: set __ARCH_IRQ_EXIT_IRQS_DISABLED
  [S390] zfcpdump: Implement async sdias event processing
  [S390] Use copy_to_absolute_zero() instead of "stura/sturg"
  [S390] rework idle code
  [S390] rework smp code
  [S390] rename lowcore field
  [S390] Fix gcc 4.6.0 compile warning

avc_audit() did a lot of jumping around and had a big stack frame, all
for the uncommon case.

Split up the uncommon case (which we really can't make go fast anyway)
into its own slow function, and mark the conditional branches
appropriately for the common likely case.

This causes avc_audit() to no longer show up as one of the hottest
functions on the branch profiles (the new "perf -b" thing), and makes
the cycle profiles look really nice and dense too.

The whole audit path is still annoyingly very much one of the biggest
costs of name lookup, so these things are worth optimizing for.  I wish
we could just tell people to turn it off, but realistically we do need
it: we just need to make sure that the overhead of the necessary evil is
as low as possible.
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

While doing the fs/namei.c cleanups, I ran sparse on it, and it pointed
out other large integers and a couple of cases of us using '0' instead
of the proper 'NULL'.

Sparse still doesn't understand some of the conditional locking going
on, but that's no excuse for not fixing up the trivial stuff.
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>