smq seems to be performing better than the old mq policy in all
situations, as well as using a quarter of the memory.

Make 'mq' an alias for 'smq' when choosing a cache policy.  The tunables
that were present for the old mq are faked, and have no effect.  mq
should be considered deprecated now.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

md->queue and q are the same thing in dm_old_init_request_queue() and
dm_mq_init_request_queue().

Also drop the temporary 'struct request_queue *q' in
dm_old_init_request_queue().
Signed-off-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Saves 16 bytes by eliminating 4 4byte holes but more importantly:
numerous members that crossed cachelines were fixed.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Change the map pointer in 'struct mapped_device' from 'struct dm_table
__rcu *' to 'void __rcu *' to avoid the need for the dummy definition.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Allows user to control which NUMA node the memory for DM device
structures (e.g. mapped_device, request_queue, gendisk, blk_mq_tag_set)
is allocated from.

Defaults to NUMA_NO_NODE (-1).  Allowable range is from -1 until the
last online NUMA node id.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Signed-off-by: Mike Snitzer <snitzer@redhat.com>

fail_path() will print a "Failing path ..." message but reinstate_path()
doesn't print a "Reinstating path ...".  Add that message to
reinstate_path() to add symmetry and aid system debugging.

Remove reinstate_path()'s check for the path_selector providing
.reinstate_path hook.  All path selectors provide this and any future
ones must too.

activate_path() calls pg_init_done() with SCSI_DH_DEV_OFFLINED but
pg_init_done() doesn't expicitly handle it in its swicth statement.  Add
SCSI_DH_DEV_OFFLINED to the default case.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Now that dm-mpath core is lockless in the per-IO fast path it is
critical, for performance, to have the .select_path hook
(rr_select_path) also be as lockless as possible.

The new percpu members of 'struct selector' allow for lockless support
of 'repeat_count' governed repeat use of a previously selected path.  If
a path fails while it is 'current_path' the worst case is concurrent IO
might be mapped to the failed path until the .fail_path hook
(rr_fail_path) is called.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

If a path selector has any use for a repeat_count it should be handled
locally and not depend on the dm-mpath core to be concerned with it.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Proper locking of the lists used by the path selectors should be handled
within the selectors (relying on dm-mpath.c code's use of the m->lock
spinlock was reckless).
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Preparation for making __multipath_map() avoid taking the m->lock
spinlock -- in favor of using RCU locking.

repeat_count was primarily for bio-based DM multipath's benefit.  There
is really no need for it anymore now that DM multipath is request-based.
As such, repeat_count > 1 is no longer honored and a warning is
displayed if the user attempts to use a value > 1.  This is a temporary
change for the round-robin path-selector (as a later commit will restore
its support for repeat_count > 1).
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Signed-off-by: Mike Snitzer <snitzer@redhat.com>

There isn't any need to support both old .request_fn and blk-mq paths
in the blk-mq specific portion of __multipath_map().  Call
blk_mq_alloc_request() directly rather than use blk_get_request().

Similarly, call blk_mq_free_request(), rather than blk_put_request(), in
multipath_release_clone().
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Refactor and rename existing interfaces to be more specific and
self-documenting.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Allow the multipath target to avoid making small allocations for each
'struct dm_mpath_io' that is needed for each request.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

This will allow DM multipath to use a portion of the blk-mq pdu space
for target data (e.g. struct dm_mpath_io).
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Request-based DM will also make use of per_bio_data_size.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Rename various methods to have either a "dm_old" or "dm_mq" prefix.
Improve code comments to assist with understanding the duality of code
that handles both "dm_old" and "dm_mq" cases.

It is no much easier to quickly look at the code and _know_ that a given
method is either 1) "dm_old" only 2) "dm_mq" only 3) common to both.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Remove all fiddley code that propped up this support for a blk-mq
request-queue ontop of all .request_fn devices.

Testing has proven this niche request-based dm-mq mode to be buggy, when
testing fault tolerance with DM multipath, and there is no point trying
to preserve it.

Should help improve efficiency of pure dm-mq code and make code
maintenance less delicate.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

old_stop_queue() was checking blk_queue_stopped() without holding the
q->queue_lock.

dm_requeue_original_request() needed to check blk_queue_stopped(), with
q->queue_lock held, before calling blk_mq_kick_requeue_list().  And a
side-effect of that change is start_queue() must also call
blk_mq_kick_requeue_list().
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

The blk_mq_tag_set is only needed for dm-mq support.  There is point
wasting space in 'struct mapped_device' for non-dm-mq devices.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> # check kzalloc return

Allow user to change these values via module params or sysfs.

'dm_mq_nr_hw_queues' defaults to 1 (max 32).

'dm_mq_queue_depth' defaults to 2048 (up from 64, which proved far too
small under moderate sized workloads -- the dm-multipath device would
continuously block waiting for tags (requests) to become available).
The maximum is BLK_MQ_MAX_DEPTH (currently 10240).

Keep in mind the total number of pre-allocated requests per
request-based dm-mq device is 'dm_mq_nr_hw_queues' * 'dm_mq_queue_depth'
(currently 2048).
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

DM multipath is the only request-based DM target -- which only supports
tables with a single target that is immutable.  Leverage this fact in
dm_request_fn().
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

DM multipath is the only dm-mq target.  But that aside, request-based DM
only supports tables with a single target that is immutable.  Leverage
this fact in dm_mq_queue_rq() by using the 'immutable_target' stored in
the mapped_device when the table was made active.  This saves the need
to even take the read-side of the SRCU via dm_{get,put}_live_table.

If the active DM table does not have an immutable target (e.g. "error"
target was swapped in) then fallback to the slow-path where the target
is looked up from the live table.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

The DM_TARGET_WILDCARD feature indicates that the "error" target may
replace any target; even immutable targets.  This feature will be useful
to preserve the ability to replace the "multipath" target even once it
is formally converted over to having the DM_TARGET_IMMUTABLE feature.

Also, implicit in the DM_TARGET_WILDCARD feature flag being set is that
.map, .map_rq, .clone_and_map_rq and .release_clone_rq are all defined
in the target_type.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

The request-based DM support for checking queue congestion doesn't
require access to the live DM table.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Request-based DM's blk-mq support (dm-mq) was reported to be 50% slower
than if an underlying null_blk device were used directly.  One of the
reasons for this drop in performance is that blk_insert_clone_request()
was calling blk_mq_insert_request() with @async=true.  This forced the
use of kblockd_schedule_delayed_work_on() to run the blk-mq hw queues
which ushered in ping-ponging between process context (fio in this case)
and kblockd's kworker to submit the cloned request.  The ftrace
function_graph tracer showed:

  kworker-2013  =>   fio-12190
  fio-12190    =>  kworker-2013
  ...
  kworker-2013  =>   fio-12190
  fio-12190    =>  kworker-2013
  ...

Fixing blk_insert_clone_request()'s blk_mq_insert_request() call to
_not_ use kblockd to submit the cloned requests isn't enough to
eliminate the observed context switches.

In addition to this dm-mq specific blk-core fix, there are 2 DM core
fixes to dm-mq that (when paired with the blk-core fix) completely
eliminate the observed context switching:

1)  don't blk_mq_run_hw_queues in blk-mq request completion

    Motivated by desire to reduce overhead of dm-mq, punting to kblockd
    just increases context switches.

    In my testing against a really fast null_blk device there was no benefit
    to running blk_mq_run_hw_queues() on completion (and no other blk-mq
    driver does this).  So hopefully this change doesn't induce the need for
    yet another revert like commit 621739b0 !

2)  use blk_mq_complete_request() in dm_complete_request()

    blk_complete_request() doesn't offer the traditional q->mq_ops vs
    .request_fn branching pattern that other historic block interfaces
    do (e.g. blk_get_request).  Using blk_mq_complete_request() for
    blk-mq requests is important for performance.  It should be noted
    that, like blk_complete_request(), blk_mq_complete_request() doesn't
    natively handle partial completions -- but the request-based
    DM-multipath target does provide the required partial completion
    support by dm.c:end_clone_bio() triggering requeueing of the request
    via dm-mpath.c:multipath_end_io()'s return of DM_ENDIO_REQUEUE.

dm-mq fix #2 is _much_ more important than #1 for eliminating the
context switches.
Before: cpu          : usr=15.10%, sys=59.39%, ctx=7905181, majf=0, minf=475
After:  cpu          : usr=20.60%, sys=79.35%, ctx=2008, majf=0, minf=472

With these changes multithreaded async read IOPs improved from ~950K
to ~1350K for this dm-mq stacked on null_blk test-case.  The raw read
IOPs of the underlying null_blk device for the same workload is ~1950K.

Fixes: 7fb4898e ("block: add blk-mq support to blk_insert_cloned_request()")
Fixes: bfebd1cd ("dm: add full blk-mq support to request-based DM")
Cc: stable@vger.kernel.org # 4.1+
Reported-by: Sagi Grimberg <sagig@dev.mellanox.co.il>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Jens Axboe <axboe@kernel.dk>

Rename dm_get_live_table_for_ioctl to dm_grab_bdev_for_ioctl and have it
do the dm_{get,put}_live_table() rather than split those operations.

The dm_grab_bdev_for_ioctl() callers only care about the block_device
associated with a singleton DM device so there isn't any need to retain
a reference to the live DM table.  It is sufficient to:
1) dm_get_live_table()
2) bdgrab() the bdev associated with the singleton table's target
3) dm_put_live_table()
4) bdput() the bdev
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

None of the callers actually used the returned target.
Also, just reuse bdev pointer passed to dm_blk_ioctl().
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Using request-based DM mpath configured with the following stacking
(.request_fn DM mpath ontop of scsi-mq paths):

echo Y > /sys/module/scsi_mod/parameters/use_blk_mq
echo N > /sys/module/dm_mod/parameters/use_blk_mq

'struct dm_rq_target_io' would leak if a request is requeued before a
blk-mq clone is allocated (or fails to allocate).  free_rq_tio()
wasn't being called.

kmemleak reported:

unreferenced object 0xffff8800b90b98c0 (size 112):
  comm "kworker/7:1H", pid 5692, jiffies 4295056109 (age 78.589s)
  hex dump (first 32 bytes):
    00 d0 5c 2c 03 88 ff ff 40 00 bf 01 00 c9 ff ff  ..\,....@.......
    e0 d9 b1 34 00 88 ff ff 00 00 00 00 00 00 00 00  ...4............
  backtrace:
    [<ffffffff81672b6e>] kmemleak_alloc+0x4e/0xb0
    [<ffffffff811dbb63>] kmem_cache_alloc+0xc3/0x1e0
    [<ffffffff8117eae5>] mempool_alloc_slab+0x15/0x20
    [<ffffffff8117ec1e>] mempool_alloc+0x6e/0x170
    [<ffffffffa00029ac>] dm_old_prep_fn+0x3c/0x180 [dm_mod]
    [<ffffffff812fbd78>] blk_peek_request+0x168/0x290
    [<ffffffffa0003e62>] dm_request_fn+0xb2/0x1b0 [dm_mod]
    [<ffffffff812f66e3>] __blk_run_queue+0x33/0x40
    [<ffffffff812f9585>] blk_delay_work+0x25/0x40
    [<ffffffff81096fff>] process_one_work+0x14f/0x3d0
    [<ffffffff81097715>] worker_thread+0x125/0x4b0
    [<ffffffff8109ce88>] kthread+0xd8/0xf0
    [<ffffffff8167cb8f>] ret_from_fork+0x3f/0x70
    [<ffffffffffffffff>] 0xffffffffffffffff

crash> struct -o dm_rq_target_io
struct dm_rq_target_io {
    ...
}
SIZE: 112

Fixes: e5863d9a ("dm: allocate requests in target when stacking on blk-mq devices")
Cc: stable@vger.kernel.org # 4.0+
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Pull x86 fixes from Ingo Molnar:
 "This is unusually large, partly due to the EFI fixes that prevent
  accidental deletion of EFI variables through efivarfs that may brick
  machines.  These fixes are somewhat involved to maintain compatibility
  with existing install methods and other usage modes, while trying to
  turn off the 'rm -rf' bricking vector.

  Other fixes are for large page ioremap()s and for non-temporal
  user-memcpy()s"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Fix vmalloc_fault() to handle large pages properly
  hpet: Drop stale URLs
  x86/uaccess/64: Handle the caching of 4-byte nocache copies properly in __copy_user_nocache()
  x86/uaccess/64: Make the __copy_user_nocache() assembly code more readable
  lib/ucs2_string: Correct ucs2 -> utf8 conversion
  efi: Add pstore variables to the deletion whitelist
  efi: Make efivarfs entries immutable by default
  efi: Make our variable validation list include the guid
  efi: Do variable name validation tests in utf8
  efi: Use ucs2_as_utf8 in efivarfs instead of open coding a bad version
  lib/ucs2_string: Add ucs2 -> utf8 helper functions

Pull perf fixes from Ingo Molnar:
 "A handful of CPU hotplug related fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/core: Plug potential memory leak in CPU_UP_PREPARE
  perf/core: Remove the bogus and dangerous CPU_DOWN_FAILED hotplug state
  perf/core: Remove bogus UP_CANCELED hotplug state
  perf/x86/amd/uncore: Plug reference leak

Pull powerpc fixes from Michael Ellerman:
 - Fix build error on 32-bit with checkpoint restart from Aneesh Kumar
 - Fix dedotify for binutils >= 2.26 from Andreas Schwab
 - Don't trace hcalls on offline CPUs from Denis Kirjanov
 - eeh: Fix stale cached primary bus from Gavin Shan
 - eeh: Fix stale PE primary bus from Gavin Shan
 - mm: Fix Multi hit ERAT cause by recent THP update from Aneesh Kumar K.V
 - ioda: Set "read" permission when "write" is set from Alexey Kardashevskiy

* tag 'powerpc-4.5-3' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/ioda: Set "read" permission when "write" is set
  powerpc/mm: Fix Multi hit ERAT cause by recent THP update
  powerpc/powernv: Fix stale PE primary bus
  powerpc/eeh: Fix stale cached primary bus
  powerpc/pseries: Don't trace hcalls on offline CPUs
  powerpc: Fix dedotify for binutils >= 2.26
  powerpc/book3s_32: Fix build error with checkpoint restart

Pull dmaengine fixes from Vinod Koul:
 "A few fixes for drivers, nothing major here.

  Fixes are: iotdma fix to restart channels, new ID for wildcat PCH,
  residue fix for edma, disable irq for non-cyclic in dw"

* tag 'dmaengine-fix-4.5-rc5' of git://git.infradead.org/users/vkoul/slave-dma:
  dmaengine: dw: disable BLOCK IRQs for non-cyclic xfer
  dmaengine: edma: fix residue race for cyclic
  dmaengine: dw: pci: add ID for WildcatPoint PCH
  dmaengine: IOATDMA: fix timer code that continues to restart channels during idle

Pull clk driver fixes from Stephen Boyd:
 "An assortment of vendor specific clk drivers fixes, most notably
  fallout from adding Tegra210 and rockchip rk3036/rk3368 drivers this
  cycle.

  There's also the random smattering of sparse/checker fixes, a build
  "fix" to get the Tango clk driver to compile because the Kconfig
  symbol was renamed after the fact, and a clk gpio fix for a patch
  mismerge"

* tag 'clk-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux: (28 commits)
  clk: gpio: Really allow an optional clock= DT property
  Revert "clk: qcom: Specify LE device endianness"
  clk: versatile: mask VCO bits before writing
  clk: tegra: super: Fix sparse warnings for functions not declared as static
  clk: tegra: Fix sparse warnings for functions not declared as static
  clk: tegra: Fix sparse warning for pll_m
  clk: tegra: Use definition for pll_u override bit
  clk: tegra: Fix warning caused by pll_u failing to lock
  clk: tegra: Fix clock sources for Tegra210 EMC
  clk: tegra: Add the APB2APE audio clock on Tegra210
  clk: tegra: Add missing of_node_put()
  clk: tegra: Fix PLLE SS coefficients
  clk: tegra: Fix typos around clearing PLLE bits during enable
  clk: tegra: Do not disable PLLE when under hardware control
  clk: tegra: Fix pllx dyn step calculation
  clk: tegra: pll: Fix potential sleeping-while-atomic
  clk: tegra: Fix the misnaming of nvenc from msenc
  clk: tegra: Fix naming of MISC registers
  clk: tango4: rename ARCH_TANGOX to ARCH_TANGO
  clk: scpi: Fix checking return value of platform_device_register_simple()
  ...

Pull more drm fixes from Dave Airlie:
 "Some more fixes trickled in:

  A bunch of VC4 ones since it's a pretty new driver not much chance of
  regressions, and it fixes GPU resets.

  Also one atomic fix, one set of fixes for a common bug in TTM cleanup,
  and one i915 hotplug fix"

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux:
  drm/nouveau: use post-decrement in error handling
  drm/atomic: Allow for holes in connector state, v2.
  drm/i915: Fix hpd live status bits for g4x
  drm/vc4: Use runtime PM to power cycle the device when the GPU hangs.
  drm/vc4: Enable runtime PM.
  drm/vc4: Fix spurious GPU resets due to BO reuse.
  drm/vc4: Drop error message on seqno wait timeouts.
  drm/vc4: Fix -ERESTARTSYS error return from BO waits.
  drm/vc4: Return an ERR_PTR from BO creation instead of NULL.
  drm/vc4: Fix the clear color for the first tile rendered.
  drm/vc4: Validate that WAIT_BO padding is cleared.
  drm/radeon: use post-decrement in error handling
  drm/amdgpu: use post-decrement in error handling