In the case of both the submit_queues param and use_per_node_hctx param
are used. We limit the number af submit_queues to the number of online
nodes.

If the submit_queues is a multiple of nr_online_nodes, its trivial. Simply map
them to the nodes. For example: 8 submit queues are mapped as node0[0,1],
node1[2,3], ...
If uneven, we are left with an uneven number of submit_queues that must be
mapped. These are mapped toward the first node and onward. E.g. 5
submit queues mapped onto 4 nodes are mapped as node0[0,1], node1[2], ...
Signed-off-by: Matias Bjorling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

The defaults for the module is to instantiate itself with blk-mq and a
submit queue for each CPU node in the system.

To save resources, initialize instead with a single submit queue.
Signed-off-by: Matias Bjorling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Randy Dunlap reported a couple of grammar errors and unfortunate usages of
socket/node/core.
Signed-off-by: Matias Bjorling <m@bjorling.me>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Let the user know when the number of submission queues are being
ignored.
Signed-off-by: Matias Bjorling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Simplify the initialization logic of the three block-layers.

- The queue initialization is split into two parts. This allows reuse of
  code when initializing the sq-, bio- and mq-based layers.
- Set submit_queues default value to 0 and always set it at init time.
- Simplify the init error code paths.
Signed-off-by: Matias Bjorling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Add description of module and its parameters.
Signed-off-by: Matias Bjorling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

For NUMA systems, initializing the blk-mq layer and using per node hctx.
We initialize submit queues to 1, while blk-mq nr_hw_queues is
initialized to the number of NUMA nodes.

This makes the null_init_hctx function overwrite memory outside of what
it allocated.  In my case it lead to writing garbage into struct
request_queue's mq_map.
Signed-off-by: Matias Bjorling <m@bjorling.me>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Mark functions skd_skmsg_state_to_str() and skd_skreq_state_to_str() as
static in skd_main.c because they are not used outside this file.

This eliminates the following warnings in skd_main.c:
drivers/block/skd_main.c:5272:13: warning: no previous prototype for ‘skd_skmsg_state_to_str’ [-Wmissing-prototypes]
drivers/block/skd_main.c:5284:13: warning: no previous prototype for ‘skd_skreq_state_to_str’ [-Wmissing-prototypes]
Signed-off-by: Rashika Kheria <rashika.kheria@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Kent writes:

Jens - small pile of bcache fixes. I've been slacking on the writeback
fixes but those definitely need to get into 3.13.

The old writeback PD controller could get into states where it had throttled all
the way down and take way too long to recover - it was too complicated to really
understand what it was doing.

This rewrites a good chunk of it to hopefully be simpler and make more sense,
and it also pays more attention to units which should make the behaviour a bit
easier to understand.
Signed-off-by: Kent Overstreet <kmo@daterainc.com>

There is a possibility for a bucket to be invalidated by the allocator
while moving_gc was copying it's contents to another bucket, if the
bucket only held cached data. To prevent this moving checks for
a stale ptr (to an invalidated bucket), before and after reads.
It it finds one, it simply ignores moving that data. This only
affects bcache if the moving_gc was turned on, note that it's
off by default.
Signed-off-by: Nicholas Swenson <nks@daterainc.com>
Signed-off-by: Kent Overstreet <kmo@daterainc.com>

Garbage collector needs to check keys in the writeback keybuf to
make sure it's not invalidating buckets to which the writeback
keys point to.
Signed-off-by: Nicholas Swenson <nks@daterainc.com>
Signed-off-by: Kent Overstreet <kmo@daterainc.com>

Removed gc_move_threshold because picking buckets only by
threshold could lead moving extra buckets (ei. if there are
buckets at the threshold that aren't supposed to be moved
do to space considerations).

This is replaced by a GC_MOVE bit in the gc_mark bitmask.
Now only marked buckets get moved.
Signed-off-by: Nicholas Swenson <nks@daterainc.com>
Signed-off-by: Kent Overstreet <kmo@daterainc.com>

Signed-off-by: Nicholas Swenson <nks@daterainc.com>
Signed-off-by: Kent Overstreet <kmo@daterainc.com>

Signed-off-by: Nicholas Swenson <nks@daterainc.com>
Signed-off-by: Kent Overstreet <kmo@daterainc.com>

Signed-off-by: Nicholas Swenson <nks@daterainc.com>
Signed-off-by: Kent Overstreet <kmo@daterainc.com>

Dirty data accounting wasn't quite right - firstly, we were adding the key we're
inserting after it could have merged with another dirty key already in the
btree, and secondly we could sometimes pass the wrong offset to
bcache_dev_sectors_dirty_add() for dirty data we were overwriting - which is
important when tracking dirty data by stripe.

NOTE FOR BACKPORTERS: For 3.10 (and 3.11?) there's other accounting fixes
necessary that got squashed in with other patches; the full patch against 3.10
is 408cc2f47eeac93a, available at:
  git://evilpiepirate.org/~kent/linux-bcache.git bcache-3.10-writeback-fixes
Signed-off-by: Kent Overstreet <kmo@daterainc.com>
Cc: linux-stable <stable@vger.kernel.org> # >= v3.10

diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 2a46036..4a12b2f 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1817,7 +1817,8 @@ static bool fix_overlapping_extents(struct btree *b, struct bkey *insert,
 			if (KEY_START(k) > KEY_START(insert) + sectors_found)
 				goto check_failed;

-			if (KEY_PTRS(replace_key) != KEY_PTRS(k))
+			if (KEY_PTRS(k) != KEY_PTRS(replace_key) ||
+			    KEY_DIRTY(k) != KEY_DIRTY(replace_key))
 				goto check_failed;

 			/* skip past gen */

We're just waiting on kthread_should_stop(), nothing else, so
interruptible sleep was wrong here.
Signed-off-by: Kent Overstreet <kmo@daterainc.com>

at the beginning (schedule_timout_interuptible) and others
do his on their own

This prevents wrong load average calculation (load of 1 per thread)
Signed-off-by: Kent Overstreet <kmo@daterainc.com>

All objects, which are allocated in blk_mq_register_disk, must be
released in blk_mq_unregister_disk.

I use a KVM virtual machine and virtio disk to reproduce this issue.

kmemleak: 18 new suspected memory leaks (see /sys/kernel/debug/kmemleak)
$ cat /sys/kernel/debug/kmemleak | head -n 30
unreferenced object 0xffff8800b6636150 (size 8):
  comm "kworker/0:2", pid 65, jiffies 4294809903 (age 86.358s)
  hex dump (first 8 bytes):
    76 69 72 74 69 6f 34 00                          virtio4.
  backtrace:
    [<ffffffff8165d41e>] kmemleak_alloc+0x4e/0xb0
    [<ffffffff8118cfc5>] __kmalloc_track_caller+0xf5/0x260
    [<ffffffff81155b11>] kstrdup+0x31/0x60
    [<ffffffff812242be>] sysfs_new_dirent+0x2e/0x140
    [<ffffffff81224678>] create_dir+0x38/0xe0
    [<ffffffff812249e3>] sysfs_create_dir_ns+0x73/0xc0
    [<ffffffff8130dfa9>] kobject_add_internal+0xc9/0x340
    [<ffffffff8130e535>] kobject_add+0x65/0xb0
    [<ffffffff813f34f8>] device_add+0x128/0x660
    [<ffffffff813f3a4a>] device_register+0x1a/0x20
    [<ffffffff813ae6f8>] register_virtio_device+0x98/0xe0
    [<ffffffff813b0cce>] virtio_pci_probe+0x12e/0x1c0
    [<ffffffff81340675>] local_pci_probe+0x45/0xa0
    [<ffffffff81341a51>] pci_device_probe+0x121/0x130
    [<ffffffff813f67f7>] driver_probe_device+0x87/0x390
    [<ffffffff813f6b3b>] __device_attach+0x3b/0x40
unreferenced object 0xffff8800b65aa1d8 (size 144):

Fixes: 320ae51f (blk-mq: new multi-queue block IO queueing mechanism)
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Pull power management fixes from Rafael Wysocki:

 - cpufreq regression fix from Bjørn Mork restoring the pre-3.12
   behavior of the framework during system suspend/hibernation to avoid
   garbage sysfs files from being left behind in case of a suspend error

 - PNP regression fix to restore the correct states of devices after
   resume from hibernation broken in 3.12.  From Dmitry Torokhov.

 - cpuidle fix to prevent cpuidle device unregistration from crashing
   due to a NULL pointer dereference if cpuidle has been disabled from
   the kernel command line.  From Konrad Rzeszutek Wilk.

 - intel_idle fix for the C6 state definition on Intel Avoton/Rangeley
   processors from Arne Bockholdt.

 - Power capping framework fix to make the energy_uj sysfs attribute
   work in accordance with the documentation.  From Srinivas Pandruvada.

 - epoll fix to make it ignore the EPOLLWAKEUP flag if the kernel has
   been compiled with CONFIG_PM_SLEEP unset (in which case that flag
   should not have any effect).  From Amit Pundir.

 - cpufreq fix to prevent governor sysfs files from being lost over
   system suspend/resume in some (arguably unusual) situations.  From
   Viresh Kumar.

* tag 'pm-3.13-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  PowerCap: Fix mode for energy counter
  PNP: fix restoring devices after hibernation
  cpuidle: Check for dev before deregistering it.
  epoll: drop EPOLLWAKEUP if PM_SLEEP is disabled
  cpufreq: fix garbage kobjects on errors during suspend/resume
  cpufreq: suspend governors on system suspend/hibernate
  intel_idle: Fixed C6 state on Avoton/Rangeley processors

* pm-epoll:
  epoll: drop EPOLLWAKEUP if PM_SLEEP is disabled

* pnp:
  PNP: fix restoring devices after hibernation

* powercap:
  PowerCap: Fix mode for energy counter

* pm-cpuidle:
  cpuidle: Check for dev before deregistering it.
  intel_idle: Fixed C6 state on Avoton/Rangeley processors

* pm-cpufreq:
  cpufreq: fix garbage kobjects on errors during suspend/resume
  cpufreq: suspend governors on system suspend/hibernate

Pull arch/tile ftrace bug fix from Chris Metcalf:
 "This fixes a build failure with allyesconfig reported by Fengguang Wu
  and fixed by Tony Lu"

* 'stable' of git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile:
  ftrace: default to tilegx if ARCH=tile is specified

Pull block layer fixes from Jens Axboe:
 "A small collection of fixes for the current series. It contains:

   - A fix for a use-after-free of a request in blk-mq.  From Ming Lei

   - A fix for a blk-mq bug that could attempt to dereference a NULL rq
     if allocation failed

   - Two xen-blkfront small fixes

   - Cleanup of submit_bio_wait() type uses in the kernel, unifying
     that.  From Kent

   - A fix for 32-bit blkg_rwstat reading.  I apologize for this one
     looking mangled in the shortlog, it's entirely my fault for missing
     an empty line between the description and body of the text"

* 'for-linus' of git://git.kernel.dk/linux-block:
  blk-mq: fix use-after-free of request
  blk-mq: fix dereference of rq->mq_ctx if allocation fails
  block: xen-blkfront: Fix possible NULL ptr dereference
  xen-blkfront: Silence pfn maybe-uninitialized warning
  block: submit_bio_wait() conversions
  Update of blkg_stat and blkg_rwstat may happen in bh context

Pull NFS client bugfixes from Trond Myklebust:
 - Stable fix for a NFSv4.1 delegation and state recovery deadlock
 - Stable fix for a loop on irrecoverable errors when returning
   delegations
 - Fix a 3-way deadlock between layoutreturn, open, and state recovery
 - Update the MAINTAINERS file with contact information for Trond
   Myklebust
 - Close needs to handle NFS4ERR_ADMIN_REVOKED
 - Enabling v4.2 should not recompile nfsd and lockd
 - Fix a couple of compile warnings

* tag 'nfs-for-3.13-3' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  nfs: fix do_div() warning by instead using sector_div()
  MAINTAINERS: Update contact information for Trond Myklebust
  NFSv4.1: Prevent a 3-way deadlock between layoutreturn, open and state recovery
  SUNRPC: do not fail gss proc NULL calls with EACCES
  NFSv4: close needs to handle NFS4ERR_ADMIN_REVOKED
  NFSv4: Update list of irrecoverable errors on DELEGRETURN
  NFSv4 wait on recovery for async session errors
  NFS: Fix a warning in nfs_setsecurity
  NFS: Enabling v4.2 should not recompile nfsd and lockd

This matches the existing behavior in arch/tile/Makefile for defconfig.

Reported-by: fengguang.wu@intel.com
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Tony Lu <zlu@tilera.com>
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>

Pull btrfs MAINTAINERS file update:
 "I'm still getting settled into new devel hardware etc, but I do have
  one commit for the next rc.

  This changes my email over to fb.com, and adds a MAINTAINERS entry for
  Josef as well"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
  Btrfs: update the MAINTAINERS file

Pull minor fbdev fixes from Tomi Valkeinen.

* tag 'fbdev-fixes-3.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tomba/linux:
  video: vt8500: fix error handling in probe()
  atmel_lcdfb: fix module autoload
  fbdev: sh_mobile_meram: Fix defined but not used compiler warnings
  video: kyro: fix incorrect sizes when copying to userspace
  ARM: OMAPFB: panel-sony-acx565akm: fix bad unlock balance

Pull sound fixes from Takashi Iwai:
 "A usual pattern of half ASoC and half HD-audio fixes, although
  HD-audio fixups have more volumes, in addition to a couple of trivial
  fixes.  Nothing to worry much is found here.

  For ASoC side: a few fixes for PCM rate constraints calculations,
  regmap byte-order fix, the rest driver specific fixes (atmel, fsl,
  omap, kirkwood, wm codecs).

  For HD-audio: Dell headset and mono out fix, ELD update in polling
  mode, ALC283 Chromebook fixes, a few fixes for old AD codecs and
  MBA2, one regression fix"

* tag 'sound-3.13-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound: (30 commits)
  ALSA: hda - Fix silent output on MacBook Air 2,1
  ALSA: hda - Fix missing ELD info when using jackpoll_ms parameter
  ALSA: hda/realtek - remove hp_automute_hook from alc283_fixup_chromebook
  ASoC: wm8731: fix dsp mode configuration
  ALSA: hda/realtek - Independent of model for HP
  ALSA: hda - Fix headset mic input after muted internal mic (Dell/Realtek)
  ALSA: hda - Use always amps for auto-mute on AD1986A codec
  ALSA: hda/analog - Handle inverted EAPD properly in vmaster hook
  ALSA: hda - Another fixup for ASUS laptop with ALC660 codec
  ALSA: atmel: Fix possible array overflow
  ALSA: hda - Fix complete_all() timing in deferred probes
  ALSA: hda - Fix bad EAPD setup for HP machines with AD1984A
  ASoC: core: fix devres parameter in devm_snd_soc_register_card()
  ASoC: omap: n810: Convert to clk_prepare_enable/clk_disable_unprepare
  ASoC: fsl: set correct platform drvdata in pcm030_fabric_probe()
  ASoC: fsl: imx-pcm-fiq: Remove unused 'runtime' variable
  ASoC: fsl: imx-pcm-fiq: remove bogus period delta calculation
  ALSA: hda - Fix silent output on ASUS W7J laptop
  ASoC: core: Use consistent byte ordering in snd_soc_bytes_get
  ALSA: dice: fix array limits in dice_proc_read()
  ...

Pull pin control fixes from Linus Walleij:

 - Minor bug fixes for the Rockchip, ST-Ericsson abx500, Renesas PFC
   r8a7740 and sh7372.

 - Compilation warning fixes.

* tag 'pinctrl-v3.13-2' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl:
  sh-pfc: sh7372: Fix pin bias setup
  sh-pfc: r8a7740: Fix pin bias setup
  pinctrl: abx500: Fix header file include guard
  pinctrl: rockchip: missing unlock on error in rockchip_set_pull()
  pinctrl: abx500: fix some more bitwise AND tests
  pinctrl: rockchip: testing the wrong variable

If accounting is on, we will do the IO completion accounting after
we have freed the request. Fix that by moving it sooner instead.
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Pull x86 and EFI fixes from Peter Anvin:
 "Half of these are EFI-related:

  The by far biggest change is the change to hold off the deletion of a
  sysfs entry while a backend scan is in progress.  This is to avoid
  calling kmemdup() while under a spinlock.

  The other major change is for each entry in the EFI pstore backend to
  get a unique identifier, as required by the pstore filesystem proper.

  The other changes are:

  A fix to the recent consolidation and optimization of using "asm goto"
  with read-modify-write operation, which broke the bitops; specifically
  in such a way that we could end up generating invalid code.

  A build hack to make sure we compile with -mno-sse.  icc, and most
  likely future versions of gcc, can generate SSE instructions unless we
  tell it not to.

  A comment-only patch to a change the was due in part to an unpublished
  erratum; now when the erratum is published we want to add a comment
  explaining why"

* 'x86/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/apic, doc: Justification for disabling IO APIC before Local APIC
  x86, bitops: Correct the assembly constraints to testing bitops
  x86-64, build: Always pass in -mno-sse
  efi-pstore: Make efi-pstore return a unique id
  x86/efi: Fix earlyprintk off-by-one bug
  efivars, efi-pstore: Hold off deletion of sysfs entry until the scan is completed

Since erratum AVR31 in "Intel Atom Processor C2000 Product Family
Specification Update" is now published, I added a justification
comment for disabling IO APIC before Local APIC, as changed in commit:

522e6646 x86/apic: Disable I/O APIC before shutdown of the local APIC
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1386202069-51515-1-git-send-email-fenghua.yu@intel.comSigned-off-by: H. Peter Anvin <hpa@linux.intel.com>

As per the documentation of powercap sysfs, energy_uj field is read only,
if it can't be reset. Currently it always allows write but will fail,
if there is no reset callback.
Changing mode field, to read only if there is no reset callback.
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Reported-by: Dirk Brandewie <dirk.j.brandewie@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

On returning from hibernation 'restore' callback is called,
not 'resume'.  Fix it.

Fixes: eaf140b6 (PNP: convert PNP driver bus legacy pm_ops to dev_pm_ops)
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: 3.12+ <stable@vger.kernel.org> # 3.12+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

In checkin:

0c44c2d0 x86: Use asm goto to implement better modify_and_test() functions

the various functions which do modify and test were unified and
optimized using "asm goto".  However, this change missed the detail
that the bitops require an "Ir" constraint rather than an "er"
constraint ("I" = integer constant from 0-31, "e" = signed 32-bit
integer constant).  This would cause code to miscompile if these
functions were used on constant bit positions 32-255 and the build to
fail if used on constant bit positions above 255.

Add the constraints as a parameter to the GEN_BINARY_RMWcc() macro to
avoid this problem.
Reported-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/529E8719.4070202@zytor.com

When compiling a 32bit kernel with CONFIG_LBDAF=n the compiler complains like
shown below.  Fix this warning by instead using sector_div() which is provided
by the kernel.h header file.

fs/nfs/blocklayout/extents.c: In function ‘normalize’:
include/asm-generic/div64.h:43:28: warning: comparison of distinct pointer types lacks a cast [enabled by default]
fs/nfs/blocklayout/extents.c:47:13: note: in expansion of macro ‘do_div’
nfs/blocklayout/extents.c:47:2: warning: right shift count >= width of type [enabled by default]
fs/nfs/blocklayout/extents.c:47:2: warning: passing argument 1 of ‘__div64_32’ from incompatible pointer type [enabled by default]
include/asm-generic/div64.h:35:17: note: expected ‘uint64_t *’ but argument is of type ‘sector_t *’
 extern uint32_t __div64_32(uint64_t *dividend, uint32_t divisor);
Signed-off-by: Helge Deller <deller@gmx.de>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>

Andy Adamson reports:

The state manager is recovering expired state and recovery OPENs are being
processed. If kswapd is pruning inodes at the same time, a deadlock can occur
when kswapd calls evict_inode on an NFSv4.1 inode with a layout, and the
resultant layoutreturn gets an error that the state mangager is to handle,
causing the layoutreturn to wait on the (NFS client) cl_rpcwaitq.

At the same time an open is waiting for the inode deletion to complete in
__wait_on_freeing_inode.

If the open is either the open called by the state manager, or an open from
the same open owner that is holding the NFSv4 sequence id which causes the
OPEN from the state manager to wait for the sequence id on the Seqid_waitqueue,
then the state is deadlocked with kswapd.

The fix is simply to have layoutreturn ignore all errors except NFS4ERR_DELAY.
We already know that layouts are dropped on all server reboots, and that
it has to be coded to deal with the "forgetful client model" that doesn't
send layoutreturns.
Reported-by: Andy Adamson <andros@netapp.com>
Link: http://lkml.kernel.org/r/1385402270-14284-1-git-send-email-andros@netapp.comSigned-off-by: Trond Myklebust <Trond.Myklebust@primarydata.com>