Roccat devices are standard compatible, specific drivers are only needed
for extended functionality.
If Roccat drivers are not configured, hid-generic binds these devices now.
Signed-off-by: Stefan Achatz <erazor_de@users.sourceforge.net>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

Return -ENOMEM instead of -1 if memory allocation fails.
Return -EINVAL instead of -1 for stack overflow and
underflow errors.
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

container_of() never returns NULL, thus also remove the NULL checking for it.
Signed-off-by: Axel Lin <axel.lin@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

Signed-off-by: Axel Lin <axel.lin@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

Signed-off-by: Axel Lin <axel.lin@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

Signed-off-by: Axel Lin <axel.lin@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

The px_probe() and px_remove() functions do not have any special initialization
and cleanup. Remove them and let HID core handle the default probe/remove
actions.
Signed-off-by: Axel Lin <axel.lin@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

The waltop_probe() and waltop_remove() functions do not have any special
initialization and cleanup. Remove them and let HID core handle the default
probe/remove actions.
Signed-off-by: Axel Lin <axel.lin@gmail.com>
Acked-by: Nikolai Kondrashov <spbnick@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

Signed-off-by: Axel Lin <axel.lin@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

Paul Walmsley has implemented dynamic quirk handling back in 2007 through
commits:

2eb5dc30 ("USB HID: encapsulate quirk handling into hid-quirks.c")
8222fbe6 ("USB HID: clarify static quirk handling as squirks")
8cef9082 ("USB HID: add support for dynamically-created quirks")
876b9276 ("USB HID: add 'quirks' module parameter")

and as such, his copyright rightly belongs to
drivers/hid/usbhid/hid-quirks.c file.

However when generic HID code has been converted to bus and individual
quirks separated out to individual drivers on the bus, the copyright has
been blindly transfered into all the tiny drivers, which actually don't
contain any of Pauls' copyrighted code.

Remove the copyright from those sub-drivers.
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Paul Walmsley <paul@pwsan.com>

HID_LOGITECH_DJ uses "default m", which enables it in default kernel
builds.  Since this module just enables extra, non-critical
functionality for one particular piece of hardware (specifically,
differentiating multiple wireless keyboards and mice as separate input
devices rather than treating them as one device), and the hardware works
just fine with the default USB HID support, drop the "default m".
Signed-off-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

Update the comment of hid_have_special_driver[] field to reflect the fact
that multitouch devices don't need to be present there.
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

Sync with Linus' tree so that we don't have build falures
due to Quanta 3001 ID reshuffling.

Since commit a7197c2e, the raw report descriptor is available also for
unclaimed devices. This patchs make it show in the rdesc debugfs node.
Signed-off-by: Henrik Rydberg <rydberg@euromail.se>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

For some reason, we had two IDs for the QUANTA 3001 touchscreen controller,
one USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3001 and one
USB_DEVICE_ID_PIXART_IMAGING_INC_OPTICAL_TOUCH_SCREEN. As this has caused
confusion, remove USB_DEVICE_ID_PIXART_IMAGING_INC_OPTICAL_TOUCH_SCREEN
completely, and fix places where it was used to refer to
USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3001.
Signed-off-by: Simon Farnsworth <simon.farnsworth@onelan.co.uk>
Acked-by: Henrik Rydberg <rydberg@euromail.se>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

Pull HID fix from Jiri Kosina:
 "Fix for one particular device not being properly claimed by
  hid-multitouch driver"

* 'upstream-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid:
  HID: Remove QUANTA from special drivers list

Pull drm fixes from Dave Airlie:
 "Intel: edid fixes, power consumption fix, s/r fix, haswell fix

  Radeon: BIOS loading fixes for UEFI and Thunderbolt machines, better
  MSAA validation, lockup timeout fixes, modesetting fixes

  One udl dpms fix, one vmwgfx fix, a couple of trivial core changes.

  There is an export added to ACPI as part of the radeon bios fixes.

  I've also included the fbcon flashing cursor vs deinit race fix, that
  seems the simplest place to start"

Trivial conflict in drivers/video/console/fbcon.c due to me having
already applied the fbcon flashing cursor vs deinit race fix, and Dave
had added a comment in there too.

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux: (22 commits)
  fbcon: fix race condition between console lock and cursor timer (v1.1)
  drm: Add missing static storage class specifiers in drm_proc.c file
  drm/udl: dpms off the crtc when disabled.
  drm: Remove two unused fields from struct drm_display_mode
  drm: stop vmgfx driver explosion
  drm/radeon/ss: use num_crtc rather than hardcoded 6
  Revert "drm/radeon: fix bo creation retry path"
  drm/i915: use hsw rps tuning values everywhere on gen6+
  drm/radeon: split ATRM support out from the ATPX handler (v3)
  drm/radeon: convert radeon vfct code to use acpi_get_table_with_size
  ACPI: export symbol acpi_get_table_with_size
  drm/radeon: implement ACPI VFCT vbios fetch (v3)
  drm/radeon/kms: extend the Fujitsu D3003-S2 board connector quirk to cover later silicon stepping
  drm/radeon: fix checking of MSAA renderbuffers on r600-r700
  drm/radeon: allow CMASK and FMASK in the CS checker on r600-r700
  drm/radeon: init lockup timeout on ring init
  drm/radeon: avoid turning off spread spectrum for used pll
  drm/i915: fall back to bit-banging if GMBUS fails in CRT EDID reads
  drm/i915: extract connector update from intel_ddc_get_modes() for reuse
  drm/i915: fix hsw uncached pte
  ...

Pull SCSI target fixes from Nicholas Bellinger:
 "The executive summary includes:

   - Post-merge review comments for tcm_vhost (MST + nab)
   - Avoid debugging overhead when not debugging for tcm-fc(FCoE) (MDR)
   - Fix NULL pointer dereference bug on alloc_page failulre (Yi Zou)
   - Fix REPORT_LUNs regression bug with pSCSI export (AlexE + nab)
   - Fix regression bug with handling of zero-length data CDBs (nab)
   - Fix vhost_scsi_target structure alignment (MST)

  Thanks again to everyone who contributed a bugfix patch, gave review
  feedback on tcm_vhost code, and/or reported a bug during their own
  testing over the last weeks.

  There is one other outstanding bug reported by Roland recently related
  to SCSI transfer length overflow handling, for which the current
  proposed bugfix has been left in queue pending further testing with
  other non iscsi-target based fabric drivers.

  As the patch is verified with loopback (local SGL memory from SCSI
  LLD) + tcm_qla2xxx (TCM allocated SGL memory mapped to PCI HW) fabric
  ports, it will be included into the next 3.6-rc-fixes PULL request."

* git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending:
  target: Remove unused se_cmd.cmd_spdtl
  tcm_fc: rcu_deref outside rcu lock/unlock section
  tcm_vhost: Fix vhost_scsi_target structure alignment
  target: Fix regression bug with handling of zero-length data CDBs
  target/pscsi: Fix bug with REPORT_LUNs handling for SCSI passthrough
  tcm_vhost: Change vhost_scsi_target->vhost_wwpn to char *
  target: fix NULL pointer dereference bug alloc_page() fails to get memory
  tcm_fc: Avoid debug overhead when not debugging
  tcm_vhost: Post-merge review changes requested by MST
  tcm_vhost: Fix incorrect IS_ERR() usage in vhost_scsi_map_iov_to_sgl

Pull i2c-embedded fixes from Wolfram Sang:
 "Some bugfixes for the "embedded" part of the I2C subsystem.  The fixes
  affect mostly drivers which have been largely reworked lately and
  where regressions appeared."

* 'i2c-embedded/for-current' of git://git.pengutronix.de/git/wsa/linux:
  i2c: tegra: protect suspend/resume callbacks with CONFIG_PM_SLEEP
  i2c: diolan-u2c: Fix master_xfer return code
  I2C: OMAP: xfer: fix runtime PM get/put balance on error
  i2c: nomadik: Add default configuration into the Nomadik I2C driver

Pull pwm fixes from Thierry Reding:
 "These patches fix the Samsung PWM driver and perform some minor
  cleanups like fixing checkpatch and sparse warnings.

  Two redundant error messages are removed and the Kconfig help text for
  the PWM subsystem is made more descriptive."

* tag 'for-3.6-rc3' of git://gitorious.org/linux-pwm/linux-pwm:
  pwm: Improve Kconfig help text
  pwm: core: Fix coding style issues
  pwm: vt8500: Fix coding style issue
  pwm: Remove a redundant error message when devm_request_and_ioremap fails
  pwm: samsung: add missing device pointer to struct pwm_chip
  pwm: Add missing static storage class specifiers in core.c file

Pull ceph fixes from Sage Weil:
 "Jim's fix closes a narrow race introduced with the msgr changes.  One
  fix resolves problems with debugfs initialization that Yan found when
  multiple client instances are created (e.g., two clusters mounted, or
  rbd + cephfs), another one fixes problems with mounting a nonexistent
  server subdirectory, and the last one fixes a divide by zero error
  from unsanitized ioctl input that Dan Carpenter found."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client:
  ceph: avoid divide by zero in __validate_layout()
  libceph: avoid truncation due to racing banners
  ceph: tolerate (and warn on) extraneous dentry from mds
  libceph: delay debugfs initialization until we learn global_id

Pull NFS client bugfixes from Trond Myklebust:
 - NFSv3 mounts need to fail if the FSINFO rpc call fails
 - Ensure that the NFS commit cache gets torn down when we unload the
   NFS module.
 - Fix memory scribble issues when interrupting a LAYOUTGET rpc call
 - Fix NFSv4 legacy idmapper regressions
 - Fix issues with the NFSv4 getacl command
 - Fix a regression when using the legacy "mount -t nfs4"

* tag 'nfs-for-3.6-3' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  NFSv3: Ensure that do_proc_get_root() reports errors correctly
  NFSv4: Ensure that nfs4_alloc_client cleans up on error.
  NFS: return -ENOKEY when the upcall fails to map the name
  NFS: Clear key construction data if the idmap upcall fails
  NFSv4: Don't use private xdr_stream fields in decode_getacl
  NFSv4: Fix the acl cache size calculation
  NFSv4: Fix pointer arithmetic in decode_getacl
  NFS: Alias the nfs module to nfs4
  NFS: Fix a regression when loading the NFS v4 module
  NFSv4.1: Remove a bogus BUG_ON() in nfs4_layoutreturn_done
  pnfs-obj: Better IO pattern in case of unaligned offset
  NFS41: add pg_layout_private to nfs_pageio_descriptor
  pnfs: nfs4_proc_layoutget returns void
  pnfs: defer release of pages in layoutget
  nfs: tear down caches in nfs_init_writepagecache when allocation fails

Pull assorted fixes - mostly vfs - from Al Viro:
 "Assorted fixes, with an unexpected detour into vfio refcounting logics
  (fell out when digging in an analog of eventpoll race in there)."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  task_work: add a scheduling point in task_work_run()
  fs: fix fs/namei.c kernel-doc warnings
  eventpoll: use-after-possible-free in epoll_create1()
  vfio: grab vfio_device reference *before* exposing the sucker via fd_install()
  vfio: get rid of vfio_device_put()/vfio_group_get_device* races
  vfio: get rid of open-coding kref_put_mutex
  introduce kref_put_mutex()
  vfio: don't dereference after kfree...
  mqueue: lift mnt_want_write() outside ->i_mutex, clean up a bit

This QUANTA device is driven by the generic hid-multitouch.ko driver, and
therefore shouldn't be in the special drivers list.

This has been an oversight in 4fa3a58 ("HID: hid-multitouch: Switch to
device groups").
Signed-off-by: Simon Farnsworth <simon.farnsworth@onelan.co.uk>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

It seems commit 4a9d4b02 (switch fput to task_work_add) reintroduced
the problem addressed in commit 944be0b2 (close_files(): add scheduling
point)

If a server process with a lot of files (say 2 million tcp sockets)
is killed, we can spend a lot of time in task_work_run() and trigger
a soft lockup.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

Fix kernel-doc warnings in fs/namei.c:

Warning(fs/namei.c:360): No description found for parameter 'inode'
Warning(fs/namei.c:672): No description found for parameter 'nd'
Signed-off-by: Randy Dunlap <rdunlap@xenotime.net>
Cc:	Alexander Viro <viro@zeniv.linux.org.uk>
Cc:	linux-fsdevel@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

As soon as we'd installed the file into descriptor table, it can
get closed by another thread.  Freeing ep in process...
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

It's not critical (anymore) since another thread closing the file will block
on ->device_lock before it gets to dropping the final reference, but it's
definitely cleaner that way...
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

we really need to make sure that dropping the last reference happens
under the group->device_lock; otherwise a loop (under device_lock)
might find vfio_device instance that is being freed right now, has
already dropped the last reference and waits on device_lock to exclude
the sucker from the list.
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

equivalent of
	mutex_lock(mutex);
	if (!kref_put(kref, release))
		mutex_unlock(mutex);
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

So we've had a fair few reports of fbcon handover breakage between
efi/vesafb and i915 surface recently, so I dedicated a couple of
days to finding the problem.

Essentially the last thing we saw was the conflicting framebuffer
message and that was all.

So after much tracing with direct netconsole writes (printks
under console_lock not so useful), I think I found the race.

Thread A (driver load)    Thread B (timer thread)
  unbind_con_driver ->              |
  bind_con_driver ->                |
  vc->vc_sw->con_deinit ->          |
  fbcon_deinit ->                   |
  console_lock()                    |
      |                             |
      |                       fbcon_flashcursor timer fires
      |                       console_lock() <- blocked for A
      |
      |
fbcon_del_cursor_timer ->
  del_timer_sync
  (BOOM)

Of course because all of this is under the console lock,
we never see anything, also since we also just unbound the active
console guess what we never see anything.

Hopefully this fixes the problem for anyone seeing vesafb->kms
driver handoff.

v1.1: add comment suggestion from Alan.

Cc: stable@vger.kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>

Merge fixes from Andrew Morton.

Random drivers and some VM fixes.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (17 commits)
  mm: compaction: Abort async compaction if locks are contended or taking too long
  mm: have order > 0 compaction start near a pageblock with free pages
  rapidio/tsi721: fix unused variable compiler warning
  rapidio/tsi721: fix inbound doorbell interrupt handling
  drivers/rtc/rtc-rs5c348.c: fix hour decoding in 12-hour mode
  mm: correct page->pfmemalloc to fix deactivate_slab regression
  drivers/rtc/rtc-pcf2123.c: initialize dynamic sysfs attributes
  mm/compaction.c: fix deferring compaction mistake
  drivers/misc/sgi-xp/xpc_uv.c: SGI XPC fails to load when cpu 0 is out of IRQ resources
  string: do not export memweight() to userspace
  hugetlb: update hugetlbpage.txt
  checkpatch: add control statement test to SINGLE_STATEMENT_DO_WHILE_MACRO
  mm: hugetlbfs: correctly populate shared pmd
  cciss: fix incorrect scsi status reporting
  Documentation: update mount option in filesystem/vfat.txt
  mm: change nr_ptes BUG_ON to WARN_ON
  cs5535-clockevt: typo, it's MFGPT, not MFPGT

Pull media fixes from Mauro Carvalho Chehab:
 "For bug fixes, at soc_camera, si470x, uvcvideo, iguanaworks IR driver,
  radio_shark Kbuild fixes, and at the V4L2 core (radio fixes)."

* 'v4l_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-media:
  [media] media: soc_camera: don't clear pix->sizeimage in JPEG mode
  [media] media: mx2_camera: Fix clock handling for i.MX27
  [media] video: mx2_camera: Use clk_prepare_enable/clk_disable_unprepare
  [media] video: mx1_camera: Use clk_prepare_enable/clk_disable_unprepare
  [media] media: mx3_camera: buf_init() add buffer state check
  [media] radio-shark2: Only compile led support when CONFIG_LED_CLASS is set
  [media] radio-shark: Only compile led support when CONFIG_LED_CLASS is set
  [media] radio-shark*: Call cancel_work_sync from disconnect rather then release
  [media] radio-shark*: Remove work-around for dangling pointer in usb intfdata
  [media] Add USB dependency for IguanaWorks USB IR Transceiver
  [media] Add missing logging for rangelow/high of hwseek
  [media] VIDIOC_ENUM_FREQ_BANDS fix
  [media] mem2mem_testdev: fix querycap regression
  [media] si470x: v4l2-compliance fixes
  [media] DocBook: Remove a spurious character
  [media] uvcvideo: Reset the bytesused field when recycling an erroneous buffer

Pull networking update from David Miller:
 "A couple weeks of bug fixing in there.  The largest chunk is all the
  broken crap Amerigo Wang found in the netpoll layer."

 1) netpoll and it's users has several serious bugs:
    a) uses GFP_KERNEL with locks held
    b) interfaces requiring interrupts disabled are called with them
       enabled
    c) and vice versa
    d) VLAN tag demuxing, as per all other RX packet input paths, is not
       applied

    All from Amerigo Wang.

 2) Hopefully cure the ipv4 mapped ipv6 address TCP early demux bugs for
    good, from Neal Cardwell.

 3) Unlike AF_UNIX, AF_PACKET sockets don't set a default credentials
    when the user doesn't specify one explicitly during sendmsg().
    Instead we attach an empty (zero) SCM credential block which is
    definitely not what we want.  Fix from Eric Dumazet.

 4) IPv6 illegally invokes netdevice notifiers with RCU lock held, fix
    from Ben Hutchings.

 5) inet_csk_route_child_sock() checks wrong inet options pointer, fix
    from Christoph Paasch.

 6) When AF_PACKET is used for transmit, packet loopback doesn't behave
    properly when a socket fanout is enabled, from Eric Leblond.

 7) On bluetooth l2cap channel create failure, we leak the socket, from
    Jaganath Kanakkassery.

 8) Fix all the netprio file handling bugs found by Al Viro, from John
    Fastabend.

 9) Several error return and NULL deref bug fixes in networking drivers
    from Julia Lawall.

10) A large smattering of struct padding et al.  kernel memory leaks to
    userspace found of Mathias Krause.

11) Conntrack expections in netfilter can access an uninitialized timer,
    fix from Pablo Neira Ayuso.

12) Several netfilter SIP tracker bug fixes from Patrick McHardy.

13) IPSEC ipv6 routes are not initialized correctly all the time,
    resulting in an OOPS in inet_putpeer().  Also from Patrick McHardy.

14) Bridging does rcu_dereference() outside of RCU protected area, from
    Stephen Hemminger.

15) Fix routing cache removal performance regression when looking up
    output routes that have a local destination.  From Zheng Yan.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (87 commits)
  af_netlink: force credentials passing [CVE-2012-3520]
  ipv4: fix ip header ident selection in __ip_make_skb()
  ipv4: Use newinet->inet_opt in inet_csk_route_child_sock()
  tcp: fix possible socket refcount problem
  net: tcp: move sk_rx_dst_set call after tcp_create_openreq_child()
  net/core/dev.c: fix kernel-doc warning
  netconsole: remove a redundant netconsole_target_put()
  net: ipv6: fix oops in inet_putpeer()
  net/stmmac: fix issue of clk_get for Loongson1B.
  caif: Do not dereference NULL in chnl_recv_cb()
  af_packet: don't emit packet on orig fanout group
  drivers/net/irda: fix error return code
  drivers/net/wan/dscc4.c: fix error return code
  drivers/net/wimax/i2400m/fw.c: fix error return code
  smsc75xx: add missing entry to MAINTAINERS
  net: qmi_wwan: new devices: UML290 and K5006-Z
  net: sh_eth: Add eth support for R8A7779 device
  netdev/phy: skip disabled mdio-mux nodes
  dt: introduce for_each_available_child_of_node, of_get_next_available_child
  net: netprio: fix cgrp create and write priomap race
  ...

Jim Schutt reported a problem that pointed at compaction contending
heavily on locks.  The workload is straight-forward and in his own words;

	The systems in question have 24 SAS drives spread across 3 HBAs,
	running 24 Ceph OSD instances, one per drive.  FWIW these servers
	are dual-socket Intel 5675 Xeons w/48 GB memory.  I've got ~160
	Ceph Linux clients doing dd simultaneously to a Ceph file system
	backed by 12 of these servers.

Early in the test everything looks fine

  procs -------------------memory------------------ ---swap-- -----io---- --system-- -----cpu-------
   r  b       swpd       free       buff      cache   si   so    bi    bo   in   cs  us sy  id wa st
  31 15          0     287216        576   38606628    0    0     2  1158    2   14   1  3  95  0  0
  27 15          0     225288        576   38583384    0    0    18 2222016 203357 134876  11 56  17 15  0
  28 17          0     219256        576   38544736    0    0    11 2305932 203141 146296  11 49  23 17  0
   6 18          0     215596        576   38552872    0    0     7 2363207 215264 166502  12 45  22 20  0
  22 18          0     226984        576   38596404    0    0     3 2445741 223114 179527  12 43  23 22  0

and then it goes to pot

  procs -------------------memory------------------ ---swap-- -----io---- --system-- -----cpu-------
   r  b       swpd       free       buff      cache   si   so    bi    bo   in   cs  us sy  id wa st
  163  8          0     464308        576   36791368    0    0    11 22210  866  536   3 13  79  4  0
  207 14          0     917752        576   36181928    0    0   712 1345376 134598 47367   7 90   1  2  0
  123 12          0     685516        576   36296148    0    0   429 1386615 158494 60077   8 84   5  3  0
  123 12          0     598572        576   36333728    0    0  1107 1233281 147542 62351   7 84   5  4  0
  622  7          0     660768        576   36118264    0    0   557 1345548 151394 59353   7 85   4  3  0
  223 11          0     283960        576   36463868    0    0    46 1107160 121846 33006   6 93   1  1  0

Note that system CPU usage is very high blocks being written out has
dropped by 42%. He analysed this with perf and found

  perf record -g -a sleep 10
  perf report --sort symbol --call-graph fractal,5
    34.63%  [k] _raw_spin_lock_irqsave
            |
            |--97.30%-- isolate_freepages
            |          compaction_alloc
            |          unmap_and_move
            |          migrate_pages
            |          compact_zone
            |          compact_zone_order
            |          try_to_compact_pages
            |          __alloc_pages_direct_compact
            |          __alloc_pages_slowpath
            |          __alloc_pages_nodemask
            |          alloc_pages_vma
            |          do_huge_pmd_anonymous_page
            |          handle_mm_fault
            |          do_page_fault
            |          page_fault
            |          |
            |          |--87.39%-- skb_copy_datagram_iovec
            |          |          tcp_recvmsg
            |          |          inet_recvmsg
            |          |          sock_recvmsg
            |          |          sys_recvfrom
            |          |          system_call
            |          |          __recv
            |          |          |
            |          |           --100.00%-- (nil)
            |          |
            |           --12.61%-- memcpy
             --2.70%-- [...]

There was other data but primarily it is all showing that compaction is
contended heavily on the zone->lock and zone->lru_lock.

commit [b2eef8c0: mm: compaction: minimise the time IRQs are disabled
while isolating pages for migration] noted that it was possible for
migration to hold the lru_lock for an excessive amount of time. Very
broadly speaking this patch expands the concept.

This patch introduces compact_checklock_irqsave() to check if a lock
is contended or the process needs to be scheduled. If either condition
is true then async compaction is aborted and the caller is informed.
The page allocator will fail a THP allocation if compaction failed due
to contention. This patch also introduces compact_trylock_irqsave()
which will acquire the lock only if it is not contended and the process
does not need to schedule.
Reported-by: Jim Schutt <jaschut@sandia.gov>
Tested-by: Jim Schutt <jaschut@sandia.gov>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Commit 7db8889a ("mm: have order > 0 compaction start off where it
left") introduced a caching mechanism to reduce the amount work the free
page scanner does in compaction.  However, it has a problem.  Consider
two process simultaneously scanning free pages

					    			C
	Process A		M     S     			F
			|---------------------------------------|
	Process B		M 	FS

	C is zone->compact_cached_free_pfn
	S is cc->start_pfree_pfn
	M is cc->migrate_pfn
	F is cc->free_pfn

In this diagram, Process A has just reached its migrate scanner, wrapped
around and updated compact_cached_free_pfn accordingly.

Simultaneously, Process B finishes isolating in a block and updates
compact_cached_free_pfn again to the location of its free scanner.

Process A moves to "end_of_zone - one_pageblock" and runs this check

                if (cc->order > 0 && (!cc->wrapped ||
                                      zone->compact_cached_free_pfn >
                                      cc->start_free_pfn))
                        pfn = min(pfn, zone->compact_cached_free_pfn);

compact_cached_free_pfn is above where it started so the free scanner
skips almost the entire space it should have scanned.  When there are
multiple processes compacting it can end in a situation where the entire
zone is not being scanned at all.  Further, it is possible for two
processes to ping-pong update to compact_cached_free_pfn which is just
random.

Overall, the end result wrecks allocation success rates.

There is not an obvious way around this problem without introducing new
locking and state so this patch takes a different approach.

First, it gets rid of the skip logic because it's not clear that it
matters if two free scanners happen to be in the same block but with
racing updates it's too easy for it to skip over blocks it should not.

Second, it updates compact_cached_free_pfn in a more limited set of
circumstances.

If a scanner has wrapped, it updates compact_cached_free_pfn to the end
	of the zone. When a wrapped scanner isolates a page, it updates
	compact_cached_free_pfn to point to the highest pageblock it
	can isolate pages from.

If a scanner has not wrapped when it has finished isolated pages it
	checks if compact_cached_free_pfn is pointing to the end of the
	zone. If so, the value is updated to point to the highest
	pageblock that pages were isolated from. This value will not
	be updated again until a free page scanner wraps and resets
	compact_cached_free_pfn.

This is not optimal and it can still race but the compact_cached_free_pfn
will be pointing to or very near a pageblock with free pages.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>