GitHub/moto-9609/android_kernel_motorola_exynos9610.git
10 years agonetfilter: don't use mutex_lock_interruptible()
Pablo Neira Ayuso [Thu, 31 Jul 2014 18:38:46 +0000 (20:38 +0200)]
netfilter: don't use mutex_lock_interruptible()

Eric Dumazet reports that getsockopt() or setsockopt() sometimes
returns -EINTR instead of -ENOPROTOOPT, causing headaches to
application developers.

This patch replaces all the mutex_lock_interruptible() by mutex_lock()
in the netfilter tree, as there is no reason we should sleep for a
long time there.

Reported-by: Eric Dumazet <edumazet@google.com>
Suggested-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Julian Anastasov <ja@ssi.bg>
10 years agonetfilter: nf_tables: don't update chain with unset counters
Pablo Neira Ayuso [Tue, 5 Aug 2014 15:25:59 +0000 (17:25 +0200)]
netfilter: nf_tables: don't update chain with unset counters

Fix possible replacement of the per-cpu chain counters by null
pointer when updating an existing chain in the commit path.

Reported-by: Matteo Croce <technoboy85@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
10 years agonetfilter: nf_tables: uninitialize element key/data from the commit path
Pablo Neira Ayuso [Fri, 1 Aug 2014 17:32:41 +0000 (19:32 +0200)]
netfilter: nf_tables: uninitialize element key/data from the commit path

This should happen once the element has been effectively released in
the commit path, not before. This fixes a possible chain refcount leak
if the transaction is aborted.

Reported-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
10 years agoMerge branch 'akpm' (patchbomb from Andrew Morton)
Linus Torvalds [Thu, 7 Aug 2014 04:14:42 +0000 (21:14 -0700)]
Merge branch 'akpm' (patchbomb from Andrew Morton)

Merge incoming from Andrew Morton:
 - Various misc things.
 - arch/sh updates.
 - Part of ocfs2.  Review is slow.
 - Slab updates.
 - Most of -mm.
 - printk updates.
 - lib/ updates.
 - checkpatch updates.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (226 commits)
  checkpatch: update $declaration_macros, add uninitialized_var
  checkpatch: warn on missing spaces in broken up quoted
  checkpatch: fix false positives for --strict "space after cast" test
  checkpatch: fix false positive MISSING_BREAK warnings with --file
  checkpatch: add test for native c90 types in unusual order
  checkpatch: add signed generic types
  checkpatch: add short int to c variable types
  checkpatch: add for_each tests to indentation and brace tests
  checkpatch: fix brace style misuses of else and while
  checkpatch: add --fix option for a couple OPEN_BRACE misuses
  checkpatch: use the correct indentation for which()
  checkpatch: add fix_insert_line and fix_delete_line helpers
  checkpatch: add ability to insert and delete lines to patch/file
  checkpatch: add an index variable for fixed lines
  checkpatch: warn on break after goto or return with same tab indentation
  checkpatch: emit a warning on file add/move/delete
  checkpatch: add test for commit id formatting style in commit log
  checkpatch: emit fewer kmalloc_array/kcalloc conversion warnings
  checkpatch: improve "no space after cast" test
  checkpatch: allow multiple const * types
  ...

10 years agoMerge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Linus Torvalds [Thu, 7 Aug 2014 04:06:02 +0000 (21:06 -0700)]
Merge git://git./linux/kernel/git/davem/net

Pull networking fixes from David Miller:
 "This fixes the most immediate fallout from yesterday's networking
  merge:

   1) sock_tx_timestamp() must not clear the passed in tx_flags, but
      rather add to them.  Fix from Eric Dumazet.

   2) The hyperv driver sendbuf region increase needs to be decreased
      slightly to handle older backends.  From KY Srinivasan.

   3) Fix RCU lockdep splats in netlink diag after recent hashing
      changes, from Thomas Graf.

   4) The new IPV6_FLOWLABEL was given a socket option number that
      overlapped with an existing IP6 tables one, breaking ip6_tables.
      Fixed by Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  netlink: hold nl_sock_hash_lock during diag dump
  tcp: md5: check md5 signature without socket lock
  net: fix USB network driver config option.
  net: reallocate new socket option number for IPV6_AUTOFLOWLABEL
  vmxnet3: fix decimal printf format specifiers prefixed with 0x
  net-timestamp: cumulative tcp timestamping fixes
  hyperv: Adjust the size of sendbuf region to support ws2008r2
  cxgb4: Fix for SR-IOV VF initialization
  net-timestamp: sock_tx_timestamp() fix

10 years agoMerge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial
Linus Torvalds [Thu, 7 Aug 2014 04:03:53 +0000 (21:03 -0700)]
Merge branch 'for-linus' of git://git./linux/kernel/git/jikos/trivial

Pull trivial tree changes from Jiri Kosina:
 "Summer edition of trivial tree updates"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial: (23 commits)
  doc: fix two typos in watchdog-api.txt
  irq-gic: remove file name from heading comment
  MAINTAINERS: Add miscdevice.h to file list for char/misc drivers.
  scsi: mvsas: mv_sas.c: Fix for possible null pointer dereference
  doc: replace "practise" with "practice" in Documentation
  befs: remove check for CONFIG_BEFS_RW
  scsi: doc: fix 'SCSI_NCR_SETUP_MASTER_PARITY'
  drivers/usb/phy/phy.c: remove a leading space
  mfd: fix comment
  cpuidle: fix comment
  doc: hpfall.c: fix missing null-terminate after strncpy call
  usb: doc: hotplug.txt code typos
  kbuild: fix comment in Makefile.modinst
  SH: add proper prompt to SH_MAGIC_PANEL_R2_VERSION
  ARM: msm: Remove MSM_SCM
  crypto: Remove MPILIB_EXTRA
  doc: CN: remove dead link, kerneltrap.org no longer works
  media: update reference, kerneltrap.org no longer works
  hexagon: update reference, kerneltrap.org no longer works
  doc: LSM: update reference, kerneltrap.org no longer works
  ...

10 years agoMerge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid
Linus Torvalds [Thu, 7 Aug 2014 03:56:28 +0000 (20:56 -0700)]
Merge branch 'for-linus' of git://git./linux/kernel/git/jikos/hid

Pull HID updates from Jiri Kosina:
 "Some highlights:

   - hid-sony improvements of Sixaxis device support by Antonio Ospite
   - hid-hyperv driven devices can now be used as wakeup source, by
     Dexuan Cui
   - hid-lenovo driver is now more generic and supports more devices, by
     Jamie Lentin
   - hid-huion now supports wider range of tablets, by Nikolai
     Kondrashov
   - other various unsorted fixes and device ID additions"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid: (30 commits)
  HID: hyperv: register as a wakeup source
  HID: sony: Default initialize all elements of the LED max_brightness array to 1
  HID: huion: Fix sparse warnings
  HID: usbhid: Use flag HID_DISCONNECTED when a usb device is removed
  HID: ignore jabra gn9350e
  HID: cp2112: add I2C mode
  HID: use multi input quirk for 22b9:2968
  HID: rmi: only bind the hid-rmi driver to the mouse interface of composite USB devices
  HID: rmi: check that report ids exist in the report_id_hash before accessing their size
  HID: lenovo: Add support for Compact (BT|USB) keyboard
  HID: lenovo: Don't call function in condition, show error codes
  HID: lenovo: Prepare support for adding other devices
  HID: lenovo: Rename hid-lenovo-tpkbd to hid-lenovo
  HID: huion: Handle tablets with UC-Logic vendor ID
  HID: huion: Switch to generating report descriptor
  HID: huion: Don't ignore other interfaces
  HID: huion: Use "tablet" instead of specific model
  HID: add quirk for 0x04d9:0xa096 device
  HID: i2c-hid: call the hid driver's suspend and resume callbacks
  HID: rmi: change logging level of log messages related to unexpected reports
  ...

10 years agoMerge git://www.linux-watchdog.org/linux-watchdog
Linus Torvalds [Thu, 7 Aug 2014 03:54:47 +0000 (20:54 -0700)]
Merge git://www.linux-watchdog.org/linux-watchdog

Pull watchdog updates from Wim Van Sebroeck:
 - remove unnecessary checks after platform_get_resource()
 - fix watchdog api documentation typo's
 - imx2_wdt: adds big endianness support
 - move restart code to the sunxi watchdog driver

* git://www.linux-watchdog.org/linux-watchdog:
  wdt: sunxi: Move restart code to the watchdog driver
  Documentation: fix two typos in watchdog-api.txt
  watchdog: imx2_wdt: adds big endianness support.
  watchdog: shwdt: Remove the unnecessary check of resource after platform_get_resource()
  watchdog: lantiq_wdt: Remove the un-necessary check of resource after platform_get_resource()
  watchdog: dw_wdt: Remove the un-necessary check after platform_get_resource()

10 years agoMerge tag 'pm+acpi-3.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael...
Linus Torvalds [Thu, 7 Aug 2014 03:34:19 +0000 (20:34 -0700)]
Merge tag 'pm+acpi-3.17-rc1' of git://git./linux/kernel/git/rafael/linux-pm

Pull ACPI and power management updates from Rafael Wysocki:
 "Again, ACPICA leads the pack (47 commits), followed by cpufreq (18
  commits) and system suspend/hibernation (9 commits).

  From the new code perspective, the ACPICA update brings ACPI 5.1 to
  the table, including a new device configuration object called _DSD
  (Device Specific Data) that will hopefully help us to operate device
  properties like Device Trees do (at least to some extent) and changes
  related to supporting ACPI on ARM.

  Apart from that we have hibernation changes making it use radix trees
  to store memory bitmaps which should speed up some operations carried
  out by it quite significantly.  We also have some power management
  changes related to suspend-to-idle (the "freeze" sleep state) support
  and more preliminary changes needed to support ACPI on ARM (outside of
  ACPICA).

  The rest is fixes and cleanups pretty much everywhere.

  Specifics:

   - ACPICA update to upstream version 20140724.  That includes ACPI 5.1
     material (support for the _CCA and _DSD predefined names, changes
     related to the DMAR and PCCT tables and ARM support among other
     things) and cleanups related to using ACPICA's header files.  A
     major part of it is related to acpidump and the core code used by
     that utility.  Changes from Bob Moore, David E Box, Lv Zheng,
     Sascha Wildner, Tomasz Nowicki, Hanjun Guo.

   - Radix trees for memory bitmaps used by the hibernation core from
     Joerg Roedel.

   - Support for waking up the system from suspend-to-idle (also known
     as the "freeze" sleep state) using ACPI-based PCI wakeup signaling
     (Rafael J Wysocki).

   - Fixes for issues related to ACPI button events (Rafael J Wysocki).

   - New device ID for an ACPI-enumerated device included into the
     Wildcat Point PCH from Jie Yang.

   - ACPI video updates related to backlight handling from Hans de Goede
     and Linus Torvalds.

   - Preliminary changes needed to support ACPI on ARM from Hanjun Guo
     and Graeme Gregory.

   - ACPI PNP core cleanups from Arjun Sreedharan and Zhang Rui.

   - Cleanups related to ACPI_COMPANION() and ACPI_HANDLE() macros
     (Rafael J Wysocki).

   - ACPI-based device hotplug cleanups from Wei Yongjun and Rafael J
     Wysocki.

   - Cleanups and improvements related to system suspend from Lan
     Tianyu, Randy Dunlap and Rafael J Wysocki.

   - ACPI battery cleanup from Wei Yongjun.

   - cpufreq core fixes from Viresh Kumar.

   - Elimination of a deadband effect from the cpufreq ondemand governor
     and intel_pstate driver cleanups from Stratos Karafotis.

   - 350MHz CPU support for the powernow-k6 cpufreq driver from Mikulas
     Patocka.

   - Fix for the imx6 cpufreq driver from Anson Huang.

   - cpuidle core and governor cleanups from Daniel Lezcano, Sandeep
     Tripathy and Mohammad Merajul Islam Molla.

   - Build fix for the big_little cpuidle driver from Sachin Kamat.

   - Configuration fix for the Operation Performance Points (OPP)
     framework from Mark Brown.

   - APM cleanup from Jean Delvare.

   - cpupower utility fixes and cleanups from Peter Senna Tschudin,
     Andrey Utkin, Himangi Saraogi, Rickard Strandqvist, Thomas
     Renninger"

* tag 'pm+acpi-3.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (118 commits)
  ACPI / LPSS: add LPSS device for Wildcat Point PCH
  ACPI / PNP: Replace faulty is_hex_digit() by isxdigit()
  ACPICA: Update version to 20140724.
  ACPICA: ACPI 5.1: Update for PCCT table changes.
  ACPICA/ARM: ACPI 5.1: Update for GTDT table changes.
  ACPICA/ARM: ACPI 5.1: Update for MADT changes.
  ACPICA/ARM: ACPI 5.1: Update for FADT changes.
  ACPICA: ACPI 5.1: Support for the _CCA predifined name.
  ACPICA: ACPI 5.1: New notify value for System Affinity Update.
  ACPICA: ACPI 5.1: Support for the _DSD predefined name.
  ACPICA: Debug object: Add current value of Timer() to debug line prefix.
  ACPICA: acpihelp: Add UUID support, restructure some existing files.
  ACPICA: Utilities: Fix local printf issue.
  ACPICA: Tables: Update for DMAR table changes.
  ACPICA: Remove some extraneous printf arguments.
  ACPICA: Update for comments/formatting. No functional changes.
  ACPICA: Disassembler: Add support for the ToUUID opererator (macro).
  ACPICA: Remove a redundant cast to acpi_size for ACPI_OFFSET() macro.
  ACPICA: Work around an ancient GCC bug.
  ACPI / processor: Make it possible to get local x2apic id via _MAT
  ...

10 years agoMerge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi
Linus Torvalds [Thu, 7 Aug 2014 03:10:32 +0000 (20:10 -0700)]
Merge tag 'scsi-misc' of git://git./linux/kernel/git/jejb/scsi

Pull SCSI updates from James Bottomley:
 "This patch set consists of the usual driver updates (ufs, storvsc,
  pm8001 hpsa).  It also has removal of the user space target driver
  code (everyone is using LIO now), a partial PCI MSI-X update, more
  multi-queue updates, conversion to 64 bit LUNs (so we could
  theoretically cope with any LUN returned by a device) and placeholder
  support for the ZBC device type (Shingle drives), plus an assortment
  of minor updates and bug fixes"

* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (143 commits)
  scsi: do not issue SCSI RSOC command to Promise Vtrak E610f
  vmw_pvscsi: Use pci_enable_msix_exact() instead of pci_enable_msix()
  pm8001: Fix invalid return when request_irq() failed
  lpfc: Remove superfluous call to pci_disable_msix()
  isci: Use pci_enable_msix_exact() instead of pci_enable_msix()
  bfa: Use pci_enable_msix_exact() instead of pci_enable_msix()
  bfa: Cleanup bfad_setup_intr() function
  bfa: Do not call pci_enable_msix() after it failed once
  fnic: Use pci_enable_msix_exact() instead of pci_enable_msix()
  scsi: use short driver name for per-driver cmd slab caches
  scsi_debug: support scsi-mq, queues and locks
  Drivers: add blist flags
  scsi: ufs: fix endianness sparse warnings
  scsi: ufs: make undeclared functions static
  bnx2i: Update driver version to 2.7.10.1
  pm8001: fix a memory leak in nvmd_resp
  pm8001: fix update_flash
  pm8001: fix a memory leak in flash_update
  pm8001: Cleaning up uninitialized variables
  pm8001: Fix to remove null pointer checks that could never happen
  ...

10 years agoMerge tag 'sound-3.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai...
Linus Torvalds [Thu, 7 Aug 2014 03:07:24 +0000 (20:07 -0700)]
Merge tag 'sound-3.17-rc1' of git://git./linux/kernel/git/tiwai/sound

Pull sound updates from Takashi Iwai:
 "There've been many updates in ASoC side at this time, especially the
  framework enhancement for multiple CODECs on a single DAI and more
  componentization works.

  The only major change in ALSA core is the addition of timestamp type
  in sw_params field.  This should behave in backward compatible way.

  Other than that, there are lots of small changes and new drivers in
  wide range, including a large code cut in HD-audio driver for
  deprecated static quirks.  Some highlights are below:

  ALSA Core:
   - Add the new timestamp type field to sw_params to choose
     MONOTONIC_RAW type

  HD-audio:
   - Continued conversion to standard printk macros, generic code
     cleanups
   - Removal of obsoleted static quirk codes for Conexant and C-Media
     codecs
   - Fixups for HP Envy TS, Dell XPS 15, HP and Dell mute/mic LED,
     Gigabyte BXBT-2807 mobo
   - Intel Braswell support

  ASoC:
   - Support for multiple CODECs attached to a single DAI, enabling
     systems with for example multiple DAC/speaker drivers on a single
     link, contributed by Benoit Cousson based on work from Misael Lopez
     Cruz
   - Support for byte controls larger than 256 bytes based on the use of
     TLVs contributed by Omair Mohammed Abdullah
   - More componentisation work from Lars-Peter Clausen
   - The remainder of the conversions of CODEC drivers to params_width()
     by Mark Brown
   - Drivers for Cirrus Logic CS4265, Freescale i.MX ASRC blocks,
     Realtek RT286 and RT5670, Rockchip RK3xxx I2S controllers and Texas
     Instruments TAS2552
   - Lots of updates and fixes, especially to the DaVinci, Intel,
     Freescale, Realtek, and rcar drivers"

* tag 'sound-3.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound: (402 commits)
  ALSA: usb-audio: Whitespace cleanups for sound/usb/midi.*
  ALSA: usb-audio: Respond to suspend and resume callbacks for MIDI input
  sound/oss/pss: Remove typedefs pss_mixerdata and pss_confdata
  sound/oss/opl3: Remove typedef opl_devinfo
  ALSA: fireworks: fix specifiers in format strings for propper output
  ASoC: imx-audmux: Use uintptr_t for port numbers
  ASoC: davinci: Enable menuconfig entry for McASP
  ASoC: fsl_asrc: Don't access members of config before checking it
  ASoC: fsl_sarc_dma: Check pair before using it
  ASoC: adau1977: Fix truncation warning on 64 bit architectures
  ALSA: virtuoso: add Xonar Essence STX II support
  ALSA: riptide: fix %d confusingly prefixed with 0x in format strings
  ALSA: fireworks: fix %d confusingly prefixed with 0x in format strings
  ALSA: hda - add codec ID for Braswell display audio codec
  ALSA: hda - add PCI IDs for Intel Braswell
  ALSA: usb-audio: Adjust Gamecom 780 volume level
  ALSA: usb-audio: improve dmesg source grepability
  ASoC: rt5670: Fix duplicate const warnings
  ASoC: rt5670: Staticise non-exported symbols
  ASoC: Intel: update stream only on stream IPC msgs
  ...

10 years agoMerge tag 'hsi-for-3.17' of git://git.kernel.org/pub/scm/linux/kernel/git/sre/linux-hsi
Linus Torvalds [Thu, 7 Aug 2014 03:06:14 +0000 (20:06 -0700)]
Merge tag 'hsi-for-3.17' of git://git./linux/kernel/git/sre/linux-hsi

Pull HSI changes from Sebastian Reichel:
 "Misc fixes in SSI related drivers"

* tag 'hsi-for-3.17' of git://git.kernel.org/pub/scm/linux/kernel/git/sre/linux-hsi:
  HSI: omap_ssi: Fix return value check in ssi_debug_add_ctrl()
  HSI: omap_ssi_port: Fix return value check in ssi_debug_add_port()
  HSI: ssi_protocol: Fix sparse non static symbol warning
  drivers/hsi/controllers/omap_ssi{,_port}.c: fix failure checks

10 years agoMerge tag 'for-v3.17' of git://git.infradead.org/battery-2.6
Linus Torvalds [Thu, 7 Aug 2014 03:05:34 +0000 (20:05 -0700)]
Merge tag 'for-v3.17' of git://git.infradead.org/battery-2.6

Pull power supply changes from Sebastian Reichel:
 - Added iPaq h3xxx battery driver
 - Added Broadcom STB reset driver
 - DT support for rx51-battery
 - misc. fixes

* tag 'for-v3.17' of git://git.infradead.org/battery-2.6:
  ipaq_micro_battery: fix sparse non static symbol warning
  power: add driver for battery reading on iPaq h3xxx
  power: twl4030_charger: detect battery presence prior to enabling charger
  power: reset: Add reboot driver for brcmstb
  power_supply: Fix sparse non static symbol warning
  power_supply: Add inlmt,iterm, min/max temp props
  charger: tps65090: Allow charger module to be used when no irq
  power/reset: Fix GPL v2 license string typo
  power: poweroff: gpio: convert to use descriptors
  bq27000: report missing device better.
  bq27x00_battery: Introduce the use of the managed version of kzalloc
  Documentation: DT: Document rx51-battery binding
  rx51_battery: convert to iio consumer
  bq2415x_charger: Fix Atomic Sleep Bug

10 years agonetlink: hold nl_sock_hash_lock during diag dump
Thomas Graf [Wed, 6 Aug 2014 23:18:47 +0000 (00:18 +0100)]
netlink: hold nl_sock_hash_lock during diag dump

Although RCU protection would be possible during diag dump, doing
so allows for concurrent table mutations which can render the
in-table offset between individual Netlink messages invalid and
thus cause legitimate sockets to be skipped in the dump.

Since the diag dump is relatively low volume and consistency is
more important than performance, the table mutex is held during
dump.

Reported-by: Andrey Wagin <avagin@gmail.com>
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Fixes: e341694e3eb57fc ("netlink: Convert netlink_lookup() to use RCU protected hash table")
Signed-off-by: David S. Miller <davem@davemloft.net>
10 years agocheckpatch: update $declaration_macros, add uninitialized_var
Joe Perches [Wed, 6 Aug 2014 23:11:31 +0000 (16:11 -0700)]
checkpatch: update $declaration_macros, add uninitialized_var

Using uninitialized_var reports a false positive for "Missing blank line
after declarations".

Fix it by adding uninitialized_var to the $declaration_macros exceptions
list.

Move the macro list after $Type is declared.

Add optional prefixes to DECLARE_<FOO> and DEFINE_<BAR>
macro declarations to allow forms like:
MLX4_DECLARE_DOORBELL_LOCK

Signed-off-by: Joe Perches <joe@perches.com>
Reported-by: Dotan Barak <dotanb@mellanox.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: warn on missing spaces in broken up quoted
Dan Carpenter [Wed, 6 Aug 2014 23:11:29 +0000 (16:11 -0700)]
checkpatch: warn on missing spaces in broken up quoted

Checkpatch already complains when people break up quoted strings but
it's still pretty common.  One mistake that people often make is they
leave out the space character between the two strings.

This check adds around 450 new warnings and has a low rate of false
positives.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Andy Whitcroft <apw@canonical.com>
Acked-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: fix false positives for --strict "space after cast" test
Joe Perches [Wed, 6 Aug 2014 23:11:27 +0000 (16:11 -0700)]
checkpatch: fix false positives for --strict "space after cast" test

Commit 89da401f6cff ("checkpatch: improve "no space after cast" test")
in -next improved the cast test for non pointer types, but also
introduced false positives for some types of static inlines.

Add a test for an open brace to the exclusions to avoid these false
positives.

Signed-off-by: Joe Perches <joe@perches.com>
Reported-by: Hartley Sweeten <HartleyS@visionengravers.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: fix false positive MISSING_BREAK warnings with --file
Joe Perches [Wed, 6 Aug 2014 23:11:25 +0000 (16:11 -0700)]
checkpatch: fix false positive MISSING_BREAK warnings with --file

Using --file mode can give false positives with MISSING_BREAK
fall-through warnings on simple but long multiple consecutive case
statements.

Look for all lines before a case statement for a switch or a statement
when using --file mode.

Fix a misspelling of preceded while there.

Signed-off-by: Joe Perches <joe@perches.com>
Reported-by: Lee Jones <lee.jones@linaro.org>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: add test for native c90 types in unusual order
Joe Perches [Wed, 6 Aug 2014 23:11:22 +0000 (16:11 -0700)]
checkpatch: add test for native c90 types in unusual order

c90 section "6.7.2 Type Specifiers" says:
    "type specifiers may occur in any order"

That means that:
    short int is the same as int short
    unsigned short int is the same as int unsigned short
    etc...

checkpatch currently parses only a subset of these allowed types.

For instance: "unsigned short" and "signed short" are found by
checkpatch as a specific type, but none of the or "int short" or "int
signed short" variants are found.

Add another table for the "kernel style misordered" variants.

Add this misordered table to the findable types.

Warn when the misordered style is used.

This improves the "Missing a blank line after declarations" test as it
depends on the correct parsing of the $Declare variable which looks for
"$Type $Ident;" (ie: declarations like "int foo;").

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Andy Whitcroft <apw@canonical.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: add signed generic types
Joe Perches [Wed, 6 Aug 2014 23:11:20 +0000 (16:11 -0700)]
checkpatch: add signed generic types

Current generic types are unsigned or unspecified.  Add signed to the
types.

Reorder the types to find the longest match first.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Andy Whitcroft <apw@canonical.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: add short int to c variable types
Joe Perches [Wed, 6 Aug 2014 23:11:18 +0000 (16:11 -0700)]
checkpatch: add short int to c variable types

short int is one of the 6.7.2 c90 types.
Find it appropriately.

This fixes a defect in checkpatch where it suggests that a line break
after declaration is required using an input like:

int foo;
short int bar;

Without this change, it warns on the short int line.

Signed-off-by: Joe Perches <joe@perches.com>
Reported-by: Hartley Sweeten <HartleyS@visionengravers.com>
Acked-by: Andy Whitcroft <apw@canonical.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: add for_each tests to indentation and brace tests
Joe Perches [Wed, 6 Aug 2014 23:11:16 +0000 (16:11 -0700)]
checkpatch: add for_each tests to indentation and brace tests

All the various for_each loop macros were not tested for trailing brace
on the following lines and for bad indentation.

Add them.

Signed-off-by: Joe Perches <joe@perches.com>
Reported-by: Greg KH <gregkh@linuxfoundation.org>
Cc: Andy Whitcroft <apw@canonical.com
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: fix brace style misuses of else and while
Joe Perches [Wed, 6 Aug 2014 23:11:14 +0000 (16:11 -0700)]
checkpatch: fix brace style misuses of else and while

Add --fix corrections for ELSE_AFTER_BRACE and WHILE_AFTER_BRACE
misuses.

if (x) {
...
}
else {
...
}

is corrected to

if (x) {
...
} else {
...
}

and

do {
...
}
while (x);

is corrected to

do {
...
} while (x);

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: add --fix option for a couple OPEN_BRACE misuses
Joe Perches [Wed, 6 Aug 2014 23:11:12 +0000 (16:11 -0700)]
checkpatch: add --fix option for a couple OPEN_BRACE misuses

Style misuses of these types are corrected:

  typedef struct foo
  {
        int bar;
  };

  int foo(int bar) { return bar+1;
  }

  int foo(int bar) {
        return bar+1;
  }

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: use the correct indentation for which()
Joe Perches [Wed, 6 Aug 2014 23:11:10 +0000 (16:11 -0700)]
checkpatch: use the correct indentation for which()

I copied the which subroutine from get_maintainer.pl.

Unfortunately, get_maintainer uses a 4 space indentation so use the
proper tab indentation instead.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: add fix_insert_line and fix_delete_line helpers
Joe Perches [Wed, 6 Aug 2014 23:11:07 +0000 (16:11 -0700)]
checkpatch: add fix_insert_line and fix_delete_line helpers

Neaten the uses of patch/file line insertions or deletions.  Hide the
mechanism used.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: add ability to insert and delete lines to patch/file
Joe Perches [Wed, 6 Aug 2014 23:11:05 +0000 (16:11 -0700)]
checkpatch: add ability to insert and delete lines to patch/file

This can be valuable to insert or delete blank lines as well as fix
misplaced brace or else uses.

Store indexes of lines to be added/deleted and the new lines.

When creating the --fix file, insert or delete the appropriate lines and
update the patch range information.

Signed-off-by: Joe Perches <joe@perches.com>
Cc: Andy Whitcroft <apw@canonical.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: add an index variable for fixed lines
Joe Perches [Wed, 6 Aug 2014 23:11:03 +0000 (16:11 -0700)]
checkpatch: add an index variable for fixed lines

Make the fix code a bit easier to read.

This should also start to allow an easier mechanism to insert/delete
lines eventually too.

Signed-off-by: Joe Perches <joe@perches.com>
Cc: Andy Whitcroft <apw@canonical.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: warn on break after goto or return with same tab indentation
Joe Perches [Wed, 6 Aug 2014 23:11:01 +0000 (16:11 -0700)]
checkpatch: warn on break after goto or return with same tab indentation

Using break; after a goto or return is unnecessary so emit a warning
when the break is at the same indent level.

So this emits a warning on:

switch (foo) {
case 1:
goto err;
break;
}

but not on:

switch (foo) {
case 1:
if (bar())
goto err;
break;
}

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: emit a warning on file add/move/delete
Joe Perches [Wed, 6 Aug 2014 23:10:59 +0000 (16:10 -0700)]
checkpatch: emit a warning on file add/move/delete

Whenever files are added, moved, or deleted, the MAINTAINERS file
patterns can be out of sync or outdated.

To try to keep MAINTAINERS more up-to-date, add a one-time warning
whenever a patch does any of those.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Andy Whitcroft <apw@canonical.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: add test for commit id formatting style in commit log
Joe Perches [Wed, 6 Aug 2014 23:10:57 +0000 (16:10 -0700)]
checkpatch: add test for commit id formatting style in commit log

Commit logs have various forms of commit id references.

Try to standardize on a 12 character long lower case commit id along
with a description of parentheses and the quoted subject line.

ie: commit 0123456789ab ("commit description")

If git and a git tree exists, look up the commit id and emit the
appropriate line as part of the message.

Signed-off-by: Joe Perches <joe@perches.com>
Requested-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: emit fewer kmalloc_array/kcalloc conversion warnings
Joe Perches [Wed, 6 Aug 2014 23:10:55 +0000 (16:10 -0700)]
checkpatch: emit fewer kmalloc_array/kcalloc conversion warnings

Avoid matching allocs that appear to be known small multiplications of a
sizeof with a constant because gcc as of 4.8 cannot optimize the code in
a calloc() exactly the same way as an alloc().

Look for numeric constants or what appear to be upper case only macro
#defines.

Signed-off-by: Joe Perches <joe@perches.com>
Reported-by: Theodore Ts'o <tytso@mit.edu>
Original-patch-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: improve "no space after cast" test
Joe Perches [Wed, 6 Aug 2014 23:10:52 +0000 (16:10 -0700)]
checkpatch: improve "no space after cast" test

This --strict test previously worked only for what appeared to be cast
to pointer types.

Make it work for all casts.

Also, there's no reason to show the previous line for this type of
message, so don't.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: allow multiple const * types
Joe Perches [Wed, 6 Aug 2014 23:10:50 +0000 (16:10 -0700)]
checkpatch: allow multiple const * types

checkpatch's $Type variable does not match declarations of multiple
const * types.

This can produce false positives for things like:

  $ ./scripts/checkpatch.pl -f drivers/staging/comedi/comedidev.h
  WARNING: Missing a blank line after declarations
  #60: FILE: drivers/staging/comedi/comedidev.h:60:
  +       const struct comedi_lrange *range_table;
  +       const struct comedi_lrange *const *range_table_list;

Fix the $Type variable to support matching multiple "* const" uses.

Signed-off-by: Joe Perches <joe@perches.com>
Reported-by: Hartley Sweeten <HartleyS@visionengravers.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: warn on unnecessary parentheses around references of foo->bar
Joe Perches [Wed, 6 Aug 2014 23:10:48 +0000 (16:10 -0700)]
checkpatch: warn on unnecessary parentheses around references of foo->bar

Parentheses around &(foo->bar) and *(foo->bar) are unnecessary.  Emit a
--strict only message on these uses.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: quiet Kconfig help message checking
Joe Perches [Wed, 6 Aug 2014 23:10:46 +0000 (16:10 -0700)]
checkpatch: quiet Kconfig help message checking

Editing Kconfig dependencies can emit unnecessary messages about missing
or too short help entries.

Only emit the message when adding help sections to Kconfig files.

Signed-off-by: Joe Perches <joe@perches.com>
Reported-by: Jean Delvare <jdelvare@suse.de>
Tested-by: Jean Delvare <jdelvare@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: change blank line after declaration type to "LINE_SPACING"
Joe Perches [Wed, 6 Aug 2014 23:10:44 +0000 (16:10 -0700)]
checkpatch: change blank line after declaration type to "LINE_SPACING"

Make it consistent with the other missing or multiple blank line tests.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: add a multiple blank lines test
Joe Perches [Wed, 6 Aug 2014 23:10:42 +0000 (16:10 -0700)]
checkpatch: add a multiple blank lines test

Multiple consecutive blank lines waste screen space.  Emit a --strict
only message with these blank lines.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: add test for blank lines after function/struct/union/enum
Joe Perches [Wed, 6 Aug 2014 23:10:39 +0000 (16:10 -0700)]
checkpatch: add test for blank lines after function/struct/union/enum

Add a --strict test asking for a blank line after
function/struct/union/enum declarations.

Allow exceptions for several attributes and macro uses.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch.pl: also suggest 'else if' when if follows brace
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:37 +0000 (16:10 -0700)]
checkpatch.pl: also suggest 'else if' when if follows brace

This might help a kernel hacker think twice before blindly adding a
newline.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Acked-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: ignore email headers better
Joe Perches [Wed, 6 Aug 2014 23:10:35 +0000 (16:10 -0700)]
checkpatch: ignore email headers better

There are some patches created by git format-patch that when scanned by
checkpatch report errors on lines like

To: address.tld

This is a checkpatch false positive.

Improve the logic a bit to ignore folded email headers to avoid emitting
these messages.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: fix function pointers in blank line needed after declarations test
Joe Perches [Wed, 6 Aug 2014 23:10:33 +0000 (16:10 -0700)]
checkpatch: fix function pointers in blank line needed after declarations test

Add a function pointer declaration check to the test for blank line
needed after declarations.

Signed-off-by: Joe Perches <joe@perches.com>
Reported-by: Bruce W Allan <bruce.w.allan@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: fix complex macro false positive for escaped constant char
Joe Perches [Wed, 6 Aug 2014 23:10:31 +0000 (16:10 -0700)]
checkpatch: fix complex macro false positive for escaped constant char

A single escaped constant char is not a complex macro.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: warn on unnecessary else after return or break
Joe Perches [Wed, 6 Aug 2014 23:10:29 +0000 (16:10 -0700)]
checkpatch: warn on unnecessary else after return or break

Using an else following a break or return can unnecessarily indent code
blocks.

ie:
for (i = 0; i < 100; i++) {
int foo = bar();
if (foo < 1)
break;
else
usleep(1);
}

is generally better written as:

for (i = 0; i < 100; i++) {
int foo = bar();
if (foo < 1)
break;
usleep(1);
}

Warn when a bare else statement is preceded by a break or return
indented 1 tab more than the else.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agocheckpatch: attempt to find unnecessary 'out of memory' messages
Joe Perches [Wed, 6 Aug 2014 23:10:27 +0000 (16:10 -0700)]
checkpatch: attempt to find unnecessary 'out of memory' messages

Logging messages that show some type of "out of memory" error are
generally unnecessary as there is a generic message and a stack dump
done by the memory subsystem.

These messages generally increase kernel size without much added value.

Emit a warning on these types of messages.

This test looks for any inserted message function, then looks at the
previous line for an "if (!foo)" or "if (foo == NULL)" test and then
looks at the preceding statement for an allocation function like "foo =
kmalloc()"

ie: this code matches:

foo = kmalloc();
if (foo == NULL) {
printk("Out of memory\n");
return -ENOMEM;
}

This test is very crude and incomplete.

This test can miss quite a lot of of OOM messages that do not have this
specific form.

ie: this code does not match:

foo = kmalloc();
if (!foo) {
rtn = -ENOMEM;
printk("Out of memory!\n");
goto out;
}

This test could also be a false positive when the logging message itself
does not specify anything about memory, but I did not find any false
positives in my limited testing.

spatch could be a better solution but correctness seems non-trivial for
that tool too.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: add missing mask in bitmap_andnot
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:24 +0000 (16:10 -0700)]
lib: bitmap: add missing mask in bitmap_andnot

Apparently, bitmap_andnot is supposed to return whether the new bitmap
is empty.  But it didn't take potential garbage bits in the last word
into account.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: add missing mask in bitmap_and
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:22 +0000 (16:10 -0700)]
lib: bitmap: add missing mask in bitmap_and

Apparently, bitmap_and is supposed to return whether the new bitmap is
empty.  But it didn't take potential garbage bits in the last word into
account.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: add missing mask in bitmap_shift_right
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:20 +0000 (16:10 -0700)]
lib: bitmap: add missing mask in bitmap_shift_right

There is no guarantee that *src does not contain garbage bits outside
the lower nbits, so we need to mask it before the shift-and-assign.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: micro-optimize bitmap_allocate_region
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:18 +0000 (16:10 -0700)]
lib: bitmap: micro-optimize bitmap_allocate_region

__reg_op(..., REG_OP_ALLOC) always returns 0, so we might as well use that
and save an instruction.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: change parameter of bitmap_*_region to unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:16 +0000 (16:10 -0700)]
lib: bitmap: change parameter of bitmap_*_region to unsigned

Changing the pos parameter of __reg_op to unsigned allows the compiler
to generate slightly smaller and simpler code.  Also update its callers
bitmap_*_region to receive and pass unsigned int.  The return types of
bitmap_find_free_region and bitmap_allocate_region are still int to
allow a negative error code to be returned.  An int is certainly capable
of representing any realistic return value.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: fix typo in kerneldoc for bitmap_pos_to_ord
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:14 +0000 (16:10 -0700)]
lib: bitmap: fix typo in kerneldoc for bitmap_pos_to_ord

A few lines above, it was stated that positions for non-set bits are
mapped to -1, which is obviously also what the code does.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: simplify bitmap_parselist
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:12 +0000 (16:10 -0700)]
lib: bitmap: simplify bitmap_parselist

We want len to be the index of the first '\n', or the length of the
string if there is no newline.  This is a good example of the usefulness
of strchrnul().  Use that instead, thus eliminating a branch and a call
to strlen().

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make the start index of bitmap_clear unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:10 +0000 (16:10 -0700)]
lib: bitmap: make the start index of bitmap_clear unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "start" is non-negative.

Also, use the names "start" and "len" for the two parameters for
consistency with bitmap_set.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make the start index of bitmap_set unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:07 +0000 (16:10 -0700)]
lib: bitmap: make the start index of bitmap_set unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "start" is non-negative.

Also, use the names "start" and "len" for the two parameters in both
header file and implementation, instead of the previous mix.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_weight unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:05 +0000 (16:10 -0700)]
lib: bitmap: make nbits parameter of bitmap_weight unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "nbits" is non-negative.  Since no-one passes a negative
bit-count, this shouldn't affect the semantics.

I didn't change the return type, since that might change the semantics
of some expression containing a call to bitmap_weight(). Certainly an
int is capable of holding the result.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_subset unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:03 +0000 (16:10 -0700)]
lib: bitmap: make nbits parameter of bitmap_subset unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "nbits" is non-negative.  Since no-one passes a negative
bit-count, this shouldn't affect the semantics.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_intersects unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:01 +0000 (16:10 -0700)]
lib: bitmap: make nbits parameter of bitmap_intersects unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "nbits" is non-negative.  Since no-one passes a negative
bit-count, this shouldn't affect the semantics.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_{and,or,xor,andnot} unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:59 +0000 (16:09 -0700)]
lib: bitmap: make nbits parameter of bitmap_{and,or,xor,andnot} unsigned

This change is only for consistency with the changes to the other
bitmap_* functions; it doesn't change the size of the generated code:
inside BITS_TO_LONGS there is a sizeof(long), which causes bits to be
interpreted as unsigned anyway.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: remove unnecessary mask from bitmap_complement
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:57 +0000 (16:09 -0700)]
lib: bitmap: remove unnecessary mask from bitmap_complement

Since the extra bits are "don't care", there is no reason to mask the
last word to the used bits when complementing.  This shaves off yet a
few bytes.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_complement unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:55 +0000 (16:09 -0700)]
lib: bitmap: make nbits parameter of bitmap_complement unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "nbits" is non-negative.  Since no-one passes a negative
bit-count, this shouldn't affect the semantics.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_equal unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:53 +0000 (16:09 -0700)]
lib: bitmap: make nbits parameter of bitmap_equal unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "nbits" is non-negative.  Since no-one passes a negative
bit-count, this shouldn't affect the semantics.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_full unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:51 +0000 (16:09 -0700)]
lib: bitmap: make nbits parameter of bitmap_full unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "nbits" is non-negative.  Since no-one passes a negative
bit-count, this shouldn't affect the semantics.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_empty unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:49 +0000 (16:09 -0700)]
lib: bitmap: make nbits parameter of bitmap_empty unsigned

Many functions in lib/bitmap.c start with an expression such as lim =
bits/BITS_PER_LONG.  Since bits has type (signed) int, and since gcc
cannot know that it is in fact non-negative, it generates worse code
than it could.  These patches, mostly consisting of changing various
parameters to unsigned, gives a slight overall code reduction:

  add/remove: 1/1 grow/shrink: 8/16 up/down: 251/-414 (-163)
  function                                     old     new   delta
  tick_device_uses_broadcast                   335     425     +90
  __irq_alloc_descs                            498     554     +56
  __bitmap_andnot                               73     115     +42
  __bitmap_and                                  70     101     +31
  bitmap_weight                                  -      11     +11
  copy_hugetlb_page_range                      752     762     +10
  follow_hugetlb_page                          846     854      +8
  hugetlb_init                                1415    1417      +2
  hugetlb_nrpages_setup                        130     131      +1
  hugetlb_add_hstate                           377     376      -1
  bitmap_allocate_region                        82      80      -2
  select_task_rq_fair                         2202    2191     -11
  hweight_long                                  66      55     -11
  __reg_op                                     230     219     -11
  dm_stats_message                            2849    2833     -16
  bitmap_parselist                              92      74     -18
  __bitmap_weight                              115      97     -18
  __bitmap_subset                              153     129     -24
  __bitmap_full                                128     104     -24
  __bitmap_empty                               120      96     -24
  bitmap_set                                   179     149     -30
  bitmap_clear                                 185     155     -30
  __bitmap_equal                               136     105     -31
  __bitmap_intersects                          148     108     -40
  __bitmap_complement                          109      67     -42
  tick_device_setup_broadcast_func.isra         81       -     -81

[The increases in __bitmap_and{,not} are due to bug fixes 17/18,18/18.
No idea why bitmap_weight suddenly appears.] While 163 bytes treewide is
insignificant, I believe the bitmap functions are often called with
locks held, so saving even a few cycles might be worth it.

While making these changes, I found a few other things that might be
worth including.  16,17,18 are actual bug fixes.  The rest shouldn't
change the behaviour of any of the functions, provided no-one passed
negative nbits values.  If something should come up, it should be fairly
bisectable.

A few issues I thought about, but didn't know what to do with:

* Many of the functions misbehave if nbits is compile-time 0; the
  out-of-line functions generally handle 0 correctly.  bitmap_fill() is
  particularly bad, whether the 0 is known at compile time or not.  It
  would probably be nice to add detection of at least compile-time 0 and
  handle that appropriately.

* I didn't change __bitmap_shift_{left,right} to use unsigned because I
  want to fully understand why the algorithm works before making that
  change.  However, AFAICT, they behave correctly for all (positive) shift
  amounts.  This is not the case for the small_const_nbits versions.  If
  for example nbits = n = BITS_PER_LONG, the shift operators turn into
  no-ops (at least on x86), so one get *dst = *src, whereas one would
  expect to get *dst=0.  That difference in behaviour is somewhat
  annoying.

This patch (of 18):

The compiler can generate slightly smaller and simpler code when it
knows that "nbits" is non-negative.  Since no-one passes a negative
bit-count, this shouldn't affect the semantics.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib/list_sort.c: convert to pr_foo
Andrew Morton [Wed, 6 Aug 2014 23:09:46 +0000 (16:09 -0700)]
lib/list_sort.c: convert to pr_foo

Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Cc: Don Mullis <don.mullis@gmail.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: list_sort.c: Limit number of unused cmp callbacks
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:44 +0000 (16:09 -0700)]
lib: list_sort.c: Limit number of unused cmp callbacks

The helper merge_and_restore_back_links() makes sure to call the
caller's cmp function during the final ->prev pointer fixup, so that the
cmp function may call cond_resched().  However, if the cmp function does
not call cond_resched() at all, this is entirely redundant.  If it does,
doing at least two function calls for every two pointer assignments is a
bit excessive.  This patch limits the calls to once for every 256
iterations.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Cc: Don Mullis <don.mullis@gmail.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: list_sort_test(): simplify and harden cleanup
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:42 +0000 (16:09 -0700)]
lib: list_sort_test(): simplify and harden cleanup

There is no reason to maintain the list structure while freeing the
debug elements.  Aside from the redundant pointer manipulations, it is
also inefficient from a locality-of-reference viewpoint, since they are
visited in a random order (wrt.  the order they were allocated).
Furthermore, if we jumped to exit: after detecting list corruption, it
is actually dangerous.

So just free the elements in the order they were allocated, using the
backing array elts.  Allocate that using kcalloc(), so that if
allocation of one of the debug element fails, we just end up calling
kfree(NULL) for the trailing elements.

Minor details: Use sizeof(*elts) instead of sizeof(void *), and return
err immediately when allocation of elts fails, to avoid introducing
another label just before the final return statement.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Cc: Don Mullis <don.mullis@gmail.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: list_sort_test(): add extra corruption check
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:40 +0000 (16:09 -0700)]
lib: list_sort_test(): add extra corruption check

Add a check to make sure that the prev pointer of the list head points
to the last element on the list.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Cc: Don Mullis <don.mullis@gmail.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: list_sort_test(): return -ENOMEM when allocation fails
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:38 +0000 (16:09 -0700)]
lib: list_sort_test(): return -ENOMEM when allocation fails

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Cc: Don Mullis <don.mullis@gmail.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agokernel.h: remove deprecated pack_hex_byte
Joe Perches [Wed, 6 Aug 2014 23:09:36 +0000 (16:09 -0700)]
kernel.h: remove deprecated pack_hex_byte

It's been nearly 3 years now since commit 55036ba76b2d ("lib: rename
pack_hex_byte() to hex_byte_pack()") so it's time to remove this
deprecated and unused static inline.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib/test-kstrtox.c: use ARRAY_SIZE instead of sizeof/sizeof[0]
Fabian Frederick [Wed, 6 Aug 2014 23:09:33 +0000 (16:09 -0700)]
lib/test-kstrtox.c: use ARRAY_SIZE instead of sizeof/sizeof[0]

Use kernel.h definition.

Signed-off-by: Fabian Frederick <fabf@skynet.be>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib/string_helpers.c: constify static arrays
Mathias Krause [Wed, 6 Aug 2014 23:09:31 +0000 (16:09 -0700)]
lib/string_helpers.c: constify static arrays

Complement commit 68aecfb97978 ("lib/string_helpers.c: make arrays
static") by making the arrays const -- not only pointing to const
strings.  This moves them out of the data section to the r/o data
section:

   text    data     bss     dec     hex filename
   1150     176       0    1326     52e lib/string_helpers.old.o
   1326       0       0    1326     52e lib/string_helpers.new.o

Signed-off-by: Mathias Krause <minipli@googlemail.com>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib/cmdline.c: add size unit t/p/e to memparse
Gui Hecheng [Wed, 6 Aug 2014 23:09:29 +0000 (16:09 -0700)]
lib/cmdline.c: add size unit t/p/e to memparse

For modern filesystems such as btrfs, t/p/e size level operations are
common.  add size unit t/p/e parsing to memparse

Signed-off-by: Gui Hecheng <guihc.fnst@cn.fujitsu.com>
Acked-by: David Rientjes <rientjes@google.com>
Reviewed-by: Satoru Takeuchi <takeuchi_satoru@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolibata: Use glob_match from lib/glob.c
George Spelvin [Wed, 6 Aug 2014 23:09:27 +0000 (16:09 -0700)]
libata: Use glob_match from lib/glob.c

The function may be useful for other drivers, so export it.  (Suggested
by Tejun Heo.)

Note that I inverted the return value of glob_match; returning true on
match seemed to make more sense.

Signed-off-by: George Spelvin <linux@horizon.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib/glob.c: add CONFIG_GLOB_SELFTEST
George Spelvin [Wed, 6 Aug 2014 23:09:25 +0000 (16:09 -0700)]
lib/glob.c: add CONFIG_GLOB_SELFTEST

This was useful during development, and is retained for future
regression testing.

GCC appears to have no way to place string literals in a particular
section; adding __initconst to a char pointer leaves the string itself
in the default string section, where it will not be thrown away after
module load.

Thus all string constants are kept in explicitly declared and named
arrays.  Sorry this makes printk a bit harder to read.  At least the
tests are more compact.

Signed-off-by: George Spelvin <linux@horizon.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: add lib/glob.c
George Spelvin [Wed, 6 Aug 2014 23:09:23 +0000 (16:09 -0700)]
lib: add lib/glob.c

This is a helper function from drivers/ata/libata_core.c, where it is
used to blacklist particular device models.  It's being moved to lib/ so
other drivers may use it for the same purpose.

This implementation in non-recursive, so is safe for the kernel stack.

[akpm@linux-foundation.org: fix sparse warning]
Signed-off-by: George Spelvin <linux@horizon.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agozlib: clean up some dead code
Sergey Senozhatsky [Wed, 6 Aug 2014 23:09:21 +0000 (16:09 -0700)]
zlib: clean up some dead code

Cleanup unused `if 0'-ed functions, which have been dead since 2006
(commits 87c2ce3b9305 ("lib/zlib*: cleanups") by Adrian Bunk and
4f3865fb57a0 ("zlib_inflate: Upgrade library code to a recent version")
by Richard Purdie):

 - zlib_deflateSetDictionary
 - zlib_deflateParams
 - zlib_deflateCopy
 - zlib_inflateSync
 - zlib_syncsearch
 - zlib_inflateSetDictionary
 - zlib_inflatePrime

Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoklist: use same naming scheme as hlist for klist_add_after()
Ken Helias [Wed, 6 Aug 2014 23:09:18 +0000 (16:09 -0700)]
klist: use same naming scheme as hlist for klist_add_after()

The name was modified from hlist_add_after() to hlist_add_behind() when
adjusting the order of arguments to match the one with
klist_add_after().  This is necessary to break old code when it would
use it the wrong way.

Make klist follow this naming scheme for consistency.

Signed-off-by: Ken Helias <kenhelias@firemail.de>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolist: fix order of arguments for hlist_add_after(_rcu)
Ken Helias [Wed, 6 Aug 2014 23:09:16 +0000 (16:09 -0700)]
list: fix order of arguments for hlist_add_after(_rcu)

All other add functions for lists have the new item as first argument
and the position where it is added as second argument.  This was changed
for no good reason in this function and makes using it unnecessary
confusing.

The name was changed to hlist_add_behind() to cause unconverted code to
generate a compile error instead of using the wrong parameter order.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Ken Helias <kenhelias@firemail.de>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> [intel driver bits]
Cc: Hugh Dickins <hughd@google.com>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolist: make hlist_add_after() argument names match hlist_add_after_rcu()
Ken Helias [Wed, 6 Aug 2014 23:09:14 +0000 (16:09 -0700)]
list: make hlist_add_after() argument names match hlist_add_after_rcu()

The argument names for hlist_add_after() are poorly chosen because they
look the same as the ones for hlist_add_before() but have to be used
differently.

hlist_add_after_rcu() has made a better choice.

Signed-off-by: Ken Helias <kenhelias@firemail.de>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agokernel/printk/printk.c: fix bool assignements
Neil Zhang [Wed, 6 Aug 2014 23:09:12 +0000 (16:09 -0700)]
kernel/printk/printk.c: fix bool assignements

Fix coccinelle warnings.

Signed-off-by: Neil Zhang <zhangwm@marvell.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: enable interrupts before calling console_trylock_for_printk()
Jan Kara [Wed, 6 Aug 2014 23:09:10 +0000 (16:09 -0700)]
printk: enable interrupts before calling console_trylock_for_printk()

We need interrupts disabled when calling console_trylock_for_printk()
only so that cpu id we pass to can_use_console() remains valid (for
other things console_sem provides all the exclusion we need and
deadlocks on console_sem due to interrupts are impossible because we use
down_trylock()).  However if we are rescheduled, we are guaranteed to
run on an online cpu so we can easily just get the cpu id in
can_use_console().

We can lose a bit of performance when we enable interrupts in
vprintk_emit() and then disable them again in console_unlock() but OTOH
it can somewhat reduce interrupt latency caused by console_unlock().

We differ from (reverted) commit 939f04bec1a4 in that we avoid calling
console_unlock() from vprintk_emit() with lockdep enabled as that has
unveiled quite some bugs leading to system freezes during boot (e.g.
  https://lkml.org/lkml/2014/5/30/242,
  https://lkml.org/lkml/2014/6/28/521).

Signed-off-by: Jan Kara <jack@suse.cz>
Tested-by: Andreas Bombe <aeb@debian.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: miscellaneous cleanups
Alex Elder [Wed, 6 Aug 2014 23:09:08 +0000 (16:09 -0700)]
printk: miscellaneous cleanups

Some small cleanups to kernel/printk/printk.c.  None of them should
cause any change in behavior.

  - When CONFIG_PRINTK is defined, parenthesize the value of LOG_LINE_MAX.
  - When CONFIG_PRINTK is *not* defined, there is an extra LOG_LINE_MAX
    definition; delete it.
  - Pull an assignment out of a conditional expression in console_setup().
  - Use isdigit() in console_setup() rather than open coding it.
  - In update_console_cmdline(), drop a NUL-termination assignment;
    the strlcpy() call that precedes it guarantees it's not needed.
  - Simplify some logic in printk_timed_ratelimit().

Signed-off-by: Alex Elder <elder@linaro.org>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Jan Kara <jack@suse.cz>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: use a clever macro
Alex Elder [Wed, 6 Aug 2014 23:09:05 +0000 (16:09 -0700)]
printk: use a clever macro

Use the IS_ENABLED() macro rather than #ifdef blocks to set certain
global values.

Signed-off-by: Alex Elder <elder@linaro.org>
Acked-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: fix some comments
Alex Elder [Wed, 6 Aug 2014 23:09:03 +0000 (16:09 -0700)]
printk: fix some comments

Fix a few comments that don't accurately describe their corresponding
code.  It also fixes some minor typographical errors.

Signed-off-by: Alex Elder <elder@linaro.org>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Jan Kara <jack@suse.cz>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: rename DEFAULT_MESSAGE_LOGLEVEL
Alex Elder [Wed, 6 Aug 2014 23:09:01 +0000 (16:09 -0700)]
printk: rename DEFAULT_MESSAGE_LOGLEVEL

Commit a8fe19ebfbfd ("kernel/printk: use symbolic defines for console
loglevels") makes consistent use of symbolic values for printk() log
levels.

The naming scheme used is different from the one used for
DEFAULT_MESSAGE_LOGLEVEL though.  Change that symbol name to be
MESSAGE_LOGLEVEL_DEFAULT for consistency.  And because the value of that
symbol comes from a similarly-named config option, rename
CONFIG_DEFAULT_MESSAGE_LOGLEVEL as well.

Signed-off-by: Alex Elder <elder@linaro.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Jan Kara <jack@suse.cz>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: tweak do_syslog() to match comments
Alex Elder [Wed, 6 Aug 2014 23:08:59 +0000 (16:08 -0700)]
printk: tweak do_syslog() to match comments

In do_syslog() there's a path used by kmsg_poll() and kmsg_read() that
only needs to know whether there's any data available to read (and not
its size).  These callers only check for non-zero return.  As a
shortcut, do_syslog() returns the difference between what has been
logged and what has been "seen."

The comments say that the "count of records" should be returned but it's
not.  Instead it returns (log_next_idx - syslog_idx), which is a
difference between buffer offsets--and the result could be negative.

The behavior is the same (it'll be zero or not in the same cases), but
the count of records is more meaningful and it matches what the comments
say.  So change the code to return that.

Signed-off-by: Alex Elder <elder@linaro.org>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Joe Perches <joe@perches.com>
Cc: John Stultz <john.stultz@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: allow increasing the ring buffer depending on the number of CPUs
Luis R. Rodriguez [Wed, 6 Aug 2014 23:08:56 +0000 (16:08 -0700)]
printk: allow increasing the ring buffer depending on the number of CPUs

The default size of the ring buffer is too small for machines with a
large amount of CPUs under heavy load.  What ends up happening when
debugging is the ring buffer overlaps and chews up old messages making
debugging impossible unless the size is passed as a kernel parameter.
An idle system upon boot up will on average spew out only about one or
two extra lines but where this really matters is on heavy load and that
will vary widely depending on the system and environment.

There are mechanisms to help increase the kernel ring buffer for tracing
through debugfs, and those interfaces even allow growing the kernel ring
buffer per CPU.  We also have a static value which can be passed upon
boot.  Relying on debugfs however is not ideal for production, and
relying on the value passed upon bootup is can only used *after* an
issue has creeped up.  Instead of being reactive this adds a proactive
measure which lets you scale the amount of contributions you'd expect to
the kernel ring buffer under load by each CPU in the worst case
scenario.

We use num_possible_cpus() to avoid complexities which could be
introduced by dynamically changing the ring buffer size at run time,
num_possible_cpus() lets us use the upper limit on possible number of
CPUs therefore avoiding having to deal with hotplugging CPUs on and off.
This introduces the kernel configuration option LOG_CPU_MAX_BUF_SHIFT
which is used to specify the maximum amount of contributions to the
kernel ring buffer in the worst case before the kernel ring buffer flips
over, the size is specified as a power of 2.  The total amount of
contributions made by each CPU must be greater than half of the default
kernel ring buffer size (1 << LOG_BUF_SHIFT bytes) in order to trigger
an increase upon bootup.  The kernel ring buffer is increased to the
next power of two that would fit the required minimum kernel ring buffer
size plus the additional CPU contribution.  For example if LOG_BUF_SHIFT
is 18 (256 KB) you'd require at least 128 KB contributions by other CPUs
in order to trigger an increase of the kernel ring buffer.  With a
LOG_CPU_BUF_SHIFT of 12 (4 KB) you'd require at least anything over > 64
possible CPUs to trigger an increase.  If you had 128 possible CPUs the
amount of minimum required kernel ring buffer bumps to:

   ((1 << 18) + ((128 - 1) * (1 << 12))) / 1024 = 764 KB

Since we require the ring buffer to be a power of two the new required
size would be 1024 KB.

This CPU contributions are ignored when the "log_buf_len" kernel
parameter is used as it forces the exact size of the ring buffer to an
expected power of two value.

[pmladek@suse.cz: fix build]
Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com>
Signed-off-by: Petr Mladek <pmladek@suse.cz>
Tested-by: Davidlohr Bueso <davidlohr@hp.com>
Tested-by: Petr Mladek <pmladek@suse.cz>
Reviewed-by: Davidlohr Bueso <davidlohr@hp.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Stephen Warren <swarren@wwwdotorg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Joe Perches <joe@perches.com>
Cc: Arun KS <arunks.linux@gmail.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: make dynamic units clear for the kernel ring buffer
Luis R. Rodriguez [Wed, 6 Aug 2014 23:08:54 +0000 (16:08 -0700)]
printk: make dynamic units clear for the kernel ring buffer

Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com>
Suggested-by: Davidlohr Bueso <davidlohr@hp.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Stephen Warren <swarren@wwwdotorg.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Joe Perches <joe@perches.com>
Cc: Arun KS <arunks.linux@gmail.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: move power of 2 practice of ring buffer size to a helper
Luis R. Rodriguez [Wed, 6 Aug 2014 23:08:52 +0000 (16:08 -0700)]
printk: move power of 2 practice of ring buffer size to a helper

In practice the power of 2 practice of the size of the kernel ring
buffer remains purely historical but not a requirement, specially now
that we have LOG_ALIGN and use it for both static and dynamic
allocations.  It could have helped with implicit alignment back in the
days given the even the dynamically sized ring buffer was guaranteed to
be aligned so long as CONFIG_LOG_BUF_SHIFT was set to produce a
__LOG_BUF_LEN which is architecture aligned, since log_buf_len=n would
be allowed only if it was > __LOG_BUF_LEN and we always ended up
rounding the log_buf_len=n to the next power of 2 with
roundup_pow_of_two(), any multiple of 2 then should be also architecture
aligned.  These assumptions of course relied heavily on
CONFIG_LOG_BUF_SHIFT producing an aligned value but users can always
change this.

We now have precise alignment requirements set for the log buffer size
for both static and dynamic allocations, but lets upkeep the old
practice of using powers of 2 for its size to help with easy expected
scalable values and the allocators for dynamic allocations.  We'll reuse
this later so move this into a helper.

Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Stephen Warren <swarren@wwwdotorg.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Joe Perches <joe@perches.com>
Cc: Arun KS <arunks.linux@gmail.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: make dynamic kernel ring buffer alignment explicit
Luis R. Rodriguez [Wed, 6 Aug 2014 23:08:49 +0000 (16:08 -0700)]
printk: make dynamic kernel ring buffer alignment explicit

We have to consider alignment for the ring buffer both for the default
static size, and then also for when an dynamic allocation is made when
the log_buf_len=n kernel parameter is passed to set the size
specifically to a size larger than the default size set by the
architecture through CONFIG_LOG_BUF_SHIFT.

The default static kernel ring buffer can be aligned properly if
architectures set CONFIG_LOG_BUF_SHIFT properly, we provide ranges for
the size though so even if CONFIG_LOG_BUF_SHIFT has a sensible aligned
value it can be reduced to a non aligned value.  Commit 6ebb017de9
("printk: Fix alignment of buf causing crash on ARM EABI") by Andrew
Lunn ensures the static buffer is always aligned and the decision of
alignment is done by the compiler by using __alignof__(struct log).

When log_buf_len=n is used we allocate the ring buffer dynamically.
Dynamic allocation varies, for the early allocation called before
setup_arch() memblock_virt_alloc() requests a page aligment and for the
default kernel allocation memblock_virt_alloc_nopanic() requests no
special alignment, which in turn ends up aligning the allocation to
SMP_CACHE_BYTES, which is L1 cache aligned.

Since we already have the required alignment for the kernel ring buffer
though we can do better and request explicit alignment for LOG_ALIGN.
This does that to be safe and make dynamic allocation alignment
explicit.

Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com>
Tested-by: Petr Mladek <pmladek@suse.cz>
Acked-by: Petr Mladek <pmladek@suse.cz>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Stephen Warren <swarren@wwwdotorg.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Joe Perches <joe@perches.com>
Cc: Arun KS <arunks.linux@gmail.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoinclude/linux/byteorder/generic.h: minor comment fix
Geoff Levand [Wed, 6 Aug 2014 23:08:47 +0000 (16:08 -0700)]
include/linux/byteorder/generic.h: minor comment fix

Signed-off-by: Geoff Levand <geoff@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agofs.h, drivers/hwmon/asus_atk0110.c: fix DEFINE_SIMPLE_ATTRIBUTE semicolon definition...
Joe Perches [Wed, 6 Aug 2014 23:08:45 +0000 (16:08 -0700)]
fs.h, drivers/hwmon/asus_atk0110.c: fix DEFINE_SIMPLE_ATTRIBUTE semicolon definition and use

The DEFINE_SIMPLE_ATTRIBUTE macro should not end in a ; Fix the one use
in the kernel tree that did not have a semicolon.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Luca Tettamanti <kronos.it@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years ago./Makefile: tell gcc optimizer to never introduce new data races
Jiri Kosina [Wed, 6 Aug 2014 23:08:43 +0000 (16:08 -0700)]
./Makefile: tell gcc optimizer to never introduce new data races

We have been chasing a memory corruption bug, which turned out to be
caused by very old gcc (4.3.4), which happily turned conditional load
into a non-conditional one, and that broke correctness (the condition
was met only if lock was held) and corrupted memory.

This particular problem with that particular code did not happen when
never gccs were used.  I've brought this up with our gcc folks, as I
wanted to make sure that this can't really happen again, and it turns
out it actually can.

Quoting Martin Jambor <mjambor@suse.cz>:
 "More current GCCs are more careful when it comes to replacing a
  conditional load with a non-conditional one, most notably they check
  that a store happens in each iteration of _a_ loop but they assume
  loops are executed.  They also perform a simple check whether the
  store cannot trap which currently passes only for non-const
  variables.  A simple testcase demonstrating it on an x86_64 is for
  example the following:

  $ cat cond_store.c

  int g_1 = 1;

  int g_2[1024] __attribute__((section ("safe_section"), aligned (4096)));

  int c = 4;

  int __attribute__ ((noinline))
  foo (void)
  {
    int l;
    for (l = 0; (l != 4); l++) {
      if (g_1)
        return l;
      for (g_2[0] = 0; (g_2[0] >= 26); ++g_2[0])
        ;
    }
    return 2;
  }

  int main (int argc, char* argv[])
  {
    if (mprotect (g_2, sizeof(g_2), PROT_READ) == -1)
      {
        int e = errno;
        error (e, e, "mprotect error %i", e);
      }
    foo ();
    __builtin_printf("OK\n");
    return 0;
  }
  /* EOF */
  $ ~/gcc/trunk/inst/bin/gcc cond_store.c -O2 --param allow-store-data-races=0
  $ ./a.out
  OK
  $ ~/gcc/trunk/inst/bin/gcc cond_store.c -O2 --param allow-store-data-races=1
  $ ./a.out
  Segmentation fault

  The testcase fails the same at least with 4.9, 4.8 and 4.7.  Therefore
  I would suggest building kernels with this parameter set to zero. I
  also agree with Jikos that the default should be changed for -O2.  I
  have run most of the SPEC 2k6 CPU benchmarks (gamess and dealII
  failed, at -O2, not sure why) compiled with and without this option
  and did not see any real difference between respective run-times"

Hopefully the default will be changed in newer gccs, but let's force it
for kernel builds so that we are on a safe side even when older gcc are
used.

The code in question was out-of-tree printk-in-NMI (yeah, surprise
suprise, once again) patch written by Petr Mladek, let me quote his
comment from our internal bugzilla:

 "I have spent few days investigating inconsistent state of kernel ring buffer.
  It went out that it was caused by speculative store generated by
  gcc-4.3.4.

  The problem is in assembly generated for make_free_space(). The functions is
  called the following way:

  + vprintk_emit();
      + log = MAIN_LOG; // with logbuf_lock
         or
         log = NMI_LOG; // with nmi_logbuf_lock
         cont_add(log, ...);
          + cont_flush(log, ...);
              + log_store(log, ...);
                    + log_make_free_space(log, ...);

  If called with log = NMI_LOG then only nmi_log_* global variables are safe to
  modify but the generated code does store also into (main_)log_* global
  variables:

  <log_make_free_space>:
         55                      push   %rbp
         89 f6                   mov    %esi,%esi

         48 8b 05 03 99 51 01    mov    0x1519903(%rip),%rax       # ffffffff82620868 <nmi_log_next_id>
         44 8b 1d ec 98 51 01    mov    0x15198ec(%rip),%r11d      # ffffffff82620858 <log_next_idx>
         8b 35 36 60 14 01       mov    0x1146036(%rip),%esi       # ffffffff8224cfa8 <log_buf_len>
         44 8b 35 33 60 14 01    mov    0x1146033(%rip),%r14d      # ffffffff8224cfac <nmi_log_buf_len>
         4c 8b 2d d0 98 51 01    mov    0x15198d0(%rip),%r13       # ffffffff82620850 <log_next_seq>
         4c 8b 25 11 61 14 01    mov    0x1146111(%rip),%r12       # ffffffff8224d098 <log_buf>
         49 89 c2                mov    %rax,%r10
         48 21 c2                and    %rax,%rdx
         48 8b 1d 0c 99 55 01    mov    0x155990c(%rip),%rbx       # ffffffff826608a0 <nmi_log_buf>
         49 c1 ea 20             shr    $0x20,%r10
         48 89 55 d0             mov    %rdx,-0x30(%rbp)
         44 29 de                sub    %r11d,%esi
         45 29 d6                sub    %r10d,%r14d
         4c 8b 0d 97 98 51 01    mov    0x1519897(%rip),%r9 # ffffffff82620840 <log_first_seq>
         eb 7e                   jmp    ffffffff81107029 <log_make_free_space+0xe9>
  [...]
         85 ff                   test   %edi,%edi                  # edi = 1 for NMI_LOG
         4c 89 e8                mov    %r13,%rax
         4c 89 ca                mov    %r9,%rdx
         74 0a                   je     ffffffff8110703d <log_make_free_space+0xfd>
         8b 15 27 98 51 01       mov    0x1519827(%rip),%edx       # ffffffff82620860 <nmi_log_first_id>
         48 8b 45 d0             mov    -0x30(%rbp),%rax
         48 39 c2                cmp    %rax,%rdx                  # end of loop
         0f 84 da 00 00 00       je     ffffffff81107120 <log_make_free_space+0x1e0>
  [...]
         85 ff                   test   %edi,%edi                  # edi = 1 for NMI_LOG
         4c 89 0d 17 97 51 01    mov    %r9,0x1519717(%rip)        # ffffffff82620840 <log_first_seq>
                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^
                                 KABOOOM
         74 35                   je     ffffffff81107160  <log_make_free_space+0x220>

  It stores log_first_seq when edi == NMI_LOG. This instructions are used also
  when edi == MAIN_LOG but the store is done speculatively before the condition
  is decided.  It is unsafe because we do not have "logbuf_lock" in NMI context
  and some other process migh modify "log_first_seq" in parallel"

I believe that the best course of action is both

 - building kernel (and anything multi-threaded, I guess) with that
   optimization turned off
 - persuade gcc folks to change the default for future releases

Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Cc: Martin Jambor <mjambor@suse.cz>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Marek Polacek <polacek@redhat.com>
Cc: Jakub Jelinek <jakub@redhat.com>
Cc: Steven Noonan <steven@uplinklabs.net>
Cc: Richard Biener <richard.guenther@gmail.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm/zpool: update zswap to use zpool
Dan Streetman [Wed, 6 Aug 2014 23:08:40 +0000 (16:08 -0700)]
mm/zpool: update zswap to use zpool

Change zswap to use the zpool api instead of directly using zbud.  Add a
boot-time param to allow selecting which zpool implementation to use,
with zbud as the default.

Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Tested-by: Seth Jennings <sjennings@variantweb.net>
Cc: Weijie Yang <weijie.yang@samsung.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm/zpool: zbud/zsmalloc implement zpool
Dan Streetman [Wed, 6 Aug 2014 23:08:38 +0000 (16:08 -0700)]
mm/zpool: zbud/zsmalloc implement zpool

Update zbud and zsmalloc to implement the zpool api.

[fengguang.wu@intel.com: make functions static]
Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Tested-by: Seth Jennings <sjennings@variantweb.net>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Weijie Yang <weijie.yang@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm/zpool: implement common zpool api to zbud/zsmalloc
Dan Streetman [Wed, 6 Aug 2014 23:08:36 +0000 (16:08 -0700)]
mm/zpool: implement common zpool api to zbud/zsmalloc

Add zpool api.

zpool provides an interface for memory storage, typically of compressed
memory.  Users can select what backend to use; currently the only
implementations are zbud, a low density implementation with up to two
compressed pages per storage page, and zsmalloc, a higher density
implementation with multiple compressed pages per storage page.

Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Tested-by: Seth Jennings <sjennings@variantweb.net>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Weijie Yang <weijie.yang@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm/zbud: change zbud_alloc size type to size_t
Dan Streetman [Wed, 6 Aug 2014 23:08:33 +0000 (16:08 -0700)]
mm/zbud: change zbud_alloc size type to size_t

Change the type of the zbud_alloc() size param from unsigned int to
size_t.

Technically, this should not make any difference, as the zbud
implementation already restricts the size to well within either type's
limits; but as zsmalloc (and kmalloc) use size_t, and zpool will use
size_t, this brings the size parameter type in line with zsmalloc/zpool.

Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Acked-by: Seth Jennings <sjennings@variantweb.net>
Tested-by: Seth Jennings <sjennings@variantweb.net>
Cc: Weijie Yang <weijie.yang@samsung.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agozram: replace global tb_lock with fine grain lock
Weijie Yang [Wed, 6 Aug 2014 23:08:31 +0000 (16:08 -0700)]
zram: replace global tb_lock with fine grain lock

Currently, we use a rwlock tb_lock to protect concurrent access to the
whole zram meta table.  However, according to the actual access model,
there is only a small chance for upper user to access the same
table[index], so the current lock granularity is too big.

The idea of optimization is to change the lock granularity from whole
meta table to per table entry (table -> table[index]), so that we can
protect concurrent access to the same table[index], meanwhile allow the
maximum concurrency.

With this in mind, several kinds of locks which could be used as a
per-entry lock were tested and compared:

Test environment:
x86-64 Intel Core2 Q8400, system memory 4GB, Ubuntu 12.04,
kernel v3.15.0-rc3 as base, zram with 4 max_comp_streams LZO.

iozone test:
iozone -t 4 -R -r 16K -s 200M -I +Z
(1GB zram with ext4 filesystem, take the average of 10 tests, KB/s)

      Test       base      CAS    spinlock    rwlock   bit_spinlock
-------------------------------------------------------------------
 Initial write  1381094   1425435   1422860   1423075   1421521
       Rewrite  1529479   1641199   1668762   1672855   1654910
          Read  8468009  11324979  11305569  11117273  10997202
       Re-read  8467476  11260914  11248059  11145336  10906486
  Reverse Read  6821393   8106334   8282174   8279195   8109186
   Stride read  7191093   8994306   9153982   8961224   9004434
   Random read  7156353   8957932   9167098   8980465   8940476
Mixed workload  4172747   5680814   5927825   5489578   5972253
  Random write  1483044   1605588   1594329   1600453   1596010
        Pwrite  1276644   1303108   1311612   1314228   1300960
         Pread  4324337   4632869   4618386   4457870   4500166

To enhance the possibility of access the same table[index] concurrently,
set zram a small disksize(10MB) and let threads run with large loop
count.

fio test:
fio --bs=32k --randrepeat=1 --randseed=100 --refill_buffers
--scramble_buffers=1 --direct=1 --loops=3000 --numjobs=4
--filename=/dev/zram0 --name=seq-write --rw=write --stonewall
--name=seq-read --rw=read --stonewall --name=seq-readwrite
--rw=rw --stonewall --name=rand-readwrite --rw=randrw --stonewall
(10MB zram raw block device, take the average of 10 tests, KB/s)

    Test     base     CAS    spinlock    rwlock  bit_spinlock
-------------------------------------------------------------
seq-write   933789   999357   1003298    995961   1001958
 seq-read  5634130  6577930   6380861   6243912   6230006
   seq-rw  1405687  1638117   1640256   1633903   1634459
  rand-rw  1386119  1614664   1617211   1609267   1612471

All the optimization methods show a higher performance than the base,
however, it is hard to say which method is the most appropriate.

On the other hand, zram is mostly used on small embedded system, so we
don't want to increase any memory footprint.

This patch pick the bit_spinlock method, pack object size and page_flag
into an unsigned long table.value, so as to not increase any memory
overhead on both 32-bit and 64-bit system.

On the third hand, even though different kinds of locks have different
performances, we can ignore this difference, because: if zram is used as
zram swapfile, the swap subsystem can prevent concurrent access to the
same swapslot; if zram is used as zram-blk for set up filesystem on it,
the upper filesystem and the page cache also prevent concurrent access
of the same block mostly.  So we can ignore the different performances
among locks.

Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Reviewed-by: Davidlohr Bueso <davidlohr@hp.com>
Signed-off-by: Weijie Yang <weijie.yang@samsung.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agozram: use size_t instead of u16
Minchan Kim [Wed, 6 Aug 2014 23:08:29 +0000 (16:08 -0700)]
zram: use size_t instead of u16

Some architectures (eg, hexagon and PowerPC) could use PAGE_SHIFT of 16
or more.  In these cases u16 is not sufficiently large to represent a
compressed page's size so use size_t.

Signed-off-by: Minchan Kim <minchan@kernel.org>
Reported-by: Weijie Yang <weijie.yang@samsung.com>
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agozram: remove unused SECTOR_SIZE define
Sergey Senozhatsky [Wed, 6 Aug 2014 23:08:27 +0000 (16:08 -0700)]
zram: remove unused SECTOR_SIZE define

Drop SECTOR_SIZE define, because it's not used.

Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Weijie Yang <weijie.yang@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>