aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2009-04-10intel-iommu: Avoid panic() for DRHD at address zero.David Woodhouse
If the BIOS does something obviously stupid, like claiming that the registers for the IOMMU are at physical address zero, then print a nasty message and abort, rather than trying to set up the IOMMU and then later panicking. It's becoming more and more obvious that trusting this stuff to the BIOS was a mistake. Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
2009-04-06Intel-IOMMU Alignment Issue in dma_pte_clear_range()Fenghua Yu
This issue was pointed out by Linus. In dma_pte_clear_range() in intel-iommu.c start = PAGE_ALIGN(start); end &= PAGE_MASK; npages = (end - start) / VTD_PAGE_SIZE; In partial page case, start could be bigger than end and npages will be negative. Currently the issue doesn't show up as a real bug in because start and end have been aligned to page boundary already by all callers. So the issue has been hidden. But it is dangerous programming practice. Signed-off-by: Fenghua Yu <fenghua.yu@intel.com> Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
2009-04-06Merge git://git.infradead.org/iommu-2.6Linus Torvalds
* git://git.infradead.org/iommu-2.6: drivers/pci/intr_remapping.c: include acpi.h intel-iommu: Fix oops in device_to_iommu() when devices not found. intel-iommu: Handle PCI domains appropriately. intel-iommu: Fix device-to-iommu mapping for PCI-PCI bridges. x2apic/intr-remap: decouple interrupt remapping from x2apic x86, dmar: check if it's initialized before disable queue invalidation intel-iommu: set compatibility format interrupt Intel IOMMU Suspend/Resume Support - Interrupt Remapping Intel IOMMU Suspend/Resume Support - Queued Invalidation Intel IOMMU Suspend/Resume Support - DMAR intel-iommu: Add for_each_iommu() and for_each_active_iommu() macros
2009-04-06Merge branch 'for-linus' of git://neil.brown.name/mdLinus Torvalds
* 'for-linus' of git://neil.brown.name/md: md/raid1 - don't assume newly allocated bvecs are initialised.
2009-04-06drivers/pci/intr_remapping.c: include acpi.hAlexander Beregalov
Fix this build error: drivers/pci/intr_remapping.c: In function 'ir_parse_ioapic_scope': drivers/pci/intr_remapping.c:617: error: invalid use of undefined type 'struct acpi_dmar_hardware_unit' Signed-off-by: Alexander Beregalov <a.beregalov@gmail.com> Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
2009-04-06percpu: __percpu_depopulate_mask can take a const maskStephen Rothwell
This eliminates a compiler warning: mm/allocpercpu.c: In function 'free_percpu': mm/allocpercpu.c:146: warning: passing argument 2 of '__percpu_depopulate_mask' discards qualifiers from pointer target type Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06docs: alphabetize entries in kernel-parameters.txtRandy Dunlap
Move entries to be in alpha order as specified near the beginning of this file. Clean up some whitespace and line-length miscues. Add '=' to "selinux" option syntax. Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06docbook: fix fatal filename errorRandy Dunlap
Fix docbook fatal error: docproc: block/blktrace.c: No such file or directory Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06kernel/sysctl.c: avoid annoying warningsLinus Torvalds
Some of the limit constants are used only depending on some complex configuration dependencies, yet it's not worth making the simple variables depend on those configuration details. Just mark them as perhaps not being unused, and avoid the warning. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06Merge branch 'locking-for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: lockdep: add stack dumps to asserts hrtimer: fix rq->lock inversion (again)
2009-04-06intel-iommu: Fix oops in device_to_iommu() when devices not found.David Woodhouse
It's possible for a device in the drhd->devices[] array to be NULL if it wasn't found at boot time, which means we have to check for that case. Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
2009-04-06Merge branch 'kmemtrace-for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'kmemtrace-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: kmemtrace: trace kfree() calls with NULL or zero-length objects kmemtrace: small cleanups kmemtrace: restore original tracing data binary format, improve ABI kmemtrace: kmemtrace_alloc() must fill type_id kmemtrace: use tracepoints kmemtrace, rcu: don't include unnecessary headers, allow kmemtrace w/ tracepoints kmemtrace, rcu: fix rcupreempt.c data structure dependencies kmemtrace, rcu: fix rcu_tree_trace.c data structure dependencies kmemtrace, rcu: fix linux/rcutree.h and linux/rcuclassic.h dependencies kmemtrace, mm: fix slab.h dependency problem in mm/failslab.c kmemtrace, kbuild: fix slab.h dependency problem in lib/decompress_unlzma.c kmemtrace, kbuild: fix slab.h dependency problem in lib/decompress_bunzip2.c kmemtrace, kbuild: fix slab.h dependency problem in lib/decompress_inflate.c kmemtrace, squashfs: fix slab.h dependency problem in squasfs kmemtrace, befs: fix slab.h dependency problem kmemtrace, security: fix linux/key.h header file dependencies kmemtrace, fs: fix linux/fdtable.h header file dependencies kmemtrace, fs: uninline simple_transaction_set() kmemtrace, fs, security: move alloc_secdata() and free_secdata() to linux/security.h
2009-04-06Merge branch 'for-2.6.30' of git://linux-nfs.org/~bfields/linuxLinus Torvalds
* 'for-2.6.30' of git://linux-nfs.org/~bfields/linux: (81 commits) nfsd41: define nfsd4_set_statp as noop for !CONFIG_NFSD_V4 nfsd41: define NFSD_DRC_SIZE_SHIFT in set_max_drc nfsd41: Documentation/filesystems/nfs41-server.txt nfsd41: CREATE_EXCLUSIVE4_1 nfsd41: SUPPATTR_EXCLCREAT attribute nfsd41: support for 3-word long attribute bitmask nfsd: dynamically skip encoded fattr bitmap in _nfsd4_verify nfsd41: pass writable attrs mask to nfsd4_decode_fattr nfsd41: provide support for minor version 1 at rpc level nfsd41: control nfsv4.1 svc via /proc/fs/nfsd/versions nfsd41: add OPEN4_SHARE_ACCESS_WANT nfs4_stateid bmap nfsd41: access_valid nfsd41: clientid handling nfsd41: check encode size for sessions maxresponse cached nfsd41: stateid handling nfsd: pass nfsd4_compound_state* to nfs4_preprocess_{state,seq}id_op nfsd41: destroy_session operation nfsd41: non-page DRC for solo sequence responses nfsd41: Add a create session replay cache nfsd41: create_session operation ...
2009-04-06Merge branch 'i2c-for-linus' of git://jdelvare.pck.nerim.net/jdelvare-2.6Linus Torvalds
* 'i2c-for-linus' of git://jdelvare.pck.nerim.net/jdelvare-2.6: i2c: Delete unused i2c-algo-sgi helper module i2c: Delete many unused driver IDs i2c: Deprecate client_register and client_unregister methods
2009-04-06Merge git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6Linus Torvalds
* git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6: (74 commits) [SCSI] sg: fix q->queue_lock on scsi_error_handler path [SCSI] replace __inline with inline [SCSI] a2091: make 2 functions static [SCSI] a3000: make 2 functions static [SCSI] ses: #if 0 the unused ses_match_host() [SCSI] use kmem_cache_zalloc instead of kmem_cache_alloc/memset [SCSI] sg: fix iovec bugs introduced by the block layer conversion [SCSI] qlogicpti: use request_firmware [SCSI] advansys: use request_firmware [SCSI] qla1280: use request_firmware [SCSI] libiscsi: fix iscsi pool error path [SCSI] cxgb3i: call ddp release function directly [SCSI] cxgb3i: merge cxgb3i_ddp into cxgb3i module [SCSI] cxgb3i: close all tcp connections upon chip reset [SCSI] cxgb3i: re-read ddp settings information after chip reset [SCSI] cxgb3i: re-initialize ddp settings after chip reset [SCSI] cxgb3i: subscribe to error notification from cxgb3 driver [SCSI] aacraid driver update [SCSI] mptsas: remove unneeded check [SCSI] config: Make need for SCSI_CDROM clearer ...
2009-04-06Merge branch 'for-linus' of git://git.o-hand.com/linux-rpurdie-backlightLinus Torvalds
* 'for-linus' of git://git.o-hand.com/linux-rpurdie-backlight: backlight: Adds HP Jornada 700 series backlight driver backlight: Add HP Jornada 700 series LCD driver backlight: fix pwm_bl.c when multiple PWM backlights exist backlight: mbp_nvidia_bl - Add a debug switch backlight: Add support for MacBook 5, MacBook Air 2, and MacBook Pro 5
2009-04-06Merge branch 'for-linus' of git://git.o-hand.com/linux-rpurdie-ledsLinus Torvalds
* 'for-linus' of git://git.o-hand.com/linux-rpurdie-leds: leds: introduce lp5521 led driver leds: just ignore invalid GPIOs in leds-gpio leds: Fix &&/|| confusion in leds-pca9532.c leds: move h1940-leds's probe function to .devinit.text leds: remove an unnecessary "goto" on drivers/leds/leds-s3c24.c leds: add BD2802GU LED driver leds: remove experimental flag from leds-clevo-mail leds: Prevent multiple LED triggers with the same name leds: Add gpio-led trigger leds: Add rb532 LED driver for the User LED leds: Add suspend/resume state flags to leds-gpio leds: simple driver for pwm driven LEDs leds: Fix leds-gpio driver multiple module_init/exit usage leds: Add dac124s085 driver leds: allow led-drivers to use a variable range of brightness values leds: Add openfirmware platform device support
2009-04-06nfsd41: define nfsd4_set_statp as noop for !CONFIG_NFSD_V4Benny Halevy
Fixes following modpost error: ERROR: "nfsd4_set_statp" [fs/nfsd/nfsd.ko] undefined! Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-04-06nfsd41: define NFSD_DRC_SIZE_SHIFT in set_max_drcBenny Halevy
Fixes the following compiler error: fs/nfsd/nfssvc.c: In function 'set_max_drc': fs/nfsd/nfssvc.c:240: error: 'NFSD_DRC_SIZE_SHIFT' undeclared CONFIG_NFSD_V4 is not set Reported-by: Alexander Beregalov <a.beregalov@gmail.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-04-06i2c: Delete unused i2c-algo-sgi helper moduleJean Delvare
The i2c-algo-sgi code was merged into the vino driver, so we can delete it now. Signed-off-by: Jean Delvare <khali@linux-fr.org>
2009-04-06i2c: Delete many unused driver IDsJean Delvare
Delete many unused I2C driver IDs. We should be able to get rid of i2c_driver.id pretty soon now. Signed-off-by: Jean Delvare <khali@linux-fr.org>
2009-04-06i2c: Deprecate client_register and client_unregister methodsJean Delvare
The new i2c binding model makes the client_register and client_unregister methods of struct i2c_adapter useless, so we can remove them with the rest of the legacy model. Signed-off-by: Jean Delvare <khali@linux-fr.org>
2009-04-06backlight: Adds HP Jornada 700 series backlight driverKristoffer Ericson
Signed-off-by: Kristoffer Ericson <kristoffer.ericson@gmail.com> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06backlight: Add HP Jornada 700 series LCD driverKristoffer Ericson
Signed-off-by: Kristoffer Ericson <kristoffer.ericson@gmail.com> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06backlight: fix pwm_bl.c when multiple PWM backlights existEric Miao
When multiple PWMs are used as backlights, the current code uses pdev->name as the backlight name when registering, which will be conflicting, use dev_name() instead. Signed-off-by: Peter Edwards <sweetlilmre@gmail.com> Signed-off-by: Eric Miao <eric.miao@marvell.com> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06backlight: mbp_nvidia_bl - Add a debug switchMario Schwalbe
This patch adds a debug switch to enable (little) diagnostic output, to help to trace down the remaining problems. Signed-off-by: Mario Schwalbe <schwalbe@inf.tu-dresden.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06backlight: Add support for MacBook 5, MacBook Air 2, and MacBook Pro 5Mario Schwalbe
This patch adds support for the new Apple models incorporating an Nvidia chipset. Apple still uses the same protocol as on older models, but the registers moved to a different address. To do this, two sets of functions are added for the Intel/Nvidia chipset models and passed by the DMI_MATCH function. The initial code has been contributed by Hu Gang <hugang@soulinfo.com>. The driver is known to work on MacBook Pro 3, MacBook Pro 4 and MacBook Pro 5. Its known to work with limitations on MacBook 5 / MacBook Air 2. Changing brightness within X doesn't work, if using Nvidia's proprietary graphics driver with no known fix at present. Changing brightness on a text console or using the open-source driver does work. MacBook Pro 5 has a known bug where the initial brightness after bootup is the last recently used brightness (in Mac OSX), while the firmware reports maximum. Impossible to fix. [akpm@linux-foundation.org: build fix] [rpurdie@linux.intel.com: Rebased the patch against latest git] Signed-off-by: Mario Schwalbe <schwalbe@inf.tu-dresden.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: introduce lp5521 led driverFelipe Balbi
LP5521 is a three channel led driver with support for hardware accelerated patterns (currently used via lp5521-only sysfs interface). Currently, it's used on n810 device. Signed-off-by: Felipe Balbi <felipe.balbi@nokia.com> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: just ignore invalid GPIOs in leds-gpioDavid Brownell
Sometimes it's awkward to make sure that the array in the platform_data handed to the leds-gpio driver has only valid data ... some leds may not be always available, and coping with that currently requires patching or rebuilding the array. This patch fixes that by making it be OK to pass an invalid GPIO (such as "-EINVAL") ... such table entries are skipped. [rpurdie@linux.intel.com: adjusted to apply against other led tree changes] Signed-off-by: David Brownell <dbrownell@users.sourceforge.net> Tested-by: Diego Dompe <diego.dompe@ridgerun.com> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: Fix &&/|| confusion in leds-pca9532.cRiku Voipio
This fixes the expression in the driver to do the correct thing, not that I think anyone would send SND_* without EV_SND. Thanks to Roel Kluin <roel.kluin@gmail.com> for noticing. Signed-off-by: Riku Voipio <riku.voipio@iki.fi> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: move h1940-leds's probe function to .devinit.textUwe Kleine-König
A pointer to h1940leds_probe is passed to the core via platform_driver_register and so the function must not disappear when the .init sections are discarded. Otherwise (if also having HOTPLUG=y) unbinding and binding a device to the driver via sysfs will result in an oops as does a device being registered late. An alternative to this patch is using platform_driver_probe instead of platform_driver_register plus removing the pointer to the probe function from the struct platform_driver. Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: remove an unnecessary "goto" on drivers/leds/leds-s3c24.cZhenwen Xu
This goto is unnecessary. Signed-off-by: Zhenwen Xu <helight.xu@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: add BD2802GU LED driverKim Kyuwon
ROHM BD2802GU is a RGB LED controller attached to i2c bus and specifically engineered for decoration purposes. This RGB controller incorporates lighting patterns and illuminates. This driver is designed to minimize power consumption, so when there is no emitting LED, it enters to reset state. And because the BD2802GU has lots of features that can't be covered by the current LED framework, it provides Advanced Configuration Function(ADF) mode, so that user applications can set registers of BD2802GU directly. Here are basic usage examples : ; to turn on LED (not blink) $ echo 1 > /sys/class/leds/led1_R/brightness ; to blink LED $ echo timer > /sys/class/leds/led1_R/trigger $ echo 1 > /sys/class/leds/led1_R/delay_on $ echo 1 > /sys/class/leds/led1_R/delay_off ; to turn off LED $ echo 0 > /sys/class/leds/led1_R/brightness [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Kim Kyuwon <chammoru@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: remove experimental flag from leds-clevo-mailNémeth Márton
The leds-clevo-mail driver is in the mainline kernel since 2.6.25 and works without severe problems. Make this driver available for a larger audience. Signed-off-by: Márton Németh <nm127@freemail.hu> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: Prevent multiple LED triggers with the same nameAdam Nielsen
Signed-off-by: Adam Nielsen <a.nielsen@shikadi.net> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: Add gpio-led triggerFelipe Balbi
The gpio led trigger will allow leds to be triggered by gpio events. When we give the led a gpio number, the trigger will request_irq() on that so we don't have to keep polling for gpio state. It's useful for usecases as n810's keypad leds that could be triggered by the gpio event generated when user slides up to show the keypad. We also provide means for userland to tell us what is the desired brightness for that special led when it goes on so userland could use information from ambient light sensors and not set led brightness too high if it's not necessary. Signed-off-by: Felipe Balbi <me@felipebalbi.com> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: Add rb532 LED driver for the User LEDPhil Sutter
Mikrotik built six LEDs into the Routerboard 532, from which one is destined for custom use, the so called "User LED". This patch adds a driver for it, based on the LEDs class. Signed-off-by: Phil Sutter <n0-1@freewrt.org> Acked-by: Florian Fainelli <florian@openwrt.org> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: Add suspend/resume state flags to leds-gpioRichard Purdie
Add an option to preserve LED state when suspending/resuming to the LED gpio driver. Based on a suggestion from Robert Jarzmik. Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: simple driver for pwm driven LEDsLuotao Fu
Add a simple driver for pwm driver LEDs. pwm_id and period can be defined in board file. It is developed for pxa, however it is probably generic enough to be used on other platforms with pwm. Signed-off-by: Luotao Fu <l.fu@pengutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: Fix leds-gpio driver multiple module_init/exit usageRichard Purdie
You can't have multiple module_init()/module_exit calls so resort to messy ifdefs potentially pending some code refactoring. Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: Add dac124s085 driverGuennadi Liakhovetski
Add an LED driver using the DAC124S085 DAC from NatSemi [randy.dunlap@oracle.com: use header files for interfaces] Signed-off-by: Guennadi Liakhovetski <lg@denx.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: allow led-drivers to use a variable range of brightness valuesGuennadi Liakhovetski
This patch allows drivers to override the default maximum brightness value of 255. We take care to preserve backwards-compatibility as much as possible, so that user-space ABI doesn't change for existing drivers. LED trigger code has also been updated to use the per-LED maximum. Signed-off-by: Guennadi Liakhovetski <lg@denx.de> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06leds: Add openfirmware platform device supportTrent Piepho
Add bindings to support LEDs defined as of_platform devices in addition to the existing bindings for platform devices. New options in Kconfig allow the platform binding code and/or the of_platform code to be turned on. The of_platform code is of course only available on archs that have OF support. The existing probe and remove methods are refactored to use new functions create_gpio_led(), to create and register one led, and delete_gpio_led(), to unregister and free one led. The new probe and remove methods for the of_platform driver can then share most of the common probe and remove code with the platform driver. The suspend and resume methods aren't shared, but they are very short. The actual led driving code is the same for LEDs created by either binding. The OF bindings are based on patch by Anton Vorontsov <avorontsov@ru.mvista.com>. They have been extended to allow multiple LEDs per device. Signed-off-by: Trent Piepho <tpiepho@freescale.com> Acked-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Sean MacLennan <smaclennan@pikatech.com> Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
2009-04-06block: switch sync_dirty_buffer() over to WRITE_SYNCJens Axboe
We should now have the logic in place to handle this properly without regressing on the write performance, so re-enable the sync writes. Signed-off-by: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06block: Add flag for telling the IO schedulers NOT to anticipate more IOJens Axboe
By default, CFQ will anticipate more IO from a given io context if the previously completed IO was sync. This used to be fine, since the only sync IO was reads and O_DIRECT writes. But with more "normal" sync writes being used now, we don't want to anticipate for those. Add a bio/request flag that informs the IO scheduler that this is a sync request that we should not idle for. Introduce WRITE_ODIRECT specifically for O_DIRECT writes, and make sure that the other sync writes set this flag. Signed-off-by: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06block: enabling plugging on SSD devices that don't do queuingJens Axboe
For the older SSD devices that don't do command queuing, we do want to enable plugging to get better merging. Signed-off-by: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06jbd2: use WRITE_SYNC_PLUG instead of WRITE_SYNCJens Axboe
When you are going to be submitting several sync writes, we want to give the IO scheduler a chance to merge some of them. Instead of using the implicitly unplugging WRITE_SYNC variant, use WRITE_SYNC_PLUG and rely on sync_buffer() doing the unplug when someone does a wait_on_buffer()/lock_buffer(). Signed-off-by: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06jbd: use WRITE_SYNC_PLUG instead of WRITE_SYNCJens Axboe
When you are going to be submitting several sync writes, we want to give the IO scheduler a chance to merge some of them. Instead of using the implicitly unplugging WRITE_SYNC variant, use WRITE_SYNC_PLUG and rely on sync_buffer() doing the unplug when someone does a wait_on_buffer()/lock_buffer(). Signed-off-by: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06block: fsync_buffers_list() should use SWRITE_SYNC_PLUGJens Axboe
Then it can submit all the buffers without unplugging for each one. We will kick off the pending IO if we come across a new address space. Signed-off-by: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06Add WRITE_SYNC_PLUG and SWRITE_SYNC_PLUGJens Axboe
(S)WRITE_SYNC always unplugs the device right after IO submission. Sometimes we want to build up a queue before doing so, so add variants that explicitly DON'T unplug the queue. The caller must then do that after submitting all the IO. Signed-off-by: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>