aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* ASoC: Convert WM8993 to use shared cache I/O codeMark Brown2010-02-041-109/+43
| | | | | | | Saves a little bit of code duplication. Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk>
* ASoC: Add a cache_sync bit to the CODEC structureMark Brown2010-02-042-5/+16
| | | | | | | | | | Add a bit to the CODEC structure indicating if a cache sync is required. By default this will be set if a cache only write is done to a soc-cache register cache. This allows us to avoid syncing the cache back after using cache only writes if there were no changes. Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk>
* ASoC: Allow CODECs to ask soc-cache to suppress physical writesMark Brown2010-02-032-2/+25
| | | | | | | | | | | Currently the soc-cache code will always write to the device, meaning that we need the device to be powered and active at pretty much all times the system is active. Allowing cache only writes lays some groundwork for future enhancements to allow devices to be put into a full off state when the audio subsystem is idle. Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk>
* ASoC: fix compilation breakage in sound/soc/sh/fsi.cGuennadi Liakhovetski2010-02-031-23/+17
| | | | | | | | | | | ctrl_outl() has become void at some point, which breaks compilation of fsi.c. Make writing functions void, as their output is anyway not evaluated, and use __raw_writel and __raw_readl instead of deprecated ctrl_outl and ctrl_inl respectively. Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* ASoC: fix PXA SSP port resumeDaniel Mack2010-02-021-5/+7
| | | | | | | | | | | | Unconditionally save the register states when suspending and restore them again at resume time. Register contents were not preserved over suspend, and hence the driver takes false assumptions about them. The clock must be enabled to access the register block. Signed-off-by: Daniel Mack <daniel@caiaq.de> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* ASoC: Fix continuation line formatsJoe Perches2010-02-021-2/+1
| | | | | | | | | String constants that are continued on subsequent lines with \ are not good. Signed-off-by: Joe Perches <joe@perches.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* ASoC: Fix BCLK calculation of WM8994Joonyoung Shim2010-02-021-5/+2
| | | | | | | | This fixes BCLK calculation and removes unnecessary check code. Signed-off-by: Joonyoung Shim <jy0922.shim@samsung.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* ASoC: Fix WM8994 dependencyMark Brown2010-02-021-1/+1
| | | | | | | The dependency on MFD_WM8994 rather than I2C went awry. Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk>
* ASoC: Add WM8994 CODEC driverMark Brown2010-02-014-0/+3902
| | | | | | | | | | | The WM8994 is a highly integrated ultra-low power hi-fi audio subsystem designed for smartphones and other portable devices rich in multimedia features. It provides advanced digital mixing facilities enabling low power high quality interconnection of CPU, baseband and other audio sources through flexible digital and analogue routing, and integrates a class W headphone driver and stereo class D speaker drivers. Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* ASoC: Activate DCS correction for WM8993Mark Brown2010-02-011-1/+2
| | | | | | | Use a two code correction for optimal performance. Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk>
* ASoC: Improved wm_hubs headphone handlingMark Brown2010-02-013-26/+130
| | | | | | | | | | | | | | | Perform DC servo offset calibration using a series update sequence rather than startup update sequence, tuning the configuration of the WM8993 DC servo to make best use of this. Also introduce currently unused data allowing us to correct for any systematic errors in the DC servo calibration results and an alternative startup path for the headphone output which performs better with some chip revisions. The alternative setup sequence is enabled for WM8993. Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk>
* ASoC: Fix continuation line formatsJoe Perches2010-02-013-10/+4
| | | | | | | | | String constants that are continued on subsequent lines with \ are not good. Signed-off-by: Joe Perches <joe@perches.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* ASoC: improve MCLKDIV calculation in wm8978, when OPCLK is not usedGuennadi Liakhovetski2010-02-011-37/+78
| | | | | | | | | | | In case, if OPCLK is not used, and PLL is used for driving the codec, the choice of PLL output frequency could result in a needlessly imprecise system clock frequency. Use an iterative process to select a precise configuration. Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* ASoC: clean up wm8974 and wm8978 clock divider handlingGuennadi Liakhovetski2010-01-295-41/+9
| | | | | | | | | | | | wm8974 and wm8978 codec drivers control DAC and ADC oversampling rates in their .set_clkdiv() methods, which is wrong, because these are simple boolean switches and not clock dividers. Move these bits to sound controls. Also remove manual configuration of the MCLK divider in wm8978, since it is configured automatically. Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* Merge branch 'for-2.6.33' into for-2.6.34Mark Brown2010-01-292-2/+2
|\
| * ASoC: AM3517: ASoC driver not getting compiledAnuj Aggarwal2010-01-291-1/+1
| | | | | | | | | | | | | | | | | | | | | | Commit 761c9d45 (ASoC: Fix build of OMAP sound drivers) changes CONFIG_MACH_OMAP3517EVM -> CONFIG_SND_OMAP_SOC_OMAP3517EVM in the Makefile. Whereas the config option defined in Kconfig is SND_OMAP_SOC_AM3517EVM. Because of this, ASoC driver for AM3517 was not getting compiled. Signed-off-by: Anuj Aggarwal <anuj.aggarwal@ti.com> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
| * ASoC: AIC23: Fixing writes to non-existing registers in resume functionAnuj Aggarwal2010-01-291-1/+1
| | | | | | | | | | | | | | | | | | | | Commit e9ff5eb2 (Fixing infinite loop in resume path) uses wrong AIC23 register in resume function because of which register writes happen on some non-existing registers. Signed-off-by: Anuj Aggarwal <anuj.aggarwal@ti.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | ASoC: remove bogus SLEEP mode from wm8978 driverGuennadi Liakhovetski2010-01-291-5/+0
| | | | | | | | | | | | | | | | | | | | Tests showed, that bit 6 of the WM8978_POWER_MANAGEMENT_2 register of wm8978 affects codec clocks. Being useless for suspend / resume, it cannot be used in bias-level control either. Remove this bit handling. Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | ASoC: add support for the sh7722 Migo-R boardGuennadi Liakhovetski2010-01-293-0/+232
| | | | | | | | | | | | | | | | | | | | Add support for audio on sh7722-based Migo-R boards, using SIU and wm8978 codec, recording via external microphone and playback via headphones are implemented. Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | ASoC: AC97: SMDK-WM9713: Convert notes from cset to ssetJassi Brar2010-01-291-16/+7
| | | | | | | | | | | | | | | | | | It's more robust when references are provided in control names rather than numid. Signed-off-by: Jassi Brar <jassi.brar@samsung.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | ASoC: Set codec->dev for AC97 devicesMark Brown2010-01-281-0/+1
| | | | | | | | | | Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk>
* | ASoC: Add TLV information and additional volumes to WM9713Mark Brown2010-01-281-16/+44
| | | | | | | | | | | | | | | | Also renames a few things to make volumes and switches match up in alsamixer. Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk>
* | ASoC: Remove version display from WM9713Mark Brown2010-01-281-4/+0
| | | | | | | | | | | | | | | | The version isn't being updated or used, the kernel revision tracking is enough. Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk>
* | ASoC: TWL4030: Modify codec default settingsPeter Ujfalusi2010-01-281-4/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Change the legacy default register configuration, which left some internal components on. Now we have either DAPM, or other ways to control these bits, so there is no need to enable them by default. The affected parts: Disable ADCL and ADCR Disable ARXL2 and ARXR2 analog PGA (playback) Disable APLL by default Signed-off-by: Peter Ujfalusi <peter.ujfalusi@nokia.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | ASoC: fsi: Add spin lock operation for accessing shared areaKuninori Morimoto2010-01-281-3/+26
| | | | | | | | | | | | | | | | | | fsi_master_xxx function should be protected by spin lock, because it are used from both FSI-A and FSI-B. Signed-off-by: Kuninori Morimoto <morimoto.kuninori@renesas.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | ASoC: add a WM8978 codec driverGuennadi Liakhovetski2010-01-274-0/+1219
| | | | | | | | | | | | | | | | | | | | | | The WM8978 codec from Wolfson Microelectronics is very similar to wm8974, but is stereo and also has some differences in pin configuration and internal signal routing. This driver is based on wm8974 and takes the differences into account. Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | ASoC: Note jumper settings for smdk_wm9713 driver on SMDK6410Mark Brown2010-01-271-0/+6
| | | | | | | | | | | | | | | | The board supports both GPIO sets for the AC97 bus and the analogue outputs can be switched between this and the WM8580 so add some comments saying what the setup the standard kernel expects is. Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | ASoC: AC97: S3C2443: Remove unused driverJassi Brar2010-01-274-462/+0
| | | | | | | | | | | | | | | | | | Since, we have generic AC97 controller driver and all the machines have moved to that, there is no need for old s3c2443-ac97.c to exist. Signed-off-by: Jassi Brar <jassi.brar@samsung.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | ASoC: AC97: LN2440SBC: Switch to s3c-ac97.cJassi Brar2010-01-272-6/+5
| | | | | | | | | | | | | | | | Switch to use s3c-ac97.c AC97 controller driver. Signed-off-by: Jassi Brar <jassi.brar@samsung.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | ASoC: AC97: SMDK2443: Switch to s3c-ac97.cJassi Brar2010-01-272-3/+5
| | | | | | | | | | | | | | | | Switch to use s3c-ac97.c AC97 controller driver. Signed-off-by: Jassi Brar <jassi.brar@samsung.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | ASoC: AC97: SMDK: Add wm9713 machine driverJassi Brar2010-01-273-0/+107
| | | | | | | | | | | | | | | | | | This patch adds the common machine driver for SMDKs that have a WM9713 codec attched to the AC97 controller. Signed-off-by: Jassi Brar <jassi.brar@samsung.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | ASoC: AC97: S3C: Add controller driverJassi Brar2010-01-274-2/+548
| | | | | | | | | | | | | | | | Add the AC97 controller driver for Samsung SoCs that have one. Signed-off-by: Jassi Brar <jassi.brar@samsung.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | ASoC: ad1938: use soc-cache framework for codec registers accessBarry Song2010-01-272-128/+144
| | | | | | | | | | | | Signed-off-by: Barry Song <Barry.Song@analog.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | ASoC: ad1836: use soc-cache framework for codec registers accessBarry Song2010-01-272-69/+90
| | | | | | | | | | | | Signed-off-by: Barry Song <Barry.Song@analog.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | ASoC: DaVinci: Fix stream restart errorChaithrika U S2010-01-261-3/+2
| | | | | | | | | | | | | | | | | | | | | | | | Sometimes after a suspend-resume cycle, the ALSA application restarts the stream when resume fails and McASP fails to work as the clock is not enabled. This patch corrects this bug. Testes on TI DA850/OMAP-L138 EVM. Signed-off-by: Chaithrika U S <chaithrika@ti.com> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
* | Merge branch 'for-2.6.33' into for-2.6.34Mark Brown2010-01-251246-11430/+31096
|\ \ | |/
| * ASoC: fix a memory-leak in wm8903Guennadi Liakhovetski2010-01-251-1/+2
| | | | | | | | | | | | | | | | | | Remember to free the temporary register-cache. Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de> Acked-by: Liam Girdwood <lrg@slimlogic.co.uk> Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Cc: stable@kernel.org
| * Linux 2.6.33-rc5Linus Torvalds2010-01-211-1/+1
| |
| * Merge branch 'perf-fixes-for-linus' of ↵Linus Torvalds2010-01-218-12/+35
| |\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: perf: x86: Add support for the ANY bit perf: Change the is_software_event() definition perf: Honour event state for aux stream data perf: Fix perf_event_do_pending() fallback callsite perf kmem: Print usage help for unknown commands perf kmem: Increase "Hit" column length hw-breakpoints, perf: Fix broken mmiotrace due to dr6 by reference change perf timechart: Use tid not pid for COMM change
| | * perf: x86: Add support for the ANY bitStephane Eranian2010-01-212-0/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Propagate the ANY bit into the fixed counter config for v3 and higher. Signed-off-by: Stephane Eranian <eranian@google.com> [a.p.zijlstra@chello.nl: split from larger patch] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <4b5430c6.0f975e0a.1bf9.ffff85fe@mx.google.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| | * perf: Change the is_software_event() definitionPeter Zijlstra2010-01-211-3/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | The is_software_event() definition always confuses me because its an exclusive expression, make it an inclusive one. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| | * perf: Honour event state for aux stream dataPeter Zijlstra2010-01-211-0/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Anton reported that perf record kept receiving events even after calling ioctl(PERF_EVENT_IOC_DISABLE). It turns out that FORK,COMM and MMAP events didn't respect the disabled state and kept flowing in. Reported-by: Anton Blanchard <anton@samba.org> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Tested-by: Anton Blanchard <anton@samba.org> LKML-Reference: <1263459187.4244.265.camel@laptop> CC: stable@kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
| | * perf: Fix perf_event_do_pending() fallback callsitePeter Zijlstra2010-01-211-2/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Paul questioned the context in which we should call perf_event_do_pending(). After looking at that I found that it should be called from IRQ context these days, however the fallback call-site is placed in softirq context. Ammend this by placing the callback in the IRQ timer path. Reported-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1263374859.4244.192.camel@laptop> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| | * perf kmem: Print usage help for unknown commandsPekka Enberg2010-01-201-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes "perf kmem" to print usage help instead of doing nothing. Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> LKML-Reference: <1263921971-10782-1-git-send-email-penberg@cs.helsinki.fi> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| | * perf kmem: Increase "Hit" column lengthPekka Enberg2010-01-201-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | It's fairly easy to overflow the "Hit" column with just few seconds of tracing so increase the column length to avoid broken formatting. Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> LKML-Reference: <1263921803-10214-1-git-send-email-penberg@cs.helsinki.fi> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| | * hw-breakpoints, perf: Fix broken mmiotrace due to dr6 by reference changeLuca Barbieri2010-01-171-3/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit 62edab9056a6cf0c9207339c8892c923a5217e45 (from June 2009 but merged in 2.6.33) changes notify_die to pass dr6 by reference. However, it forgets to fix the check for DR_STEP in kmmio.c, breaking mmiotrace. It also passes a wrong value to the post handler. This simple fix makes mmiotrace work again. Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> Acked-by: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1263634770-14578-1-git-send-email-luca@luca-barbieri.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| | * perf timechart: Use tid not pid for COMM changeArjan van de Ven2010-01-171-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | A process that changes its comm field, does this on a per kernel task struct basis. The timechart tool used, incorrectly, the pid to track this, and should have used the tid instead... Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> CC: <stable@kernel.org> LKML-Reference: <20100116125319.34ac3edd@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | Merge branch 'sched-fixes-for-linus' of ↵Linus Torvalds2010-01-213-3/+6
| |\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: sched: Reassign prev and switch_count when reacquire_kernel_lock() fail sched: Fix vmark regression on big machines
| | * | sched: Reassign prev and switch_count when reacquire_kernel_lock() failYong Zhang2010-01-211-1/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Assume A->B schedule is processing, if B have acquired BKL before and it need reschedule this time. Then on B's context, it will go to need_resched_nonpreemptible for reschedule. But at this time, prev and switch_count are related to A. It's wrong and will lead to incorrect scheduler statistics. Signed-off-by: Yong Zhang <yong.zhang0@gmail.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <2674af741001102238w7b0ddcadref00d345e2181d11@mail.gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| | * | sched: Fix vmark regression on big machinesMike Galbraith2010-01-212-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | SD_PREFER_SIBLING is set at the CPU domain level if power saving isn't enabled, leading to many cache misses on large machines as we traverse looking for an idle shared cache to wake to. Change the enabler of select_idle_sibling() to SD_SHARE_PKG_RESOURCES, and enable same at the sibling domain level. Reported-by: Lin Ming <ming.m.lin@intel.com> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1262612696.15495.15.camel@marge.simson.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
generated by cgit v1.1 at 2025-01-30 14:49:13 +0000