summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Merge branch 'timers-cleanup-for-linus' of ↵Linus Torvalds2011-07-2240-359/+199
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'timers-cleanup-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: mips: Fix i8253 clockevent fallout i8253: Cleanup outb/inb magic arm: Footbridge: Use common i8253 clockevent mips: Use common i8253 clockevent x86: Use common i8253 clockevent i8253: Create common clockevent implementation i8253: Export i8253_lock unconditionally pcpskr: MIPS: Make config dependencies finer grained pcspkr: Cleanup Kconfig dependencies i8253: Move remaining content and delete asm/i8253.h i8253: Consolidate definitions of PIT_LATCH x86: i8253: Consolidate definitions of global_clock_event i8253: Alpha, PowerPC: Remove unused asm/8253pit.h alpha: i8253: Cleanup remaining users of i8253pit.h i8253: Remove I8253_LOCK config i8253: Make pcsp sound driver use the shared i8253_lock i8253: Make pcspkr input driver use the shared i8253_lock i8253: Consolidate all kernel definitions of i8253_lock i8253: Unify all kernel declarations of i8253_lock i8253: Create linux/i8253.h and use it in all 8253 related files
| * mips: Fix i8253 clockevent falloutThomas Gleixner2011-07-221-1/+1
| | | | | | | | | | | | | | | | pit_clockevent wants to replaced in the argument of the callback function as well. Reported-by; Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * i8253: Cleanup outb/inb magicThomas Gleixner2011-07-012-6/+3
| | | | | | | | | | | | | | | | | | | | | | Remove the hysterical outb/inb_pit defines and use outb_p/inb_p in the code. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Russell King <linux@arm.linux.org.uk> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: John Stultz <john.stultz@linaro.org> Link: http://lkml.kernel.org/r/20110609130622.348437125@linutronix.de
| * arm: Footbridge: Use common i8253 clockeventThomas Gleixner2011-07-012-52/+4
| | | | | | | | | | | | | | | | Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Russell King <linux@arm.linux.org.uk> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: John Stultz <john.stultz@linaro.org> Link: http://lkml.kernel.org/r/20110609130622.241312122@linutronix.de
| * mips: Use common i8253 clockeventThomas Gleixner2011-07-012-95/+3
| | | | | | | | | | | | | | | | Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Russell King <linux@arm.linux.org.uk> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: John Stultz <john.stultz@linaro.org> Link: http://lkml.kernel.org/r/20110609130622.133068765@linutronix.de
| * x86: Use common i8253 clockeventThomas Gleixner2011-07-012-91/+4
| | | | | | | | | | | | | | | | Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Russell King <linux@arm.linux.org.uk> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: John Stultz <john.stultz@linaro.org> Link: http://lkml.kernel.org/r/20110609130622.026152527@linutronix.de
| * i8253: Create common clockevent implementationThomas Gleixner2011-07-013-8/+100
| | | | | | | | | | | | | | | | | | | | | | | | | | | | arm, mips and x86 implement i8253 based clockevents. All the same code copied. Create a common implementation in drivers/clocksource/i8253.c. About time to rename drivers/clocksource/ to something else. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Russell King <linux@arm.linux.org.uk> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: John Stultz <john.stultz@linaro.org> Link: http://lkml.kernel.org/r/20110609130621.921710458@linutronix.de
| * i8253: Export i8253_lock unconditionallyThomas Gleixner2011-06-101-2/+0
| | | | | | | | | | | | | | We don't want to add endless selects and module ifdefs. Reported-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * pcpskr: MIPS: Make config dependencies finer grainedRalf Baechle2011-06-091-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | Only the Siemens-Nixdorf RM series workstations and the Jazz family workstations have PC speakers built in; Malta can connect one via the infamous AMR connector with an AMR sound card or a little creativity. So we don't want to offer the PC speaker driver on all MIPS systems. Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Link: http://lkml.kernel.org/r/20110601180611.061710714@duck.linux-mips.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * pcspkr: Cleanup Kconfig dependenciesRalf Baechle2011-06-098-2/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Lenghty lists of the kind "depends on ARCH1 || ARCH2 ... || ARCH123" are usually either wrong or too coarse grained. Or plain an ugly sin. [ tglx: Fixed up amigaone ] Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Matt Turner <mattst88@gmail.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: linux-alpha@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linuxppc-dev@lists.ozlabs.org Cc: Gerhard Pircher <gerhard_pircher@gmx.net> Link: http://lkml.kernel.org/r/20110601180610.984881988@duck.linux-mips.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * i8253: Move remaining content and delete asm/i8253.hRalf Baechle2011-06-094-21/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Move setup_pit_timer() declaration to the common header file and remove the arch specific ones. [ tglx: Move it to linux/i8253.h instead of asm/mips and asm/x86 ] Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Cc: linux-arm-kernel@lists.infradead.org Cc: Russell King <linux@arm.linux.org.uk> Cc: linux-mips@linux-mips.org Cc: Sergei Shtylyov <sshtylyov@mvista.com Link: http://lkml.kernel.org/r/20110601180610.913463093@duck.linux-mips.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * i8253: Consolidate definitions of PIT_LATCHRalf Baechle2011-06-094-6/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | x86 defines PIT_LATCH as LATCH which in <linux/timex.h> is defined as ((CLOCK_TICK_RATE + HZ/2) / HZ) and <asm/timex.h> again defines CLOCK_TICK_RATE as PIT_TICK_RATE. MIPS defines PIT_LATCH as LATCH which in <linux/timex.h> is defined as ((CLOCK_TICK_RATE + HZ/2) / HZ) and <asm/timex.h> again defines CLOCK_TICK_RATE as 1193182. ARM defines PITCH_LATCH as ((PIT_TICK_RATE + HZ / 2) / HZ) - and that's the sanest thing and equivalent to above definitions so use that as the new definition in <linux/i8253.h>. Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-mips@linux-mips.org Link: http://lkml.kernel.org/r/20110601180610.832810002@duck.linux-mips.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * x86: i8253: Consolidate definitions of global_clock_eventRalf Baechle2011-06-097-5/+8
| | | | | | | | | | | | | | | | | | | | | | | | There are multiple declarations of global_clock_event in header files specific to particular clock event implementations. Consolidate them in <asm/time.h> and make sure all users include that header. Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Cc: Venkatesh Pallipadi (Venki) <venki@google.com> Link: http://lkml.kernel.org/r/20110601180610.762763451@duck.linux-mips.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * i8253: Alpha, PowerPC: Remove unused asm/8253pit.hRalf Baechle2011-06-092-6/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Matt Turner <mattst88@gmail.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20110601180610.684557757@duck.linux-mips.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * alpha: i8253: Cleanup remaining users of i8253pit.hRalf Baechle2011-06-092-2/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | The Alpha <asm/i8253pit.h> header is empty so this inclusion can just be removed. Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Matt Turner <mattst88@gmail.com> Link: http://lkml.kernel.org/r/20110601180610.608083130@duck.linux-mips.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * i8253: Remove I8253_LOCK configThomas Gleixner2011-06-091-0/+2
| | | | | | | | | | | | | | | | | | Now that all extra ifdeffed implementations are gone, depend the lock export on PCSPKR_PLATFORM Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@arm.linux.org.uk>
| * i8253: Make pcsp sound driver use the shared i8253_lockRalf Baechle2011-06-091-7/+1
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Cc: Jaroslav Kysela <perex@perex.cz> Acked-by: Takashi Iwai <tiwai@suse.de> Cc: alsa-devel@alsa-project.org Link: http://lkml.kernel.org/r/20110601180610.532642190@duck.linux-mips.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * i8253: Make pcspkr input driver use the shared i8253_lockRalf Baechle2011-06-091-8/+1
| | | | | | | | | | | | | | | | | | Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com> Cc: linux-input@vger.kernel.org Link: http://lkml.kernel.org/r/20110601180610.453577265@duck.linux-mips.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * i8253: Consolidate all kernel definitions of i8253_lockRalf Baechle2011-06-098-10/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Move them to drivers/clocksource/i8253.c and remove the implementations in arch/ [ tglx: Avoid the extra file in lib - folded arch patches in. The export will become conditional in a later step ] Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Link: http://lkml.kernel.org/r/20110601180610.221426078@duck.linux-mips.net Cc: Russell King <linux@arm.linux.org.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * i8253: Unify all kernel declarations of i8253_lockRalf Baechle2011-06-094-31/+14
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-mips@linux-mips.org Link: http://lkml.kernel.org/r/20110601180610.134151920@duck.linux-mips.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * i8253: Create linux/i8253.h and use it in all 8253 related filesRalf Baechle2011-06-0919-18/+29
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Link: http://lkml.kernel.org/r/20110601180610.054254048@duck.linux-mips.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de> arch/arm/mach-footbridge/isa-timer.c | 2 +- arch/mips/cobalt/time.c | 2 +- arch/mips/jazz/irq.c | 2 +- arch/mips/kernel/i8253.c | 2 +- arch/mips/mti-malta/malta-time.c | 2 +- arch/mips/sgi-ip22/ip22-time.c | 2 +- arch/mips/sni/time.c | 2 +- arch/x86/kernel/apic/apic.c | 2 +- arch/x86/kernel/apm_32.c | 2 +- arch/x86/kernel/hpet.c | 2 +- arch/x86/kernel/i8253.c | 2 +- arch/x86/kernel/time.c | 2 +- drivers/block/hd.c | 2 +- drivers/clocksource/i8253.c | 2 +- drivers/input/gameport/gameport.c | 2 +- drivers/input/joystick/analog.c | 2 +- drivers/input/misc/pcspkr.c | 2 +- include/linux/i8253.h | 11 +++++++++++ sound/drivers/pcsp/pcsp.h | 2 +- 19 files changed, 29 insertions(+), 18 deletions(-)
* | Merge branch 'sched-core-for-linus' of ↵Linus Torvalds2011-07-2221-174/+145
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (24 commits) sched: Cleanup duplicate local variable in [enqueue|dequeue]_task_fair sched: Replace use of entity_key() sched: Separate group-scheduling code more clearly sched: Reorder root_domain to remove 64 bit alignment padding sched: Do not attempt to destroy uninitialized rt_bandwidth sched: Remove unused function cpu_cfs_rq() sched: Fix (harmless) typo 'CONFG_FAIR_GROUP_SCHED' sched, cgroup: Optimize load_balance_fair() sched: Don't update shares twice on on_rq parent sched: update correct entity's runtime in check_preempt_wakeup() xtensa: Use generic config PREEMPT definition h8300: Use generic config PREEMPT definition m32r: Use generic PREEMPT config sched: Skip autogroup when looking for all rt sched groups sched: Simplify mutex_spin_on_owner() sched: Remove rcu_read_lock() from wake_affine() sched: Generalize sleep inside spinlock detection sched: Make sleeping inside spinlock detection working in !CONFIG_PREEMPT sched: Isolate preempt counting in its own config option sched: Remove pointless in_atomic() definition check ...
| * | sched: Cleanup duplicate local variable in [enqueue|dequeue]_task_fairLin Ming2011-07-221-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | No need to define a new "cfs_rq" variable in the "for" block. Just use the one at the top of the function. Signed-off-by: Lin Ming <ming.m.lin@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1311297271.3938.1352.camel@minggr.sh.intel.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | sched: Replace use of entity_key()Stephan Baerwolf2011-07-211-7/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | "entity_key()" is only used in "__enqueue_entity()" and its only function is to subtract a tasks vruntime by its groups minvruntime. Before this patch a rbtree enqueue-decision is done by comparing two tasks in the style: "if (entity_key(cfs_rq, se) < entity_key(cfs_rq, entry))" which would be "if (se->vruntime-cfs_rq->min_vruntime < entry->vruntime-cfs_rq->min_vruntime)" or (if reducing cfs_rq->min_vruntime out) "if (se->vruntime < entry->vruntime)" which is "if (entity_before(se, entry))" So we do not need "entity_key()". If "entity_before()" is inline we will also save one subtraction (only one, because "entity_key(cfs_rq, se)" was cached in "key") Signed-off-by: Stephan Baerwolf <stephan.baerwolf@tu-ilmenau.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/n/tip-ns12mnd2h5w8rb9agd8hnsfk@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | sched: Separate group-scheduling code more clearlyJan H. Schönherr2011-07-211-24/+19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Clean up cfs/rt runqueue initialization by moving group scheduling related code into the corresponding functions. Also, keep group scheduling as an add-on, so that things are only done additionally, i. e. remove the init_*_rq() calls from init_tg_*_entry(). (This removes a redundant initalization during sched_init()). In case of group scheduling rt_rq->highest_prio.curr is now initialized twice, but adding another #ifdef seems not worth it. Signed-off-by: Jan H. Schönherr <schnhrr@cs.tu-berlin.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1310661163-16606-1-git-send-email-schnhrr@cs.tu-berlin.de Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | sched: Reorder root_domain to remove 64 bit alignment paddingRichard Kennedy2011-07-211-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Reorder root_domain to remove 8 bytes of alignment padding on 64 bit builds, this shrinks the size from 1736 to 1728 bytes, therefore using one fewer cachelines. Signed-off-by: Richard Kennedy <richard@rsk.demon.co.uk> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1310726492.1977.5.camel@castor.rsk Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | sched: Do not attempt to destroy uninitialized rt_bandwidthBianca Lutz2011-07-211-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If a task group is to be created and alloc_fair_sched_group() fails, then the rt_bandwidth of the corresponding task group is not yet initialized. The caller, sched_create_group(), starts a clean up procedure which calls free_rt_sched_group() which unconditionally destroys the not yet initialized rt_bandwidth. This crashes or hangs the system in lock_hrtimer_base(): UP systems dereference a NULL pointer, while SMP systems loop endlessly on a condition that cannot become true. This patch simply avoids the destruction of rt_bandwidth when the initialization code path was not reached. (This was discovered by accident with a custom kernel modification.) Signed-off-by: Bianca Lutz <sowilo@cs.tu-berlin.de> Signed-off-by: Jan Schoenherr <schnhrr@cs.tu-berlin.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1310580816-10861-7-git-send-email-schnhrr@cs.tu-berlin.de Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | sched: Remove unused function cpu_cfs_rq()Jan Schoenherr2011-07-211-13/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The last reference to cpu_cfs_rq() was removed with commit 88ec22d3 ("sched: Remove the cfs_rq dependency from set_task_cpu()"). Thus, remove this function, too. Signed-off-by: Jan Schoenherr <schnhrr@cs.tu-berlin.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1310580816-10861-3-git-send-email-schnhrr@cs.tu-berlin.de Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | sched: Fix (harmless) typo 'CONFG_FAIR_GROUP_SCHED'Jan Schoenherr2011-07-211-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes a typo located in a comment. Signed-off-by: Jan Schoenherr <schnhrr@cs.tu-berlin.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1310580816-10861-2-git-send-email-schnhrr@cs.tu-berlin.de Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | sched, cgroup: Optimize load_balance_fair()Peter Zijlstra2011-07-212-37/+35
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Use for_each_leaf_cfs_rq() instead of list_for_each_entry_rcu(), this achieves that load_balance_fair() only iterates those task_groups that actually have tasks on busiest, and that we iterate bottom-up, trying to move light groups before the heavier ones. No idea if it will actually work out to be beneficial in practice, does anybody have a cgroup workload that might show a difference one way or the other? [ Also move update_h_load to sched_fair.c, loosing #ifdef-ery ] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Reviewed-by: Paul Turner <pjt@google.com> Link: http://lkml.kernel.org/r/1310557009.2586.28.camel@twins Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | sched: Don't update shares twice on on_rq parentPaul Turner2011-07-211-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In dequeue_task_fair() we bail on dequeue when we encounter a parenting entity with additional weight. However, we perform a double shares update on this entity as we continue the shares update traversal from this point, despite dequeue_entity() having already updated its queuing cfs_rq. Avoid this by starting from the parent when we resume. Signed-off-by: Paul Turner <pjt@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110707053059.797714697@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | sched: update correct entity's runtime in check_preempt_wakeup()Paul Turner2011-07-211-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | While looking at check_preempt_wakeup() I realized that we are potentially updating the wrong entity in the fair-group scheduling case. In this case the current task's cfs_rq may not be the same as the one used for the comparison between the waking task and the existing task's vruntime. This potentially results in us using a stale vruntime in the pre-emption decision, providing a small false preference for the previous task. The effects of this are bounded since we always perform a hierarchal update on the tick. Signed-off-by: Paul Turner <pjt@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/CAPM31R+2Ke2urUZKao5W92_LupdR4AYEv-EZWiJ3tG=tEes2cw@mail.gmail.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | Merge branch 'linus' into sched/coreIngo Molnar2011-07-21542-2825/+28625
| |\ \ | | | | | | | | | | | | | | | | | | | | Merge reason: pick up the latest scheduler fixes. Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | xtensa: Use generic config PREEMPT definitionFrederic Weisbecker2011-07-051-12/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | So that it can handle the new CONFIG_PREEMPT_COUNT. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Chris Zankel <chris@zankel.net>
| * | | h8300: Use generic config PREEMPT definitionFrederic Weisbecker2011-07-051-3/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | So that it can handle the new CONFIG_PREEMPT_COUNT. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
| * | | m32r: Use generic PREEMPT configFrederic Weisbecker2011-07-051-11/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Use the generic preempt config definition in m32r instead of using a custom one. This also makes it handle the new CONFIG_PREEMPT_COUNT that need to be selected by CONFIG_PREEMPT. Without that it breaks kernel/sched.c: In function 'preempt_schedule': kernel/sched.c:4364: error: implicit declaration of function 'add_preempt_count_notrace' kernel/sched.c:4366: error: implicit declaration of function 'sub_preempt_count_notrace' Reported-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Hirokazu Takata <takata@linux-m32r.org>
| * | | Merge branch 'sched/core-v2' of ↵Ingo Molnar2011-07-0115-34/+46
| |\ \ \ | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing into sched/core
| | * | | sched: Generalize sleep inside spinlock detectionFrederic Weisbecker2011-06-238-10/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The sleeping inside spinlock detection is actually used for more general sleeping inside atomic sections debugging: preemption disabled, rcu read side critical sections, interrupts, interrupt disabled, etc... Change the name of the config and its help section to reflect its more general role. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu>
| | * | | sched: Make sleeping inside spinlock detection working in !CONFIG_PREEMPTFrederic Weisbecker2011-06-101-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Select CONFIG_PREEMPT_COUNT when we enable the sleeping inside spinlock detection, so that the preempt offset gets correctly incremented/decremented from preempt_disable()/preempt_enable(). This makes the preempt count eventually working in !CONFIG_PREEMPT when that debug option is set and thus fixes the detection of explicit preemption disabled sections under such config. Code that sleeps in explicitly preempt disabled section can be finally spotted in non-preemptible kernels. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
| | * | | sched: Isolate preempt counting in its own config optionFrederic Weisbecker2011-06-108-22/+33
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Create a new CONFIG_PREEMPT_COUNT that handles the inc/dec of preempt count offset independently. So that the offset can be updated by preempt_disable() and preempt_enable() even without the need for CONFIG_PREEMPT beeing set. This prepares to make CONFIG_DEBUG_SPINLOCK_SLEEP working with !CONFIG_PREEMPT where it currently doesn't detect code that sleeps inside explicit preemption disabled sections. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
| | * | | sched: Remove pointless in_atomic() definition checkFrederic Weisbecker2011-06-071-2/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | It's really supposed to be defined here. If it's not then we actually want the build to crash so that we know it, and not keep it silent. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
| * | | | sched: Skip autogroup when looking for all rt sched groupsYong Zhang2011-07-012-5/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Since commit ec514c48 ("sched: Fix rt_rq runtime leakage bug") 'cat /proc/sched_debug' will print data of root_task_group.rt_rq multiple times. This is because autogroup does not have its own rt group, instead rt group of autogroup is linked to root_task_group. So skip it when we are looking for all rt sched groups, and it will also save some noop operation against root_task_group when __disable_runtime()/__enable_runtime(). -v2: Based on Cheng Xu's idea which uses less code. Signed-off-by: Yong Zhang <yong.zhang0@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Cheng Xu <chengxu@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/BANLkTi=87P3RoTF_UEtamNfc_XGxQXE__Q@mail.gmail.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | | sched: Simplify mutex_spin_on_owner()Thomas Gleixner2011-07-011-16/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | It does not make sense to rcu_read_lock/unlock() in every loop iteration while spinning on the mutex. Move the rcu protection outside the loop. Also simplify the return path to always check for lock->owner == NULL which meets the requirements of both owner changed and need_resched() caused loop exits. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1106101458350.11814@ionos Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | | sched: Remove rcu_read_lock() from wake_affine()Nikunj A. Dadhania2011-07-011-2/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | wake_affine() is only called from one path: select_task_rq_fair(), which already has the RCU read lock held. Signed-off-by: Nikunj A. Dadhania <nikunj@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/20110607101251.777.34547.stgit@IBM-009124035060.in.ibm.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | | Merge commit 'v3.0-rc5' into sched/coreIngo Molnar2011-07-012032-28109/+52386
| |\ \ \ \ | | |/ / / | |/| | | | | | | | | | | | | | | | | | Merge reason: Move to a (much) newer base. Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | | Merge branch 'unlikely/sched' of ↵Ingo Molnar2011-06-032-4/+4
| |\ \ \ \ | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into sched/urgent
| | * | | | sched: Remove unlikely() from ttwu_post_activationSteven Rostedt2010-12-131-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The unlikely() used in ttwu_post_activation() tests if the rq->idle_stamp is set. But since this is for a wakeup, and wakeups happen when tasks block on IO, and blocking tasks on IO may put the system into idle, this can actually be a common occurence. Running the annotated branch profiler on an average desktop running firefox, evolution, xchat and distcc, the report shows: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 34884862 146110926 80 ttwu_post_activation sched.c 2309 80% of the time, this unlikely is incorrect. Best not to assume what the result is, and just remove the branch annotation. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
| | * | | | sched: Remove unlikely() from rt_policy() in sched.cSteven Rostedt2010-12-131-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The rt_policy() has an unlikely() that the policy it is checking is of RT priority (SCHED_FIFO or SCHED_RR). According to the annotate branch profiler it is incorrect most of the time: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 36667 654674 94 rt_policy sched.c 126 This makes sense because the rt_policy() is used by the sched_set_scheduler() and nice(). Although users may use sys_nice a bit, all RT users use the sched_set_scheduler() to set their RT priority, including kernel threads. The above numbers were from a normal desktop computer running firefox, evolution, xchat and was part of a distcc compile farm. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
| | * | | | sched: Change pick_next_task_rt from unlikely to likelySteven Rostedt2010-12-131-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The if (unlikely(!rt_rq->rt_nr_running)) test in pick_next_task_rt() tests if there is another rt task ready to run. If so, then pick it. In most systems, only one RT task runs at a time most of the time. Running the branch unlikely annotator profiler on a system doing average work "running firefox, evolution, xchat, distcc builds, etc", it showed the following: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 324344 135104992 99 _pick_next_task_rt sched_rt.c 1064 99% of the time the condition is true. When an RT task schedules out, it is unlikely that another RT task is waiting to run on that same run queue. Simply remove the unlikely() condition. Acked-by: Gregory Haskins <ghaskins@novell.com> Cc:Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
| | * | | | sched: Cleanup pre_schedule_rtYong Zhang2010-12-131-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Since [commit 9a897c5a: sched: RT-balance, replace hooks with pre/post schedule and wakeup methods] we must call pre_schedule_rt if prev is rt task. So condition rt_task(prev) is always true and the 'unlikely' declaration is simply incorrect. Signed-off-by: Yong Zhang <yong.zhang0@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
generated by cgit v1.2.3 (git 2.25.1) at 2025-01-01 14:43:01 +0000