aboutsummaryrefslogtreecommitdiffstats
path: root/kernel
Commit message (Collapse)AuthorAge
* headers: taskstats_kern.h trimAlexey Dobriyan2009-09-18
| | | | | | | | Remove net/genetlink.h inclusion, now sched.c won't be recompiled because of some networking changes. Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* Merge branch 'timers-for-linus' of ↵Linus Torvalds2009-09-18
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (34 commits) time: Prevent 32 bit overflow with set_normalized_timespec() clocksource: Delay clocksource down rating to late boot clocksource: clocksource_select must be called with mutex locked clocksource: Resolve cpu hotplug dead lock with TSC unstable, fix crash timers: Drop a function prototype clocksource: Resolve cpu hotplug dead lock with TSC unstable timer.c: Fix S/390 comments timekeeping: Fix invalid getboottime() value timekeeping: Fix up read_persistent_clock() breakage on sh timekeeping: Increase granularity of read_persistent_clock(), build fix time: Introduce CLOCK_REALTIME_COARSE x86: Do not unregister PIT clocksource on PIT oneshot setup/shutdown clocksource: Avoid clocksource watchdog circular locking dependency clocksource: Protect the watchdog rating changes with clocksource_mutex clocksource: Call clocksource_change_rating() outside of watchdog_lock timekeeping: Introduce read_boot_clock timekeeping: Increase granularity of read_persistent_clock() timekeeping: Update clocksource with stop_machine timekeeping: Add timekeeper read_clock helper functions timekeeping: Move NTP adjusted clock multiplier to struct timekeeper ... Fix trivial conflict due to MIPS lemote -> loongson renaming.
| * time: Prevent 32 bit overflow with set_normalized_timespec()Thomas Gleixner2009-09-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | set_normalized_timespec() nsec argument is of type long. The recent timekeeping changes of ktime_get_ts() feed ts->tv_nsec + tomono.tv_nsec + nsecs to set_normalized_timespec(). On 32 bit machines that sum can be larger than (1 << 31) and therefor result in a negative value which screws up the result completely. Make the nsec argument of set_normalized_timespec() s64 to fix the problem at hand. This also prevents similar problems for future users of set_normalized_timespec(). Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Carsten Emde <carsten.emde@osadl.org> LKML-Reference: <new-submission> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: John Stultz <johnstul@us.ibm.com>
| * clocksource: Delay clocksource down rating to late bootThomas Gleixner2009-09-14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The down rating of clock sources in the early boot process via the clock source watchdog mechanism can happen way before the per cpu event queues are initialized. This leads to a boot crash on x86 when the TSC is marked unstable in the SMP bring up. The selection of a clock source for time keeping happens in the late boot process so we can safely delay the list manipulation until clocksource_done_booting() is called. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <new-submission> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
| * clocksource: clocksource_select must be called with mutex lockedThomas Gleixner2009-09-14
| | | | | | | | | | | | | | | | | | The callers of clocksource_select must hold clocksource_mutex to protect the clocksource_list. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <new-submission> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
| * clocksource: Resolve cpu hotplug dead lock with TSC unstable, fix crashMartin Schwidefsky2009-09-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The watchdog timer is started after the watchdog clocksource and at least one watched clocksource have been registered. The clocksource work element watchdog_work is initialized just before the clocksource timer is started. This is too late for the clocksource_mark_unstable call from native_cpu_up. To fix this use a static initializer for watchdog_work. This resolves a boot crash reported by multiple people. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: John Stultz <johnstul@us.ibm.com> LKML-Reference: <20090911153305.3fe9a361@skybase> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * clocksource: Resolve cpu hotplug dead lock with TSC unstableThomas Gleixner2009-08-28
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Martin Schwidefsky analyzed it: To register a clocksource the clocksource_mutex is acquired and if necessary timekeeping_notify is called to install the clocksource as the timekeeper clock. timekeeping_notify uses stop_machine which needs to take cpu_add_remove_lock mutex. Starting a new cpu is done with the cpu_add_remove_lock mutex held. native_cpu_up checks the tsc of the new cpu and if the tsc is no good clocksource_change_rating is called. Which needs the clocksource_mutex and the deadlock is complete. The solution is to replace the TSC via the clocksource watchdog mechanism. Mark the TSC as unstable and schedule the watchdog work so it gets removed in the watchdog thread context. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <new-submission> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: John Stultz <johnstul@us.ibm.com>
| * timer.c: Fix S/390 commentsRandy Dunlap2009-08-26
| | | | | | | | | | | | | | | | | | | | | | | | Fix typos and add omitted words. Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: akpm <akpm@linux-foundation.org> Cc: linux390@de.ibm.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> LKML-Reference: <20090825143541.43fc2ed8.randy.dunlap@oracle.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * timekeeping: Fix invalid getboottime() valueHiroshi Shimamoto2009-08-25
| | | | | | | | | | | | | | | | | | | | | | | | | | Don't use timespec_add_safe() with wall_to_monotonic, because wall_to_monotonic has negative values which will cause overflow in timespec_add_safe(). That makes btime in /proc/stat invalid. Signed-off-by: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: John Stultz <johnstul@us.ibm.com> Cc: Daniel Walker <dwalker@fifo99.com> LKML-Reference: <4A937FDE.4050506@ct.jp.nec.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * time: Introduce CLOCK_REALTIME_COARSEjohn stultz2009-08-21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | After talking with some application writers who want very fast, but not fine-grained timestamps, I decided to try to implement new clock_ids to clock_gettime(): CLOCK_REALTIME_COARSE and CLOCK_MONOTONIC_COARSE which returns the time at the last tick. This is very fast as we don't have to access any hardware (which can be very painful if you're using something like the acpi_pm clocksource), and we can even use the vdso clock_gettime() method to avoid the syscall. The only trade off is you only get low-res tick grained time resolution. This isn't a new idea, I know Ingo has a patch in the -rt tree that made the vsyscall gettimeofday() return coarse grained time when the vsyscall64 sysctrl was set to 2. However this affects all applications on a system. With this method, applications can choose the proper speed/granularity trade-off for themselves. Signed-off-by: John Stultz <johnstul@us.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: nikolag@ca.ibm.com Cc: Darren Hart <dvhltc@us.ibm.com> Cc: arjan@infradead.org Cc: jonathan@jonmasters.org LKML-Reference: <1250734414.6897.5.camel@localhost.localdomain> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * clocksource: Avoid clocksource watchdog circular locking dependencyMartin Schwidefsky2009-08-19
| | | | | | | | | | | | | | | | | | | | | | | | | | stop_machine from a multithreaded workqueue is not allowed because of a circular locking dependency between cpu_down and the workqueue execution. Use a kernel thread to do the clocksource downgrade. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: john stultz <johnstul@us.ibm.com> LKML-Reference: <20090818170942.3ab80c91@skybase> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * clocksource: Protect the watchdog rating changes with clocksource_mutexThomas Gleixner2009-08-19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Martin pointed out that commit 6ea41d2529 (clocksource: Call clocksource_change_rating() outside of watchdog_lock) has a theoretical reference count problem. The calls to clocksource_change_rating() are now done outside of the clocksource mutex and outside of the watchdog lock. A concurrent clocksource_unregister() could remove the clock. Split out the code which changes the rating from clocksource_change_rating() into __clocksource_change_rating(). Protect the clocksource_watchdog_work() code sequence with the clocksource_mutex() and call __clocksource_change_rating(). LKML-Reference: <alpine.LFD.2.00.0908171038420.2782@localhost.localdomain> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
| * clocksource: Call clocksource_change_rating() outside of watchdog_lockThomas Gleixner2009-08-15
| | | | | | | | | | | | | | | | The changes to the watchdog logic introduced a lock inversion between watchdog_lock and clocksource_mutex. Change the rating outside of watchdog_lock to avoid it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * timekeeping: Introduce read_boot_clockMartin Schwidefsky2009-08-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add the new function read_boot_clock to get the exact time the system has been started. For architectures without support for exact boot time a new weak function is added that returns 0. Use the exact boot time to initialize wall_to_monotonic, or xtime if the read_boot_clock returned 0. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: John Stultz <johnstul@us.ibm.com> Cc: Daniel Walker <dwalker@fifo99.com> LKML-Reference: <20090814134811.296703241@de.ibm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * timekeeping: Increase granularity of read_persistent_clock()Martin Schwidefsky2009-08-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | The persistent clock of some architectures (e.g. s390) have a better granularity than seconds. To reduce the delta between the host clock and the guest clock in a virtualized system change the read_persistent_clock function to return a struct timespec. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: John Stultz <johnstul@us.ibm.com> Cc: Daniel Walker <dwalker@fifo99.com> LKML-Reference: <20090814134811.013873340@de.ibm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * timekeeping: Update clocksource with stop_machineMartin Schwidefsky2009-08-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | update_wall_time calls change_clocksource HZ times per second to check if a new clock source is available. In close to 100% of all calls there is no new clock. Replace the tick based check by an update done with stop_machine. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: John Stultz <johnstul@us.ibm.com> Cc: Daniel Walker <dwalker@fifo99.com> LKML-Reference: <20090814134810.711836357@de.ibm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * timekeeping: Add timekeeper read_clock helper functionsMartin Schwidefsky2009-08-15
| | | | | | | | | | | | | | | | | | | | | | | | Add timekeeper_read_clock_ntp and timekeeper_read_clock_raw and use them for getnstimeofday, ktime_get, ktime_get_ts and getrawmonotonic. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: John Stultz <johnstul@us.ibm.com> Cc: Daniel Walker <dwalker@fifo99.com> LKML-Reference: <20090814134810.435105711@de.ibm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * timekeeping: Move NTP adjusted clock multiplier to struct timekeeperMartin Schwidefsky2009-08-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The clocksource structure has two multipliers, the unmodified multiplier clock->mult_orig and the NTP corrected multiplier clock->mult. The NTP multiplier is misplaced in the struct clocksource, this is private information of the timekeeping code. Add the mult field to the struct timekeeper to contain the NTP corrected value, keep the unmodifed multiplier in clock->mult and remove clock->mult_orig. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: John Stultz <johnstul@us.ibm.com> Cc: Daniel Walker <dwalker@fifo99.com> LKML-Reference: <20090814134810.149047645@de.ibm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * timekeeping: Add xtime_shift and ntp_error_shift to struct timekeeperMartin Schwidefsky2009-08-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The xtime_nsec value in the timekeeper structure is shifted by a few bits to improve precision. This happens to be the same value as the clock->shift. To improve readability add xtime_shift to the timekeeper and use it instead of the clock->shift. Likewise add ntp_error_shift and replace all (NTP_SCALE_SHIFT - clock->shift) expressions. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: John Stultz <johnstul@us.ibm.com> Cc: Daniel Walker <dwalker@fifo99.com> LKML-Reference: <20090814134809.871899606@de.ibm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * timekeeping: Introduce struct timekeeperMartin Schwidefsky2009-08-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add struct timekeeper to keep the internal values timekeeping.c needs in regard to the currently selected clock source. This moves the timekeeping intervals, xtime_nsec and the ntp error value from struct clocksource to struct timekeeper. The raw_time is removed from the clocksource as well. It gets treated like xtime as a global variable. Eventually xtime raw_time should be moved to struct timekeeper. [ tglx: minor cleanup ] Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: John Stultz <johnstul@us.ibm.com> Cc: Daniel Walker <dwalker@fifo99.com> LKML-Reference: <20090814134809.613209842@de.ibm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * clocksource: Move watchdog downgrade to a work queue threadMartin Schwidefsky2009-08-15
| | | | | | | | | | | | | | | | | | | | | | | | | | Move the downgrade of an unstable clocksource from the timer interrupt context into the process context of a work queue thread. This is needed to be able to do the clocksource switch with stop_machine. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: John Stultz <johnstul@us.ibm.com> Cc: Daniel Walker <dwalker@fifo99.com> LKML-Reference: <20090814134809.354926067@de.ibm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * clocksource: Refactor clocksource watchdogMartin Schwidefsky2009-08-15
| | | | | | | | | | | | | | | | | | | | | | | | | | Refactor clocksource watchdog code to make it more readable. Add clocksource_dequeue_watchdog to remove a clocksource from the watchdog list when it is unregistered. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: John Stultz <johnstul@us.ibm.com> Cc: Daniel Walker <dwalker@fifo99.com> LKML-Reference: <20090814134809.110881699@de.ibm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * clocksource: Simplify clocksource watchdog resume logicMartin Schwidefsky2009-08-15
| | | | | | | | | | | | | | | | | | | | | | | | To resume the clocksource watchdog just remove the CLOCK_SOURCE_WATCHDOG bit from the watched clocksource. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: John Stultz <johnstul@us.ibm.com> Cc: Daniel Walker <dwalker@fifo99.com> LKML-Reference: <20090814134808.880925790@de.ibm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * clocksource: Delay clocksource watchdog highres enablementMartin Schwidefsky2009-08-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | The clocksource watchdog marks a clock as highres capable before it checked the deviation from the watchdog clocksource even for a single time. Make sure that the deviation is at least checked once before doing the switch to highres mode. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: John Stultz <johnstul@us.ibm.com> Cc: Daniel Walker <dwalker@fifo99.com> LKML-Reference: <20090814134808.627795883@de.ibm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * clocksource: Cleanup clocksource selectionMartin Schwidefsky2009-08-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If a non high-resolution clocksource is first set as override clock and then registered it becomes active even if the system is in one-shot mode. Move the override check from sysfs_override_clocksource to the clocksource selection. That fixes the bug and simplifies the code. The check in clocksource_register for double registration of the same clocksource is removed without replacement. To find the initial clocksource a new weak function in jiffies.c is defined that returns the jiffies clocksource. The architecture code can then override the weak function with a more suitable clocksource, e.g. the TOD clock on s390. [ tglx: Folded in a fix from John Stultz ] Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Acked-by: John Stultz <johnstul@us.ibm.com> Cc: Daniel Walker <dwalker@fifo99.com> LKML-Reference: <20090814134808.388024160@de.ibm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * timekeeping: Move reset of cycle_last for tsc clocksource to tscMartin Schwidefsky2009-08-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | change_clocksource resets the cycle_last value to zero then sets it to a value read from the clocksource. The reset to zero is required only for the TSC clocksource to make the read_tsc function work after a resume. The reason is that the TSC read function uses cycle_last to detect backwards going TSCs. In the resume case cycle_last contains the TSC value from the last update before the suspend. On resume the TSC starts counting from 0 again and would trip over the cycle_last comparison. This is subtle and surprising. Move the reset to a resume function in the tsc code. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: John Stultz <johnstul@us.ibm.com> Cc: Daniel Walker <dwalker@fifo99.com> LKML-Reference: <20090814134808.142191175@de.ibm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * timekeeping: Remove clocksource inline functionsMartin Schwidefsky2009-08-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The three inline functions clocksource_read, clocksource_enable and clocksource_disable are simple wrappers of an indirect call plus the copy from and to the mult_orig value. The functions are exclusively used by the timekeeping code which has intimate knowledge of the clocksource anyway. Therefore remove the inline functions. No functional change. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Acked-by: John Stultz <johnstul@us.ibm.com> Cc: Daniel Walker <dwalker@fifo99.com> LKML-Reference: <20090814134807.903108946@de.ibm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * timekeeping: Introduce timekeeping_leap_insertJohn Stultz2009-08-15
| | | | | | | | | | | | | | | | | | | | Move the adjustment of xtime, wall_to_monotonic and the update of the vsyscall variables to the timekeeping code. Signed-off-by: John Stultz <johnstul@us.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> LKML-Reference: <20090814134807.609730216@de.ibm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * Merge branch 'linus' into timers/coreThomas Gleixner2009-08-14
| |\ | | | | | | | | | | | | | | | | | | Reason: Martin's timekeeping cleanup series depends on both timers/core and mainline changes. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * | timers: Cache __next_timer_interrupt resultMartin Schwidefsky2009-08-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Each time a cpu goes to sleep on a NOHZ=y system the timer wheel is searched for the next timer interrupt. It can take quite a few cycles to find the next pending timer. This patch adds a field to tvec_base that caches the result of __next_timer_interrupt. The hit ratio is around 80% on my thinkpad under normal use, on a server I've seen hit ratios from 5% to 95% dependent on the workload. -v2: jiffies wrap fixes Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Venki Pallipadi <venkatesh.pallipadi@intel.com> LKML-Reference: <20090721202505.7d56a079@skybase> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | hrtimer: Remove cb_entry from struct hrtimerPeter Zijlstra2009-07-22
| | | | | | | | | | | | | | | | | | | | | | | | It's unused, remove it. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <new-submission>
| * | timekeeping: Move ktime_get() functions to timekeeping.cThomas Gleixner2009-07-07
| | | | | | | | | | | | | | | | | | | | | | | | The ktime_get() functions for GENERIC_TIME=n are still located in hrtimer.c. Move them to time/timekeeping.c where they belong. LKML-Reference: <new-submission> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * | timekeeping: optimized ktime_get[_ts] for GENERIC_TIME=yMartin Schwidefsky2009-07-07
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The generic ktime_get function defined in kernel/hrtimer.c is suboptimial for GENERIC_TIME=y: 0) | ktime_get() { 0) | ktime_get_ts() { 0) | getnstimeofday() { 0) | read_tod_clock() { 0) 0.601 us | } 0) 1.938 us | } 0) | set_normalized_timespec() { 0) 0.602 us | } 0) 4.375 us | } 0) 5.523 us | } Overall there are two read_seqbegin/read_seqretry loops and a lot of unnecessary struct timespec calculations. ktime_get returns a nano second value which is the sum of xtime, wall_to_monotonic and the nano second delta from the clock source. ktime_get can be optimized for GENERIC_TIME=y. The new version only calls clocksource_read: 0) | ktime_get() { 0) | read_tod_clock() { 0) 0.610 us | } 0) 1.977 us | } It uses a single read_seqbegin/readseqretry loop and just adds everthing to a nano second value. ktime_get_ts is optimized in a similar fashion. [ tglx: added WARN_ON(timekeeping_suspended) as in getnstimeofday() ] Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Acked-by: john stultz <johnstul@us.ibm.com> LKML-Reference: <20090707112728.3005244d@skybase> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* | | Merge branch 'sched-core-for-linus' of ↵Linus Torvalds2009-09-18
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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: (37 commits) sched: Fix SD_POWERSAVING_BALANCE|SD_PREFER_LOCAL vs SD_WAKE_AFFINE sched: Stop buddies from hogging the system sched: Add new wakeup preemption mode: WAKEUP_RUNNING sched: Fix TASK_WAKING & loadaverage breakage sched: Disable wakeup balancing sched: Rename flags to wake_flags sched: Clean up the load_idx selection in select_task_rq_fair sched: Optimize cgroup vs wakeup a bit sched: x86: Name old_perf in a unique way sched: Implement a gentler fair-sleepers feature sched: Add SD_PREFER_LOCAL sched: Add a few SYNC hint knobs to play with sched: Fix sync wakeups again sched: Add WF_FORK sched: Rename sync arguments sched: Rename select_task_rq() argument sched: Feature to disable APERF/MPERF cpu_power x86: sched: Provide arch implementations using aperf/mperf x86: Add generic aperf/mperf code x86: Move APERF/MPERF into a X86_FEATURE ... Fix up trivial conflict in arch/x86/include/asm/processor.h due to nearby addition of amd_get_nb_id() declaration from the EDAC merge.
| * | | sched: Fix SD_POWERSAVING_BALANCE|SD_PREFER_LOCAL vs SD_WAKE_AFFINEPeter Zijlstra2009-09-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The SD_POWERSAVING_BALANCE|SD_PREFER_LOCAL code can break out of the domain iteration early, making us miss the SD_WAKE_AFFINE bits. Fix this by continuing iteration until there is no need for a larger domain. This also cleans up the cgroup stuff a bit, but not having two update_shares() invocations. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | sched: Stop buddies from hogging the systemPeter Zijlstra2009-09-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Clear buddies more agressively. The (theoretical, haven't actually observed any of this) problem is that when we do not select either buddy in pick_next_entity() because they are too far ahead of the left-most task, we do not clear the buddies. This means that as soon as we service the left-most task, these same buddies will be tried again on the next schedule. Now if the left-most task was a pure hog, it wouldn't have done any wakeups and it wouldn't have set buddies of its own. That leads to the old buddies dominating, which would lead to bad latencies. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | sched: Add new wakeup preemption mode: WAKEUP_RUNNINGPeter Zijlstra2009-09-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Create a new wakeup preemption mode, preempt towards tasks that run shorter on avg. It sets next buddy to be sure we actually run the task we preempted for. Test results: root@twins:~# while :; do :; done & [1] 6537 root@twins:~# while :; do :; done & [2] 6538 root@twins:~# while :; do :; done & [3] 6539 root@twins:~# while :; do :; done & [4] 6540 root@twins:/home/peter# ./latt -c4 sleep 4 Entries: 48 (clients=4) Averages: ------------------------------ Max 4750 usec Avg 497 usec Stdev 737 usec root@twins:/home/peter# echo WAKEUP_RUNNING > /debug/sched_features root@twins:/home/peter# ./latt -c4 sleep 4 Entries: 48 (clients=4) Averages: ------------------------------ Max 14 usec Avg 5 usec Stdev 3 usec Disabled by default - needs more testing. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Ingo Molnar <mingo@elte.hu> LKML-Reference: <new-submission>
| * | | sched: Fix TASK_WAKING & loadaverage breakageIngo Molnar2009-09-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fix this: top - 21:54:00 up 2:59, 1 user, load average: 432512.33, 426421.74, 417432.74 Which happens because we now set TASK_WAKING before activate_task(). Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | sched: Rename flags to wake_flagsPeter Zijlstra2009-09-16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | For consistencies sake, rename the argument (again). Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | sched: Clean up the load_idx selection in select_task_rq_fairPeter Zijlstra2009-09-16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Clean up the code a little. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | sched: Optimize cgroup vs wakeup a bitPeter Zijlstra2009-09-16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We don't need to call update_shares() for each domain we iterate, just got the largets one. However, we should call it before wake_affine() as well, so that that can use up-to-date values too. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | sched: Implement a gentler fair-sleepers featureIngo Molnar2009-09-16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add back FAIR_SLEEPERS and GENTLE_FAIR_SLEEPERS. FAIR_SLEEPERS is the old logic: credit sleepers with their sleep time. GENTLE_FAIR_SLEEPERS dampens this a bit: 50% of their sleep time gets credited. The hope here is to still give the benefits of fair-sleepers logic (quick wakeups, etc.) while not allow them to have 100% of their sleep time as if they were running. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | sched: Add SD_PREFER_LOCALPeter Zijlstra2009-09-16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | And turn it on for NUMA and MC domains. This improves locality in balancing decisions by keeping up to capacity amount of tasks local before looking for idle CPUs. (and twice the capacity if SD_POWERSAVINGS_BALANCE is set.) Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | sched: Add a few SYNC hint knobs to play withPeter Zijlstra2009-09-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently we use overlap to weaken the SYNC hint, but allow it to set the hint as well. echo NO_SYNC_WAKEUP > /debug/sched_features echo SYNC_MORE > /debug/sched_features preserves pipe-test behaviour without using the WF_SYNC hint. Worth playing with on more workloads... Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | sched: Fix sync wakeups againPeter Zijlstra2009-09-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The sync argument rename to introduce WF_* broke stuff by missing a local alias for an argument in __wake_up_common, fix it by using the more descriptive wake_flags name. This restores WF_SYNC propagation, which fixes wake_affine() behaviour, which fixes pipe-test. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | sched: Add WF_FORKPeter Zijlstra2009-09-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Avoid the cache buddies from biasing the time distribution away from fork()ers. Normally the next buddy will be the preferred scheduling target, but this makes fork()s prefer to run the new child, whereas we prefer to run the parent, since that will generate more work. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | sched: Rename sync argumentsPeter Zijlstra2009-09-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In order to extend the functions to have more than 1 flag (sync), rename the argument to flags, and explicitly define a WF_ space for individual flags. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | sched: Rename select_task_rq() argumentPeter Zijlstra2009-09-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In order to be able to rename the sync argument, we need to rename the current flag argument. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | sched: Feature to disable APERF/MPERF cpu_powerPeter Zijlstra2009-09-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | I suspect a feed-back loop between cpuidle and the aperf/mperf cpu_power bits, where when we have idle C-states lower the ratio, which leads to lower cpu_power and then less load, which generates more idle time, etc.. Put in a knob to disable it. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | sched: Provide arch_scale_freq_powerPeter Zijlstra2009-09-15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Provide an ach specific hook for cpufreq based scaling of cpu_power. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> [ego@in.ibm.com: spotting bugs] LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>