linux_dsm_epyc7002/include/linux/timer.h

283 lines
8.8 KiB
C
Raw Normal View History

#ifndef _LINUX_TIMER_H
#define _LINUX_TIMER_H
#include <linux/list.h>
[PATCH] Add debugging feature /proc/timer_stat Add /proc/timer_stats support: debugging feature to profile timer expiration. Both the starting site, process/PID and the expiration function is captured. This allows the quick identification of timer event sources in a system. Sample output: # echo 1 > /proc/timer_stats # cat /proc/timer_stats Timer Stats Version: v0.1 Sample period: 4.010 s 24, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 11, 0 swapper sk_reset_timer (tcp_delack_timer) 6, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 17, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 4, 2050 pcscd do_nanosleep (hrtimer_wakeup) 5, 4179 sshd sk_reset_timer (tcp_write_timer) 4, 2248 yum-updatesd schedule_timeout (process_timeout) 18, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 3, 0 swapper sk_reset_timer (tcp_delack_timer) 1, 1 swapper neigh_table_init_no_netlink (neigh_periodic_timer) 2, 1 swapper e1000_up (e1000_watchdog) 1, 1 init schedule_timeout (process_timeout) 100 total events, 25.24 events/sec [ cleanups and hrtimers support from Thomas Gleixner <tglx@linutronix.de> ] [bunk@stusta.de: nr_entries can become static] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 16:28:13 +07:00
#include <linux/ktime.h>
#include <linux/stddef.h>
#include <linux/debugobjects.h>
#include <linux/stringify.h>
struct tvec_base;
struct timer_list {
/*
* All fields that change during normal runtime grouped to the
* same cacheline
*/
timer: Replace timer base by a cpu index Instead of storing a pointer to the per cpu tvec_base we can simply cache a CPU index in the timer_list and use that to get hold of the correct per cpu tvec_base. This is only used in lock_timer_base() and the slightly larger code is peanuts versus the spinlock operation and the d-cache foot print of the timer wheel. Aside of that this allows to get rid of following nuisances: - boot_tvec_base That statically allocated 4k bss data is just kept around so the timer has a home when it gets statically initialized. It serves no other purpose. With the CPU index we assign the timer to CPU0 at static initialization time and therefor can avoid the whole boot_tvec_base dance. That also simplifies the init code, which just can use the per cpu base. Before: text data bss dec hex filename 17491 9201 4160 30852 7884 ../build/kernel/time/timer.o After: text data bss dec hex filename 17440 9193 0 26633 6809 ../build/kernel/time/timer.o - Overloading the base pointer with various flags The CPU index has enough space to hold the flags (deferrable, irqsafe) so we can get rid of the extra masking and bit fiddling with the base pointer. As a benefit we reduce the size of struct timer_list on 64 bit machines. 4 - 8 bytes, a size reduction up to 15% per struct timer_list, which is a real win as we have tons of them embedded in other structs. This changes also the newly added deferrable printout of the timer start trace point to capture and print all timer->flags, which allows us to decode the target cpu of the timer as well. We might have used bitfields for this, but that would change the static initializers and the init function for no value to accomodate big endian bitfields. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Joonwoo Park <joonwoop@codeaurora.org> Cc: Wenbo Wang <wenbo.wang@memblaze.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Badhri Jagan Sridharan <Badhri@google.com> Link: http://lkml.kernel.org/r/20150526224511.950084301@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-05-27 05:50:29 +07:00
struct hlist_node entry;
unsigned long expires;
void (*function)(unsigned long);
unsigned long data;
u32 flags;
[PATCH] Add debugging feature /proc/timer_stat Add /proc/timer_stats support: debugging feature to profile timer expiration. Both the starting site, process/PID and the expiration function is captured. This allows the quick identification of timer event sources in a system. Sample output: # echo 1 > /proc/timer_stats # cat /proc/timer_stats Timer Stats Version: v0.1 Sample period: 4.010 s 24, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 11, 0 swapper sk_reset_timer (tcp_delack_timer) 6, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 17, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 4, 2050 pcscd do_nanosleep (hrtimer_wakeup) 5, 4179 sshd sk_reset_timer (tcp_write_timer) 4, 2248 yum-updatesd schedule_timeout (process_timeout) 18, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 3, 0 swapper sk_reset_timer (tcp_delack_timer) 1, 1 swapper neigh_table_init_no_netlink (neigh_periodic_timer) 2, 1 swapper e1000_up (e1000_watchdog) 1, 1 init schedule_timeout (process_timeout) 100 total events, 25.24 events/sec [ cleanups and hrtimers support from Thomas Gleixner <tglx@linutronix.de> ] [bunk@stusta.de: nr_entries can become static] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 16:28:13 +07:00
#ifdef CONFIG_TIMER_STATS
timer: Replace timer base by a cpu index Instead of storing a pointer to the per cpu tvec_base we can simply cache a CPU index in the timer_list and use that to get hold of the correct per cpu tvec_base. This is only used in lock_timer_base() and the slightly larger code is peanuts versus the spinlock operation and the d-cache foot print of the timer wheel. Aside of that this allows to get rid of following nuisances: - boot_tvec_base That statically allocated 4k bss data is just kept around so the timer has a home when it gets statically initialized. It serves no other purpose. With the CPU index we assign the timer to CPU0 at static initialization time and therefor can avoid the whole boot_tvec_base dance. That also simplifies the init code, which just can use the per cpu base. Before: text data bss dec hex filename 17491 9201 4160 30852 7884 ../build/kernel/time/timer.o After: text data bss dec hex filename 17440 9193 0 26633 6809 ../build/kernel/time/timer.o - Overloading the base pointer with various flags The CPU index has enough space to hold the flags (deferrable, irqsafe) so we can get rid of the extra masking and bit fiddling with the base pointer. As a benefit we reduce the size of struct timer_list on 64 bit machines. 4 - 8 bytes, a size reduction up to 15% per struct timer_list, which is a real win as we have tons of them embedded in other structs. This changes also the newly added deferrable printout of the timer start trace point to capture and print all timer->flags, which allows us to decode the target cpu of the timer as well. We might have used bitfields for this, but that would change the static initializers and the init function for no value to accomodate big endian bitfields. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Joonwoo Park <joonwoop@codeaurora.org> Cc: Wenbo Wang <wenbo.wang@memblaze.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Badhri Jagan Sridharan <Badhri@google.com> Link: http://lkml.kernel.org/r/20150526224511.950084301@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-05-27 05:50:29 +07:00
int start_pid;
void *start_site;
char start_comm[16];
[PATCH] Add debugging feature /proc/timer_stat Add /proc/timer_stats support: debugging feature to profile timer expiration. Both the starting site, process/PID and the expiration function is captured. This allows the quick identification of timer event sources in a system. Sample output: # echo 1 > /proc/timer_stats # cat /proc/timer_stats Timer Stats Version: v0.1 Sample period: 4.010 s 24, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 11, 0 swapper sk_reset_timer (tcp_delack_timer) 6, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 17, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 4, 2050 pcscd do_nanosleep (hrtimer_wakeup) 5, 4179 sshd sk_reset_timer (tcp_write_timer) 4, 2248 yum-updatesd schedule_timeout (process_timeout) 18, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 3, 0 swapper sk_reset_timer (tcp_delack_timer) 1, 1 swapper neigh_table_init_no_netlink (neigh_periodic_timer) 2, 1 swapper e1000_up (e1000_watchdog) 1, 1 init schedule_timeout (process_timeout) 100 total events, 25.24 events/sec [ cleanups and hrtimers support from Thomas Gleixner <tglx@linutronix.de> ] [bunk@stusta.de: nr_entries can become static] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 16:28:13 +07:00
#endif
#ifdef CONFIG_LOCKDEP
timer: Replace timer base by a cpu index Instead of storing a pointer to the per cpu tvec_base we can simply cache a CPU index in the timer_list and use that to get hold of the correct per cpu tvec_base. This is only used in lock_timer_base() and the slightly larger code is peanuts versus the spinlock operation and the d-cache foot print of the timer wheel. Aside of that this allows to get rid of following nuisances: - boot_tvec_base That statically allocated 4k bss data is just kept around so the timer has a home when it gets statically initialized. It serves no other purpose. With the CPU index we assign the timer to CPU0 at static initialization time and therefor can avoid the whole boot_tvec_base dance. That also simplifies the init code, which just can use the per cpu base. Before: text data bss dec hex filename 17491 9201 4160 30852 7884 ../build/kernel/time/timer.o After: text data bss dec hex filename 17440 9193 0 26633 6809 ../build/kernel/time/timer.o - Overloading the base pointer with various flags The CPU index has enough space to hold the flags (deferrable, irqsafe) so we can get rid of the extra masking and bit fiddling with the base pointer. As a benefit we reduce the size of struct timer_list on 64 bit machines. 4 - 8 bytes, a size reduction up to 15% per struct timer_list, which is a real win as we have tons of them embedded in other structs. This changes also the newly added deferrable printout of the timer start trace point to capture and print all timer->flags, which allows us to decode the target cpu of the timer as well. We might have used bitfields for this, but that would change the static initializers and the init function for no value to accomodate big endian bitfields. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Joonwoo Park <joonwoop@codeaurora.org> Cc: Wenbo Wang <wenbo.wang@memblaze.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Badhri Jagan Sridharan <Badhri@google.com> Link: http://lkml.kernel.org/r/20150526224511.950084301@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-05-27 05:50:29 +07:00
struct lockdep_map lockdep_map;
#endif
};
#ifdef CONFIG_LOCKDEP
/*
* NB: because we have to copy the lockdep_map, setting the lockdep_map key
* (second argument) here is required, otherwise it could be initialised to
* the copy of the lockdep_map later! We use the pointer to and the string
* "<file>:<line>" as the key resp. the name of the lockdep_map.
*/
#define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn) \
.lockdep_map = STATIC_LOCKDEP_MAP_INIT(_kn, &_kn),
#else
#define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn)
#endif
/*
* A deferrable timer will work normally when the system is busy, but
* will not cause a CPU to come out of idle just to service it; instead,
* the timer will be serviced when the CPU eventually wakes up with a
* subsequent non-deferrable timer.
*
* An irqsafe timer is executed with IRQ disabled and it's safe to wait for
* the completion of the running instance from IRQ handlers, for example,
* by calling del_timer_sync().
*
* Note: The irq disabled callback execution is a special case for
* workqueue locking issues. It's not meant for executing random crap
* with interrupts disabled. Abuse is monitored!
*/
#define TIMER_CPUMASK 0x0003FFFF
#define TIMER_MIGRATING 0x00040000
timer: Replace timer base by a cpu index Instead of storing a pointer to the per cpu tvec_base we can simply cache a CPU index in the timer_list and use that to get hold of the correct per cpu tvec_base. This is only used in lock_timer_base() and the slightly larger code is peanuts versus the spinlock operation and the d-cache foot print of the timer wheel. Aside of that this allows to get rid of following nuisances: - boot_tvec_base That statically allocated 4k bss data is just kept around so the timer has a home when it gets statically initialized. It serves no other purpose. With the CPU index we assign the timer to CPU0 at static initialization time and therefor can avoid the whole boot_tvec_base dance. That also simplifies the init code, which just can use the per cpu base. Before: text data bss dec hex filename 17491 9201 4160 30852 7884 ../build/kernel/time/timer.o After: text data bss dec hex filename 17440 9193 0 26633 6809 ../build/kernel/time/timer.o - Overloading the base pointer with various flags The CPU index has enough space to hold the flags (deferrable, irqsafe) so we can get rid of the extra masking and bit fiddling with the base pointer. As a benefit we reduce the size of struct timer_list on 64 bit machines. 4 - 8 bytes, a size reduction up to 15% per struct timer_list, which is a real win as we have tons of them embedded in other structs. This changes also the newly added deferrable printout of the timer start trace point to capture and print all timer->flags, which allows us to decode the target cpu of the timer as well. We might have used bitfields for this, but that would change the static initializers and the init function for no value to accomodate big endian bitfields. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Joonwoo Park <joonwoop@codeaurora.org> Cc: Wenbo Wang <wenbo.wang@memblaze.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Badhri Jagan Sridharan <Badhri@google.com> Link: http://lkml.kernel.org/r/20150526224511.950084301@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-05-27 05:50:29 +07:00
#define TIMER_BASEMASK (TIMER_CPUMASK | TIMER_MIGRATING)
#define TIMER_DEFERRABLE 0x00080000
#define TIMER_PINNED 0x00100000
#define TIMER_IRQSAFE 0x00200000
timers: Switch to a non-cascading wheel The current timer wheel has some drawbacks: 1) Cascading: Cascading can be an unbound operation and is completely pointless in most cases because the vast majority of the timer wheel timers are canceled or rearmed before expiration. (They are used as timeout safeguards, not as real timers to measure time.) 2) No fast lookup of the next expiring timer: In NOHZ scenarios the first timer soft interrupt after a long NOHZ period must fast forward the base time to the current value of jiffies. As we have no way to find the next expiring timer fast, the code loops linearly and increments the base time one by one and checks for expired timers in each step. This causes unbound overhead spikes exactly in the moment when we should wake up as fast as possible. After a thorough analysis of real world data gathered on laptops, workstations, webservers and other machines (thanks Chris!) I came to the conclusion that the current 'classic' timer wheel implementation can be modified to address the above issues. The vast majority of timer wheel timers is canceled or rearmed before expiry. Most of them are timeouts for networking and other I/O tasks. The nature of timeouts is to catch the exception from normal operation (TCP ack timed out, disk does not respond, etc.). For these kinds of timeouts the accuracy of the timeout is not really a concern. Timeouts are very often approximate worst-case values and in case the timeout fires, we already waited for a long time and performance is down the drain already. The few timers which actually expire can be split into two categories: 1) Short expiry times which expect halfways accurate expiry 2) Long term expiry times are inaccurate today already due to the batching which is done for NOHZ automatically and also via the set_timer_slack() API. So for long term expiry timers we can avoid the cascading property and just leave them in the less granular outer wheels until expiry or cancelation. Timers which are armed with a timeout larger than the wheel capacity are no longer cascaded. We expire them with the longest possible timeout (6+ days). We have not observed such timeouts in our data collection, but at least we handle them, applying the rule of the least surprise. To avoid extending the wheel levels for HZ=1000 so we can accomodate the longest observed timeouts (5 days in the network conntrack code) we reduce the first level granularity on HZ=1000 to 4ms, which effectively is the same as the HZ=250 behaviour. From our data analysis there is nothing which relies on that 1ms granularity and as a side effect we get better batching and timer locality for the networking code as well. Contrary to the classic wheel the granularity of the next wheel is not the capacity of the first wheel. The granularities of the wheels are in the currently chosen setting 8 times the granularity of the previous wheel. So for HZ=250 we end up with the following granularity levels: Level Offset Granularity Range 0 0 4 ms 0 ms - 252 ms 1 64 32 ms 256 ms - 2044 ms (256ms - ~2s) 2 128 256 ms 2048 ms - 16380 ms (~2s - ~16s) 3 192 2048 ms (~2s) 16384 ms - 131068 ms (~16s - ~2m) 4 256 16384 ms (~16s) 131072 ms - 1048572 ms (~2m - ~17m) 5 320 131072 ms (~2m) 1048576 ms - 8388604 ms (~17m - ~2h) 6 384 1048576 ms (~17m) 8388608 ms - 67108863 ms (~2h - ~18h) 7 448 8388608 ms (~2h) 67108864 ms - 536870911 ms (~18h - ~6d) That's a worst case inaccuracy of 12.5% for the timers which are queued at the beginning of a level. So the new wheel concept addresses the old issues: 1) Cascading is avoided completely 2) By keeping the timers in the bucket until expiry/cancelation we can track the buckets which have timers enqueued in a bucket bitmap and therefore can look up the next expiring timer very fast and O(1). A further benefit of the concept is that the slack calculation which is done on every timer start is no longer necessary because the granularity levels provide natural batching already. Our extensive testing with various loads did not show any performance degradation vs. the current wheel implementation. This patch does not address the 'fast lookup' issue as we wanted to make sure that there is no regression introduced by the wheel redesign. The optimizations are in follow up patches. This patch contains fixes from Anna-Maria Gleixner and Richard Cochran. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Chris Mason <clm@fb.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: George Spelvin <linux@sciencehorizons.net> Cc: Josh Triplett <josh@joshtriplett.org> Cc: Len Brown <lenb@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160704094342.108621834@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-07-04 16:50:30 +07:00
#define TIMER_ARRAYSHIFT 22
#define TIMER_ARRAYMASK 0xFFC00000
#define __TIMER_INITIALIZER(_function, _expires, _data, _flags) { \
.entry = { .next = TIMER_ENTRY_STATIC }, \
.function = (_function), \
.expires = (_expires), \
.data = (_data), \
timer: Replace timer base by a cpu index Instead of storing a pointer to the per cpu tvec_base we can simply cache a CPU index in the timer_list and use that to get hold of the correct per cpu tvec_base. This is only used in lock_timer_base() and the slightly larger code is peanuts versus the spinlock operation and the d-cache foot print of the timer wheel. Aside of that this allows to get rid of following nuisances: - boot_tvec_base That statically allocated 4k bss data is just kept around so the timer has a home when it gets statically initialized. It serves no other purpose. With the CPU index we assign the timer to CPU0 at static initialization time and therefor can avoid the whole boot_tvec_base dance. That also simplifies the init code, which just can use the per cpu base. Before: text data bss dec hex filename 17491 9201 4160 30852 7884 ../build/kernel/time/timer.o After: text data bss dec hex filename 17440 9193 0 26633 6809 ../build/kernel/time/timer.o - Overloading the base pointer with various flags The CPU index has enough space to hold the flags (deferrable, irqsafe) so we can get rid of the extra masking and bit fiddling with the base pointer. As a benefit we reduce the size of struct timer_list on 64 bit machines. 4 - 8 bytes, a size reduction up to 15% per struct timer_list, which is a real win as we have tons of them embedded in other structs. This changes also the newly added deferrable printout of the timer start trace point to capture and print all timer->flags, which allows us to decode the target cpu of the timer as well. We might have used bitfields for this, but that would change the static initializers and the init function for no value to accomodate big endian bitfields. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Joonwoo Park <joonwoop@codeaurora.org> Cc: Wenbo Wang <wenbo.wang@memblaze.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Badhri Jagan Sridharan <Badhri@google.com> Link: http://lkml.kernel.org/r/20150526224511.950084301@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-05-27 05:50:29 +07:00
.flags = (_flags), \
__TIMER_LOCKDEP_MAP_INITIALIZER( \
__FILE__ ":" __stringify(__LINE__)) \
}
#define TIMER_INITIALIZER(_function, _expires, _data) \
__TIMER_INITIALIZER((_function), (_expires), (_data), 0)
#define TIMER_PINNED_INITIALIZER(_function, _expires, _data) \
__TIMER_INITIALIZER((_function), (_expires), (_data), TIMER_PINNED)
#define TIMER_DEFERRED_INITIALIZER(_function, _expires, _data) \
__TIMER_INITIALIZER((_function), (_expires), (_data), TIMER_DEFERRABLE)
#define TIMER_PINNED_DEFERRED_INITIALIZER(_function, _expires, _data) \
__TIMER_INITIALIZER((_function), (_expires), (_data), TIMER_DEFERRABLE | TIMER_PINNED)
#define DEFINE_TIMER(_name, _function, _expires, _data) \
struct timer_list _name = \
TIMER_INITIALIZER(_function, _expires, _data)
void init_timer_key(struct timer_list *timer, unsigned int flags,
const char *name, struct lock_class_key *key);
#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
extern void init_timer_on_stack_key(struct timer_list *timer,
unsigned int flags, const char *name,
struct lock_class_key *key);
extern void destroy_timer_on_stack(struct timer_list *timer);
#else
static inline void destroy_timer_on_stack(struct timer_list *timer) { }
static inline void init_timer_on_stack_key(struct timer_list *timer,
unsigned int flags, const char *name,
struct lock_class_key *key)
{
init_timer_key(timer, flags, name, key);
}
#endif
#ifdef CONFIG_LOCKDEP
#define __init_timer(_timer, _flags) \
do { \
static struct lock_class_key __key; \
init_timer_key((_timer), (_flags), #_timer, &__key); \
} while (0)
#define __init_timer_on_stack(_timer, _flags) \
do { \
static struct lock_class_key __key; \
init_timer_on_stack_key((_timer), (_flags), #_timer, &__key); \
} while (0)
#else
#define __init_timer(_timer, _flags) \
init_timer_key((_timer), (_flags), NULL, NULL)
#define __init_timer_on_stack(_timer, _flags) \
init_timer_on_stack_key((_timer), (_flags), NULL, NULL)
#endif
#define init_timer(timer) \
__init_timer((timer), 0)
#define init_timer_pinned(timer) \
__init_timer((timer), TIMER_PINNED)
#define init_timer_deferrable(timer) \
__init_timer((timer), TIMER_DEFERRABLE)
#define init_timer_pinned_deferrable(timer) \
__init_timer((timer), TIMER_DEFERRABLE | TIMER_PINNED)
#define init_timer_on_stack(timer) \
__init_timer_on_stack((timer), 0)
#define __setup_timer(_timer, _fn, _data, _flags) \
do { \
__init_timer((_timer), (_flags)); \
(_timer)->function = (_fn); \
(_timer)->data = (_data); \
} while (0)
#define __setup_timer_on_stack(_timer, _fn, _data, _flags) \
do { \
__init_timer_on_stack((_timer), (_flags)); \
(_timer)->function = (_fn); \
(_timer)->data = (_data); \
} while (0)
#define setup_timer(timer, fn, data) \
__setup_timer((timer), (fn), (data), 0)
#define setup_pinned_timer(timer, fn, data) \
__setup_timer((timer), (fn), (data), TIMER_PINNED)
#define setup_deferrable_timer(timer, fn, data) \
__setup_timer((timer), (fn), (data), TIMER_DEFERRABLE)
#define setup_pinned_deferrable_timer(timer, fn, data) \
__setup_timer((timer), (fn), (data), TIMER_DEFERRABLE | TIMER_PINNED)
#define setup_timer_on_stack(timer, fn, data) \
__setup_timer_on_stack((timer), (fn), (data), 0)
#define setup_pinned_timer_on_stack(timer, fn, data) \
__setup_timer_on_stack((timer), (fn), (data), TIMER_PINNED)
#define setup_deferrable_timer_on_stack(timer, fn, data) \
__setup_timer_on_stack((timer), (fn), (data), TIMER_DEFERRABLE)
#define setup_pinned_deferrable_timer_on_stack(timer, fn, data) \
__setup_timer_on_stack((timer), (fn), (data), TIMER_DEFERRABLE | TIMER_PINNED)
/**
* timer_pending - is a timer pending?
* @timer: the timer in question
*
* timer_pending will tell whether a given timer is currently pending,
* or not. Callers must ensure serialization wrt. other operations done
* to this timer, eg. interrupt contexts, or other CPUs on SMP.
*
* return value: 1 if the timer is pending, 0 if not.
*/
static inline int timer_pending(const struct timer_list * timer)
{
return timer->entry.pprev != NULL;
}
extern void add_timer_on(struct timer_list *timer, int cpu);
extern int del_timer(struct timer_list * timer);
extern int mod_timer(struct timer_list *timer, unsigned long expires);
extern int mod_timer_pending(struct timer_list *timer, unsigned long expires);
/*
* The jiffies value which is added to now, when there is no timer
* in the timer wheel:
*/
#define NEXT_TIMER_MAX_DELTA ((1UL << 30) - 1)
[PATCH] Add debugging feature /proc/timer_stat Add /proc/timer_stats support: debugging feature to profile timer expiration. Both the starting site, process/PID and the expiration function is captured. This allows the quick identification of timer event sources in a system. Sample output: # echo 1 > /proc/timer_stats # cat /proc/timer_stats Timer Stats Version: v0.1 Sample period: 4.010 s 24, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 11, 0 swapper sk_reset_timer (tcp_delack_timer) 6, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 17, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 4, 2050 pcscd do_nanosleep (hrtimer_wakeup) 5, 4179 sshd sk_reset_timer (tcp_write_timer) 4, 2248 yum-updatesd schedule_timeout (process_timeout) 18, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 3, 0 swapper sk_reset_timer (tcp_delack_timer) 1, 1 swapper neigh_table_init_no_netlink (neigh_periodic_timer) 2, 1 swapper e1000_up (e1000_watchdog) 1, 1 init schedule_timeout (process_timeout) 100 total events, 25.24 events/sec [ cleanups and hrtimers support from Thomas Gleixner <tglx@linutronix.de> ] [bunk@stusta.de: nr_entries can become static] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 16:28:13 +07:00
/*
* Timer-statistics info:
*/
#ifdef CONFIG_TIMER_STATS
extern int timer_stats_active;
[PATCH] Add debugging feature /proc/timer_stat Add /proc/timer_stats support: debugging feature to profile timer expiration. Both the starting site, process/PID and the expiration function is captured. This allows the quick identification of timer event sources in a system. Sample output: # echo 1 > /proc/timer_stats # cat /proc/timer_stats Timer Stats Version: v0.1 Sample period: 4.010 s 24, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 11, 0 swapper sk_reset_timer (tcp_delack_timer) 6, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 17, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 4, 2050 pcscd do_nanosleep (hrtimer_wakeup) 5, 4179 sshd sk_reset_timer (tcp_write_timer) 4, 2248 yum-updatesd schedule_timeout (process_timeout) 18, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 3, 0 swapper sk_reset_timer (tcp_delack_timer) 1, 1 swapper neigh_table_init_no_netlink (neigh_periodic_timer) 2, 1 swapper e1000_up (e1000_watchdog) 1, 1 init schedule_timeout (process_timeout) 100 total events, 25.24 events/sec [ cleanups and hrtimers support from Thomas Gleixner <tglx@linutronix.de> ] [bunk@stusta.de: nr_entries can become static] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 16:28:13 +07:00
extern void init_timer_stats(void);
extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
void *timerf, char *comm, u32 flags);
[PATCH] Add debugging feature /proc/timer_stat Add /proc/timer_stats support: debugging feature to profile timer expiration. Both the starting site, process/PID and the expiration function is captured. This allows the quick identification of timer event sources in a system. Sample output: # echo 1 > /proc/timer_stats # cat /proc/timer_stats Timer Stats Version: v0.1 Sample period: 4.010 s 24, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 11, 0 swapper sk_reset_timer (tcp_delack_timer) 6, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 17, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 4, 2050 pcscd do_nanosleep (hrtimer_wakeup) 5, 4179 sshd sk_reset_timer (tcp_write_timer) 4, 2248 yum-updatesd schedule_timeout (process_timeout) 18, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 3, 0 swapper sk_reset_timer (tcp_delack_timer) 1, 1 swapper neigh_table_init_no_netlink (neigh_periodic_timer) 2, 1 swapper e1000_up (e1000_watchdog) 1, 1 init schedule_timeout (process_timeout) 100 total events, 25.24 events/sec [ cleanups and hrtimers support from Thomas Gleixner <tglx@linutronix.de> ] [bunk@stusta.de: nr_entries can become static] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 16:28:13 +07:00
extern void __timer_stats_timer_set_start_info(struct timer_list *timer,
void *addr);
static inline void timer_stats_timer_set_start_info(struct timer_list *timer)
{
if (likely(!timer_stats_active))
return;
[PATCH] Add debugging feature /proc/timer_stat Add /proc/timer_stats support: debugging feature to profile timer expiration. Both the starting site, process/PID and the expiration function is captured. This allows the quick identification of timer event sources in a system. Sample output: # echo 1 > /proc/timer_stats # cat /proc/timer_stats Timer Stats Version: v0.1 Sample period: 4.010 s 24, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 11, 0 swapper sk_reset_timer (tcp_delack_timer) 6, 0 swapper hrtimer_stop_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 17, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 2, 1 swapper queue_delayed_work_on (delayed_work_timer_fn) 4, 2050 pcscd do_nanosleep (hrtimer_wakeup) 5, 4179 sshd sk_reset_timer (tcp_write_timer) 4, 2248 yum-updatesd schedule_timeout (process_timeout) 18, 0 swapper hrtimer_restart_sched_tick (hrtimer_sched_tick) 3, 0 swapper sk_reset_timer (tcp_delack_timer) 1, 1 swapper neigh_table_init_no_netlink (neigh_periodic_timer) 2, 1 swapper e1000_up (e1000_watchdog) 1, 1 init schedule_timeout (process_timeout) 100 total events, 25.24 events/sec [ cleanups and hrtimers support from Thomas Gleixner <tglx@linutronix.de> ] [bunk@stusta.de: nr_entries can become static] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 16:28:13 +07:00
__timer_stats_timer_set_start_info(timer, __builtin_return_address(0));
}
static inline void timer_stats_timer_clear_start_info(struct timer_list *timer)
{
timer->start_site = NULL;
}
#else
static inline void init_timer_stats(void)
{
}
static inline void timer_stats_timer_set_start_info(struct timer_list *timer)
{
}
static inline void timer_stats_timer_clear_start_info(struct timer_list *timer)
{
}
#endif
extern void add_timer(struct timer_list *timer);
extern int try_to_del_timer_sync(struct timer_list *timer);
#ifdef CONFIG_SMP
extern int del_timer_sync(struct timer_list *timer);
#else
# define del_timer_sync(t) del_timer(t)
#endif
[PATCH] timers fixes/improvements This patch tries to solve following problems: 1. del_timer_sync() is racy. The timer can be fired again after del_timer_sync have checked all cpus and before it will recheck timer_pending(). 2. It has scalability problems. All cpus are scanned to determine if the timer is running on that cpu. With this patch del_timer_sync is O(1) and no slower than plain del_timer(pending_timer), unless it has to actually wait for completion of the currently running timer. The only restriction is that the recurring timer should not use add_timer_on(). 3. The timers are not serialized wrt to itself. If CPU_0 does mod_timer(jiffies+1) while the timer is currently running on CPU 1, it is quite possible that local interrupt on CPU_0 will start that timer before it finished on CPU_1. 4. The timers locking is suboptimal. __mod_timer() takes 3 locks at once and still requires wmb() in del_timer/run_timers. The new implementation takes 2 locks sequentially and does not need memory barriers. Currently ->base != NULL means that the timer is pending. In that case ->base.lock is used to lock the timer. __mod_timer also takes timer->lock because ->base can be == NULL. This patch uses timer->entry.next != NULL as indication that the timer is pending. So it does __list_del(), entry->next = NULL instead of list_del() when the timer is deleted. The ->base field is used for hashed locking only, it is initialized in init_timer() which sets ->base = per_cpu(tvec_bases). When the tvec_bases.lock is locked, it means that all timers which are tied to this base via timer->base are locked, and the base itself is locked too. So __run_timers/migrate_timers can safely modify all timers which could be found on ->tvX lists (pending timers). When the timer's base is locked, and the timer removed from ->entry list (which means that _run_timers/migrate_timers can't see this timer), it is possible to set timer->base = NULL and drop the lock: the timer remains locked. This patch adds lock_timer_base() helper, which waits for ->base != NULL, locks the ->base, and checks it is still the same. __mod_timer() schedules the timer on the local CPU and changes it's base. However, it does not lock both old and new bases at once. It locks the timer via lock_timer_base(), deletes the timer, sets ->base = NULL, and unlocks old base. Then __mod_timer() locks new_base, sets ->base = new_base, and adds this timer. This simplifies the code, because AB-BA deadlock is not possible. __mod_timer() also ensures that the timer's base is not changed while the timer's handler is running on the old base. __run_timers(), del_timer() do not change ->base anymore, they only clear pending flag. So del_timer_sync() can test timer->base->running_timer == timer to detect whether it is running or not. We don't need timer_list->lock anymore, this patch kills it. We also don't need barriers. del_timer() and __run_timers() used smp_wmb() before clearing timer's pending flag. It was needed because __mod_timer() did not lock old_base if the timer is not pending, so __mod_timer()->list_add() could race with del_timer()->list_del(). With this patch these functions are serialized through base->lock. One problem. TIMER_INITIALIZER can't use per_cpu(tvec_bases). So this patch adds global struct timer_base_s { spinlock_t lock; struct timer_list *running_timer; } __init_timer_base; which is used by TIMER_INITIALIZER. The corresponding fields in tvec_t_base_s struct are replaced by struct timer_base_s t_base. It is indeed ugly. But this can't have scalability problems. The global __init_timer_base.lock is used only when __mod_timer() is called for the first time AND the timer was compile time initialized. After that the timer migrates to the local CPU. Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Renaud Lienhart <renaud.lienhart@free.fr> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 14:08:56 +07:00
#define del_singleshot_timer_sync(t) del_timer_sync(t)
extern void init_timers(void);
extern void run_local_timers(void);
struct hrtimer;
extern enum hrtimer_restart it_real_fn(struct hrtimer *);
timer: Reduce timer migration overhead if disabled Eric reported that the timer_migration sysctl is not really nice performance wise as it needs to check at every timer insertion whether the feature is enabled or not. Further the check does not live in the timer code, so we have an extra function call which checks an extra cache line to figure out that it is disabled. We can do better and store that information in the per cpu (hr)timer bases. I pondered to use a static key, but that's a nightmare to update from the nohz code and the timer base cache line is hot anyway when we select a timer base. The old logic enabled the timer migration unconditionally if CONFIG_NO_HZ was set even if nohz was disabled on the kernel command line. With this modification, we start off with migration disabled. The user visible sysctl is still set to enabled. If the kernel switches to NOHZ migration is enabled, if the user did not disable it via the sysctl prior to the switch. If nohz=off is on the kernel command line, migration stays disabled no matter what. Before: 47.76% hog [.] main 14.84% [kernel] [k] _raw_spin_lock_irqsave 9.55% [kernel] [k] _raw_spin_unlock_irqrestore 6.71% [kernel] [k] mod_timer 6.24% [kernel] [k] lock_timer_base.isra.38 3.76% [kernel] [k] detach_if_pending 3.71% [kernel] [k] del_timer 2.50% [kernel] [k] internal_add_timer 1.51% [kernel] [k] get_nohz_timer_target 1.28% [kernel] [k] __internal_add_timer 0.78% [kernel] [k] timerfn 0.48% [kernel] [k] wake_up_nohz_cpu After: 48.10% hog [.] main 15.25% [kernel] [k] _raw_spin_lock_irqsave 9.76% [kernel] [k] _raw_spin_unlock_irqrestore 6.50% [kernel] [k] mod_timer 6.44% [kernel] [k] lock_timer_base.isra.38 3.87% [kernel] [k] detach_if_pending 3.80% [kernel] [k] del_timer 2.67% [kernel] [k] internal_add_timer 1.33% [kernel] [k] __internal_add_timer 0.73% [kernel] [k] timerfn 0.54% [kernel] [k] wake_up_nohz_cpu Reported-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Joonwoo Park <joonwoop@codeaurora.org> Cc: Wenbo Wang <wenbo.wang@memblaze.com> Link: http://lkml.kernel.org/r/20150526224512.127050787@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-05-27 05:50:33 +07:00
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
#include <linux/sysctl.h>
extern unsigned int sysctl_timer_migration;
int timer_migration_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
#endif
unsigned long __round_jiffies(unsigned long j, int cpu);
unsigned long __round_jiffies_relative(unsigned long j, int cpu);
unsigned long round_jiffies(unsigned long j);
unsigned long round_jiffies_relative(unsigned long j);
unsigned long __round_jiffies_up(unsigned long j, int cpu);
unsigned long __round_jiffies_up_relative(unsigned long j, int cpu);
unsigned long round_jiffies_up(unsigned long j);
unsigned long round_jiffies_up_relative(unsigned long j);
#ifdef CONFIG_HOTPLUG_CPU
int timers_dead_cpu(unsigned int cpu);
#else
#define timers_dead_cpu NULL
#endif
#endif