linux/kernel/time
Paul E. McKenney 0edd1b1784 nohz_full: Add full-system-idle state machine
This commit adds the state machine that takes the per-CPU idle data
as input and produces a full-system-idle indication as output.  This
state machine is driven out of RCU's quiescent-state-forcing
mechanism, which invokes rcu_sysidle_check_cpu() to collect per-CPU
idle state and then rcu_sysidle_report() to drive the state machine.

The full-system-idle state is sampled using rcu_sys_is_idle(), which
also drives the state machine if RCU is idle (and does so by forcing
RCU to become non-idle).  This function returns true if all but the
timekeeping CPU (tick_do_timer_cpu) are idle and have been idle long
enough to avoid memory contention on the full_sysidle_state state
variable.  The rcu_sysidle_force_exit() may be called externally
to reset the state machine back into non-idle state.

For large systems the state machine is driven out of RCU's
force-quiescent-state logic, which provides good scalability at the price
of millisecond-scale latencies on the transition to full-system-idle
state.  This is not so good for battery-powered systems, which are usually
small enough that they don't need to care about scalability, but which
do care deeply about energy efficiency.  Small systems therefore drive
the state machine directly out of the idle-entry code.  The number of
CPUs in a "small" system is defined by a new NO_HZ_FULL_SYSIDLE_SMALL
Kconfig parameter, which defaults to 8.  Note that this is a build-time
definition.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
[ paulmck: Use true and false for boolean constants per Lai Jiangshan. ]
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
[ paulmck: Simplify logic and provide better comments for memory barriers,
  based on review comments and questions by Lai Jiangshan. ]
2013-08-31 14:43:50 -07:00
..
alarmtimer.c alarmtimer: Export symbols of functions declared in linux/alarmtimer.h 2013-06-12 14:02:12 -07:00
clockevents.c clockevents: Implement unbind functionality 2013-05-16 11:09:18 +02:00
clocksource.c clocksource: Reselect clocksource when watchdog validated high-res capability 2013-07-05 11:09:28 +02:00
jiffies.c time: Kill xtime_lock, replacing it with jiffies_lock 2012-11-13 14:08:23 -05:00
Kconfig nohz_full: Add full-system-idle state machine 2013-08-31 14:43:50 -07:00
Makefile sched_clock: Make ARM's sched_clock generic for all architectures 2013-06-12 14:02:13 -07:00
ntp_internal.h ntp: Rework do_adjtimex to take timespec and tai arguments 2013-04-04 13:18:15 -07:00
ntp.c ntp: Remove unused variable flags in __hardpps 2013-05-28 13:45:19 -07:00
posix-clock.c kernel: Fix files explicitly needing EXPORT_SYMBOL infrastructure 2011-10-31 19:30:05 -04:00
sched_clock.c ARM: sched_clock: Load cycle count after epoch stabilizes 2013-06-17 15:56:11 -07:00
tick-broadcast.c tick: broadcast: Check broadcast mode on CPU hotplug 2013-07-12 12:35:40 +02:00
tick-common.c tick: Sanitize broadcast control logic 2013-07-02 14:26:45 +02:00
tick-internal.h clockevents: Define CS_NAME_LEN unconditionally 2013-05-28 09:28:02 +02:00
tick-oneshot.c clockevents: Make minimum delay adjustments configurable 2011-09-08 11:10:56 +02:00
tick-sched.c kernel: delete __cpuinit usage from all core kernel files 2013-07-14 19:36:59 -04:00
timeconv.c time: add function to convert between calendar time and broken-down time for universal use 2009-09-24 07:20:56 -07:00
timekeeping_debug.c power: Add option to log time spent in suspend 2013-05-29 12:57:34 -07:00
timekeeping_internal.h power: Add option to log time spent in suspend 2013-05-29 12:57:34 -07:00
timekeeping.c Merge branch 'timers/posix-cpu-timers-for-tglx' of 2013-07-04 23:11:22 +02:00
timer_list.c timer_list: Convert timer list to be a proper seq_file 2013-04-17 20:51:02 +02:00
timer_stats.c locking, timer_stats: Annotate table_lock as raw 2011-09-13 11:12:00 +02:00