WSL2-Linux-Kernel/kernel/time/tick-sched.c

1589 строки
39 KiB
C
Исходник Обычный вид История

time: Add SPDX license identifiers Update the time(r) core files files with the correct SPDX license identifier based on the license text in the file itself. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This work is based on a script and data from Philippe Ombredanne, Kate Stewart and myself. The data has been created with two independent license scanners and manual inspection. The following files do not contain any direct license information and have been omitted from the big initial SPDX changes: timeconst.bc: The .bc files were not touched time.c, timer.c, timekeeping.c: Licence was deduced from EXPORT_SYMBOL_GPL As those files do not contain direct license references they fall under the project license, i.e. GPL V2 only. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: John Stultz <john.stultz@linaro.org> Acked-by: Corey Minyard <cminyard@mvista.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Kate Stewart <kstewart@linuxfoundation.org> Cc: Philippe Ombredanne <pombredanne@nexb.com> Cc: Russell King <rmk+kernel@armlinux.org.uk> Cc: Richard Cochran <richardcochran@gmail.com> Cc: Nicolas Pitre <nicolas.pitre@linaro.org> Cc: David Riley <davidriley@chromium.org> Cc: Colin Cross <ccross@android.com> Cc: Mark Brown <broonie@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Link: https://lkml.kernel.org/r/20181031182252.879109557@linutronix.de
2018-10-31 21:21:09 +03:00
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner
*
* No idle tick implementation for low and high resolution timers
*
* Started by: Thomas Gleixner and Ingo Molnar
*/
#include <linux/cpu.h>
#include <linux/err.h>
#include <linux/hrtimer.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/percpu.h>
#include <linux/nmi.h>
#include <linux/profile.h>
#include <linux/sched/signal.h>
#include <linux/sched/clock.h>
#include <linux/sched/stat.h>
#include <linux/sched/nohz.h>
#include <linux/sched/loadavg.h>
#include <linux/module.h>
#include <linux/irq_work.h>
#include <linux/posix-timers.h>
#include <linux/context_tracking.h>
#include <linux/mm.h>
#include <asm/irq_regs.h>
#include "tick-internal.h"
#include <trace/events/timer.h>
/*
* Per-CPU nohz control structure
*/
static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
[PATCH] Add debugging feature /proc/timer_list add /proc/timer_list, which prints all currently pending (high-res) timers, all clock-event sources and their parameters in a human-readable form. Sample output: Timer List Version: v0.1 HRTIMER_MAX_CLOCK_BASES: 2 now at 4246046273872 nsecs cpu: 0 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_stop_sched_tick, swapper/0 # expires at 4246432689566 nsecs [in 386415694 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, pcscd/2050 # expires at 4247018194689 nsecs [in 971920817 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, irqbalance/1909 # expires at 4247351358392 nsecs [in 1305084520 nsecs] #3: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, crond/2157 # expires at 4249097614968 nsecs [in 3051341096 nsecs] #4: <f5a90ec8>, it_real_fn, do_setitimer, syslogd/1888 # expires at 4251329900926 nsecs [in 5283627054 nsecs] .expires_next : 4246432689566 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 31306 .idle_tick : 4246020791890 nsecs .tick_stopped : 1 .idle_jiffies : 986504 .idle_calls : 40700 .idle_sleeps : 36014 .idle_entrytime : 4246019418883 nsecs .idle_sleeptime : 4178181972709 nsecs cpu: 1 clock 0: .index: 0 .resolution: 1 nsecs .get_time: ktime_get_real .offset: 1273998312645738432 nsecs active timers: clock 1: .index: 1 .resolution: 1 nsecs .get_time: ktime_get .offset: 0 nsecs active timers: #0: <f5a90ec8>, hrtimer_sched_tick, hrtimer_restart_sched_tick, swapper/0 # expires at 4246050084568 nsecs [in 3810696 nsecs] #1: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, atd/2227 # expires at 4261010635003 nsecs [in 14964361131 nsecs] #2: <f5a90ec8>, hrtimer_wakeup, do_nanosleep, smartd/2332 # expires at 5469485798970 nsecs [in 1223439525098 nsecs] .expires_next : 4246050084568 nsecs .hres_active : 1 .check_clocks : 0 .nr_events : 24043 .idle_tick : 4246046084568 nsecs .tick_stopped : 0 .idle_jiffies : 986510 .idle_calls : 26360 .idle_sleeps : 22551 .idle_entrytime : 4246043874339 nsecs .idle_sleeptime : 4170763761184 nsecs tick_broadcast_mask: 00000003 event_broadcast_mask: 00000001 CPU#0's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246432689566 nsecs CPU#1's local event device: Clock Event Device: lapic capabilities: 0000000e max_delta_ns: 807385544 min_delta_ns: 1443 mult: 44624025 shift: 32 set_next_event: lapic_next_event set_mode: lapic_timer_setup event_handler: hrtimer_interrupt .installed: 1 .expires: 4246050084568 nsecs Clock Event Device: hpet capabilities: 00000007 max_delta_ns: 2147483647 min_delta_ns: 3352 mult: 61496110 shift: 32 set_next_event: hpet_next_event set_mode: hpet_set_mode event_handler: handle_nextevt_broadcast 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> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-16 12:28:15 +03:00
struct tick_sched *tick_get_tick_sched(int cpu)
{
return &per_cpu(tick_cpu_sched, cpu);
}
#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
/*
* The time, when the last jiffy update happened. Write access must hold
* jiffies_lock and jiffies_seq. tick_nohz_next_event() needs to get a
* consistent view of jiffies and last_jiffies_update.
*/
static ktime_t last_jiffies_update;
/*
* Must be called with interrupts disabled !
*/
static void tick_do_update_jiffies64(ktime_t now)
{
unsigned long ticks = 1;
ktime_t delta, nextp;
/*
* 64bit can do a quick check without holding jiffies lock and
* without looking at the sequence count. The smp_load_acquire()
* pairs with the update done later in this function.
*
* 32bit cannot do that because the store of tick_next_period
* consists of two 32bit stores and the first store could move it
* to a random point in the future.
*/
if (IS_ENABLED(CONFIG_64BIT)) {
if (ktime_before(now, smp_load_acquire(&tick_next_period)))
return;
} else {
unsigned int seq;
/*
* Avoid contention on jiffies_lock and protect the quick
* check with the sequence count.
*/
do {
seq = read_seqcount_begin(&jiffies_seq);
nextp = tick_next_period;
} while (read_seqcount_retry(&jiffies_seq, seq));
if (ktime_before(now, nextp))
return;
}
/* Quick check failed, i.e. update is required. */
raw_spin_lock(&jiffies_lock);
/*
* Reevaluate with the lock held. Another CPU might have done the
* update already.
*/
if (ktime_before(now, tick_next_period)) {
raw_spin_unlock(&jiffies_lock);
return;
}
write_seqcount_begin(&jiffies_seq);
delta = ktime_sub(now, tick_next_period);
if (unlikely(delta >= TICK_NSEC)) {
/* Slow path for long idle sleep times */
s64 incr = TICK_NSEC;
ticks += ktime_divns(delta, incr);
last_jiffies_update = ktime_add_ns(last_jiffies_update,
incr * ticks);
} else {
last_jiffies_update = ktime_add_ns(last_jiffies_update,
TICK_NSEC);
}
/* Advance jiffies to complete the jiffies_seq protected job */
jiffies_64 += ticks;
/*
* Keep the tick_next_period variable up to date.
*/
nextp = ktime_add_ns(last_jiffies_update, TICK_NSEC);
if (IS_ENABLED(CONFIG_64BIT)) {
/*
* Pairs with smp_load_acquire() in the lockless quick
* check above and ensures that the update to jiffies_64 is
* not reordered vs. the store to tick_next_period, neither
* by the compiler nor by the CPU.
*/
smp_store_release(&tick_next_period, nextp);
} else {
/*
* A plain store is good enough on 32bit as the quick check
* above is protected by the sequence count.
*/
tick_next_period = nextp;
}
/*
* Release the sequence count. calc_global_load() below is not
* protected by it, but jiffies_lock needs to be held to prevent
* concurrent invocations.
*/
write_seqcount_end(&jiffies_seq);
calc_global_load();
raw_spin_unlock(&jiffies_lock);
update_wall_time();
}
/*
* Initialize and return retrieve the jiffies update.
*/
static ktime_t tick_init_jiffy_update(void)
{
ktime_t period;
raw_spin_lock(&jiffies_lock);
write_seqcount_begin(&jiffies_seq);
/* Did we start the jiffies update yet ? */
tick/common: Align tick period during sched_timer setup commit 13bb06f8dd42071cb9a49f6e21099eea05d4b856 upstream. The tick period is aligned very early while the first clock_event_device is registered. At that point the system runs in periodic mode and switches later to one-shot mode if possible. The next wake-up event is programmed based on the aligned value (tick_next_period) but the delta value, that is used to program the clock_event_device, is computed based on ktime_get(). With the subtracted offset, the device fires earlier than the exact time frame. With a large enough offset the system programs the timer for the next wake-up and the remaining time left is too small to make any boot progress. The system hangs. Move the alignment later to the setup of tick_sched timer. At this point the system switches to oneshot mode and a high resolution clocksource is available. At this point it is safe to align tick_next_period because ktime_get() will now return accurate (not jiffies based) time. [bigeasy: Patch description + testing]. Fixes: e9523a0d81899 ("tick/common: Align tick period with the HZ tick.") Reported-by: Mathias Krause <minipli@grsecurity.net> Reported-by: "Bhatnagar, Rishabh" <risbhat@amazon.com> Suggested-by: Mathias Krause <minipli@grsecurity.net> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Richard W.M. Jones <rjones@redhat.com> Tested-by: Mathias Krause <minipli@grsecurity.net> Acked-by: SeongJae Park <sj@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/5a56290d-806e-b9a5-f37c-f21958b5a8c0@grsecurity.net Link: https://lore.kernel.org/12c6f9a3-d087-b824-0d05-0d18c9bc1bf3@amazon.com Link: https://lore.kernel.org/r/20230615091830.RxMV2xf_@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2023-06-15 12:18:30 +03:00
if (last_jiffies_update == 0) {
u32 rem;
/*
* Ensure that the tick is aligned to a multiple of
* TICK_NSEC.
*/
div_u64_rem(tick_next_period, TICK_NSEC, &rem);
if (rem)
tick_next_period += TICK_NSEC - rem;
last_jiffies_update = tick_next_period;
tick/common: Align tick period during sched_timer setup commit 13bb06f8dd42071cb9a49f6e21099eea05d4b856 upstream. The tick period is aligned very early while the first clock_event_device is registered. At that point the system runs in periodic mode and switches later to one-shot mode if possible. The next wake-up event is programmed based on the aligned value (tick_next_period) but the delta value, that is used to program the clock_event_device, is computed based on ktime_get(). With the subtracted offset, the device fires earlier than the exact time frame. With a large enough offset the system programs the timer for the next wake-up and the remaining time left is too small to make any boot progress. The system hangs. Move the alignment later to the setup of tick_sched timer. At this point the system switches to oneshot mode and a high resolution clocksource is available. At this point it is safe to align tick_next_period because ktime_get() will now return accurate (not jiffies based) time. [bigeasy: Patch description + testing]. Fixes: e9523a0d81899 ("tick/common: Align tick period with the HZ tick.") Reported-by: Mathias Krause <minipli@grsecurity.net> Reported-by: "Bhatnagar, Rishabh" <risbhat@amazon.com> Suggested-by: Mathias Krause <minipli@grsecurity.net> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Richard W.M. Jones <rjones@redhat.com> Tested-by: Mathias Krause <minipli@grsecurity.net> Acked-by: SeongJae Park <sj@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/5a56290d-806e-b9a5-f37c-f21958b5a8c0@grsecurity.net Link: https://lore.kernel.org/12c6f9a3-d087-b824-0d05-0d18c9bc1bf3@amazon.com Link: https://lore.kernel.org/r/20230615091830.RxMV2xf_@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2023-06-15 12:18:30 +03:00
}
period = last_jiffies_update;
write_seqcount_end(&jiffies_seq);
raw_spin_unlock(&jiffies_lock);
return period;
}
#define MAX_STALLED_JIFFIES 5
static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
{
int cpu = smp_processor_id();
nohz: Rename CONFIG_NO_HZ to CONFIG_NO_HZ_COMMON We are planning to convert the dynticks Kconfig options layout into a choice menu. The user must be able to easily pick any of the following implementations: constant periodic tick, idle dynticks, full dynticks. As this implies a mutual exclusion, the two dynticks implementions need to converge on the selection of a common Kconfig option in order to ease the sharing of a common infrastructure. It would thus seem pretty natural to reuse CONFIG_NO_HZ to that end. It already implements all the idle dynticks code and the full dynticks depends on all that code for now. So ideally the choice menu would propose CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED then both would select CONFIG_NO_HZ. On the other hand we want to stay backward compatible: if CONFIG_NO_HZ is set in an older config file, we want to enable CONFIG_NO_HZ_IDLE by default. But we can't afford both at the same time or we run into a circular dependency: 1) CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED both select CONFIG_NO_HZ 2) If CONFIG_NO_HZ is set, we default to CONFIG_NO_HZ_IDLE We might be able to support that from Kconfig/Kbuild but it may not be wise to introduce such a confusing behaviour. So to solve this, create a new CONFIG_NO_HZ_COMMON option which gathers the common code between idle and full dynticks (that common code for now is simply the idle dynticks code) and select it from their referring Kconfig. Then we'll later create CONFIG_NO_HZ_IDLE and map CONFIG_NO_HZ to it for backward compatibility. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2011-08-11 01:21:01 +04:00
#ifdef CONFIG_NO_HZ_COMMON
/*
* Check if the do_timer duty was dropped. We don't care about
* concurrency: This happens only when the CPU in charge went
* into a long sleep. If two CPUs happen to assign themselves to
* this duty, then the jiffies update is still serialized by
* jiffies_lock.
*
* If nohz_full is enabled, this should not happen because the
* tick_do_timer_cpu never relinquishes.
*/
if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) {
#ifdef CONFIG_NO_HZ_FULL
WARN_ON_ONCE(tick_nohz_full_running);
#endif
tick_do_timer_cpu = cpu;
}
#endif
/* Check, if the jiffies need an update */
if (tick_do_timer_cpu == cpu)
tick_do_update_jiffies64(now);
/*
* If jiffies update stalled for too long (timekeeper in stop_machine()
* or VMEXIT'ed for several msecs), force an update.
*/
if (ts->last_tick_jiffies != jiffies) {
ts->stalled_jiffies = 0;
ts->last_tick_jiffies = READ_ONCE(jiffies);
} else {
if (++ts->stalled_jiffies == MAX_STALLED_JIFFIES) {
tick_do_update_jiffies64(now);
ts->stalled_jiffies = 0;
ts->last_tick_jiffies = READ_ONCE(jiffies);
}
}
if (ts->inidle)
ts->got_idle_tick = 1;
}
static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
{
nohz: Rename CONFIG_NO_HZ to CONFIG_NO_HZ_COMMON We are planning to convert the dynticks Kconfig options layout into a choice menu. The user must be able to easily pick any of the following implementations: constant periodic tick, idle dynticks, full dynticks. As this implies a mutual exclusion, the two dynticks implementions need to converge on the selection of a common Kconfig option in order to ease the sharing of a common infrastructure. It would thus seem pretty natural to reuse CONFIG_NO_HZ to that end. It already implements all the idle dynticks code and the full dynticks depends on all that code for now. So ideally the choice menu would propose CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED then both would select CONFIG_NO_HZ. On the other hand we want to stay backward compatible: if CONFIG_NO_HZ is set in an older config file, we want to enable CONFIG_NO_HZ_IDLE by default. But we can't afford both at the same time or we run into a circular dependency: 1) CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED both select CONFIG_NO_HZ 2) If CONFIG_NO_HZ is set, we default to CONFIG_NO_HZ_IDLE We might be able to support that from Kconfig/Kbuild but it may not be wise to introduce such a confusing behaviour. So to solve this, create a new CONFIG_NO_HZ_COMMON option which gathers the common code between idle and full dynticks (that common code for now is simply the idle dynticks code) and select it from their referring Kconfig. Then we'll later create CONFIG_NO_HZ_IDLE and map CONFIG_NO_HZ to it for backward compatibility. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2011-08-11 01:21:01 +04:00
#ifdef CONFIG_NO_HZ_COMMON
/*
* When we are idle and the tick is stopped, we have to touch
* the watchdog as we might not schedule for a really long
* time. This happens on complete idle SMP systems while
* waiting on the login prompt. We also increment the "start of
* idle" jiffy stamp so the idle accounting adjustment we do
* when we go busy again does not account too much ticks.
*/
if (ts->tick_stopped) {
touch_softlockup_watchdog_sched();
if (is_idle_task(current))
ts->idle_jiffies++;
nohz: Fix collision between tick and other hrtimers, again This restores commit: 24b91e360ef5: ("nohz: Fix collision between tick and other hrtimers") ... which got reverted by commit: 558e8e27e73f: ('Revert "nohz: Fix collision between tick and other hrtimers"') ... due to a regression where CPUs spuriously stopped ticking. The bug happened when a tick fired too early past its expected expiration: on IRQ exit the tick was scheduled again to the same deadline but skipped reprogramming because ts->next_tick still kept in cache the deadline. This has been fixed now with resetting ts->next_tick from the tick itself. Extra care has also been taken to prevent from obsolete values throughout CPU hotplug operations. When the tick is stopped and an interrupt occurs afterward, we check on that interrupt exit if the next tick needs to be rescheduled. If it doesn't need any update, we don't want to do anything. In order to check if the tick needs an update, we compare it against the clockevent device deadline. Now that's a problem because the clockevent device is at a lower level than the tick itself if it is implemented on top of hrtimer. Every hrtimer share this clockevent device. So comparing the next tick deadline against the clockevent device deadline is wrong because the device may be programmed for another hrtimer whose deadline collides with the tick. As a result we may end up not reprogramming the tick accidentally. In a worst case scenario under full dynticks mode, the tick stops firing as it is supposed to every 1hz, leaving /proc/stat stalled: Task in a full dynticks CPU ---------------------------- * hrtimer A is queued 2 seconds ahead * the tick is stopped, scheduled 1 second ahead * tick fires 1 second later * on tick exit, nohz schedules the tick 1 second ahead but sees the clockevent device is already programmed to that deadline, fooled by hrtimer A, the tick isn't rescheduled. * hrtimer A is cancelled before its deadline * tick never fires again until an interrupt happens... In order to fix this, store the next tick deadline to the tick_sched local structure and reuse that value later to check whether we need to reprogram the clock after an interrupt. On the other hand, ts->sleep_length still wants to know about the next clock event and not just the tick, so we want to improve the related comment to avoid confusion. Reported-and-tested-by: Tim Wright <tim@binbash.co.uk> Reported-and-tested-by: Pavel Machek <pavel@ucw.cz> Reported-by: James Hartsock <hartsjc@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1492783255-5051-2-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-04-21 17:00:54 +03:00
/*
* In case the current tick fired too early past its expected
* expiration, make sure we don't bypass the next clock reprogramming
* to the same deadline.
*/
ts->next_tick = 0;
}
#endif
update_process_times(user_mode(regs));
profile_tick(CPU_PROFILING);
}
#endif
#ifdef CONFIG_NO_HZ_FULL
cpumask_var_t tick_nohz_full_mask;
EXPORT_SYMBOL_GPL(tick_nohz_full_mask);
bool tick_nohz_full_running;
EXPORT_SYMBOL_GPL(tick_nohz_full_running);
static atomic_t tick_dep_mask;
nohz: Basic full dynticks interface For extreme usecases such as Real Time or HPC, having the ability to shutdown the tick when a single task runs on a CPU is a desired feature: * Reducing the amount of interrupts improves throughput for CPU-bound tasks. The CPU is less distracted from its real job, from an execution time and from the cache point of views. * This also improve latency response as we have less critical sections. Start with introducing a very simple interface to define full dynticks CPU: use a boot time option defined cpumask through the "nohz_extended=" kernel parameter. CPUs that are part of this range will have their tick shutdown whenever possible: provided they run a single task and they don't do kernel activity that require the periodic tick. These details will be later documented in Documentation/* An online CPU must be kept outside this range to handle the timekeeping. Suggested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2012-12-18 20:32:19 +04:00
static bool check_tick_dependency(atomic_t *dep)
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
{
int val = atomic_read(dep);
if (val & TICK_DEP_MASK_POSIX_TIMER) {
trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER);
return true;
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
}
if (val & TICK_DEP_MASK_PERF_EVENTS) {
trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS);
return true;
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
}
if (val & TICK_DEP_MASK_SCHED) {
trace_tick_stop(0, TICK_DEP_MASK_SCHED);
return true;
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
}
if (val & TICK_DEP_MASK_CLOCK_UNSTABLE) {
trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE);
return true;
}
if (val & TICK_DEP_MASK_RCU) {
trace_tick_stop(0, TICK_DEP_MASK_RCU);
return true;
}
if (val & TICK_DEP_MASK_RCU_EXP) {
trace_tick_stop(0, TICK_DEP_MASK_RCU_EXP);
return true;
}
return false;
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
}
static bool can_stop_full_tick(int cpu, struct tick_sched *ts)
{
lockdep_assert_irqs_disabled();
if (unlikely(!cpu_online(cpu)))
return false;
if (check_tick_dependency(&tick_dep_mask))
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
return false;
if (check_tick_dependency(&ts->tick_dep_mask))
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
return false;
if (check_tick_dependency(&current->tick_dep_mask))
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
return false;
if (check_tick_dependency(&current->signal->tick_dep_mask))
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
return false;
return true;
}
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
static void nohz_full_kick_func(struct irq_work *work)
{
/* Empty, the tick restart happens on tick_nohz_irq_exit() */
}
static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) =
IRQ_WORK_INIT_HARD(nohz_full_kick_func);
nohz: Restore NMI safe local irq work for local nohz kick The local nohz kick is currently used by perf which needs it to be NMI-safe. Recent commit though (7d1311b93e58ed55f3a31cc8f94c4b8fe988a2b9) changed its implementation to fire the local kick using the remote kick API. It was convenient to make the code more generic but the remote kick isn't NMI-safe. As a result: WARNING: CPU: 3 PID: 18062 at kernel/irq_work.c:72 irq_work_queue_on+0x11e/0x140() CPU: 3 PID: 18062 Comm: trinity-subchil Not tainted 3.16.0+ #34 0000000000000009 00000000903774d1 ffff880244e06c00 ffffffff9a7f1e37 0000000000000000 ffff880244e06c38 ffffffff9a0791dd ffff880244fce180 0000000000000003 ffff880244e06d58 ffff880244e06ef8 0000000000000000 Call Trace: <NMI> [<ffffffff9a7f1e37>] dump_stack+0x4e/0x7a [<ffffffff9a0791dd>] warn_slowpath_common+0x7d/0xa0 [<ffffffff9a07930a>] warn_slowpath_null+0x1a/0x20 [<ffffffff9a17ca1e>] irq_work_queue_on+0x11e/0x140 [<ffffffff9a10a2c7>] tick_nohz_full_kick_cpu+0x57/0x90 [<ffffffff9a186cd5>] __perf_event_overflow+0x275/0x350 [<ffffffff9a184f80>] ? perf_event_task_disable+0xa0/0xa0 [<ffffffff9a01a4cf>] ? x86_perf_event_set_period+0xbf/0x150 [<ffffffff9a187934>] perf_event_overflow+0x14/0x20 [<ffffffff9a020386>] intel_pmu_handle_irq+0x206/0x410 [<ffffffff9a0b54d3>] ? arch_vtime_task_switch+0x63/0x130 [<ffffffff9a01937b>] perf_event_nmi_handler+0x2b/0x50 [<ffffffff9a007b72>] nmi_handle+0xd2/0x390 [<ffffffff9a007aa5>] ? nmi_handle+0x5/0x390 [<ffffffff9a0d131b>] ? lock_release+0xab/0x330 [<ffffffff9a008062>] default_do_nmi+0x72/0x1c0 [<ffffffff9a0c925f>] ? cpuacct_account_field+0xcf/0x200 [<ffffffff9a008268>] do_nmi+0xb8/0x100 Lets fix this by restoring the use of local irq work for the nohz local kick. Reported-by: Catalin Iacob <iacobcatalin@gmail.com> Reported-and-tested-by: Dave Jones <davej@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2014-08-13 20:50:16 +04:00
/*
* Kick this CPU if it's full dynticks in order to force it to
* re-evaluate its dependency on the tick and restart it if necessary.
* This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(),
* is NMI safe.
*/
static void tick_nohz_full_kick(void)
nohz: Restore NMI safe local irq work for local nohz kick The local nohz kick is currently used by perf which needs it to be NMI-safe. Recent commit though (7d1311b93e58ed55f3a31cc8f94c4b8fe988a2b9) changed its implementation to fire the local kick using the remote kick API. It was convenient to make the code more generic but the remote kick isn't NMI-safe. As a result: WARNING: CPU: 3 PID: 18062 at kernel/irq_work.c:72 irq_work_queue_on+0x11e/0x140() CPU: 3 PID: 18062 Comm: trinity-subchil Not tainted 3.16.0+ #34 0000000000000009 00000000903774d1 ffff880244e06c00 ffffffff9a7f1e37 0000000000000000 ffff880244e06c38 ffffffff9a0791dd ffff880244fce180 0000000000000003 ffff880244e06d58 ffff880244e06ef8 0000000000000000 Call Trace: <NMI> [<ffffffff9a7f1e37>] dump_stack+0x4e/0x7a [<ffffffff9a0791dd>] warn_slowpath_common+0x7d/0xa0 [<ffffffff9a07930a>] warn_slowpath_null+0x1a/0x20 [<ffffffff9a17ca1e>] irq_work_queue_on+0x11e/0x140 [<ffffffff9a10a2c7>] tick_nohz_full_kick_cpu+0x57/0x90 [<ffffffff9a186cd5>] __perf_event_overflow+0x275/0x350 [<ffffffff9a184f80>] ? perf_event_task_disable+0xa0/0xa0 [<ffffffff9a01a4cf>] ? x86_perf_event_set_period+0xbf/0x150 [<ffffffff9a187934>] perf_event_overflow+0x14/0x20 [<ffffffff9a020386>] intel_pmu_handle_irq+0x206/0x410 [<ffffffff9a0b54d3>] ? arch_vtime_task_switch+0x63/0x130 [<ffffffff9a01937b>] perf_event_nmi_handler+0x2b/0x50 [<ffffffff9a007b72>] nmi_handle+0xd2/0x390 [<ffffffff9a007aa5>] ? nmi_handle+0x5/0x390 [<ffffffff9a0d131b>] ? lock_release+0xab/0x330 [<ffffffff9a008062>] default_do_nmi+0x72/0x1c0 [<ffffffff9a0c925f>] ? cpuacct_account_field+0xcf/0x200 [<ffffffff9a008268>] do_nmi+0xb8/0x100 Lets fix this by restoring the use of local irq work for the nohz local kick. Reported-by: Catalin Iacob <iacobcatalin@gmail.com> Reported-and-tested-by: Dave Jones <davej@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2014-08-13 20:50:16 +04:00
{
if (!tick_nohz_full_cpu(smp_processor_id()))
return;
irq_work_queue(this_cpu_ptr(&nohz_full_kick_work));
nohz: Restore NMI safe local irq work for local nohz kick The local nohz kick is currently used by perf which needs it to be NMI-safe. Recent commit though (7d1311b93e58ed55f3a31cc8f94c4b8fe988a2b9) changed its implementation to fire the local kick using the remote kick API. It was convenient to make the code more generic but the remote kick isn't NMI-safe. As a result: WARNING: CPU: 3 PID: 18062 at kernel/irq_work.c:72 irq_work_queue_on+0x11e/0x140() CPU: 3 PID: 18062 Comm: trinity-subchil Not tainted 3.16.0+ #34 0000000000000009 00000000903774d1 ffff880244e06c00 ffffffff9a7f1e37 0000000000000000 ffff880244e06c38 ffffffff9a0791dd ffff880244fce180 0000000000000003 ffff880244e06d58 ffff880244e06ef8 0000000000000000 Call Trace: <NMI> [<ffffffff9a7f1e37>] dump_stack+0x4e/0x7a [<ffffffff9a0791dd>] warn_slowpath_common+0x7d/0xa0 [<ffffffff9a07930a>] warn_slowpath_null+0x1a/0x20 [<ffffffff9a17ca1e>] irq_work_queue_on+0x11e/0x140 [<ffffffff9a10a2c7>] tick_nohz_full_kick_cpu+0x57/0x90 [<ffffffff9a186cd5>] __perf_event_overflow+0x275/0x350 [<ffffffff9a184f80>] ? perf_event_task_disable+0xa0/0xa0 [<ffffffff9a01a4cf>] ? x86_perf_event_set_period+0xbf/0x150 [<ffffffff9a187934>] perf_event_overflow+0x14/0x20 [<ffffffff9a020386>] intel_pmu_handle_irq+0x206/0x410 [<ffffffff9a0b54d3>] ? arch_vtime_task_switch+0x63/0x130 [<ffffffff9a01937b>] perf_event_nmi_handler+0x2b/0x50 [<ffffffff9a007b72>] nmi_handle+0xd2/0x390 [<ffffffff9a007aa5>] ? nmi_handle+0x5/0x390 [<ffffffff9a0d131b>] ? lock_release+0xab/0x330 [<ffffffff9a008062>] default_do_nmi+0x72/0x1c0 [<ffffffff9a0c925f>] ? cpuacct_account_field+0xcf/0x200 [<ffffffff9a008268>] do_nmi+0xb8/0x100 Lets fix this by restoring the use of local irq work for the nohz local kick. Reported-by: Catalin Iacob <iacobcatalin@gmail.com> Reported-and-tested-by: Dave Jones <davej@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2014-08-13 20:50:16 +04:00
}
/*
* Kick the CPU if it's full dynticks in order to force it to
* re-evaluate its dependency on the tick and restart it if necessary.
*/
void tick_nohz_full_kick_cpu(int cpu)
{
if (!tick_nohz_full_cpu(cpu))
return;
irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu);
}
static void tick_nohz_kick_task(struct task_struct *tsk)
{
tick/nohz: Kick only _queued_ task whose tick dependency is updated When the tick dependency of a task is updated, we want it to aknowledge the new state and restart the tick if needed. If the task is not running, we don't need to kick it because it will observe the new dependency upon scheduling in. But if the task is running, we may need to send an IPI to it so that it gets notified. Unfortunately we don't have the means to check if a task is running in a race free way. Checking p->on_cpu in a synchronized way against p->tick_dep_mask would imply adding a full barrier between prepare_task_switch() and tick_nohz_task_switch(), which we want to avoid in this fast-path. Therefore we blindly fire an IPI to the task's CPU. Meanwhile we can check if the task is queued on the CPU rq because p->on_rq is always set to TASK_ON_RQ_QUEUED _before_ schedule() and its full barrier that precedes tick_nohz_task_switch(). And if the task is queued on a nohz_full CPU, it also has fair chances to be running as the isolation constraints prescribe running single tasks on full dynticks CPUs. So use this as a trick to check if we can spare an IPI toward a non-running task. NOTE: For the ordering to be correct, it is assumed that we never deactivate a task while it is running, the only exception being the task deactivating itself while scheduling out. Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Frederic Weisbecker <frederic@kernel.org> Signed-off-by: Ingo Molnar <mingo@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20210512232924.150322-9-frederic@kernel.org
2021-05-13 02:29:22 +03:00
int cpu;
/*
* If the task is not running, run_posix_cpu_timers()
* has nothing to elapse, IPI can then be spared.
*
* activate_task() STORE p->tick_dep_mask
* STORE p->on_rq
* __schedule() (switch to task 'p') smp_mb() (atomic_fetch_or())
* LOCK rq->lock LOAD p->on_rq
* smp_mb__after_spin_lock()
* tick_nohz_task_switch()
* LOAD p->tick_dep_mask
*/
if (!sched_task_on_rq(tsk))
return;
/*
* If the task concurrently migrates to another CPU,
* we guarantee it sees the new tick dependency upon
* schedule.
*
* set_task_cpu(p, cpu);
* STORE p->cpu = @cpu
* __schedule() (switch to task 'p')
* LOCK rq->lock
* smp_mb__after_spin_lock() STORE p->tick_dep_mask
* tick_nohz_task_switch() smp_mb() (atomic_fetch_or())
* LOAD p->tick_dep_mask LOAD p->cpu
*/
tick/nohz: Kick only _queued_ task whose tick dependency is updated When the tick dependency of a task is updated, we want it to aknowledge the new state and restart the tick if needed. If the task is not running, we don't need to kick it because it will observe the new dependency upon scheduling in. But if the task is running, we may need to send an IPI to it so that it gets notified. Unfortunately we don't have the means to check if a task is running in a race free way. Checking p->on_cpu in a synchronized way against p->tick_dep_mask would imply adding a full barrier between prepare_task_switch() and tick_nohz_task_switch(), which we want to avoid in this fast-path. Therefore we blindly fire an IPI to the task's CPU. Meanwhile we can check if the task is queued on the CPU rq because p->on_rq is always set to TASK_ON_RQ_QUEUED _before_ schedule() and its full barrier that precedes tick_nohz_task_switch(). And if the task is queued on a nohz_full CPU, it also has fair chances to be running as the isolation constraints prescribe running single tasks on full dynticks CPUs. So use this as a trick to check if we can spare an IPI toward a non-running task. NOTE: For the ordering to be correct, it is assumed that we never deactivate a task while it is running, the only exception being the task deactivating itself while scheduling out. Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Frederic Weisbecker <frederic@kernel.org> Signed-off-by: Ingo Molnar <mingo@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20210512232924.150322-9-frederic@kernel.org
2021-05-13 02:29:22 +03:00
cpu = task_cpu(tsk);
preempt_disable();
if (cpu_online(cpu))
tick_nohz_full_kick_cpu(cpu);
preempt_enable();
}
/*
* Kick all full dynticks CPUs in order to force these to re-evaluate
* their dependency on the tick and restart it if necessary.
*/
static void tick_nohz_full_kick_all(void)
{
int cpu;
if (!tick_nohz_full_running)
return;
preempt_disable();
for_each_cpu_and(cpu, tick_nohz_full_mask, cpu_online_mask)
tick_nohz_full_kick_cpu(cpu);
preempt_enable();
}
static void tick_nohz_dep_set_all(atomic_t *dep,
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
enum tick_dep_bits bit)
{
int prev;
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
prev = atomic_fetch_or(BIT(bit), dep);
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
if (!prev)
tick_nohz_full_kick_all();
}
/*
* Set a global tick dependency. Used by perf events that rely on freq and
* by unstable clock.
*/
void tick_nohz_dep_set(enum tick_dep_bits bit)
{
tick_nohz_dep_set_all(&tick_dep_mask, bit);
}
void tick_nohz_dep_clear(enum tick_dep_bits bit)
{
atomic_andnot(BIT(bit), &tick_dep_mask);
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
}
/*
* Set per-CPU tick dependency. Used by scheduler and perf events in order to
* manage events throttling.
*/
void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit)
{
int prev;
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
struct tick_sched *ts;
ts = per_cpu_ptr(&tick_cpu_sched, cpu);
prev = atomic_fetch_or(BIT(bit), &ts->tick_dep_mask);
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
if (!prev) {
preempt_disable();
/* Perf needs local kick that is NMI safe */
if (cpu == smp_processor_id()) {
tick_nohz_full_kick();
} else {
/* Remote irq work not NMI-safe */
if (!WARN_ON_ONCE(in_nmi()))
tick_nohz_full_kick_cpu(cpu);
}
preempt_enable();
}
}
EXPORT_SYMBOL_GPL(tick_nohz_dep_set_cpu);
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
{
struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu);
atomic_andnot(BIT(bit), &ts->tick_dep_mask);
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
}
EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu);
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
/*
tick/nohz: Narrow down noise while setting current task's tick dependency Setting a tick dependency on any task, including the case where a task sets that dependency on itself, triggers an IPI to all CPUs. That is of course suboptimal but it had previously not been an issue because it was only used by POSIX CPU timers on nohz_full, which apparently never occurs in latency-sensitive workloads in production. (Or users of such systems are suffering in silence on the one hand or venting their ire on the wrong people on the other.) But RCU now sets a task tick dependency on the current task in order to fix stall issues that can occur during RCU callback processing. Thus, RCU callback processing triggers frequent system-wide IPIs from nohz_full CPUs. This is quite counter-productive, after all, avoiding IPIs is what nohz_full is supposed to be all about. This commit therefore optimizes tasks' self-setting of a task tick dependency by using tick_nohz_full_kick() to avoid the system-wide IPI. Instead, only the execution of the one task is disturbed, which is acceptable given that this disturbance is well down into the noise compared to the degree to which the RCU callback processing itself disturbs execution. Fixes: 6a949b7af82d (rcu: Force on tick when invoking lots of callbacks) Reported-by: Matt Fleming <matt@codeblueprint.co.uk> Signed-off-by: Frederic Weisbecker <frederic@kernel.org> Cc: stable@kernel.org Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
2020-05-15 03:34:29 +03:00
* Set a per-task tick dependency. RCU need this. Also posix CPU timers
* in order to elapse per task timers.
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
*/
void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit)
{
if (!atomic_fetch_or(BIT(bit), &tsk->tick_dep_mask))
tick_nohz_kick_task(tsk);
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
}
EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task);
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit)
{
atomic_andnot(BIT(bit), &tsk->tick_dep_mask);
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
}
EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_task);
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
/*
* Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse
* per process timers.
*/
void tick_nohz_dep_set_signal(struct task_struct *tsk,
enum tick_dep_bits bit)
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
{
int prev;
struct signal_struct *sig = tsk->signal;
prev = atomic_fetch_or(BIT(bit), &sig->tick_dep_mask);
if (!prev) {
struct task_struct *t;
lockdep_assert_held(&tsk->sighand->siglock);
__for_each_thread(sig, t)
tick_nohz_kick_task(t);
}
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
}
void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit)
{
atomic_andnot(BIT(bit), &sig->tick_dep_mask);
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
}
/*
* Re-evaluate the need for the tick as we switch the current task.
* It might need the tick due to per task/process properties:
* perf events, posix CPU timers, ...
*/
void __tick_nohz_task_switch(void)
{
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
struct tick_sched *ts;
if (!tick_nohz_full_cpu(smp_processor_id()))
return;
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
ts = this_cpu_ptr(&tick_cpu_sched);
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
if (ts->tick_stopped) {
if (atomic_read(&current->tick_dep_mask) ||
atomic_read(&current->signal->tick_dep_mask))
nohz: New tick dependency mask The tick dependency is evaluated on every IRQ and context switch. This consists is a batch of checks which determine whether it is safe to stop the tick or not. These checks are often split in many details: posix cpu timers, scheduler, sched clock, perf events.... each of which are made of smaller details: posix cpu timer involves checking process wide timers then thread wide timers. Perf involves checking freq events then more per cpu details. Checking these informations asynchronously every time we update the full dynticks state bring avoidable overhead and a messy layout. Let's introduce instead tick dependency masks: one for system wide dependency (unstable sched clock, freq based perf events), one for CPU wide dependency (sched, throttling perf events), and task/signal level dependencies (posix cpu timers). The subsystems are responsible for setting and clearing their dependency through a set of APIs that will take care of concurrent dependency mask modifications and kick targets to restart the relevant CPU tick whenever needed. This new dependency engine stays beside the old one until all subsystems having a tick dependency are converted to it. Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2015-06-07 16:54:30 +03:00
tick_nohz_full_kick();
}
}
/* Get the boot-time nohz CPU list from the kernel parameters. */
void __init tick_nohz_full_setup(cpumask_var_t cpumask)
nohz: Basic full dynticks interface For extreme usecases such as Real Time or HPC, having the ability to shutdown the tick when a single task runs on a CPU is a desired feature: * Reducing the amount of interrupts improves throughput for CPU-bound tasks. The CPU is less distracted from its real job, from an execution time and from the cache point of views. * This also improve latency response as we have less critical sections. Start with introducing a very simple interface to define full dynticks CPU: use a boot time option defined cpumask through the "nohz_extended=" kernel parameter. CPUs that are part of this range will have their tick shutdown whenever possible: provided they run a single task and they don't do kernel activity that require the periodic tick. These details will be later documented in Documentation/* An online CPU must be kept outside this range to handle the timekeeping. Suggested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2012-12-18 20:32:19 +04:00
{
alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
cpumask_copy(tick_nohz_full_mask, cpumask);
tick_nohz_full_running = true;
nohz: Basic full dynticks interface For extreme usecases such as Real Time or HPC, having the ability to shutdown the tick when a single task runs on a CPU is a desired feature: * Reducing the amount of interrupts improves throughput for CPU-bound tasks. The CPU is less distracted from its real job, from an execution time and from the cache point of views. * This also improve latency response as we have less critical sections. Start with introducing a very simple interface to define full dynticks CPU: use a boot time option defined cpumask through the "nohz_extended=" kernel parameter. CPUs that are part of this range will have their tick shutdown whenever possible: provided they run a single task and they don't do kernel activity that require the periodic tick. These details will be later documented in Documentation/* An online CPU must be kept outside this range to handle the timekeeping. Suggested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2012-12-18 20:32:19 +04:00
}
bool tick_nohz_cpu_hotpluggable(unsigned int cpu)
{
/*
* The tick_do_timer_cpu CPU handles housekeeping duty (unbound
* timers, workqueues, timekeeping, ...) on behalf of full dynticks
* CPUs. It must remain online when nohz full is enabled.
*/
if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
return false;
return true;
}
static int tick_nohz_cpu_down(unsigned int cpu)
{
return tick_nohz_cpu_hotpluggable(cpu) ? 0 : -EBUSY;
}
void __init tick_nohz_init(void)
nohz: Basic full dynticks interface For extreme usecases such as Real Time or HPC, having the ability to shutdown the tick when a single task runs on a CPU is a desired feature: * Reducing the amount of interrupts improves throughput for CPU-bound tasks. The CPU is less distracted from its real job, from an execution time and from the cache point of views. * This also improve latency response as we have less critical sections. Start with introducing a very simple interface to define full dynticks CPU: use a boot time option defined cpumask through the "nohz_extended=" kernel parameter. CPUs that are part of this range will have their tick shutdown whenever possible: provided they run a single task and they don't do kernel activity that require the periodic tick. These details will be later documented in Documentation/* An online CPU must be kept outside this range to handle the timekeeping. Suggested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2012-12-18 20:32:19 +04:00
{
int cpu, ret;
sched/isolation: Eliminate NO_HZ_FULL_ALL Commit 6f1982fedd59 ("sched/isolation: Handle the nohz_full= parameter") broke CONFIG_NO_HZ_FULL_ALL=y kernels. This breakage is due to the code under CONFIG_NO_HZ_FULL_ALL failing to invoke the shiny new housekeeping functions. This means that rcutorture scenario TREE04 now emits RCU CPU stall warnings due to the RCU grace-period kthreads not being awakened at a time of their choosing, or perhaps even not at all: [ 27.731422] rcu_bh kthread starved for 21001 jiffies! g18446744073709551369 c18446744073709551368 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x402 ->cpu=3 [ 27.731423] rcu_bh I14936 9 2 0x80080000 [ 27.731435] Call Trace: [ 27.731440] __schedule+0x31a/0x6d0 [ 27.731442] schedule+0x31/0x80 [ 27.731446] schedule_timeout+0x15a/0x320 [ 27.731453] ? call_timer_fn+0x130/0x130 [ 27.731457] rcu_gp_kthread+0x66c/0xea0 [ 27.731458] ? rcu_gp_kthread+0x66c/0xea0 Because no one has complained about CONFIG_NO_HZ_FULL_ALL=y being broken, I hypothesize that no one is in fact using it, other than rcutorture. This commit therefore eliminates CONFIG_NO_HZ_FULL_ALL and updates rcutorture's config files to instead use the nohz_full= kernel parameter to put the desired CPUs into nohz_full mode. Fixes: 6f1982fedd59 ("sched/isolation: Handle the nohz_full= parameter") Reported-by: kernel test robot <xiaolong.ye@intel.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Frederic Weisbecker <frederic@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Christoph Lameter <cl@linux.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Wanpeng Li <kernellwp@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Jonathan Corbet <corbet@lwn.net>
2017-12-01 02:36:35 +03:00
if (!tick_nohz_full_running)
return;
/*
* Full dynticks uses irq work to drive the tick rescheduling on safe
* locking contexts. But then we need irq work to raise its own
* interrupts to avoid circular dependency on the tick
*/
if (!arch_irq_work_has_interrupt()) {
pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support irq work self-IPIs\n");
cpumask_clear(tick_nohz_full_mask);
tick_nohz_full_running = false;
return;
}
if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) &&
!IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) {
cpu = smp_processor_id();
if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
pr_warn("NO_HZ: Clearing %d from nohz_full range "
"for timekeeping\n", cpu);
cpumask_clear_cpu(cpu, tick_nohz_full_mask);
}
}
for_each_cpu(cpu, tick_nohz_full_mask)
context_tracking_cpu_set(cpu);
ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
"kernel/nohz:predown", NULL,
tick_nohz_cpu_down);
WARN_ON(ret < 0);
pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n",
cpumask_pr_args(tick_nohz_full_mask));
nohz: Basic full dynticks interface For extreme usecases such as Real Time or HPC, having the ability to shutdown the tick when a single task runs on a CPU is a desired feature: * Reducing the amount of interrupts improves throughput for CPU-bound tasks. The CPU is less distracted from its real job, from an execution time and from the cache point of views. * This also improve latency response as we have less critical sections. Start with introducing a very simple interface to define full dynticks CPU: use a boot time option defined cpumask through the "nohz_extended=" kernel parameter. CPUs that are part of this range will have their tick shutdown whenever possible: provided they run a single task and they don't do kernel activity that require the periodic tick. These details will be later documented in Documentation/* An online CPU must be kept outside this range to handle the timekeeping. Suggested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2012-12-18 20:32:19 +04:00
}
#endif
/*
* NOHZ - aka dynamic tick functionality
*/
nohz: Rename CONFIG_NO_HZ to CONFIG_NO_HZ_COMMON We are planning to convert the dynticks Kconfig options layout into a choice menu. The user must be able to easily pick any of the following implementations: constant periodic tick, idle dynticks, full dynticks. As this implies a mutual exclusion, the two dynticks implementions need to converge on the selection of a common Kconfig option in order to ease the sharing of a common infrastructure. It would thus seem pretty natural to reuse CONFIG_NO_HZ to that end. It already implements all the idle dynticks code and the full dynticks depends on all that code for now. So ideally the choice menu would propose CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED then both would select CONFIG_NO_HZ. On the other hand we want to stay backward compatible: if CONFIG_NO_HZ is set in an older config file, we want to enable CONFIG_NO_HZ_IDLE by default. But we can't afford both at the same time or we run into a circular dependency: 1) CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED both select CONFIG_NO_HZ 2) If CONFIG_NO_HZ is set, we default to CONFIG_NO_HZ_IDLE We might be able to support that from Kconfig/Kbuild but it may not be wise to introduce such a confusing behaviour. So to solve this, create a new CONFIG_NO_HZ_COMMON option which gathers the common code between idle and full dynticks (that common code for now is simply the idle dynticks code) and select it from their referring Kconfig. Then we'll later create CONFIG_NO_HZ_IDLE and map CONFIG_NO_HZ to it for backward compatibility. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2011-08-11 01:21:01 +04:00
#ifdef CONFIG_NO_HZ_COMMON
/*
* NO HZ enabled ?
*/
bool tick_nohz_enabled __read_mostly = true;
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 01:50:33 +03:00
unsigned long tick_nohz_active __read_mostly;
/*
* Enable / Disable tickless mode
*/
static int __init setup_tick_nohz(char *str)
{
return (kstrtobool(str, &tick_nohz_enabled) == 0);
}
__setup("nohz=", setup_tick_nohz);
bool tick_nohz_tick_stopped(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
return ts->tick_stopped;
}
bool tick_nohz_tick_stopped_cpu(int cpu)
{
struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu);
return ts->tick_stopped;
}
/**
* tick_nohz_update_jiffies - update jiffies when idle was interrupted
*
* Called from interrupt entry when the CPU was idle
*
* In case the sched_tick was stopped on this CPU, we have to check if jiffies
* must be updated. Otherwise an interrupt handler could use a stale jiffy
* value. We do this unconditionally on any CPU, as we don't know whether the
* CPU, which has the update task assigned is in a long sleep.
*/
static void tick_nohz_update_jiffies(ktime_t now)
{
unsigned long flags;
__this_cpu_write(tick_cpu_sched.idle_waketime, now);
local_irq_save(flags);
tick_do_update_jiffies64(now);
local_irq_restore(flags);
touch_softlockup_watchdog_sched();
}
/*
* Updates the per-CPU time idle statistics counters
*/
static void
update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_update_time)
{
ktime_t delta;
if (ts->idle_active) {
delta = ktime_sub(now, ts->idle_entrytime);
if (nr_iowait_cpu(cpu) > 0)
ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
else
ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
ts->idle_entrytime = now;
}
if (last_update_time)
*last_update_time = ktime_to_us(now);
}
static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
{
update_ts_time_stats(smp_processor_id(), ts, now, NULL);
ts->idle_active = 0;
sched_clock_idle_wakeup_event();
}
static void tick_nohz_start_idle(struct tick_sched *ts)
{
ts->idle_entrytime = ktime_get();
ts->idle_active = 1;
sched_clock_idle_sleep_event();
}
/**
* get_cpu_idle_time_us - get the total idle time of a CPU
* @cpu: CPU number to query
* @last_update_time: variable to store update time in. Do not update
* counters if NULL.
*
* Return the cumulative idle time (since boot) for a given
* CPU, in microseconds.
*
* This time is measured via accounting rather than sampling,
* and is as accurate as ktime_get() is.
*
* This function returns -1 if NOHZ is not enabled.
*/
u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
ktime_t now, idle;
if (!tick_nohz_active)
return -1;
now = ktime_get();
if (last_update_time) {
update_ts_time_stats(cpu, ts, now, last_update_time);
idle = ts->idle_sleeptime;
} else {
if (ts->idle_active && !nr_iowait_cpu(cpu)) {
ktime_t delta = ktime_sub(now, ts->idle_entrytime);
idle = ktime_add(ts->idle_sleeptime, delta);
} else {
idle = ts->idle_sleeptime;
}
}
return ktime_to_us(idle);
}
EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
/**
* get_cpu_iowait_time_us - get the total iowait time of a CPU
* @cpu: CPU number to query
* @last_update_time: variable to store update time in. Do not update
* counters if NULL.
*
* Return the cumulative iowait time (since boot) for a given
* CPU, in microseconds.
*
* This time is measured via accounting rather than sampling,
* and is as accurate as ktime_get() is.
*
* This function returns -1 if NOHZ is not enabled.
*/
u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
ktime_t now, iowait;
if (!tick_nohz_active)
return -1;
now = ktime_get();
if (last_update_time) {
update_ts_time_stats(cpu, ts, now, last_update_time);
iowait = ts->iowait_sleeptime;
} else {
if (ts->idle_active && nr_iowait_cpu(cpu) > 0) {
ktime_t delta = ktime_sub(now, ts->idle_entrytime);
iowait = ktime_add(ts->iowait_sleeptime, delta);
} else {
iowait = ts->iowait_sleeptime;
}
}
return ktime_to_us(iowait);
}
EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
{
hrtimer_cancel(&ts->sched_timer);
hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
/* Forward the time to expire in the future */
hrtimer_forward(&ts->sched_timer, now, TICK_NSEC);
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
hrtimer_start_expires(&ts->sched_timer,
HRTIMER_MODE_ABS_PINNED_HARD);
} else {
tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
}
nohz: Fix collision between tick and other hrtimers, again This restores commit: 24b91e360ef5: ("nohz: Fix collision between tick and other hrtimers") ... which got reverted by commit: 558e8e27e73f: ('Revert "nohz: Fix collision between tick and other hrtimers"') ... due to a regression where CPUs spuriously stopped ticking. The bug happened when a tick fired too early past its expected expiration: on IRQ exit the tick was scheduled again to the same deadline but skipped reprogramming because ts->next_tick still kept in cache the deadline. This has been fixed now with resetting ts->next_tick from the tick itself. Extra care has also been taken to prevent from obsolete values throughout CPU hotplug operations. When the tick is stopped and an interrupt occurs afterward, we check on that interrupt exit if the next tick needs to be rescheduled. If it doesn't need any update, we don't want to do anything. In order to check if the tick needs an update, we compare it against the clockevent device deadline. Now that's a problem because the clockevent device is at a lower level than the tick itself if it is implemented on top of hrtimer. Every hrtimer share this clockevent device. So comparing the next tick deadline against the clockevent device deadline is wrong because the device may be programmed for another hrtimer whose deadline collides with the tick. As a result we may end up not reprogramming the tick accidentally. In a worst case scenario under full dynticks mode, the tick stops firing as it is supposed to every 1hz, leaving /proc/stat stalled: Task in a full dynticks CPU ---------------------------- * hrtimer A is queued 2 seconds ahead * the tick is stopped, scheduled 1 second ahead * tick fires 1 second later * on tick exit, nohz schedules the tick 1 second ahead but sees the clockevent device is already programmed to that deadline, fooled by hrtimer A, the tick isn't rescheduled. * hrtimer A is cancelled before its deadline * tick never fires again until an interrupt happens... In order to fix this, store the next tick deadline to the tick_sched local structure and reuse that value later to check whether we need to reprogram the clock after an interrupt. On the other hand, ts->sleep_length still wants to know about the next clock event and not just the tick, so we want to improve the related comment to avoid confusion. Reported-and-tested-by: Tim Wright <tim@binbash.co.uk> Reported-and-tested-by: Pavel Machek <pavel@ucw.cz> Reported-by: James Hartsock <hartsjc@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1492783255-5051-2-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-04-21 17:00:54 +03:00
/*
* Reset to make sure next tick stop doesn't get fooled by past
* cached clock deadline.
*/
ts->next_tick = 0;
}
nohz: Prevent a timer interrupt storm in tick_nohz_stop_sched_tick() The conditions in irq_exit() to invoke tick_nohz_irq_exit() which subsequently invokes tick_nohz_stop_sched_tick() are: if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) If need_resched() is not set, but a timer softirq is pending then this is an indication that the softirq code punted and delegated the execution to softirqd. need_resched() is not true because the current interrupted task takes precedence over softirqd. Invoking tick_nohz_irq_exit() in this case can cause an endless loop of timer interrupts because the timer wheel contains an expired timer, but softirqs are not yet executed. So it returns an immediate expiry request, which causes the timer to fire immediately again. Lather, rinse and repeat.... Prevent that by adding a check for a pending timer soft interrupt to the conditions in tick_nohz_stop_sched_tick() which avoid calling get_next_timer_interrupt(). That keeps the tick sched timer on the tick and prevents a repetitive programming of an already expired timer. Reported-by: Sebastian Siewior <bigeasy@linutronix.d> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Cc: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712272156050.2431@nanos
2017-12-22 17:51:13 +03:00
static inline bool local_timer_softirq_pending(void)
{
return local_softirq_pending() & BIT(TIMER_SOFTIRQ);
nohz: Prevent a timer interrupt storm in tick_nohz_stop_sched_tick() The conditions in irq_exit() to invoke tick_nohz_irq_exit() which subsequently invokes tick_nohz_stop_sched_tick() are: if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) If need_resched() is not set, but a timer softirq is pending then this is an indication that the softirq code punted and delegated the execution to softirqd. need_resched() is not true because the current interrupted task takes precedence over softirqd. Invoking tick_nohz_irq_exit() in this case can cause an endless loop of timer interrupts because the timer wheel contains an expired timer, but softirqs are not yet executed. So it returns an immediate expiry request, which causes the timer to fire immediately again. Lather, rinse and repeat.... Prevent that by adding a check for a pending timer soft interrupt to the conditions in tick_nohz_stop_sched_tick() which avoid calling get_next_timer_interrupt(). That keeps the tick sched timer on the tick and prevents a repetitive programming of an already expired timer. Reported-by: Sebastian Siewior <bigeasy@linutronix.d> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Cc: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712272156050.2431@nanos
2017-12-22 17:51:13 +03:00
}
static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
{
u64 basemono, next_tick, next_tmr, next_rcu, delta, expires;
unsigned long basejiff;
unsigned int seq;
/* Read jiffies and the time when jiffies were updated last */
do {
seq = read_seqcount_begin(&jiffies_seq);
basemono = last_jiffies_update;
basejiff = jiffies;
} while (read_seqcount_retry(&jiffies_seq, seq));
ts->last_jiffies = basejiff;
ts->timer_expires_base = basemono;
nohz: Prevent a timer interrupt storm in tick_nohz_stop_sched_tick() The conditions in irq_exit() to invoke tick_nohz_irq_exit() which subsequently invokes tick_nohz_stop_sched_tick() are: if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) If need_resched() is not set, but a timer softirq is pending then this is an indication that the softirq code punted and delegated the execution to softirqd. need_resched() is not true because the current interrupted task takes precedence over softirqd. Invoking tick_nohz_irq_exit() in this case can cause an endless loop of timer interrupts because the timer wheel contains an expired timer, but softirqs are not yet executed. So it returns an immediate expiry request, which causes the timer to fire immediately again. Lather, rinse and repeat.... Prevent that by adding a check for a pending timer soft interrupt to the conditions in tick_nohz_stop_sched_tick() which avoid calling get_next_timer_interrupt(). That keeps the tick sched timer on the tick and prevents a repetitive programming of an already expired timer. Reported-by: Sebastian Siewior <bigeasy@linutronix.d> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Cc: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712272156050.2431@nanos
2017-12-22 17:51:13 +03:00
/*
* Keep the periodic tick, when RCU, architecture or irq_work
* requests it.
* Aside of that check whether the local timer softirq is
* pending. If so its a bad idea to call get_next_timer_interrupt()
* because there is an already expired timer, so it will request
* immediate expiry, which rearms the hardware timer with a
nohz: Prevent a timer interrupt storm in tick_nohz_stop_sched_tick() The conditions in irq_exit() to invoke tick_nohz_irq_exit() which subsequently invokes tick_nohz_stop_sched_tick() are: if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) If need_resched() is not set, but a timer softirq is pending then this is an indication that the softirq code punted and delegated the execution to softirqd. need_resched() is not true because the current interrupted task takes precedence over softirqd. Invoking tick_nohz_irq_exit() in this case can cause an endless loop of timer interrupts because the timer wheel contains an expired timer, but softirqs are not yet executed. So it returns an immediate expiry request, which causes the timer to fire immediately again. Lather, rinse and repeat.... Prevent that by adding a check for a pending timer soft interrupt to the conditions in tick_nohz_stop_sched_tick() which avoid calling get_next_timer_interrupt(). That keeps the tick sched timer on the tick and prevents a repetitive programming of an already expired timer. Reported-by: Sebastian Siewior <bigeasy@linutronix.d> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Cc: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712272156050.2431@nanos
2017-12-22 17:51:13 +03:00
* minimal delta which brings us back to this place
* immediately. Lather, rinse and repeat...
*/
if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() ||
irq_work_needs_cpu() || local_timer_softirq_pending()) {
next_tick = basemono + TICK_NSEC;
} else {
/*
* Get the next pending timer. If high resolution
* timers are enabled this only takes the timer wheel
* timers into account. If high resolution timers are
* disabled this also looks at the next expiring
* hrtimer.
*/
next_tmr = get_next_timer_interrupt(basejiff, basemono);
ts->next_timer = next_tmr;
/* Take the next rcu event into account */
next_tick = next_rcu < next_tmr ? next_rcu : next_tmr;
}
/*
* If the tick is due in the next period, keep it ticking or
* force prod the timer.
*/
delta = next_tick - basemono;
if (delta <= (u64)TICK_NSEC) {
/*
* Tell the timer code that the base is not idle, i.e. undo
* the effect of get_next_timer_interrupt():
*/
timer_clear_idle();
/*
* We've not stopped the tick yet, and there's a timer in the
* next period, so no point in stopping it either, bail.
*/
nohz: Fix buggy tick delay on IRQ storms When the tick is stopped and we reach the dynticks evaluation code on IRQ exit, we perform a soft tick restart if we observe an expired timer from there. It means we program the nearest possible tick but we stay in dynticks mode (ts->tick_stopped = 1) because we may need to stop the tick again after that expired timer is handled. Now this solution works most of the time but if we suffer an IRQ storm and those interrupts trigger faster than the hardware clockevents min delay, our tick won't fire until that IRQ storm is finished. Here is the problem: on IRQ exit we reprog the timer to at least NOW() + min_clockevents_delay. Another IRQ fires before the tick so we reschedule again to NOW() + min_clockevents_delay, etc... The tick is eternally rescheduled min_clockevents_delay ahead. A solution is to simply remove this soft tick restart. After all the normal dynticks evaluation path can handle 0 delay just fine. And by doing that we benefit from the optimization branch which avoids clock reprogramming if the clockevents deadline hasn't changed since the last reprog. This fixes our issue because we don't do repetitive clock reprog that always add hardware min delay. As a side effect it should even optimize the 0 delay path in general. Reported-and-tested-by: Octavian Purdila <octavian.purdila@nxp.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1496328429-13317-1-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-01 17:47:09 +03:00
if (!ts->tick_stopped) {
ts->timer_expires = 0;
goto out;
}
}
/*
* If this CPU is the one which had the do_timer() duty last, we limit
* the sleep time to the timekeeping max_deferment value.
* Otherwise we can sleep as long as we want.
*/
delta = timekeeping_max_deferment();
if (cpu != tick_do_timer_cpu &&
(tick_do_timer_cpu != TICK_DO_TIMER_NONE || !ts->do_timer_last))
delta = KTIME_MAX;
/* Calculate the next expiry time */
if (delta < (KTIME_MAX - basemono))
expires = basemono + delta;
else
expires = KTIME_MAX;
ts->timer_expires = min_t(u64, expires, next_tick);
out:
return ts->timer_expires;
}
static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
{
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
u64 basemono = ts->timer_expires_base;
u64 expires = ts->timer_expires;
ktime_t tick = expires;
/* Make sure we won't be trying to stop it twice in a row. */
ts->timer_expires_base = 0;
/*
* If this CPU is the one which updates jiffies, then give up
* the assignment and let it be taken by the CPU which runs
* the tick timer next, which might be this CPU as well. If we
* don't drop this here the jiffies might be stale and
* do_timer() never invoked. Keep track of the fact that it
* was the one which had the do_timer() duty last.
*/
if (cpu == tick_do_timer_cpu) {
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
ts->do_timer_last = 1;
} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
ts->do_timer_last = 0;
}
/* Skip reprogram of event if its not changed */
nohz: Fix collision between tick and other hrtimers, again This restores commit: 24b91e360ef5: ("nohz: Fix collision between tick and other hrtimers") ... which got reverted by commit: 558e8e27e73f: ('Revert "nohz: Fix collision between tick and other hrtimers"') ... due to a regression where CPUs spuriously stopped ticking. The bug happened when a tick fired too early past its expected expiration: on IRQ exit the tick was scheduled again to the same deadline but skipped reprogramming because ts->next_tick still kept in cache the deadline. This has been fixed now with resetting ts->next_tick from the tick itself. Extra care has also been taken to prevent from obsolete values throughout CPU hotplug operations. When the tick is stopped and an interrupt occurs afterward, we check on that interrupt exit if the next tick needs to be rescheduled. If it doesn't need any update, we don't want to do anything. In order to check if the tick needs an update, we compare it against the clockevent device deadline. Now that's a problem because the clockevent device is at a lower level than the tick itself if it is implemented on top of hrtimer. Every hrtimer share this clockevent device. So comparing the next tick deadline against the clockevent device deadline is wrong because the device may be programmed for another hrtimer whose deadline collides with the tick. As a result we may end up not reprogramming the tick accidentally. In a worst case scenario under full dynticks mode, the tick stops firing as it is supposed to every 1hz, leaving /proc/stat stalled: Task in a full dynticks CPU ---------------------------- * hrtimer A is queued 2 seconds ahead * the tick is stopped, scheduled 1 second ahead * tick fires 1 second later * on tick exit, nohz schedules the tick 1 second ahead but sees the clockevent device is already programmed to that deadline, fooled by hrtimer A, the tick isn't rescheduled. * hrtimer A is cancelled before its deadline * tick never fires again until an interrupt happens... In order to fix this, store the next tick deadline to the tick_sched local structure and reuse that value later to check whether we need to reprogram the clock after an interrupt. On the other hand, ts->sleep_length still wants to know about the next clock event and not just the tick, so we want to improve the related comment to avoid confusion. Reported-and-tested-by: Tim Wright <tim@binbash.co.uk> Reported-and-tested-by: Pavel Machek <pavel@ucw.cz> Reported-by: James Hartsock <hartsjc@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1492783255-5051-2-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-04-21 17:00:54 +03:00
if (ts->tick_stopped && (expires == ts->next_tick)) {
/* Sanity check: make sure clockevent is actually programmed */
nohz: Fix spurious warning when hrtimer and clockevent get out of sync The sanity check ensuring that the tick expiry cache (ts->next_tick) is actually in sync with the hardware clock (dev->next_event) makes the wrong assumption that the clock can't be programmed later than the hrtimer deadline. In fact the clock hardware can be programmed later on some conditions such as: * The hrtimer deadline is already in the past. * The hrtimer deadline is earlier than the minimum delay supported by the hardware. Such conditions can be met when we program the tick, for example if the last jiffies update hasn't been seen by the current CPU yet, we may program the hrtimer to a deadline that is earlier than ktime_get() because last_jiffies_update is our timestamp base to compute the next tick. As a result, we can randomly observe such warning: WARNING: CPU: 5 PID: 0 at kernel/time/tick-sched.c:794 tick_nohz_stop_sched_tick kernel/time/tick-sched.c:791 [inline] Call Trace: tick_nohz_irq_exit tick_irq_exit irq_exit exiting_irq smp_call_function_interrupt smp_call_function_single_interrupt call_function_single_interrupt Therefore, let's rather make sure that the tick expiry cache is sync'ed with the tick hrtimer deadline, against which it is not supposed to drift away. The clock hardware instead has its own will and can't be used as a reliable comparison point. Reported-and-tested-by: Sasha Levin <alexander.levin@verizon.com> Reported-and-tested-by: Abdul Haleem <abdhalee@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: James Hartsock <hartsjc@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tim Wright <tim@binbash.co.uk> Link: http://lkml.kernel.org/r/1497326654-14122-1-git-send-email-fweisbec@gmail.com [ Minor readability edit. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-13 07:04:14 +03:00
if (tick == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer))
return;
nohz: Fix collision between tick and other hrtimers, again This restores commit: 24b91e360ef5: ("nohz: Fix collision between tick and other hrtimers") ... which got reverted by commit: 558e8e27e73f: ('Revert "nohz: Fix collision between tick and other hrtimers"') ... due to a regression where CPUs spuriously stopped ticking. The bug happened when a tick fired too early past its expected expiration: on IRQ exit the tick was scheduled again to the same deadline but skipped reprogramming because ts->next_tick still kept in cache the deadline. This has been fixed now with resetting ts->next_tick from the tick itself. Extra care has also been taken to prevent from obsolete values throughout CPU hotplug operations. When the tick is stopped and an interrupt occurs afterward, we check on that interrupt exit if the next tick needs to be rescheduled. If it doesn't need any update, we don't want to do anything. In order to check if the tick needs an update, we compare it against the clockevent device deadline. Now that's a problem because the clockevent device is at a lower level than the tick itself if it is implemented on top of hrtimer. Every hrtimer share this clockevent device. So comparing the next tick deadline against the clockevent device deadline is wrong because the device may be programmed for another hrtimer whose deadline collides with the tick. As a result we may end up not reprogramming the tick accidentally. In a worst case scenario under full dynticks mode, the tick stops firing as it is supposed to every 1hz, leaving /proc/stat stalled: Task in a full dynticks CPU ---------------------------- * hrtimer A is queued 2 seconds ahead * the tick is stopped, scheduled 1 second ahead * tick fires 1 second later * on tick exit, nohz schedules the tick 1 second ahead but sees the clockevent device is already programmed to that deadline, fooled by hrtimer A, the tick isn't rescheduled. * hrtimer A is cancelled before its deadline * tick never fires again until an interrupt happens... In order to fix this, store the next tick deadline to the tick_sched local structure and reuse that value later to check whether we need to reprogram the clock after an interrupt. On the other hand, ts->sleep_length still wants to know about the next clock event and not just the tick, so we want to improve the related comment to avoid confusion. Reported-and-tested-by: Tim Wright <tim@binbash.co.uk> Reported-and-tested-by: Pavel Machek <pavel@ucw.cz> Reported-by: James Hartsock <hartsjc@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1492783255-5051-2-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-04-21 17:00:54 +03:00
WARN_ON_ONCE(1);
printk_once("basemono: %llu ts->next_tick: %llu dev->next_event: %llu timer->active: %d timer->expires: %llu\n",
basemono, ts->next_tick, dev->next_event,
hrtimer_active(&ts->sched_timer), hrtimer_get_expires(&ts->sched_timer));
}
/*
* nohz_stop_sched_tick can be called several times before
* the nohz_restart_sched_tick is called. This happens when
* interrupts arrive which do not cause a reschedule. In the
* first call we save the current tick time, so we can restart
* the scheduler tick in nohz_restart_sched_tick.
*/
if (!ts->tick_stopped) {
calc_load_nohz_start();
quiet_vmstat();
ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
trace_tick_stop(1, TICK_DEP_MASK_NONE);
}
nohz: Fix collision between tick and other hrtimers, again This restores commit: 24b91e360ef5: ("nohz: Fix collision between tick and other hrtimers") ... which got reverted by commit: 558e8e27e73f: ('Revert "nohz: Fix collision between tick and other hrtimers"') ... due to a regression where CPUs spuriously stopped ticking. The bug happened when a tick fired too early past its expected expiration: on IRQ exit the tick was scheduled again to the same deadline but skipped reprogramming because ts->next_tick still kept in cache the deadline. This has been fixed now with resetting ts->next_tick from the tick itself. Extra care has also been taken to prevent from obsolete values throughout CPU hotplug operations. When the tick is stopped and an interrupt occurs afterward, we check on that interrupt exit if the next tick needs to be rescheduled. If it doesn't need any update, we don't want to do anything. In order to check if the tick needs an update, we compare it against the clockevent device deadline. Now that's a problem because the clockevent device is at a lower level than the tick itself if it is implemented on top of hrtimer. Every hrtimer share this clockevent device. So comparing the next tick deadline against the clockevent device deadline is wrong because the device may be programmed for another hrtimer whose deadline collides with the tick. As a result we may end up not reprogramming the tick accidentally. In a worst case scenario under full dynticks mode, the tick stops firing as it is supposed to every 1hz, leaving /proc/stat stalled: Task in a full dynticks CPU ---------------------------- * hrtimer A is queued 2 seconds ahead * the tick is stopped, scheduled 1 second ahead * tick fires 1 second later * on tick exit, nohz schedules the tick 1 second ahead but sees the clockevent device is already programmed to that deadline, fooled by hrtimer A, the tick isn't rescheduled. * hrtimer A is cancelled before its deadline * tick never fires again until an interrupt happens... In order to fix this, store the next tick deadline to the tick_sched local structure and reuse that value later to check whether we need to reprogram the clock after an interrupt. On the other hand, ts->sleep_length still wants to know about the next clock event and not just the tick, so we want to improve the related comment to avoid confusion. Reported-and-tested-by: Tim Wright <tim@binbash.co.uk> Reported-and-tested-by: Pavel Machek <pavel@ucw.cz> Reported-by: James Hartsock <hartsjc@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1492783255-5051-2-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-04-21 17:00:54 +03:00
ts->next_tick = tick;
/*
* If the expiration time == KTIME_MAX, then we simply stop
* the tick timer.
*/
if (unlikely(expires == KTIME_MAX)) {
if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
hrtimer_cancel(&ts->sched_timer);
else
tick_program_event(KTIME_MAX, 1);
return;
}
tick/sched: Do not mess with an enqueued hrtimer Kaike reported that in tests rdma hrtimers occasionaly stopped working. He did great debugging, which provided enough context to decode the problem. CPU 3 CPU 2 idle start sched_timer expires = 712171000000 queue->next = sched_timer start rdmavt timer. expires = 712172915662 lock(baseof(CPU3)) tick_nohz_stop_tick() tick = 716767000000 timerqueue_add(tmr) hrtimer_set_expires(sched_timer, tick); sched_timer->expires = 716767000000 <---- FAIL if (tmr->expires < queue->next->expires) hrtimer_start(sched_timer) queue->next = tmr; lock(baseof(CPU3)) unlock(baseof(CPU3)) timerqueue_remove() timerqueue_add() ts->sched_timer is queued and queue->next is pointing to it, but then ts->sched_timer.expires is modified. This not only corrupts the ordering of the timerqueue RB tree, it also makes CPU2 see the new expiry time of timerqueue->next->expires when checking whether timerqueue->next needs to be updated. So CPU2 sees that the rdma timer is earlier than timerqueue->next and sets the rdma timer as new next. Depending on whether it had also seen the new time at RB tree enqueue, it might have queued the rdma timer at the wrong place and then after removing the sched_timer the RB tree is completely hosed. The problem was introduced with a commit which tried to solve inconsistency between the hrtimer in the tick_sched data and the underlying hardware clockevent. It split out hrtimer_set_expires() to store the new tick time in both the NOHZ and the NOHZ + HIGHRES case, but missed the fact that in the NOHZ + HIGHRES case the hrtimer might still be queued. Use hrtimer_start(timer, tick...) for the NOHZ + HIGHRES case which sets timer->expires after canceling the timer and move the hrtimer_set_expires() invocation into the NOHZ only code path which is not affected as it merily uses the hrtimer as next event storage so code pathes can be shared with the NOHZ + HIGHRES case. Fixes: d4af6d933ccf ("nohz: Fix spurious warning when hrtimer and clockevent get out of sync") Reported-by: "Wan Kaike" <kaike.wan@intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Frederic Weisbecker <frederic@kernel.org> Cc: "Marciniszyn Mike" <mike.marciniszyn@intel.com> Cc: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: linux-rdma@vger.kernel.org Cc: "Dalessandro Dennis" <dennis.dalessandro@intel.com> Cc: "Fleck John" <john.fleck@intel.com> Cc: stable@vger.kernel.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: "Weiny Ira" <ira.weiny@intel.com> Cc: "linux-rdma@vger.kernel.org" Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1804241637390.1679@nanos.tec.linutronix.de Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1804242119210.1597@nanos.tec.linutronix.de
2018-04-24 22:22:18 +03:00
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
hrtimer_start(&ts->sched_timer, tick,
HRTIMER_MODE_ABS_PINNED_HARD);
tick/sched: Do not mess with an enqueued hrtimer Kaike reported that in tests rdma hrtimers occasionaly stopped working. He did great debugging, which provided enough context to decode the problem. CPU 3 CPU 2 idle start sched_timer expires = 712171000000 queue->next = sched_timer start rdmavt timer. expires = 712172915662 lock(baseof(CPU3)) tick_nohz_stop_tick() tick = 716767000000 timerqueue_add(tmr) hrtimer_set_expires(sched_timer, tick); sched_timer->expires = 716767000000 <---- FAIL if (tmr->expires < queue->next->expires) hrtimer_start(sched_timer) queue->next = tmr; lock(baseof(CPU3)) unlock(baseof(CPU3)) timerqueue_remove() timerqueue_add() ts->sched_timer is queued and queue->next is pointing to it, but then ts->sched_timer.expires is modified. This not only corrupts the ordering of the timerqueue RB tree, it also makes CPU2 see the new expiry time of timerqueue->next->expires when checking whether timerqueue->next needs to be updated. So CPU2 sees that the rdma timer is earlier than timerqueue->next and sets the rdma timer as new next. Depending on whether it had also seen the new time at RB tree enqueue, it might have queued the rdma timer at the wrong place and then after removing the sched_timer the RB tree is completely hosed. The problem was introduced with a commit which tried to solve inconsistency between the hrtimer in the tick_sched data and the underlying hardware clockevent. It split out hrtimer_set_expires() to store the new tick time in both the NOHZ and the NOHZ + HIGHRES case, but missed the fact that in the NOHZ + HIGHRES case the hrtimer might still be queued. Use hrtimer_start(timer, tick...) for the NOHZ + HIGHRES case which sets timer->expires after canceling the timer and move the hrtimer_set_expires() invocation into the NOHZ only code path which is not affected as it merily uses the hrtimer as next event storage so code pathes can be shared with the NOHZ + HIGHRES case. Fixes: d4af6d933ccf ("nohz: Fix spurious warning when hrtimer and clockevent get out of sync") Reported-by: "Wan Kaike" <kaike.wan@intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Frederic Weisbecker <frederic@kernel.org> Cc: "Marciniszyn Mike" <mike.marciniszyn@intel.com> Cc: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: linux-rdma@vger.kernel.org Cc: "Dalessandro Dennis" <dennis.dalessandro@intel.com> Cc: "Fleck John" <john.fleck@intel.com> Cc: stable@vger.kernel.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: "Weiny Ira" <ira.weiny@intel.com> Cc: "linux-rdma@vger.kernel.org" Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1804241637390.1679@nanos.tec.linutronix.de Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1804242119210.1597@nanos.tec.linutronix.de
2018-04-24 22:22:18 +03:00
} else {
hrtimer_set_expires(&ts->sched_timer, tick);
tick_program_event(tick, 1);
tick/sched: Do not mess with an enqueued hrtimer Kaike reported that in tests rdma hrtimers occasionaly stopped working. He did great debugging, which provided enough context to decode the problem. CPU 3 CPU 2 idle start sched_timer expires = 712171000000 queue->next = sched_timer start rdmavt timer. expires = 712172915662 lock(baseof(CPU3)) tick_nohz_stop_tick() tick = 716767000000 timerqueue_add(tmr) hrtimer_set_expires(sched_timer, tick); sched_timer->expires = 716767000000 <---- FAIL if (tmr->expires < queue->next->expires) hrtimer_start(sched_timer) queue->next = tmr; lock(baseof(CPU3)) unlock(baseof(CPU3)) timerqueue_remove() timerqueue_add() ts->sched_timer is queued and queue->next is pointing to it, but then ts->sched_timer.expires is modified. This not only corrupts the ordering of the timerqueue RB tree, it also makes CPU2 see the new expiry time of timerqueue->next->expires when checking whether timerqueue->next needs to be updated. So CPU2 sees that the rdma timer is earlier than timerqueue->next and sets the rdma timer as new next. Depending on whether it had also seen the new time at RB tree enqueue, it might have queued the rdma timer at the wrong place and then after removing the sched_timer the RB tree is completely hosed. The problem was introduced with a commit which tried to solve inconsistency between the hrtimer in the tick_sched data and the underlying hardware clockevent. It split out hrtimer_set_expires() to store the new tick time in both the NOHZ and the NOHZ + HIGHRES case, but missed the fact that in the NOHZ + HIGHRES case the hrtimer might still be queued. Use hrtimer_start(timer, tick...) for the NOHZ + HIGHRES case which sets timer->expires after canceling the timer and move the hrtimer_set_expires() invocation into the NOHZ only code path which is not affected as it merily uses the hrtimer as next event storage so code pathes can be shared with the NOHZ + HIGHRES case. Fixes: d4af6d933ccf ("nohz: Fix spurious warning when hrtimer and clockevent get out of sync") Reported-by: "Wan Kaike" <kaike.wan@intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Frederic Weisbecker <frederic@kernel.org> Cc: "Marciniszyn Mike" <mike.marciniszyn@intel.com> Cc: Anna-Maria Gleixner <anna-maria@linutronix.de> Cc: linux-rdma@vger.kernel.org Cc: "Dalessandro Dennis" <dennis.dalessandro@intel.com> Cc: "Fleck John" <john.fleck@intel.com> Cc: stable@vger.kernel.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: "Weiny Ira" <ira.weiny@intel.com> Cc: "linux-rdma@vger.kernel.org" Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1804241637390.1679@nanos.tec.linutronix.de Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1804242119210.1597@nanos.tec.linutronix.de
2018-04-24 22:22:18 +03:00
}
nohz: Separate out irq exit and idle loop dyntick logic The tick_nohz_stop_sched_tick() function, which tries to delay the next timer tick as long as possible, can be called from two places: - From the idle loop to start the dytick idle mode - From interrupt exit if we have interrupted the dyntick idle mode, so that we reprogram the next tick event in case the irq changed some internal state that requires this action. There are only few minor differences between both that are handled by that function, driven by the ts->inidle cpu variable and the inidle parameter. The whole guarantees that we only update the dyntick mode on irq exit if we actually interrupted the dyntick idle mode, and that we enter in RCU extended quiescent state from idle loop entry only. Split this function into: - tick_nohz_idle_enter(), which sets ts->inidle to 1, enters dynticks idle mode unconditionally if it can, and enters into RCU extended quiescent state. - tick_nohz_irq_exit() which only updates the dynticks idle mode when ts->inidle is set (ie: if tick_nohz_idle_enter() has been called). To maintain symmetry, tick_nohz_restart_sched_tick() has been renamed into tick_nohz_idle_exit(). This simplifies the code and micro-optimize the irq exit path (no need for local_irq_save there). This also prepares for the split between dynticks and rcu extended quiescent state logics. We'll need this split to further fix illegal uses of RCU in extended quiescent states in the idle loop. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: David Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-10-07 20:22:06 +04:00
}
static void tick_nohz_retain_tick(struct tick_sched *ts)
{
ts->timer_expires_base = 0;
}
#ifdef CONFIG_NO_HZ_FULL
static void tick_nohz_stop_sched_tick(struct tick_sched *ts, int cpu)
{
if (tick_nohz_next_event(ts, cpu))
tick_nohz_stop_tick(ts, cpu);
else
tick_nohz_retain_tick(ts);
}
#endif /* CONFIG_NO_HZ_FULL */
sched/fair: Correctly handle nohz ticks CPU load accounting Ticks can happen while the CPU is in dynticks-idle or dynticks-singletask mode. In fact "nohz" or "dynticks" only mean that we exit the periodic mode and we try to minimize the ticks as much as possible. The nohz subsystem uses a confusing terminology with the internal state "ts->tick_stopped" which is also available through its public interface with tick_nohz_tick_stopped(). This is a misnomer as the tick is instead reduced with the best effort rather than stopped. In the best case the tick can indeed be actually stopped but there is no guarantee about that. If a timer needs to fire one second later, a tick will fire while the CPU is in nohz mode and this is a very common scenario. Now this confusion happens to be a problem with CPU load updates: cpu_load_update_active() doesn't handle nohz ticks correctly because it assumes that ticks are completely stopped in nohz mode and that cpu_load_update_active() can't be called in dynticks mode. When that happens, the whole previous tickless load is ignored and the function just records the load for the current tick, ignoring potentially long idle periods behind. In order to solve this, we could account the current load for the previous nohz time but there is a risk that we account the load of a task that got freshly enqueued for the whole nohz period. So instead, lets record the dynticks load on nohz frame entry so we know what to record in case of nohz ticks, then use this record to account the tickless load on nohz ticks and nohz frame end. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Byungchul Park <byungchul.park@lge.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul E . McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1460555812-25375-3-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-04-13 16:56:51 +03:00
static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
{
/* Update jiffies first */
tick_do_update_jiffies64(now);
/*
* Clear the timer idle flag, so we avoid IPIs on remote queueing and
* the clock forward checks in the enqueue path:
*/
timer_clear_idle();
calc_load_nohz_stop();
touch_softlockup_watchdog_sched();
/*
* Cancel the scheduled timer and restore the tick
*/
ts->tick_stopped = 0;
tick_nohz_restart(ts, now);
}
static void __tick_nohz_full_update_tick(struct tick_sched *ts,
ktime_t now)
{
#ifdef CONFIG_NO_HZ_FULL
int cpu = smp_processor_id();
if (can_stop_full_tick(cpu, ts))
tick_nohz_stop_sched_tick(ts, cpu);
else if (ts->tick_stopped)
tick_nohz_restart_sched_tick(ts, now);
#endif
}
static void tick_nohz_full_update_tick(struct tick_sched *ts)
{
if (!tick_nohz_full_cpu(smp_processor_id()))
return;
if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE)
return;
__tick_nohz_full_update_tick(ts, ktime_get());
}
static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
{
/*
* If this CPU is offline and it is the one which updates
* jiffies, then give up the assignment and let it be taken by
* the CPU which runs the tick timer next. If we don't drop
* this here the jiffies might be stale and do_timer() never
* invoked.
*/
if (unlikely(!cpu_online(cpu))) {
if (cpu == tick_do_timer_cpu)
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
nohz: Fix collision between tick and other hrtimers, again This restores commit: 24b91e360ef5: ("nohz: Fix collision between tick and other hrtimers") ... which got reverted by commit: 558e8e27e73f: ('Revert "nohz: Fix collision between tick and other hrtimers"') ... due to a regression where CPUs spuriously stopped ticking. The bug happened when a tick fired too early past its expected expiration: on IRQ exit the tick was scheduled again to the same deadline but skipped reprogramming because ts->next_tick still kept in cache the deadline. This has been fixed now with resetting ts->next_tick from the tick itself. Extra care has also been taken to prevent from obsolete values throughout CPU hotplug operations. When the tick is stopped and an interrupt occurs afterward, we check on that interrupt exit if the next tick needs to be rescheduled. If it doesn't need any update, we don't want to do anything. In order to check if the tick needs an update, we compare it against the clockevent device deadline. Now that's a problem because the clockevent device is at a lower level than the tick itself if it is implemented on top of hrtimer. Every hrtimer share this clockevent device. So comparing the next tick deadline against the clockevent device deadline is wrong because the device may be programmed for another hrtimer whose deadline collides with the tick. As a result we may end up not reprogramming the tick accidentally. In a worst case scenario under full dynticks mode, the tick stops firing as it is supposed to every 1hz, leaving /proc/stat stalled: Task in a full dynticks CPU ---------------------------- * hrtimer A is queued 2 seconds ahead * the tick is stopped, scheduled 1 second ahead * tick fires 1 second later * on tick exit, nohz schedules the tick 1 second ahead but sees the clockevent device is already programmed to that deadline, fooled by hrtimer A, the tick isn't rescheduled. * hrtimer A is cancelled before its deadline * tick never fires again until an interrupt happens... In order to fix this, store the next tick deadline to the tick_sched local structure and reuse that value later to check whether we need to reprogram the clock after an interrupt. On the other hand, ts->sleep_length still wants to know about the next clock event and not just the tick, so we want to improve the related comment to avoid confusion. Reported-and-tested-by: Tim Wright <tim@binbash.co.uk> Reported-and-tested-by: Pavel Machek <pavel@ucw.cz> Reported-by: James Hartsock <hartsjc@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1492783255-5051-2-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-04-21 17:00:54 +03:00
/*
* Make sure the CPU doesn't get fooled by obsolete tick
* deadline if it comes back online later.
*/
ts->next_tick = 0;
return false;
}
if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
return false;
if (need_resched())
return false;
if (unlikely(local_softirq_pending())) {
static int ratelimit;
if (ratelimit < 10 && !local_bh_blocked() &&
(local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
pr_warn("NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #%02x!!!\n",
(unsigned int) local_softirq_pending());
ratelimit++;
}
return false;
}
if (tick_nohz_full_enabled()) {
/*
* Keep the tick alive to guarantee timekeeping progression
* if there are full dynticks CPUs around
*/
if (tick_do_timer_cpu == cpu)
return false;
/* Should not happen for nohz-full */
if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
return false;
}
return true;
}
static void __tick_nohz_idle_stop_tick(struct tick_sched *ts)
{
ktime_t expires;
int cpu = smp_processor_id();
sched: idle: Select idle state before stopping the tick In order to address the issue with short idle duration predictions by the idle governor after the scheduler tick has been stopped, reorder the code in cpuidle_idle_call() so that the governor idle state selection runs before tick_nohz_idle_go_idle() and use the "nohz" hint returned by cpuidle_select() to decide whether or not to stop the tick. This isn't straightforward, because menu_select() invokes tick_nohz_get_sleep_length() to get the time to the next timer event and the number returned by the latter comes from __tick_nohz_idle_stop_tick(). Fortunately, however, it is possible to compute that number without actually stopping the tick and with the help of the existing code. Namely, tick_nohz_get_sleep_length() can be made call tick_nohz_next_event(), introduced earlier, to get the time to the next non-highres timer event. If that happens, tick_nohz_next_event() need not be called by __tick_nohz_idle_stop_tick() again. If it turns out that the scheduler tick cannot be stopped going forward or the next timer event is too close for the tick to be stopped, tick_nohz_get_sleep_length() can simply return the time to the next event currently programmed into the corresponding clock event device. In addition to knowing the return value of tick_nohz_next_event(), however, tick_nohz_get_sleep_length() needs to know the time to the next highres timer event, but with the scheduler tick timer excluded, which can be computed with the help of hrtimer_get_next_event(). That minimum of that number and the tick_nohz_next_event() return value is the total time to the next timer event with the assumption that the tick will be stopped. It can be returned to the idle governor which can use it for predicting idle duration (under the assumption that the tick will be stopped) and deciding whether or not it makes sense to stop the tick before putting the CPU into the selected idle state. With the above, the sleep_length field in struct tick_sched is not necessary any more, so drop it. Link: https://bugzilla.kernel.org/show_bug.cgi?id=199227 Reported-by: Doug Smythies <dsmythies@telus.net> Reported-by: Thomas Ilsche <thomas.ilsche@tu-dresden.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
2018-04-04 00:17:11 +03:00
/*
* If tick_nohz_get_sleep_length() ran tick_nohz_next_event(), the
* tick timer expiration time is known already.
*/
if (ts->timer_expires_base)
expires = ts->timer_expires;
else if (can_stop_idle_tick(cpu, ts))
expires = tick_nohz_next_event(ts, cpu);
else
return;
ts->idle_calls++;
tick/nohz: Fix softlockup on scheduler stalls in kvm guest tick_nohz_start_idle() is prevented to be called if the idle tick can't be stopped since commit 1f3b0f8243cb934 ("tick/nohz: Optimize nohz idle enter"). As a result, after suspend/resume the host machine, full dynticks kvm guest will softlockup: NMI watchdog: BUG: soft lockup - CPU#0 stuck for 26s! [swapper/0:0] Call Trace: default_idle+0x31/0x1a0 arch_cpu_idle+0xf/0x20 default_idle_call+0x2a/0x50 cpu_startup_entry+0x39b/0x4d0 rest_init+0x138/0x140 ? rest_init+0x5/0x140 start_kernel+0x4c1/0x4ce ? set_init_arg+0x55/0x55 ? early_idt_handler_array+0x120/0x120 x86_64_start_reservations+0x24/0x26 x86_64_start_kernel+0x142/0x14f In addition, cat /proc/stat | grep cpu in guest or host: cpu 398 16 5049 15754 5490 0 1 46 0 0 cpu0 206 5 450 0 0 0 1 14 0 0 cpu1 81 0 3937 3149 1514 0 0 9 0 0 cpu2 45 6 332 6052 2243 0 0 11 0 0 cpu3 65 2 328 6552 1732 0 0 11 0 0 The idle and iowait states are weird 0 for cpu0(housekeeping). The bug is present in both guest and host kernels, and they both have cpu0's idle and iowait states issue, however, host kernel's suspend/resume path etc will touch watchdog to avoid the softlockup. - The watchdog will not be touched in tick_nohz_stop_idle path (need be touched since the scheduler stall is expected) if idle_active flags are not detected. - The idle and iowait states will not be accounted when exit idle loop (resched or interrupt) if idle start time and idle_active flags are not set. This patch fixes it by reverting commit 1f3b0f8243cb934 since can't stop idle tick doesn't mean can't be idle. Fixes: 1f3b0f8243cb934 ("tick/nohz: Optimize nohz idle enter") Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com> Cc: Sanjeev Yadav<sanjeev.yadav@spreadtrum.com> Cc: Gaurav Jindal<gaurav.jindal@spreadtrum.com> Cc: stable@vger.kernel.org Cc: kvm@vger.kernel.org Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Link: http://lkml.kernel.org/r/1472798303-4154-1-git-send-email-wanpeng.li@hotmail.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-09-02 09:38:23 +03:00
if (expires > 0LL) {
int was_stopped = ts->tick_stopped;
tick_nohz_stop_tick(ts, cpu);
ts->idle_sleeps++;
ts->idle_expires = expires;
if (!was_stopped && ts->tick_stopped) {
ts->idle_jiffies = ts->last_jiffies;
nohz_balance_enter_idle(cpu);
}
} else {
tick_nohz_retain_tick(ts);
}
nohz: Separate out irq exit and idle loop dyntick logic The tick_nohz_stop_sched_tick() function, which tries to delay the next timer tick as long as possible, can be called from two places: - From the idle loop to start the dytick idle mode - From interrupt exit if we have interrupted the dyntick idle mode, so that we reprogram the next tick event in case the irq changed some internal state that requires this action. There are only few minor differences between both that are handled by that function, driven by the ts->inidle cpu variable and the inidle parameter. The whole guarantees that we only update the dyntick mode on irq exit if we actually interrupted the dyntick idle mode, and that we enter in RCU extended quiescent state from idle loop entry only. Split this function into: - tick_nohz_idle_enter(), which sets ts->inidle to 1, enters dynticks idle mode unconditionally if it can, and enters into RCU extended quiescent state. - tick_nohz_irq_exit() which only updates the dynticks idle mode when ts->inidle is set (ie: if tick_nohz_idle_enter() has been called). To maintain symmetry, tick_nohz_restart_sched_tick() has been renamed into tick_nohz_idle_exit(). This simplifies the code and micro-optimize the irq exit path (no need for local_irq_save there). This also prepares for the split between dynticks and rcu extended quiescent state logics. We'll need this split to further fix illegal uses of RCU in extended quiescent states in the idle loop. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: David Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-10-07 20:22:06 +04:00
}
/**
* tick_nohz_idle_stop_tick - stop the idle tick from the idle task
nohz: Separate out irq exit and idle loop dyntick logic The tick_nohz_stop_sched_tick() function, which tries to delay the next timer tick as long as possible, can be called from two places: - From the idle loop to start the dytick idle mode - From interrupt exit if we have interrupted the dyntick idle mode, so that we reprogram the next tick event in case the irq changed some internal state that requires this action. There are only few minor differences between both that are handled by that function, driven by the ts->inidle cpu variable and the inidle parameter. The whole guarantees that we only update the dyntick mode on irq exit if we actually interrupted the dyntick idle mode, and that we enter in RCU extended quiescent state from idle loop entry only. Split this function into: - tick_nohz_idle_enter(), which sets ts->inidle to 1, enters dynticks idle mode unconditionally if it can, and enters into RCU extended quiescent state. - tick_nohz_irq_exit() which only updates the dynticks idle mode when ts->inidle is set (ie: if tick_nohz_idle_enter() has been called). To maintain symmetry, tick_nohz_restart_sched_tick() has been renamed into tick_nohz_idle_exit(). This simplifies the code and micro-optimize the irq exit path (no need for local_irq_save there). This also prepares for the split between dynticks and rcu extended quiescent state logics. We'll need this split to further fix illegal uses of RCU in extended quiescent states in the idle loop. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: David Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-10-07 20:22:06 +04:00
*
* When the next event is more than a tick into the future, stop the idle tick
*/
void tick_nohz_idle_stop_tick(void)
{
__tick_nohz_idle_stop_tick(this_cpu_ptr(&tick_cpu_sched));
}
sched: idle: Select idle state before stopping the tick In order to address the issue with short idle duration predictions by the idle governor after the scheduler tick has been stopped, reorder the code in cpuidle_idle_call() so that the governor idle state selection runs before tick_nohz_idle_go_idle() and use the "nohz" hint returned by cpuidle_select() to decide whether or not to stop the tick. This isn't straightforward, because menu_select() invokes tick_nohz_get_sleep_length() to get the time to the next timer event and the number returned by the latter comes from __tick_nohz_idle_stop_tick(). Fortunately, however, it is possible to compute that number without actually stopping the tick and with the help of the existing code. Namely, tick_nohz_get_sleep_length() can be made call tick_nohz_next_event(), introduced earlier, to get the time to the next non-highres timer event. If that happens, tick_nohz_next_event() need not be called by __tick_nohz_idle_stop_tick() again. If it turns out that the scheduler tick cannot be stopped going forward or the next timer event is too close for the tick to be stopped, tick_nohz_get_sleep_length() can simply return the time to the next event currently programmed into the corresponding clock event device. In addition to knowing the return value of tick_nohz_next_event(), however, tick_nohz_get_sleep_length() needs to know the time to the next highres timer event, but with the scheduler tick timer excluded, which can be computed with the help of hrtimer_get_next_event(). That minimum of that number and the tick_nohz_next_event() return value is the total time to the next timer event with the assumption that the tick will be stopped. It can be returned to the idle governor which can use it for predicting idle duration (under the assumption that the tick will be stopped) and deciding whether or not it makes sense to stop the tick before putting the CPU into the selected idle state. With the above, the sleep_length field in struct tick_sched is not necessary any more, so drop it. Link: https://bugzilla.kernel.org/show_bug.cgi?id=199227 Reported-by: Doug Smythies <dsmythies@telus.net> Reported-by: Thomas Ilsche <thomas.ilsche@tu-dresden.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
2018-04-04 00:17:11 +03:00
void tick_nohz_idle_retain_tick(void)
{
tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched));
/*
* Undo the effect of get_next_timer_interrupt() called from
* tick_nohz_next_event().
*/
timer_clear_idle();
}
/**
* tick_nohz_idle_enter - prepare for entering idle on the current CPU
nohz: Allow rcu extended quiescent state handling seperately from tick stop It is assumed that rcu won't be used once we switch to tickless mode and until we restart the tick. However this is not always true, as in x86-64 where we dereference the idle notifiers after the tick is stopped. To prepare for fixing this, add two new APIs: tick_nohz_idle_enter_norcu() and tick_nohz_idle_exit_norcu(). If no use of RCU is made in the idle loop between tick_nohz_enter_idle() and tick_nohz_exit_idle() calls, the arch must instead call the new *_norcu() version such that the arch doesn't need to call rcu_idle_enter() and rcu_idle_exit(). Otherwise the arch must call tick_nohz_enter_idle() and tick_nohz_exit_idle() and also call explicitly: - rcu_idle_enter() after its last use of RCU before the CPU is put to sleep. - rcu_idle_exit() before the first use of RCU after the CPU is woken up. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: David Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
2011-10-08 18:01:00 +04:00
*
* Called when we start the idle loop.
nohz: Separate out irq exit and idle loop dyntick logic The tick_nohz_stop_sched_tick() function, which tries to delay the next timer tick as long as possible, can be called from two places: - From the idle loop to start the dytick idle mode - From interrupt exit if we have interrupted the dyntick idle mode, so that we reprogram the next tick event in case the irq changed some internal state that requires this action. There are only few minor differences between both that are handled by that function, driven by the ts->inidle cpu variable and the inidle parameter. The whole guarantees that we only update the dyntick mode on irq exit if we actually interrupted the dyntick idle mode, and that we enter in RCU extended quiescent state from idle loop entry only. Split this function into: - tick_nohz_idle_enter(), which sets ts->inidle to 1, enters dynticks idle mode unconditionally if it can, and enters into RCU extended quiescent state. - tick_nohz_irq_exit() which only updates the dynticks idle mode when ts->inidle is set (ie: if tick_nohz_idle_enter() has been called). To maintain symmetry, tick_nohz_restart_sched_tick() has been renamed into tick_nohz_idle_exit(). This simplifies the code and micro-optimize the irq exit path (no need for local_irq_save there). This also prepares for the split between dynticks and rcu extended quiescent state logics. We'll need this split to further fix illegal uses of RCU in extended quiescent states in the idle loop. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: David Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-10-07 20:22:06 +04:00
*/
void tick_nohz_idle_enter(void)
nohz: Separate out irq exit and idle loop dyntick logic The tick_nohz_stop_sched_tick() function, which tries to delay the next timer tick as long as possible, can be called from two places: - From the idle loop to start the dytick idle mode - From interrupt exit if we have interrupted the dyntick idle mode, so that we reprogram the next tick event in case the irq changed some internal state that requires this action. There are only few minor differences between both that are handled by that function, driven by the ts->inidle cpu variable and the inidle parameter. The whole guarantees that we only update the dyntick mode on irq exit if we actually interrupted the dyntick idle mode, and that we enter in RCU extended quiescent state from idle loop entry only. Split this function into: - tick_nohz_idle_enter(), which sets ts->inidle to 1, enters dynticks idle mode unconditionally if it can, and enters into RCU extended quiescent state. - tick_nohz_irq_exit() which only updates the dynticks idle mode when ts->inidle is set (ie: if tick_nohz_idle_enter() has been called). To maintain symmetry, tick_nohz_restart_sched_tick() has been renamed into tick_nohz_idle_exit(). This simplifies the code and micro-optimize the irq exit path (no need for local_irq_save there). This also prepares for the split between dynticks and rcu extended quiescent state logics. We'll need this split to further fix illegal uses of RCU in extended quiescent states in the idle loop. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: David Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-10-07 20:22:06 +04:00
{
struct tick_sched *ts;
lockdep_assert_irqs_enabled();
local_irq_disable();
ts = this_cpu_ptr(&tick_cpu_sched);
WARN_ON_ONCE(ts->timer_expires_base);
nohz: Separate out irq exit and idle loop dyntick logic The tick_nohz_stop_sched_tick() function, which tries to delay the next timer tick as long as possible, can be called from two places: - From the idle loop to start the dytick idle mode - From interrupt exit if we have interrupted the dyntick idle mode, so that we reprogram the next tick event in case the irq changed some internal state that requires this action. There are only few minor differences between both that are handled by that function, driven by the ts->inidle cpu variable and the inidle parameter. The whole guarantees that we only update the dyntick mode on irq exit if we actually interrupted the dyntick idle mode, and that we enter in RCU extended quiescent state from idle loop entry only. Split this function into: - tick_nohz_idle_enter(), which sets ts->inidle to 1, enters dynticks idle mode unconditionally if it can, and enters into RCU extended quiescent state. - tick_nohz_irq_exit() which only updates the dynticks idle mode when ts->inidle is set (ie: if tick_nohz_idle_enter() has been called). To maintain symmetry, tick_nohz_restart_sched_tick() has been renamed into tick_nohz_idle_exit(). This simplifies the code and micro-optimize the irq exit path (no need for local_irq_save there). This also prepares for the split between dynticks and rcu extended quiescent state logics. We'll need this split to further fix illegal uses of RCU in extended quiescent states in the idle loop. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: David Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-10-07 20:22:06 +04:00
ts->inidle = 1;
tick_nohz_start_idle(ts);
local_irq_enable();
nohz: Separate out irq exit and idle loop dyntick logic The tick_nohz_stop_sched_tick() function, which tries to delay the next timer tick as long as possible, can be called from two places: - From the idle loop to start the dytick idle mode - From interrupt exit if we have interrupted the dyntick idle mode, so that we reprogram the next tick event in case the irq changed some internal state that requires this action. There are only few minor differences between both that are handled by that function, driven by the ts->inidle cpu variable and the inidle parameter. The whole guarantees that we only update the dyntick mode on irq exit if we actually interrupted the dyntick idle mode, and that we enter in RCU extended quiescent state from idle loop entry only. Split this function into: - tick_nohz_idle_enter(), which sets ts->inidle to 1, enters dynticks idle mode unconditionally if it can, and enters into RCU extended quiescent state. - tick_nohz_irq_exit() which only updates the dynticks idle mode when ts->inidle is set (ie: if tick_nohz_idle_enter() has been called). To maintain symmetry, tick_nohz_restart_sched_tick() has been renamed into tick_nohz_idle_exit(). This simplifies the code and micro-optimize the irq exit path (no need for local_irq_save there). This also prepares for the split between dynticks and rcu extended quiescent state logics. We'll need this split to further fix illegal uses of RCU in extended quiescent states in the idle loop. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: David Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-10-07 20:22:06 +04:00
}
/**
* tick_nohz_irq_exit - update next tick event from interrupt exit
*
* When an interrupt fires while we are idle and it doesn't cause
* a reschedule, it may still add, modify or delete a timer, enqueue
* an RCU callback, etc...
* So we need to re-calculate and reprogram the next tick event.
*/
void tick_nohz_irq_exit(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
nohz: Separate out irq exit and idle loop dyntick logic The tick_nohz_stop_sched_tick() function, which tries to delay the next timer tick as long as possible, can be called from two places: - From the idle loop to start the dytick idle mode - From interrupt exit if we have interrupted the dyntick idle mode, so that we reprogram the next tick event in case the irq changed some internal state that requires this action. There are only few minor differences between both that are handled by that function, driven by the ts->inidle cpu variable and the inidle parameter. The whole guarantees that we only update the dyntick mode on irq exit if we actually interrupted the dyntick idle mode, and that we enter in RCU extended quiescent state from idle loop entry only. Split this function into: - tick_nohz_idle_enter(), which sets ts->inidle to 1, enters dynticks idle mode unconditionally if it can, and enters into RCU extended quiescent state. - tick_nohz_irq_exit() which only updates the dynticks idle mode when ts->inidle is set (ie: if tick_nohz_idle_enter() has been called). To maintain symmetry, tick_nohz_restart_sched_tick() has been renamed into tick_nohz_idle_exit(). This simplifies the code and micro-optimize the irq exit path (no need for local_irq_save there). This also prepares for the split between dynticks and rcu extended quiescent state logics. We'll need this split to further fix illegal uses of RCU in extended quiescent states in the idle loop. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: David Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-10-07 20:22:06 +04:00
Revert "cpuidle: Quickly notice prediction failure for repeat mode" Revert commit 69a37bea (cpuidle: Quickly notice prediction failure for repeat mode), because it has been identified as the source of a significant performance regression in v3.8 and later as explained by Jeremy Eder: We believe we've identified a particular commit to the cpuidle code that seems to be impacting performance of variety of workloads. The simplest way to reproduce is using netperf TCP_RR test, so we're using that, on a pair of Sandy Bridge based servers. We also have data from a large database setup where performance is also measurably/positively impacted, though that test data isn't easily share-able. Included below are test results from 3 test kernels: kernel reverts ----------------------------------------------------------- 1) vanilla upstream (no reverts) 2) perfteam2 reverts e11538d1f03914eb92af5a1a378375c05ae8520c 3) test reverts 69a37beabf1f0a6705c08e879bdd5d82ff6486c4 e11538d1f03914eb92af5a1a378375c05ae8520c In summary, netperf TCP_RR numbers improve by approximately 4% after reverting 69a37beabf1f0a6705c08e879bdd5d82ff6486c4. When 69a37beabf1f0a6705c08e879bdd5d82ff6486c4 is included, C0 residency never seems to get above 40%. Taking that patch out gets C0 near 100% quite often, and performance increases. The below data are histograms representing the %c0 residency @ 1-second sample rates (using turbostat), while under netperf test. - If you look at the first 4 histograms, you can see %c0 residency almost entirely in the 30,40% bin. - The last pair, which reverts 69a37beabf1f0a6705c08e879bdd5d82ff6486c4, shows %c0 in the 80,90,100% bins. Below each kernel name are netperf TCP_RR trans/s numbers for the particular kernel that can be disclosed publicly, comparing the 3 test kernels. We ran a 4th test with the vanilla kernel where we've also set /dev/cpu_dma_latency=0 to show overall impact boosting single-threaded TCP_RR performance over 11% above baseline. 3.10-rc2 vanilla RX + c0 lock (/dev/cpu_dma_latency=0): TCP_RR trans/s 54323.78 ----------------------------------------------------------- 3.10-rc2 vanilla RX (no reverts) TCP_RR trans/s 48192.47 Receiver %c0 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 0]: 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 59]: *********************************************************** 40.0000 - 50.0000 [ 1]: * 50.0000 - 60.0000 [ 0]: 60.0000 - 70.0000 [ 0]: 70.0000 - 80.0000 [ 0]: 80.0000 - 90.0000 [ 0]: 90.0000 - 100.0000 [ 0]: Sender %c0 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 0]: 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 11]: *********** 40.0000 - 50.0000 [ 49]: ************************************************* 50.0000 - 60.0000 [ 0]: 60.0000 - 70.0000 [ 0]: 70.0000 - 80.0000 [ 0]: 80.0000 - 90.0000 [ 0]: 90.0000 - 100.0000 [ 0]: ----------------------------------------------------------- 3.10-rc2 perfteam2 RX (reverts commit e11538d1f03914eb92af5a1a378375c05ae8520c) TCP_RR trans/s 49698.69 Receiver %c0 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 1]: * 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 59]: *********************************************************** 40.0000 - 50.0000 [ 0]: 50.0000 - 60.0000 [ 0]: 60.0000 - 70.0000 [ 0]: 70.0000 - 80.0000 [ 0]: 80.0000 - 90.0000 [ 0]: 90.0000 - 100.0000 [ 0]: Sender %c0 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 0]: 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 2]: ** 40.0000 - 50.0000 [ 58]: ********************************************************** 50.0000 - 60.0000 [ 0]: 60.0000 - 70.0000 [ 0]: 70.0000 - 80.0000 [ 0]: 80.0000 - 90.0000 [ 0]: 90.0000 - 100.0000 [ 0]: ----------------------------------------------------------- 3.10-rc2 test RX (reverts 69a37beabf1f0a6705c08e879bdd5d82ff6486c4 and e11538d1f03914eb92af5a1a378375c05ae8520c) TCP_RR trans/s 47766.95 Receiver %c0 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 1]: * 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 27]: *************************** 40.0000 - 50.0000 [ 2]: ** 50.0000 - 60.0000 [ 0]: 60.0000 - 70.0000 [ 2]: ** 70.0000 - 80.0000 [ 0]: 80.0000 - 90.0000 [ 0]: 90.0000 - 100.0000 [ 28]: **************************** Sender: 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 0]: 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 11]: *********** 40.0000 - 50.0000 [ 0]: 50.0000 - 60.0000 [ 1]: * 60.0000 - 70.0000 [ 0]: 70.0000 - 80.0000 [ 3]: *** 80.0000 - 90.0000 [ 7]: ******* 90.0000 - 100.0000 [ 38]: ************************************** These results demonstrate gaining back the tendency of the CPU to stay in more responsive, performant C-states (and thus yield measurably better performance), by reverting commit 69a37beabf1f0a6705c08e879bdd5d82ff6486c4. Requested-by: Jeremy Eder <jeder@redhat.com> Tested-by: Len Brown <len.brown@intel.com> Cc: 3.8+ <stable@vger.kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-07-27 03:41:34 +04:00
if (ts->inidle)
tick_nohz_start_idle(ts);
Revert "cpuidle: Quickly notice prediction failure for repeat mode" Revert commit 69a37bea (cpuidle: Quickly notice prediction failure for repeat mode), because it has been identified as the source of a significant performance regression in v3.8 and later as explained by Jeremy Eder: We believe we've identified a particular commit to the cpuidle code that seems to be impacting performance of variety of workloads. The simplest way to reproduce is using netperf TCP_RR test, so we're using that, on a pair of Sandy Bridge based servers. We also have data from a large database setup where performance is also measurably/positively impacted, though that test data isn't easily share-able. Included below are test results from 3 test kernels: kernel reverts ----------------------------------------------------------- 1) vanilla upstream (no reverts) 2) perfteam2 reverts e11538d1f03914eb92af5a1a378375c05ae8520c 3) test reverts 69a37beabf1f0a6705c08e879bdd5d82ff6486c4 e11538d1f03914eb92af5a1a378375c05ae8520c In summary, netperf TCP_RR numbers improve by approximately 4% after reverting 69a37beabf1f0a6705c08e879bdd5d82ff6486c4. When 69a37beabf1f0a6705c08e879bdd5d82ff6486c4 is included, C0 residency never seems to get above 40%. Taking that patch out gets C0 near 100% quite often, and performance increases. The below data are histograms representing the %c0 residency @ 1-second sample rates (using turbostat), while under netperf test. - If you look at the first 4 histograms, you can see %c0 residency almost entirely in the 30,40% bin. - The last pair, which reverts 69a37beabf1f0a6705c08e879bdd5d82ff6486c4, shows %c0 in the 80,90,100% bins. Below each kernel name are netperf TCP_RR trans/s numbers for the particular kernel that can be disclosed publicly, comparing the 3 test kernels. We ran a 4th test with the vanilla kernel where we've also set /dev/cpu_dma_latency=0 to show overall impact boosting single-threaded TCP_RR performance over 11% above baseline. 3.10-rc2 vanilla RX + c0 lock (/dev/cpu_dma_latency=0): TCP_RR trans/s 54323.78 ----------------------------------------------------------- 3.10-rc2 vanilla RX (no reverts) TCP_RR trans/s 48192.47 Receiver %c0 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 0]: 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 59]: *********************************************************** 40.0000 - 50.0000 [ 1]: * 50.0000 - 60.0000 [ 0]: 60.0000 - 70.0000 [ 0]: 70.0000 - 80.0000 [ 0]: 80.0000 - 90.0000 [ 0]: 90.0000 - 100.0000 [ 0]: Sender %c0 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 0]: 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 11]: *********** 40.0000 - 50.0000 [ 49]: ************************************************* 50.0000 - 60.0000 [ 0]: 60.0000 - 70.0000 [ 0]: 70.0000 - 80.0000 [ 0]: 80.0000 - 90.0000 [ 0]: 90.0000 - 100.0000 [ 0]: ----------------------------------------------------------- 3.10-rc2 perfteam2 RX (reverts commit e11538d1f03914eb92af5a1a378375c05ae8520c) TCP_RR trans/s 49698.69 Receiver %c0 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 1]: * 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 59]: *********************************************************** 40.0000 - 50.0000 [ 0]: 50.0000 - 60.0000 [ 0]: 60.0000 - 70.0000 [ 0]: 70.0000 - 80.0000 [ 0]: 80.0000 - 90.0000 [ 0]: 90.0000 - 100.0000 [ 0]: Sender %c0 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 0]: 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 2]: ** 40.0000 - 50.0000 [ 58]: ********************************************************** 50.0000 - 60.0000 [ 0]: 60.0000 - 70.0000 [ 0]: 70.0000 - 80.0000 [ 0]: 80.0000 - 90.0000 [ 0]: 90.0000 - 100.0000 [ 0]: ----------------------------------------------------------- 3.10-rc2 test RX (reverts 69a37beabf1f0a6705c08e879bdd5d82ff6486c4 and e11538d1f03914eb92af5a1a378375c05ae8520c) TCP_RR trans/s 47766.95 Receiver %c0 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 1]: * 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 27]: *************************** 40.0000 - 50.0000 [ 2]: ** 50.0000 - 60.0000 [ 0]: 60.0000 - 70.0000 [ 2]: ** 70.0000 - 80.0000 [ 0]: 80.0000 - 90.0000 [ 0]: 90.0000 - 100.0000 [ 28]: **************************** Sender: 0.0000 - 10.0000 [ 1]: * 10.0000 - 20.0000 [ 0]: 20.0000 - 30.0000 [ 0]: 30.0000 - 40.0000 [ 11]: *********** 40.0000 - 50.0000 [ 0]: 50.0000 - 60.0000 [ 1]: * 60.0000 - 70.0000 [ 0]: 70.0000 - 80.0000 [ 3]: *** 80.0000 - 90.0000 [ 7]: ******* 90.0000 - 100.0000 [ 38]: ************************************** These results demonstrate gaining back the tendency of the CPU to stay in more responsive, performant C-states (and thus yield measurably better performance), by reverting commit 69a37beabf1f0a6705c08e879bdd5d82ff6486c4. Requested-by: Jeremy Eder <jeder@redhat.com> Tested-by: Len Brown <len.brown@intel.com> Cc: 3.8+ <stable@vger.kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-07-27 03:41:34 +04:00
else
tick_nohz_full_update_tick(ts);
}
cpuidle: consolidate 2.6.22 cpuidle branch into one patch commit e5a16b1f9eec0af7cfa0830304b41c1c0833cf9f Author: Len Brown <len.brown@intel.com> Date: Tue Oct 2 23:44:44 2007 -0400 cpuidle: shrink diff processor_idle.c | 440 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 429 insertions(+), 11 deletions(-) Signed-off-by: Len Brown <len.brown@intel.com> commit dfbb9d5aedfb18848a3e0d6f6e3e4969febb209c Author: Len Brown <len.brown@intel.com> Date: Wed Sep 26 02:17:55 2007 -0400 cpuidle: reduce diff size Reduces the cpuidle processor_idle.c diff vs 2.6.22 from this processor_idle.c | 2006 ++++++++++++++++++++++++++----------------- 1 file changed, 1219 insertions(+), 787 deletions(-) to this: processor_idle.c | 502 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 458 insertions(+), 44 deletions(-) ...for the purpose of making the cpuilde patch less invasive and easier to review. no functional changes. build tested only. Signed-off-by: Len Brown <len.brown@intel.com> commit 889172fc915f5a7fe20f35b133cbd205ce69bf6c Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Sep 13 13:40:05 2007 -0700 cpuidle: Retain old ACPI policy for !CONFIG_CPU_IDLE Retain the old policy in processor_idle, so that when CPU_IDLE is not configured, old C-state policy will still be used. This provides a clean gradual migration path from old ACPI policy to new cpuidle based policy. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 9544a8181edc7ecc33b3bfd69271571f98ed08bc Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Sep 13 13:39:17 2007 -0700 cpuidle: Configure governors by default Quoting Len "Do not give an option to users to shoot themselves in the foot". Remove the configurability of ladder and menu governors as they are needed for default policy of cpuidle. That way users will not be able to have cpuidle without any policy loosing all C-state power savings. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 8975059a2c1e56cfe83d1bcf031bcf4cb39be743 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:27:07 2007 -0400 CPUIDLE: load ACPI properly when CPUIDLE is disabled Change the registration return codes for when CPUIDLE support is not compiled into the kernel. As a result, the ACPI processor driver will load properly even if CPUIDLE is unavailable. However, it may be possible to cleanup the ACPI processor driver further and eliminate some dead code paths. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit e0322e2b58dd1b12ec669bf84693efe0dc2414a8 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:26:06 2007 -0400 CPUIDLE: remove cpuidle_get_bm_activity() Remove cpuidle_get_bm_activity() and updates governors accordingly. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 18a6e770d5c82ba26653e53d240caa617e09e9ab Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:58 2007 -0400 CPUIDLE: max_cstate fix Currently max_cstate is limited to 0, resulting in no idle processor power management on ACPI platforms. This patch restores the value to the array size. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 1fdc0887286179b40ce24bcdbde663172e205ef0 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:40 2007 -0400 CPUIDLE: handle BM detection inside the ACPI Processor driver Update the ACPI processor driver to detect BM activity and limit state entry depth internally, rather than exposing such requirements to CPUIDLE. As a result, CPUIDLE can drop this ACPI-specific interface and become more platform independent. BM activity is now handled much more aggressively than it was in the original implementation, so some testing coverage may be needed to verify that this doesn't introduce any DMA buffer under-run issues. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 0ef38840db666f48e3cdd2b769da676c57228dd9 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:14 2007 -0400 CPUIDLE: menu governor updates Tweak the menu governor to more effectively handle non-timer break events. Non-timer break events are detected by comparing the actual sleep time to the expected sleep time. In future revisions, it may be more reliable to use the timer data structures directly. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit bb4d74fca63fa96cf3ace644b15ae0f12b7df5a1 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:24:40 2007 -0400 CPUIDLE: fix 'current_governor' sysfs entry Allow the "current_governor" sysfs entry to properly handle input terminated with '\n'. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit df3c71559bb69b125f1a48971bf0d17f78bbdf47 Author: Len Brown <len.brown@intel.com> Date: Sun Aug 12 02:00:45 2007 -0400 cpuidle: fix IA64 build (again) Signed-off-by: Len Brown <len.brown@intel.com> commit a02064579e3f9530fd31baae16b1fc46b5a7bca8 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:39:27 2007 -0400 cpuidle: Remove support for runtime changing of max_cstate Remove support for runtime changeability of max_cstate. Drivers can use use latency APIs. max_cstate can still be used as a boot time option and dmi override. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 0912a44b13adf22f5e3f607d263aed23b4910d7e Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:39:16 2007 -0400 cpuidle: Remove ACPI cstate_limit calls from ipw2100 ipw2100 already has code to use accetable_latency interfaces to limit the C-state. Remove the calls to acpi_set_cstate_limit and acpi_get_cstate_limit as they are redundant. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit c649a76e76be6bff1fd770d0a775798813a3f6e0 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:35:39 2007 -0400 cpuidle: compile fix for pause and resume functions Fix the compilation failure when cpuidle is not compiled in. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: Adam Belay <adam.belay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 2305a5920fb8ee6ccec1c62ade05aa8351091d71 Author: Adam Belay <abelay@novell.com> Date: Thu Jul 19 00:49:00 2007 -0400 cpuidle: re-write Some portions have been rewritten to make the code cleaner and lighter weight. The following is a list of changes: 1.) the state name is now included in the sysfs interface 2.) detection, hotplug, and available state modifications are handled by CPUIDLE drivers directly 3.) the CPUIDLE idle handler is only ever installed when at least one cpuidle_device is enabled and ready 4.) the menu governor BM code no longer overflows 5.) the sysfs attributes are now printed as unsigned integers, avoiding negative values 6.) a variety of other small cleanups Also, Idle drivers are no longer swappable during runtime through the CPUIDLE sysfs inteface. On i386 and x86_64 most idle handlers (e.g. poll, mwait, halt, etc.) don't benefit from an infrastructure that supports multiple states, so I think using a more general case idle handler selection mechanism would be cleaner. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit df25b6b56955714e6e24b574d88d1fd11f0c3ee5 Author: Len Brown <len.brown@intel.com> Date: Tue Jul 24 17:08:21 2007 -0400 cpuidle: fix IA64 buid Signed-off-by: Len Brown <len.brown@intel.com> commit fd6ada4c14488755ff7068860078c437431fbccd Author: Adrian Bunk <bunk@stusta.de> Date: Mon Jul 9 11:33:13 2007 -0700 cpuidle: static make cpuidle_replace_governor() static Signed-off-by: Adrian Bunk <bunk@stusta.de> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit c1d4a2cebcadf2429c0c72e1d29aa2a9684c32e0 Author: Adrian Bunk <bunk@stusta.de> Date: Tue Jul 3 00:54:40 2007 -0400 cpuidle: static This patch makes the needlessly global struct menu_governor static. Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit dbf8780c6e8d572c2c273da97ed1cca7608fd999 Author: Andrew Morton <akpm@linux-foundation.org> Date: Tue Jul 3 00:49:14 2007 -0400 export symbol tick_nohz_get_sleep_length ERROR: "tick_nohz_get_sleep_length" [drivers/cpuidle/governors/menu.ko] undefined! ERROR: "tick_nohz_get_idle_jiffies" [drivers/cpuidle/governors/menu.ko] undefined! And please be sure to get your changes to core kernel suitably reviewed. Cc: Adam Belay <abelay@novell.com> Cc: Venki Pallipadi <venkatesh.pallipadi@intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 29f0e248e7017be15f99febf9143a2cef00b2961 Author: Andrew Morton <akpm@linux-foundation.org> Date: Tue Jul 3 00:43:04 2007 -0400 tick.h needs hrtimer.h It uses hrtimers. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit e40cede7d63a029e92712a3fe02faee60cc38fb4 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:40:34 2007 -0400 cpuidle: first round of documentation updates Documentation changes based on Pavel's feedback. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 83b42be2efece386976507555c29e7773a0dfcd1 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:39:25 2007 -0400 cpuidle: add rating to the governors and pick the one with highest rating by default Introduce a governor rating scheme to pick the right governor by default. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit d2a74b8c5e8f22def4709330d4bfc4a29209b71c Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:38:08 2007 -0400 cpuidle: make cpuidle sysfs driver governor switch off by default Make default cpuidle sysfs to show current_governor and current_driver in read-only mode. More elaborate available_governors and available_drivers with writeable current_governor and current_driver interface only appear with "cpuidle_sysfs_switch" boot parameter. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 1f60a0e80bf83cf6b55c8845bbe5596ed8f6307b Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:37:00 2007 -0400 cpuidle: menu governor: change the early break condition Change the C-state early break out algorithm in menu governor. We only look at early breakouts that result in wakeups shorter than idle state's target_residency. If such a breakout is frequent enough, eliminate the particular idle state upto a timeout period. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 45a42095cf64b003b4a69be3ce7f434f97d7af51 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:35:38 2007 -0400 cpuidle: fix uninitialized variable in sysfs routine Fix the uninitialized usage of ret. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 80dca7cdba3e6ee13eae277660873ab9584eb3be Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:34:16 2007 -0400 cpuidle: reenable /proc/acpi//power interface for the time being Keep /proc/acpi/processor/CPU*/power around for a while as powertop depends on it. It will be marked deprecated and removed in future. powertop can use cpuidle interfaces instead. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 589c37c2646c5e3813a51255a5ee1159cb4c33fc Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:32:37 2007 -0400 cpuidle: menu governor and hrtimer compile fix Compile fix for menu governor. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 0ba80bd9ab3ed304cb4f19b722e4cc6740588b5e Author: Len Brown <len.brown@intel.com> Date: Thu May 31 22:51:43 2007 -0400 cpuidle: build fix - cpuidle vs ipw2100 module ERROR: "acpi_set_cstate_limit" [drivers/net/wireless/ipw2100.ko] undefined! Signed-off-by: Len Brown <len.brown@intel.com> commit d7d8fa7f96a7f7682be7c6cc0cc53fa7a18c3b58 Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:47:07 2007 -0400 cpuidle: add the 'menu' governor Here is my first take at implementing an idle PM governor that takes full advantage of NO_HZ. I call it the 'menu' governor because it considers the full list of idle states before each entry. I've kept the implementation fairly simple. It attempts to guess the next residency time and then chooses a state that would meet at least the break-even point between power savings and entry cost. To this end, it selects the deepest idle state that satisfies the following constraints: 1. If the idle time elapsed since bus master activity was detected is below a threshold (currently 20 ms), then limit the selection to C2-type or above. 2. Do not choose a state with a break-even residency that exceeds the expected time remaining until the next timer interrupt. 3. Do not choose a state with a break-even residency that exceeds the elapsed time between the last pair of break events, excluding timer interrupts. This governor has an advantage over "ladder" governor because it proactively checks how much time remains until the next timer interrupt using the tick infrastructure. Also, it handles device interrupt activity more intelligently by not including timer interrupts in break event calculations. Finally, it doesn't make policy decisions using the number of state entries, which can have variable residency times (NO_HZ makes these potentially very large), and instead only considers sleep time deltas. The menu governor can be selected during runtime using the cpuidle sysfs interface like so: "echo "menu" > /sys/devices/system/cpu/cpuidle/current_governor" Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit a4bec7e65aa3b7488b879d971651cc99a6c410fe Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:47:03 2007 -0400 cpuidle: export time until next timer interrupt using NO_HZ Expose information about the time remaining until the next timer interrupt expires by utilizing the dynticks infrastructure. Also modify the main idle loop to allow dynticks to handle non-interrupt break events (e.g. DMA). Finally, expose sleep ticks information to external code. Thomas Gleixner is responsible for much of the code in this patch. However, I've made some additional changes, so I'm probably responsible if there are any bugs or oversights :) Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 2929d8996fbc77f41a5ff86bb67cdde3ca7d2d72 Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:46:58 2007 -0400 cpuidle: governor API changes This patch prepares cpuidle for the menu governor. It adds an optional stage after idle state entry to give the governor an opportunity to check why the state was exited. Also it makes sure the idle loop returns after each state entry, allowing the appropriate dynticks code to run. Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 3a7fd42f9825c3b03e364ca59baa751bb350775f Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Apr 26 00:03:59 2007 -0700 cpuidle: hang fix Prevent hang on x86-64, when ACPI processor driver is added as a module on a system that does not support C-states. x86-64 expects all idle handlers to enable interrupts before returning from idle handler. This is due to enter_idle(), exit_idle() races. Make cpuidle_idle_call() confirm to this when there is no pm_idle_old. Also, cpuidle look at the return values of attch_driver() and set current_driver to NULL if attach fails on all CPUs. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 4893339a142afbd5b7c01ffadfd53d14746e858e Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:09 2007 +0800 cpuidle: add support for max_cstate limit With CPUIDLE framework, the max_cstate (to limit max cpu c-state) parameter is ingored. Some systems require it to ignore C2/C3 and some drivers like ipw require it too. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 43bbbbe1cb998cbd2df656f55bb3bfe30f30e7d1 Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:13 2007 +0800 cpuidle: add cpuidle_fore_redetect_devices API add cpuidle_force_redetect_devices API, which forces all CPU redetect idle states. Next patch will use it. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit d1edadd608f24836def5ec483d2edccfb37b1d19 Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:01 2007 +0800 cpuidle: fix sysfs related issue Fix the cpuidle sysfs issue. a. make kobject dynamicaly allocated b. fixed sysfs init issue to avoid suspend/resume issue Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 7169a5cc0d67b263978859672e86c13c23a5570d Author: Randy Dunlap <randy.dunlap@oracle.com> Date: Wed Mar 28 22:52:53 2007 -0400 cpuidle: 1-bit field must be unsigned A 1-bit bitfield has no room for a sign bit. drivers/cpuidle/governors/ladder.c:54:16: error: dubious bitfield without explicit `signed' or `unsigned' Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 4658620158dc2fbd9e4bcb213c5b6fb5d05ba7d4 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Wed Mar 28 22:52:41 2007 -0400 cpuidle: fix boot hang Patch for cpuidle boot hang reported by Larry Finger here. http://www.ussg.iu.edu/hypermail/linux/kernel/0703.2/2025.html Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Larry Finger <larry.finger@lwfinger.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit c17e168aa6e5fe3851baaae8df2fbc1cf11443a9 Author: Len Brown <len.brown@intel.com> Date: Wed Mar 7 04:37:53 2007 -0500 cpuidle: ladder does not depend on ACPI build fix for CONFIG_ACPI=n In file included from drivers/cpuidle/governors/ladder.c:21: include/acpi/processor.h:88: error: expected specifier-qualifier-list before ‘acpi_integer’ include/acpi/processor.h:106: error: expected specifier-qualifier-list before ‘acpi_integer’ include/acpi/processor.h:168: error: expected specifier-qualifier-list before ‘acpi_handle’ Signed-off-by: Len Brown <len.brown@intel.com> commit 8c91d958246bde68db0c3f0c57b535962ce861cb Author: Adrian Bunk <bunk@stusta.de> Date: Tue Mar 6 02:29:40 2007 -0800 cpuidle: make code static This patch makes the following needlessly global code static: - driver.c: __cpuidle_find_driver() - governor.c: __cpuidle_find_governor() - ladder.c: struct ladder_governor Signed-off-by: Adrian Bunk <bunk@stusta.de> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Adam Belay <abelay@novell.com> Cc: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 0c39dc3187094c72c33ab65a64d2017b21f372d2 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Wed Mar 7 02:38:22 2007 -0500 cpu_idle: fix build break This patch fixes a build breakage with !CONFIG_HOTPLUG_CPU and CONFIG_CPU_IDLE. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 8112e3b115659b07df340ef170515799c0105f82 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Mar 6 02:29:39 2007 -0800 cpuidle: build fix for !CPU_IDLE Fix the compile issues when CPU_IDLE is not configured. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Adam Belay <abelay@novell.com> Cc: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 1eb4431e9599cd25e0d9872f3c2c8986821839dd Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:54:57 2007 -0800 cpuidle take2: Basic documentation for cpuidle Documentation for cpuidle infrastructure Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit ef5f15a8b79123a047285ec2e3899108661df779 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:54:03 2007 -0800 cpuidle take2: Hookup ACPI C-states driver with cpuidle Hookup ACPI C-states onto generic cpuidle infrastructure. drivers/acpi/procesor_idle.c is now a ACPI C-states driver that registers as a driver in cpuidle infrastructure and the policy part is removed from drivers/acpi/processor_idle.c. We use governor in cpuidle instead. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 987196fa82d4db52c407e8c9d5dec884ba602183 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:52:57 2007 -0800 cpuidle take2: Core cpuidle infrastructure Announcing 'cpuidle', a new CPU power management infrastructure to manage idle CPUs in a clean and efficient manner. cpuidle separates out the drivers that can provide support for multiple types of idle states and policy governors that decide on what idle state to use at run time. A cpuidle driver can support multiple idle states based on parameters like varying power consumption, wakeup latency, etc (ACPI C-states for example). A cpuidle governor can be usage model specific (laptop, server, laptop on battery etc). Main advantage of the infrastructure being, it allows independent development of drivers and governors and allows for better CPU power management. A huge thanks to Adam Belay and Shaohua Li who were part of this mini-project since its beginning and are greatly responsible for this patchset. This patch: Core cpuidle infrastructure. Introduces a new abstraction layer for cpuidle: * which manages drivers that can support multiple idles states. Drivers can be generic or particular to specific hardware/platform * allows pluging in multiple policy governors that can take idle state policy decision * The core also has a set of sysfs interfaces with which administrato can know about supported drivers and governors and switch them at run time. Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> Signed-off-by: Len Brown <len.brown@intel.com>
2007-10-04 02:58:00 +04:00
/**
cpuidle: Return nohz hint from cpuidle_select() Add a new pointer argument to cpuidle_select() and to the ->select cpuidle governor callback to allow a boolean value indicating whether or not the tick should be stopped before entering the selected state to be returned from there. Make the ladder governor ignore that pointer (to preserve its current behavior) and make the menu governor return 'false" through it if: (1) the idle exit latency is constrained at 0, or (2) the selected state is a polling one, or (3) the expected idle period duration is within the tick period range. In addition to that, the correction factor computations in the menu governor need to take the possibility that the tick may not be stopped into account to avoid artificially small correction factor values. To that end, add a mechanism to record tick wakeups, as suggested by Peter Zijlstra, and use it to modify the menu_update() behavior when tick wakeup occurs. Namely, if the CPU is woken up by the tick and the return value of tick_nohz_get_sleep_length() is not within the tick boundary, the predicted idle duration is likely too short, so make menu_update() try to compensate for that by updating the governor statistics as though the CPU was idle for a long time. Since the value returned through the new argument pointer of cpuidle_select() is not used by its caller yet, this change by itself is not expected to alter the functionality of the code. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
2018-03-22 19:50:49 +03:00
* tick_nohz_idle_got_tick - Check whether or not the tick handler has run
*/
bool tick_nohz_idle_got_tick(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
if (ts->got_idle_tick) {
ts->got_idle_tick = 0;
cpuidle: Return nohz hint from cpuidle_select() Add a new pointer argument to cpuidle_select() and to the ->select cpuidle governor callback to allow a boolean value indicating whether or not the tick should be stopped before entering the selected state to be returned from there. Make the ladder governor ignore that pointer (to preserve its current behavior) and make the menu governor return 'false" through it if: (1) the idle exit latency is constrained at 0, or (2) the selected state is a polling one, or (3) the expected idle period duration is within the tick period range. In addition to that, the correction factor computations in the menu governor need to take the possibility that the tick may not be stopped into account to avoid artificially small correction factor values. To that end, add a mechanism to record tick wakeups, as suggested by Peter Zijlstra, and use it to modify the menu_update() behavior when tick wakeup occurs. Namely, if the CPU is woken up by the tick and the return value of tick_nohz_get_sleep_length() is not within the tick boundary, the predicted idle duration is likely too short, so make menu_update() try to compensate for that by updating the governor statistics as though the CPU was idle for a long time. Since the value returned through the new argument pointer of cpuidle_select() is not used by its caller yet, this change by itself is not expected to alter the functionality of the code. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
2018-03-22 19:50:49 +03:00
return true;
}
return false;
}
cpuidle: Export the next timer expiration for CPUs To be able to predict the sleep duration for a CPU entering idle, it is essential to know the expiration time of the next timer. Both the teo and the menu cpuidle governors already use this information for CPU idle state selection. Moving forward, a similar prediction needs to be made for a group of idle CPUs rather than for a single one and the following changes implement a new genpd governor for that purpose. In order to support that feature, add a new function called tick_nohz_get_next_hrtimer() that will return the next hrtimer expiration time of a given CPU to be invoked after deciding whether or not to stop the scheduler tick on that CPU. Make the cpuidle core call tick_nohz_get_next_hrtimer() right before invoking the ->enter() callback provided by the cpuidle driver for the given state and store its return value in the per-CPU struct cpuidle_device, so as to make it available to code outside of cpuidle. Note that at the point when cpuidle calls tick_nohz_get_next_hrtimer(), the governor's ->select() callback has already returned and indicated whether or not the tick should be stopped, so in fact the value returned by tick_nohz_get_next_hrtimer() always is the next hrtimer expiration time for the given CPU, possibly including the tick (if it hasn't been stopped). Co-developed-by: Lina Iyer <lina.iyer@linaro.org> Co-developed-by: Daniel Lezcano <daniel.lezcano@linaro.org> Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org> [ rjw: Subject & changelog ] Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2019-03-27 17:35:47 +03:00
/**
* tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer
* or the tick, whatever that expires first. Note that, if the tick has been
* stopped, it returns the next hrtimer.
*
* Called from power state control code with interrupts disabled
*/
ktime_t tick_nohz_get_next_hrtimer(void)
{
return __this_cpu_read(tick_cpu_device.evtdev)->next_event;
}
cpuidle: consolidate 2.6.22 cpuidle branch into one patch commit e5a16b1f9eec0af7cfa0830304b41c1c0833cf9f Author: Len Brown <len.brown@intel.com> Date: Tue Oct 2 23:44:44 2007 -0400 cpuidle: shrink diff processor_idle.c | 440 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 429 insertions(+), 11 deletions(-) Signed-off-by: Len Brown <len.brown@intel.com> commit dfbb9d5aedfb18848a3e0d6f6e3e4969febb209c Author: Len Brown <len.brown@intel.com> Date: Wed Sep 26 02:17:55 2007 -0400 cpuidle: reduce diff size Reduces the cpuidle processor_idle.c diff vs 2.6.22 from this processor_idle.c | 2006 ++++++++++++++++++++++++++----------------- 1 file changed, 1219 insertions(+), 787 deletions(-) to this: processor_idle.c | 502 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 458 insertions(+), 44 deletions(-) ...for the purpose of making the cpuilde patch less invasive and easier to review. no functional changes. build tested only. Signed-off-by: Len Brown <len.brown@intel.com> commit 889172fc915f5a7fe20f35b133cbd205ce69bf6c Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Sep 13 13:40:05 2007 -0700 cpuidle: Retain old ACPI policy for !CONFIG_CPU_IDLE Retain the old policy in processor_idle, so that when CPU_IDLE is not configured, old C-state policy will still be used. This provides a clean gradual migration path from old ACPI policy to new cpuidle based policy. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 9544a8181edc7ecc33b3bfd69271571f98ed08bc Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Sep 13 13:39:17 2007 -0700 cpuidle: Configure governors by default Quoting Len "Do not give an option to users to shoot themselves in the foot". Remove the configurability of ladder and menu governors as they are needed for default policy of cpuidle. That way users will not be able to have cpuidle without any policy loosing all C-state power savings. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 8975059a2c1e56cfe83d1bcf031bcf4cb39be743 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:27:07 2007 -0400 CPUIDLE: load ACPI properly when CPUIDLE is disabled Change the registration return codes for when CPUIDLE support is not compiled into the kernel. As a result, the ACPI processor driver will load properly even if CPUIDLE is unavailable. However, it may be possible to cleanup the ACPI processor driver further and eliminate some dead code paths. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit e0322e2b58dd1b12ec669bf84693efe0dc2414a8 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:26:06 2007 -0400 CPUIDLE: remove cpuidle_get_bm_activity() Remove cpuidle_get_bm_activity() and updates governors accordingly. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 18a6e770d5c82ba26653e53d240caa617e09e9ab Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:58 2007 -0400 CPUIDLE: max_cstate fix Currently max_cstate is limited to 0, resulting in no idle processor power management on ACPI platforms. This patch restores the value to the array size. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 1fdc0887286179b40ce24bcdbde663172e205ef0 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:40 2007 -0400 CPUIDLE: handle BM detection inside the ACPI Processor driver Update the ACPI processor driver to detect BM activity and limit state entry depth internally, rather than exposing such requirements to CPUIDLE. As a result, CPUIDLE can drop this ACPI-specific interface and become more platform independent. BM activity is now handled much more aggressively than it was in the original implementation, so some testing coverage may be needed to verify that this doesn't introduce any DMA buffer under-run issues. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 0ef38840db666f48e3cdd2b769da676c57228dd9 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:14 2007 -0400 CPUIDLE: menu governor updates Tweak the menu governor to more effectively handle non-timer break events. Non-timer break events are detected by comparing the actual sleep time to the expected sleep time. In future revisions, it may be more reliable to use the timer data structures directly. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit bb4d74fca63fa96cf3ace644b15ae0f12b7df5a1 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:24:40 2007 -0400 CPUIDLE: fix 'current_governor' sysfs entry Allow the "current_governor" sysfs entry to properly handle input terminated with '\n'. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit df3c71559bb69b125f1a48971bf0d17f78bbdf47 Author: Len Brown <len.brown@intel.com> Date: Sun Aug 12 02:00:45 2007 -0400 cpuidle: fix IA64 build (again) Signed-off-by: Len Brown <len.brown@intel.com> commit a02064579e3f9530fd31baae16b1fc46b5a7bca8 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:39:27 2007 -0400 cpuidle: Remove support for runtime changing of max_cstate Remove support for runtime changeability of max_cstate. Drivers can use use latency APIs. max_cstate can still be used as a boot time option and dmi override. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 0912a44b13adf22f5e3f607d263aed23b4910d7e Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:39:16 2007 -0400 cpuidle: Remove ACPI cstate_limit calls from ipw2100 ipw2100 already has code to use accetable_latency interfaces to limit the C-state. Remove the calls to acpi_set_cstate_limit and acpi_get_cstate_limit as they are redundant. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit c649a76e76be6bff1fd770d0a775798813a3f6e0 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:35:39 2007 -0400 cpuidle: compile fix for pause and resume functions Fix the compilation failure when cpuidle is not compiled in. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: Adam Belay <adam.belay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 2305a5920fb8ee6ccec1c62ade05aa8351091d71 Author: Adam Belay <abelay@novell.com> Date: Thu Jul 19 00:49:00 2007 -0400 cpuidle: re-write Some portions have been rewritten to make the code cleaner and lighter weight. The following is a list of changes: 1.) the state name is now included in the sysfs interface 2.) detection, hotplug, and available state modifications are handled by CPUIDLE drivers directly 3.) the CPUIDLE idle handler is only ever installed when at least one cpuidle_device is enabled and ready 4.) the menu governor BM code no longer overflows 5.) the sysfs attributes are now printed as unsigned integers, avoiding negative values 6.) a variety of other small cleanups Also, Idle drivers are no longer swappable during runtime through the CPUIDLE sysfs inteface. On i386 and x86_64 most idle handlers (e.g. poll, mwait, halt, etc.) don't benefit from an infrastructure that supports multiple states, so I think using a more general case idle handler selection mechanism would be cleaner. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit df25b6b56955714e6e24b574d88d1fd11f0c3ee5 Author: Len Brown <len.brown@intel.com> Date: Tue Jul 24 17:08:21 2007 -0400 cpuidle: fix IA64 buid Signed-off-by: Len Brown <len.brown@intel.com> commit fd6ada4c14488755ff7068860078c437431fbccd Author: Adrian Bunk <bunk@stusta.de> Date: Mon Jul 9 11:33:13 2007 -0700 cpuidle: static make cpuidle_replace_governor() static Signed-off-by: Adrian Bunk <bunk@stusta.de> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit c1d4a2cebcadf2429c0c72e1d29aa2a9684c32e0 Author: Adrian Bunk <bunk@stusta.de> Date: Tue Jul 3 00:54:40 2007 -0400 cpuidle: static This patch makes the needlessly global struct menu_governor static. Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit dbf8780c6e8d572c2c273da97ed1cca7608fd999 Author: Andrew Morton <akpm@linux-foundation.org> Date: Tue Jul 3 00:49:14 2007 -0400 export symbol tick_nohz_get_sleep_length ERROR: "tick_nohz_get_sleep_length" [drivers/cpuidle/governors/menu.ko] undefined! ERROR: "tick_nohz_get_idle_jiffies" [drivers/cpuidle/governors/menu.ko] undefined! And please be sure to get your changes to core kernel suitably reviewed. Cc: Adam Belay <abelay@novell.com> Cc: Venki Pallipadi <venkatesh.pallipadi@intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 29f0e248e7017be15f99febf9143a2cef00b2961 Author: Andrew Morton <akpm@linux-foundation.org> Date: Tue Jul 3 00:43:04 2007 -0400 tick.h needs hrtimer.h It uses hrtimers. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit e40cede7d63a029e92712a3fe02faee60cc38fb4 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:40:34 2007 -0400 cpuidle: first round of documentation updates Documentation changes based on Pavel's feedback. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 83b42be2efece386976507555c29e7773a0dfcd1 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:39:25 2007 -0400 cpuidle: add rating to the governors and pick the one with highest rating by default Introduce a governor rating scheme to pick the right governor by default. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit d2a74b8c5e8f22def4709330d4bfc4a29209b71c Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:38:08 2007 -0400 cpuidle: make cpuidle sysfs driver governor switch off by default Make default cpuidle sysfs to show current_governor and current_driver in read-only mode. More elaborate available_governors and available_drivers with writeable current_governor and current_driver interface only appear with "cpuidle_sysfs_switch" boot parameter. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 1f60a0e80bf83cf6b55c8845bbe5596ed8f6307b Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:37:00 2007 -0400 cpuidle: menu governor: change the early break condition Change the C-state early break out algorithm in menu governor. We only look at early breakouts that result in wakeups shorter than idle state's target_residency. If such a breakout is frequent enough, eliminate the particular idle state upto a timeout period. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 45a42095cf64b003b4a69be3ce7f434f97d7af51 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:35:38 2007 -0400 cpuidle: fix uninitialized variable in sysfs routine Fix the uninitialized usage of ret. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 80dca7cdba3e6ee13eae277660873ab9584eb3be Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:34:16 2007 -0400 cpuidle: reenable /proc/acpi//power interface for the time being Keep /proc/acpi/processor/CPU*/power around for a while as powertop depends on it. It will be marked deprecated and removed in future. powertop can use cpuidle interfaces instead. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 589c37c2646c5e3813a51255a5ee1159cb4c33fc Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:32:37 2007 -0400 cpuidle: menu governor and hrtimer compile fix Compile fix for menu governor. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 0ba80bd9ab3ed304cb4f19b722e4cc6740588b5e Author: Len Brown <len.brown@intel.com> Date: Thu May 31 22:51:43 2007 -0400 cpuidle: build fix - cpuidle vs ipw2100 module ERROR: "acpi_set_cstate_limit" [drivers/net/wireless/ipw2100.ko] undefined! Signed-off-by: Len Brown <len.brown@intel.com> commit d7d8fa7f96a7f7682be7c6cc0cc53fa7a18c3b58 Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:47:07 2007 -0400 cpuidle: add the 'menu' governor Here is my first take at implementing an idle PM governor that takes full advantage of NO_HZ. I call it the 'menu' governor because it considers the full list of idle states before each entry. I've kept the implementation fairly simple. It attempts to guess the next residency time and then chooses a state that would meet at least the break-even point between power savings and entry cost. To this end, it selects the deepest idle state that satisfies the following constraints: 1. If the idle time elapsed since bus master activity was detected is below a threshold (currently 20 ms), then limit the selection to C2-type or above. 2. Do not choose a state with a break-even residency that exceeds the expected time remaining until the next timer interrupt. 3. Do not choose a state with a break-even residency that exceeds the elapsed time between the last pair of break events, excluding timer interrupts. This governor has an advantage over "ladder" governor because it proactively checks how much time remains until the next timer interrupt using the tick infrastructure. Also, it handles device interrupt activity more intelligently by not including timer interrupts in break event calculations. Finally, it doesn't make policy decisions using the number of state entries, which can have variable residency times (NO_HZ makes these potentially very large), and instead only considers sleep time deltas. The menu governor can be selected during runtime using the cpuidle sysfs interface like so: "echo "menu" > /sys/devices/system/cpu/cpuidle/current_governor" Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit a4bec7e65aa3b7488b879d971651cc99a6c410fe Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:47:03 2007 -0400 cpuidle: export time until next timer interrupt using NO_HZ Expose information about the time remaining until the next timer interrupt expires by utilizing the dynticks infrastructure. Also modify the main idle loop to allow dynticks to handle non-interrupt break events (e.g. DMA). Finally, expose sleep ticks information to external code. Thomas Gleixner is responsible for much of the code in this patch. However, I've made some additional changes, so I'm probably responsible if there are any bugs or oversights :) Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 2929d8996fbc77f41a5ff86bb67cdde3ca7d2d72 Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:46:58 2007 -0400 cpuidle: governor API changes This patch prepares cpuidle for the menu governor. It adds an optional stage after idle state entry to give the governor an opportunity to check why the state was exited. Also it makes sure the idle loop returns after each state entry, allowing the appropriate dynticks code to run. Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 3a7fd42f9825c3b03e364ca59baa751bb350775f Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Apr 26 00:03:59 2007 -0700 cpuidle: hang fix Prevent hang on x86-64, when ACPI processor driver is added as a module on a system that does not support C-states. x86-64 expects all idle handlers to enable interrupts before returning from idle handler. This is due to enter_idle(), exit_idle() races. Make cpuidle_idle_call() confirm to this when there is no pm_idle_old. Also, cpuidle look at the return values of attch_driver() and set current_driver to NULL if attach fails on all CPUs. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 4893339a142afbd5b7c01ffadfd53d14746e858e Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:09 2007 +0800 cpuidle: add support for max_cstate limit With CPUIDLE framework, the max_cstate (to limit max cpu c-state) parameter is ingored. Some systems require it to ignore C2/C3 and some drivers like ipw require it too. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 43bbbbe1cb998cbd2df656f55bb3bfe30f30e7d1 Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:13 2007 +0800 cpuidle: add cpuidle_fore_redetect_devices API add cpuidle_force_redetect_devices API, which forces all CPU redetect idle states. Next patch will use it. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit d1edadd608f24836def5ec483d2edccfb37b1d19 Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:01 2007 +0800 cpuidle: fix sysfs related issue Fix the cpuidle sysfs issue. a. make kobject dynamicaly allocated b. fixed sysfs init issue to avoid suspend/resume issue Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 7169a5cc0d67b263978859672e86c13c23a5570d Author: Randy Dunlap <randy.dunlap@oracle.com> Date: Wed Mar 28 22:52:53 2007 -0400 cpuidle: 1-bit field must be unsigned A 1-bit bitfield has no room for a sign bit. drivers/cpuidle/governors/ladder.c:54:16: error: dubious bitfield without explicit `signed' or `unsigned' Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 4658620158dc2fbd9e4bcb213c5b6fb5d05ba7d4 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Wed Mar 28 22:52:41 2007 -0400 cpuidle: fix boot hang Patch for cpuidle boot hang reported by Larry Finger here. http://www.ussg.iu.edu/hypermail/linux/kernel/0703.2/2025.html Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Larry Finger <larry.finger@lwfinger.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit c17e168aa6e5fe3851baaae8df2fbc1cf11443a9 Author: Len Brown <len.brown@intel.com> Date: Wed Mar 7 04:37:53 2007 -0500 cpuidle: ladder does not depend on ACPI build fix for CONFIG_ACPI=n In file included from drivers/cpuidle/governors/ladder.c:21: include/acpi/processor.h:88: error: expected specifier-qualifier-list before ‘acpi_integer’ include/acpi/processor.h:106: error: expected specifier-qualifier-list before ‘acpi_integer’ include/acpi/processor.h:168: error: expected specifier-qualifier-list before ‘acpi_handle’ Signed-off-by: Len Brown <len.brown@intel.com> commit 8c91d958246bde68db0c3f0c57b535962ce861cb Author: Adrian Bunk <bunk@stusta.de> Date: Tue Mar 6 02:29:40 2007 -0800 cpuidle: make code static This patch makes the following needlessly global code static: - driver.c: __cpuidle_find_driver() - governor.c: __cpuidle_find_governor() - ladder.c: struct ladder_governor Signed-off-by: Adrian Bunk <bunk@stusta.de> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Adam Belay <abelay@novell.com> Cc: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 0c39dc3187094c72c33ab65a64d2017b21f372d2 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Wed Mar 7 02:38:22 2007 -0500 cpu_idle: fix build break This patch fixes a build breakage with !CONFIG_HOTPLUG_CPU and CONFIG_CPU_IDLE. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 8112e3b115659b07df340ef170515799c0105f82 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Mar 6 02:29:39 2007 -0800 cpuidle: build fix for !CPU_IDLE Fix the compile issues when CPU_IDLE is not configured. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Adam Belay <abelay@novell.com> Cc: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 1eb4431e9599cd25e0d9872f3c2c8986821839dd Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:54:57 2007 -0800 cpuidle take2: Basic documentation for cpuidle Documentation for cpuidle infrastructure Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit ef5f15a8b79123a047285ec2e3899108661df779 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:54:03 2007 -0800 cpuidle take2: Hookup ACPI C-states driver with cpuidle Hookup ACPI C-states onto generic cpuidle infrastructure. drivers/acpi/procesor_idle.c is now a ACPI C-states driver that registers as a driver in cpuidle infrastructure and the policy part is removed from drivers/acpi/processor_idle.c. We use governor in cpuidle instead. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 987196fa82d4db52c407e8c9d5dec884ba602183 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:52:57 2007 -0800 cpuidle take2: Core cpuidle infrastructure Announcing 'cpuidle', a new CPU power management infrastructure to manage idle CPUs in a clean and efficient manner. cpuidle separates out the drivers that can provide support for multiple types of idle states and policy governors that decide on what idle state to use at run time. A cpuidle driver can support multiple idle states based on parameters like varying power consumption, wakeup latency, etc (ACPI C-states for example). A cpuidle governor can be usage model specific (laptop, server, laptop on battery etc). Main advantage of the infrastructure being, it allows independent development of drivers and governors and allows for better CPU power management. A huge thanks to Adam Belay and Shaohua Li who were part of this mini-project since its beginning and are greatly responsible for this patchset. This patch: Core cpuidle infrastructure. Introduces a new abstraction layer for cpuidle: * which manages drivers that can support multiple idles states. Drivers can be generic or particular to specific hardware/platform * allows pluging in multiple policy governors that can take idle state policy decision * The core also has a set of sysfs interfaces with which administrato can know about supported drivers and governors and switch them at run time. Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> Signed-off-by: Len Brown <len.brown@intel.com>
2007-10-04 02:58:00 +04:00
/**
sched: idle: Select idle state before stopping the tick In order to address the issue with short idle duration predictions by the idle governor after the scheduler tick has been stopped, reorder the code in cpuidle_idle_call() so that the governor idle state selection runs before tick_nohz_idle_go_idle() and use the "nohz" hint returned by cpuidle_select() to decide whether or not to stop the tick. This isn't straightforward, because menu_select() invokes tick_nohz_get_sleep_length() to get the time to the next timer event and the number returned by the latter comes from __tick_nohz_idle_stop_tick(). Fortunately, however, it is possible to compute that number without actually stopping the tick and with the help of the existing code. Namely, tick_nohz_get_sleep_length() can be made call tick_nohz_next_event(), introduced earlier, to get the time to the next non-highres timer event. If that happens, tick_nohz_next_event() need not be called by __tick_nohz_idle_stop_tick() again. If it turns out that the scheduler tick cannot be stopped going forward or the next timer event is too close for the tick to be stopped, tick_nohz_get_sleep_length() can simply return the time to the next event currently programmed into the corresponding clock event device. In addition to knowing the return value of tick_nohz_next_event(), however, tick_nohz_get_sleep_length() needs to know the time to the next highres timer event, but with the scheduler tick timer excluded, which can be computed with the help of hrtimer_get_next_event(). That minimum of that number and the tick_nohz_next_event() return value is the total time to the next timer event with the assumption that the tick will be stopped. It can be returned to the idle governor which can use it for predicting idle duration (under the assumption that the tick will be stopped) and deciding whether or not it makes sense to stop the tick before putting the CPU into the selected idle state. With the above, the sleep_length field in struct tick_sched is not necessary any more, so drop it. Link: https://bugzilla.kernel.org/show_bug.cgi?id=199227 Reported-by: Doug Smythies <dsmythies@telus.net> Reported-by: Thomas Ilsche <thomas.ilsche@tu-dresden.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
2018-04-04 00:17:11 +03:00
* tick_nohz_get_sleep_length - return the expected length of the current sleep
* @delta_next: duration until the next event if the tick cannot be stopped
cpuidle: consolidate 2.6.22 cpuidle branch into one patch commit e5a16b1f9eec0af7cfa0830304b41c1c0833cf9f Author: Len Brown <len.brown@intel.com> Date: Tue Oct 2 23:44:44 2007 -0400 cpuidle: shrink diff processor_idle.c | 440 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 429 insertions(+), 11 deletions(-) Signed-off-by: Len Brown <len.brown@intel.com> commit dfbb9d5aedfb18848a3e0d6f6e3e4969febb209c Author: Len Brown <len.brown@intel.com> Date: Wed Sep 26 02:17:55 2007 -0400 cpuidle: reduce diff size Reduces the cpuidle processor_idle.c diff vs 2.6.22 from this processor_idle.c | 2006 ++++++++++++++++++++++++++----------------- 1 file changed, 1219 insertions(+), 787 deletions(-) to this: processor_idle.c | 502 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 458 insertions(+), 44 deletions(-) ...for the purpose of making the cpuilde patch less invasive and easier to review. no functional changes. build tested only. Signed-off-by: Len Brown <len.brown@intel.com> commit 889172fc915f5a7fe20f35b133cbd205ce69bf6c Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Sep 13 13:40:05 2007 -0700 cpuidle: Retain old ACPI policy for !CONFIG_CPU_IDLE Retain the old policy in processor_idle, so that when CPU_IDLE is not configured, old C-state policy will still be used. This provides a clean gradual migration path from old ACPI policy to new cpuidle based policy. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 9544a8181edc7ecc33b3bfd69271571f98ed08bc Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Sep 13 13:39:17 2007 -0700 cpuidle: Configure governors by default Quoting Len "Do not give an option to users to shoot themselves in the foot". Remove the configurability of ladder and menu governors as they are needed for default policy of cpuidle. That way users will not be able to have cpuidle without any policy loosing all C-state power savings. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 8975059a2c1e56cfe83d1bcf031bcf4cb39be743 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:27:07 2007 -0400 CPUIDLE: load ACPI properly when CPUIDLE is disabled Change the registration return codes for when CPUIDLE support is not compiled into the kernel. As a result, the ACPI processor driver will load properly even if CPUIDLE is unavailable. However, it may be possible to cleanup the ACPI processor driver further and eliminate some dead code paths. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit e0322e2b58dd1b12ec669bf84693efe0dc2414a8 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:26:06 2007 -0400 CPUIDLE: remove cpuidle_get_bm_activity() Remove cpuidle_get_bm_activity() and updates governors accordingly. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 18a6e770d5c82ba26653e53d240caa617e09e9ab Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:58 2007 -0400 CPUIDLE: max_cstate fix Currently max_cstate is limited to 0, resulting in no idle processor power management on ACPI platforms. This patch restores the value to the array size. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 1fdc0887286179b40ce24bcdbde663172e205ef0 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:40 2007 -0400 CPUIDLE: handle BM detection inside the ACPI Processor driver Update the ACPI processor driver to detect BM activity and limit state entry depth internally, rather than exposing such requirements to CPUIDLE. As a result, CPUIDLE can drop this ACPI-specific interface and become more platform independent. BM activity is now handled much more aggressively than it was in the original implementation, so some testing coverage may be needed to verify that this doesn't introduce any DMA buffer under-run issues. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 0ef38840db666f48e3cdd2b769da676c57228dd9 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:14 2007 -0400 CPUIDLE: menu governor updates Tweak the menu governor to more effectively handle non-timer break events. Non-timer break events are detected by comparing the actual sleep time to the expected sleep time. In future revisions, it may be more reliable to use the timer data structures directly. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit bb4d74fca63fa96cf3ace644b15ae0f12b7df5a1 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:24:40 2007 -0400 CPUIDLE: fix 'current_governor' sysfs entry Allow the "current_governor" sysfs entry to properly handle input terminated with '\n'. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit df3c71559bb69b125f1a48971bf0d17f78bbdf47 Author: Len Brown <len.brown@intel.com> Date: Sun Aug 12 02:00:45 2007 -0400 cpuidle: fix IA64 build (again) Signed-off-by: Len Brown <len.brown@intel.com> commit a02064579e3f9530fd31baae16b1fc46b5a7bca8 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:39:27 2007 -0400 cpuidle: Remove support for runtime changing of max_cstate Remove support for runtime changeability of max_cstate. Drivers can use use latency APIs. max_cstate can still be used as a boot time option and dmi override. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 0912a44b13adf22f5e3f607d263aed23b4910d7e Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:39:16 2007 -0400 cpuidle: Remove ACPI cstate_limit calls from ipw2100 ipw2100 already has code to use accetable_latency interfaces to limit the C-state. Remove the calls to acpi_set_cstate_limit and acpi_get_cstate_limit as they are redundant. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit c649a76e76be6bff1fd770d0a775798813a3f6e0 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:35:39 2007 -0400 cpuidle: compile fix for pause and resume functions Fix the compilation failure when cpuidle is not compiled in. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: Adam Belay <adam.belay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 2305a5920fb8ee6ccec1c62ade05aa8351091d71 Author: Adam Belay <abelay@novell.com> Date: Thu Jul 19 00:49:00 2007 -0400 cpuidle: re-write Some portions have been rewritten to make the code cleaner and lighter weight. The following is a list of changes: 1.) the state name is now included in the sysfs interface 2.) detection, hotplug, and available state modifications are handled by CPUIDLE drivers directly 3.) the CPUIDLE idle handler is only ever installed when at least one cpuidle_device is enabled and ready 4.) the menu governor BM code no longer overflows 5.) the sysfs attributes are now printed as unsigned integers, avoiding negative values 6.) a variety of other small cleanups Also, Idle drivers are no longer swappable during runtime through the CPUIDLE sysfs inteface. On i386 and x86_64 most idle handlers (e.g. poll, mwait, halt, etc.) don't benefit from an infrastructure that supports multiple states, so I think using a more general case idle handler selection mechanism would be cleaner. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit df25b6b56955714e6e24b574d88d1fd11f0c3ee5 Author: Len Brown <len.brown@intel.com> Date: Tue Jul 24 17:08:21 2007 -0400 cpuidle: fix IA64 buid Signed-off-by: Len Brown <len.brown@intel.com> commit fd6ada4c14488755ff7068860078c437431fbccd Author: Adrian Bunk <bunk@stusta.de> Date: Mon Jul 9 11:33:13 2007 -0700 cpuidle: static make cpuidle_replace_governor() static Signed-off-by: Adrian Bunk <bunk@stusta.de> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit c1d4a2cebcadf2429c0c72e1d29aa2a9684c32e0 Author: Adrian Bunk <bunk@stusta.de> Date: Tue Jul 3 00:54:40 2007 -0400 cpuidle: static This patch makes the needlessly global struct menu_governor static. Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit dbf8780c6e8d572c2c273da97ed1cca7608fd999 Author: Andrew Morton <akpm@linux-foundation.org> Date: Tue Jul 3 00:49:14 2007 -0400 export symbol tick_nohz_get_sleep_length ERROR: "tick_nohz_get_sleep_length" [drivers/cpuidle/governors/menu.ko] undefined! ERROR: "tick_nohz_get_idle_jiffies" [drivers/cpuidle/governors/menu.ko] undefined! And please be sure to get your changes to core kernel suitably reviewed. Cc: Adam Belay <abelay@novell.com> Cc: Venki Pallipadi <venkatesh.pallipadi@intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 29f0e248e7017be15f99febf9143a2cef00b2961 Author: Andrew Morton <akpm@linux-foundation.org> Date: Tue Jul 3 00:43:04 2007 -0400 tick.h needs hrtimer.h It uses hrtimers. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit e40cede7d63a029e92712a3fe02faee60cc38fb4 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:40:34 2007 -0400 cpuidle: first round of documentation updates Documentation changes based on Pavel's feedback. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 83b42be2efece386976507555c29e7773a0dfcd1 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:39:25 2007 -0400 cpuidle: add rating to the governors and pick the one with highest rating by default Introduce a governor rating scheme to pick the right governor by default. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit d2a74b8c5e8f22def4709330d4bfc4a29209b71c Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:38:08 2007 -0400 cpuidle: make cpuidle sysfs driver governor switch off by default Make default cpuidle sysfs to show current_governor and current_driver in read-only mode. More elaborate available_governors and available_drivers with writeable current_governor and current_driver interface only appear with "cpuidle_sysfs_switch" boot parameter. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 1f60a0e80bf83cf6b55c8845bbe5596ed8f6307b Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:37:00 2007 -0400 cpuidle: menu governor: change the early break condition Change the C-state early break out algorithm in menu governor. We only look at early breakouts that result in wakeups shorter than idle state's target_residency. If such a breakout is frequent enough, eliminate the particular idle state upto a timeout period. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 45a42095cf64b003b4a69be3ce7f434f97d7af51 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:35:38 2007 -0400 cpuidle: fix uninitialized variable in sysfs routine Fix the uninitialized usage of ret. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 80dca7cdba3e6ee13eae277660873ab9584eb3be Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:34:16 2007 -0400 cpuidle: reenable /proc/acpi//power interface for the time being Keep /proc/acpi/processor/CPU*/power around for a while as powertop depends on it. It will be marked deprecated and removed in future. powertop can use cpuidle interfaces instead. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 589c37c2646c5e3813a51255a5ee1159cb4c33fc Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:32:37 2007 -0400 cpuidle: menu governor and hrtimer compile fix Compile fix for menu governor. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 0ba80bd9ab3ed304cb4f19b722e4cc6740588b5e Author: Len Brown <len.brown@intel.com> Date: Thu May 31 22:51:43 2007 -0400 cpuidle: build fix - cpuidle vs ipw2100 module ERROR: "acpi_set_cstate_limit" [drivers/net/wireless/ipw2100.ko] undefined! Signed-off-by: Len Brown <len.brown@intel.com> commit d7d8fa7f96a7f7682be7c6cc0cc53fa7a18c3b58 Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:47:07 2007 -0400 cpuidle: add the 'menu' governor Here is my first take at implementing an idle PM governor that takes full advantage of NO_HZ. I call it the 'menu' governor because it considers the full list of idle states before each entry. I've kept the implementation fairly simple. It attempts to guess the next residency time and then chooses a state that would meet at least the break-even point between power savings and entry cost. To this end, it selects the deepest idle state that satisfies the following constraints: 1. If the idle time elapsed since bus master activity was detected is below a threshold (currently 20 ms), then limit the selection to C2-type or above. 2. Do not choose a state with a break-even residency that exceeds the expected time remaining until the next timer interrupt. 3. Do not choose a state with a break-even residency that exceeds the elapsed time between the last pair of break events, excluding timer interrupts. This governor has an advantage over "ladder" governor because it proactively checks how much time remains until the next timer interrupt using the tick infrastructure. Also, it handles device interrupt activity more intelligently by not including timer interrupts in break event calculations. Finally, it doesn't make policy decisions using the number of state entries, which can have variable residency times (NO_HZ makes these potentially very large), and instead only considers sleep time deltas. The menu governor can be selected during runtime using the cpuidle sysfs interface like so: "echo "menu" > /sys/devices/system/cpu/cpuidle/current_governor" Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit a4bec7e65aa3b7488b879d971651cc99a6c410fe Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:47:03 2007 -0400 cpuidle: export time until next timer interrupt using NO_HZ Expose information about the time remaining until the next timer interrupt expires by utilizing the dynticks infrastructure. Also modify the main idle loop to allow dynticks to handle non-interrupt break events (e.g. DMA). Finally, expose sleep ticks information to external code. Thomas Gleixner is responsible for much of the code in this patch. However, I've made some additional changes, so I'm probably responsible if there are any bugs or oversights :) Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 2929d8996fbc77f41a5ff86bb67cdde3ca7d2d72 Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:46:58 2007 -0400 cpuidle: governor API changes This patch prepares cpuidle for the menu governor. It adds an optional stage after idle state entry to give the governor an opportunity to check why the state was exited. Also it makes sure the idle loop returns after each state entry, allowing the appropriate dynticks code to run. Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 3a7fd42f9825c3b03e364ca59baa751bb350775f Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Apr 26 00:03:59 2007 -0700 cpuidle: hang fix Prevent hang on x86-64, when ACPI processor driver is added as a module on a system that does not support C-states. x86-64 expects all idle handlers to enable interrupts before returning from idle handler. This is due to enter_idle(), exit_idle() races. Make cpuidle_idle_call() confirm to this when there is no pm_idle_old. Also, cpuidle look at the return values of attch_driver() and set current_driver to NULL if attach fails on all CPUs. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 4893339a142afbd5b7c01ffadfd53d14746e858e Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:09 2007 +0800 cpuidle: add support for max_cstate limit With CPUIDLE framework, the max_cstate (to limit max cpu c-state) parameter is ingored. Some systems require it to ignore C2/C3 and some drivers like ipw require it too. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 43bbbbe1cb998cbd2df656f55bb3bfe30f30e7d1 Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:13 2007 +0800 cpuidle: add cpuidle_fore_redetect_devices API add cpuidle_force_redetect_devices API, which forces all CPU redetect idle states. Next patch will use it. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit d1edadd608f24836def5ec483d2edccfb37b1d19 Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:01 2007 +0800 cpuidle: fix sysfs related issue Fix the cpuidle sysfs issue. a. make kobject dynamicaly allocated b. fixed sysfs init issue to avoid suspend/resume issue Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 7169a5cc0d67b263978859672e86c13c23a5570d Author: Randy Dunlap <randy.dunlap@oracle.com> Date: Wed Mar 28 22:52:53 2007 -0400 cpuidle: 1-bit field must be unsigned A 1-bit bitfield has no room for a sign bit. drivers/cpuidle/governors/ladder.c:54:16: error: dubious bitfield without explicit `signed' or `unsigned' Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 4658620158dc2fbd9e4bcb213c5b6fb5d05ba7d4 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Wed Mar 28 22:52:41 2007 -0400 cpuidle: fix boot hang Patch for cpuidle boot hang reported by Larry Finger here. http://www.ussg.iu.edu/hypermail/linux/kernel/0703.2/2025.html Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Larry Finger <larry.finger@lwfinger.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit c17e168aa6e5fe3851baaae8df2fbc1cf11443a9 Author: Len Brown <len.brown@intel.com> Date: Wed Mar 7 04:37:53 2007 -0500 cpuidle: ladder does not depend on ACPI build fix for CONFIG_ACPI=n In file included from drivers/cpuidle/governors/ladder.c:21: include/acpi/processor.h:88: error: expected specifier-qualifier-list before ‘acpi_integer’ include/acpi/processor.h:106: error: expected specifier-qualifier-list before ‘acpi_integer’ include/acpi/processor.h:168: error: expected specifier-qualifier-list before ‘acpi_handle’ Signed-off-by: Len Brown <len.brown@intel.com> commit 8c91d958246bde68db0c3f0c57b535962ce861cb Author: Adrian Bunk <bunk@stusta.de> Date: Tue Mar 6 02:29:40 2007 -0800 cpuidle: make code static This patch makes the following needlessly global code static: - driver.c: __cpuidle_find_driver() - governor.c: __cpuidle_find_governor() - ladder.c: struct ladder_governor Signed-off-by: Adrian Bunk <bunk@stusta.de> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Adam Belay <abelay@novell.com> Cc: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 0c39dc3187094c72c33ab65a64d2017b21f372d2 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Wed Mar 7 02:38:22 2007 -0500 cpu_idle: fix build break This patch fixes a build breakage with !CONFIG_HOTPLUG_CPU and CONFIG_CPU_IDLE. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 8112e3b115659b07df340ef170515799c0105f82 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Mar 6 02:29:39 2007 -0800 cpuidle: build fix for !CPU_IDLE Fix the compile issues when CPU_IDLE is not configured. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Adam Belay <abelay@novell.com> Cc: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 1eb4431e9599cd25e0d9872f3c2c8986821839dd Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:54:57 2007 -0800 cpuidle take2: Basic documentation for cpuidle Documentation for cpuidle infrastructure Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit ef5f15a8b79123a047285ec2e3899108661df779 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:54:03 2007 -0800 cpuidle take2: Hookup ACPI C-states driver with cpuidle Hookup ACPI C-states onto generic cpuidle infrastructure. drivers/acpi/procesor_idle.c is now a ACPI C-states driver that registers as a driver in cpuidle infrastructure and the policy part is removed from drivers/acpi/processor_idle.c. We use governor in cpuidle instead. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 987196fa82d4db52c407e8c9d5dec884ba602183 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:52:57 2007 -0800 cpuidle take2: Core cpuidle infrastructure Announcing 'cpuidle', a new CPU power management infrastructure to manage idle CPUs in a clean and efficient manner. cpuidle separates out the drivers that can provide support for multiple types of idle states and policy governors that decide on what idle state to use at run time. A cpuidle driver can support multiple idle states based on parameters like varying power consumption, wakeup latency, etc (ACPI C-states for example). A cpuidle governor can be usage model specific (laptop, server, laptop on battery etc). Main advantage of the infrastructure being, it allows independent development of drivers and governors and allows for better CPU power management. A huge thanks to Adam Belay and Shaohua Li who were part of this mini-project since its beginning and are greatly responsible for this patchset. This patch: Core cpuidle infrastructure. Introduces a new abstraction layer for cpuidle: * which manages drivers that can support multiple idles states. Drivers can be generic or particular to specific hardware/platform * allows pluging in multiple policy governors that can take idle state policy decision * The core also has a set of sysfs interfaces with which administrato can know about supported drivers and governors and switch them at run time. Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> Signed-off-by: Len Brown <len.brown@intel.com>
2007-10-04 02:58:00 +04:00
*
* Called from power state control code with interrupts disabled.
*
* The return value of this function and/or the value returned by it through the
* @delta_next pointer can be negative which must be taken into account by its
* callers.
cpuidle: consolidate 2.6.22 cpuidle branch into one patch commit e5a16b1f9eec0af7cfa0830304b41c1c0833cf9f Author: Len Brown <len.brown@intel.com> Date: Tue Oct 2 23:44:44 2007 -0400 cpuidle: shrink diff processor_idle.c | 440 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 429 insertions(+), 11 deletions(-) Signed-off-by: Len Brown <len.brown@intel.com> commit dfbb9d5aedfb18848a3e0d6f6e3e4969febb209c Author: Len Brown <len.brown@intel.com> Date: Wed Sep 26 02:17:55 2007 -0400 cpuidle: reduce diff size Reduces the cpuidle processor_idle.c diff vs 2.6.22 from this processor_idle.c | 2006 ++++++++++++++++++++++++++----------------- 1 file changed, 1219 insertions(+), 787 deletions(-) to this: processor_idle.c | 502 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 458 insertions(+), 44 deletions(-) ...for the purpose of making the cpuilde patch less invasive and easier to review. no functional changes. build tested only. Signed-off-by: Len Brown <len.brown@intel.com> commit 889172fc915f5a7fe20f35b133cbd205ce69bf6c Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Sep 13 13:40:05 2007 -0700 cpuidle: Retain old ACPI policy for !CONFIG_CPU_IDLE Retain the old policy in processor_idle, so that when CPU_IDLE is not configured, old C-state policy will still be used. This provides a clean gradual migration path from old ACPI policy to new cpuidle based policy. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 9544a8181edc7ecc33b3bfd69271571f98ed08bc Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Sep 13 13:39:17 2007 -0700 cpuidle: Configure governors by default Quoting Len "Do not give an option to users to shoot themselves in the foot". Remove the configurability of ladder and menu governors as they are needed for default policy of cpuidle. That way users will not be able to have cpuidle without any policy loosing all C-state power savings. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 8975059a2c1e56cfe83d1bcf031bcf4cb39be743 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:27:07 2007 -0400 CPUIDLE: load ACPI properly when CPUIDLE is disabled Change the registration return codes for when CPUIDLE support is not compiled into the kernel. As a result, the ACPI processor driver will load properly even if CPUIDLE is unavailable. However, it may be possible to cleanup the ACPI processor driver further and eliminate some dead code paths. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit e0322e2b58dd1b12ec669bf84693efe0dc2414a8 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:26:06 2007 -0400 CPUIDLE: remove cpuidle_get_bm_activity() Remove cpuidle_get_bm_activity() and updates governors accordingly. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 18a6e770d5c82ba26653e53d240caa617e09e9ab Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:58 2007 -0400 CPUIDLE: max_cstate fix Currently max_cstate is limited to 0, resulting in no idle processor power management on ACPI platforms. This patch restores the value to the array size. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 1fdc0887286179b40ce24bcdbde663172e205ef0 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:40 2007 -0400 CPUIDLE: handle BM detection inside the ACPI Processor driver Update the ACPI processor driver to detect BM activity and limit state entry depth internally, rather than exposing such requirements to CPUIDLE. As a result, CPUIDLE can drop this ACPI-specific interface and become more platform independent. BM activity is now handled much more aggressively than it was in the original implementation, so some testing coverage may be needed to verify that this doesn't introduce any DMA buffer under-run issues. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 0ef38840db666f48e3cdd2b769da676c57228dd9 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:14 2007 -0400 CPUIDLE: menu governor updates Tweak the menu governor to more effectively handle non-timer break events. Non-timer break events are detected by comparing the actual sleep time to the expected sleep time. In future revisions, it may be more reliable to use the timer data structures directly. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit bb4d74fca63fa96cf3ace644b15ae0f12b7df5a1 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:24:40 2007 -0400 CPUIDLE: fix 'current_governor' sysfs entry Allow the "current_governor" sysfs entry to properly handle input terminated with '\n'. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit df3c71559bb69b125f1a48971bf0d17f78bbdf47 Author: Len Brown <len.brown@intel.com> Date: Sun Aug 12 02:00:45 2007 -0400 cpuidle: fix IA64 build (again) Signed-off-by: Len Brown <len.brown@intel.com> commit a02064579e3f9530fd31baae16b1fc46b5a7bca8 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:39:27 2007 -0400 cpuidle: Remove support for runtime changing of max_cstate Remove support for runtime changeability of max_cstate. Drivers can use use latency APIs. max_cstate can still be used as a boot time option and dmi override. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 0912a44b13adf22f5e3f607d263aed23b4910d7e Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:39:16 2007 -0400 cpuidle: Remove ACPI cstate_limit calls from ipw2100 ipw2100 already has code to use accetable_latency interfaces to limit the C-state. Remove the calls to acpi_set_cstate_limit and acpi_get_cstate_limit as they are redundant. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit c649a76e76be6bff1fd770d0a775798813a3f6e0 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:35:39 2007 -0400 cpuidle: compile fix for pause and resume functions Fix the compilation failure when cpuidle is not compiled in. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: Adam Belay <adam.belay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 2305a5920fb8ee6ccec1c62ade05aa8351091d71 Author: Adam Belay <abelay@novell.com> Date: Thu Jul 19 00:49:00 2007 -0400 cpuidle: re-write Some portions have been rewritten to make the code cleaner and lighter weight. The following is a list of changes: 1.) the state name is now included in the sysfs interface 2.) detection, hotplug, and available state modifications are handled by CPUIDLE drivers directly 3.) the CPUIDLE idle handler is only ever installed when at least one cpuidle_device is enabled and ready 4.) the menu governor BM code no longer overflows 5.) the sysfs attributes are now printed as unsigned integers, avoiding negative values 6.) a variety of other small cleanups Also, Idle drivers are no longer swappable during runtime through the CPUIDLE sysfs inteface. On i386 and x86_64 most idle handlers (e.g. poll, mwait, halt, etc.) don't benefit from an infrastructure that supports multiple states, so I think using a more general case idle handler selection mechanism would be cleaner. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit df25b6b56955714e6e24b574d88d1fd11f0c3ee5 Author: Len Brown <len.brown@intel.com> Date: Tue Jul 24 17:08:21 2007 -0400 cpuidle: fix IA64 buid Signed-off-by: Len Brown <len.brown@intel.com> commit fd6ada4c14488755ff7068860078c437431fbccd Author: Adrian Bunk <bunk@stusta.de> Date: Mon Jul 9 11:33:13 2007 -0700 cpuidle: static make cpuidle_replace_governor() static Signed-off-by: Adrian Bunk <bunk@stusta.de> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit c1d4a2cebcadf2429c0c72e1d29aa2a9684c32e0 Author: Adrian Bunk <bunk@stusta.de> Date: Tue Jul 3 00:54:40 2007 -0400 cpuidle: static This patch makes the needlessly global struct menu_governor static. Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit dbf8780c6e8d572c2c273da97ed1cca7608fd999 Author: Andrew Morton <akpm@linux-foundation.org> Date: Tue Jul 3 00:49:14 2007 -0400 export symbol tick_nohz_get_sleep_length ERROR: "tick_nohz_get_sleep_length" [drivers/cpuidle/governors/menu.ko] undefined! ERROR: "tick_nohz_get_idle_jiffies" [drivers/cpuidle/governors/menu.ko] undefined! And please be sure to get your changes to core kernel suitably reviewed. Cc: Adam Belay <abelay@novell.com> Cc: Venki Pallipadi <venkatesh.pallipadi@intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 29f0e248e7017be15f99febf9143a2cef00b2961 Author: Andrew Morton <akpm@linux-foundation.org> Date: Tue Jul 3 00:43:04 2007 -0400 tick.h needs hrtimer.h It uses hrtimers. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit e40cede7d63a029e92712a3fe02faee60cc38fb4 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:40:34 2007 -0400 cpuidle: first round of documentation updates Documentation changes based on Pavel's feedback. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 83b42be2efece386976507555c29e7773a0dfcd1 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:39:25 2007 -0400 cpuidle: add rating to the governors and pick the one with highest rating by default Introduce a governor rating scheme to pick the right governor by default. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit d2a74b8c5e8f22def4709330d4bfc4a29209b71c Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:38:08 2007 -0400 cpuidle: make cpuidle sysfs driver governor switch off by default Make default cpuidle sysfs to show current_governor and current_driver in read-only mode. More elaborate available_governors and available_drivers with writeable current_governor and current_driver interface only appear with "cpuidle_sysfs_switch" boot parameter. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 1f60a0e80bf83cf6b55c8845bbe5596ed8f6307b Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:37:00 2007 -0400 cpuidle: menu governor: change the early break condition Change the C-state early break out algorithm in menu governor. We only look at early breakouts that result in wakeups shorter than idle state's target_residency. If such a breakout is frequent enough, eliminate the particular idle state upto a timeout period. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 45a42095cf64b003b4a69be3ce7f434f97d7af51 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:35:38 2007 -0400 cpuidle: fix uninitialized variable in sysfs routine Fix the uninitialized usage of ret. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 80dca7cdba3e6ee13eae277660873ab9584eb3be Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:34:16 2007 -0400 cpuidle: reenable /proc/acpi//power interface for the time being Keep /proc/acpi/processor/CPU*/power around for a while as powertop depends on it. It will be marked deprecated and removed in future. powertop can use cpuidle interfaces instead. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 589c37c2646c5e3813a51255a5ee1159cb4c33fc Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:32:37 2007 -0400 cpuidle: menu governor and hrtimer compile fix Compile fix for menu governor. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 0ba80bd9ab3ed304cb4f19b722e4cc6740588b5e Author: Len Brown <len.brown@intel.com> Date: Thu May 31 22:51:43 2007 -0400 cpuidle: build fix - cpuidle vs ipw2100 module ERROR: "acpi_set_cstate_limit" [drivers/net/wireless/ipw2100.ko] undefined! Signed-off-by: Len Brown <len.brown@intel.com> commit d7d8fa7f96a7f7682be7c6cc0cc53fa7a18c3b58 Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:47:07 2007 -0400 cpuidle: add the 'menu' governor Here is my first take at implementing an idle PM governor that takes full advantage of NO_HZ. I call it the 'menu' governor because it considers the full list of idle states before each entry. I've kept the implementation fairly simple. It attempts to guess the next residency time and then chooses a state that would meet at least the break-even point between power savings and entry cost. To this end, it selects the deepest idle state that satisfies the following constraints: 1. If the idle time elapsed since bus master activity was detected is below a threshold (currently 20 ms), then limit the selection to C2-type or above. 2. Do not choose a state with a break-even residency that exceeds the expected time remaining until the next timer interrupt. 3. Do not choose a state with a break-even residency that exceeds the elapsed time between the last pair of break events, excluding timer interrupts. This governor has an advantage over "ladder" governor because it proactively checks how much time remains until the next timer interrupt using the tick infrastructure. Also, it handles device interrupt activity more intelligently by not including timer interrupts in break event calculations. Finally, it doesn't make policy decisions using the number of state entries, which can have variable residency times (NO_HZ makes these potentially very large), and instead only considers sleep time deltas. The menu governor can be selected during runtime using the cpuidle sysfs interface like so: "echo "menu" > /sys/devices/system/cpu/cpuidle/current_governor" Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit a4bec7e65aa3b7488b879d971651cc99a6c410fe Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:47:03 2007 -0400 cpuidle: export time until next timer interrupt using NO_HZ Expose information about the time remaining until the next timer interrupt expires by utilizing the dynticks infrastructure. Also modify the main idle loop to allow dynticks to handle non-interrupt break events (e.g. DMA). Finally, expose sleep ticks information to external code. Thomas Gleixner is responsible for much of the code in this patch. However, I've made some additional changes, so I'm probably responsible if there are any bugs or oversights :) Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 2929d8996fbc77f41a5ff86bb67cdde3ca7d2d72 Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:46:58 2007 -0400 cpuidle: governor API changes This patch prepares cpuidle for the menu governor. It adds an optional stage after idle state entry to give the governor an opportunity to check why the state was exited. Also it makes sure the idle loop returns after each state entry, allowing the appropriate dynticks code to run. Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 3a7fd42f9825c3b03e364ca59baa751bb350775f Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Apr 26 00:03:59 2007 -0700 cpuidle: hang fix Prevent hang on x86-64, when ACPI processor driver is added as a module on a system that does not support C-states. x86-64 expects all idle handlers to enable interrupts before returning from idle handler. This is due to enter_idle(), exit_idle() races. Make cpuidle_idle_call() confirm to this when there is no pm_idle_old. Also, cpuidle look at the return values of attch_driver() and set current_driver to NULL if attach fails on all CPUs. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 4893339a142afbd5b7c01ffadfd53d14746e858e Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:09 2007 +0800 cpuidle: add support for max_cstate limit With CPUIDLE framework, the max_cstate (to limit max cpu c-state) parameter is ingored. Some systems require it to ignore C2/C3 and some drivers like ipw require it too. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 43bbbbe1cb998cbd2df656f55bb3bfe30f30e7d1 Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:13 2007 +0800 cpuidle: add cpuidle_fore_redetect_devices API add cpuidle_force_redetect_devices API, which forces all CPU redetect idle states. Next patch will use it. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit d1edadd608f24836def5ec483d2edccfb37b1d19 Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:01 2007 +0800 cpuidle: fix sysfs related issue Fix the cpuidle sysfs issue. a. make kobject dynamicaly allocated b. fixed sysfs init issue to avoid suspend/resume issue Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 7169a5cc0d67b263978859672e86c13c23a5570d Author: Randy Dunlap <randy.dunlap@oracle.com> Date: Wed Mar 28 22:52:53 2007 -0400 cpuidle: 1-bit field must be unsigned A 1-bit bitfield has no room for a sign bit. drivers/cpuidle/governors/ladder.c:54:16: error: dubious bitfield without explicit `signed' or `unsigned' Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 4658620158dc2fbd9e4bcb213c5b6fb5d05ba7d4 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Wed Mar 28 22:52:41 2007 -0400 cpuidle: fix boot hang Patch for cpuidle boot hang reported by Larry Finger here. http://www.ussg.iu.edu/hypermail/linux/kernel/0703.2/2025.html Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Larry Finger <larry.finger@lwfinger.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit c17e168aa6e5fe3851baaae8df2fbc1cf11443a9 Author: Len Brown <len.brown@intel.com> Date: Wed Mar 7 04:37:53 2007 -0500 cpuidle: ladder does not depend on ACPI build fix for CONFIG_ACPI=n In file included from drivers/cpuidle/governors/ladder.c:21: include/acpi/processor.h:88: error: expected specifier-qualifier-list before ‘acpi_integer’ include/acpi/processor.h:106: error: expected specifier-qualifier-list before ‘acpi_integer’ include/acpi/processor.h:168: error: expected specifier-qualifier-list before ‘acpi_handle’ Signed-off-by: Len Brown <len.brown@intel.com> commit 8c91d958246bde68db0c3f0c57b535962ce861cb Author: Adrian Bunk <bunk@stusta.de> Date: Tue Mar 6 02:29:40 2007 -0800 cpuidle: make code static This patch makes the following needlessly global code static: - driver.c: __cpuidle_find_driver() - governor.c: __cpuidle_find_governor() - ladder.c: struct ladder_governor Signed-off-by: Adrian Bunk <bunk@stusta.de> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Adam Belay <abelay@novell.com> Cc: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 0c39dc3187094c72c33ab65a64d2017b21f372d2 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Wed Mar 7 02:38:22 2007 -0500 cpu_idle: fix build break This patch fixes a build breakage with !CONFIG_HOTPLUG_CPU and CONFIG_CPU_IDLE. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 8112e3b115659b07df340ef170515799c0105f82 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Mar 6 02:29:39 2007 -0800 cpuidle: build fix for !CPU_IDLE Fix the compile issues when CPU_IDLE is not configured. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Adam Belay <abelay@novell.com> Cc: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 1eb4431e9599cd25e0d9872f3c2c8986821839dd Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:54:57 2007 -0800 cpuidle take2: Basic documentation for cpuidle Documentation for cpuidle infrastructure Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit ef5f15a8b79123a047285ec2e3899108661df779 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:54:03 2007 -0800 cpuidle take2: Hookup ACPI C-states driver with cpuidle Hookup ACPI C-states onto generic cpuidle infrastructure. drivers/acpi/procesor_idle.c is now a ACPI C-states driver that registers as a driver in cpuidle infrastructure and the policy part is removed from drivers/acpi/processor_idle.c. We use governor in cpuidle instead. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 987196fa82d4db52c407e8c9d5dec884ba602183 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:52:57 2007 -0800 cpuidle take2: Core cpuidle infrastructure Announcing 'cpuidle', a new CPU power management infrastructure to manage idle CPUs in a clean and efficient manner. cpuidle separates out the drivers that can provide support for multiple types of idle states and policy governors that decide on what idle state to use at run time. A cpuidle driver can support multiple idle states based on parameters like varying power consumption, wakeup latency, etc (ACPI C-states for example). A cpuidle governor can be usage model specific (laptop, server, laptop on battery etc). Main advantage of the infrastructure being, it allows independent development of drivers and governors and allows for better CPU power management. A huge thanks to Adam Belay and Shaohua Li who were part of this mini-project since its beginning and are greatly responsible for this patchset. This patch: Core cpuidle infrastructure. Introduces a new abstraction layer for cpuidle: * which manages drivers that can support multiple idles states. Drivers can be generic or particular to specific hardware/platform * allows pluging in multiple policy governors that can take idle state policy decision * The core also has a set of sysfs interfaces with which administrato can know about supported drivers and governors and switch them at run time. Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> Signed-off-by: Len Brown <len.brown@intel.com>
2007-10-04 02:58:00 +04:00
*/
ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
cpuidle: consolidate 2.6.22 cpuidle branch into one patch commit e5a16b1f9eec0af7cfa0830304b41c1c0833cf9f Author: Len Brown <len.brown@intel.com> Date: Tue Oct 2 23:44:44 2007 -0400 cpuidle: shrink diff processor_idle.c | 440 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 429 insertions(+), 11 deletions(-) Signed-off-by: Len Brown <len.brown@intel.com> commit dfbb9d5aedfb18848a3e0d6f6e3e4969febb209c Author: Len Brown <len.brown@intel.com> Date: Wed Sep 26 02:17:55 2007 -0400 cpuidle: reduce diff size Reduces the cpuidle processor_idle.c diff vs 2.6.22 from this processor_idle.c | 2006 ++++++++++++++++++++++++++----------------- 1 file changed, 1219 insertions(+), 787 deletions(-) to this: processor_idle.c | 502 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 458 insertions(+), 44 deletions(-) ...for the purpose of making the cpuilde patch less invasive and easier to review. no functional changes. build tested only. Signed-off-by: Len Brown <len.brown@intel.com> commit 889172fc915f5a7fe20f35b133cbd205ce69bf6c Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Sep 13 13:40:05 2007 -0700 cpuidle: Retain old ACPI policy for !CONFIG_CPU_IDLE Retain the old policy in processor_idle, so that when CPU_IDLE is not configured, old C-state policy will still be used. This provides a clean gradual migration path from old ACPI policy to new cpuidle based policy. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 9544a8181edc7ecc33b3bfd69271571f98ed08bc Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Sep 13 13:39:17 2007 -0700 cpuidle: Configure governors by default Quoting Len "Do not give an option to users to shoot themselves in the foot". Remove the configurability of ladder and menu governors as they are needed for default policy of cpuidle. That way users will not be able to have cpuidle without any policy loosing all C-state power savings. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 8975059a2c1e56cfe83d1bcf031bcf4cb39be743 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:27:07 2007 -0400 CPUIDLE: load ACPI properly when CPUIDLE is disabled Change the registration return codes for when CPUIDLE support is not compiled into the kernel. As a result, the ACPI processor driver will load properly even if CPUIDLE is unavailable. However, it may be possible to cleanup the ACPI processor driver further and eliminate some dead code paths. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit e0322e2b58dd1b12ec669bf84693efe0dc2414a8 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:26:06 2007 -0400 CPUIDLE: remove cpuidle_get_bm_activity() Remove cpuidle_get_bm_activity() and updates governors accordingly. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 18a6e770d5c82ba26653e53d240caa617e09e9ab Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:58 2007 -0400 CPUIDLE: max_cstate fix Currently max_cstate is limited to 0, resulting in no idle processor power management on ACPI platforms. This patch restores the value to the array size. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 1fdc0887286179b40ce24bcdbde663172e205ef0 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:40 2007 -0400 CPUIDLE: handle BM detection inside the ACPI Processor driver Update the ACPI processor driver to detect BM activity and limit state entry depth internally, rather than exposing such requirements to CPUIDLE. As a result, CPUIDLE can drop this ACPI-specific interface and become more platform independent. BM activity is now handled much more aggressively than it was in the original implementation, so some testing coverage may be needed to verify that this doesn't introduce any DMA buffer under-run issues. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 0ef38840db666f48e3cdd2b769da676c57228dd9 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:14 2007 -0400 CPUIDLE: menu governor updates Tweak the menu governor to more effectively handle non-timer break events. Non-timer break events are detected by comparing the actual sleep time to the expected sleep time. In future revisions, it may be more reliable to use the timer data structures directly. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit bb4d74fca63fa96cf3ace644b15ae0f12b7df5a1 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:24:40 2007 -0400 CPUIDLE: fix 'current_governor' sysfs entry Allow the "current_governor" sysfs entry to properly handle input terminated with '\n'. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit df3c71559bb69b125f1a48971bf0d17f78bbdf47 Author: Len Brown <len.brown@intel.com> Date: Sun Aug 12 02:00:45 2007 -0400 cpuidle: fix IA64 build (again) Signed-off-by: Len Brown <len.brown@intel.com> commit a02064579e3f9530fd31baae16b1fc46b5a7bca8 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:39:27 2007 -0400 cpuidle: Remove support for runtime changing of max_cstate Remove support for runtime changeability of max_cstate. Drivers can use use latency APIs. max_cstate can still be used as a boot time option and dmi override. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 0912a44b13adf22f5e3f607d263aed23b4910d7e Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:39:16 2007 -0400 cpuidle: Remove ACPI cstate_limit calls from ipw2100 ipw2100 already has code to use accetable_latency interfaces to limit the C-state. Remove the calls to acpi_set_cstate_limit and acpi_get_cstate_limit as they are redundant. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit c649a76e76be6bff1fd770d0a775798813a3f6e0 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:35:39 2007 -0400 cpuidle: compile fix for pause and resume functions Fix the compilation failure when cpuidle is not compiled in. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: Adam Belay <adam.belay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 2305a5920fb8ee6ccec1c62ade05aa8351091d71 Author: Adam Belay <abelay@novell.com> Date: Thu Jul 19 00:49:00 2007 -0400 cpuidle: re-write Some portions have been rewritten to make the code cleaner and lighter weight. The following is a list of changes: 1.) the state name is now included in the sysfs interface 2.) detection, hotplug, and available state modifications are handled by CPUIDLE drivers directly 3.) the CPUIDLE idle handler is only ever installed when at least one cpuidle_device is enabled and ready 4.) the menu governor BM code no longer overflows 5.) the sysfs attributes are now printed as unsigned integers, avoiding negative values 6.) a variety of other small cleanups Also, Idle drivers are no longer swappable during runtime through the CPUIDLE sysfs inteface. On i386 and x86_64 most idle handlers (e.g. poll, mwait, halt, etc.) don't benefit from an infrastructure that supports multiple states, so I think using a more general case idle handler selection mechanism would be cleaner. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit df25b6b56955714e6e24b574d88d1fd11f0c3ee5 Author: Len Brown <len.brown@intel.com> Date: Tue Jul 24 17:08:21 2007 -0400 cpuidle: fix IA64 buid Signed-off-by: Len Brown <len.brown@intel.com> commit fd6ada4c14488755ff7068860078c437431fbccd Author: Adrian Bunk <bunk@stusta.de> Date: Mon Jul 9 11:33:13 2007 -0700 cpuidle: static make cpuidle_replace_governor() static Signed-off-by: Adrian Bunk <bunk@stusta.de> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit c1d4a2cebcadf2429c0c72e1d29aa2a9684c32e0 Author: Adrian Bunk <bunk@stusta.de> Date: Tue Jul 3 00:54:40 2007 -0400 cpuidle: static This patch makes the needlessly global struct menu_governor static. Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit dbf8780c6e8d572c2c273da97ed1cca7608fd999 Author: Andrew Morton <akpm@linux-foundation.org> Date: Tue Jul 3 00:49:14 2007 -0400 export symbol tick_nohz_get_sleep_length ERROR: "tick_nohz_get_sleep_length" [drivers/cpuidle/governors/menu.ko] undefined! ERROR: "tick_nohz_get_idle_jiffies" [drivers/cpuidle/governors/menu.ko] undefined! And please be sure to get your changes to core kernel suitably reviewed. Cc: Adam Belay <abelay@novell.com> Cc: Venki Pallipadi <venkatesh.pallipadi@intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 29f0e248e7017be15f99febf9143a2cef00b2961 Author: Andrew Morton <akpm@linux-foundation.org> Date: Tue Jul 3 00:43:04 2007 -0400 tick.h needs hrtimer.h It uses hrtimers. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit e40cede7d63a029e92712a3fe02faee60cc38fb4 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:40:34 2007 -0400 cpuidle: first round of documentation updates Documentation changes based on Pavel's feedback. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 83b42be2efece386976507555c29e7773a0dfcd1 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:39:25 2007 -0400 cpuidle: add rating to the governors and pick the one with highest rating by default Introduce a governor rating scheme to pick the right governor by default. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit d2a74b8c5e8f22def4709330d4bfc4a29209b71c Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:38:08 2007 -0400 cpuidle: make cpuidle sysfs driver governor switch off by default Make default cpuidle sysfs to show current_governor and current_driver in read-only mode. More elaborate available_governors and available_drivers with writeable current_governor and current_driver interface only appear with "cpuidle_sysfs_switch" boot parameter. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 1f60a0e80bf83cf6b55c8845bbe5596ed8f6307b Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:37:00 2007 -0400 cpuidle: menu governor: change the early break condition Change the C-state early break out algorithm in menu governor. We only look at early breakouts that result in wakeups shorter than idle state's target_residency. If such a breakout is frequent enough, eliminate the particular idle state upto a timeout period. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 45a42095cf64b003b4a69be3ce7f434f97d7af51 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:35:38 2007 -0400 cpuidle: fix uninitialized variable in sysfs routine Fix the uninitialized usage of ret. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 80dca7cdba3e6ee13eae277660873ab9584eb3be Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:34:16 2007 -0400 cpuidle: reenable /proc/acpi//power interface for the time being Keep /proc/acpi/processor/CPU*/power around for a while as powertop depends on it. It will be marked deprecated and removed in future. powertop can use cpuidle interfaces instead. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 589c37c2646c5e3813a51255a5ee1159cb4c33fc Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:32:37 2007 -0400 cpuidle: menu governor and hrtimer compile fix Compile fix for menu governor. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 0ba80bd9ab3ed304cb4f19b722e4cc6740588b5e Author: Len Brown <len.brown@intel.com> Date: Thu May 31 22:51:43 2007 -0400 cpuidle: build fix - cpuidle vs ipw2100 module ERROR: "acpi_set_cstate_limit" [drivers/net/wireless/ipw2100.ko] undefined! Signed-off-by: Len Brown <len.brown@intel.com> commit d7d8fa7f96a7f7682be7c6cc0cc53fa7a18c3b58 Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:47:07 2007 -0400 cpuidle: add the 'menu' governor Here is my first take at implementing an idle PM governor that takes full advantage of NO_HZ. I call it the 'menu' governor because it considers the full list of idle states before each entry. I've kept the implementation fairly simple. It attempts to guess the next residency time and then chooses a state that would meet at least the break-even point between power savings and entry cost. To this end, it selects the deepest idle state that satisfies the following constraints: 1. If the idle time elapsed since bus master activity was detected is below a threshold (currently 20 ms), then limit the selection to C2-type or above. 2. Do not choose a state with a break-even residency that exceeds the expected time remaining until the next timer interrupt. 3. Do not choose a state with a break-even residency that exceeds the elapsed time between the last pair of break events, excluding timer interrupts. This governor has an advantage over "ladder" governor because it proactively checks how much time remains until the next timer interrupt using the tick infrastructure. Also, it handles device interrupt activity more intelligently by not including timer interrupts in break event calculations. Finally, it doesn't make policy decisions using the number of state entries, which can have variable residency times (NO_HZ makes these potentially very large), and instead only considers sleep time deltas. The menu governor can be selected during runtime using the cpuidle sysfs interface like so: "echo "menu" > /sys/devices/system/cpu/cpuidle/current_governor" Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit a4bec7e65aa3b7488b879d971651cc99a6c410fe Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:47:03 2007 -0400 cpuidle: export time until next timer interrupt using NO_HZ Expose information about the time remaining until the next timer interrupt expires by utilizing the dynticks infrastructure. Also modify the main idle loop to allow dynticks to handle non-interrupt break events (e.g. DMA). Finally, expose sleep ticks information to external code. Thomas Gleixner is responsible for much of the code in this patch. However, I've made some additional changes, so I'm probably responsible if there are any bugs or oversights :) Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 2929d8996fbc77f41a5ff86bb67cdde3ca7d2d72 Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:46:58 2007 -0400 cpuidle: governor API changes This patch prepares cpuidle for the menu governor. It adds an optional stage after idle state entry to give the governor an opportunity to check why the state was exited. Also it makes sure the idle loop returns after each state entry, allowing the appropriate dynticks code to run. Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 3a7fd42f9825c3b03e364ca59baa751bb350775f Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Apr 26 00:03:59 2007 -0700 cpuidle: hang fix Prevent hang on x86-64, when ACPI processor driver is added as a module on a system that does not support C-states. x86-64 expects all idle handlers to enable interrupts before returning from idle handler. This is due to enter_idle(), exit_idle() races. Make cpuidle_idle_call() confirm to this when there is no pm_idle_old. Also, cpuidle look at the return values of attch_driver() and set current_driver to NULL if attach fails on all CPUs. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 4893339a142afbd5b7c01ffadfd53d14746e858e Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:09 2007 +0800 cpuidle: add support for max_cstate limit With CPUIDLE framework, the max_cstate (to limit max cpu c-state) parameter is ingored. Some systems require it to ignore C2/C3 and some drivers like ipw require it too. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 43bbbbe1cb998cbd2df656f55bb3bfe30f30e7d1 Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:13 2007 +0800 cpuidle: add cpuidle_fore_redetect_devices API add cpuidle_force_redetect_devices API, which forces all CPU redetect idle states. Next patch will use it. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit d1edadd608f24836def5ec483d2edccfb37b1d19 Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:01 2007 +0800 cpuidle: fix sysfs related issue Fix the cpuidle sysfs issue. a. make kobject dynamicaly allocated b. fixed sysfs init issue to avoid suspend/resume issue Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 7169a5cc0d67b263978859672e86c13c23a5570d Author: Randy Dunlap <randy.dunlap@oracle.com> Date: Wed Mar 28 22:52:53 2007 -0400 cpuidle: 1-bit field must be unsigned A 1-bit bitfield has no room for a sign bit. drivers/cpuidle/governors/ladder.c:54:16: error: dubious bitfield without explicit `signed' or `unsigned' Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 4658620158dc2fbd9e4bcb213c5b6fb5d05ba7d4 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Wed Mar 28 22:52:41 2007 -0400 cpuidle: fix boot hang Patch for cpuidle boot hang reported by Larry Finger here. http://www.ussg.iu.edu/hypermail/linux/kernel/0703.2/2025.html Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Larry Finger <larry.finger@lwfinger.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit c17e168aa6e5fe3851baaae8df2fbc1cf11443a9 Author: Len Brown <len.brown@intel.com> Date: Wed Mar 7 04:37:53 2007 -0500 cpuidle: ladder does not depend on ACPI build fix for CONFIG_ACPI=n In file included from drivers/cpuidle/governors/ladder.c:21: include/acpi/processor.h:88: error: expected specifier-qualifier-list before ‘acpi_integer’ include/acpi/processor.h:106: error: expected specifier-qualifier-list before ‘acpi_integer’ include/acpi/processor.h:168: error: expected specifier-qualifier-list before ‘acpi_handle’ Signed-off-by: Len Brown <len.brown@intel.com> commit 8c91d958246bde68db0c3f0c57b535962ce861cb Author: Adrian Bunk <bunk@stusta.de> Date: Tue Mar 6 02:29:40 2007 -0800 cpuidle: make code static This patch makes the following needlessly global code static: - driver.c: __cpuidle_find_driver() - governor.c: __cpuidle_find_governor() - ladder.c: struct ladder_governor Signed-off-by: Adrian Bunk <bunk@stusta.de> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Adam Belay <abelay@novell.com> Cc: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 0c39dc3187094c72c33ab65a64d2017b21f372d2 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Wed Mar 7 02:38:22 2007 -0500 cpu_idle: fix build break This patch fixes a build breakage with !CONFIG_HOTPLUG_CPU and CONFIG_CPU_IDLE. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 8112e3b115659b07df340ef170515799c0105f82 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Mar 6 02:29:39 2007 -0800 cpuidle: build fix for !CPU_IDLE Fix the compile issues when CPU_IDLE is not configured. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Adam Belay <abelay@novell.com> Cc: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 1eb4431e9599cd25e0d9872f3c2c8986821839dd Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:54:57 2007 -0800 cpuidle take2: Basic documentation for cpuidle Documentation for cpuidle infrastructure Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit ef5f15a8b79123a047285ec2e3899108661df779 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:54:03 2007 -0800 cpuidle take2: Hookup ACPI C-states driver with cpuidle Hookup ACPI C-states onto generic cpuidle infrastructure. drivers/acpi/procesor_idle.c is now a ACPI C-states driver that registers as a driver in cpuidle infrastructure and the policy part is removed from drivers/acpi/processor_idle.c. We use governor in cpuidle instead. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 987196fa82d4db52c407e8c9d5dec884ba602183 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:52:57 2007 -0800 cpuidle take2: Core cpuidle infrastructure Announcing 'cpuidle', a new CPU power management infrastructure to manage idle CPUs in a clean and efficient manner. cpuidle separates out the drivers that can provide support for multiple types of idle states and policy governors that decide on what idle state to use at run time. A cpuidle driver can support multiple idle states based on parameters like varying power consumption, wakeup latency, etc (ACPI C-states for example). A cpuidle governor can be usage model specific (laptop, server, laptop on battery etc). Main advantage of the infrastructure being, it allows independent development of drivers and governors and allows for better CPU power management. A huge thanks to Adam Belay and Shaohua Li who were part of this mini-project since its beginning and are greatly responsible for this patchset. This patch: Core cpuidle infrastructure. Introduces a new abstraction layer for cpuidle: * which manages drivers that can support multiple idles states. Drivers can be generic or particular to specific hardware/platform * allows pluging in multiple policy governors that can take idle state policy decision * The core also has a set of sysfs interfaces with which administrato can know about supported drivers and governors and switch them at run time. Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> Signed-off-by: Len Brown <len.brown@intel.com>
2007-10-04 02:58:00 +04:00
{
sched: idle: Select idle state before stopping the tick In order to address the issue with short idle duration predictions by the idle governor after the scheduler tick has been stopped, reorder the code in cpuidle_idle_call() so that the governor idle state selection runs before tick_nohz_idle_go_idle() and use the "nohz" hint returned by cpuidle_select() to decide whether or not to stop the tick. This isn't straightforward, because menu_select() invokes tick_nohz_get_sleep_length() to get the time to the next timer event and the number returned by the latter comes from __tick_nohz_idle_stop_tick(). Fortunately, however, it is possible to compute that number without actually stopping the tick and with the help of the existing code. Namely, tick_nohz_get_sleep_length() can be made call tick_nohz_next_event(), introduced earlier, to get the time to the next non-highres timer event. If that happens, tick_nohz_next_event() need not be called by __tick_nohz_idle_stop_tick() again. If it turns out that the scheduler tick cannot be stopped going forward or the next timer event is too close for the tick to be stopped, tick_nohz_get_sleep_length() can simply return the time to the next event currently programmed into the corresponding clock event device. In addition to knowing the return value of tick_nohz_next_event(), however, tick_nohz_get_sleep_length() needs to know the time to the next highres timer event, but with the scheduler tick timer excluded, which can be computed with the help of hrtimer_get_next_event(). That minimum of that number and the tick_nohz_next_event() return value is the total time to the next timer event with the assumption that the tick will be stopped. It can be returned to the idle governor which can use it for predicting idle duration (under the assumption that the tick will be stopped) and deciding whether or not it makes sense to stop the tick before putting the CPU into the selected idle state. With the above, the sleep_length field in struct tick_sched is not necessary any more, so drop it. Link: https://bugzilla.kernel.org/show_bug.cgi?id=199227 Reported-by: Doug Smythies <dsmythies@telus.net> Reported-by: Thomas Ilsche <thomas.ilsche@tu-dresden.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
2018-04-04 00:17:11 +03:00
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
sched: idle: Select idle state before stopping the tick In order to address the issue with short idle duration predictions by the idle governor after the scheduler tick has been stopped, reorder the code in cpuidle_idle_call() so that the governor idle state selection runs before tick_nohz_idle_go_idle() and use the "nohz" hint returned by cpuidle_select() to decide whether or not to stop the tick. This isn't straightforward, because menu_select() invokes tick_nohz_get_sleep_length() to get the time to the next timer event and the number returned by the latter comes from __tick_nohz_idle_stop_tick(). Fortunately, however, it is possible to compute that number without actually stopping the tick and with the help of the existing code. Namely, tick_nohz_get_sleep_length() can be made call tick_nohz_next_event(), introduced earlier, to get the time to the next non-highres timer event. If that happens, tick_nohz_next_event() need not be called by __tick_nohz_idle_stop_tick() again. If it turns out that the scheduler tick cannot be stopped going forward or the next timer event is too close for the tick to be stopped, tick_nohz_get_sleep_length() can simply return the time to the next event currently programmed into the corresponding clock event device. In addition to knowing the return value of tick_nohz_next_event(), however, tick_nohz_get_sleep_length() needs to know the time to the next highres timer event, but with the scheduler tick timer excluded, which can be computed with the help of hrtimer_get_next_event(). That minimum of that number and the tick_nohz_next_event() return value is the total time to the next timer event with the assumption that the tick will be stopped. It can be returned to the idle governor which can use it for predicting idle duration (under the assumption that the tick will be stopped) and deciding whether or not it makes sense to stop the tick before putting the CPU into the selected idle state. With the above, the sleep_length field in struct tick_sched is not necessary any more, so drop it. Link: https://bugzilla.kernel.org/show_bug.cgi?id=199227 Reported-by: Doug Smythies <dsmythies@telus.net> Reported-by: Thomas Ilsche <thomas.ilsche@tu-dresden.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
2018-04-04 00:17:11 +03:00
int cpu = smp_processor_id();
/*
* The idle entry time is expected to be a sufficient approximation of
* the current time at this point.
*/
ktime_t now = ts->idle_entrytime;
ktime_t next_event;
WARN_ON_ONCE(!ts->inidle);
*delta_next = ktime_sub(dev->next_event, now);
sched: idle: Select idle state before stopping the tick In order to address the issue with short idle duration predictions by the idle governor after the scheduler tick has been stopped, reorder the code in cpuidle_idle_call() so that the governor idle state selection runs before tick_nohz_idle_go_idle() and use the "nohz" hint returned by cpuidle_select() to decide whether or not to stop the tick. This isn't straightforward, because menu_select() invokes tick_nohz_get_sleep_length() to get the time to the next timer event and the number returned by the latter comes from __tick_nohz_idle_stop_tick(). Fortunately, however, it is possible to compute that number without actually stopping the tick and with the help of the existing code. Namely, tick_nohz_get_sleep_length() can be made call tick_nohz_next_event(), introduced earlier, to get the time to the next non-highres timer event. If that happens, tick_nohz_next_event() need not be called by __tick_nohz_idle_stop_tick() again. If it turns out that the scheduler tick cannot be stopped going forward or the next timer event is too close for the tick to be stopped, tick_nohz_get_sleep_length() can simply return the time to the next event currently programmed into the corresponding clock event device. In addition to knowing the return value of tick_nohz_next_event(), however, tick_nohz_get_sleep_length() needs to know the time to the next highres timer event, but with the scheduler tick timer excluded, which can be computed with the help of hrtimer_get_next_event(). That minimum of that number and the tick_nohz_next_event() return value is the total time to the next timer event with the assumption that the tick will be stopped. It can be returned to the idle governor which can use it for predicting idle duration (under the assumption that the tick will be stopped) and deciding whether or not it makes sense to stop the tick before putting the CPU into the selected idle state. With the above, the sleep_length field in struct tick_sched is not necessary any more, so drop it. Link: https://bugzilla.kernel.org/show_bug.cgi?id=199227 Reported-by: Doug Smythies <dsmythies@telus.net> Reported-by: Thomas Ilsche <thomas.ilsche@tu-dresden.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
2018-04-04 00:17:11 +03:00
if (!can_stop_idle_tick(cpu, ts))
return *delta_next;
sched: idle: Select idle state before stopping the tick In order to address the issue with short idle duration predictions by the idle governor after the scheduler tick has been stopped, reorder the code in cpuidle_idle_call() so that the governor idle state selection runs before tick_nohz_idle_go_idle() and use the "nohz" hint returned by cpuidle_select() to decide whether or not to stop the tick. This isn't straightforward, because menu_select() invokes tick_nohz_get_sleep_length() to get the time to the next timer event and the number returned by the latter comes from __tick_nohz_idle_stop_tick(). Fortunately, however, it is possible to compute that number without actually stopping the tick and with the help of the existing code. Namely, tick_nohz_get_sleep_length() can be made call tick_nohz_next_event(), introduced earlier, to get the time to the next non-highres timer event. If that happens, tick_nohz_next_event() need not be called by __tick_nohz_idle_stop_tick() again. If it turns out that the scheduler tick cannot be stopped going forward or the next timer event is too close for the tick to be stopped, tick_nohz_get_sleep_length() can simply return the time to the next event currently programmed into the corresponding clock event device. In addition to knowing the return value of tick_nohz_next_event(), however, tick_nohz_get_sleep_length() needs to know the time to the next highres timer event, but with the scheduler tick timer excluded, which can be computed with the help of hrtimer_get_next_event(). That minimum of that number and the tick_nohz_next_event() return value is the total time to the next timer event with the assumption that the tick will be stopped. It can be returned to the idle governor which can use it for predicting idle duration (under the assumption that the tick will be stopped) and deciding whether or not it makes sense to stop the tick before putting the CPU into the selected idle state. With the above, the sleep_length field in struct tick_sched is not necessary any more, so drop it. Link: https://bugzilla.kernel.org/show_bug.cgi?id=199227 Reported-by: Doug Smythies <dsmythies@telus.net> Reported-by: Thomas Ilsche <thomas.ilsche@tu-dresden.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
2018-04-04 00:17:11 +03:00
next_event = tick_nohz_next_event(ts, cpu);
if (!next_event)
return *delta_next;
sched: idle: Select idle state before stopping the tick In order to address the issue with short idle duration predictions by the idle governor after the scheduler tick has been stopped, reorder the code in cpuidle_idle_call() so that the governor idle state selection runs before tick_nohz_idle_go_idle() and use the "nohz" hint returned by cpuidle_select() to decide whether or not to stop the tick. This isn't straightforward, because menu_select() invokes tick_nohz_get_sleep_length() to get the time to the next timer event and the number returned by the latter comes from __tick_nohz_idle_stop_tick(). Fortunately, however, it is possible to compute that number without actually stopping the tick and with the help of the existing code. Namely, tick_nohz_get_sleep_length() can be made call tick_nohz_next_event(), introduced earlier, to get the time to the next non-highres timer event. If that happens, tick_nohz_next_event() need not be called by __tick_nohz_idle_stop_tick() again. If it turns out that the scheduler tick cannot be stopped going forward or the next timer event is too close for the tick to be stopped, tick_nohz_get_sleep_length() can simply return the time to the next event currently programmed into the corresponding clock event device. In addition to knowing the return value of tick_nohz_next_event(), however, tick_nohz_get_sleep_length() needs to know the time to the next highres timer event, but with the scheduler tick timer excluded, which can be computed with the help of hrtimer_get_next_event(). That minimum of that number and the tick_nohz_next_event() return value is the total time to the next timer event with the assumption that the tick will be stopped. It can be returned to the idle governor which can use it for predicting idle duration (under the assumption that the tick will be stopped) and deciding whether or not it makes sense to stop the tick before putting the CPU into the selected idle state. With the above, the sleep_length field in struct tick_sched is not necessary any more, so drop it. Link: https://bugzilla.kernel.org/show_bug.cgi?id=199227 Reported-by: Doug Smythies <dsmythies@telus.net> Reported-by: Thomas Ilsche <thomas.ilsche@tu-dresden.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
2018-04-04 00:17:11 +03:00
/*
* If the next highres timer to expire is earlier than next_event, the
* idle governor needs to know that.
*/
next_event = min_t(u64, next_event,
hrtimer_next_event_without(&ts->sched_timer));
cpuidle: consolidate 2.6.22 cpuidle branch into one patch commit e5a16b1f9eec0af7cfa0830304b41c1c0833cf9f Author: Len Brown <len.brown@intel.com> Date: Tue Oct 2 23:44:44 2007 -0400 cpuidle: shrink diff processor_idle.c | 440 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 429 insertions(+), 11 deletions(-) Signed-off-by: Len Brown <len.brown@intel.com> commit dfbb9d5aedfb18848a3e0d6f6e3e4969febb209c Author: Len Brown <len.brown@intel.com> Date: Wed Sep 26 02:17:55 2007 -0400 cpuidle: reduce diff size Reduces the cpuidle processor_idle.c diff vs 2.6.22 from this processor_idle.c | 2006 ++++++++++++++++++++++++++----------------- 1 file changed, 1219 insertions(+), 787 deletions(-) to this: processor_idle.c | 502 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 458 insertions(+), 44 deletions(-) ...for the purpose of making the cpuilde patch less invasive and easier to review. no functional changes. build tested only. Signed-off-by: Len Brown <len.brown@intel.com> commit 889172fc915f5a7fe20f35b133cbd205ce69bf6c Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Sep 13 13:40:05 2007 -0700 cpuidle: Retain old ACPI policy for !CONFIG_CPU_IDLE Retain the old policy in processor_idle, so that when CPU_IDLE is not configured, old C-state policy will still be used. This provides a clean gradual migration path from old ACPI policy to new cpuidle based policy. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 9544a8181edc7ecc33b3bfd69271571f98ed08bc Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Sep 13 13:39:17 2007 -0700 cpuidle: Configure governors by default Quoting Len "Do not give an option to users to shoot themselves in the foot". Remove the configurability of ladder and menu governors as they are needed for default policy of cpuidle. That way users will not be able to have cpuidle without any policy loosing all C-state power savings. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 8975059a2c1e56cfe83d1bcf031bcf4cb39be743 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:27:07 2007 -0400 CPUIDLE: load ACPI properly when CPUIDLE is disabled Change the registration return codes for when CPUIDLE support is not compiled into the kernel. As a result, the ACPI processor driver will load properly even if CPUIDLE is unavailable. However, it may be possible to cleanup the ACPI processor driver further and eliminate some dead code paths. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit e0322e2b58dd1b12ec669bf84693efe0dc2414a8 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:26:06 2007 -0400 CPUIDLE: remove cpuidle_get_bm_activity() Remove cpuidle_get_bm_activity() and updates governors accordingly. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 18a6e770d5c82ba26653e53d240caa617e09e9ab Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:58 2007 -0400 CPUIDLE: max_cstate fix Currently max_cstate is limited to 0, resulting in no idle processor power management on ACPI platforms. This patch restores the value to the array size. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 1fdc0887286179b40ce24bcdbde663172e205ef0 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:40 2007 -0400 CPUIDLE: handle BM detection inside the ACPI Processor driver Update the ACPI processor driver to detect BM activity and limit state entry depth internally, rather than exposing such requirements to CPUIDLE. As a result, CPUIDLE can drop this ACPI-specific interface and become more platform independent. BM activity is now handled much more aggressively than it was in the original implementation, so some testing coverage may be needed to verify that this doesn't introduce any DMA buffer under-run issues. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 0ef38840db666f48e3cdd2b769da676c57228dd9 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:14 2007 -0400 CPUIDLE: menu governor updates Tweak the menu governor to more effectively handle non-timer break events. Non-timer break events are detected by comparing the actual sleep time to the expected sleep time. In future revisions, it may be more reliable to use the timer data structures directly. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit bb4d74fca63fa96cf3ace644b15ae0f12b7df5a1 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:24:40 2007 -0400 CPUIDLE: fix 'current_governor' sysfs entry Allow the "current_governor" sysfs entry to properly handle input terminated with '\n'. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit df3c71559bb69b125f1a48971bf0d17f78bbdf47 Author: Len Brown <len.brown@intel.com> Date: Sun Aug 12 02:00:45 2007 -0400 cpuidle: fix IA64 build (again) Signed-off-by: Len Brown <len.brown@intel.com> commit a02064579e3f9530fd31baae16b1fc46b5a7bca8 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:39:27 2007 -0400 cpuidle: Remove support for runtime changing of max_cstate Remove support for runtime changeability of max_cstate. Drivers can use use latency APIs. max_cstate can still be used as a boot time option and dmi override. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 0912a44b13adf22f5e3f607d263aed23b4910d7e Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:39:16 2007 -0400 cpuidle: Remove ACPI cstate_limit calls from ipw2100 ipw2100 already has code to use accetable_latency interfaces to limit the C-state. Remove the calls to acpi_set_cstate_limit and acpi_get_cstate_limit as they are redundant. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit c649a76e76be6bff1fd770d0a775798813a3f6e0 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:35:39 2007 -0400 cpuidle: compile fix for pause and resume functions Fix the compilation failure when cpuidle is not compiled in. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: Adam Belay <adam.belay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 2305a5920fb8ee6ccec1c62ade05aa8351091d71 Author: Adam Belay <abelay@novell.com> Date: Thu Jul 19 00:49:00 2007 -0400 cpuidle: re-write Some portions have been rewritten to make the code cleaner and lighter weight. The following is a list of changes: 1.) the state name is now included in the sysfs interface 2.) detection, hotplug, and available state modifications are handled by CPUIDLE drivers directly 3.) the CPUIDLE idle handler is only ever installed when at least one cpuidle_device is enabled and ready 4.) the menu governor BM code no longer overflows 5.) the sysfs attributes are now printed as unsigned integers, avoiding negative values 6.) a variety of other small cleanups Also, Idle drivers are no longer swappable during runtime through the CPUIDLE sysfs inteface. On i386 and x86_64 most idle handlers (e.g. poll, mwait, halt, etc.) don't benefit from an infrastructure that supports multiple states, so I think using a more general case idle handler selection mechanism would be cleaner. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit df25b6b56955714e6e24b574d88d1fd11f0c3ee5 Author: Len Brown <len.brown@intel.com> Date: Tue Jul 24 17:08:21 2007 -0400 cpuidle: fix IA64 buid Signed-off-by: Len Brown <len.brown@intel.com> commit fd6ada4c14488755ff7068860078c437431fbccd Author: Adrian Bunk <bunk@stusta.de> Date: Mon Jul 9 11:33:13 2007 -0700 cpuidle: static make cpuidle_replace_governor() static Signed-off-by: Adrian Bunk <bunk@stusta.de> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit c1d4a2cebcadf2429c0c72e1d29aa2a9684c32e0 Author: Adrian Bunk <bunk@stusta.de> Date: Tue Jul 3 00:54:40 2007 -0400 cpuidle: static This patch makes the needlessly global struct menu_governor static. Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit dbf8780c6e8d572c2c273da97ed1cca7608fd999 Author: Andrew Morton <akpm@linux-foundation.org> Date: Tue Jul 3 00:49:14 2007 -0400 export symbol tick_nohz_get_sleep_length ERROR: "tick_nohz_get_sleep_length" [drivers/cpuidle/governors/menu.ko] undefined! ERROR: "tick_nohz_get_idle_jiffies" [drivers/cpuidle/governors/menu.ko] undefined! And please be sure to get your changes to core kernel suitably reviewed. Cc: Adam Belay <abelay@novell.com> Cc: Venki Pallipadi <venkatesh.pallipadi@intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 29f0e248e7017be15f99febf9143a2cef00b2961 Author: Andrew Morton <akpm@linux-foundation.org> Date: Tue Jul 3 00:43:04 2007 -0400 tick.h needs hrtimer.h It uses hrtimers. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit e40cede7d63a029e92712a3fe02faee60cc38fb4 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:40:34 2007 -0400 cpuidle: first round of documentation updates Documentation changes based on Pavel's feedback. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 83b42be2efece386976507555c29e7773a0dfcd1 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:39:25 2007 -0400 cpuidle: add rating to the governors and pick the one with highest rating by default Introduce a governor rating scheme to pick the right governor by default. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit d2a74b8c5e8f22def4709330d4bfc4a29209b71c Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:38:08 2007 -0400 cpuidle: make cpuidle sysfs driver governor switch off by default Make default cpuidle sysfs to show current_governor and current_driver in read-only mode. More elaborate available_governors and available_drivers with writeable current_governor and current_driver interface only appear with "cpuidle_sysfs_switch" boot parameter. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 1f60a0e80bf83cf6b55c8845bbe5596ed8f6307b Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:37:00 2007 -0400 cpuidle: menu governor: change the early break condition Change the C-state early break out algorithm in menu governor. We only look at early breakouts that result in wakeups shorter than idle state's target_residency. If such a breakout is frequent enough, eliminate the particular idle state upto a timeout period. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 45a42095cf64b003b4a69be3ce7f434f97d7af51 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:35:38 2007 -0400 cpuidle: fix uninitialized variable in sysfs routine Fix the uninitialized usage of ret. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 80dca7cdba3e6ee13eae277660873ab9584eb3be Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:34:16 2007 -0400 cpuidle: reenable /proc/acpi//power interface for the time being Keep /proc/acpi/processor/CPU*/power around for a while as powertop depends on it. It will be marked deprecated and removed in future. powertop can use cpuidle interfaces instead. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 589c37c2646c5e3813a51255a5ee1159cb4c33fc Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:32:37 2007 -0400 cpuidle: menu governor and hrtimer compile fix Compile fix for menu governor. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 0ba80bd9ab3ed304cb4f19b722e4cc6740588b5e Author: Len Brown <len.brown@intel.com> Date: Thu May 31 22:51:43 2007 -0400 cpuidle: build fix - cpuidle vs ipw2100 module ERROR: "acpi_set_cstate_limit" [drivers/net/wireless/ipw2100.ko] undefined! Signed-off-by: Len Brown <len.brown@intel.com> commit d7d8fa7f96a7f7682be7c6cc0cc53fa7a18c3b58 Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:47:07 2007 -0400 cpuidle: add the 'menu' governor Here is my first take at implementing an idle PM governor that takes full advantage of NO_HZ. I call it the 'menu' governor because it considers the full list of idle states before each entry. I've kept the implementation fairly simple. It attempts to guess the next residency time and then chooses a state that would meet at least the break-even point between power savings and entry cost. To this end, it selects the deepest idle state that satisfies the following constraints: 1. If the idle time elapsed since bus master activity was detected is below a threshold (currently 20 ms), then limit the selection to C2-type or above. 2. Do not choose a state with a break-even residency that exceeds the expected time remaining until the next timer interrupt. 3. Do not choose a state with a break-even residency that exceeds the elapsed time between the last pair of break events, excluding timer interrupts. This governor has an advantage over "ladder" governor because it proactively checks how much time remains until the next timer interrupt using the tick infrastructure. Also, it handles device interrupt activity more intelligently by not including timer interrupts in break event calculations. Finally, it doesn't make policy decisions using the number of state entries, which can have variable residency times (NO_HZ makes these potentially very large), and instead only considers sleep time deltas. The menu governor can be selected during runtime using the cpuidle sysfs interface like so: "echo "menu" > /sys/devices/system/cpu/cpuidle/current_governor" Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit a4bec7e65aa3b7488b879d971651cc99a6c410fe Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:47:03 2007 -0400 cpuidle: export time until next timer interrupt using NO_HZ Expose information about the time remaining until the next timer interrupt expires by utilizing the dynticks infrastructure. Also modify the main idle loop to allow dynticks to handle non-interrupt break events (e.g. DMA). Finally, expose sleep ticks information to external code. Thomas Gleixner is responsible for much of the code in this patch. However, I've made some additional changes, so I'm probably responsible if there are any bugs or oversights :) Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 2929d8996fbc77f41a5ff86bb67cdde3ca7d2d72 Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:46:58 2007 -0400 cpuidle: governor API changes This patch prepares cpuidle for the menu governor. It adds an optional stage after idle state entry to give the governor an opportunity to check why the state was exited. Also it makes sure the idle loop returns after each state entry, allowing the appropriate dynticks code to run. Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 3a7fd42f9825c3b03e364ca59baa751bb350775f Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Apr 26 00:03:59 2007 -0700 cpuidle: hang fix Prevent hang on x86-64, when ACPI processor driver is added as a module on a system that does not support C-states. x86-64 expects all idle handlers to enable interrupts before returning from idle handler. This is due to enter_idle(), exit_idle() races. Make cpuidle_idle_call() confirm to this when there is no pm_idle_old. Also, cpuidle look at the return values of attch_driver() and set current_driver to NULL if attach fails on all CPUs. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 4893339a142afbd5b7c01ffadfd53d14746e858e Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:09 2007 +0800 cpuidle: add support for max_cstate limit With CPUIDLE framework, the max_cstate (to limit max cpu c-state) parameter is ingored. Some systems require it to ignore C2/C3 and some drivers like ipw require it too. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 43bbbbe1cb998cbd2df656f55bb3bfe30f30e7d1 Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:13 2007 +0800 cpuidle: add cpuidle_fore_redetect_devices API add cpuidle_force_redetect_devices API, which forces all CPU redetect idle states. Next patch will use it. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit d1edadd608f24836def5ec483d2edccfb37b1d19 Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:01 2007 +0800 cpuidle: fix sysfs related issue Fix the cpuidle sysfs issue. a. make kobject dynamicaly allocated b. fixed sysfs init issue to avoid suspend/resume issue Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 7169a5cc0d67b263978859672e86c13c23a5570d Author: Randy Dunlap <randy.dunlap@oracle.com> Date: Wed Mar 28 22:52:53 2007 -0400 cpuidle: 1-bit field must be unsigned A 1-bit bitfield has no room for a sign bit. drivers/cpuidle/governors/ladder.c:54:16: error: dubious bitfield without explicit `signed' or `unsigned' Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 4658620158dc2fbd9e4bcb213c5b6fb5d05ba7d4 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Wed Mar 28 22:52:41 2007 -0400 cpuidle: fix boot hang Patch for cpuidle boot hang reported by Larry Finger here. http://www.ussg.iu.edu/hypermail/linux/kernel/0703.2/2025.html Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Larry Finger <larry.finger@lwfinger.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit c17e168aa6e5fe3851baaae8df2fbc1cf11443a9 Author: Len Brown <len.brown@intel.com> Date: Wed Mar 7 04:37:53 2007 -0500 cpuidle: ladder does not depend on ACPI build fix for CONFIG_ACPI=n In file included from drivers/cpuidle/governors/ladder.c:21: include/acpi/processor.h:88: error: expected specifier-qualifier-list before ‘acpi_integer’ include/acpi/processor.h:106: error: expected specifier-qualifier-list before ‘acpi_integer’ include/acpi/processor.h:168: error: expected specifier-qualifier-list before ‘acpi_handle’ Signed-off-by: Len Brown <len.brown@intel.com> commit 8c91d958246bde68db0c3f0c57b535962ce861cb Author: Adrian Bunk <bunk@stusta.de> Date: Tue Mar 6 02:29:40 2007 -0800 cpuidle: make code static This patch makes the following needlessly global code static: - driver.c: __cpuidle_find_driver() - governor.c: __cpuidle_find_governor() - ladder.c: struct ladder_governor Signed-off-by: Adrian Bunk <bunk@stusta.de> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Adam Belay <abelay@novell.com> Cc: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 0c39dc3187094c72c33ab65a64d2017b21f372d2 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Wed Mar 7 02:38:22 2007 -0500 cpu_idle: fix build break This patch fixes a build breakage with !CONFIG_HOTPLUG_CPU and CONFIG_CPU_IDLE. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 8112e3b115659b07df340ef170515799c0105f82 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Mar 6 02:29:39 2007 -0800 cpuidle: build fix for !CPU_IDLE Fix the compile issues when CPU_IDLE is not configured. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Adam Belay <abelay@novell.com> Cc: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 1eb4431e9599cd25e0d9872f3c2c8986821839dd Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:54:57 2007 -0800 cpuidle take2: Basic documentation for cpuidle Documentation for cpuidle infrastructure Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit ef5f15a8b79123a047285ec2e3899108661df779 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:54:03 2007 -0800 cpuidle take2: Hookup ACPI C-states driver with cpuidle Hookup ACPI C-states onto generic cpuidle infrastructure. drivers/acpi/procesor_idle.c is now a ACPI C-states driver that registers as a driver in cpuidle infrastructure and the policy part is removed from drivers/acpi/processor_idle.c. We use governor in cpuidle instead. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 987196fa82d4db52c407e8c9d5dec884ba602183 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:52:57 2007 -0800 cpuidle take2: Core cpuidle infrastructure Announcing 'cpuidle', a new CPU power management infrastructure to manage idle CPUs in a clean and efficient manner. cpuidle separates out the drivers that can provide support for multiple types of idle states and policy governors that decide on what idle state to use at run time. A cpuidle driver can support multiple idle states based on parameters like varying power consumption, wakeup latency, etc (ACPI C-states for example). A cpuidle governor can be usage model specific (laptop, server, laptop on battery etc). Main advantage of the infrastructure being, it allows independent development of drivers and governors and allows for better CPU power management. A huge thanks to Adam Belay and Shaohua Li who were part of this mini-project since its beginning and are greatly responsible for this patchset. This patch: Core cpuidle infrastructure. Introduces a new abstraction layer for cpuidle: * which manages drivers that can support multiple idles states. Drivers can be generic or particular to specific hardware/platform * allows pluging in multiple policy governors that can take idle state policy decision * The core also has a set of sysfs interfaces with which administrato can know about supported drivers and governors and switch them at run time. Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> Signed-off-by: Len Brown <len.brown@intel.com>
2007-10-04 02:58:00 +04:00
sched: idle: Select idle state before stopping the tick In order to address the issue with short idle duration predictions by the idle governor after the scheduler tick has been stopped, reorder the code in cpuidle_idle_call() so that the governor idle state selection runs before tick_nohz_idle_go_idle() and use the "nohz" hint returned by cpuidle_select() to decide whether or not to stop the tick. This isn't straightforward, because menu_select() invokes tick_nohz_get_sleep_length() to get the time to the next timer event and the number returned by the latter comes from __tick_nohz_idle_stop_tick(). Fortunately, however, it is possible to compute that number without actually stopping the tick and with the help of the existing code. Namely, tick_nohz_get_sleep_length() can be made call tick_nohz_next_event(), introduced earlier, to get the time to the next non-highres timer event. If that happens, tick_nohz_next_event() need not be called by __tick_nohz_idle_stop_tick() again. If it turns out that the scheduler tick cannot be stopped going forward or the next timer event is too close for the tick to be stopped, tick_nohz_get_sleep_length() can simply return the time to the next event currently programmed into the corresponding clock event device. In addition to knowing the return value of tick_nohz_next_event(), however, tick_nohz_get_sleep_length() needs to know the time to the next highres timer event, but with the scheduler tick timer excluded, which can be computed with the help of hrtimer_get_next_event(). That minimum of that number and the tick_nohz_next_event() return value is the total time to the next timer event with the assumption that the tick will be stopped. It can be returned to the idle governor which can use it for predicting idle duration (under the assumption that the tick will be stopped) and deciding whether or not it makes sense to stop the tick before putting the CPU into the selected idle state. With the above, the sleep_length field in struct tick_sched is not necessary any more, so drop it. Link: https://bugzilla.kernel.org/show_bug.cgi?id=199227 Reported-by: Doug Smythies <dsmythies@telus.net> Reported-by: Thomas Ilsche <thomas.ilsche@tu-dresden.de> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
2018-04-04 00:17:11 +03:00
return ktime_sub(next_event, now);
cpuidle: consolidate 2.6.22 cpuidle branch into one patch commit e5a16b1f9eec0af7cfa0830304b41c1c0833cf9f Author: Len Brown <len.brown@intel.com> Date: Tue Oct 2 23:44:44 2007 -0400 cpuidle: shrink diff processor_idle.c | 440 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 429 insertions(+), 11 deletions(-) Signed-off-by: Len Brown <len.brown@intel.com> commit dfbb9d5aedfb18848a3e0d6f6e3e4969febb209c Author: Len Brown <len.brown@intel.com> Date: Wed Sep 26 02:17:55 2007 -0400 cpuidle: reduce diff size Reduces the cpuidle processor_idle.c diff vs 2.6.22 from this processor_idle.c | 2006 ++++++++++++++++++++++++++----------------- 1 file changed, 1219 insertions(+), 787 deletions(-) to this: processor_idle.c | 502 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 458 insertions(+), 44 deletions(-) ...for the purpose of making the cpuilde patch less invasive and easier to review. no functional changes. build tested only. Signed-off-by: Len Brown <len.brown@intel.com> commit 889172fc915f5a7fe20f35b133cbd205ce69bf6c Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Sep 13 13:40:05 2007 -0700 cpuidle: Retain old ACPI policy for !CONFIG_CPU_IDLE Retain the old policy in processor_idle, so that when CPU_IDLE is not configured, old C-state policy will still be used. This provides a clean gradual migration path from old ACPI policy to new cpuidle based policy. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 9544a8181edc7ecc33b3bfd69271571f98ed08bc Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Sep 13 13:39:17 2007 -0700 cpuidle: Configure governors by default Quoting Len "Do not give an option to users to shoot themselves in the foot". Remove the configurability of ladder and menu governors as they are needed for default policy of cpuidle. That way users will not be able to have cpuidle without any policy loosing all C-state power savings. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 8975059a2c1e56cfe83d1bcf031bcf4cb39be743 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:27:07 2007 -0400 CPUIDLE: load ACPI properly when CPUIDLE is disabled Change the registration return codes for when CPUIDLE support is not compiled into the kernel. As a result, the ACPI processor driver will load properly even if CPUIDLE is unavailable. However, it may be possible to cleanup the ACPI processor driver further and eliminate some dead code paths. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit e0322e2b58dd1b12ec669bf84693efe0dc2414a8 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:26:06 2007 -0400 CPUIDLE: remove cpuidle_get_bm_activity() Remove cpuidle_get_bm_activity() and updates governors accordingly. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 18a6e770d5c82ba26653e53d240caa617e09e9ab Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:58 2007 -0400 CPUIDLE: max_cstate fix Currently max_cstate is limited to 0, resulting in no idle processor power management on ACPI platforms. This patch restores the value to the array size. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 1fdc0887286179b40ce24bcdbde663172e205ef0 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:40 2007 -0400 CPUIDLE: handle BM detection inside the ACPI Processor driver Update the ACPI processor driver to detect BM activity and limit state entry depth internally, rather than exposing such requirements to CPUIDLE. As a result, CPUIDLE can drop this ACPI-specific interface and become more platform independent. BM activity is now handled much more aggressively than it was in the original implementation, so some testing coverage may be needed to verify that this doesn't introduce any DMA buffer under-run issues. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 0ef38840db666f48e3cdd2b769da676c57228dd9 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:25:14 2007 -0400 CPUIDLE: menu governor updates Tweak the menu governor to more effectively handle non-timer break events. Non-timer break events are detected by comparing the actual sleep time to the expected sleep time. In future revisions, it may be more reliable to use the timer data structures directly. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit bb4d74fca63fa96cf3ace644b15ae0f12b7df5a1 Author: Adam Belay <abelay@novell.com> Date: Tue Aug 21 18:24:40 2007 -0400 CPUIDLE: fix 'current_governor' sysfs entry Allow the "current_governor" sysfs entry to properly handle input terminated with '\n'. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit df3c71559bb69b125f1a48971bf0d17f78bbdf47 Author: Len Brown <len.brown@intel.com> Date: Sun Aug 12 02:00:45 2007 -0400 cpuidle: fix IA64 build (again) Signed-off-by: Len Brown <len.brown@intel.com> commit a02064579e3f9530fd31baae16b1fc46b5a7bca8 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:39:27 2007 -0400 cpuidle: Remove support for runtime changing of max_cstate Remove support for runtime changeability of max_cstate. Drivers can use use latency APIs. max_cstate can still be used as a boot time option and dmi override. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 0912a44b13adf22f5e3f607d263aed23b4910d7e Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:39:16 2007 -0400 cpuidle: Remove ACPI cstate_limit calls from ipw2100 ipw2100 already has code to use accetable_latency interfaces to limit the C-state. Remove the calls to acpi_set_cstate_limit and acpi_get_cstate_limit as they are redundant. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit c649a76e76be6bff1fd770d0a775798813a3f6e0 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Sun Aug 12 01:35:39 2007 -0400 cpuidle: compile fix for pause and resume functions Fix the compilation failure when cpuidle is not compiled in. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: Adam Belay <adam.belay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 2305a5920fb8ee6ccec1c62ade05aa8351091d71 Author: Adam Belay <abelay@novell.com> Date: Thu Jul 19 00:49:00 2007 -0400 cpuidle: re-write Some portions have been rewritten to make the code cleaner and lighter weight. The following is a list of changes: 1.) the state name is now included in the sysfs interface 2.) detection, hotplug, and available state modifications are handled by CPUIDLE drivers directly 3.) the CPUIDLE idle handler is only ever installed when at least one cpuidle_device is enabled and ready 4.) the menu governor BM code no longer overflows 5.) the sysfs attributes are now printed as unsigned integers, avoiding negative values 6.) a variety of other small cleanups Also, Idle drivers are no longer swappable during runtime through the CPUIDLE sysfs inteface. On i386 and x86_64 most idle handlers (e.g. poll, mwait, halt, etc.) don't benefit from an infrastructure that supports multiple states, so I think using a more general case idle handler selection mechanism would be cleaner. Signed-off-by: Adam Belay <abelay@novell.com> Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit df25b6b56955714e6e24b574d88d1fd11f0c3ee5 Author: Len Brown <len.brown@intel.com> Date: Tue Jul 24 17:08:21 2007 -0400 cpuidle: fix IA64 buid Signed-off-by: Len Brown <len.brown@intel.com> commit fd6ada4c14488755ff7068860078c437431fbccd Author: Adrian Bunk <bunk@stusta.de> Date: Mon Jul 9 11:33:13 2007 -0700 cpuidle: static make cpuidle_replace_governor() static Signed-off-by: Adrian Bunk <bunk@stusta.de> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit c1d4a2cebcadf2429c0c72e1d29aa2a9684c32e0 Author: Adrian Bunk <bunk@stusta.de> Date: Tue Jul 3 00:54:40 2007 -0400 cpuidle: static This patch makes the needlessly global struct menu_governor static. Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit dbf8780c6e8d572c2c273da97ed1cca7608fd999 Author: Andrew Morton <akpm@linux-foundation.org> Date: Tue Jul 3 00:49:14 2007 -0400 export symbol tick_nohz_get_sleep_length ERROR: "tick_nohz_get_sleep_length" [drivers/cpuidle/governors/menu.ko] undefined! ERROR: "tick_nohz_get_idle_jiffies" [drivers/cpuidle/governors/menu.ko] undefined! And please be sure to get your changes to core kernel suitably reviewed. Cc: Adam Belay <abelay@novell.com> Cc: Venki Pallipadi <venkatesh.pallipadi@intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 29f0e248e7017be15f99febf9143a2cef00b2961 Author: Andrew Morton <akpm@linux-foundation.org> Date: Tue Jul 3 00:43:04 2007 -0400 tick.h needs hrtimer.h It uses hrtimers. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit e40cede7d63a029e92712a3fe02faee60cc38fb4 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:40:34 2007 -0400 cpuidle: first round of documentation updates Documentation changes based on Pavel's feedback. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 83b42be2efece386976507555c29e7773a0dfcd1 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:39:25 2007 -0400 cpuidle: add rating to the governors and pick the one with highest rating by default Introduce a governor rating scheme to pick the right governor by default. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit d2a74b8c5e8f22def4709330d4bfc4a29209b71c Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:38:08 2007 -0400 cpuidle: make cpuidle sysfs driver governor switch off by default Make default cpuidle sysfs to show current_governor and current_driver in read-only mode. More elaborate available_governors and available_drivers with writeable current_governor and current_driver interface only appear with "cpuidle_sysfs_switch" boot parameter. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 1f60a0e80bf83cf6b55c8845bbe5596ed8f6307b Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:37:00 2007 -0400 cpuidle: menu governor: change the early break condition Change the C-state early break out algorithm in menu governor. We only look at early breakouts that result in wakeups shorter than idle state's target_residency. If such a breakout is frequent enough, eliminate the particular idle state upto a timeout period. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 45a42095cf64b003b4a69be3ce7f434f97d7af51 Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:35:38 2007 -0400 cpuidle: fix uninitialized variable in sysfs routine Fix the uninitialized usage of ret. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 80dca7cdba3e6ee13eae277660873ab9584eb3be Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:34:16 2007 -0400 cpuidle: reenable /proc/acpi//power interface for the time being Keep /proc/acpi/processor/CPU*/power around for a while as powertop depends on it. It will be marked deprecated and removed in future. powertop can use cpuidle interfaces instead. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 589c37c2646c5e3813a51255a5ee1159cb4c33fc Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Jul 3 00:32:37 2007 -0400 cpuidle: menu governor and hrtimer compile fix Compile fix for menu governor. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 0ba80bd9ab3ed304cb4f19b722e4cc6740588b5e Author: Len Brown <len.brown@intel.com> Date: Thu May 31 22:51:43 2007 -0400 cpuidle: build fix - cpuidle vs ipw2100 module ERROR: "acpi_set_cstate_limit" [drivers/net/wireless/ipw2100.ko] undefined! Signed-off-by: Len Brown <len.brown@intel.com> commit d7d8fa7f96a7f7682be7c6cc0cc53fa7a18c3b58 Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:47:07 2007 -0400 cpuidle: add the 'menu' governor Here is my first take at implementing an idle PM governor that takes full advantage of NO_HZ. I call it the 'menu' governor because it considers the full list of idle states before each entry. I've kept the implementation fairly simple. It attempts to guess the next residency time and then chooses a state that would meet at least the break-even point between power savings and entry cost. To this end, it selects the deepest idle state that satisfies the following constraints: 1. If the idle time elapsed since bus master activity was detected is below a threshold (currently 20 ms), then limit the selection to C2-type or above. 2. Do not choose a state with a break-even residency that exceeds the expected time remaining until the next timer interrupt. 3. Do not choose a state with a break-even residency that exceeds the elapsed time between the last pair of break events, excluding timer interrupts. This governor has an advantage over "ladder" governor because it proactively checks how much time remains until the next timer interrupt using the tick infrastructure. Also, it handles device interrupt activity more intelligently by not including timer interrupts in break event calculations. Finally, it doesn't make policy decisions using the number of state entries, which can have variable residency times (NO_HZ makes these potentially very large), and instead only considers sleep time deltas. The menu governor can be selected during runtime using the cpuidle sysfs interface like so: "echo "menu" > /sys/devices/system/cpu/cpuidle/current_governor" Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit a4bec7e65aa3b7488b879d971651cc99a6c410fe Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:47:03 2007 -0400 cpuidle: export time until next timer interrupt using NO_HZ Expose information about the time remaining until the next timer interrupt expires by utilizing the dynticks infrastructure. Also modify the main idle loop to allow dynticks to handle non-interrupt break events (e.g. DMA). Finally, expose sleep ticks information to external code. Thomas Gleixner is responsible for much of the code in this patch. However, I've made some additional changes, so I'm probably responsible if there are any bugs or oversights :) Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 2929d8996fbc77f41a5ff86bb67cdde3ca7d2d72 Author: Adam Belay <abelay@novell.com> Date: Sat Mar 24 03:46:58 2007 -0400 cpuidle: governor API changes This patch prepares cpuidle for the menu governor. It adds an optional stage after idle state entry to give the governor an opportunity to check why the state was exited. Also it makes sure the idle loop returns after each state entry, allowing the appropriate dynticks code to run. Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 3a7fd42f9825c3b03e364ca59baa751bb350775f Author: Venki Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Apr 26 00:03:59 2007 -0700 cpuidle: hang fix Prevent hang on x86-64, when ACPI processor driver is added as a module on a system that does not support C-states. x86-64 expects all idle handlers to enable interrupts before returning from idle handler. This is due to enter_idle(), exit_idle() races. Make cpuidle_idle_call() confirm to this when there is no pm_idle_old. Also, cpuidle look at the return values of attch_driver() and set current_driver to NULL if attach fails on all CPUs. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 4893339a142afbd5b7c01ffadfd53d14746e858e Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:09 2007 +0800 cpuidle: add support for max_cstate limit With CPUIDLE framework, the max_cstate (to limit max cpu c-state) parameter is ingored. Some systems require it to ignore C2/C3 and some drivers like ipw require it too. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 43bbbbe1cb998cbd2df656f55bb3bfe30f30e7d1 Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:13 2007 +0800 cpuidle: add cpuidle_fore_redetect_devices API add cpuidle_force_redetect_devices API, which forces all CPU redetect idle states. Next patch will use it. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit d1edadd608f24836def5ec483d2edccfb37b1d19 Author: Shaohua Li <shaohua.li@intel.com> Date: Thu Apr 26 10:40:01 2007 +0800 cpuidle: fix sysfs related issue Fix the cpuidle sysfs issue. a. make kobject dynamicaly allocated b. fixed sysfs init issue to avoid suspend/resume issue Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 7169a5cc0d67b263978859672e86c13c23a5570d Author: Randy Dunlap <randy.dunlap@oracle.com> Date: Wed Mar 28 22:52:53 2007 -0400 cpuidle: 1-bit field must be unsigned A 1-bit bitfield has no room for a sign bit. drivers/cpuidle/governors/ladder.c:54:16: error: dubious bitfield without explicit `signed' or `unsigned' Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 4658620158dc2fbd9e4bcb213c5b6fb5d05ba7d4 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Wed Mar 28 22:52:41 2007 -0400 cpuidle: fix boot hang Patch for cpuidle boot hang reported by Larry Finger here. http://www.ussg.iu.edu/hypermail/linux/kernel/0703.2/2025.html Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Larry Finger <larry.finger@lwfinger.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit c17e168aa6e5fe3851baaae8df2fbc1cf11443a9 Author: Len Brown <len.brown@intel.com> Date: Wed Mar 7 04:37:53 2007 -0500 cpuidle: ladder does not depend on ACPI build fix for CONFIG_ACPI=n In file included from drivers/cpuidle/governors/ladder.c:21: include/acpi/processor.h:88: error: expected specifier-qualifier-list before ‘acpi_integer’ include/acpi/processor.h:106: error: expected specifier-qualifier-list before ‘acpi_integer’ include/acpi/processor.h:168: error: expected specifier-qualifier-list before ‘acpi_handle’ Signed-off-by: Len Brown <len.brown@intel.com> commit 8c91d958246bde68db0c3f0c57b535962ce861cb Author: Adrian Bunk <bunk@stusta.de> Date: Tue Mar 6 02:29:40 2007 -0800 cpuidle: make code static This patch makes the following needlessly global code static: - driver.c: __cpuidle_find_driver() - governor.c: __cpuidle_find_governor() - ladder.c: struct ladder_governor Signed-off-by: Adrian Bunk <bunk@stusta.de> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Adam Belay <abelay@novell.com> Cc: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 0c39dc3187094c72c33ab65a64d2017b21f372d2 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Wed Mar 7 02:38:22 2007 -0500 cpu_idle: fix build break This patch fixes a build breakage with !CONFIG_HOTPLUG_CPU and CONFIG_CPU_IDLE. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 8112e3b115659b07df340ef170515799c0105f82 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Tue Mar 6 02:29:39 2007 -0800 cpuidle: build fix for !CPU_IDLE Fix the compile issues when CPU_IDLE is not configured. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: Adam Belay <abelay@novell.com> Cc: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Len Brown <len.brown@intel.com> commit 1eb4431e9599cd25e0d9872f3c2c8986821839dd Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:54:57 2007 -0800 cpuidle take2: Basic documentation for cpuidle Documentation for cpuidle infrastructure Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> commit ef5f15a8b79123a047285ec2e3899108661df779 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:54:03 2007 -0800 cpuidle take2: Hookup ACPI C-states driver with cpuidle Hookup ACPI C-states onto generic cpuidle infrastructure. drivers/acpi/procesor_idle.c is now a ACPI C-states driver that registers as a driver in cpuidle infrastructure and the policy part is removed from drivers/acpi/processor_idle.c. We use governor in cpuidle instead. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Len Brown <len.brown@intel.com> commit 987196fa82d4db52c407e8c9d5dec884ba602183 Author: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Date: Thu Feb 22 13:52:57 2007 -0800 cpuidle take2: Core cpuidle infrastructure Announcing 'cpuidle', a new CPU power management infrastructure to manage idle CPUs in a clean and efficient manner. cpuidle separates out the drivers that can provide support for multiple types of idle states and policy governors that decide on what idle state to use at run time. A cpuidle driver can support multiple idle states based on parameters like varying power consumption, wakeup latency, etc (ACPI C-states for example). A cpuidle governor can be usage model specific (laptop, server, laptop on battery etc). Main advantage of the infrastructure being, it allows independent development of drivers and governors and allows for better CPU power management. A huge thanks to Adam Belay and Shaohua Li who were part of this mini-project since its beginning and are greatly responsible for this patchset. This patch: Core cpuidle infrastructure. Introduces a new abstraction layer for cpuidle: * which manages drivers that can support multiple idles states. Drivers can be generic or particular to specific hardware/platform * allows pluging in multiple policy governors that can take idle state policy decision * The core also has a set of sysfs interfaces with which administrato can know about supported drivers and governors and switch them at run time. Signed-off-by: Adam Belay <abelay@novell.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Len Brown <len.brown@intel.com> Signed-off-by: Len Brown <len.brown@intel.com>
2007-10-04 02:58:00 +04:00
}
/**
* tick_nohz_get_idle_calls_cpu - return the current idle calls counter value
* for a particular CPU.
*
* Called from the schedutil frequency scaling governor in scheduler context.
*/
unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
{
struct tick_sched *ts = tick_get_tick_sched(cpu);
return ts->idle_calls;
}
cpufreq: schedutil: Avoid reducing frequency of busy CPUs prematurely The way the schedutil governor uses the PELT metric causes it to underestimate the CPU utilization in some cases. That can be easily demonstrated by running kernel compilation on a Sandy Bridge Intel processor, running turbostat in parallel with it and looking at the values written to the MSR_IA32_PERF_CTL register. Namely, the expected result would be that when all CPUs were 100% busy, all of them would be requested to run in the maximum P-state, but observation shows that this clearly isn't the case. The CPUs run in the maximum P-state for a while and then are requested to run slower and go back to the maximum P-state after a while again. That causes the actual frequency of the processor to visibly oscillate below the sustainable maximum in a jittery fashion which clearly is not desirable. That has been attributed to CPU utilization metric updates on task migration that cause the total utilization value for the CPU to be reduced by the utilization of the migrated task. If that happens, the schedutil governor may see a CPU utilization reduction and will attempt to reduce the CPU frequency accordingly right away. That may be premature, though, for example if the system is generally busy and there are other runnable tasks waiting to be run on that CPU already. This is unlikely to be an issue on systems where cpufreq policies are shared between multiple CPUs, because in those cases the policy utilization is computed as the maximum of the CPU utilization values over the whole policy and if that turns out to be low, reducing the frequency for the policy most likely is a good idea anyway. On systems with one CPU per policy, however, it may affect performance adversely and even lead to increased energy consumption in some cases. On those systems it may be addressed by taking another utilization metric into consideration, like whether or not the CPU whose frequency is about to be reduced has been idle recently, because if that's not the case, the CPU is likely to be busy in the near future and its frequency should not be reduced. To that end, use the counter of idle calls in the timekeeping code. Namely, make the schedutil governor look at that counter for the current CPU every time before its frequency is about to be reduced. If the counter has not changed since the previous iteration of the governor computations for that CPU, the CPU has been busy for all that time and its frequency should not be decreased, so if the new frequency would be lower than the one set previously, the governor will skip the frequency update. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Reviewed-by: Joel Fernandes <joelaf@google.com>
2017-03-22 02:08:50 +03:00
/**
* tick_nohz_get_idle_calls - return the current idle calls counter value
*
* Called from the schedutil frequency scaling governor in scheduler context.
*/
unsigned long tick_nohz_get_idle_calls(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
return ts->idle_calls;
}
static void tick_nohz_account_idle_time(struct tick_sched *ts,
ktime_t now)
nohz: Make nohz API agnostic against idle ticks cputime accounting When the timer tick fires, it accounts the new jiffy as either part of system, user or idle time. This is how we record the cputime statistics. But when the tick is stopped from the idle task, we still need to record the number of jiffies spent tickless until we restart the tick and fall back to traditional tick-based cputime accounting. To do this, we take a snapshot of jiffies when the tick is stopped and compute the difference against the new value of jiffies when the tick is restarted. Then we account this whole difference to the idle cputime. However we are preparing to be able to stop the tick from other places than idle. So this idle time accounting needs to be performed from the callers of nohz APIs, not from the nohz APIs themselves because we now want them to be agnostic against places that stop/restart tick. Therefore, we pull the tickless idle time accounting out of generic nohz helpers up to idle entry/exit callers. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Alessio Igor Bogani <abogani@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Avi Kivity <avi@redhat.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@ti.com> Cc: Max Krasnyansky <maxk@qualcomm.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sven-Thorsten Dietrich <thebigcorporation@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de>
2011-07-28 06:00:47 +04:00
{
unsigned long ticks;
ts->idle_exittime = now;
if (vtime_accounting_enabled_this_cpu())
return;
/*
* We stopped the tick in idle. Update process times would miss the
* time we slept as update_process_times does only a 1 tick
* accounting. Enforce that this is accounted to idle !
*/
ticks = jiffies - ts->idle_jiffies;
/*
* We might be one off. Do not randomly account a huge number of ticks!
*/
2008-12-31 17:11:38 +03:00
if (ticks && ticks < LONG_MAX)
account_idle_ticks(ticks);
}
void tick_nohz_idle_restart_tick(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
if (ts->tick_stopped) {
ktime_t now = ktime_get();
tick_nohz_restart_sched_tick(ts, now);
tick_nohz_account_idle_time(ts, now);
}
}
static void tick_nohz_idle_update_tick(struct tick_sched *ts, ktime_t now)
{
if (tick_nohz_full_cpu(smp_processor_id()))
__tick_nohz_full_update_tick(ts, now);
else
tick_nohz_restart_sched_tick(ts, now);
tick_nohz_account_idle_time(ts, now);
}
/**
nohz: Separate out irq exit and idle loop dyntick logic The tick_nohz_stop_sched_tick() function, which tries to delay the next timer tick as long as possible, can be called from two places: - From the idle loop to start the dytick idle mode - From interrupt exit if we have interrupted the dyntick idle mode, so that we reprogram the next tick event in case the irq changed some internal state that requires this action. There are only few minor differences between both that are handled by that function, driven by the ts->inidle cpu variable and the inidle parameter. The whole guarantees that we only update the dyntick mode on irq exit if we actually interrupted the dyntick idle mode, and that we enter in RCU extended quiescent state from idle loop entry only. Split this function into: - tick_nohz_idle_enter(), which sets ts->inidle to 1, enters dynticks idle mode unconditionally if it can, and enters into RCU extended quiescent state. - tick_nohz_irq_exit() which only updates the dynticks idle mode when ts->inidle is set (ie: if tick_nohz_idle_enter() has been called). To maintain symmetry, tick_nohz_restart_sched_tick() has been renamed into tick_nohz_idle_exit(). This simplifies the code and micro-optimize the irq exit path (no need for local_irq_save there). This also prepares for the split between dynticks and rcu extended quiescent state logics. We'll need this split to further fix illegal uses of RCU in extended quiescent states in the idle loop. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: David Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-10-07 20:22:06 +04:00
* tick_nohz_idle_exit - restart the idle tick from the idle task
*
* Restart the idle tick when the CPU is woken up from idle
nohz: Separate out irq exit and idle loop dyntick logic The tick_nohz_stop_sched_tick() function, which tries to delay the next timer tick as long as possible, can be called from two places: - From the idle loop to start the dytick idle mode - From interrupt exit if we have interrupted the dyntick idle mode, so that we reprogram the next tick event in case the irq changed some internal state that requires this action. There are only few minor differences between both that are handled by that function, driven by the ts->inidle cpu variable and the inidle parameter. The whole guarantees that we only update the dyntick mode on irq exit if we actually interrupted the dyntick idle mode, and that we enter in RCU extended quiescent state from idle loop entry only. Split this function into: - tick_nohz_idle_enter(), which sets ts->inidle to 1, enters dynticks idle mode unconditionally if it can, and enters into RCU extended quiescent state. - tick_nohz_irq_exit() which only updates the dynticks idle mode when ts->inidle is set (ie: if tick_nohz_idle_enter() has been called). To maintain symmetry, tick_nohz_restart_sched_tick() has been renamed into tick_nohz_idle_exit(). This simplifies the code and micro-optimize the irq exit path (no need for local_irq_save there). This also prepares for the split between dynticks and rcu extended quiescent state logics. We'll need this split to further fix illegal uses of RCU in extended quiescent states in the idle loop. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: David Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-10-07 20:22:06 +04:00
* This also exit the RCU extended quiescent state. The CPU
* can use RCU again after this function is called.
*/
nohz: Separate out irq exit and idle loop dyntick logic The tick_nohz_stop_sched_tick() function, which tries to delay the next timer tick as long as possible, can be called from two places: - From the idle loop to start the dytick idle mode - From interrupt exit if we have interrupted the dyntick idle mode, so that we reprogram the next tick event in case the irq changed some internal state that requires this action. There are only few minor differences between both that are handled by that function, driven by the ts->inidle cpu variable and the inidle parameter. The whole guarantees that we only update the dyntick mode on irq exit if we actually interrupted the dyntick idle mode, and that we enter in RCU extended quiescent state from idle loop entry only. Split this function into: - tick_nohz_idle_enter(), which sets ts->inidle to 1, enters dynticks idle mode unconditionally if it can, and enters into RCU extended quiescent state. - tick_nohz_irq_exit() which only updates the dynticks idle mode when ts->inidle is set (ie: if tick_nohz_idle_enter() has been called). To maintain symmetry, tick_nohz_restart_sched_tick() has been renamed into tick_nohz_idle_exit(). This simplifies the code and micro-optimize the irq exit path (no need for local_irq_save there). This also prepares for the split between dynticks and rcu extended quiescent state logics. We'll need this split to further fix illegal uses of RCU in extended quiescent states in the idle loop. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: David Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-10-07 20:22:06 +04:00
void tick_nohz_idle_exit(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
bool idle_active, tick_stopped;
ktime_t now;
local_irq_disable();
nohz: Allow rcu extended quiescent state handling seperately from tick stop It is assumed that rcu won't be used once we switch to tickless mode and until we restart the tick. However this is not always true, as in x86-64 where we dereference the idle notifiers after the tick is stopped. To prepare for fixing this, add two new APIs: tick_nohz_idle_enter_norcu() and tick_nohz_idle_exit_norcu(). If no use of RCU is made in the idle loop between tick_nohz_enter_idle() and tick_nohz_exit_idle() calls, the arch must instead call the new *_norcu() version such that the arch doesn't need to call rcu_idle_enter() and rcu_idle_exit(). Otherwise the arch must call tick_nohz_enter_idle() and tick_nohz_exit_idle() and also call explicitly: - rcu_idle_enter() after its last use of RCU before the CPU is put to sleep. - rcu_idle_exit() before the first use of RCU after the CPU is woken up. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: David Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
2011-10-08 18:01:00 +04:00
WARN_ON_ONCE(!ts->inidle);
WARN_ON_ONCE(ts->timer_expires_base);
ts->inidle = 0;
idle_active = ts->idle_active;
tick_stopped = ts->tick_stopped;
if (idle_active || tick_stopped)
now = ktime_get();
if (idle_active)
tick_nohz_stop_idle(ts, now);
if (tick_stopped)
tick_nohz_idle_update_tick(ts, now);
local_irq_enable();
}
/*
* The nohz low res interrupt handler
*/
static void tick_nohz_handler(struct clock_event_device *dev)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
struct pt_regs *regs = get_irq_regs();
ktime_t now = ktime_get();
dev->next_event = KTIME_MAX;
tick_sched_do_timer(ts, now);
tick_sched_handle(ts, regs);
if (unlikely(ts->tick_stopped)) {
/*
* The clockevent device is not reprogrammed, so change the
* clock event device to ONESHOT_STOPPED to avoid spurious
* interrupts on devices which might not be truly one shot.
*/
tick_program_event(KTIME_MAX, 1);
nohz: Fix spurious periodic tick behaviour in low-res dynticks mode When we reach the end of the tick handler, we unconditionally reschedule the next tick to the next jiffy. Then on irq exit, the nohz code overrides that setting if needed and defers the next tick as far away in the future as possible. Now in the best dynticks case, when we actually don't need any tick in the future (ie: expires == KTIME_MAX), low-res and high-res behave differently. What we want in this case is to cancel the next tick programmed by the previous one. That's what we do in high-res mode. OTOH we lack a low-res mode equivalent of hrtimer_cancel() so we simply don't do anything in this case and the next tick remains scheduled to jiffies + 1. As a result, in low-res mode, when the dynticks code determines that no tick is needed in the future, we can recursively get a spurious tick every jiffy because then the next tick is always reprogrammed from the tick handler and is never cancelled. And this can happen indefinetly until some subsystem actually needs a precise tick in the future and only then we eventually overwrite the previous tick handler setting to defer the next tick. We are fixing this by introducing the ONESHOT_STOPPED mode which will let us pause a clockevent when no further interrupt is needed. Meanwhile we can't expect all drivers to support this new mode. So lets reduce much of the symptoms by skipping the nohz-blind tick rescheduling from the tick-handler when the CPU is in dynticks mode. That tick rescheduling wrongly assumed periodicity and the low-res dynticks code can't cancel such decision. This breaks the recursive (and thus the worst) part of the problem. In the worst case now, we'll get only one extra tick due to uncancelled tick scheduled before we entered dynticks mode. This also removes a needless clockevent write on idle ticks. Since those clock write are usually considered to be slow, it's a general win. Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2014-06-12 14:54:41 +04:00
return;
}
nohz: Fix spurious periodic tick behaviour in low-res dynticks mode When we reach the end of the tick handler, we unconditionally reschedule the next tick to the next jiffy. Then on irq exit, the nohz code overrides that setting if needed and defers the next tick as far away in the future as possible. Now in the best dynticks case, when we actually don't need any tick in the future (ie: expires == KTIME_MAX), low-res and high-res behave differently. What we want in this case is to cancel the next tick programmed by the previous one. That's what we do in high-res mode. OTOH we lack a low-res mode equivalent of hrtimer_cancel() so we simply don't do anything in this case and the next tick remains scheduled to jiffies + 1. As a result, in low-res mode, when the dynticks code determines that no tick is needed in the future, we can recursively get a spurious tick every jiffy because then the next tick is always reprogrammed from the tick handler and is never cancelled. And this can happen indefinetly until some subsystem actually needs a precise tick in the future and only then we eventually overwrite the previous tick handler setting to defer the next tick. We are fixing this by introducing the ONESHOT_STOPPED mode which will let us pause a clockevent when no further interrupt is needed. Meanwhile we can't expect all drivers to support this new mode. So lets reduce much of the symptoms by skipping the nohz-blind tick rescheduling from the tick-handler when the CPU is in dynticks mode. That tick rescheduling wrongly assumed periodicity and the low-res dynticks code can't cancel such decision. This breaks the recursive (and thus the worst) part of the problem. In the worst case now, we'll get only one extra tick due to uncancelled tick scheduled before we entered dynticks mode. This also removes a needless clockevent write on idle ticks. Since those clock write are usually considered to be slow, it's a general win. Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2014-06-12 14:54:41 +04:00
hrtimer_forward(&ts->sched_timer, now, TICK_NSEC);
tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
}
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 01:50:33 +03:00
static inline void tick_nohz_activate(struct tick_sched *ts, int mode)
{
if (!tick_nohz_enabled)
return;
ts->nohz_mode = mode;
/* One update is enough */
if (!test_and_set_bit(0, &tick_nohz_active))
timers_update_nohz();
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 01:50:33 +03:00
}
/**
* tick_nohz_switch_to_nohz - switch to nohz mode
*/
static void tick_nohz_switch_to_nohz(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
ktime_t next;
if (!tick_nohz_enabled)
return;
if (tick_switch_to_oneshot(tick_nohz_handler))
return;
/*
* Recycle the hrtimer in ts, so we can share the
* hrtimer_forward with the highres code.
*/
hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
/* Get the next period */
next = tick_init_jiffy_update();
hrtimer_set_expires(&ts->sched_timer, next);
hrtimer_forward_now(&ts->sched_timer, TICK_NSEC);
tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
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 01:50:33 +03:00
tick_nohz_activate(ts, NOHZ_MODE_LOWRES);
}
static inline void tick_nohz_irq_enter(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
ktime_t now;
if (!ts->idle_active && !ts->tick_stopped)
return;
now = ktime_get();
if (ts->idle_active)
tick_nohz_stop_idle(ts, now);
timers/nohz: Last resort update jiffies on nohz_full IRQ entry [ Upstream commit 53e87e3cdc155f20c3417b689df8d2ac88d79576 ] When at least one CPU runs in nohz_full mode, a dedicated timekeeper CPU is guaranteed to stay online and to never stop its tick. Meanwhile on some rare case, the dedicated timekeeper may be running with interrupts disabled for a while, such as in stop_machine. If jiffies stop being updated, a nohz_full CPU may end up endlessly programming the next tick in the past, taking the last jiffies update monotonic timestamp as a stale base, resulting in an tick storm. Here is a scenario where it matters: 0) CPU 0 is the timekeeper and CPU 1 a nohz_full CPU. 1) A stop machine callback is queued to execute somewhere. 2) CPU 0 reaches MULTI_STOP_DISABLE_IRQ while CPU 1 is still in MULTI_STOP_PREPARE. Hence CPU 0 can't do its timekeeping duty. CPU 1 can still take IRQs. 3) CPU 1 receives an IRQ which queues a timer callback one jiffy forward. 4) On IRQ exit, CPU 1 schedules the tick one jiffy forward, taking last_jiffies_update as a base. But last_jiffies_update hasn't been updated for 2 jiffies since the timekeeper has interrupts disabled. 5) clockevents_program_event(), which relies on ktime_get(), observes that the expiration is in the past and therefore programs the min delta event on the clock. 6) The tick fires immediately, goto 3) 7) Tick storm, the nohz_full CPU is drown and takes ages to reach MULTI_STOP_DISABLE_IRQ, which is the only way out of this situation. Solve this with unconditionally updating jiffies if the value is stale on nohz_full IRQ entry. IRQs and other disturbances are expected to be rare enough on nohz_full for the unconditional call to ktime_get() to actually matter. Reported-by: Paul E. McKenney <paulmck@kernel.org> Signed-off-by: Frederic Weisbecker <frederic@kernel.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Paul E. McKenney <paulmck@kernel.org> Link: https://lore.kernel.org/r/20211026141055.57358-2-frederic@kernel.org Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2023-08-13 06:16:20 +03:00
/*
* If all CPUs are idle. We may need to update a stale jiffies value.
* Note nohz_full is a special case: a timekeeper is guaranteed to stay
* alive but it might be busy looping with interrupts disabled in some
* rare case (typically stop machine). So we must make sure we have a
* last resort.
*/
if (ts->tick_stopped)
tick_nohz_update_jiffies(now);
}
#else
static inline void tick_nohz_switch_to_nohz(void) { }
static inline void tick_nohz_irq_enter(void) { }
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 01:50:33 +03:00
static inline void tick_nohz_activate(struct tick_sched *ts, int mode) { }
nohz: Rename CONFIG_NO_HZ to CONFIG_NO_HZ_COMMON We are planning to convert the dynticks Kconfig options layout into a choice menu. The user must be able to easily pick any of the following implementations: constant periodic tick, idle dynticks, full dynticks. As this implies a mutual exclusion, the two dynticks implementions need to converge on the selection of a common Kconfig option in order to ease the sharing of a common infrastructure. It would thus seem pretty natural to reuse CONFIG_NO_HZ to that end. It already implements all the idle dynticks code and the full dynticks depends on all that code for now. So ideally the choice menu would propose CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED then both would select CONFIG_NO_HZ. On the other hand we want to stay backward compatible: if CONFIG_NO_HZ is set in an older config file, we want to enable CONFIG_NO_HZ_IDLE by default. But we can't afford both at the same time or we run into a circular dependency: 1) CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED both select CONFIG_NO_HZ 2) If CONFIG_NO_HZ is set, we default to CONFIG_NO_HZ_IDLE We might be able to support that from Kconfig/Kbuild but it may not be wise to introduce such a confusing behaviour. So to solve this, create a new CONFIG_NO_HZ_COMMON option which gathers the common code between idle and full dynticks (that common code for now is simply the idle dynticks code) and select it from their referring Kconfig. Then we'll later create CONFIG_NO_HZ_IDLE and map CONFIG_NO_HZ to it for backward compatibility. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2011-08-11 01:21:01 +04:00
#endif /* CONFIG_NO_HZ_COMMON */
/*
* Called from irq_enter to notify about the possible interruption of idle()
*/
void tick_irq_enter(void)
{
tick_check_oneshot_broadcast_this_cpu();
tick_nohz_irq_enter();
}
/*
* High resolution timer specific code
*/
#ifdef CONFIG_HIGH_RES_TIMERS
/*
* We rearm the timer until we get disabled by the idle code.
* Called with interrupts disabled.
*/
static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
{
struct tick_sched *ts =
container_of(timer, struct tick_sched, sched_timer);
struct pt_regs *regs = get_irq_regs();
ktime_t now = ktime_get();
tick_sched_do_timer(ts, now);
/*
* Do not call, when we are not in irq context and have
* no valid regs pointer
*/
if (regs)
tick_sched_handle(ts, regs);
else
ts->next_tick = 0;
/* No need to reprogram if we are in idle or full dynticks mode */
if (unlikely(ts->tick_stopped))
return HRTIMER_NORESTART;
hrtimer_forward(timer, now, TICK_NSEC);
return HRTIMER_RESTART;
}
static int sched_skew_tick;
static int __init skew_tick(char *str)
{
get_option(&str, &sched_skew_tick);
return 0;
}
early_param("skew_tick", skew_tick);
/**
* tick_setup_sched_timer - setup the tick emulation timer
*/
void tick_setup_sched_timer(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
ktime_t now = ktime_get();
/*
* Emulate tick processing via per-CPU hrtimers:
*/
hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
ts->sched_timer.function = tick_sched_timer;
/* Get the next period (per-CPU) */
hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
/* Offset the tick to avert jiffies_lock contention. */
if (sched_skew_tick) {
u64 offset = TICK_NSEC >> 1;
do_div(offset, num_possible_cpus());
offset *= smp_processor_id();
hrtimer_add_expires_ns(&ts->sched_timer, offset);
}
hrtimer_forward(&ts->sched_timer, now, TICK_NSEC);
hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD);
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 01:50:33 +03:00
tick_nohz_activate(ts, NOHZ_MODE_HIGHRES);
}
#endif /* HIGH_RES_TIMERS */
nohz: Rename CONFIG_NO_HZ to CONFIG_NO_HZ_COMMON We are planning to convert the dynticks Kconfig options layout into a choice menu. The user must be able to easily pick any of the following implementations: constant periodic tick, idle dynticks, full dynticks. As this implies a mutual exclusion, the two dynticks implementions need to converge on the selection of a common Kconfig option in order to ease the sharing of a common infrastructure. It would thus seem pretty natural to reuse CONFIG_NO_HZ to that end. It already implements all the idle dynticks code and the full dynticks depends on all that code for now. So ideally the choice menu would propose CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED then both would select CONFIG_NO_HZ. On the other hand we want to stay backward compatible: if CONFIG_NO_HZ is set in an older config file, we want to enable CONFIG_NO_HZ_IDLE by default. But we can't afford both at the same time or we run into a circular dependency: 1) CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED both select CONFIG_NO_HZ 2) If CONFIG_NO_HZ is set, we default to CONFIG_NO_HZ_IDLE We might be able to support that from Kconfig/Kbuild but it may not be wise to introduce such a confusing behaviour. So to solve this, create a new CONFIG_NO_HZ_COMMON option which gathers the common code between idle and full dynticks (that common code for now is simply the idle dynticks code) and select it from their referring Kconfig. Then we'll later create CONFIG_NO_HZ_IDLE and map CONFIG_NO_HZ to it for backward compatibility. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Gilad Ben Yossef <gilad@benyossef.com> Cc: Hakan Akkan <hakanakkan@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kevin Hilman <khilman@linaro.org> Cc: Li Zhong <zhong@linux.vnet.ibm.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de>
2011-08-11 01:21:01 +04:00
#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS
void tick_cancel_sched_timer(int cpu)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
# ifdef CONFIG_HIGH_RES_TIMERS
if (ts->sched_timer.base)
hrtimer_cancel(&ts->sched_timer);
# endif
memset(ts, 0, sizeof(*ts));
}
#endif
/**
* Async notification about clocksource changes
*/
void tick_clock_notify(void)
{
int cpu;
for_each_possible_cpu(cpu)
set_bit(0, &per_cpu(tick_cpu_sched, cpu).check_clocks);
}
/*
* Async notification about clock event changes
*/
void tick_oneshot_notify(void)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
set_bit(0, &ts->check_clocks);
}
/**
* Check, if a change happened, which makes oneshot possible.
*
* Called cyclic from the hrtimer softirq (driven by the timer
* softirq) allow_nohz signals, that we can switch into low-res nohz
* mode, because high resolution timers are disabled (either compile
* or runtime). Called with interrupts disabled.
*/
int tick_check_oneshot_change(int allow_nohz)
{
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
if (!test_and_clear_bit(0, &ts->check_clocks))
return 0;
if (ts->nohz_mode != NOHZ_MODE_INACTIVE)
return 0;
if (!timekeeping_valid_for_hres() || !tick_is_oneshot_available())
return 0;
if (!allow_nohz)
return 1;
tick_nohz_switch_to_nohz();
return 0;
}