kernel_optimize_test/kernel/time/tick-common.c

420 lines
9.5 KiB
C
Raw Normal View History

/*
* linux/kernel/time/tick-common.c
*
* This file contains the base functions to manage periodic tick
* related events.
*
* 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
*
* This code is licenced under the GPL version 2. For details see
* kernel-base/COPYING.
*/
#include <linux/cpu.h>
#include <linux/err.h>
#include <linux/hrtimer.h>
[S390] genirq/clockevents: move irq affinity prototypes/inlines to interrupt.h > Generic code is not supposed to include irq.h. Replace this include > by linux/hardirq.h instead and add/replace an include of linux/irq.h > in asm header files where necessary. > This change should only matter for architectures that make use of > GENERIC_CLOCKEVENTS. > Architectures in question are mips, x86, arm, sh, powerpc, uml and sparc64. > > I did some cross compile tests for mips, x86_64, arm, powerpc and sparc64. > This patch fixes also build breakages caused by the include replacement in > tick-common.h. I generally dislike adding optional linux/* includes in asm/* includes - I'm nervous about this causing include loops. However, there's a separate point to be discussed here. That is, what interfaces are expected of every architecture in the kernel. If generic code wants to be able to set the affinity of interrupts, then that needs to become part of the interfaces listed in linux/interrupt.h rather than linux/irq.h. So what I suggest is this approach instead (against Linus' tree of a couple of days ago) - we move irq_set_affinity() and irq_can_set_affinity() to linux/interrupt.h, change the linux/irq.h includes to linux/interrupt.h and include asm/irq_regs.h where needed (asm/irq_regs.h is supposed to be rarely used include since not much touches the stacked parent context registers.) Build tested on ARM PXA family kernels and ARM's Realview platform kernels which both use genirq. [ tglx@linutronix.de: add GENERIC_HARDIRQ dependencies ] Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:24 +08:00
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
[S390] genirq/clockevents: move irq affinity prototypes/inlines to interrupt.h > Generic code is not supposed to include irq.h. Replace this include > by linux/hardirq.h instead and add/replace an include of linux/irq.h > in asm header files where necessary. > This change should only matter for architectures that make use of > GENERIC_CLOCKEVENTS. > Architectures in question are mips, x86, arm, sh, powerpc, uml and sparc64. > > I did some cross compile tests for mips, x86_64, arm, powerpc and sparc64. > This patch fixes also build breakages caused by the include replacement in > tick-common.h. I generally dislike adding optional linux/* includes in asm/* includes - I'm nervous about this causing include loops. However, there's a separate point to be discussed here. That is, what interfaces are expected of every architecture in the kernel. If generic code wants to be able to set the affinity of interrupts, then that needs to become part of the interfaces listed in linux/interrupt.h rather than linux/irq.h. So what I suggest is this approach instead (against Linus' tree of a couple of days ago) - we move irq_set_affinity() and irq_can_set_affinity() to linux/interrupt.h, change the linux/irq.h includes to linux/interrupt.h and include asm/irq_regs.h where needed (asm/irq_regs.h is supposed to be rarely used include since not much touches the stacked parent context registers.) Build tested on ARM PXA family kernels and ARM's Realview platform kernels which both use genirq. [ tglx@linutronix.de: add GENERIC_HARDIRQ dependencies ] Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:24 +08:00
#include <asm/irq_regs.h>
#include "tick-internal.h"
/*
* Tick devices
*/
DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
/*
* Tick next event: keeps track of the tick time
*/
ktime_t tick_next_period;
ktime_t tick_period;
int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
static DEFINE_RAW_SPINLOCK(tick_device_lock);
[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 17:28:15 +08:00
/*
* Debugging: see timer_list.c
*/
struct tick_device *tick_get_device(int cpu)
{
return &per_cpu(tick_cpu_device, cpu);
}
/**
* tick_is_oneshot_available - check for a oneshot capable event device
*/
int tick_is_oneshot_available(void)
{
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT))
return 0;
if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
return 1;
return tick_broadcast_oneshot_available();
}
/*
* Periodic tick
*/
static void tick_periodic(int cpu)
{
if (tick_do_timer_cpu == cpu) {
write_seqlock(&xtime_lock);
/* Keep track of the next tick event */
tick_next_period = ktime_add(tick_next_period, tick_period);
do_timer(1);
write_sequnlock(&xtime_lock);
}
update_process_times(user_mode(get_irq_regs()));
profile_tick(CPU_PROFILING);
}
/*
* Event handler for periodic ticks
*/
void tick_handle_periodic(struct clock_event_device *dev)
{
int cpu = smp_processor_id();
ktime_t next;
tick_periodic(cpu);
if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
return;
/*
* Setup the next period for devices, which do not have
* periodic mode:
*/
next = ktime_add(dev->next_event, tick_period);
for (;;) {
if (!clockevents_program_event(dev, next, false))
return;
/*
* Have to be careful here. If we're in oneshot mode,
* before we call tick_periodic() in a loop, we need
* to be sure we're using a real hardware clocksource.
* Otherwise we could get trapped in an infinite
* loop, as the tick_periodic() increments jiffies,
* when then will increment time, posibly causing
* the loop to trigger again and again.
*/
if (timekeeping_valid_for_hres())
tick_periodic(cpu);
next = ktime_add(next, tick_period);
}
}
/*
* Setup the device for a periodic tick
*/
void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
{
tick_set_periodic_handler(dev, broadcast);
/* Broadcast setup ? */
if (!tick_device_is_functional(dev))
return;
if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
!tick_broadcast_oneshot_active()) {
clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC);
} else {
unsigned long seq;
ktime_t next;
do {
seq = read_seqbegin(&xtime_lock);
next = tick_next_period;
} while (read_seqretry(&xtime_lock, seq));
clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
for (;;) {
if (!clockevents_program_event(dev, next, false))
return;
next = ktime_add(next, tick_period);
}
}
}
/*
* Setup the tick device
*/
static void tick_setup_device(struct tick_device *td,
struct clock_event_device *newdev, int cpu,
const struct cpumask *cpumask)
{
ktime_t next_event;
void (*handler)(struct clock_event_device *) = NULL;
/*
* First device setup ?
*/
if (!td->evtdev) {
/*
* If no cpu took the do_timer update, assign it to
* this cpu:
*/
if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
tick_do_timer_cpu = cpu;
tick_next_period = ktime_get();
tick_period = ktime_set(0, NSEC_PER_SEC / HZ);
}
/*
* Startup in periodic mode first.
*/
td->mode = TICKDEV_MODE_PERIODIC;
} else {
handler = td->evtdev->event_handler;
next_event = td->evtdev->next_event;
td->evtdev->event_handler = clockevents_handle_noop;
}
td->evtdev = newdev;
/*
* When the device is not per cpu, pin the interrupt to the
* current cpu:
*/
if (!cpumask_equal(newdev->cpumask, cpumask))
irq_set_affinity(newdev->irq, cpumask);
/*
* When global broadcasting is active, check if the current
* device is registered as a placeholder for broadcast mode.
* This allows us to handle this x86 misfeature in a generic
* way.
*/
if (tick_device_uses_broadcast(newdev, cpu))
return;
if (td->mode == TICKDEV_MODE_PERIODIC)
tick_setup_periodic(newdev, 0);
else
tick_setup_oneshot(newdev, handler, next_event);
}
/*
* Check, if the new registered device should be used.
*/
static int tick_check_new_device(struct clock_event_device *newdev)
{
struct clock_event_device *curdev;
struct tick_device *td;
int cpu, ret = NOTIFY_OK;
unsigned long flags;
raw_spin_lock_irqsave(&tick_device_lock, flags);
cpu = smp_processor_id();
if (!cpumask_test_cpu(cpu, newdev->cpumask))
goto out_bc;
td = &per_cpu(tick_cpu_device, cpu);
curdev = td->evtdev;
/* cpu local device ? */
if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) {
/*
* If the cpu affinity of the device interrupt can not
* be set, ignore it.
*/
if (!irq_can_set_affinity(newdev->irq))
goto out_bc;
/*
* If we have a cpu local device already, do not replace it
* by a non cpu local device
*/
if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
goto out_bc;
}
/*
* If we have an active device, then check the rating and the oneshot
* feature.
*/
if (curdev) {
/*
* Prefer one shot capable devices !
*/
if ((curdev->features & CLOCK_EVT_FEAT_ONESHOT) &&
!(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
goto out_bc;
/*
* Check the rating
*/
if (curdev->rating >= newdev->rating)
goto out_bc;
}
/*
* Replace the eventually existing device by the new
* device. If the current device is the broadcast device, do
* not give it back to the clockevents layer !
*/
if (tick_is_broadcast_device(curdev)) {
clockevents_shutdown(curdev);
curdev = NULL;
}
clockevents_exchange_device(curdev, newdev);
tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
tick_oneshot_notify();
raw_spin_unlock_irqrestore(&tick_device_lock, flags);
return NOTIFY_STOP;
out_bc:
/*
* Can the new device be used as a broadcast device ?
*/
if (tick_check_broadcast_device(newdev))
ret = NOTIFY_STOP;
raw_spin_unlock_irqrestore(&tick_device_lock, flags);
return ret;
}
/*
* Transfer the do_timer job away from a dying cpu.
*
* Called with interrupts disabled.
*/
static void tick_handover_do_timer(int *cpup)
{
if (*cpup == tick_do_timer_cpu) {
int cpu = cpumask_first(cpu_online_mask);
tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
TICK_DO_TIMER_NONE;
}
}
/*
* Shutdown an event device on a given cpu:
*
* This is called on a life CPU, when a CPU is dead. So we cannot
* access the hardware device itself.
* We just set the mode and remove it from the lists.
*/
static void tick_shutdown(unsigned int *cpup)
{
struct tick_device *td = &per_cpu(tick_cpu_device, *cpup);
struct clock_event_device *dev = td->evtdev;
unsigned long flags;
raw_spin_lock_irqsave(&tick_device_lock, flags);
td->mode = TICKDEV_MODE_PERIODIC;
if (dev) {
/*
* Prevent that the clock events layer tries to call
* the set mode function!
*/
dev->mode = CLOCK_EVT_MODE_UNUSED;
clockevents_exchange_device(dev, NULL);
td->evtdev = NULL;
}
raw_spin_unlock_irqrestore(&tick_device_lock, flags);
}
static void tick_suspend(void)
{
struct tick_device *td = &__get_cpu_var(tick_cpu_device);
unsigned long flags;
raw_spin_lock_irqsave(&tick_device_lock, flags);
clockevents_shutdown(td->evtdev);
raw_spin_unlock_irqrestore(&tick_device_lock, flags);
}
static void tick_resume(void)
{
struct tick_device *td = &__get_cpu_var(tick_cpu_device);
unsigned long flags;
int broadcast = tick_resume_broadcast();
raw_spin_lock_irqsave(&tick_device_lock, flags);
clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME);
if (!broadcast) {
if (td->mode == TICKDEV_MODE_PERIODIC)
tick_setup_periodic(td->evtdev, 0);
else
tick_resume_oneshot();
}
raw_spin_unlock_irqrestore(&tick_device_lock, flags);
}
/*
* Notification about clock event devices
*/
static int tick_notify(struct notifier_block *nb, unsigned long reason,
void *dev)
{
switch (reason) {
case CLOCK_EVT_NOTIFY_ADD:
return tick_check_new_device(dev);
case CLOCK_EVT_NOTIFY_BROADCAST_ON:
case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
tick_broadcast_on_off(reason, dev);
break;
case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
tick_broadcast_oneshot_control(reason);
break;
case CLOCK_EVT_NOTIFY_CPU_DYING:
tick_handover_do_timer(dev);
break;
case CLOCK_EVT_NOTIFY_CPU_DEAD:
tick_shutdown_broadcast_oneshot(dev);
tick_shutdown_broadcast(dev);
tick_shutdown(dev);
break;
case CLOCK_EVT_NOTIFY_SUSPEND:
tick_suspend();
tick_suspend_broadcast();
break;
case CLOCK_EVT_NOTIFY_RESUME:
tick_resume();
break;
default:
break;
}
return NOTIFY_OK;
}
static struct notifier_block tick_notifier = {
.notifier_call = tick_notify,
};
/**
* tick_init - initialize the tick control
*
* Register the notifier with the clockevents framework
*/
void __init tick_init(void)
{
clockevents_register_notifier(&tick_notifier);
}