linux_dsm_epyc7002/kernel/time/tick-common.c

404 lines
9.8 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 12:46:24 +07:00
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
#include <linux/module.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 12:46:24 +07:00
#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;
/*
* tick_do_timer_cpu is a timer core internal variable which holds the CPU NR
* which is responsible for calling do_timer(), i.e. the timekeeping stuff. This
* variable has two functions:
*
* 1) Prevent a thundering herd issue of a gazillion of CPUs trying to grab the
* timekeeping lock all at once. Only the CPU which is assigned to do the
* update is handling it.
*
* 2) Hand off the duty in the NOHZ idle case by setting the value to
* TICK_DO_TIMER_NONE, i.e. a non existing CPU. So the next cpu which looks
* at it will take over and keep the time keeping alive. The handover
* procedure also covers cpu hotplug.
*/
int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
[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 16:28:15 +07:00
/*
* 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(&jiffies_lock);
/* Keep track of the next tick event */
tick_next_period = ktime_add(tick_next_period, tick_period);
do_timer(1);
write_sequnlock(&jiffies_lock);
update_wall_time();
}
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 = dev->next_event;
tick_periodic(cpu);
if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
return;
for (;;) {
/*
* Setup the next period for devices, which do not have
* periodic mode:
*/
next = ktime_add(next, tick_period);
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,
* which then will increment time, possibly causing
* the loop to trigger again and again.
*/
if (timekeeping_valid_for_hres())
tick_periodic(cpu);
}
}
/*
* 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(&jiffies_lock);
next = tick_next_period;
} while (read_seqretry(&jiffies_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) {
if (!tick_nohz_full_cpu(cpu))
tick_do_timer_cpu = cpu;
else
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
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
tick: Sanitize broadcast control logic The recent implementation of a generic dummy timer resulted in a different registration order of per cpu local timers which made the broadcast control logic go belly up. If the dummy timer is the first clock event device which is registered for a CPU, then it is installed, the broadcast timer is initialized and the CPU is marked as broadcast target. If a real clock event device is installed after that, we can fail to take the CPU out of the broadcast mask. In the worst case we end up with two periodic timer events firing for the same CPU. One from the per cpu hardware device and one from the broadcast. Now the problem is that we have no way to distinguish whether the system is in a state which makes broadcasting necessary or the broadcast bit was set due to the nonfunctional dummy timer installment. To solve this we need to keep track of the system state seperately and provide a more detailed decision logic whether we keep the CPU in broadcast mode or not. The old decision logic only clears the broadcast mode, if the newly installed clock event device is not affected by power states. The new logic clears the broadcast mode if one of the following is true: - The new device is not affected by power states. - The system is not in a power state affected mode - The system has switched to oneshot mode. The oneshot broadcast is controlled from the deep idle state. The CPU is not in idle at this point, so it's safe to remove it from the mask. If we clear the broadcast bit for the CPU when a new device is installed, we also shutdown the broadcast device when this was the last CPU in the broadcast mask. If the broadcast bit is kept, then we leave the new device in shutdown state and rely on the broadcast to deliver the timer interrupts via the broadcast ipis. Reported-and-tested-by: Stehle Vincent-B46079 <B46079@freescale.com> Reviewed-by: Stephen Boyd <sboyd@codeaurora.org> Cc: John Stultz <john.stultz@linaro.org>, Cc: Mark Rutland <mark.rutland@arm.com> Link: http://lkml.kernel.org/r/alpine.DEB.2.02.1307012153060.4013@ionos.tec.linutronix.de Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-07-02 03:14:10 +07:00
* way. This function also returns !=0 when we keep the
* current active broadcast state for this CPU.
*/
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);
}
void tick_install_replacement(struct clock_event_device *newdev)
{
struct tick_device *td = &__get_cpu_var(tick_cpu_device);
int cpu = smp_processor_id();
clockevents_exchange_device(td->evtdev, newdev);
tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
tick_oneshot_notify();
}
static bool tick_check_percpu(struct clock_event_device *curdev,
struct clock_event_device *newdev, int cpu)
{
if (!cpumask_test_cpu(cpu, newdev->cpumask))
return false;
if (cpumask_equal(newdev->cpumask, cpumask_of(cpu)))
return true;
/* Check if irq affinity can be set */
if (newdev->irq >= 0 && !irq_can_set_affinity(newdev->irq))
return false;
/* Prefer an existing cpu local device */
if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
return false;
return true;
}
static bool tick_check_preferred(struct clock_event_device *curdev,
struct clock_event_device *newdev)
{
/* Prefer oneshot capable device */
if (!(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) {
if (curdev && (curdev->features & CLOCK_EVT_FEAT_ONESHOT))
return false;
if (tick_oneshot_mode_active())
return false;
}
clockevents: Prefer CPU local devices over global devices On an SMP system with only one global clockevent and a dummy clockevent per CPU we run into problems. We want the dummy clockevents to be registered as the per CPU tick devices, but we can only achieve that if we register the dummy clockevents before the global clockevent or if we artificially inflate the rating of the dummy clockevents to be higher than the rating of the global clockevent. Failure to do so leads to boot hangs when the dummy timers are registered on all other CPUs besides the CPU that accepted the global clockevent as its tick device and there is no broadcast timer to poke the dummy devices. If we're registering multiple clockevents and one clockevent is global and the other is local to a particular CPU we should choose to use the local clockevent regardless of the rating of the device. This way, if the clockevent is a dummy it will take the tick device duty as long as there isn't a higher rated tick device and any global clockevent will be bumped out into broadcast mode, fixing the problem described above. Reported-and-tested-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Stephen Boyd <sboyd@codeaurora.org> Tested-by: soren.brinkmann@xilinx.com Cc: John Stultz <john.stultz@linaro.org> Cc: Daniel Lezcano <daniel.lezcano@linaro.org> Cc: linux-arm-kernel@lists.infradead.org Cc: John Stultz <john.stultz@linaro.org> Link: http://lkml.kernel.org/r/20130613183950.GA32061@codeaurora.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-06-14 01:39:50 +07:00
/*
* Use the higher rated one, but prefer a CPU local device with a lower
* rating than a non-CPU local device
*/
return !curdev ||
newdev->rating > curdev->rating ||
!cpumask_equal(curdev->cpumask, newdev->cpumask);
}
/*
* Check whether the new device is a better fit than curdev. curdev
* can be NULL !
*/
bool tick_check_replacement(struct clock_event_device *curdev,
struct clock_event_device *newdev)
{
if (!tick_check_percpu(curdev, newdev, smp_processor_id()))
return false;
return tick_check_preferred(curdev, newdev);
}
/*
* Check, if the new registered device should be used. Called with
* clockevents_lock held and interrupts disabled.
*/
void tick_check_new_device(struct clock_event_device *newdev)
{
struct clock_event_device *curdev;
struct tick_device *td;
int cpu;
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 (!tick_check_percpu(curdev, newdev, cpu))
goto out_bc;
/* Preference decision */
if (!tick_check_preferred(curdev, newdev))
goto out_bc;
if (!try_module_get(newdev->owner))
return;
/*
* 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();
return;
out_bc:
/*
* Can the new device be used as a broadcast device ?
*/
tick_install_broadcast_device(newdev);
}
/*
* Transfer the do_timer job away from a dying cpu.
*
* Called with interrupts disabled.
*/
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.
*/
void tick_shutdown(unsigned int *cpup)
{
struct tick_device *td = &per_cpu(tick_cpu_device, *cpup);
struct clock_event_device *dev = td->evtdev;
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);
dev->event_handler = clockevents_handle_noop;
td->evtdev = NULL;
}
}
void tick_suspend(void)
{
struct tick_device *td = &__get_cpu_var(tick_cpu_device);
clockevents_shutdown(td->evtdev);
}
void tick_resume(void)
{
struct tick_device *td = &__get_cpu_var(tick_cpu_device);
int broadcast = tick_resume_broadcast();
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();
}
}
/**
* tick_init - initialize the tick control
*/
void __init tick_init(void)
{
tick_broadcast_init();
}