提交 9cf57731 编写于 作者: P Peter Zijlstra 提交者: Ingo Molnar

watchdog/softlockup: Replace "watchdog/%u" threads with cpu_stop_work

Oleg suggested to replace the "watchdog/%u" threads with
cpu_stop_work. That removes one thread per CPU while at the same time
fixes softlockup vs SCHED_DEADLINE.

But more importantly, it does away with the single
smpboot_update_cpumask_percpu_thread() user, which allows
cleanups/shrinkage of the smpboot interface.
Suggested-by: NOleg Nesterov <oleg@redhat.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: NIngo Molnar <mingo@kernel.org>
上级 4520843d
......@@ -164,6 +164,7 @@ enum cpuhp_state {
CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE,
CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE,
CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE,
CPUHP_AP_WATCHDOG_ONLINE,
CPUHP_AP_WORKQUEUE_ONLINE,
CPUHP_AP_RCUTREE_ONLINE,
CPUHP_AP_ONLINE_DYN,
......
......@@ -33,10 +33,15 @@ extern int sysctl_hardlockup_all_cpu_backtrace;
#define sysctl_hardlockup_all_cpu_backtrace 0
#endif /* !CONFIG_SMP */
extern int lockup_detector_online_cpu(unsigned int cpu);
extern int lockup_detector_offline_cpu(unsigned int cpu);
#else /* CONFIG_LOCKUP_DETECTOR */
static inline void lockup_detector_init(void) { }
static inline void lockup_detector_soft_poweroff(void) { }
static inline void lockup_detector_cleanup(void) { }
#define lockup_detector_online_cpu NULL
#define lockup_detector_offline_cpu NULL
#endif /* !CONFIG_LOCKUP_DETECTOR */
#ifdef CONFIG_SOFTLOCKUP_DETECTOR
......
......@@ -1344,6 +1344,11 @@ static struct cpuhp_step cpuhp_hp_states[] = {
.startup.single = perf_event_init_cpu,
.teardown.single = perf_event_exit_cpu,
},
[CPUHP_AP_WATCHDOG_ONLINE] = {
.name = "lockup_detector:online",
.startup.single = lockup_detector_online_cpu,
.teardown.single = lockup_detector_offline_cpu,
},
[CPUHP_AP_WORKQUEUE_ONLINE] = {
.name = "workqueue:online",
.startup.single = workqueue_online_cpu,
......
......@@ -18,18 +18,14 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <linux/smpboot.h>
#include <linux/sched/rt.h>
#include <uapi/linux/sched/types.h>
#include <linux/tick.h>
#include <linux/workqueue.h>
#include <linux/sched/clock.h>
#include <linux/sched/debug.h>
#include <linux/sched/isolation.h>
#include <linux/stop_machine.h>
#include <asm/irq_regs.h>
#include <linux/kvm_para.h>
#include <linux/kthread.h>
static DEFINE_MUTEX(watchdog_mutex);
......@@ -169,11 +165,10 @@ static void lockup_detector_update_enable(void)
unsigned int __read_mostly softlockup_panic =
CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
static bool softlockup_threads_initialized __read_mostly;
static bool softlockup_initialized __read_mostly;
static u64 __read_mostly sample_period;
static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
static DEFINE_PER_CPU(bool, softlockup_touch_sync);
static DEFINE_PER_CPU(bool, soft_watchdog_warn);
......@@ -335,6 +330,25 @@ static void watchdog_interrupt_count(void)
__this_cpu_inc(hrtimer_interrupts);
}
/*
* The watchdog thread function - touches the timestamp.
*
* It only runs once every sample_period seconds (4 seconds by
* default) to reset the softlockup timestamp. If this gets delayed
* for more than 2*watchdog_thresh seconds then the debug-printout
* triggers in watchdog_timer_fn().
*/
static int softlockup_fn(void *data)
{
__this_cpu_write(soft_lockup_hrtimer_cnt,
__this_cpu_read(hrtimer_interrupts));
__touch_watchdog();
return 0;
}
static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
/* watchdog kicker functions */
static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
{
......@@ -350,7 +364,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
watchdog_interrupt_count();
/* kick the softlockup detector */
wake_up_process(__this_cpu_read(softlockup_watchdog));
stop_one_cpu_nowait(smp_processor_id(),
softlockup_fn, NULL,
this_cpu_ptr(&softlockup_stop_work));
/* .. and repeat */
hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
......@@ -448,17 +464,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
return HRTIMER_RESTART;
}
static void watchdog_set_prio(unsigned int policy, unsigned int prio)
{
struct sched_param param = { .sched_priority = prio };
sched_setscheduler(current, policy, &param);
}
static void watchdog_enable(unsigned int cpu)
{
struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
WARN_ON_ONCE(cpu != smp_processor_id());
/*
* Start the timer first to prevent the NMI watchdog triggering
* before the timer has a chance to fire.
......@@ -473,15 +484,14 @@ static void watchdog_enable(unsigned int cpu)
/* Enable the perf event */
if (watchdog_enabled & NMI_WATCHDOG_ENABLED)
watchdog_nmi_enable(cpu);
watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
}
static void watchdog_disable(unsigned int cpu)
{
struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
watchdog_set_prio(SCHED_NORMAL, 0);
WARN_ON_ONCE(cpu != smp_processor_id());
/*
* Disable the perf event first. That prevents that a large delay
* between disabling the timer and disabling the perf event causes
......@@ -491,77 +501,63 @@ static void watchdog_disable(unsigned int cpu)
hrtimer_cancel(hrtimer);
}
static void watchdog_cleanup(unsigned int cpu, bool online)
static int softlockup_stop_fn(void *data)
{
watchdog_disable(cpu);
watchdog_disable(smp_processor_id());
return 0;
}
static int watchdog_should_run(unsigned int cpu)
static void softlockup_stop_all(void)
{
return __this_cpu_read(hrtimer_interrupts) !=
__this_cpu_read(soft_lockup_hrtimer_cnt);
int cpu;
if (!softlockup_initialized)
return;
for_each_cpu(cpu, &watchdog_allowed_mask)
smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false);
cpumask_clear(&watchdog_allowed_mask);
}
/*
* The watchdog thread function - touches the timestamp.
*
* It only runs once every sample_period seconds (4 seconds by
* default) to reset the softlockup timestamp. If this gets delayed
* for more than 2*watchdog_thresh seconds then the debug-printout
* triggers in watchdog_timer_fn().
*/
static void watchdog(unsigned int cpu)
static int softlockup_start_fn(void *data)
{
__this_cpu_write(soft_lockup_hrtimer_cnt,
__this_cpu_read(hrtimer_interrupts));
__touch_watchdog();
watchdog_enable(smp_processor_id());
return 0;
}
static struct smp_hotplug_thread watchdog_threads = {
.store = &softlockup_watchdog,
.thread_should_run = watchdog_should_run,
.thread_fn = watchdog,
.thread_comm = "watchdog/%u",
.setup = watchdog_enable,
.cleanup = watchdog_cleanup,
.park = watchdog_disable,
.unpark = watchdog_enable,
};
static void softlockup_update_smpboot_threads(void)
static void softlockup_start_all(void)
{
lockdep_assert_held(&watchdog_mutex);
if (!softlockup_threads_initialized)
return;
int cpu;
smpboot_update_cpumask_percpu_thread(&watchdog_threads,
&watchdog_allowed_mask);
cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
for_each_cpu(cpu, &watchdog_allowed_mask)
smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false);
}
/* Temporarily park all watchdog threads */
static void softlockup_park_all_threads(void)
int lockup_detector_online_cpu(unsigned int cpu)
{
cpumask_clear(&watchdog_allowed_mask);
softlockup_update_smpboot_threads();
watchdog_enable(cpu);
return 0;
}
/* Unpark enabled threads */
static void softlockup_unpark_threads(void)
int lockup_detector_offline_cpu(unsigned int cpu)
{
cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
softlockup_update_smpboot_threads();
watchdog_disable(cpu);
return 0;
}
static void lockup_detector_reconfigure(void)
{
cpus_read_lock();
watchdog_nmi_stop();
softlockup_park_all_threads();
softlockup_stop_all();
set_sample_period();
lockup_detector_update_enable();
if (watchdog_enabled && watchdog_thresh)
softlockup_unpark_threads();
softlockup_start_all();
watchdog_nmi_start();
cpus_read_unlock();
/*
......@@ -580,8 +576,6 @@ static void lockup_detector_reconfigure(void)
*/
static __init void lockup_detector_setup(void)
{
int ret;
/*
* If sysctl is off and watchdog got disabled on the command line,
* nothing to do here.
......@@ -592,24 +586,13 @@ static __init void lockup_detector_setup(void)
!(watchdog_enabled && watchdog_thresh))
return;
ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
&watchdog_allowed_mask);
if (ret) {
pr_err("Failed to initialize soft lockup detector threads\n");
return;
}
mutex_lock(&watchdog_mutex);
softlockup_threads_initialized = true;
lockup_detector_reconfigure();
softlockup_initialized = true;
mutex_unlock(&watchdog_mutex);
}
#else /* CONFIG_SOFTLOCKUP_DETECTOR */
static inline int watchdog_park_threads(void) { return 0; }
static inline void watchdog_unpark_threads(void) { }
static inline int watchdog_enable_all_cpus(void) { return 0; }
static inline void watchdog_disable_all_cpus(void) { }
static void lockup_detector_reconfigure(void)
{
cpus_read_lock();
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册