Commit cea92e84 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull timer fixes from Thomas Gleixner:
 "A pile of fixes for long standing issues with the timer wheel and the
  NOHZ code:

   - Prevent timer base confusion accross the nohz switch, which can
     cause unlocked access and data corruption

   - Reinitialize the stale base clock on cpu hotplug to prevent subtle
     side effects including rollovers on 32bit

   - Prevent an interrupt storm when the timer softirq is already
     pending caused by tick_nohz_stop_sched_tick()

   - Move the timer start tracepoint to a place where it actually makes
     sense

   - Add documentation to timerqueue functions as they caused confusion
     several times now"

* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  timerqueue: Document return values of timerqueue_add/del()
  timers: Invoke timer_start_debug() where it makes sense
  nohz: Prevent a timer interrupt storm in tick_nohz_stop_sched_tick()
  timers: Reinitialize per cpu bases on hotplug
  timers: Use deferrable base independent of base::nohz_active
parents 8d517bdf 9f4533cd

include/linux/cpuhotplug.h

+1 −1
Original line number Diff line number Diff line
@@ -86,7 +86,7 @@ enum cpuhp_state { 
	CPUHP_MM_ZSWP_POOL_PREPARE,

	CPUHP_KVM_PPC_BOOK3S_PREPARE,

	CPUHP_ZCOMP_PREPARE,

	CPUHP_TIMERS_DEAD,

	CPUHP_TIMERS_PREPARE,

	CPUHP_MIPS_SOC_PREPARE,

	CPUHP_BP_PREPARE_DYN,

	CPUHP_BP_PREPARE_DYN_END		= CPUHP_BP_PREPARE_DYN + 20,

include/linux/timer.h

+3 −1
Original line number Diff line number Diff line
@@ -207,8 +207,10 @@ unsigned long round_jiffies_up(unsigned long j); 
unsigned long round_jiffies_up_relative(unsigned long j);



#ifdef CONFIG_HOTPLUG_CPU

int timers_prepare_cpu(unsigned int cpu);

int timers_dead_cpu(unsigned int cpu);

#else

#define timers_prepare_cpu	NULL

#define timers_dead_cpu		NULL

#endif

kernel/cpu.c

+2 −2
Original line number Diff line number Diff line
@@ -1277,9 +1277,9 @@ static struct cpuhp_step cpuhp_bp_states[] = { 
	 * before blk_mq_queue_reinit_notify() from notify_dead(),

	 * otherwise a RCU stall occurs.

	 */

	[CPUHP_TIMERS_DEAD] = {

	[CPUHP_TIMERS_PREPARE] = {

		.name			= "timers:dead",

		.startup.single		= NULL,

		.startup.single		= timers_prepare_cpu,

		.teardown.single	= timers_dead_cpu,

	},

	/* Kicks the plugged cpu into life */

kernel/time/tick-sched.c

+17 −2
Original line number Diff line number Diff line
@@ -650,6 +650,11 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) 
	ts->next_tick = 0;

}



static inline bool local_timer_softirq_pending(void)

{

	return local_softirq_pending() & TIMER_SOFTIRQ;

}



static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,

					 ktime_t now, int cpu)

{
@@ -666,8 +671,18 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, 
	} while (read_seqretry(&jiffies_lock, seq));

	ts->last_jiffies = basejiff;



	if (rcu_needs_cpu(basemono, &next_rcu) ||

	    arch_needs_cpu() || irq_work_needs_cpu()) {

	/*

	 * 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

	 * immeditate expiry, which rearms the hardware timer with a

	 * 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 {

		/*

kernel/time/timer.c

+24 −11
Original line number Diff line number Diff line
@@ -823,11 +823,10 @@ static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) 
	struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu);



	/*

	 * If the timer is deferrable and nohz is active then we need to use

	 * the deferrable base.

	 * If the timer is deferrable and NO_HZ_COMMON is set then we need

	 * to use the deferrable base.

	 */

	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&

	    (tflags & TIMER_DEFERRABLE))

	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))

		base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu);

	return base;

}
@@ -837,11 +836,10 @@ static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) 
	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);



	/*

	 * If the timer is deferrable and nohz is active then we need to use

	 * the deferrable base.

	 * If the timer is deferrable and NO_HZ_COMMON is set then we need

	 * to use the deferrable base.

	 */

	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&

	    (tflags & TIMER_DEFERRABLE))

	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))

		base = this_cpu_ptr(&timer_bases[BASE_DEF]);

	return base;

}
@@ -1009,8 +1007,6 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option 
	if (!ret && (options & MOD_TIMER_PENDING_ONLY))

		goto out_unlock;



	debug_activate(timer, expires);



	new_base = get_target_base(base, timer->flags);



	if (base != new_base) {
@@ -1034,6 +1030,8 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option 
		}

	}



	debug_activate(timer, expires);



	timer->expires = expires;

	/*

	 * If 'idx' was calculated above and the base time did not advance
@@ -1684,7 +1682,7 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h) 
	base->must_forward_clk = false;



	__run_timers(base);

	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active)

	if (IS_ENABLED(CONFIG_NO_HZ_COMMON))

		__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));

}
@@ -1855,6 +1853,21 @@ static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *h 
	}

}



int timers_prepare_cpu(unsigned int cpu)

{

	struct timer_base *base;

	int b;



	for (b = 0; b < NR_BASES; b++) {

		base = per_cpu_ptr(&timer_bases[b], cpu);

		base->clk = jiffies;

		base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;

		base->is_idle = false;

		base->must_forward_clk = true;

	}

	return 0;

}



int timers_dead_cpu(unsigned int cpu)

{

	struct timer_base *old_base;

CRA Git | Maintained and supported by SUSTech CRA and CCSE