Merge tag 'v5.4-rc7' into sched/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/time/hrtimer.c

@@ -164,7 +164,7 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 	struct hrtimer_clock_base *base;
 
 	for (;;) {
-		base = timer->base;
+		base = READ_ONCE(timer->base);
 		if (likely(base != &migration_base)) {
 			raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
 			if (likely(base == timer->base))
@@ -244,7 +244,7 @@ again:
 			return base;
 
 		/* See the comment in lock_hrtimer_base() */
-		timer->base = &migration_base;
+		WRITE_ONCE(timer->base, &migration_base);
 		raw_spin_unlock(&base->cpu_base->lock);
 		raw_spin_lock(&new_base->cpu_base->lock);
 
@@ -253,10 +253,10 @@ again:
 			raw_spin_unlock(&new_base->cpu_base->lock);
 			raw_spin_lock(&base->cpu_base->lock);
 			new_cpu_base = this_cpu_base;
-			timer->base = base;
+			WRITE_ONCE(timer->base, base);
 			goto again;
 		}
-		timer->base = new_base;
+		WRITE_ONCE(timer->base, new_base);
 	} else {
 		if (new_cpu_base != this_cpu_base &&
 		    hrtimer_check_target(timer, new_base)) {

kernel/time/posix-cpu-timers.c

@@ -266,7 +266,7 @@ static void update_gt_cputime(struct task_cputime_atomic *cputime_atomic,
 /**
  * thread_group_sample_cputime - Sample cputime for a given task
  * @tsk:	Task for which cputime needs to be started
- * @iimes:	Storage for time samples
+ * @samples:	Storage for time samples
  *
  * Called from sys_getitimer() to calculate the expiry time of an active
  * timer. That means group cputime accounting is already active. Called
@@ -1038,12 +1038,12 @@ unlock:
  * member of @pct->bases[CLK].nextevt. False otherwise
  */
 static inline bool
-task_cputimers_expired(const u64 *sample, struct posix_cputimers *pct)
+task_cputimers_expired(const u64 *samples, struct posix_cputimers *pct)
 {
 	int i;
 
 	for (i = 0; i < CPUCLOCK_MAX; i++) {
-		if (sample[i] >= pct->bases[i].nextevt)
+		if (samples[i] >= pct->bases[i].nextevt)
 			return true;
 	}
 	return false;

kernel/time/sched_clock.c

@@ -17,6 +17,8 @@
 #include <linux/seqlock.h>
 #include <linux/bitops.h>
 
+#include "timekeeping.h"
+
 /**
  * struct clock_read_data - data required to read from sched_clock()
  *

kernel/time/tick-broadcast-hrtimer.c

@@ -42,39 +42,39 @@ static int bc_shutdown(struct clock_event_device *evt)
  */
 static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
 {
-	int bc_moved;
 	/*
-	 * We try to cancel the timer first. If the callback is on
-	 * flight on some other cpu then we let it handle it. If we
-	 * were able to cancel the timer nothing can rearm it as we
-	 * own broadcast_lock.
+	 * This is called either from enter/exit idle code or from the
+	 * broadcast handler. In all cases tick_broadcast_lock is held.
 	 *
-	 * However we can also be called from the event handler of
-	 * ce_broadcast_hrtimer itself when it expires. We cannot
-	 * restart the timer because we are in the callback, but we
-	 * can set the expiry time and let the callback return
-	 * HRTIMER_RESTART.
+	 * hrtimer_cancel() cannot be called here neither from the
+	 * broadcast handler nor from the enter/exit idle code. The idle
+	 * code can run into the problem described in bc_shutdown() and the
+	 * broadcast handler cannot wait for itself to complete for obvious
+	 * reasons.
 	 *
-	 * Since we are in the idle loop at this point and because
-	 * hrtimer_{start/cancel} functions call into tracing,
-	 * calls to these functions must be bound within RCU_NONIDLE.
+	 * Each caller tries to arm the hrtimer on its own CPU, but if the
+	 * hrtimer callbback function is currently running, then
+	 * hrtimer_start() cannot move it and the timer stays on the CPU on
+	 * which it is assigned at the moment.
+	 *
+	 * As this can be called from idle code, the hrtimer_start()
+	 * invocation has to be wrapped with RCU_NONIDLE() as
+	 * hrtimer_start() can call into tracing.
 	 */
-	RCU_NONIDLE(
-		{
-			bc_moved = hrtimer_try_to_cancel(&bctimer) >= 0;
-			if (bc_moved) {
-				hrtimer_start(&bctimer, expires,
-					      HRTIMER_MODE_ABS_PINNED_HARD);
-			}
-		}
-	);
-
-	if (bc_moved) {
-		/* Bind the "device" to the cpu */
-		bc->bound_on = smp_processor_id();
-	} else if (bc->bound_on == smp_processor_id()) {
-		hrtimer_set_expires(&bctimer, expires);
-	}
+	RCU_NONIDLE( {
+		hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED_HARD);
+		/*
+		 * The core tick broadcast mode expects bc->bound_on to be set
+		 * correctly to prevent a CPU which has the broadcast hrtimer
+		 * armed from going deep idle.
+		 *
+		 * As tick_broadcast_lock is held, nothing can change the cpu
+		 * base which was just established in hrtimer_start() above. So
+		 * the below access is safe even without holding the hrtimer
+		 * base lock.
+		 */
+		bc->bound_on = bctimer.base->cpu_base->cpu;
+	} );
 	return 0;
 }
 
@@ -100,10 +100,6 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t)
 {
 	ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
 
-	if (clockevent_state_oneshot(&ce_broadcast_hrtimer))
-		if (ce_broadcast_hrtimer.next_event != KTIME_MAX)
-			return HRTIMER_RESTART;
-
 	return HRTIMER_NORESTART;
 }
 

kernel/time/vsyscall.c

@@ -110,8 +110,7 @@ void update_vsyscall(struct timekeeper *tk)
 	nsec		= nsec + tk->wall_to_monotonic.tv_nsec;
 	vdso_ts->sec	+= __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec);
 
-	if (__arch_use_vsyscall(vdata))
-		update_vdso_data(vdata, tk);
+	update_vdso_data(vdata, tk);
 
 	__arch_update_vsyscall(vdata, tk);
 
@@ -124,10 +123,8 @@ void update_vsyscall_tz(void)
 {
 	struct vdso_data *vdata = __arch_get_k_vdso_data();
 
-	if (__arch_use_vsyscall(vdata)) {
-		vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest;
-		vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime;
-	}
+	vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest;
+	vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime;
 
 	__arch_sync_vdso_data(vdata);
 }