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

Pull timer updates from Thomas Gleixner:
 "The timer departement provides:

   - More y2038 work in the area of ntp and pps.

   - Optimization of posix cpu timers

   - New time related selftests

   - Some new clocksource drivers

   - The usual pile of fixes, cleanups and improvements"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (25 commits)
  timeconst: Update path in comment
  timers/x86/hpet: Type adjustments
  clocksource/drivers/armada-370-xp: Implement ARM delay timer
  clocksource/drivers/tango_xtal: Add new timer for Tango SoCs
  clocksource/drivers/imx: Allow timer irq affinity change
  clocksource/drivers/exynos_mct: Use container_of() instead of this_cpu_ptr()
  clocksource/drivers/h8300_*: Remove unneeded memset()s
  clocksource/drivers/sh_cmt: Remove unneeded memset() in sh_cmt_setup()
  clocksource/drivers/em_sti: Remove unneeded memset()s
  clocksource/drivers/mediatek: Use GPT as sched clock source
  clockevents/drivers/mtk: Fix spurious interrupt leading to crash
  posix_cpu_timer: Reduce unnecessary sighand lock contention
  posix_cpu_timer: Convert cputimer->running to bool
  posix_cpu_timer: Check thread timers only when there are active thread timers
  posix_cpu_timer: Optimize fastpath_timer_check()
  timers, kselftest: Add 'adjtick' test to validate adjtimex() tick adjustments
  timers: Use __fls in apply_slack()
  clocksource: Remove return statement from void functions
  net: sfc: avoid using timespec
  ntp/pps: use y2038 safe types in pps_event_time
  ...

9 files changed, 79 insertions, 46 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 2845623fb582..6ac894244d39 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1101,7 +1101,7 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
 	cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
 	if (cpu_limit != RLIM_INFINITY) {
 		sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit);
-		sig->cputimer.running = 1;
+		sig->cputimer.running = true;
 	}
 
 	/* The timer lists. */
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 3a38775b50c2..0d8fe8b8f727 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -479,7 +479,7 @@ static u32 clocksource_max_adjustment(struct clocksource *cs)
  * return half the number of nanoseconds the hardware counter can technically
  * cover. This is done so that we can potentially detect problems caused by
  * delayed timers or bad hardware, which might result in time intervals that
- * are larger then what the math used can handle without overflows.
+ * are larger than what the math used can handle without overflows.
  */
 u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cyc)
 {
@@ -595,16 +595,15 @@ static void __clocksource_select(bool skipcur)
  */
 static void clocksource_select(void)
 {
-	return __clocksource_select(false);
+	__clocksource_select(false);
 }
 
 static void clocksource_select_fallback(void)
 {
-	return __clocksource_select(true);
+	__clocksource_select(true);
 }
 
 #else /* !CONFIG_ARCH_USES_GETTIMEOFFSET */
-
 static inline void clocksource_select(void) { }
 static inline void clocksource_select_fallback(void) { }
 
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 457a373e2181..435b8850dd80 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -59,7 +59,7 @@
 /*
  * The timer bases:
  *
- * There are more clockids then hrtimer bases. Thus, we index
+ * There are more clockids than hrtimer bases. Thus, we index
  * into the timer bases by the hrtimer_base_type enum. When trying
  * to reach a base using a clockid, hrtimer_clockid_to_base()
  * is used to convert from clockid to the proper hrtimer_base_type.
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index df68cb875248..149cc8086aea 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -99,7 +99,7 @@ static time64_t			ntp_next_leap_sec = TIME64_MAX;
 static int pps_valid;		/* signal watchdog counter */
 static long pps_tf[3];		/* phase median filter */
 static long pps_jitter;		/* current jitter (ns) */
-static struct timespec pps_fbase; /* beginning of the last freq interval */
+static struct timespec64 pps_fbase; /* beginning of the last freq interval */
 static int pps_shift;		/* current interval duration (s) (shift) */
 static int pps_intcnt;		/* interval counter */
 static s64 pps_freq;		/* frequency offset (scaled ns/s) */
@@ -509,7 +509,7 @@ static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock);
 static void sync_cmos_clock(struct work_struct *work)
 {
 	struct timespec64 now;
-	struct timespec next;
+	struct timespec64 next;
 	int fail = 1;
 
 	/*
@@ -559,7 +559,7 @@ static void sync_cmos_clock(struct work_struct *work)
 		next.tv_nsec -= NSEC_PER_SEC;
 	}
 	queue_delayed_work(system_power_efficient_wq,
-			   &sync_cmos_work, timespec_to_jiffies(&next));
+			   &sync_cmos_work, timespec64_to_jiffies(&next));
 }
 
 void ntp_notify_cmos_timer(void)
@@ -773,13 +773,13 @@ int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai)
  * pps_normtime.nsec has a range of ( -NSEC_PER_SEC / 2, NSEC_PER_SEC / 2 ]
  * while timespec.tv_nsec has a range of [0, NSEC_PER_SEC) */
 struct pps_normtime {
-	__kernel_time_t	sec;	/* seconds */
+	s64		sec;	/* seconds */
 	long		nsec;	/* nanoseconds */
 };
 
 /* normalize the timestamp so that nsec is in the
    ( -NSEC_PER_SEC / 2, NSEC_PER_SEC / 2 ] interval */
-static inline struct pps_normtime pps_normalize_ts(struct timespec ts)
+static inline struct pps_normtime pps_normalize_ts(struct timespec64 ts)
 {
 	struct pps_normtime norm = {
 		.sec = ts.tv_sec,
@@ -861,7 +861,7 @@ static long hardpps_update_freq(struct pps_normtime freq_norm)
 		pps_errcnt++;
 		pps_dec_freq_interval();
 		printk_deferred(KERN_ERR
-			"hardpps: PPSERROR: interval too long - %ld s\n",
+			"hardpps: PPSERROR: interval too long - %lld s\n",
 			freq_norm.sec);
 		return 0;
 	}
@@ -948,7 +948,7 @@ static void hardpps_update_phase(long error)
  * This code is based on David Mills's reference nanokernel
  * implementation. It was mostly rewritten but keeps the same idea.
  */
-void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
+void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts)
 {
 	struct pps_normtime pts_norm, freq_norm;
 
@@ -969,7 +969,7 @@ void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
 	}
 
 	/* ok, now we have a base for frequency calculation */
-	freq_norm = pps_normalize_ts(timespec_sub(*raw_ts, pps_fbase));
+	freq_norm = pps_normalize_ts(timespec64_sub(*raw_ts, pps_fbase));
 
 	/* check that the signal is in the range
 	 * [1s - MAXFREQ us, 1s + MAXFREQ us], otherwise reject it */
diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h
index 65430504ca26..af924470eac0 100644
--- a/kernel/time/ntp_internal.h
+++ b/kernel/time/ntp_internal.h
@@ -9,5 +9,5 @@ extern ktime_t ntp_get_next_leap(void);
 extern int second_overflow(unsigned long secs);
 extern int ntp_validate_timex(struct timex *);
 extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *);
-extern void __hardpps(const struct timespec *, const struct timespec *);
+extern void __hardpps(const struct timespec64 *, const struct timespec64 *);
 #endif /* _LINUX_NTP_INTERNAL_H */
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 892e3dae0aac..f5e86d282d52 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -249,7 +249,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
 		 * but barriers are not required because update_gt_cputime()
 		 * can handle concurrent updates.
 		 */
-		WRITE_ONCE(cputimer->running, 1);
+		WRITE_ONCE(cputimer->running, true);
 	}
 	sample_cputime_atomic(times, &cputimer->cputime_atomic);
 }
@@ -864,6 +864,13 @@ static void check_thread_timers(struct task_struct *tsk,
 	unsigned long long expires;
 	unsigned long soft;
 
+	/*
+	 * If cputime_expires is zero, then there are no active
+	 * per thread CPU timers.
+	 */
+	if (task_cputime_zero(&tsk->cputime_expires))
+		return;
+
 	expires = check_timers_list(timers, firing, prof_ticks(tsk));
 	tsk_expires->prof_exp = expires_to_cputime(expires);
 
@@ -911,7 +918,7 @@ static inline void stop_process_timers(struct signal_struct *sig)
 	struct thread_group_cputimer *cputimer = &sig->cputimer;
 
 	/* Turn off cputimer->running. This is done without locking. */
-	WRITE_ONCE(cputimer->running, 0);
+	WRITE_ONCE(cputimer->running, false);
 }
 
 static u32 onecputick;
@@ -962,6 +969,19 @@ static void check_process_timers(struct task_struct *tsk,
 	unsigned long soft;
 
 	/*
+	 * If cputimer is not running, then there are no active
+	 * process wide timers (POSIX 1.b, itimers, RLIMIT_CPU).
+	 */
+	if (!READ_ONCE(tsk->signal->cputimer.running))
+		return;
+
+        /*
+	 * Signify that a thread is checking for process timers.
+	 * Write access to this field is protected by the sighand lock.
+	 */
+	sig->cputimer.checking_timer = true;
+
+	/*
 	 * Collect the current process totals.
 	 */
 	thread_group_cputimer(tsk, &cputime);
@@ -1015,6 +1035,8 @@ static void check_process_timers(struct task_struct *tsk,
 	sig->cputime_expires.sched_exp = sched_expires;
 	if (task_cputime_zero(&sig->cputime_expires))
 		stop_process_timers(sig);
+
+	sig->cputimer.checking_timer = false;
 }
 
 /*
@@ -1117,24 +1139,33 @@ static inline int task_cputime_expired(const struct task_cputime *sample,
 static inline int fastpath_timer_check(struct task_struct *tsk)
 {
 	struct signal_struct *sig;
-	cputime_t utime, stime;
-
-	task_cputime(tsk, &utime, &stime);
 
 	if (!task_cputime_zero(&tsk->cputime_expires)) {
-		struct task_cputime task_sample = {
-			.utime = utime,
-			.stime = stime,
-			.sum_exec_runtime = tsk->se.sum_exec_runtime
-		};
+		struct task_cputime task_sample;
 
+		task_cputime(tsk, &task_sample.utime, &task_sample.stime);
+		task_sample.sum_exec_runtime = tsk->se.sum_exec_runtime;
 		if (task_cputime_expired(&task_sample, &tsk->cputime_expires))
 			return 1;
 	}
 
 	sig = tsk->signal;
-	/* Check if cputimer is running. This is accessed without locking. */
-	if (READ_ONCE(sig->cputimer.running)) {
+	/*
+	 * Check if thread group timers expired when the cputimer is
+	 * running and no other thread in the group is already checking
+	 * for thread group cputimers. These fields are read without the
+	 * sighand lock. However, this is fine because this is meant to
+	 * be a fastpath heuristic to determine whether we should try to
+	 * acquire the sighand lock to check/handle timers.
+	 *
+	 * In the worst case scenario, if 'running' or 'checking_timer' gets
+	 * set but the current thread doesn't see the change yet, we'll wait
+	 * until the next thread in the group gets a scheduler interrupt to
+	 * handle the timer. This isn't an issue in practice because these
+	 * types of delays with signals actually getting sent are expected.
+	 */
+	if (READ_ONCE(sig->cputimer.running) &&
+	    !READ_ONCE(sig->cputimer.checking_timer)) {
 		struct task_cputime group_sample;
 
 		sample_cputime_atomic(&group_sample, &sig->cputimer.cputime_atomic);
@@ -1174,12 +1205,8 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	 * put them on the firing list.
 	 */
 	check_thread_timers(tsk, &firing);
-	/*
-	 * If there are any active process wide timers (POSIX 1.b, itimers,
-	 * RLIMIT_CPU) cputimer must be running.
-	 */
-	if (READ_ONCE(tsk->signal->cputimer.running))
-		check_process_timers(tsk, &firing);
+
+	check_process_timers(tsk, &firing);
 
 	/*
 	 * We must release these locks before taking any timer's lock.
diff --git a/kernel/time/timeconst.bc b/kernel/time/timeconst.bc
index c7388dee8635..c48688904f9f 100644
--- a/kernel/time/timeconst.bc
+++ b/kernel/time/timeconst.bc
@@ -39,7 +39,7 @@ define fmuls(b,n,d) {
 }
 
 define timeconst(hz) {
-	print "/* Automatically generated by kernel/timeconst.bc */\n"
+	print "/* Automatically generated by kernel/time/timeconst.bc */\n"
 	print "/* Time conversion constants for HZ == ", hz, " */\n"
 	print "\n"
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 44d2cc0436f4..b1356b7ae570 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -849,7 +849,7 @@ EXPORT_SYMBOL_GPL(ktime_get_real_seconds);
 #ifdef CONFIG_NTP_PPS
 
 /**
- * getnstime_raw_and_real - get day and raw monotonic time in timespec format
+ * ktime_get_raw_and_real_ts64 - get day and raw monotonic time in timespec format
  * @ts_raw:	pointer to the timespec to be set to raw monotonic time
  * @ts_real:	pointer to the timespec to be set to the time of day
  *
@@ -857,7 +857,7 @@ EXPORT_SYMBOL_GPL(ktime_get_real_seconds);
  * same time atomically and stores the resulting timestamps in timespec
  * format.
  */
-void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real)
+void ktime_get_raw_and_real_ts64(struct timespec64 *ts_raw, struct timespec64 *ts_real)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long seq;
@@ -868,7 +868,7 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real)
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 
-		*ts_raw = timespec64_to_timespec(tk->raw_time);
+		*ts_raw = tk->raw_time;
 		ts_real->tv_sec = tk->xtime_sec;
 		ts_real->tv_nsec = 0;
 
@@ -877,10 +877,10 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real)
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
-	timespec_add_ns(ts_raw, nsecs_raw);
-	timespec_add_ns(ts_real, nsecs_real);
+	timespec64_add_ns(ts_raw, nsecs_raw);
+	timespec64_add_ns(ts_real, nsecs_real);
 }
-EXPORT_SYMBOL(getnstime_raw_and_real);
+EXPORT_SYMBOL(ktime_get_raw_and_real_ts64);
 
 #endif /* CONFIG_NTP_PPS */
 
@@ -1674,7 +1674,7 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
 /**
  * accumulate_nsecs_to_secs - Accumulates nsecs into secs
  *
- * Helper function that accumulates a the nsecs greater then a second
+ * Helper function that accumulates the nsecs greater than a second
  * from the xtime_nsec field to the xtime_secs field.
  * It also calls into the NTP code to handle leapsecond processing.
  *
@@ -1726,7 +1726,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
 	cycle_t interval = tk->cycle_interval << shift;
 	u64 raw_nsecs;
 
-	/* If the offset is smaller then a shifted interval, do nothing */
+	/* If the offset is smaller than a shifted interval, do nothing */
 	if (offset < interval)
 		return offset;
 
@@ -2025,7 +2025,7 @@ int do_adjtimex(struct timex *txc)
 /**
  * hardpps() - Accessor function to NTP __hardpps function
  */
-void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
+void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts)
 {
 	unsigned long flags;
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 84190f02b521..74591ba9474f 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -461,10 +461,17 @@ void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr)
 
 static void timer_stats_account_timer(struct timer_list *timer)
 {
-	if (likely(!timer->start_site))
+	void *site;
+
+	/*
+	 * start_site can be concurrently reset by
+	 * timer_stats_timer_clear_start_info()
+	 */
+	site = READ_ONCE(timer->start_site);
+	if (likely(!site))
 		return;
 
-	timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
+	timer_stats_update_stats(timer, timer->start_pid, site,
 				 timer->function, timer->start_comm,
 				 timer->flags);
 }
@@ -867,7 +874,7 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
 	if (mask == 0)
 		return expires;
 
-	bit = find_last_bit(&mask, BITS_PER_LONG);
+	bit = __fls(mask);
 
 	mask = (1UL << bit) - 1;