MFC r315280 r315287

When the RTC is adjusted, reevaluate absolute sleep times based on the RTC

POSIX 2008 says this about clock_settime(2):

    If the value of the CLOCK_REALTIME clock is set via clock_settime(),
    the new value of the clock shall be used to determine the time
    of expiration for absolute time services based upon the
    CLOCK_REALTIME clock.  This applies to the time at which armed
    absolute timers expire.  If the absolute time requested at the
    invocation of such a time service is before the new value of
    the clock, the time service shall expire immediately as if the
    clock had reached the requested time normally.

    Setting the value of the CLOCK_REALTIME clock via clock_settime()
    shall have no effect on threads that are blocked waiting for
    a relative time service based upon this clock, including the
    nanosleep() function; nor on the expiration of relative timers
    based upon this clock.  Consequently, these time services shall
    expire when the requested relative interval elapses, independently
    of the new or old value of the clock.

When the real-time clock is adjusted, such as by clock_settime(3),
wake any threads sleeping until an absolute real-clock time.
Such a sleep is indicated by a non-zero td_rtcgen.  The sleep functions
will set that field to zero and return zero to tell the caller
to reevaluate its sleep duration based on the new value of the clock.

At present, this affects the following functions:

    pthread_cond_timedwait(3)
    pthread_mutex_timedlock(3)
    pthread_rwlock_timedrdlock(3)
    pthread_rwlock_timedwrlock(3)
    sem_timedwait(3)
    sem_clockwait_np(3)

I'm working on adding clock_nanosleep(2), which will also be affected.

Reported by:	Sebastian Huber <sebastian.huber@embedded-brains.de>
Relnotes:	yes
Sponsored by:	Dell EMC

3 files changed, 7 insertions, 0 deletions

diff --git a/sys/sys/proc.h b/sys/sys/proc.h
index 140732f..178b980 100644
--- a/sys/sys/proc.h
+++ b/sys/sys/proc.h
@@ -148,6 +148,7 @@ struct pargs {
  *      o - ktrace lock
  *      q - td_contested lock
  *      r - p_peers lock
+ *      s - see sleepq_switch(), sleeping_on_old_rtc(), and sleep(9)
  *      t - thread lock
  *	u - process stat lock
  *	w - process timer lock
@@ -282,6 +283,7 @@ struct thread {
 	int		td_no_sleeping;	/* (k) Sleeping disabled count. */
 	int		td_dom_rr_idx;	/* (k) RR Numa domain selection. */
 	void		*td_su;		/* (k) FFS SU private */
+	int		td_rtcgen;	/* (s) rtc_generation of abs. sleep */
 #define	td_endzero td_sigmask
 
 /* Copied during fork1() or create_thread(). */
diff --git a/sys/sys/sleepqueue.h b/sys/sys/sleepqueue.h
index d59dc7e..30a1893 100644
--- a/sys/sys/sleepqueue.h
+++ b/sys/sys/sleepqueue.h
@@ -90,11 +90,14 @@ void	sleepq_add(void *wchan, struct lock_object *lock, const char *wmesg,
 	    int flags, int queue);
 struct sleepqueue *sleepq_alloc(void);
 int	sleepq_broadcast(void *wchan, int flags, int pri, int queue);
+void	sleepq_chains_remove_matching(bool (*matches)(struct thread *));
 void	sleepq_free(struct sleepqueue *sq);
 void	sleepq_lock(void *wchan);
 struct sleepqueue *sleepq_lookup(void *wchan);
 void	sleepq_release(void *wchan);
 void	sleepq_remove(struct thread *td, void *wchan);
+int	sleepq_remove_matching(struct sleepqueue *sq, int queue,
+	    bool (*matches)(struct thread *), int pri);
 int	sleepq_signal(void *wchan, int flags, int pri, int queue);
 void	sleepq_set_timeout_sbt(void *wchan, sbintime_t sbt,
 	    sbintime_t pr, int flags);
diff --git a/sys/sys/time.h b/sys/sys/time.h
index 659f8e0..f2a6301 100644
--- a/sys/sys/time.h
+++ b/sys/sys/time.h
@@ -383,6 +383,8 @@ extern struct bintime bt_tickthreshold;
 extern sbintime_t sbt_timethreshold;
 extern sbintime_t sbt_tickthreshold;
 
+extern volatile int rtc_generation;
+
 /*
  * Functions for looking at our clock: [get]{bin,nano,micro}[up]time()
  *