diff mbox

[5/5] 3.10.y: timekeeping: Avoid possible deadlock from clock_was_set_delayed

Message ID 1392066713-5025-6-git-send-email-john.stultz@linaro.org
State New
Headers show

Commit Message

John Stultz Feb. 10, 2014, 9:11 p.m. UTC
This is a 3.10-stable backport of 6fdda9a9c5db367130cf32df5d6618d08b89f46a

As part of normal operaions, the hrtimer subsystem frequently calls
into the timekeeping code, creating a locking order of
hrtimer locks -> timekeeping locks

clock_was_set_delayed() was suppoed to allow us to avoid deadlocks
between the timekeeping the hrtimer subsystem, so that we could
notify the hrtimer subsytem the time had changed while holding
the timekeeping locks. This was done by scheduling delayed work
that would run later once we were out of the timekeeing code.

But unfortunately the lock chains are complex enoguh that in
scheduling delayed work, we end up eventually trying to grab
an hrtimer lock.

Sasha Levin noticed this in testing when the new seqlock lockdep
enablement triggered the following (somewhat abrieviated) message:

[  251.100221] ======================================================
[  251.100221] [ INFO: possible circular locking dependency detected ]
[  251.100221] 3.13.0-rc2-next-20131206-sasha-00005-g8be2375-dirty #4053 Not tainted
[  251.101967] -------------------------------------------------------
[  251.101967] kworker/10:1/4506 is trying to acquire lock:
[  251.101967]  (timekeeper_seq){----..}, at: [<ffffffff81160e96>] retrigger_next_event+0x56/0x70
[  251.101967]
[  251.101967] but task is already holding lock:
[  251.101967]  (hrtimer_bases.lock#11){-.-...}, at: [<ffffffff81160e7c>] retrigger_next_event+0x3c/0x70
[  251.101967]
[  251.101967] which lock already depends on the new lock.
[  251.101967]
[  251.101967]
[  251.101967] the existing dependency chain (in reverse order) is:
[  251.101967]
-> #5 (hrtimer_bases.lock#11){-.-...}:
[snipped]
-> #4 (&rt_b->rt_runtime_lock){-.-...}:
[snipped]
-> #3 (&rq->lock){-.-.-.}:
[snipped]
-> #2 (&p->pi_lock){-.-.-.}:
[snipped]
-> #1 (&(&pool->lock)->rlock){-.-...}:
[  251.101967]        [<ffffffff81194803>] validate_chain+0x6c3/0x7b0
[  251.101967]        [<ffffffff81194d9d>] __lock_acquire+0x4ad/0x580
[  251.101967]        [<ffffffff81194ff2>] lock_acquire+0x182/0x1d0
[  251.101967]        [<ffffffff84398500>] _raw_spin_lock+0x40/0x80
[  251.101967]        [<ffffffff81153e69>] __queue_work+0x1a9/0x3f0
[  251.101967]        [<ffffffff81154168>] queue_work_on+0x98/0x120
[  251.101967]        [<ffffffff81161351>] clock_was_set_delayed+0x21/0x30
[  251.101967]        [<ffffffff811c4bd1>] do_adjtimex+0x111/0x160
[  251.101967]        [<ffffffff811e2711>] compat_sys_adjtimex+0x41/0x70
[  251.101967]        [<ffffffff843a4b49>] ia32_sysret+0x0/0x5
[  251.101967]
-> #0 (timekeeper_seq){----..}:
[snipped]
[  251.101967] other info that might help us debug this:
[  251.101967]
[  251.101967] Chain exists of:
  timekeeper_seq --> &rt_b->rt_runtime_lock --> hrtimer_bases.lock#11

[  251.101967]  Possible unsafe locking scenario:
[  251.101967]
[  251.101967]        CPU0                    CPU1
[  251.101967]        ----                    ----
[  251.101967]   lock(hrtimer_bases.lock#11);
[  251.101967]                                lock(&rt_b->rt_runtime_lock);
[  251.101967]                                lock(hrtimer_bases.lock#11);
[  251.101967]   lock(timekeeper_seq);
[  251.101967]
[  251.101967]  *** DEADLOCK ***
[  251.101967]
[  251.101967] 3 locks held by kworker/10:1/4506:
[  251.101967]  #0:  (events){.+.+.+}, at: [<ffffffff81154960>] process_one_work+0x200/0x530
[  251.101967]  #1:  (hrtimer_work){+.+...}, at: [<ffffffff81154960>] process_one_work+0x200/0x530
[  251.101967]  #2:  (hrtimer_bases.lock#11){-.-...}, at: [<ffffffff81160e7c>] retrigger_next_event+0x3c/0x70
[  251.101967]
[  251.101967] stack backtrace:
[  251.101967] CPU: 10 PID: 4506 Comm: kworker/10:1 Not tainted 3.13.0-rc2-next-20131206-sasha-00005-g8be2375-dirty #4053
[  251.101967] Workqueue: events clock_was_set_work

So the best solution is to avoid calling clock_was_set_delayed() while
holding the timekeeping lock, and instead using a flag variable to
decide if we should call clock_was_set() once we've released the locks.

This works for the case here, where the do_adjtimex() was the deadlock
trigger point. Unfortuantely, in update_wall_time() we still hold
the jiffies lock, which would deadlock with the ipi triggered by
clock_was_set(), preventing us from calling it even after we drop the
timekeeping lock. So instead call clock_was_set_delayed() at that point.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: stable <stable@vger.kernel.org> #3.10+
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 kernel/time/timekeeping.c | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)
diff mbox

Patch

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index d81b111..76fefb1 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1239,9 +1239,10 @@  out_adjust:
  * It also calls into the NTP code to handle leapsecond processing.
  *
  */
-static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
+static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
 {
 	u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
+	unsigned int clock_set = 0;
 
 	while (tk->xtime_nsec >= nsecps) {
 		int leap;
@@ -1263,9 +1264,10 @@  static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
 
 			__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
 
-			clock_was_set_delayed();
+			clock_set = 1;
 		}
 	}
+	return clock_set;
 }
 
 /**
@@ -1278,7 +1280,8 @@  static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
  * Returns the unconsumed cycles.
  */
 static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
-						u32 shift)
+						u32 shift,
+						unsigned int *clock_set)
 {
 	cycle_t interval = tk->cycle_interval << shift;
 	u64 raw_nsecs;
@@ -1292,7 +1295,7 @@  static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
 	tk->cycle_last += interval;
 
 	tk->xtime_nsec += tk->xtime_interval << shift;
-	accumulate_nsecs_to_secs(tk);
+	*clock_set |= accumulate_nsecs_to_secs(tk);
 
 	/* Accumulate raw time */
 	raw_nsecs = (u64)tk->raw_interval << shift;
@@ -1350,6 +1353,7 @@  static void update_wall_time(void)
 	struct timekeeper *tk = &shadow_timekeeper;
 	cycle_t offset;
 	int shift = 0, maxshift;
+	unsigned int clock_set = 0;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -1384,7 +1388,8 @@  static void update_wall_time(void)
 	maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
 	shift = min(shift, maxshift);
 	while (offset >= tk->cycle_interval) {
-		offset = logarithmic_accumulation(tk, offset, shift);
+		offset = logarithmic_accumulation(tk, offset, shift,
+							&clock_set);
 		if (offset < tk->cycle_interval<<shift)
 			shift--;
 	}
@@ -1402,7 +1407,7 @@  static void update_wall_time(void)
 	 * Finally, make sure that after the rounding
 	 * xtime_nsec isn't larger than NSEC_PER_SEC
 	 */
-	accumulate_nsecs_to_secs(tk);
+	clock_set |= accumulate_nsecs_to_secs(tk);
 
 	write_seqcount_begin(&timekeeper_seq);
 	/* Update clock->cycle_last with the new value */
@@ -1422,6 +1427,10 @@  static void update_wall_time(void)
 	write_seqcount_end(&timekeeper_seq);
 out:
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+	if (clock_set)
+		/* have to call outside the timekeeper_seq */
+		clock_was_set_delayed();
+
 }
 
 /**
@@ -1681,11 +1690,13 @@  int do_adjtimex(struct timex *txc)
 	if (tai != orig_tai) {
 		__timekeeping_set_tai_offset(tk, tai);
 		timekeeping_update(tk, false, true);
-		clock_was_set_delayed();
 	}
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
+	if (tai != orig_tai)
+		clock_was_set();
+
 	ntp_notify_cmos_timer();
 
 	return ret;