linux/kernel/locking/test-ww_mutex.c, branch v4.11

locking/ww_mutex: Adjust the lock number for stress test

2017-03-02T08:00:39Z

Because there are only 12 bits in held_lock::references, so we only support 4095 nested lock held in the same time, adjust the lock number for ww_mutex stress test to kill one lockdep splat: [ ] [ BUG: bad unlock balance detected! ] [ ] kworker/u2:0/5 is trying to release lock (ww_class_mutex) at: [ ] ww_mutex_unlock() [ ] but there are no more locks to release! ... Signed-off-by: Boqun Feng Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Chris Wilson Cc: Fengguang Wu Cc: Linus Torvalds Cc: Nicolai Hähnle Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20170301150138.hdixnmafzfsox7nn@tardis.cn.ibm.com Signed-off-by: Ingo Molnar

locking/ww_mutex: Replace cpu_relax() with cond_resched() for tests

2017-03-02T08:00:38Z

When busy-spinning on a ww_mutex_trylock(), we depend upon the other thread advancing and releasing the lock. This can not happen on a single CPU unless we relinquish it: [ ] NMI watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [kworker/0:1:18] ... [ ] Call Trace: [ ] mutex_trylock() [ ] test_mutex_work+0x31/0x56 [ ] process_one_work+0x1b4/0x2f9 [ ] worker_thread+0x1b0/0x27c [ ] kthread+0xd1/0xd3 [ ] ret_from_fork+0x19/0x30 Reported-by: Fengguang Wu Signed-off-by: Chris Wilson Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: f2a5fec17395 ("locking/ww_mutex: Begin kselftests for ww_mutex") Link: http://lkml.kernel.org/r/20170228094011.2595-1-chris@chris-wilson.co.uk Signed-off-by: Ingo Molnar

locking/ww_mutex: Add kselftests for ww_mutex stress

2017-01-14T10:37:17Z

Signed-off-by: Chris Wilson Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Maarten Lankhorst Cc: Nicolai Hähnle Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20161201114711.28697-8-chris@chris-wilson.co.uk Signed-off-by: Ingo Molnar

locking/ww_mutex: Add kselftests for resolving ww_mutex cyclic deadlocks

2017-01-14T10:37:16Z

Check that ww_mutexes can detect cyclic deadlocks (generalised ABBA cycles) and resolve them by lock reordering. Signed-off-by: Chris Wilson Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Maarten Lankhorst Cc: Nicolai Hähnle Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20161201114711.28697-7-chris@chris-wilson.co.uk Signed-off-by: Ingo Molnar

locking/ww_mutex: Add kselftests for ww_mutex ABBA deadlock detection

2017-01-14T10:37:16Z

Signed-off-by: Chris Wilson Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Maarten Lankhorst Cc: Nicolai Hähnle Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20161201114711.28697-6-chris@chris-wilson.co.uk Signed-off-by: Ingo Molnar

locking/ww_mutex: Add kselftests for ww_mutex AA deadlock detection

2017-01-14T10:37:15Z

Signed-off-by: Chris Wilson Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Maarten Lankhorst Cc: Nicolai Hähnle Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20161201114711.28697-5-chris@chris-wilson.co.uk Signed-off-by: Ingo Molnar

locking/ww_mutex: Begin kselftests for ww_mutex

2017-01-14T10:37:14Z

Signed-off-by: Chris Wilson Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Maarten Lankhorst Cc: Nicolai Hähnle Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20161201114711.28697-4-chris@chris-wilson.co.uk Signed-off-by: Ingo Molnar