Commit 2b232e0c authored Feb 28, 2017 by Chris Wilson Committed by Ingo Molnar Mar 02, 2017

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



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 <fengguang.wu@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: f2a5fec1 ("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 <mingo@kernel.org>

parent e2679aec

kernel/locking/test-ww_mutex.c

+2 −2

Original line number	Diff line number	Diff line
		@@ -50,7 +50,7 @@ static void test_mutex_work(struct work_struct *work)

		if (mtx->flags & TEST_MTX_TRY) {
		while (!ww_mutex_trylock(&mtx->mutex))
		cpu_relax();
		cond_resched();
		} else {
		ww_mutex_lock(&mtx->mutex, NULL);
		}
		@@ -88,7 +88,7 @@ static int __test_mutex(unsigned int flags)
		ret = -EINVAL;
		break;
		}
		cpu_relax();
		cond_resched();
		} while (time_before(jiffies, timeout));
		} else {
		ret = wait_for_completion_timeout(&mtx.done, TIMEOUT);