summaryrefslogtreecommitdiffstats
path: root/drivers/dma-buf
diff options
context:
space:
mode:
authorThomas Gleixner <tglx@linutronix.de>2016-01-13 11:25:38 +0100
committerThomas Gleixner <tglx@linutronix.de>2016-01-26 11:08:35 +0100
commitb4abf91047cf054f203dcfac97e1038388826937 (patch)
treea018e1a33d72f3c8f154db82acad5b70858417ba /drivers/dma-buf
parent92e963f50fc74041b5e9e744c330dca48e04f08d (diff)
downloadlinux-b4abf91047cf054f203dcfac97e1038388826937.tar.bz2
rtmutex: Make wait_lock irq safe
Sasha reported a lockdep splat about a potential deadlock between RCU boosting rtmutex and the posix timer it_lock. CPU0 CPU1 rtmutex_lock(&rcu->rt_mutex) spin_lock(&rcu->rt_mutex.wait_lock) local_irq_disable() spin_lock(&timer->it_lock) spin_lock(&rcu->mutex.wait_lock) --> Interrupt spin_lock(&timer->it_lock) This is caused by the following code sequence on CPU1 rcu_read_lock() x = lookup(); if (x) spin_lock_irqsave(&x->it_lock); rcu_read_unlock(); return x; We could fix that in the posix timer code by keeping rcu read locked across the spinlocked and irq disabled section, but the above sequence is common and there is no reason not to support it. Taking rt_mutex.wait_lock irq safe prevents the deadlock. Reported-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
Diffstat (limited to 'drivers/dma-buf')
0 files changed, 0 insertions, 0 deletions