summary refs log tree commit diff
path: root/kernel/rcu
diff options
context:
space:
mode:
authorLai Jiangshan <laijs@cn.fujitsu.com>2014-11-18 16:30:01 +0800
committerPaul E. McKenney <paulmck@linux.vnet.ibm.com>2015-01-06 11:02:52 -0800
commitabaf3f9d275b8d856ae5e47531e40c0bfeac012b (patch)
tree017561fdbffe2f3e840d6af7c5a7bbcf015c70c9 /kernel/rcu
parent3ba4d0e09bf965297e97adf195e0ea246cfe5c74 (diff)
downloadlinux-abaf3f9d275b8d856ae5e47531e40c0bfeac012b.tar.gz
rcu: Revert "Allow post-unlock reference for rt_mutex" to avoid priority-inversion
The patch dfeb9765ce3c ("Allow post-unlock reference for rt_mutex")
ensured rcu-boost safe even the rt_mutex has post-unlock reference.

But rt_mutex allowing post-unlock reference is definitely a bug and it was
fixed by the commit 27e35715df54 ("rtmutex: Plug slow unlock race").
This fix made the previous patch (dfeb9765ce3c) useless.

And even worse, the priority-inversion introduced by the the previous
patch still exists.

rcu_read_unlock_special() {
	rt_mutex_unlock(&rnp->boost_mtx);
	/* Priority-Inversion:
	 * the current task had been deboosted and preempted as a low
	 * priority task immediately, it could wait long before reschedule in,
	 * and the rcu-booster also waits on this low priority task and sleeps.
	 * This priority-inversion makes rcu-booster can't work
	 * as expected.
	 */
	complete(&rnp->boost_completion);
}

Just revert the patch to avoid it.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Diffstat (limited to 'kernel/rcu')
-rw-r--r--kernel/rcu/tree.h5
-rw-r--r--kernel/rcu/tree_plugin.h8
2 files changed, 1 insertions, 12 deletions
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 883ebc8e2b6e..95356477d560 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -172,11 +172,6 @@ struct rcu_node {
 				/*  queued on this rcu_node structure that */
 				/*  are blocking the current grace period, */
 				/*  there can be no such task. */
-	struct completion boost_completion;
-				/* Used to ensure that the rt_mutex used */
-				/*  to carry out the boosting is fully */
-				/*  released with no future boostee accesses */
-				/*  before that rt_mutex is re-initialized. */
 	struct rt_mutex boost_mtx;
 				/* Used only for the priority-boosting */
 				/*  side effect, not as a lock. */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 1fac68220999..625e26040e6b 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -429,10 +429,8 @@ void rcu_read_unlock_special(struct task_struct *t)
 
 #ifdef CONFIG_RCU_BOOST
 		/* Unboost if we were boosted. */
-		if (drop_boost_mutex) {
+		if (drop_boost_mutex)
 			rt_mutex_unlock(&rnp->boost_mtx);
-			complete(&rnp->boost_completion);
-		}
 #endif /* #ifdef CONFIG_RCU_BOOST */
 
 		/*
@@ -1081,15 +1079,11 @@ static int rcu_boost(struct rcu_node *rnp)
 	 */
 	t = container_of(tb, struct task_struct, rcu_node_entry);
 	rt_mutex_init_proxy_locked(&rnp->boost_mtx, t);
-	init_completion(&rnp->boost_completion);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	/* Lock only for side effect: boosts task t's priority. */
 	rt_mutex_lock(&rnp->boost_mtx);
 	rt_mutex_unlock(&rnp->boost_mtx);  /* Then keep lockdep happy. */
 
-	/* Wait for boostee to be done w/boost_mtx before reinitializing. */
-	wait_for_completion(&rnp->boost_completion);
-
 	return ACCESS_ONCE(rnp->exp_tasks) != NULL ||
 	       ACCESS_ONCE(rnp->boost_tasks) != NULL;
 }