Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1416586

[RFC][PATCH 8/8] rtmutex: Fix PI chain order integrity

Show all headers | View raw

rt_mutex_waiter::prio is a copy of task_struct::prio which is updated
during the PI chain walk, such that the PI chain order isn't messed up
by (asynchronous) task state updates.

Currently rt_mutex_waiter_less() uses task state for deadline tasks;
this is broken, since the task state can, as said above, change
asynchronously, causing the RB tree order to change without actual
tree update -> FAIL.

Fix this by also copying the deadline into the rt_mutex_waiter state
and updating it along with its prio field.

Ideally we would also force PI chain updates whenever DL tasks update
their deadline parameter, but for first approximation this is less
broken than it was.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/locking/rtmutex.c        |    5 +++--
 kernel/locking/rtmutex_common.h |    1 +
 2 files changed, 4 insertions(+), 2 deletions(-)

--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -172,8 +172,7 @@ rt_mutex_waiter_less(struct rt_mutex_wai
 	 * then right waiter has a dl_prio() too.
 	 */
 	if (dl_prio(left->prio))
-		return dl_time_before(left->task->dl.deadline,
-				      right->task->dl.deadline);
+		return dl_time_before(left->deadline, right->deadline);
 
 	return 0;
 }
@@ -585,6 +584,7 @@ static int rt_mutex_adjust_prio_chain(st
 	/* [7] Requeue the waiter in the lock waiter tree. */
 	rt_mutex_dequeue(lock, waiter);
 	waiter->prio = task->prio;
+	waiter->deadline = task->dl.deadline;
 	rt_mutex_enqueue(lock, waiter);
 
 	/* [8] Release the task */
@@ -855,6 +855,7 @@ static int task_blocks_on_rt_mutex(struc
 	waiter->task = task;
 	waiter->lock = lock;
 	waiter->prio = task->prio;
+	waiter->deadline = task->dl.deadline;
 
 	/* Get the top priority waiter on the lock */
 	if (rt_mutex_has_waiters(lock))
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -33,6 +33,7 @@ struct rt_mutex_waiter {
 	struct rt_mutex		*deadlock_lock;
 #endif
 	int prio;
+	u64 deadline;
 };
 
 /*

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[RFC][PATCH 0/8] PI and assorted failings Peter Zijlstra <peterz@infradead.org> - 2016-06-07 22:20 +0200
  [RFC][PATCH 1/8] rtmutex: Deboost before waking up the top waiter Peter Zijlstra <peterz@infradead.org> - 2016-06-07 22:20 +0200
  [RFC][PATCH 3/8] sched/deadline/rtmutex: Dont miss the dl_runtime/dl_period update Peter Zijlstra <peterz@infradead.org> - 2016-06-07 22:30 +0200
  [RFC][PATCH 8/8] rtmutex: Fix PI chain order integrity Peter Zijlstra <peterz@infradead.org> - 2016-06-07 22:30 +0200
  [RFC][PATCH 4/8] rtmutex: Remove rt_mutex_fastunlock() Peter Zijlstra <peterz@infradead.org> - 2016-06-07 22:30 +0200
  [RFC][PATCH 6/8] sched/rtmutex: Refactor rt_mutex_setprio() Peter Zijlstra <peterz@infradead.org> - 2016-06-07 22:30 +0200
  [RFC][PATCH 5/8] rtmutex: Clean up Peter Zijlstra <peterz@infradead.org> - 2016-06-07 22:30 +0200
  [RFC][PATCH 2/8] sched/rtmutex/deadline: Fix a PI crash for deadline tasks Peter Zijlstra <peterz@infradead.org> - 2016-06-07 22:30 +0200
  [RFC][PATCH 7/8] sched,tracing: Update trace_sched_pi_setprio() Peter Zijlstra <peterz@infradead.org> - 2016-06-07 22:30 +0200

csiph-web