locking/rtmutex: Implement equal priority lock stealing

The current logic only allows lock stealing to occur if the current task is
of higher priority than the pending owner.

Significant throughput improvements can be gained by allowing the lock
stealing to include tasks of equal priority when the contended lock is a
spin_lock or a rw_lock and the tasks are not in a RT scheduling task.

The assumption was that the system will make faster progress by allowing
the task already on the CPU to take the lock rather than waiting for the
system to wake up a different task.

This does add a degree of unfairness, but in reality no negative side
effects have been observed in the many years that this has been used in the
RT kernel.

[ tglx: Refactored and rewritten several times by Steve Rostedt, Sebastian
  	Siewior and myself ]

Signed-off-by: Gregory Haskins <ghaskins@novell.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210815211305.857240222@linutronix.de

1 files changed, 35 insertions, 17 deletions

diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index af7e3af4d313..3eaf636606fd 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -338,6 +338,26 @@ static __always_inline int rt_mutex_waiter_equal(struct rt_mutex_waiter *left,
 	return 1;
 }
 
+static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter,
+				  struct rt_mutex_waiter *top_waiter)
+{
+	if (rt_mutex_waiter_less(waiter, top_waiter))
+		return true;
+
+#ifdef RT_MUTEX_BUILD_SPINLOCKS
+	/*
+	 * Note that RT tasks are excluded from same priority (lateral)
+	 * steals to prevent the introduction of an unbounded latency.
+	 */
+	if (rt_prio(waiter->prio) || dl_prio(waiter->prio))
+		return false;
+
+	return rt_mutex_waiter_equal(waiter, top_waiter);
+#else
+	return false;
+#endif
+}
+
 #define __node_2_waiter(node) \
 	rb_entry((node), struct rt_mutex_waiter, tree_entry)
 
@@ -932,19 +952,21 @@ try_to_take_rt_mutex(struct rt_mutex_base *lock, struct task_struct *task,
 	 * trylock attempt.
 	 */
 	if (waiter) {
-		/*
-		 * If waiter is not the highest priority waiter of
-		 * @lock, give up.
-		 */
-		if (waiter != rt_mutex_top_waiter(lock))
-			return 0;
+		struct rt_mutex_waiter *top_waiter = rt_mutex_top_waiter(lock);
 
 		/*
-		 * We can acquire the lock. Remove the waiter from the
-		 * lock waiters tree.
+		 * If waiter is the highest priority waiter of @lock,
+		 * or allowed to steal it, take it over.
 		 */
-		rt_mutex_dequeue(lock, waiter);
-
+		if (waiter == top_waiter || rt_mutex_steal(waiter, top_waiter)) {
+			/*
+			 * We can acquire the lock. Remove the waiter from the
+			 * lock waiters tree.
+			 */
+			rt_mutex_dequeue(lock, waiter);
+		} else {
+			return 0;
+		}
 	} else {
 		/*
 		 * If the lock has waiters already we check whether @task is
@@ -955,13 +977,9 @@ try_to_take_rt_mutex(struct rt_mutex_base *lock, struct task_struct *task,
 		 * not need to be dequeued.
 		 */
 		if (rt_mutex_has_waiters(lock)) {
-			/*
-			 * If @task->prio is greater than or equal to
-			 * the top waiter priority (kernel view),
-			 * @task lost.
-			 */
-			if (!rt_mutex_waiter_less(task_to_waiter(task),
-						  rt_mutex_top_waiter(lock)))
+			/* Check whether the trylock can steal it. */
+			if (!rt_mutex_steal(task_to_waiter(task),
+					    rt_mutex_top_waiter(lock)))
 				return 0;
 
 			/*