[(RT RFC) PATCH v2 1/9] allow rt-mutex lock-stealing to includelateral priority

[Gregory Haskins]

The current logic only allows lock stealing to occur if the current task
is of higher priority than the pending owner. We can gain signficant
throughput improvements (200%+) by allowing the lock-stealing code to
include tasks of equal priority.  The theory is 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, yes.  But also note that the users
of these locks under non -rt environments have already been using unfair
raw spinlocks anyway so the tradeoff is probably worth it.

The way I like to think of this is that higher priority tasks should
clearly preempt, and lower priority tasks should clearly block.  However,
if tasks have an identical priority value, then we can think of the
scheduler decisions as the tie-breaking parameter. (e.g. tasks that the
scheduler picked to run first have a logically higher priority amoung tasks
of the same prio).  This helps to keep the system "primed" with tasks doing
useful work, and the end result is higher throughput.

Signed-off-by: Gregory Haskins <ghaskins@xxxxxxxxxx>
---

 kernel/Kconfig.preempt |   10 ++++++++++
 kernel/rtmutex.c       |   31 +++++++++++++++++++++++--------
 2 files changed, 33 insertions(+), 8 deletions(-)

diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 41a0d88..e493257 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -196,3 +196,13 @@ config SPINLOCK_BKL
 	  Say Y here if you are building a kernel for a desktop system.
 	  Say N if you are unsure.
 
+config RTLOCK_LATERAL_STEAL
+        bool "Allow equal-priority rtlock stealing"
+        default y
+        depends on PREEMPT_RT
+        help
+          This option alters the rtlock lock-stealing logic to allow
+          equal priority tasks to preempt a pending owner in addition
+          to higher priority tasks.  This allows for a significant
+          boost in throughput under certain circumstances at the expense
+          of strict FIFO lock access.
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index a2b00cc..6624c66 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -313,12 +313,27 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	return ret;
 }
 
+static inline int lock_is_stealable(struct task_struct *pendowner, int unfair)
+{
+#ifndef CONFIG_RTLOCK_LATERAL_STEAL
+	if (current->prio >= pendowner->prio)
+#else
+	if (current->prio > pendowner->prio)
+		return 0;
+
+	if (!unfair && (current->prio == pendowner->prio))
+#endif
+		return 0;
+
+	return 1;
+}
+
 /*
  * Optimization: check if we can steal the lock from the
  * assigned pending owner [which might not have taken the
  * lock yet]:
  */
-static inline int try_to_steal_lock(struct rt_mutex *lock)
+static inline int try_to_steal_lock(struct rt_mutex *lock, int unfair)
 {
 	struct task_struct *pendowner = rt_mutex_owner(lock);
 	struct rt_mutex_waiter *next;
@@ -330,7 +345,7 @@ static inline int try_to_steal_lock(struct rt_mutex *lock)
 		return 1;
 
 	spin_lock(&pendowner->pi_lock);
-	if (current->prio >= pendowner->prio) {
+	if (!lock_is_stealable(pendowner, unfair)) {
 		spin_unlock(&pendowner->pi_lock);
 		return 0;
 	}
@@ -383,7 +398,7 @@ static inline int try_to_steal_lock(struct rt_mutex *lock)
  *
  * Must be called with lock->wait_lock held.
  */
-static int try_to_take_rt_mutex(struct rt_mutex *lock)
+static int try_to_take_rt_mutex(struct rt_mutex *lock, int unfair)
 {
 	/*
 	 * We have to be careful here if the atomic speedups are
@@ -406,7 +421,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock)
 	 */
 	mark_rt_mutex_waiters(lock);
 
-	if (rt_mutex_owner(lock) && !try_to_steal_lock(lock))
+	if (rt_mutex_owner(lock) && !try_to_steal_lock(lock, unfair))
 		return 0;
 
 	/* We got the lock. */
@@ -707,7 +722,7 @@ rt_spin_lock_slowlock(struct rt_mutex *lock)
 		int saved_lock_depth = current->lock_depth;
 
 		/* Try to acquire the lock */
-		if (try_to_take_rt_mutex(lock))
+		if (try_to_take_rt_mutex(lock, 1))
 			break;
 		/*
 		 * waiter.task is NULL the first time we come here and
@@ -947,7 +962,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	init_lists(lock);
 
 	/* Try to acquire the lock again: */
-	if (try_to_take_rt_mutex(lock)) {
+	if (try_to_take_rt_mutex(lock, 0)) {
 		spin_unlock_irqrestore(&lock->wait_lock, flags);
 		return 0;
 	}
@@ -970,7 +985,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		unsigned long saved_flags;
 
 		/* Try to acquire the lock: */
-		if (try_to_take_rt_mutex(lock))
+		if (try_to_take_rt_mutex(lock, 0))
 			break;
 
 		/*
@@ -1078,7 +1093,7 @@ rt_mutex_slowtrylock(struct rt_mutex *lock)
 
 		init_lists(lock);
 
-		ret = try_to_take_rt_mutex(lock);
+		ret = try_to_take_rt_mutex(lock, 0);
 		/*
 		 * try_to_take_rt_mutex() sets the lock waiters
 		 * bit unconditionally. Clean this up.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/