rtmutex: Turn the plist into an rb-tree

Turn the pi-chains from plist to rb-tree, in the rt_mutex code,
and provide a proper comparison function for -deadline and
-priority tasks.

This is done mainly because:
 - classical prio field of the plist is just an int, which might
   not be enough for representing a deadline;
 - manipulating such a list would become O(nr_deadline_tasks),
   which might be to much, as the number of -deadline task increases.

Therefore, an rb-tree is used, and tasks are queued in it according
to the following logic:
 - among two -priority (i.e., SCHED_BATCH/OTHER/RR/FIFO) tasks, the
   one with the higher (lower, actually!) prio wins;
 - among a -priority and a -deadline task, the latter always wins;
 - among two -deadline tasks, the one with the earliest deadline
   wins.

Queueing and dequeueing functions are changed accordingly, for both
the list of a task's pi-waiters and the list of tasks blocked on
a pi-lock.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-again-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-10-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 0dd6aec..3bf0aa6 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -14,6 +14,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
 #include <linux/timer.h>
 
 #include "rtmutex_common.h"
@@ -91,10 +92,104 @@
 }
 #endif
 
+static inline int
+rt_mutex_waiter_less(struct rt_mutex_waiter *left,
+		     struct rt_mutex_waiter *right)
+{
+	if (left->task->prio < right->task->prio)
+		return 1;
+
+	/*
+	 * If both tasks are dl_task(), we check their deadlines.
+	 */
+	if (dl_prio(left->task->prio) && dl_prio(right->task->prio))
+		return (left->task->dl.deadline < right->task->dl.deadline);
+
+	return 0;
+}
+
+static void
+rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+	struct rb_node **link = &lock->waiters.rb_node;
+	struct rb_node *parent = NULL;
+	struct rt_mutex_waiter *entry;
+	int leftmost = 1;
+
+	while (*link) {
+		parent = *link;
+		entry = rb_entry(parent, struct rt_mutex_waiter, tree_entry);
+		if (rt_mutex_waiter_less(waiter, entry)) {
+			link = &parent->rb_left;
+		} else {
+			link = &parent->rb_right;
+			leftmost = 0;
+		}
+	}
+
+	if (leftmost)
+		lock->waiters_leftmost = &waiter->tree_entry;
+
+	rb_link_node(&waiter->tree_entry, parent, link);
+	rb_insert_color(&waiter->tree_entry, &lock->waiters);
+}
+
+static void
+rt_mutex_dequeue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+	if (RB_EMPTY_NODE(&waiter->tree_entry))
+		return;
+
+	if (lock->waiters_leftmost == &waiter->tree_entry)
+		lock->waiters_leftmost = rb_next(&waiter->tree_entry);
+
+	rb_erase(&waiter->tree_entry, &lock->waiters);
+	RB_CLEAR_NODE(&waiter->tree_entry);
+}
+
+static void
+rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+	struct rb_node **link = &task->pi_waiters.rb_node;
+	struct rb_node *parent = NULL;
+	struct rt_mutex_waiter *entry;
+	int leftmost = 1;
+
+	while (*link) {
+		parent = *link;
+		entry = rb_entry(parent, struct rt_mutex_waiter, pi_tree_entry);
+		if (rt_mutex_waiter_less(waiter, entry)) {
+			link = &parent->rb_left;
+		} else {
+			link = &parent->rb_right;
+			leftmost = 0;
+		}
+	}
+
+	if (leftmost)
+		task->pi_waiters_leftmost = &waiter->pi_tree_entry;
+
+	rb_link_node(&waiter->pi_tree_entry, parent, link);
+	rb_insert_color(&waiter->pi_tree_entry, &task->pi_waiters);
+}
+
+static void
+rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+	if (RB_EMPTY_NODE(&waiter->pi_tree_entry))
+		return;
+
+	if (task->pi_waiters_leftmost == &waiter->pi_tree_entry)
+		task->pi_waiters_leftmost = rb_next(&waiter->pi_tree_entry);
+
+	rb_erase(&waiter->pi_tree_entry, &task->pi_waiters);
+	RB_CLEAR_NODE(&waiter->pi_tree_entry);
+}
+
 /*
- * Calculate task priority from the waiter list priority
+ * Calculate task priority from the waiter tree priority
  *
- * Return task->normal_prio when the waiter list is empty or when
+ * Return task->normal_prio when the waiter tree is empty or when
  * the waiter is not allowed to do priority boosting
  */
 int rt_mutex_getprio(struct task_struct *task)
@@ -102,7 +197,7 @@
 	if (likely(!task_has_pi_waiters(task)))
 		return task->normal_prio;
 
-	return min(task_top_pi_waiter(task)->pi_list_entry.prio,
+	return min(task_top_pi_waiter(task)->task->prio,
 		   task->normal_prio);
 }
 
@@ -233,7 +328,7 @@
 	 * When deadlock detection is off then we check, if further
 	 * priority adjustment is necessary.
 	 */
-	if (!detect_deadlock && waiter->list_entry.prio == task->prio)
+	if (!detect_deadlock && waiter->task->prio == task->prio)
 		goto out_unlock_pi;
 
 	lock = waiter->lock;
@@ -254,9 +349,9 @@
 	top_waiter = rt_mutex_top_waiter(lock);
 
 	/* Requeue the waiter */
-	plist_del(&waiter->list_entry, &lock->wait_list);
-	waiter->list_entry.prio = task->prio;
-	plist_add(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_dequeue(lock, waiter);
+	waiter->task->prio = task->prio;
+	rt_mutex_enqueue(lock, waiter);
 
 	/* Release the task */
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
@@ -280,17 +375,15 @@
 
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		/* Boost the owner */
-		plist_del(&top_waiter->pi_list_entry, &task->pi_waiters);
-		waiter->pi_list_entry.prio = waiter->list_entry.prio;
-		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+		rt_mutex_dequeue_pi(task, top_waiter);
+		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
 
 	} else if (top_waiter == waiter) {
 		/* Deboost the owner */
-		plist_del(&waiter->pi_list_entry, &task->pi_waiters);
+		rt_mutex_dequeue_pi(task, waiter);
 		waiter = rt_mutex_top_waiter(lock);
-		waiter->pi_list_entry.prio = waiter->list_entry.prio;
-		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
 	}
 
@@ -355,7 +448,7 @@
 	 * 3) it is top waiter
 	 */
 	if (rt_mutex_has_waiters(lock)) {
-		if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) {
+		if (task->prio >= rt_mutex_top_waiter(lock)->task->prio) {
 			if (!waiter || waiter != rt_mutex_top_waiter(lock))
 				return 0;
 		}
@@ -369,7 +462,7 @@
 
 		/* remove the queued waiter. */
 		if (waiter) {
-			plist_del(&waiter->list_entry, &lock->wait_list);
+			rt_mutex_dequeue(lock, waiter);
 			task->pi_blocked_on = NULL;
 		}
 
@@ -379,8 +472,7 @@
 		 */
 		if (rt_mutex_has_waiters(lock)) {
 			top = rt_mutex_top_waiter(lock);
-			top->pi_list_entry.prio = top->list_entry.prio;
-			plist_add(&top->pi_list_entry, &task->pi_waiters);
+			rt_mutex_enqueue_pi(task, top);
 		}
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	}
@@ -416,13 +508,11 @@
 	__rt_mutex_adjust_prio(task);
 	waiter->task = task;
 	waiter->lock = lock;
-	plist_node_init(&waiter->list_entry, task->prio);
-	plist_node_init(&waiter->pi_list_entry, task->prio);
 
 	/* Get the top priority waiter on the lock */
 	if (rt_mutex_has_waiters(lock))
 		top_waiter = rt_mutex_top_waiter(lock);
-	plist_add(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_enqueue(lock, waiter);
 
 	task->pi_blocked_on = waiter;
 
@@ -433,8 +523,8 @@
 
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		raw_spin_lock_irqsave(&owner->pi_lock, flags);
-		plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
-		plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
+		rt_mutex_dequeue_pi(owner, top_waiter);
+		rt_mutex_enqueue_pi(owner, waiter);
 
 		__rt_mutex_adjust_prio(owner);
 		if (owner->pi_blocked_on)
@@ -486,7 +576,7 @@
 	 * boosted mode and go back to normal after releasing
 	 * lock->wait_lock.
 	 */
-	plist_del(&waiter->pi_list_entry, &current->pi_waiters);
+	rt_mutex_dequeue_pi(current, waiter);
 
 	rt_mutex_set_owner(lock, NULL);
 
@@ -510,7 +600,7 @@
 	int chain_walk = 0;
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
-	plist_del(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_dequeue(lock, waiter);
 	current->pi_blocked_on = NULL;
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
@@ -521,13 +611,13 @@
 
 		raw_spin_lock_irqsave(&owner->pi_lock, flags);
 
-		plist_del(&waiter->pi_list_entry, &owner->pi_waiters);
+		rt_mutex_dequeue_pi(owner, waiter);
 
 		if (rt_mutex_has_waiters(lock)) {
 			struct rt_mutex_waiter *next;
 
 			next = rt_mutex_top_waiter(lock);
-			plist_add(&next->pi_list_entry, &owner->pi_waiters);
+			rt_mutex_enqueue_pi(owner, next);
 		}
 		__rt_mutex_adjust_prio(owner);
 
@@ -537,8 +627,6 @@
 		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
 	}
 
-	WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
-
 	if (!chain_walk)
 		return;
 
@@ -565,7 +653,7 @@
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
 	waiter = task->pi_blocked_on;
-	if (!waiter || waiter->list_entry.prio == task->prio) {
+	if (!waiter || waiter->task->prio == task->prio) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
@@ -638,6 +726,8 @@
 	int ret = 0;
 
 	debug_rt_mutex_init_waiter(&waiter);
+	RB_CLEAR_NODE(&waiter.pi_tree_entry);
+	RB_CLEAR_NODE(&waiter.tree_entry);
 
 	raw_spin_lock(&lock->wait_lock);
 
@@ -904,7 +994,8 @@
 {
 	lock->owner = NULL;
 	raw_spin_lock_init(&lock->wait_lock);
-	plist_head_init(&lock->wait_list);
+	lock->waiters = RB_ROOT;
+	lock->waiters_leftmost = NULL;
 
 	debug_rt_mutex_init(lock, name);
 }