[PATCH v23 8/9] sched: Add blocked_donor link to task for smarter mutex handoffs

[John Stultz <jstultz@google.com>]

From: Peter Zijlstra <peterz@infradead.org>

Add link to the task this task is proxying for, and use it so
the mutex owner can do an intelligent hand-off of the mutex to
the task that the owner is running on behalf.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Connor O'Brien <connoro@google.com>
[jstultz: This patch was split out from larger proxy patch]
Signed-off-by: John Stultz <jstultz@google.com>
---
v5:
* Split out from larger proxy patch
v6:
* Moved proxied value from earlier patch to this one where it
  is actually used
* Rework logic to check sched_proxy_exec() instead of using ifdefs
* Moved comment change to this patch where it makes sense
v7:
* Use more descriptive term then "us" in comments, as suggested
  by Metin Kaya.
* Minor typo fixup from Metin Kaya
* Reworked proxied variable to prev_not_proxied to simplify usage
v8:
* Use helper for donor blocked_on_state transition
v9:
* Re-add mutex lock handoff in the unlock path, but only when we
  have a blocked donor
* Slight reword of commit message suggested by Metin
v18:
* Add task_init initialization for blocked_donor, suggested by
  Suleiman
v23:
* Reworks for PROXY_WAKING approach suggested by PeterZ

Cc: Joel Fernandes <joelagnelf@nvidia.com>
Cc: Qais Yousef <qyousef@layalina.io>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Zimuzo Ezeozue <zezeozue@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Will Deacon <will@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Metin Kaya <Metin.Kaya@arm.com>
Cc: Xuewen Yan <xuewen.yan94@gmail.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: kuyo chang <kuyo.chang@mediatek.com>
Cc: hupu <hupu.gm@gmail.com>
Cc: kernel-team@android.com
---
 include/linux/sched.h  |  1 +
 init/init_task.c       |  1 +
 kernel/fork.c          |  1 +
 kernel/locking/mutex.c | 44 +++++++++++++++++++++++++++++++++++++++---
 kernel/sched/core.c    | 18 +++++++++++++++--
 5 files changed, 60 insertions(+), 5 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 863c54685684c..bac1b956027e2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1241,6 +1241,7 @@ struct task_struct {
 #endif
 
 	struct mutex			*blocked_on;	/* lock we're blocked on */
+	struct task_struct		*blocked_donor;	/* task that is boosting this task */
 	raw_spinlock_t			blocked_lock;
 
 #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
diff --git a/init/init_task.c b/init/init_task.c
index 60477d74546e0..34853a511b4d8 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -177,6 +177,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
 	.mems_allowed_seq = SEQCNT_SPINLOCK_ZERO(init_task.mems_allowed_seq,
 						 &init_task.alloc_lock),
 #endif
+	.blocked_donor = NULL,
 #ifdef CONFIG_RT_MUTEXES
 	.pi_waiters	= RB_ROOT_CACHED,
 	.pi_top_task	= NULL,
diff --git a/kernel/fork.c b/kernel/fork.c
index 0697084be202f..0a9a17e25b85d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2136,6 +2136,7 @@ __latent_entropy struct task_struct *copy_process(
 	lockdep_init_task(p);
 
 	p->blocked_on = NULL; /* not blocked yet */
+	p->blocked_donor = NULL; /* nobody is boosting p yet */
 
 #ifdef CONFIG_BCACHE
 	p->sequential_io	= 0;
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 3cb9001d15119..08f438a54f56f 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -926,7 +926,7 @@ EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible);
  */
 static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip)
 {
-	struct task_struct *next = NULL;
+	struct task_struct *donor, *next = NULL;
 	DEFINE_WAKE_Q(wake_q);
 	unsigned long owner;
 	unsigned long flags;
@@ -945,6 +945,12 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 		MUTEX_WARN_ON(__owner_task(owner) != current);
 		MUTEX_WARN_ON(owner & MUTEX_FLAG_PICKUP);
 
+		if (sched_proxy_exec() && current->blocked_donor) {
+			/* force handoff if we have a blocked_donor */
+			owner = MUTEX_FLAG_HANDOFF;
+			break;
+		}
+
 		if (owner & MUTEX_FLAG_HANDOFF)
 			break;
 
@@ -958,7 +964,34 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 
 	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 	debug_mutex_unlock(lock);
-	if (!list_empty(&lock->wait_list)) {
+
+	if (sched_proxy_exec()) {
+		raw_spin_lock(&current->blocked_lock);
+		/*
+		 * If we have a task boosting current, and that task was boosting
+		 * current through this lock, hand the lock to that task, as that
+		 * is the highest waiter, as selected by the scheduling function.
+		 */
+		donor = current->blocked_donor;
+		if (donor) {
+			struct mutex *next_lock;
+
+			raw_spin_lock_nested(&donor->blocked_lock, SINGLE_DEPTH_NESTING);
+			next_lock = __get_task_blocked_on(donor);
+			if (next_lock == lock) {
+				next = donor;
+				__set_task_blocked_on_waking(donor, next_lock);
+				wake_q_add(&wake_q, donor);
+				current->blocked_donor = NULL;
+			}
+			raw_spin_unlock(&donor->blocked_lock);
+		}
+	}
+
+	/*
+	 * Failing that, pick any on the wait list.
+	 */
+	if (!next && !list_empty(&lock->wait_list)) {
 		/* get the first entry from the wait-list: */
 		struct mutex_waiter *waiter =
 			list_first_entry(&lock->wait_list,
@@ -966,14 +999,19 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 
 		next = waiter->task;
 
+		raw_spin_lock_nested(&next->blocked_lock, SINGLE_DEPTH_NESTING);
 		debug_mutex_wake_waiter(lock, waiter);
-		set_task_blocked_on_waking(next, lock);
+		__set_task_blocked_on_waking(next, lock);
+		raw_spin_unlock(&next->blocked_lock);
 		wake_q_add(&wake_q, next);
+
 	}
 
 	if (owner & MUTEX_FLAG_HANDOFF)
 		__mutex_handoff(lock, next);
 
+	if (sched_proxy_exec())
+		raw_spin_unlock(&current->blocked_lock);
 	raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q);
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4546ceb8eae56..eabde9706981a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6846,7 +6846,17 @@ static void proxy_force_return(struct rq *rq, struct rq_flags *rf,
  * Find runnable lock owner to proxy for mutex blocked donor
  *
  * Follow the blocked-on relation:
- *   task->blocked_on -> mutex->owner -> task...
+ *
+ *                ,-> task
+ *                |     | blocked-on
+ *                |     v
+ *  blocked_donor |   mutex
+ *                |     | owner
+ *                |     v
+ *                `-- task
+ *
+ * and set the blocked_donor relation, this latter is used by the mutex
+ * code to find which (blocked) task to hand-off to.
  *
  * Lock order:
  *
@@ -6995,6 +7005,7 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
 		 * rq, therefore holding @rq->lock is sufficient to
 		 * guarantee its existence, as per ttwu_remote().
 		 */
+		owner->blocked_donor = p;
 	}
 
 	/* Handle actions we need to do outside of the guard() scope */
@@ -7095,6 +7106,7 @@ static void __sched notrace __schedule(int sched_mode)
 	unsigned long prev_state;
 	struct rq_flags rf;
 	struct rq *rq;
+	bool prev_not_proxied;
 	int cpu;
 
 	/* Trace preemptions consistently with task switches */
@@ -7167,10 +7179,12 @@ static void __sched notrace __schedule(int sched_mode)
 		switch_count = &prev->nvcsw;
 	}
 
+	prev_not_proxied = !prev->blocked_donor;
 pick_again:
 	assert_balance_callbacks_empty(rq);
 	next = pick_next_task(rq, rq->donor, &rf);
 	rq_set_donor(rq, next);
+	next->blocked_donor = NULL;
 	if (unlikely(task_is_blocked(next))) {
 		next = find_proxy_task(rq, next, &rf);
 		if (!next) {
@@ -7236,7 +7250,7 @@ static void __sched notrace __schedule(int sched_mode)
 		rq = context_switch(rq, prev, next, &rf);
 	} else {
 		/* In case next was already curr but just got blocked_donor */
-		if (!task_current_donor(rq, next))
+		if (prev_not_proxied && next->blocked_donor)
 			proxy_tag_curr(rq, next);
 
 		rq_unpin_lock(rq, &rf);
-- 
2.51.1.930.gacf6e81ea2-goog