From 465f85fe913342a669d29d0e64760950669244b1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 24 Jul 2023 16:49:22 +0000 Subject: [PATCH] ANDROID: sched: Add blocked_donor link to task for smarter mutex handoffs 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. Cc: Joel Fernandes Cc: Qais Yousef Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Juri Lelli Cc: Vincent Guittot Cc: Dietmar Eggemann Cc: Valentin Schneider Cc: Steven Rostedt Cc: Ben Segall Cc: Zimuzo Ezeozue Cc: Mel Gorman Cc: Will Deacon Cc: Waiman Long Cc: Boqun Feng Cc: "Paul E. McKenney" Cc: Metin Kaya Cc: Xuewen Yan Cc: K Prateek Nayak Cc: Thomas Gleixner Cc: Daniel Lezcano Cc: kernel-team@android.com Change-Id: Iad6f775f928b9e90e22d1d831aff26f60f37e773 Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Juri Lelli Signed-off-by: Valentin Schneider Signed-off-by: Connor O'Brien [jstultz: This patch was split out from larger proxy patch] Signed-off-by: John Stultz Bug: 306081722 --- 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 --- include/linux/sched.h | 1 + kernel/fork.c | 1 + kernel/locking/mutex.c | 41 ++++++++++++++++++++++++++++++++++++++--- kernel/sched/core.c | 19 +++++++++++++++++-- 4 files changed, 57 insertions(+), 5 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 7bddf41bceaf..0d385fffe271 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1212,6 +1212,7 @@ struct task_struct { enum blocked_on_state blocked_on_state; 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_DEBUG_ATOMIC_SLEEP diff --git a/kernel/fork.c b/kernel/fork.c index a43629d84157..f830d2163bdc 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2365,6 +2365,7 @@ __latent_entropy struct task_struct *copy_process( p->blocked_on_state = BO_RUNNABLE; p->blocked_on = NULL; /* not blocked yet */ + p->blocked_donor = NULL; /* nobody is boosting p yet */ #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0; diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 899bec7ace3b..fb3c7b02bc69 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -921,7 +921,7 @@ 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; @@ -940,6 +940,12 @@ 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; @@ -953,7 +959,34 @@ 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(¤t->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_blocked_on_waking(donor); + 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, @@ -961,7 +994,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne next = waiter->task; - raw_spin_lock(&next->blocked_lock); + raw_spin_lock_nested(&next->blocked_lock, SINGLE_DEPTH_NESTING); debug_mutex_wake_waiter(lock, waiter); WARN_ON(get_task_blocked_on(next) != lock); set_blocked_on_waking(next); @@ -972,6 +1005,8 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne if (owner & MUTEX_FLAG_HANDOFF) __mutex_handoff(lock, next); + if (sched_proxy_exec()) + raw_spin_unlock(¤t->blocked_lock); preempt_disable(); raw_spin_unlock_irqrestore(&lock->wait_lock, flags); wake_up_q(&wake_q); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 33e36914c51c..b739ed894278 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6915,7 +6915,17 @@ void proxy_migrate_task(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: * @@ -7089,6 +7099,8 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf) */ raw_spin_unlock(&p->blocked_lock); raw_spin_unlock(&mutex->wait_lock); + + owner->blocked_donor = p; } WARN_ON_ONCE(owner && !owner->on_rq); @@ -7195,6 +7207,7 @@ 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; bool preserve_need_resched = false; @@ -7257,9 +7270,11 @@ static void __sched notrace __schedule(int sched_mode) switch_count = &prev->nvcsw; } + prev_not_proxied = !prev->blocked_donor; pick_again: 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) { @@ -7324,7 +7339,7 @@ picked: 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);