Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:7 as permitted sender) client-ip=2620:137:e000::3:7;
Date:   Mon,  6 Nov 2023 19:34:45 +0000
In-Reply-To: <20231106193524.866104-1-jstultz@google.com>
Mime-Version: 1.0
References: <20231106193524.866104-1-jstultz@google.com>
Message-ID: <20231106193524.866104-3-jstultz@google.com>
Subject: [PATCH v6 02/20] locking/mutex: Removes wakeups from under mutex::wait_lock
From:   John Stultz <jstultz@google.com>
To:     LKML <linux-kernel@vger.kernel.org>
Cc:     John Stultz <jstultz@google.com>,
        Joel Fernandes <joelaf@google.com>,
        Qais Yousef <qyousef@google.com>,
        Ingo Molnar <mingo@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Juri Lelli <juri.lelli@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Valentin Schneider <vschneid@redhat.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ben Segall <bsegall@google.com>,
        Zimuzo Ezeozue <zezeozue@google.com>,
        Youssef Esmat <youssefesmat@google.com>,
        Mel Gorman <mgorman@suse.de>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Will Deacon <will@kernel.org>,
        Waiman Long <longman@redhat.com>,
        Boqun Feng <boqun.feng@gmail.com>,
        "Paul E . McKenney" <paulmck@kernel.org>, kernel-team@android.com
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

In preparation to nest mutex::wait_lock under rq::lock we need to remove
wakeups from under it.

Cc: Joel Fernandes <joelaf@google.com>
Cc: Qais Yousef <qyousef@google.com>
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: Youssef Esmat <youssefesmat@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
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: kernel-team@android.com
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
[Heavily changed after 55f036ca7e74 ("locking: WW mutex cleanup") and
08295b3b5bee ("locking: Implement an algorithm choice for Wound-Wait
mutexes")]
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
[jstultz: rebased to mainline, added extra wake_up_q & init
 to avoid hangs, similar to Connor's rework of this patch]
Signed-off-by: John Stultz <jstultz@google.com>
---
v5:
* Reverted back to an earlier version of this patch to undo
  the change that kept the wake_q in the ctx structure, as
  that broke the rule that the wake_q must always be on the
  stack, as its not safe for concurrency.
v6:
* Made tweaks suggested by Waiman Long
---
 kernel/locking/mutex.c    | 17 +++++++++++++----
 kernel/locking/ww_mutex.h | 29 ++++++++++++++++++-----------
 2 files changed, 31 insertions(+), 15 deletions(-)

diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index d973fe6041bf..4ada158eb7ca 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -570,6 +570,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 		    struct lockdep_map *nest_lock, unsigned long ip,
 		    struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
 {
+	DEFINE_WAKE_Q(wake_q);
 	struct mutex_waiter waiter;
 	struct ww_mutex *ww;
 	int ret;
@@ -620,7 +621,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 	 */
 	if (__mutex_trylock(lock)) {
 		if (ww_ctx)
-			__ww_mutex_check_waiters(lock, ww_ctx);
+			__ww_mutex_check_waiters(lock, ww_ctx, &wake_q);
 
 		goto skip_wait;
 	}
@@ -640,7 +641,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 		 * Add in stamp order, waking up waiters that must kill
 		 * themselves.
 		 */
-		ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx);
+		ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx, &wake_q);
 		if (ret)
 			goto err_early_kill;
 	}
@@ -676,6 +677,11 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 		}
 
 		raw_spin_unlock(&lock->wait_lock);
+		/* Make sure we do wakeups before calling schedule */
+		if (!wake_q_empty(&wake_q)) {
+			wake_up_q(&wake_q);
+			wake_q_init(&wake_q);
+		}
 		schedule_preempt_disabled();
 
 		first = __mutex_waiter_is_first(lock, &waiter);
@@ -709,7 +715,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 		 */
 		if (!ww_ctx->is_wait_die &&
 		    !__mutex_waiter_is_first(lock, &waiter))
-			__ww_mutex_check_waiters(lock, ww_ctx);
+			__ww_mutex_check_waiters(lock, ww_ctx, &wake_q);
 	}
 
 	__mutex_remove_waiter(lock, &waiter);
@@ -725,6 +731,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 		ww_mutex_lock_acquired(ww, ww_ctx);
 
 	raw_spin_unlock(&lock->wait_lock);
+	wake_up_q(&wake_q);
 	preempt_enable();
 	return 0;
 
@@ -736,6 +743,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 	raw_spin_unlock(&lock->wait_lock);
 	debug_mutex_free_waiter(&waiter);
 	mutex_release(&lock->dep_map, ip);
+	wake_up_q(&wake_q);
 	preempt_enable();
 	return ret;
 }
@@ -929,6 +937,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 		}
 	}
 
+	preempt_disable();
 	raw_spin_lock(&lock->wait_lock);
 	debug_mutex_unlock(lock);
 	if (!list_empty(&lock->wait_list)) {
@@ -947,8 +956,8 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 		__mutex_handoff(lock, next);
 
 	raw_spin_unlock(&lock->wait_lock);
-
 	wake_up_q(&wake_q);
+	preempt_enable();
 }
 
 #ifndef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h
index 3ad2cc4823e5..7189c6631d90 100644
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -275,7 +275,7 @@ __ww_ctx_less(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b)
  */
 static bool
 __ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter,
-	       struct ww_acquire_ctx *ww_ctx)
+	       struct ww_acquire_ctx *ww_ctx, struct wake_q_head *wake_q)
 {
 	if (!ww_ctx->is_wait_die)
 		return false;
@@ -284,7 +284,7 @@ __ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter,
 #ifndef WW_RT
 		debug_mutex_wake_waiter(lock, waiter);
 #endif
-		wake_up_process(waiter->task);
+		wake_q_add(wake_q, waiter->task);
 	}
 
 	return true;
@@ -299,7 +299,8 @@ __ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter,
  */
 static bool __ww_mutex_wound(struct MUTEX *lock,
 			     struct ww_acquire_ctx *ww_ctx,
-			     struct ww_acquire_ctx *hold_ctx)
+			     struct ww_acquire_ctx *hold_ctx,
+			     struct wake_q_head *wake_q)
 {
 	struct task_struct *owner = __ww_mutex_owner(lock);
 
@@ -331,7 +332,7 @@ static bool __ww_mutex_wound(struct MUTEX *lock,
 		 * wakeup pending to re-read the wounded state.
 		 */
 		if (owner != current)
-			wake_up_process(owner);
+			wake_q_add(wake_q, owner);
 
 		return true;
 	}
@@ -352,7 +353,8 @@ static bool __ww_mutex_wound(struct MUTEX *lock,
  * The current task must not be on the wait list.
  */
 static void
-__ww_mutex_check_waiters(struct MUTEX *lock, struct ww_acquire_ctx *ww_ctx)
+__ww_mutex_check_waiters(struct MUTEX *lock, struct ww_acquire_ctx *ww_ctx,
+			 struct wake_q_head *wake_q)
 {
 	struct MUTEX_WAITER *cur;
 
@@ -364,8 +366,8 @@ __ww_mutex_check_waiters(struct MUTEX *lock, struct ww_acquire_ctx *ww_ctx)
 		if (!cur->ww_ctx)
 			continue;
 
-		if (__ww_mutex_die(lock, cur, ww_ctx) ||
-		    __ww_mutex_wound(lock, cur->ww_ctx, ww_ctx))
+		if (__ww_mutex_die(lock, cur, ww_ctx, wake_q) ||
+		    __ww_mutex_wound(lock, cur->ww_ctx, ww_ctx, wake_q))
 			break;
 	}
 }
@@ -377,6 +379,8 @@ __ww_mutex_check_waiters(struct MUTEX *lock, struct ww_acquire_ctx *ww_ctx)
 static __always_inline void
 ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
+	DEFINE_WAKE_Q(wake_q);
+
 	ww_mutex_lock_acquired(lock, ctx);
 
 	/*
@@ -405,8 +409,10 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 	 * die or wound us.
 	 */
 	lock_wait_lock(&lock->base);
-	__ww_mutex_check_waiters(&lock->base, ctx);
+	__ww_mutex_check_waiters(&lock->base, ctx, &wake_q);
 	unlock_wait_lock(&lock->base);
+
+	wake_up_q(&wake_q);
 }
 
 static __always_inline int
@@ -488,7 +494,8 @@ __ww_mutex_check_kill(struct MUTEX *lock, struct MUTEX_WAITER *waiter,
 static inline int
 __ww_mutex_add_waiter(struct MUTEX_WAITER *waiter,
 		      struct MUTEX *lock,
-		      struct ww_acquire_ctx *ww_ctx)
+		      struct ww_acquire_ctx *ww_ctx,
+		      struct wake_q_head *wake_q)
 {
 	struct MUTEX_WAITER *cur, *pos = NULL;
 	bool is_wait_die;
@@ -532,7 +539,7 @@ __ww_mutex_add_waiter(struct MUTEX_WAITER *waiter,
 		pos = cur;
 
 		/* Wait-Die: ensure younger waiters die. */
-		__ww_mutex_die(lock, cur, ww_ctx);
+		__ww_mutex_die(lock, cur, ww_ctx, wake_q);
 	}
 
 	__ww_waiter_add(lock, waiter, pos);
@@ -550,7 +557,7 @@ __ww_mutex_add_waiter(struct MUTEX_WAITER *waiter,
 		 * such that either we or the fastpath will wound @ww->ctx.
 		 */
 		smp_mb();
-		__ww_mutex_wound(lock, ww_ctx, ww->ctx);
+		__ww_mutex_wound(lock, ww_ctx, ww->ctx, wake_q);
 	}
 
 	return 0;
-- 
2.42.0.869.gea05f2083d-goog