Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Mon,  3 Oct 2022 21:44:51 +0000
In-Reply-To: <20221003214501.2050087-1-connoro@google.com>
Mime-Version: 1.0
References: <20221003214501.2050087-1-connoro@google.com>
Message-ID: <20221003214501.2050087-2-connoro@google.com>
Subject: [RFC PATCH 01/11] locking/ww_mutex: Remove wakeups from under mutex::wait_lock
From:   "Connor O'Brien" <connoro@google.com>
To:     linux-kernel@vger.kernel.org
Cc:     kernel-team@android.com, John Stultz <jstultz@google.com>,
        Joel Fernandes <joelaf@google.com>,
        Qais Yousef <qais.yousef@arm.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>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Valentin Schneider <vschneid@redhat.com>,
        Will Deacon <will@kernel.org>,
        Waiman Long <longman@redhat.com>,
        Boqun Feng <boqun.feng@gmail.com>,
        "Paul E . McKenney" <paulmck@kernel.org>,
        "Connor O'Brien" <connoro@google.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

From: Peter Zijlstra <peterz@infradead.org>

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

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Connor O'Brien <connoro@google.com>
---
 include/linux/ww_mutex.h  | 3 +++
 kernel/locking/mutex.c    | 8 ++++++++
 kernel/locking/ww_mutex.h | 9 +++++++--
 kernel/sched/core.c       | 7 +++++++
 4 files changed, 25 insertions(+), 2 deletions(-)

diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index bb763085479a..9335b2202017 100644
--- a/include/linux/ww_mutex.h
+++ b/include/linux/ww_mutex.h
@@ -19,6 +19,7 @@
 
 #include <linux/mutex.h>
 #include <linux/rtmutex.h>
+#include <linux/sched/wake_q.h>
 
 #if defined(CONFIG_DEBUG_MUTEXES) || \
    (defined(CONFIG_PREEMPT_RT) && defined(CONFIG_DEBUG_RT_MUTEXES))
@@ -58,6 +59,7 @@ struct ww_acquire_ctx {
 	unsigned int acquired;
 	unsigned short wounded;
 	unsigned short is_wait_die;
+	struct wake_q_head wake_q;
 #ifdef DEBUG_WW_MUTEXES
 	unsigned int done_acquire;
 	struct ww_class *ww_class;
@@ -137,6 +139,7 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx,
 	ctx->acquired = 0;
 	ctx->wounded = false;
 	ctx->is_wait_die = ww_class->is_wait_die;
+	wake_q_init(&ctx->wake_q);
 #ifdef DEBUG_WW_MUTEXES
 	ctx->ww_class = ww_class;
 	ctx->done_acquire = 0;
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index d973fe6041bf..1582756914df 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -676,6 +676,8 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 		}
 
 		raw_spin_unlock(&lock->wait_lock);
+		if (ww_ctx)
+			ww_ctx_wake(ww_ctx);
 		schedule_preempt_disabled();
 
 		first = __mutex_waiter_is_first(lock, &waiter);
@@ -725,6 +727,8 @@ __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);
+	if (ww_ctx)
+		ww_ctx_wake(ww_ctx);
 	preempt_enable();
 	return 0;
 
@@ -736,6 +740,8 @@ __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);
+	if (ww_ctx)
+		ww_ctx_wake(ww_ctx);
 	preempt_enable();
 	return ret;
 }
@@ -946,9 +952,11 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 	if (owner & MUTEX_FLAG_HANDOFF)
 		__mutex_handoff(lock, next);
 
+	preempt_disable();
 	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 56f139201f24..dfc174cd96c6 100644
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -161,6 +161,11 @@ static inline void lockdep_assert_wait_lock_held(struct rt_mutex *lock)
 
 #endif /* WW_RT */
 
+void ww_ctx_wake(struct ww_acquire_ctx *ww_ctx)
+{
+	wake_up_q(&ww_ctx->wake_q);
+}
+
 /*
  * Wait-Die:
  *   The newer transactions are killed when:
@@ -284,7 +289,7 @@ __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(&ww_ctx->wake_q, waiter->task);
 	}
 
 	return true;
@@ -331,7 +336,7 @@ 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(&ww_ctx->wake_q, owner);
 
 		return true;
 	}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ee28253c9ac0..617e737392be 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1013,6 +1013,13 @@ void wake_up_q(struct wake_q_head *head)
 		wake_up_process(task);
 		put_task_struct(task);
 	}
+	/*
+	 * XXX connoro: seems this is needed now that ww_ctx_wake() passes in a
+	 * wake_q_head that is embedded in struct ww_acquire_ctx rather than
+	 * declared locally.
+	 */
+	head->first = node;
+	head->lastp = &head->first;
 }
 
 /*
-- 
2.38.0.rc1.362.ged0d419d3c-goog