mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "tip-bot2 for Sebastian Andrzej Siewior" <tip-bot2@linutronix.de>
To: linux-tip-commits@vger.kernel.org
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Thomas Gleixner <tglx@linutronix.de>,
	"Peter Zijlstra (Intel)" <peterz@infradead.org>,
	x86@kernel.org, linux-kernel@vger.kernel.org
Subject: [tip: locking/core] locking/rtmutex: Avoid unconditional slowpath for DEBUG_RT_MUTEXES
Date: Wed, 20 Sep 2023 07:36:11 -0000	[thread overview]
Message-ID: <169519537199.27769.4944666008849551688.tip-bot2@tip-bot2> (raw)
In-Reply-To: <20230908162254.999499-3-bigeasy@linutronix.de>

The following commit has been merged into the locking/core branch of tip:

Commit-ID:     af9f006393b53409be0ca83ae234bef840cdef4a
Gitweb:        https://git.kernel.org/tip/af9f006393b53409be0ca83ae234bef840cdef4a
Author:        Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate:    Fri, 08 Sep 2023 18:22:49 +02:00
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Wed, 20 Sep 2023 09:31:11 +02:00

locking/rtmutex: Avoid unconditional slowpath for DEBUG_RT_MUTEXES

With DEBUG_RT_MUTEXES enabled the fast-path rt_mutex_cmpxchg_acquire()
always fails and all lock operations take the slow path.

Provide a new helper inline rt_mutex_try_acquire() which maps to
rt_mutex_cmpxchg_acquire() in the non-debug case. For the debug case
it invokes rt_mutex_slowtrylock() which can acquire a non-contended
rtmutex under full debug coverage.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230908162254.999499-3-bigeasy@linutronix.de
---
 kernel/locking/rtmutex.c     | 21 ++++++++++++++++++++-
 kernel/locking/ww_rt_mutex.c |  2 +-
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 21db0df..bcec053 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -218,6 +218,11 @@ static __always_inline bool rt_mutex_cmpxchg_acquire(struct rt_mutex_base *lock,
 	return try_cmpxchg_acquire(&lock->owner, &old, new);
 }
 
+static __always_inline bool rt_mutex_try_acquire(struct rt_mutex_base *lock)
+{
+	return rt_mutex_cmpxchg_acquire(lock, NULL, current);
+}
+
 static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex_base *lock,
 						     struct task_struct *old,
 						     struct task_struct *new)
@@ -297,6 +302,20 @@ static __always_inline bool rt_mutex_cmpxchg_acquire(struct rt_mutex_base *lock,
 
 }
 
+static int __sched rt_mutex_slowtrylock(struct rt_mutex_base *lock);
+
+static __always_inline bool rt_mutex_try_acquire(struct rt_mutex_base *lock)
+{
+	/*
+	 * With debug enabled rt_mutex_cmpxchg trylock() will always fail.
+	 *
+	 * Avoid unconditionally taking the slow path by using
+	 * rt_mutex_slow_trylock() which is covered by the debug code and can
+	 * acquire a non-contended rtmutex.
+	 */
+	return rt_mutex_slowtrylock(lock);
+}
+
 static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex_base *lock,
 						     struct task_struct *old,
 						     struct task_struct *new)
@@ -1755,7 +1774,7 @@ static int __sched rt_mutex_slowlock(struct rt_mutex_base *lock,
 static __always_inline int __rt_mutex_lock(struct rt_mutex_base *lock,
 					   unsigned int state)
 {
-	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
+	if (likely(rt_mutex_try_acquire(lock)))
 		return 0;
 
 	return rt_mutex_slowlock(lock, NULL, state);
diff --git a/kernel/locking/ww_rt_mutex.c b/kernel/locking/ww_rt_mutex.c
index d1473c6..c7196de 100644
--- a/kernel/locking/ww_rt_mutex.c
+++ b/kernel/locking/ww_rt_mutex.c
@@ -62,7 +62,7 @@ __ww_rt_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx,
 	}
 	mutex_acquire_nest(&rtm->dep_map, 0, 0, nest_lock, ip);
 
-	if (likely(rt_mutex_cmpxchg_acquire(&rtm->rtmutex, NULL, current))) {
+	if (likely(rt_mutex_try_acquire(&rtm->rtmutex))) {
 		if (ww_ctx)
 			ww_mutex_set_context_fastpath(lock, ww_ctx);
 		return 0;

  reply	other threads:[~2023-09-20  7:36 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-09-08 16:22 [PATCH v3 0/7] locking/rtmutex: Avoid PI state recursion through sched_submit_work() Sebastian Andrzej Siewior
2023-09-08 16:22 ` [PATCH v3 1/7] sched: Constrain locks in sched_submit_work() Sebastian Andrzej Siewior
2023-09-20  7:36   ` [tip: locking/core] " tip-bot2 for Peter Zijlstra
2023-09-08 16:22 ` [PATCH v3 2/7] locking/rtmutex: Avoid unconditional slowpath for DEBUG_RT_MUTEXES Sebastian Andrzej Siewior
2023-09-20  7:36   ` tip-bot2 for Sebastian Andrzej Siewior [this message]
2023-09-08 16:22 ` [PATCH v3 3/7] sched: Extract __schedule_loop() Sebastian Andrzej Siewior
2023-09-20  7:36   ` [tip: locking/core] " tip-bot2 for Thomas Gleixner
2023-09-08 16:22 ` [PATCH v3 4/7] sched: Provide rt_mutex specific scheduler helpers Sebastian Andrzej Siewior
2023-09-20  7:36   ` [tip: locking/core] " tip-bot2 for Peter Zijlstra
2023-09-08 16:22 ` [PATCH v3 5/7] locking/rtmutex: Use " Sebastian Andrzej Siewior
2023-09-20  7:36   ` [tip: locking/core] " tip-bot2 for Sebastian Andrzej Siewior
2023-09-08 16:22 ` [PATCH v3 6/7] locking/rtmutex: Add a lockdep assert to catch potential nested blocking Sebastian Andrzej Siewior
2023-09-20  7:36   ` [tip: locking/core] " tip-bot2 for Thomas Gleixner
2023-09-08 16:22 ` [PATCH v3 7/7] locking/rtmutex: Acquire the hb lock via trylock after wait-proxylock Sebastian Andrzej Siewior
2023-09-09 18:29   ` Peter Zijlstra
2023-09-11 14:11   ` Peter Zijlstra
2023-09-12 10:57     ` Peter Zijlstra
2023-09-12 11:26       ` Sebastian Andrzej Siewior
2023-09-12 11:17     ` Sebastian Andrzej Siewior
2023-09-12 11:24       ` Peter Zijlstra
2023-09-12 11:25       ` Sebastian Andrzej Siewior
2023-09-12 11:25       ` Peter Zijlstra
2023-09-12 11:28         ` Sebastian Andrzej Siewior
2023-09-15 12:58     ` Thomas Gleixner
2023-09-15 13:15       ` Sebastian Andrzej Siewior
2023-09-15 15:19       ` Peter Zijlstra
2023-09-15 18:59         ` Thomas Gleixner
2023-09-19 11:03         ` Sebastian Andrzej Siewior
2023-09-20  7:36         ` [tip: locking/core] futex/pi: Fix recursive rt_mutex waiter state tip-bot2 for Peter Zijlstra
2024-01-15 11:40         ` [PATCH v3 7/7] locking/rtmutex: Acquire the hb lock via trylock after wait-proxylock Jiri Slaby
2024-01-15 11:52           ` Jiri Slaby
2024-01-15 12:16             ` Sebastian Andrzej Siewior
2024-01-15 12:54             ` Jiri Slaby
2024-01-15 15:32               ` Yann Ylavic
2024-01-15 18:33               ` Sebastian Andrzej Siewior
2024-01-16  7:07                 ` Jiri Slaby

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=169519537199.27769.4944666008849551688.tip-bot2@tip-bot2 \
    --to=tip-bot2@linutronix.de \
    --cc=bigeasy@linutronix.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-tip-commits@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®