linux-kernel - [PATCH 2/6] locking/rtmutex: Avoid unconditional slowpath for DEBUG_RT

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20230815111430.220899937@infradead.org>
Date:   Tue, 15 Aug 2023 13:01:23 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     bigeasy@...utronix.de, tglx@...utronix.de
Cc:     linux-kernel@...r.kernel.org, peterz@...radead.org,
        bsegall@...gle.com, boqun.feng@...il.com, swood@...hat.com,
        bristot@...hat.com, dietmar.eggemann@....com, mingo@...hat.com,
        jstultz@...gle.com, juri.lelli@...hat.com, mgorman@...e.de,
        rostedt@...dmis.org, vschneid@...hat.com,
        vincent.guittot@...aro.org, longman@...hat.com, will@...nel.org
Subject: [PATCH 2/6] locking/rtmutex: Avoid unconditional slowpath for DEBUG_RT_MUTEXES

From: Sebastian Andrzej Siewior <bigeasy@...utronix.de>

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@...utronix.de>
Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Link: https://lkml.kernel.org/r/20230427111937.2745231-4-bigeasy@linutronix.de
---
 kernel/locking/rtmutex.c     |   21 ++++++++++++++++++++-
 kernel/locking/ww_rt_mutex.c |    2 +-
 2 files changed, 21 insertions(+), 2 deletions(-)

--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -218,6 +218,11 @@ static __always_inline bool rt_mutex_cmp
 	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_cmp
 
 }
 
+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(str
 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);
--- 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
 	}
 	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;