From 6510e4a2d04f33e4bfd221760faab23e55d8772b Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 4 Feb 2021 17:28:54 +0000 Subject: futex,rt_mutex: Provide futex specific rt_mutex API From: Peter Zijlstra [ Upstream commit 5293c2efda37775346885c7e924d4ef7018ea60b ] Part of what makes futex_unlock_pi() intricate is that rt_mutex_futex_unlock() -> rt_mutex_slowunlock() can drop rt_mutex::wait_lock. This means it cannot rely on the atomicy of wait_lock, which would be preferred in order to not rely on hb->lock so much. The reason rt_mutex_slowunlock() needs to drop wait_lock is because it can race with the rt_mutex fastpath, however futexes have their own fast path. Since futexes already have a bunch of separate rt_mutex accessors, complete that set and implement a rt_mutex variant without fastpath for them. Signed-off-by: Peter Zijlstra (Intel) Cc: juri.lelli@arm.com Cc: bigeasy@linutronix.de Cc: xlpang@redhat.com Cc: rostedt@goodmis.org Cc: mathieu.desnoyers@efficios.com Cc: jdesfossez@efficios.com Cc: dvhart@infradead.org Cc: bristot@redhat.com Link: http://lkml.kernel.org/r/20170322104151.702962446@infradead.org Signed-off-by: Thomas Gleixner [Lee: Back-ported to solve a dependency] Signed-off-by: Lee Jones Signed-off-by: Greg Kroah-Hartman --- kernel/locking/rtmutex.c | 56 ++++++++++++++++++++++++++++++----------- kernel/locking/rtmutex_common.h | 8 ++++-- 2 files changed, 47 insertions(+), 17 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index dd173df9ee5e..3323ef935372 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1485,15 +1485,23 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); /* * Futex variant with full deadlock detection. + * Futex variants must not use the fast-path, see __rt_mutex_futex_unlock(). */ -int rt_mutex_timed_futex_lock(struct rt_mutex *lock, +int __sched rt_mutex_timed_futex_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout) { might_sleep(); - return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, - RT_MUTEX_FULL_CHAINWALK, - rt_mutex_slowlock); + return rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, + timeout, RT_MUTEX_FULL_CHAINWALK); +} + +/* + * Futex variant, must not use fastpath. + */ +int __sched rt_mutex_futex_trylock(struct rt_mutex *lock) +{ + return rt_mutex_slowtrylock(lock); } /** @@ -1552,20 +1560,38 @@ void __sched rt_mutex_unlock(struct rt_mutex *lock) EXPORT_SYMBOL_GPL(rt_mutex_unlock); /** - * rt_mutex_futex_unlock - Futex variant of rt_mutex_unlock - * @lock: the rt_mutex to be unlocked - * - * Returns: true/false indicating whether priority adjustment is - * required or not. + * Futex variant, that since futex variants do not use the fast-path, can be + * simple and will not need to retry. */ -bool __sched rt_mutex_futex_unlock(struct rt_mutex *lock, - struct wake_q_head *wqh) +bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, + struct wake_q_head *wake_q) { - if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) { - rt_mutex_deadlock_account_unlock(current); - return false; + lockdep_assert_held(&lock->wait_lock); + + debug_rt_mutex_unlock(lock); + + if (!rt_mutex_has_waiters(lock)) { + lock->owner = NULL; + return false; /* done */ + } + + mark_wakeup_next_waiter(wake_q, lock); + return true; /* deboost and wakeups */ +} + +void __sched rt_mutex_futex_unlock(struct rt_mutex *lock) +{ + WAKE_Q(wake_q); + bool deboost; + + raw_spin_lock_irq(&lock->wait_lock); + deboost = __rt_mutex_futex_unlock(lock, &wake_q); + raw_spin_unlock_irq(&lock->wait_lock); + + if (deboost) { + wake_up_q(&wake_q); + rt_mutex_adjust_prio(current); } - return rt_mutex_slowunlock(lock, wqh); } /** diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index 6f8f68edb700..cdcaccfb7443 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -112,8 +112,12 @@ extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter); extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to); -extern bool rt_mutex_futex_unlock(struct rt_mutex *lock, - struct wake_q_head *wqh); +extern int rt_mutex_futex_trylock(struct rt_mutex *l); + +extern void rt_mutex_futex_unlock(struct rt_mutex *lock); +extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock, + struct wake_q_head *wqh); + extern void rt_mutex_adjust_prio(struct task_struct *task); #ifdef CONFIG_DEBUG_RT_MUTEXES -- cgit v1.2.3 From fd7924d6f23c8b9a1da45e438be773d5d11bda10 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 4 Feb 2021 17:28:55 +0000 Subject: futex: Remove rt_mutex_deadlock_account_*() From: Peter Zijlstra These are unused and clutter up the code. Signed-off-by: Peter Zijlstra (Intel) Cc: juri.lelli@arm.com Cc: bigeasy@linutronix.de Cc: xlpang@redhat.com Cc: rostedt@goodmis.org Cc: mathieu.desnoyers@efficios.com Cc: jdesfossez@efficios.com Cc: dvhart@infradead.org Cc: bristot@redhat.com Link: http://lkml.kernel.org/r/20170322104151.652692478@infradead.org Signed-off-by: Thomas Gleixner [Lee: Back-ported to solve a dependency] Signed-off-by: Lee Jones Signed-off-by: Greg Kroah-Hartman --- kernel/locking/rtmutex-debug.c | 9 --------- kernel/locking/rtmutex-debug.h | 3 --- kernel/locking/rtmutex.c | 42 ++++++++++++++++-------------------------- kernel/locking/rtmutex.h | 2 -- 4 files changed, 16 insertions(+), 40 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c index 62b6cee8ea7f..0613c4b1d059 100644 --- a/kernel/locking/rtmutex-debug.c +++ b/kernel/locking/rtmutex-debug.c @@ -173,12 +173,3 @@ void debug_rt_mutex_init(struct rt_mutex *lock, const char *name) lock->name = name; } -void -rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task) -{ -} - -void rt_mutex_deadlock_account_unlock(struct task_struct *task) -{ -} - diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h index d0519c3432b6..b585af9a1b50 100644 --- a/kernel/locking/rtmutex-debug.h +++ b/kernel/locking/rtmutex-debug.h @@ -9,9 +9,6 @@ * This file contains macros used solely by rtmutex.c. Debug version. */ -extern void -rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task); -extern void rt_mutex_deadlock_account_unlock(struct task_struct *task); extern void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); extern void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter); extern void debug_rt_mutex_init(struct rt_mutex *lock, const char *name); diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 3323ef935372..e3dd1642423f 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -937,8 +937,6 @@ takeit: */ rt_mutex_set_owner(lock, task); - rt_mutex_deadlock_account_lock(lock, task); - return 1; } @@ -1331,8 +1329,6 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, debug_rt_mutex_unlock(lock); - rt_mutex_deadlock_account_unlock(current); - /* * We must be careful here if the fast path is enabled. If we * have no waiters queued we cannot set owner to NULL here @@ -1398,11 +1394,10 @@ rt_mutex_fastlock(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, enum rtmutex_chainwalk chwalk)) { - if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { - rt_mutex_deadlock_account_lock(lock, current); + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) return 0; - } else - return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); + + return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); } static inline int @@ -1414,21 +1409,19 @@ rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, enum rtmutex_chainwalk chwalk)) { if (chwalk == RT_MUTEX_MIN_CHAINWALK && - likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { - rt_mutex_deadlock_account_lock(lock, current); + likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) return 0; - } else - return slowfn(lock, state, timeout, chwalk); + + return slowfn(lock, state, timeout, chwalk); } static inline int rt_mutex_fasttrylock(struct rt_mutex *lock, int (*slowfn)(struct rt_mutex *lock)) { - if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { - rt_mutex_deadlock_account_lock(lock, current); + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) return 1; - } + return slowfn(lock); } @@ -1438,19 +1431,18 @@ rt_mutex_fastunlock(struct rt_mutex *lock, struct wake_q_head *wqh)) { WAKE_Q(wake_q); + bool deboost; - if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) { - rt_mutex_deadlock_account_unlock(current); + if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) + return; - } else { - bool deboost = slowfn(lock, &wake_q); + deboost = slowfn(lock, &wake_q); - wake_up_q(&wake_q); + wake_up_q(&wake_q); - /* Undo pi boosting if necessary: */ - if (deboost) - rt_mutex_adjust_prio(current); - } + /* Undo pi boosting if necessary: */ + if (deboost) + rt_mutex_adjust_prio(current); } /** @@ -1648,7 +1640,6 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock, __rt_mutex_init(lock, NULL); debug_rt_mutex_proxy_lock(lock, proxy_owner); rt_mutex_set_owner(lock, proxy_owner); - rt_mutex_deadlock_account_lock(lock, proxy_owner); } /** @@ -1664,7 +1655,6 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock, { debug_rt_mutex_proxy_unlock(lock); rt_mutex_set_owner(lock, NULL); - rt_mutex_deadlock_account_unlock(proxy_owner); } /** diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h index c4060584c407..6607802efa8b 100644 --- a/kernel/locking/rtmutex.h +++ b/kernel/locking/rtmutex.h @@ -11,8 +11,6 @@ */ #define rt_mutex_deadlock_check(l) (0) -#define rt_mutex_deadlock_account_lock(m, t) do { } while (0) -#define rt_mutex_deadlock_account_unlock(l) do { } while (0) #define debug_rt_mutex_init_waiter(w) do { } while (0) #define debug_rt_mutex_free_waiter(w) do { } while (0) #define debug_rt_mutex_lock(l) do { } while (0) -- cgit v1.2.3 From ad4740ceccfbf326b7f82ebac43d860a64240c1c Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 4 Feb 2021 17:28:57 +0000 Subject: futex: Avoid violating the 10th rule of futex From: Peter Zijlstra commit c1e2f0eaf015fb7076d51a339011f2383e6dd389 upstream. Julia reported futex state corruption in the following scenario: waiter waker stealer (prio > waiter) futex(WAIT_REQUEUE_PI, uaddr, uaddr2, timeout=[N ms]) futex_wait_requeue_pi() futex_wait_queue_me() freezable_schedule() futex(LOCK_PI, uaddr2) futex(CMP_REQUEUE_PI, uaddr, uaddr2, 1, 0) /* requeues waiter to uaddr2 */ futex(UNLOCK_PI, uaddr2) wake_futex_pi() cmp_futex_value_locked(uaddr2, waiter) wake_up_q() task> futex(LOCK_PI, uaddr2) __rt_mutex_start_proxy_lock() try_to_take_rt_mutex() /* steals lock */ rt_mutex_set_owner(lock, stealer) rt_mutex_wait_proxy_lock() __rt_mutex_slowlock() try_to_take_rt_mutex() /* fails, lock held by stealer */ if (timeout && !timeout->task) return -ETIMEDOUT; fixup_owner() /* lock wasn't acquired, so, fixup_pi_state_owner skipped */ return -ETIMEDOUT; /* At this point, we've returned -ETIMEDOUT to userspace, but the * futex word shows waiter to be the owner, and the pi_mutex has * stealer as the owner */ futex_lock(LOCK_PI, uaddr2) -> bails with EDEADLK, futex word says we're owner. And suggested that what commit: 73d786bd043e ("futex: Rework inconsistent rt_mutex/futex_q state") removes from fixup_owner() looks to be just what is needed. And indeed it is -- I completely missed that requeue_pi could also result in this case. So we need to restore that, except that subsequent patches, like commit: 16ffa12d7425 ("futex: Pull rt_mutex_futex_unlock() out from under hb->lock") changed all the locking rules. Even without that, the sequence: - if (rt_mutex_futex_trylock(&q->pi_state->pi_mutex)) { - locked = 1; - goto out; - } - raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock); - owner = rt_mutex_owner(&q->pi_state->pi_mutex); - if (!owner) - owner = rt_mutex_next_owner(&q->pi_state->pi_mutex); - raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock); - ret = fixup_pi_state_owner(uaddr, q, owner); already suggests there were races; otherwise we'd never have to look at next_owner. So instead of doing 3 consecutive wait_lock sections with who knows what races, we do it all in a single section. Additionally, the usage of pi_state->owner in fixup_owner() was only safe because only the rt_mutex owner would modify it, which this additional case wrecks. Luckily the values can only change away and not to the value we're testing, this means we can do a speculative test and double check once we have the wait_lock. Fixes: 73d786bd043e ("futex: Rework inconsistent rt_mutex/futex_q state") Reported-by: Julia Cartwright Reported-by: Gratian Crisan Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Tested-by: Julia Cartwright Tested-by: Gratian Crisan Cc: Darren Hart Link: https://lkml.kernel.org/r/20171208124939.7livp7no2ov65rrc@hirez.programming.kicks-ass.net Signed-off-by: Greg Kroah-Hartman [Lee: Back-ported to solve a dependency] Signed-off-by: Lee Jones Signed-off-by: Greg Kroah-Hartman --- kernel/locking/rtmutex.c | 26 +++++++++++++++++++------- kernel/locking/rtmutex_common.h | 1 + 2 files changed, 20 insertions(+), 7 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index e3dd1642423f..45d3c9aec853 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1284,6 +1284,19 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, return ret; } +static inline int __rt_mutex_slowtrylock(struct rt_mutex *lock) +{ + int ret = try_to_take_rt_mutex(lock, current, NULL); + + /* + * try_to_take_rt_mutex() sets the lock waiters bit + * unconditionally. Clean this up. + */ + fixup_rt_mutex_waiters(lock); + + return ret; +} + /* * Slow path try-lock function: */ @@ -1305,13 +1318,7 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) */ raw_spin_lock(&lock->wait_lock); - ret = try_to_take_rt_mutex(lock, current, NULL); - - /* - * try_to_take_rt_mutex() sets the lock waiters bit - * unconditionally. Clean this up. - */ - fixup_rt_mutex_waiters(lock); + ret = __rt_mutex_slowtrylock(lock); raw_spin_unlock(&lock->wait_lock); @@ -1496,6 +1503,11 @@ int __sched rt_mutex_futex_trylock(struct rt_mutex *lock) return rt_mutex_slowtrylock(lock); } +int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock) +{ + return __rt_mutex_slowtrylock(lock); +} + /** * rt_mutex_timed_lock - lock a rt_mutex interruptible * the timeout structure is provided diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index cdcaccfb7443..ea7310b9ce83 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -113,6 +113,7 @@ extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter); extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to); extern int rt_mutex_futex_trylock(struct rt_mutex *l); +extern int __rt_mutex_futex_trylock(struct rt_mutex *l); extern void rt_mutex_futex_unlock(struct rt_mutex *lock); extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock, -- cgit v1.2.3 From 42255927e832f9c1ed8db4e84530bc6a54aa2fee Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 4 Feb 2021 17:29:00 +0000 Subject: rtmutex: Remove unused argument from rt_mutex_proxy_unlock() From: Thomas Gleixner [ Upstream commit 2156ac1934166d6deb6cd0f6ffc4c1076ec63697 ] Nothing uses the argument. Remove it as preparation to use pi_state_update_owner(). Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org Signed-off-by: Lee Jones Signed-off-by: Greg Kroah-Hartman --- kernel/locking/rtmutex.c | 3 +-- kernel/locking/rtmutex_common.h | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 45d3c9aec853..1c0cb5c3c6ad 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1662,8 +1662,7 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock, * No locking. Caller has to do serializing itself * Special API call for PI-futex support */ -void rt_mutex_proxy_unlock(struct rt_mutex *lock, - struct task_struct *proxy_owner) +void rt_mutex_proxy_unlock(struct rt_mutex *lock) { debug_rt_mutex_proxy_unlock(lock); rt_mutex_set_owner(lock, NULL); diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index ea7310b9ce83..4584db96265d 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -101,8 +101,7 @@ enum rtmutex_chainwalk { extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner); -extern void rt_mutex_proxy_unlock(struct rt_mutex *lock, - struct task_struct *proxy_owner); +extern void rt_mutex_proxy_unlock(struct rt_mutex *lock); extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, struct task_struct *task); -- cgit v1.2.3