From 1c0908d8e441631f5b8ba433523cf39339ee2ba0 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 2 Dec 2022 10:02:23 +0000 Subject: rtmutex: Add acquire semantics for rtmutex lock acquisition slow path Jan Kara reported the following bug triggering on 6.0.5-rt14 running dbench on XFS on arm64. kernel BUG at fs/inode.c:625! Internal error: Oops - BUG: 0 [#1] PREEMPT_RT SMP CPU: 11 PID: 6611 Comm: dbench Tainted: G E 6.0.0-rt14-rt+ #1 pc : clear_inode+0xa0/0xc0 lr : clear_inode+0x38/0xc0 Call trace: clear_inode+0xa0/0xc0 evict+0x160/0x180 iput+0x154/0x240 do_unlinkat+0x184/0x300 __arm64_sys_unlinkat+0x48/0xc0 el0_svc_common.constprop.4+0xe4/0x2c0 do_el0_svc+0xac/0x100 el0_svc+0x78/0x200 el0t_64_sync_handler+0x9c/0xc0 el0t_64_sync+0x19c/0x1a0 It also affects 6.1-rc7-rt5 and affects a preempt-rt fork of 5.14 so this is likely a bug that existed forever and only became visible when ARM support was added to preempt-rt. The same problem does not occur on x86-64 and he also reported that converting sb->s_inode_wblist_lock to raw_spinlock_t makes the problem disappear indicating that the RT spinlock variant is the problem. Which in turn means that RT mutexes on ARM64 and any other weakly ordered architecture are affected by this independent of RT. Will Deacon observed: "I'd be more inclined to be suspicious of the slowpath tbh, as we need to make sure that we have acquire semantics on all paths where the lock can be taken. Looking at the rtmutex code, this really isn't obvious to me -- for example, try_to_take_rt_mutex() appears to be able to return via the 'takeit' label without acquire semantics and it looks like we might be relying on the caller's subsequent _unlock_ of the wait_lock for ordering, but that will give us release semantics which aren't correct." Sebastian Andrzej Siewior prototyped a fix that does work based on that comment but it was a little bit overkill and added some fences that should not be necessary. The lock owner is updated with an IRQ-safe raw spinlock held, but the spin_unlock does not provide acquire semantics which are needed when acquiring a mutex. Adds the necessary acquire semantics for lock owner updates in the slow path acquisition and the waiter bit logic. It successfully completed 10 iterations of the dbench workload while the vanilla kernel fails on the first iteration. [ bigeasy@linutronix.de: Initial prototype fix ] Fixes: 700318d1d7b38 ("locking/rtmutex: Use acquire/release semantics") Fixes: 23f78d4a03c5 ("[PATCH] pi-futex: rt mutex core") Reported-by: Jan Kara Signed-off-by: Mel Gorman Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221202100223.6mevpbl7i6x5udfd@techsingularity.net --- kernel/locking/rtmutex.c | 55 ++++++++++++++++++++++++++++++++++++-------- kernel/locking/rtmutex_api.c | 6 ++--- 2 files changed, 49 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 7779ee8abc2a..010cf4e6d0b8 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -89,15 +89,31 @@ static inline int __ww_mutex_check_kill(struct rt_mutex *lock, * set this bit before looking at the lock. */ -static __always_inline void -rt_mutex_set_owner(struct rt_mutex_base *lock, struct task_struct *owner) +static __always_inline struct task_struct * +rt_mutex_owner_encode(struct rt_mutex_base *lock, struct task_struct *owner) { unsigned long val = (unsigned long)owner; if (rt_mutex_has_waiters(lock)) val |= RT_MUTEX_HAS_WAITERS; - WRITE_ONCE(lock->owner, (struct task_struct *)val); + return (struct task_struct *)val; +} + +static __always_inline void +rt_mutex_set_owner(struct rt_mutex_base *lock, struct task_struct *owner) +{ + /* + * lock->wait_lock is held but explicit acquire semantics are needed + * for a new lock owner so WRITE_ONCE is insufficient. + */ + xchg_acquire(&lock->owner, rt_mutex_owner_encode(lock, owner)); +} + +static __always_inline void rt_mutex_clear_owner(struct rt_mutex_base *lock) +{ + /* lock->wait_lock is held so the unlock provides release semantics. */ + WRITE_ONCE(lock->owner, rt_mutex_owner_encode(lock, NULL)); } static __always_inline void clear_rt_mutex_waiters(struct rt_mutex_base *lock) @@ -106,7 +122,8 @@ static __always_inline void clear_rt_mutex_waiters(struct rt_mutex_base *lock) ((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS); } -static __always_inline void fixup_rt_mutex_waiters(struct rt_mutex_base *lock) +static __always_inline void +fixup_rt_mutex_waiters(struct rt_mutex_base *lock, bool acquire_lock) { unsigned long owner, *p = (unsigned long *) &lock->owner; @@ -172,8 +189,21 @@ static __always_inline void fixup_rt_mutex_waiters(struct rt_mutex_base *lock) * still set. */ owner = READ_ONCE(*p); - if (owner & RT_MUTEX_HAS_WAITERS) - WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS); + if (owner & RT_MUTEX_HAS_WAITERS) { + /* + * See rt_mutex_set_owner() and rt_mutex_clear_owner() on + * why xchg_acquire() is used for updating owner for + * locking and WRITE_ONCE() for unlocking. + * + * WRITE_ONCE() would work for the acquire case too, but + * in case that the lock acquisition failed it might + * force other lockers into the slow path unnecessarily. + */ + if (acquire_lock) + xchg_acquire(p, owner & ~RT_MUTEX_HAS_WAITERS); + else + WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS); + } } /* @@ -208,6 +238,13 @@ static __always_inline void mark_rt_mutex_waiters(struct rt_mutex_base *lock) owner = *p; } while (cmpxchg_relaxed(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner); + + /* + * The cmpxchg loop above is relaxed to avoid back-to-back ACQUIRE + * operations in the event of contention. Ensure the successful + * cmpxchg is visible. + */ + smp_mb__after_atomic(); } /* @@ -1243,7 +1280,7 @@ static int __sched __rt_mutex_slowtrylock(struct rt_mutex_base *lock) * try_to_take_rt_mutex() sets the lock waiters bit * unconditionally. Clean this up. */ - fixup_rt_mutex_waiters(lock); + fixup_rt_mutex_waiters(lock, true); return ret; } @@ -1604,7 +1641,7 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock, * try_to_take_rt_mutex() sets the waiter bit * unconditionally. We might have to fix that up. */ - fixup_rt_mutex_waiters(lock); + fixup_rt_mutex_waiters(lock, true); trace_contention_end(lock, ret); @@ -1719,7 +1756,7 @@ static void __sched rtlock_slowlock_locked(struct rt_mutex_base *lock) * try_to_take_rt_mutex() sets the waiter bit unconditionally. * We might have to fix that up: */ - fixup_rt_mutex_waiters(lock); + fixup_rt_mutex_waiters(lock, true); debug_rt_mutex_free_waiter(&waiter); trace_contention_end(lock, 0); diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c index 900220941caa..cb9fdff76a8a 100644 --- a/kernel/locking/rtmutex_api.c +++ b/kernel/locking/rtmutex_api.c @@ -267,7 +267,7 @@ void __sched rt_mutex_init_proxy_locked(struct rt_mutex_base *lock, void __sched rt_mutex_proxy_unlock(struct rt_mutex_base *lock) { debug_rt_mutex_proxy_unlock(lock); - rt_mutex_set_owner(lock, NULL); + rt_mutex_clear_owner(lock); } /** @@ -382,7 +382,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock, * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might * have to fix that up. */ - fixup_rt_mutex_waiters(lock); + fixup_rt_mutex_waiters(lock, true); raw_spin_unlock_irq(&lock->wait_lock); return ret; @@ -438,7 +438,7 @@ bool __sched rt_mutex_cleanup_proxy_lock(struct rt_mutex_base *lock, * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might * have to fix that up. */ - fixup_rt_mutex_waiters(lock); + fixup_rt_mutex_waiters(lock, false); raw_spin_unlock_irq(&lock->wait_lock); -- cgit v1.2.3 From 94cd8fa09f5f1ebdd4e90964b08b7f2cc4b36c43 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Wed, 14 Dec 2022 17:20:08 -0500 Subject: futex: Fix futex_waitv() hrtimer debug object leak on kcalloc error In a scenario where kcalloc() fails to allocate memory, the futex_waitv system call immediately returns -ENOMEM without invoking destroy_hrtimer_on_stack(). When CONFIG_DEBUG_OBJECTS_TIMERS=y, this results in leaking a timer debug object. Fixes: bf69bad38cf6 ("futex: Implement sys_futex_waitv()") Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Davidlohr Bueso Cc: stable@vger.kernel.org Cc: stable@vger.kernel.org # v5.16+ Link: https://lore.kernel.org/r/20221214222008.200393-1-mathieu.desnoyers@efficios.com --- kernel/futex/syscalls.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c index 086a22d1adb7..a8074079b09e 100644 --- a/kernel/futex/syscalls.c +++ b/kernel/futex/syscalls.c @@ -286,19 +286,22 @@ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, } futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL); - if (!futexv) - return -ENOMEM; + if (!futexv) { + ret = -ENOMEM; + goto destroy_timer; + } ret = futex_parse_waitv(futexv, waiters, nr_futexes); if (!ret) ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL); + kfree(futexv); + +destroy_timer: if (timeout) { hrtimer_cancel(&to.timer); destroy_hrtimer_on_stack(&to.timer); } - - kfree(futexv); return ret; } -- cgit v1.2.3