forked from Minki/linux
54cf809b95
Similar to commits:51d7d5205d
("powerpc: Add smp_mb() to arch_spin_is_locked()")d86b8da04d
("arm64: spinlock: serialise spin_unlock_wait against concurrent lockers") qspinlock suffers from the fact that the _Q_LOCKED_VAL store is unordered inside the ACQUIRE of the lock. And while this is not a problem for the regular mutual exclusive critical section usage of spinlocks, it breaks creative locking like: spin_lock(A) spin_lock(B) spin_unlock_wait(B) if (!spin_is_locked(A)) do_something() do_something() In that both CPUs can end up running do_something at the same time, because our _Q_LOCKED_VAL store can drop past the spin_unlock_wait() spin_is_locked() loads (even on x86!!). To avoid making the normal case slower, add smp_mb()s to the less used spin_unlock_wait() / spin_is_locked() side of things to avoid this problem. Reported-and-tested-by: Davidlohr Bueso <dave@stgolabs.net> Reported-by: Giovanni Gherdovich <ggherdovich@suse.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: stable@vger.kernel.org # v4.2 and later Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
161 lines
4.9 KiB
C
161 lines
4.9 KiB
C
/*
|
|
* Queued spinlock
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
|
|
* (C) Copyright 2015 Hewlett-Packard Enterprise Development LP
|
|
*
|
|
* Authors: Waiman Long <waiman.long@hpe.com>
|
|
*/
|
|
#ifndef __ASM_GENERIC_QSPINLOCK_H
|
|
#define __ASM_GENERIC_QSPINLOCK_H
|
|
|
|
#include <asm-generic/qspinlock_types.h>
|
|
|
|
/**
|
|
* queued_spin_is_locked - is the spinlock locked?
|
|
* @lock: Pointer to queued spinlock structure
|
|
* Return: 1 if it is locked, 0 otherwise
|
|
*/
|
|
static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
|
|
{
|
|
/*
|
|
* queued_spin_lock_slowpath() can ACQUIRE the lock before
|
|
* issuing the unordered store that sets _Q_LOCKED_VAL.
|
|
*
|
|
* See both smp_cond_acquire() sites for more detail.
|
|
*
|
|
* This however means that in code like:
|
|
*
|
|
* spin_lock(A) spin_lock(B)
|
|
* spin_unlock_wait(B) spin_is_locked(A)
|
|
* do_something() do_something()
|
|
*
|
|
* Both CPUs can end up running do_something() because the store
|
|
* setting _Q_LOCKED_VAL will pass through the loads in
|
|
* spin_unlock_wait() and/or spin_is_locked().
|
|
*
|
|
* Avoid this by issuing a full memory barrier between the spin_lock()
|
|
* and the loads in spin_unlock_wait() and spin_is_locked().
|
|
*
|
|
* Note that regular mutual exclusion doesn't care about this
|
|
* delayed store.
|
|
*/
|
|
smp_mb();
|
|
return atomic_read(&lock->val) & _Q_LOCKED_MASK;
|
|
}
|
|
|
|
/**
|
|
* queued_spin_value_unlocked - is the spinlock structure unlocked?
|
|
* @lock: queued spinlock structure
|
|
* Return: 1 if it is unlocked, 0 otherwise
|
|
*
|
|
* N.B. Whenever there are tasks waiting for the lock, it is considered
|
|
* locked wrt the lockref code to avoid lock stealing by the lockref
|
|
* code and change things underneath the lock. This also allows some
|
|
* optimizations to be applied without conflict with lockref.
|
|
*/
|
|
static __always_inline int queued_spin_value_unlocked(struct qspinlock lock)
|
|
{
|
|
return !atomic_read(&lock.val);
|
|
}
|
|
|
|
/**
|
|
* queued_spin_is_contended - check if the lock is contended
|
|
* @lock : Pointer to queued spinlock structure
|
|
* Return: 1 if lock contended, 0 otherwise
|
|
*/
|
|
static __always_inline int queued_spin_is_contended(struct qspinlock *lock)
|
|
{
|
|
return atomic_read(&lock->val) & ~_Q_LOCKED_MASK;
|
|
}
|
|
/**
|
|
* queued_spin_trylock - try to acquire the queued spinlock
|
|
* @lock : Pointer to queued spinlock structure
|
|
* Return: 1 if lock acquired, 0 if failed
|
|
*/
|
|
static __always_inline int queued_spin_trylock(struct qspinlock *lock)
|
|
{
|
|
if (!atomic_read(&lock->val) &&
|
|
(atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL) == 0))
|
|
return 1;
|
|
return 0;
|
|
}
|
|
|
|
extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
|
|
|
|
/**
|
|
* queued_spin_lock - acquire a queued spinlock
|
|
* @lock: Pointer to queued spinlock structure
|
|
*/
|
|
static __always_inline void queued_spin_lock(struct qspinlock *lock)
|
|
{
|
|
u32 val;
|
|
|
|
val = atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL);
|
|
if (likely(val == 0))
|
|
return;
|
|
queued_spin_lock_slowpath(lock, val);
|
|
}
|
|
|
|
#ifndef queued_spin_unlock
|
|
/**
|
|
* queued_spin_unlock - release a queued spinlock
|
|
* @lock : Pointer to queued spinlock structure
|
|
*/
|
|
static __always_inline void queued_spin_unlock(struct qspinlock *lock)
|
|
{
|
|
/*
|
|
* smp_mb__before_atomic() in order to guarantee release semantics
|
|
*/
|
|
smp_mb__before_atomic();
|
|
atomic_sub(_Q_LOCKED_VAL, &lock->val);
|
|
}
|
|
#endif
|
|
|
|
/**
|
|
* queued_spin_unlock_wait - wait until current lock holder releases the lock
|
|
* @lock : Pointer to queued spinlock structure
|
|
*
|
|
* There is a very slight possibility of live-lock if the lockers keep coming
|
|
* and the waiter is just unfortunate enough to not see any unlock state.
|
|
*/
|
|
static inline void queued_spin_unlock_wait(struct qspinlock *lock)
|
|
{
|
|
/* See queued_spin_is_locked() */
|
|
smp_mb();
|
|
while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
|
|
cpu_relax();
|
|
}
|
|
|
|
#ifndef virt_spin_lock
|
|
static __always_inline bool virt_spin_lock(struct qspinlock *lock)
|
|
{
|
|
return false;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Remapping spinlock architecture specific functions to the corresponding
|
|
* queued spinlock functions.
|
|
*/
|
|
#define arch_spin_is_locked(l) queued_spin_is_locked(l)
|
|
#define arch_spin_is_contended(l) queued_spin_is_contended(l)
|
|
#define arch_spin_value_unlocked(l) queued_spin_value_unlocked(l)
|
|
#define arch_spin_lock(l) queued_spin_lock(l)
|
|
#define arch_spin_trylock(l) queued_spin_trylock(l)
|
|
#define arch_spin_unlock(l) queued_spin_unlock(l)
|
|
#define arch_spin_lock_flags(l, f) queued_spin_lock(l)
|
|
#define arch_spin_unlock_wait(l) queued_spin_unlock_wait(l)
|
|
|
|
#endif /* __ASM_GENERIC_QSPINLOCK_H */
|