From 6e1e5196975fb7ecc501b3fe1075b77aea2b7839 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Mon, 14 Sep 2015 00:37:22 -0700 Subject: locking/qrwlock: Rename ->lock to ->wait_lock ... trivial, but reads a little nicer when we name our actual primitive 'lock'. Signed-off-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman Long Link: http://lkml.kernel.org/r/1442216244-4409-1-git-send-email-dave@stgolabs.net Signed-off-by: Ingo Molnar --- kernel/locking/qrwlock.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c index f17a3e3b3550..fec082338668 100644 --- a/kernel/locking/qrwlock.c +++ b/kernel/locking/qrwlock.c @@ -86,7 +86,7 @@ void queued_read_lock_slowpath(struct qrwlock *lock, u32 cnts) /* * Put the reader into the wait queue */ - arch_spin_lock(&lock->lock); + arch_spin_lock(&lock->wait_lock); /* * The ACQUIRE semantics of the following spinning code ensure @@ -99,7 +99,7 @@ void queued_read_lock_slowpath(struct qrwlock *lock, u32 cnts) /* * Signal the next one in queue to become queue head */ - arch_spin_unlock(&lock->lock); + arch_spin_unlock(&lock->wait_lock); } EXPORT_SYMBOL(queued_read_lock_slowpath); @@ -112,7 +112,7 @@ void queued_write_lock_slowpath(struct qrwlock *lock) u32 cnts; /* Put the writer into the wait queue */ - arch_spin_lock(&lock->lock); + arch_spin_lock(&lock->wait_lock); /* Try to acquire the lock directly if no reader is present */ if (!atomic_read(&lock->cnts) && @@ -144,6 +144,6 @@ void queued_write_lock_slowpath(struct qrwlock *lock) cpu_relax_lowlatency(); } unlock: - arch_spin_unlock(&lock->lock); + arch_spin_unlock(&lock->wait_lock); } EXPORT_SYMBOL(queued_write_lock_slowpath); -- cgit v1.2.3 From c55a6ffa6285e29f874ed403979472631ec70bff Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Mon, 14 Sep 2015 00:37:24 -0700 Subject: locking/osq: Relax atomic semantics ... by using acquire/release for ops around the lock->tail. As such, weakly ordered archs can benefit from more relaxed use of barriers when issuing atomics. Signed-off-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman Long Link: http://lkml.kernel.org/r/1442216244-4409-3-git-send-email-dave@stgolabs.net Signed-off-by: Ingo Molnar --- kernel/locking/osq_lock.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index dc85ee23a26f..d092a0c9c2d4 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -50,7 +50,7 @@ osq_wait_next(struct optimistic_spin_queue *lock, for (;;) { if (atomic_read(&lock->tail) == curr && - atomic_cmpxchg(&lock->tail, curr, old) == curr) { + atomic_cmpxchg_acquire(&lock->tail, curr, old) == curr) { /* * We were the last queued, we moved @lock back. @prev * will now observe @lock and will complete its @@ -92,7 +92,11 @@ bool osq_lock(struct optimistic_spin_queue *lock) node->next = NULL; node->cpu = curr; - old = atomic_xchg(&lock->tail, curr); + /* + * ACQUIRE semantics, pairs with corresponding RELEASE + * in unlock() uncontended, or fastpath. + */ + old = atomic_xchg_acquire(&lock->tail, curr); if (old == OSQ_UNLOCKED_VAL) return true; @@ -184,7 +188,8 @@ void osq_unlock(struct optimistic_spin_queue *lock) /* * Fast path for the uncontended case. */ - if (likely(atomic_cmpxchg(&lock->tail, curr, OSQ_UNLOCKED_VAL) == curr)) + if (likely(atomic_cmpxchg_release(&lock->tail, curr, + OSQ_UNLOCKED_VAL) == curr)) return; /* -- cgit v1.2.3 From 93edc8bd7750ff3cae088bfca453ea73dc9004a4 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 11 Sep 2015 14:37:34 -0400 Subject: locking/pvqspinlock: Kick the PV CPU unconditionally when _Q_SLOW_VAL If _Q_SLOW_VAL has been set, the vCPU state must have been vcpu_hashed. The extra check at the end of __pv_queued_spin_unlock() is unnecessary and can be removed. Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Davidlohr Bueso Cc: Andrew Morton Cc: Douglas Hatch Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Scott J Norton Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1441996658-62854-3-git-send-email-Waiman.Long@hpe.com Signed-off-by: Ingo Molnar --- kernel/locking/qspinlock_paravirt.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index c8e6e9a596f5..f0450ff4829b 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -267,7 +267,6 @@ static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node) } if (!lp) { /* ONCE */ - WRITE_ONCE(pn->state, vcpu_hashed); lp = pv_hash(lock, pn); /* @@ -275,11 +274,9 @@ static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node) * when we observe _Q_SLOW_VAL in __pv_queued_spin_unlock() * we'll be sure to be able to observe our hash entry. * - * [S] pn->state * [S] [Rmw] l->locked == _Q_SLOW_VAL * MB RMB * [RmW] l->locked = _Q_SLOW_VAL [L] - * [L] pn->state * * Matches the smp_rmb() in __pv_queued_spin_unlock(). */ @@ -364,8 +361,7 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock) * vCPU is harmless other than the additional latency in completing * the unlock. */ - if (READ_ONCE(node->state) == vcpu_hashed) - pv_kick(node->cpu); + pv_kick(node->cpu); } /* * Include the architecture specific callee-save thunk of the -- cgit v1.2.3 From 21199f27b430576552b26210b3194a363d7f05cd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Sep 2015 16:10:40 +0200 Subject: locking/lockdep: Fix hlock->pin_count reset on lock stack rebuilds Various people reported hitting the "unpinning an unpinned lock" warning. As it turns out there are 2 places where we take a lock out of the middle of a stack, and in those cases it would fail to preserve the pin_count when rebuilding the lock stack. Reported-by: Sasha Levin Reported-by: Tim Spriggs Tested-by: Sasha Levin Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: davej@codemonkey.org.uk Link: http://lkml.kernel.org/r/20150916141040.GA11639@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/locking/lockdep.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 8acfbf773e06..4e49cc4c9952 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3068,7 +3068,7 @@ static int __lock_is_held(struct lockdep_map *lock); static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, int trylock, int read, int check, int hardirqs_off, struct lockdep_map *nest_lock, unsigned long ip, - int references) + int references, int pin_count) { struct task_struct *curr = current; struct lock_class *class = NULL; @@ -3157,7 +3157,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, hlock->waittime_stamp = 0; hlock->holdtime_stamp = lockstat_clock(); #endif - hlock->pin_count = 0; + hlock->pin_count = pin_count; if (check && !mark_irqflags(curr, hlock)) return 0; @@ -3343,7 +3343,7 @@ found_it: hlock_class(hlock)->subclass, hlock->trylock, hlock->read, hlock->check, hlock->hardirqs_off, hlock->nest_lock, hlock->acquire_ip, - hlock->references)) + hlock->references, hlock->pin_count)) return 0; } @@ -3433,7 +3433,7 @@ found_it: hlock_class(hlock)->subclass, hlock->trylock, hlock->read, hlock->check, hlock->hardirqs_off, hlock->nest_lock, hlock->acquire_ip, - hlock->references)) + hlock->references, hlock->pin_count)) return 0; } @@ -3583,7 +3583,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, current->lockdep_recursion = 1; trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip); __lock_acquire(lock, subclass, trylock, read, check, - irqs_disabled_flags(flags), nest_lock, ip, 0); + irqs_disabled_flags(flags), nest_lock, ip, 0, 0); current->lockdep_recursion = 0; raw_local_irq_restore(flags); } -- cgit v1.2.3 From f52405757e4e9bddd868d6b8ca501d58f292969f Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Wed, 2 Sep 2015 11:01:35 +0100 Subject: sched/deadline, locking/rtmutex: Fix open coded check in rt_mutex_waiter_less() rt_mutex_waiter_less() check of task deadlines is open coded. Since this is subject to wraparound bugs, make it use the correct helper. Reported-by: Luca Abeni Signed-off-by: Juri Lelli Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1441188096-23021-4-git-send-email-juri.lelli@arm.com Signed-off-by: Ingo Molnar --- kernel/locking/rtmutex.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/locking') diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 7781d801212f..35e9bfcc6ad9 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -158,7 +158,8 @@ rt_mutex_waiter_less(struct rt_mutex_waiter *left, * then right waiter has a dl_prio() too. */ if (dl_prio(left->prio)) - return (left->task->dl.deadline < right->task->dl.deadline); + return dl_time_before(left->task->dl.deadline, + right->task->dl.deadline); return 0; } -- cgit v1.2.3 From 81a43adae3b943193fb3afd20a36a7482332f964 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 30 Sep 2015 13:03:12 -0700 Subject: locking/mutex: Use acquire/release semantics As of 654672d4ba1 (locking/atomics: Add _{acquire|release|relaxed}() variants of some atomic operations) and 6d79ef2d30e (locking, asm-generic: Add _{relaxed|acquire|release}() variants for 'atomic_long_t'), weakly ordered archs can benefit from more relaxed use of barriers when locking and unlocking, instead of regular full barrier semantics. While currently only arm64 supports such optimizations, updating corresponding locking primitives serves for other archs to immediately benefit as well, once the necessary machinery is implemented of course. Signed-off-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Paul E.McKenney Cc: Peter Zijlstra Cc: Will Deacon Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/1443643395-17016-3-git-send-email-dave@stgolabs.net Signed-off-by: Ingo Molnar --- include/asm-generic/mutex-dec.h | 8 ++++---- include/asm-generic/mutex-xchg.h | 10 +++++----- kernel/locking/mutex.c | 9 +++++---- 3 files changed, 14 insertions(+), 13 deletions(-) (limited to 'kernel/locking') diff --git a/include/asm-generic/mutex-dec.h b/include/asm-generic/mutex-dec.h index d4f9fb4e53df..fd694cfd678a 100644 --- a/include/asm-generic/mutex-dec.h +++ b/include/asm-generic/mutex-dec.h @@ -20,7 +20,7 @@ static inline void __mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) { - if (unlikely(atomic_dec_return(count) < 0)) + if (unlikely(atomic_dec_return_acquire(count) < 0)) fail_fn(count); } @@ -35,7 +35,7 @@ __mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) static inline int __mutex_fastpath_lock_retval(atomic_t *count) { - if (unlikely(atomic_dec_return(count) < 0)) + if (unlikely(atomic_dec_return_acquire(count) < 0)) return -1; return 0; } @@ -56,7 +56,7 @@ __mutex_fastpath_lock_retval(atomic_t *count) static inline void __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) { - if (unlikely(atomic_inc_return(count) <= 0)) + if (unlikely(atomic_inc_return_release(count) <= 0)) fail_fn(count); } @@ -80,7 +80,7 @@ __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) static inline int __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) { - if (likely(atomic_cmpxchg(count, 1, 0) == 1)) + if (likely(atomic_cmpxchg_acquire(count, 1, 0) == 1)) return 1; return 0; } diff --git a/include/asm-generic/mutex-xchg.h b/include/asm-generic/mutex-xchg.h index f169ec064785..a6b4a7bd6ac9 100644 --- a/include/asm-generic/mutex-xchg.h +++ b/include/asm-generic/mutex-xchg.h @@ -31,7 +31,7 @@ __mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) * to ensure that any waiting tasks are woken up by the * unlock slow path. */ - if (likely(atomic_xchg(count, -1) != 1)) + if (likely(atomic_xchg_acquire(count, -1) != 1)) fail_fn(count); } @@ -46,7 +46,7 @@ __mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) static inline int __mutex_fastpath_lock_retval(atomic_t *count) { - if (unlikely(atomic_xchg(count, 0) != 1)) + if (unlikely(atomic_xchg_acquire(count, 0) != 1)) if (likely(atomic_xchg(count, -1) != 1)) return -1; return 0; @@ -67,7 +67,7 @@ __mutex_fastpath_lock_retval(atomic_t *count) static inline void __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) { - if (unlikely(atomic_xchg(count, 1) != 0)) + if (unlikely(atomic_xchg_release(count, 1) != 0)) fail_fn(count); } @@ -91,7 +91,7 @@ __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) static inline int __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) { - int prev = atomic_xchg(count, 0); + int prev = atomic_xchg_acquire(count, 0); if (unlikely(prev < 0)) { /* @@ -105,7 +105,7 @@ __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) * owner's unlock path needlessly, but that's not a problem * in practice. ] */ - prev = atomic_xchg(count, prev); + prev = atomic_xchg_acquire(count, prev); if (prev < 0) prev = 0; } diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 4cccea6b8934..0551c219c40e 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -277,7 +277,7 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock) static inline bool mutex_try_to_acquire(struct mutex *lock) { return !mutex_is_locked(lock) && - (atomic_cmpxchg(&lock->count, 1, 0) == 1); + (atomic_cmpxchg_acquire(&lock->count, 1, 0) == 1); } /* @@ -529,7 +529,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * Once more, try to acquire the lock. Only try-lock the mutex if * it is unlocked to reduce unnecessary xchg() operations. */ - if (!mutex_is_locked(lock) && (atomic_xchg(&lock->count, 0) == 1)) + if (!mutex_is_locked(lock) && + (atomic_xchg_acquire(&lock->count, 0) == 1)) goto skip_wait; debug_mutex_lock_common(lock, &waiter); @@ -553,7 +554,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * non-negative in order to avoid unnecessary xchg operations: */ if (atomic_read(&lock->count) >= 0 && - (atomic_xchg(&lock->count, -1) == 1)) + (atomic_xchg_acquire(&lock->count, -1) == 1)) break; /* @@ -867,7 +868,7 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count) spin_lock_mutex(&lock->wait_lock, flags); - prev = atomic_xchg(&lock->count, -1); + prev = atomic_xchg_acquire(&lock->count, -1); if (likely(prev == 1)) { mutex_set_owner(lock); mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); -- cgit v1.2.3 From 700318d1d7b38bbfe86813d9c5c18364dd941526 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 30 Sep 2015 13:03:13 -0700 Subject: locking/rtmutex: Use acquire/release semantics As of 654672d4ba1 (locking/atomics: Add _{acquire|release|relaxed}() variants of some atomic operations) and 6d79ef2d30e (locking, asm-generic: Add _{relaxed|acquire|release}() variants for 'atomic_long_t'), weakly ordered archs can benefit from more relaxed use of barriers when locking and unlocking, instead of regular full barrier semantics. While currently only arm64 supports such optimizations, updating corresponding locking primitives serves for other archs to immediately benefit as well, once the necessary machinery is implemented of course. Signed-off-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Paul E.McKenney Cc: Peter Zijlstra Cc: Will Deacon Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/1443643395-17016-4-git-send-email-dave@stgolabs.net Signed-off-by: Ingo Molnar --- kernel/locking/rtmutex.c | 30 +++++++++++++++++++++--------- 1 file changed, 21 insertions(+), 9 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 7781d801212f..bbb72b4f64a1 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -74,14 +74,23 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock) * set up. */ #ifndef CONFIG_DEBUG_RT_MUTEXES -# define rt_mutex_cmpxchg(l,c,n) (cmpxchg(&l->owner, c, n) == c) +# define rt_mutex_cmpxchg_relaxed(l,c,n) (cmpxchg_relaxed(&l->owner, c, n) == c) +# define rt_mutex_cmpxchg_acquire(l,c,n) (cmpxchg_acquire(&l->owner, c, n) == c) +# define rt_mutex_cmpxchg_release(l,c,n) (cmpxchg_release(&l->owner, c, n) == c) + +/* + * Callers must hold the ->wait_lock -- which is the whole purpose as we force + * all future threads that attempt to [Rmw] the lock to the slowpath. As such + * relaxed semantics suffice. + */ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) { unsigned long owner, *p = (unsigned long *) &lock->owner; do { owner = *p; - } while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner); + } while (cmpxchg_relaxed(p, owner, + owner | RT_MUTEX_HAS_WAITERS) != owner); } /* @@ -121,11 +130,14 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) * lock(wait_lock); * acquire(lock); */ - return rt_mutex_cmpxchg(lock, owner, NULL); + return rt_mutex_cmpxchg_release(lock, owner, NULL); } #else -# define rt_mutex_cmpxchg(l,c,n) (0) +# define rt_mutex_cmpxchg_relaxed(l,c,n) (0) +# define rt_mutex_cmpxchg_acquire(l,c,n) (0) +# define rt_mutex_cmpxchg_release(l,c,n) (0) + static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) { lock->owner = (struct task_struct *) @@ -1321,7 +1333,7 @@ rt_mutex_fastlock(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, enum rtmutex_chainwalk chwalk)) { - if (likely(rt_mutex_cmpxchg(lock, NULL, current))) { + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { rt_mutex_deadlock_account_lock(lock, current); return 0; } else @@ -1337,7 +1349,7 @@ rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, enum rtmutex_chainwalk chwalk)) { if (chwalk == RT_MUTEX_MIN_CHAINWALK && - likely(rt_mutex_cmpxchg(lock, NULL, current))) { + likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { rt_mutex_deadlock_account_lock(lock, current); return 0; } else @@ -1348,7 +1360,7 @@ static inline int rt_mutex_fasttrylock(struct rt_mutex *lock, int (*slowfn)(struct rt_mutex *lock)) { - if (likely(rt_mutex_cmpxchg(lock, NULL, current))) { + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { rt_mutex_deadlock_account_lock(lock, current); return 1; } @@ -1362,7 +1374,7 @@ rt_mutex_fastunlock(struct rt_mutex *lock, { WAKE_Q(wake_q); - if (likely(rt_mutex_cmpxchg(lock, current, NULL))) { + if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) { rt_mutex_deadlock_account_unlock(current); } else { @@ -1484,7 +1496,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_unlock); bool __sched rt_mutex_futex_unlock(struct rt_mutex *lock, struct wake_q_head *wqh) { - if (likely(rt_mutex_cmpxchg(lock, current, NULL))) { + if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) { rt_mutex_deadlock_account_unlock(current); return false; } -- cgit v1.2.3 From 3552a07a9c4aea32cc092fadf10a186c84ed8a61 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 30 Sep 2015 13:03:14 -0700 Subject: locking/mcs: Use acquire/release semantics As of 654672d4ba1 (locking/atomics: Add _{acquire|release|relaxed}() variants of some atomic operations) and 6d79ef2d30e (locking, asm-generic: Add _{relaxed|acquire|release}() variants for 'atomic_long_t'), weakly ordered archs can benefit from more relaxed use of barriers when locking and unlocking, instead of regular full barrier semantics. While currently only arm64 supports such optimizations, updating corresponding locking primitives serves for other archs to immediately benefit as well, once the necessary machinery is implemented of course. Signed-off-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Paul E.McKenney Cc: Peter Zijlstra Cc: Will Deacon Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/1443643395-17016-5-git-send-email-dave@stgolabs.net Signed-off-by: Ingo Molnar --- kernel/locking/mcs_spinlock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index fd91aaa4554c..5b9102a47ea5 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -67,7 +67,7 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) node->locked = 0; node->next = NULL; - prev = xchg(lock, node); + prev = xchg_acquire(lock, node); if (likely(prev == NULL)) { /* * Lock acquired, don't need to set node->locked to 1. Threads @@ -98,7 +98,7 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node) /* * Release the lock by setting it to NULL */ - if (likely(cmpxchg(lock, node, NULL) == node)) + if (likely(cmpxchg_release(lock, node, NULL) == node)) return; /* Wait until the next pointer is set */ while (!(next = READ_ONCE(node->next))) -- cgit v1.2.3 From 00eb4bab69db349c3bdc7e0b0f7e9070dafea58c Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 30 Sep 2015 13:03:15 -0700 Subject: locking/rwsem: Use acquire/release semantics As of 654672d4ba1 (locking/atomics: Add _{acquire|release|relaxed}() variants of some atomic operations) and 6d79ef2d30e (locking, asm-generic: Add _{relaxed|acquire|release}() variants for 'atomic_long_t'), weakly ordered archs can benefit from more relaxed use of barriers when locking and unlocking, instead of regular full barrier semantics. While currently only arm64 supports such optimizations, updating corresponding locking primitives serves for other archs to immediately benefit as well, once the necessary machinery is implemented of course. Signed-off-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Paul E.McKenney Cc: Peter Zijlstra Cc: Will Deacon Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/1443643395-17016-6-git-send-email-dave@stgolabs.net Signed-off-by: Ingo Molnar --- include/asm-generic/rwsem.h | 21 ++++++++++++++------- kernel/locking/rwsem-xadd.c | 5 +++-- 2 files changed, 17 insertions(+), 9 deletions(-) (limited to 'kernel/locking') diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h index d48bf5a95cc1..d6d5dc98d7da 100644 --- a/include/asm-generic/rwsem.h +++ b/include/asm-generic/rwsem.h @@ -33,7 +33,7 @@ */ static inline void __down_read(struct rw_semaphore *sem) { - if (unlikely(atomic_long_inc_return((atomic_long_t *)&sem->count) <= 0)) + if (unlikely(atomic_long_inc_return_acquire((atomic_long_t *)&sem->count) <= 0)) rwsem_down_read_failed(sem); } @@ -42,7 +42,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) long tmp; while ((tmp = sem->count) >= 0) { - if (tmp == cmpxchg(&sem->count, tmp, + if (tmp == cmpxchg_acquire(&sem->count, tmp, tmp + RWSEM_ACTIVE_READ_BIAS)) { return 1; } @@ -57,7 +57,7 @@ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) { long tmp; - tmp = atomic_long_add_return(RWSEM_ACTIVE_WRITE_BIAS, + tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS, (atomic_long_t *)&sem->count); if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS)) rwsem_down_write_failed(sem); @@ -72,7 +72,7 @@ static inline int __down_write_trylock(struct rw_semaphore *sem) { long tmp; - tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE, + tmp = cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE, RWSEM_ACTIVE_WRITE_BIAS); return tmp == RWSEM_UNLOCKED_VALUE; } @@ -84,7 +84,7 @@ static inline void __up_read(struct rw_semaphore *sem) { long tmp; - tmp = atomic_long_dec_return((atomic_long_t *)&sem->count); + tmp = atomic_long_dec_return_release((atomic_long_t *)&sem->count); if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0)) rwsem_wake(sem); } @@ -94,7 +94,7 @@ static inline void __up_read(struct rw_semaphore *sem) */ static inline void __up_write(struct rw_semaphore *sem) { - if (unlikely(atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS, + if (unlikely(atomic_long_sub_return_release(RWSEM_ACTIVE_WRITE_BIAS, (atomic_long_t *)&sem->count) < 0)) rwsem_wake(sem); } @@ -114,7 +114,14 @@ static inline void __downgrade_write(struct rw_semaphore *sem) { long tmp; - tmp = atomic_long_add_return(-RWSEM_WAITING_BIAS, + /* + * When downgrading from exclusive to shared ownership, + * anything inside the write-locked region cannot leak + * into the read side. In contrast, anything in the + * read-locked region is ok to be re-ordered into the + * write side. As such, rely on RELEASE semantics. + */ + tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, (atomic_long_t *)&sem->count); if (tmp < 0) rwsem_downgrade_wake(sem); diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 0f189714e457..a4d4de05b2d1 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -262,7 +262,7 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) * to reduce unnecessary expensive cmpxchg() operations. */ if (count == RWSEM_WAITING_BIAS && - cmpxchg(&sem->count, RWSEM_WAITING_BIAS, + cmpxchg_acquire(&sem->count, RWSEM_WAITING_BIAS, RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) { if (!list_is_singular(&sem->wait_list)) rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); @@ -285,7 +285,8 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem) if (!(count == 0 || count == RWSEM_WAITING_BIAS)) return false; - old = cmpxchg(&sem->count, count, count + RWSEM_ACTIVE_WRITE_BIAS); + old = cmpxchg_acquire(&sem->count, count, + count + RWSEM_ACTIVE_WRITE_BIAS); if (old == count) { rwsem_set_owner(sem); return true; -- cgit v1.2.3 From 095777c417db142970adeb776fa0cb10810b8122 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 22 Jul 2015 14:07:27 -0700 Subject: locktorture: Support rtmutex torturing Real time mutexes is one of the few general primitives that we do not have in locktorture. Address this -- a few considerations: o To spice things up, enable competing thread(s) to become rt, such that we can stress different prio boosting paths in the rtmutex code. Introduce a ->task_boost callback, only used by rtmutex-torturer. Tasks will boost/deboost around every 50k (arbitrarily) lock/unlock operations. o Hold times are similar to what we have for other locks: only occasionally having longer hold times (per ~200k ops). So we roughly do two full rt boost+deboosting ops with short hold times. Signed-off-by: Davidlohr Bueso Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- Documentation/locking/locktorture.txt | 3 + kernel/locking/locktorture.c | 114 ++++++++++++++++++++- .../selftests/rcutorture/configs/lock/CFLIST | 3 +- .../selftests/rcutorture/configs/lock/LOCK05 | 6 ++ .../selftests/rcutorture/configs/lock/LOCK05.boot | 1 + 5 files changed, 124 insertions(+), 3 deletions(-) create mode 100644 tools/testing/selftests/rcutorture/configs/lock/LOCK05 create mode 100644 tools/testing/selftests/rcutorture/configs/lock/LOCK05.boot (limited to 'kernel/locking') diff --git a/Documentation/locking/locktorture.txt b/Documentation/locking/locktorture.txt index 619f2bb136a5..a2ef3a929bf1 100644 --- a/Documentation/locking/locktorture.txt +++ b/Documentation/locking/locktorture.txt @@ -52,6 +52,9 @@ torture_type Type of lock to torture. By default, only spinlocks will o "mutex_lock": mutex_lock() and mutex_unlock() pairs. + o "rtmutex_lock": rtmutex_lock() and rtmutex_unlock() + pairs. Kernel must have CONFIG_RT_MUTEX=y. + o "rwsem_lock": read/write down() and up() semaphore pairs. torture_runnable Start locktorture at boot time in the case where the diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 32244186f1f2..e1ca7a2fae91 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -17,12 +17,14 @@ * * Copyright (C) IBM Corporation, 2014 * - * Author: Paul E. McKenney + * Authors: Paul E. McKenney + * Davidlohr Bueso * Based on kernel/rcu/torture.c. */ #include #include #include +#include #include #include #include @@ -91,11 +93,13 @@ struct lock_torture_ops { void (*init)(void); int (*writelock)(void); void (*write_delay)(struct torture_random_state *trsp); + void (*task_boost)(struct torture_random_state *trsp); void (*writeunlock)(void); int (*readlock)(void); void (*read_delay)(struct torture_random_state *trsp); void (*readunlock)(void); - unsigned long flags; + + unsigned long flags; /* for irq spinlocks */ const char *name; }; @@ -139,9 +143,15 @@ static void torture_lock_busted_write_unlock(void) /* BUGGY, do not use in real life!!! */ } +static void torture_boost_dummy(struct torture_random_state *trsp) +{ + /* Only rtmutexes care about priority */ +} + static struct lock_torture_ops lock_busted_ops = { .writelock = torture_lock_busted_write_lock, .write_delay = torture_lock_busted_write_delay, + .task_boost = torture_boost_dummy, .writeunlock = torture_lock_busted_write_unlock, .readlock = NULL, .read_delay = NULL, @@ -185,6 +195,7 @@ static void torture_spin_lock_write_unlock(void) __releases(torture_spinlock) static struct lock_torture_ops spin_lock_ops = { .writelock = torture_spin_lock_write_lock, .write_delay = torture_spin_lock_write_delay, + .task_boost = torture_boost_dummy, .writeunlock = torture_spin_lock_write_unlock, .readlock = NULL, .read_delay = NULL, @@ -211,6 +222,7 @@ __releases(torture_spinlock) static struct lock_torture_ops spin_lock_irq_ops = { .writelock = torture_spin_lock_write_lock_irq, .write_delay = torture_spin_lock_write_delay, + .task_boost = torture_boost_dummy, .writeunlock = torture_lock_spin_write_unlock_irq, .readlock = NULL, .read_delay = NULL, @@ -275,6 +287,7 @@ static void torture_rwlock_read_unlock(void) __releases(torture_rwlock) static struct lock_torture_ops rw_lock_ops = { .writelock = torture_rwlock_write_lock, .write_delay = torture_rwlock_write_delay, + .task_boost = torture_boost_dummy, .writeunlock = torture_rwlock_write_unlock, .readlock = torture_rwlock_read_lock, .read_delay = torture_rwlock_read_delay, @@ -315,6 +328,7 @@ __releases(torture_rwlock) static struct lock_torture_ops rw_lock_irq_ops = { .writelock = torture_rwlock_write_lock_irq, .write_delay = torture_rwlock_write_delay, + .task_boost = torture_boost_dummy, .writeunlock = torture_rwlock_write_unlock_irq, .readlock = torture_rwlock_read_lock_irq, .read_delay = torture_rwlock_read_delay, @@ -354,6 +368,7 @@ static void torture_mutex_unlock(void) __releases(torture_mutex) static struct lock_torture_ops mutex_lock_ops = { .writelock = torture_mutex_lock, .write_delay = torture_mutex_delay, + .task_boost = torture_boost_dummy, .writeunlock = torture_mutex_unlock, .readlock = NULL, .read_delay = NULL, @@ -361,6 +376,90 @@ static struct lock_torture_ops mutex_lock_ops = { .name = "mutex_lock" }; +#ifdef CONFIG_RT_MUTEXES +static DEFINE_RT_MUTEX(torture_rtmutex); + +static int torture_rtmutex_lock(void) __acquires(torture_rtmutex) +{ + rt_mutex_lock(&torture_rtmutex); + return 0; +} + +static void torture_rtmutex_boost(struct torture_random_state *trsp) +{ + int policy; + struct sched_param param; + const unsigned int factor = 50000; /* yes, quite arbitrary */ + + if (!rt_task(current)) { + /* + * (1) Boost priority once every ~50k operations. When the + * task tries to take the lock, the rtmutex it will account + * for the new priority, and do any corresponding pi-dance. + */ + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * factor))) { + policy = SCHED_FIFO; + param.sched_priority = MAX_RT_PRIO - 1; + } else /* common case, do nothing */ + return; + } else { + /* + * The task will remain boosted for another ~500k operations, + * then restored back to its original prio, and so forth. + * + * When @trsp is nil, we want to force-reset the task for + * stopping the kthread. + */ + if (!trsp || !(torture_random(trsp) % + (cxt.nrealwriters_stress * factor * 2))) { + policy = SCHED_NORMAL; + param.sched_priority = 0; + } else /* common case, do nothing */ + return; + } + + sched_setscheduler_nocheck(current, policy, ¶m); +} + +static void torture_rtmutex_delay(struct torture_random_state *trsp) +{ + const unsigned long shortdelay_us = 2; + const unsigned long longdelay_ms = 100; + + /* + * We want a short delay mostly to emulate likely code, and + * we want a long delay occasionally to force massive contention. + */ + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * 2000 * longdelay_ms))) + mdelay(longdelay_ms); + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * 2 * shortdelay_us))) + udelay(shortdelay_us); +#ifdef CONFIG_PREEMPT + if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000))) + preempt_schedule(); /* Allow test to be preempted. */ +#endif +} + +static void torture_rtmutex_unlock(void) __releases(torture_rtmutex) +{ + rt_mutex_unlock(&torture_rtmutex); +} + +static struct lock_torture_ops rtmutex_lock_ops = { + .writelock = torture_rtmutex_lock, + .write_delay = torture_rtmutex_delay, + .task_boost = torture_rtmutex_boost, + .writeunlock = torture_rtmutex_unlock, + .readlock = NULL, + .read_delay = NULL, + .readunlock = NULL, + .name = "rtmutex_lock" +}; +#endif + static DECLARE_RWSEM(torture_rwsem); static int torture_rwsem_down_write(void) __acquires(torture_rwsem) { @@ -419,6 +518,7 @@ static void torture_rwsem_up_read(void) __releases(torture_rwsem) static struct lock_torture_ops rwsem_lock_ops = { .writelock = torture_rwsem_down_write, .write_delay = torture_rwsem_write_delay, + .task_boost = torture_boost_dummy, .writeunlock = torture_rwsem_up_write, .readlock = torture_rwsem_down_read, .read_delay = torture_rwsem_read_delay, @@ -442,6 +542,7 @@ static int lock_torture_writer(void *arg) if ((torture_random(&rand) & 0xfffff) == 0) schedule_timeout_uninterruptible(1); + cxt.cur_ops->task_boost(&rand); cxt.cur_ops->writelock(); if (WARN_ON_ONCE(lock_is_write_held)) lwsp->n_lock_fail++; @@ -456,6 +557,8 @@ static int lock_torture_writer(void *arg) stutter_wait("lock_torture_writer"); } while (!torture_must_stop()); + + cxt.cur_ops->task_boost(NULL); /* reset prio */ torture_kthread_stopping("lock_torture_writer"); return 0; } @@ -642,6 +745,9 @@ static int __init lock_torture_init(void) &spin_lock_ops, &spin_lock_irq_ops, &rw_lock_ops, &rw_lock_irq_ops, &mutex_lock_ops, +#ifdef CONFIG_RT_MUTEXES + &rtmutex_lock_ops, +#endif &rwsem_lock_ops, }; @@ -676,6 +782,10 @@ static int __init lock_torture_init(void) if (strncmp(torture_type, "mutex", 5) == 0) cxt.debug_lock = true; #endif +#ifdef CONFIG_DEBUG_RT_MUTEXES + if (strncmp(torture_type, "rtmutex", 7) == 0) + cxt.debug_lock = true; +#endif #ifdef CONFIG_DEBUG_SPINLOCK if ((strncmp(torture_type, "spin", 4) == 0) || (strncmp(torture_type, "rw_lock", 7) == 0)) diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFLIST b/tools/testing/selftests/rcutorture/configs/lock/CFLIST index 6910b7370761..6ed32794eaa1 100644 --- a/tools/testing/selftests/rcutorture/configs/lock/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/lock/CFLIST @@ -1,4 +1,5 @@ LOCK01 LOCK02 LOCK03 -LOCK04 \ No newline at end of file +LOCK04 +LOCK05 diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK05 b/tools/testing/selftests/rcutorture/configs/lock/LOCK05 new file mode 100644 index 000000000000..1d1da1477fc3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK05 @@ -0,0 +1,6 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=4 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK05.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK05.boot new file mode 100644 index 000000000000..8ac37307c987 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK05.boot @@ -0,0 +1 @@ +locktorture.torture_type=rtmutex_lock -- cgit v1.2.3 From 302707fd7cd341a23dbc448a335d432ad0069c20 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 31 Aug 2015 20:21:59 -0700 Subject: locking/percpu-rwsem: Export symbols for locktorture This commit exports percpu_down_read(), percpu_down_write(), __percpu_init_rwsem(), percpu_up_read(), and percpu_up_write() to allow locktorture to test them when built as a module. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/locking/percpu-rwsem.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel/locking') diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index f32567254867..e2621fbbcbd1 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -22,6 +22,7 @@ int __percpu_init_rwsem(struct percpu_rw_semaphore *brw, init_waitqueue_head(&brw->write_waitq); return 0; } +EXPORT_SYMBOL_GPL(__percpu_init_rwsem); void percpu_free_rwsem(struct percpu_rw_semaphore *brw) { @@ -87,6 +88,7 @@ void percpu_down_read(struct percpu_rw_semaphore *brw) /* avoid up_read()->rwsem_release() */ __up_read(&brw->rw_sem); } +EXPORT_SYMBOL_GPL(percpu_down_read); int percpu_down_read_trylock(struct percpu_rw_semaphore *brw) { @@ -112,6 +114,7 @@ void percpu_up_read(struct percpu_rw_semaphore *brw) if (atomic_dec_and_test(&brw->slow_read_ctr)) wake_up_all(&brw->write_waitq); } +EXPORT_SYMBOL_GPL(percpu_up_read); static int clear_fast_ctr(struct percpu_rw_semaphore *brw) { @@ -163,6 +166,7 @@ void percpu_down_write(struct percpu_rw_semaphore *brw) /* wait for all readers to complete their percpu_up_read() */ wait_event(brw->write_waitq, !atomic_read(&brw->slow_read_ctr)); } +EXPORT_SYMBOL_GPL(percpu_down_write); void percpu_up_write(struct percpu_rw_semaphore *brw) { @@ -176,3 +180,4 @@ void percpu_up_write(struct percpu_rw_semaphore *brw) /* the last writer unblocks update_fast_ctr() */ atomic_dec(&brw->write_ctr); } +EXPORT_SYMBOL_GPL(percpu_up_write); -- cgit v1.2.3 From 617783dd99704331e22636388c932450e02ee636 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 29 Aug 2015 14:46:29 -0700 Subject: locktorture: Add torture tests for percpu_rwsem This commit adds percpu_rwsem tests based on the earlier rwsem tests. Signed-off-by: Paul E. McKenney Cc: Oleg Nesterov Cc: Davidlohr Bueso Reviewed-by: Josh Triplett --- kernel/locking/locktorture.c | 44 ++++++++++++++++++++++ .../selftests/rcutorture/configs/lock/CFLIST | 1 + .../selftests/rcutorture/configs/lock/LOCK06 | 6 +++ .../selftests/rcutorture/configs/lock/LOCK06.boot | 1 + 4 files changed, 52 insertions(+) create mode 100644 tools/testing/selftests/rcutorture/configs/lock/LOCK06 create mode 100644 tools/testing/selftests/rcutorture/configs/lock/LOCK06.boot (limited to 'kernel/locking') diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index e1ca7a2fae91..8545e12598ce 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -36,6 +36,7 @@ #include #include #include +#include #include MODULE_LICENSE("GPL"); @@ -526,6 +527,48 @@ static struct lock_torture_ops rwsem_lock_ops = { .name = "rwsem_lock" }; +#include +static struct percpu_rw_semaphore pcpu_rwsem; + +void torture_percpu_rwsem_init(void) +{ + BUG_ON(percpu_init_rwsem(&pcpu_rwsem)); +} + +static int torture_percpu_rwsem_down_write(void) __acquires(pcpu_rwsem) +{ + percpu_down_write(&pcpu_rwsem); + return 0; +} + +static void torture_percpu_rwsem_up_write(void) __releases(pcpu_rwsem) +{ + percpu_up_write(&pcpu_rwsem); +} + +static int torture_percpu_rwsem_down_read(void) __acquires(pcpu_rwsem) +{ + percpu_down_read(&pcpu_rwsem); + return 0; +} + +static void torture_percpu_rwsem_up_read(void) __releases(pcpu_rwsem) +{ + percpu_up_read(&pcpu_rwsem); +} + +static struct lock_torture_ops percpu_rwsem_lock_ops = { + .init = torture_percpu_rwsem_init, + .writelock = torture_percpu_rwsem_down_write, + .write_delay = torture_rwsem_write_delay, + .task_boost = torture_boost_dummy, + .writeunlock = torture_percpu_rwsem_up_write, + .readlock = torture_percpu_rwsem_down_read, + .read_delay = torture_rwsem_read_delay, + .readunlock = torture_percpu_rwsem_up_read, + .name = "percpu_rwsem_lock" +}; + /* * Lock torture writer kthread. Repeatedly acquires and releases * the lock, checking for duplicate acquisitions. @@ -749,6 +792,7 @@ static int __init lock_torture_init(void) &rtmutex_lock_ops, #endif &rwsem_lock_ops, + &percpu_rwsem_lock_ops, }; if (!torture_init_begin(torture_type, verbose, &torture_runnable)) diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFLIST b/tools/testing/selftests/rcutorture/configs/lock/CFLIST index 6ed32794eaa1..b9611c523723 100644 --- a/tools/testing/selftests/rcutorture/configs/lock/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/lock/CFLIST @@ -3,3 +3,4 @@ LOCK02 LOCK03 LOCK04 LOCK05 +LOCK06 diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK06 b/tools/testing/selftests/rcutorture/configs/lock/LOCK06 new file mode 100644 index 000000000000..1d1da1477fc3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK06 @@ -0,0 +1,6 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=4 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK06.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK06.boot new file mode 100644 index 000000000000..f92219cd4ad9 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK06.boot @@ -0,0 +1 @@ +locktorture.torture_type=percpu_rwsem_lock -- cgit v1.2.3 From 95b19f684c61ffc9b039e02c5d1113c2d8cd7105 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 21 Aug 2015 19:42:55 +0200 Subject: locking/percpu-rwsem: Make percpu_free_rwsem() after kzalloc() safe This is the temporary ugly hack which will be reverted later. We only need it to ensure that the next patch will not break "change sb_writers to use percpu_rw_semaphore" patches routed via the VFS tree. The alloc_super()->destroy_super() error path assumes that it is safe to call percpu_free_rwsem() after kzalloc() without percpu_init_rwsem(), so let's not disappoint it. Signed-off-by: Oleg Nesterov Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/locking/percpu-rwsem.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel/locking') diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index e2621fbbcbd1..9529a30ec57b 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -26,6 +26,13 @@ EXPORT_SYMBOL_GPL(__percpu_init_rwsem); void percpu_free_rwsem(struct percpu_rw_semaphore *brw) { + /* + * XXX: temporary kludge. The error path in alloc_super() + * assumes that percpu_free_rwsem() is safe after kzalloc(). + */ + if (!brw->fast_read_ctr) + return; + free_percpu(brw->fast_read_ctr); brw->fast_read_ctr = NULL; /* catch use after free bugs */ } -- cgit v1.2.3 From 001dac627ff37433d5528ffb0d897cd19c2b1e43 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 21 Aug 2015 19:42:57 +0200 Subject: locking/percpu-rwsem: Make use of the rcu_sync infrastructure Currently down_write/up_write calls synchronize_sched_expedited() twice, which is evil. Change this code to rely on rcu-sync primitives. This avoids the _expedited "big hammer", and this can be faster in the contended case or even in the case when a single thread does down_write/up_write in a loop. Of course, a single down_write() will take more time, but otoh it will be much more friendly to the whole system. To simplify the review this patch doesn't update the comments, fixed by the next change. Signed-off-by: Oleg Nesterov Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/linux/percpu-rwsem.h | 3 ++- kernel/locking/percpu-rwsem.c | 18 +++++++----------- 2 files changed, 9 insertions(+), 12 deletions(-) (limited to 'kernel/locking') diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 834c4e52cb2d..c2fa3ecb0dce 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -5,11 +5,12 @@ #include #include #include +#include #include struct percpu_rw_semaphore { + struct rcu_sync rss; unsigned int __percpu *fast_read_ctr; - atomic_t write_ctr; struct rw_semaphore rw_sem; atomic_t slow_read_ctr; wait_queue_head_t write_waitq; diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index 9529a30ec57b..183a71151ac0 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -17,7 +17,7 @@ int __percpu_init_rwsem(struct percpu_rw_semaphore *brw, /* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */ __init_rwsem(&brw->rw_sem, name, rwsem_key); - atomic_set(&brw->write_ctr, 0); + rcu_sync_init(&brw->rss, RCU_SCHED_SYNC); atomic_set(&brw->slow_read_ctr, 0); init_waitqueue_head(&brw->write_waitq); return 0; @@ -33,6 +33,7 @@ void percpu_free_rwsem(struct percpu_rw_semaphore *brw) if (!brw->fast_read_ctr) return; + rcu_sync_dtor(&brw->rss); free_percpu(brw->fast_read_ctr); brw->fast_read_ctr = NULL; /* catch use after free bugs */ } @@ -62,13 +63,12 @@ void percpu_free_rwsem(struct percpu_rw_semaphore *brw) */ static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val) { - bool success = false; + bool success; preempt_disable(); - if (likely(!atomic_read(&brw->write_ctr))) { + success = rcu_sync_is_idle(&brw->rss); + if (likely(success)) __this_cpu_add(*brw->fast_read_ctr, val); - success = true; - } preempt_enable(); return success; @@ -149,8 +149,6 @@ static int clear_fast_ctr(struct percpu_rw_semaphore *brw) */ void percpu_down_write(struct percpu_rw_semaphore *brw) { - /* tell update_fast_ctr() there is a pending writer */ - atomic_inc(&brw->write_ctr); /* * 1. Ensures that write_ctr != 0 is visible to any down_read/up_read * so that update_fast_ctr() can't succeed. @@ -162,7 +160,7 @@ void percpu_down_write(struct percpu_rw_semaphore *brw) * fast-path, it executes a full memory barrier before we return. * See R_W case in the comment above update_fast_ctr(). */ - synchronize_sched_expedited(); + rcu_sync_enter(&brw->rss); /* exclude other writers, and block the new readers completely */ down_write(&brw->rw_sem); @@ -183,8 +181,6 @@ void percpu_up_write(struct percpu_rw_semaphore *brw) * Insert the barrier before the next fast-path in down_read, * see W_R case in the comment above update_fast_ctr(). */ - synchronize_sched_expedited(); - /* the last writer unblocks update_fast_ctr() */ - atomic_dec(&brw->write_ctr); + rcu_sync_exit(&brw->rss); } EXPORT_SYMBOL_GPL(percpu_up_write); -- cgit v1.2.3 From f324a76324c97e81a6ba66a8efac20cdbffd759e Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 21 Aug 2015 19:43:00 +0200 Subject: locking/percpu-rwsem: Fix the comments outdated by rcu_sync Update the comments broken by the previous change. Signed-off-by: Oleg Nesterov Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/locking/percpu-rwsem.c | 50 ++++++++++--------------------------------- 1 file changed, 11 insertions(+), 39 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index 183a71151ac0..02a726dd9adc 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -39,27 +39,12 @@ void percpu_free_rwsem(struct percpu_rw_semaphore *brw) } /* - * This is the fast-path for down_read/up_read, it only needs to ensure - * there is no pending writer (atomic_read(write_ctr) == 0) and inc/dec the - * fast per-cpu counter. The writer uses synchronize_sched_expedited() to - * serialize with the preempt-disabled section below. - * - * The nontrivial part is that we should guarantee acquire/release semantics - * in case when - * - * R_W: down_write() comes after up_read(), the writer should see all - * changes done by the reader - * or - * W_R: down_read() comes after up_write(), the reader should see all - * changes done by the writer + * This is the fast-path for down_read/up_read. If it succeeds we rely + * on the barriers provided by rcu_sync_enter/exit; see the comments in + * percpu_down_write() and percpu_up_write(). * * If this helper fails the callers rely on the normal rw_semaphore and * atomic_dec_and_test(), so in this case we have the necessary barriers. - * - * But if it succeeds we do not have any barriers, atomic_read(write_ctr) or - * __this_cpu_add() below can be reordered with any LOAD/STORE done by the - * reader inside the critical section. See the comments in down_write and - * up_write below. */ static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val) { @@ -136,29 +121,15 @@ static int clear_fast_ctr(struct percpu_rw_semaphore *brw) return sum; } -/* - * A writer increments ->write_ctr to force the readers to switch to the - * slow mode, note the atomic_read() check in update_fast_ctr(). - * - * After that the readers can only inc/dec the slow ->slow_read_ctr counter, - * ->fast_read_ctr is stable. Once the writer moves its sum into the slow - * counter it represents the number of active readers. - * - * Finally the writer takes ->rw_sem for writing and blocks the new readers, - * then waits until the slow counter becomes zero. - */ void percpu_down_write(struct percpu_rw_semaphore *brw) { /* - * 1. Ensures that write_ctr != 0 is visible to any down_read/up_read - * so that update_fast_ctr() can't succeed. - * - * 2. Ensures we see the result of every previous this_cpu_add() in - * update_fast_ctr(). + * Make rcu_sync_is_idle() == F and thus disable the fast-path in + * percpu_down_read() and percpu_up_read(), and wait for gp pass. * - * 3. Ensures that if any reader has exited its critical section via - * fast-path, it executes a full memory barrier before we return. - * See R_W case in the comment above update_fast_ctr(). + * The latter synchronises us with the preceding readers which used + * the fast-past, so we can not miss the result of __this_cpu_add() + * or anything else inside their criticial sections. */ rcu_sync_enter(&brw->rss); @@ -178,8 +149,9 @@ void percpu_up_write(struct percpu_rw_semaphore *brw) /* release the lock, but the readers can't use the fast-path */ up_write(&brw->rw_sem); /* - * Insert the barrier before the next fast-path in down_read, - * see W_R case in the comment above update_fast_ctr(). + * Enable the fast-path in percpu_down_read() and percpu_up_read() + * but only after another gp pass; this adds the necessary barrier + * to ensure the reader can't miss the changes done by us. */ rcu_sync_exit(&brw->rss); } -- cgit v1.2.3 From cc5f730b41506d37a5c2826b2e801d0a59853d11 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 21 Aug 2015 19:43:03 +0200 Subject: locking/percpu-rwsem: Clean up the lockdep annotations in percpu_down_read() Based on Peter Zijlstra's earlier patch. Change percpu_down_read() to use __down_read(), this way we can do rwsem_acquire_read() unconditionally at the start to make this code more symmetric and clean. Originally-From: Peter Zijlstra Signed-off-by: Oleg Nesterov Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/locking/percpu-rwsem.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index 02a726dd9adc..f231e0bb311c 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -70,14 +70,14 @@ static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val) void percpu_down_read(struct percpu_rw_semaphore *brw) { might_sleep(); - if (likely(update_fast_ctr(brw, +1))) { - rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 0, _RET_IP_); + rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 0, _RET_IP_); + + if (likely(update_fast_ctr(brw, +1))) return; - } - down_read(&brw->rw_sem); + /* Avoid rwsem_acquire_read() and rwsem_release() */ + __down_read(&brw->rw_sem); atomic_inc(&brw->slow_read_ctr); - /* avoid up_read()->rwsem_release() */ __up_read(&brw->rw_sem); } EXPORT_SYMBOL_GPL(percpu_down_read); -- cgit v1.2.3 From a36a99618b1adb2d6ca0b7e08e3a656a04e477fe Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 30 Aug 2015 20:01:48 -0700 Subject: locktorture: Fix module unwind when bad torture_type specified The locktorture module has a list of torture types, and specifying a type not on this list is supposed to cleanly fail the module load. Unfortunately, the "fail" happens without the "cleanly". This commit therefore adds the needed clean-up after an incorrect torture_type. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/locking/locktorture.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 32244186f1f2..820852f69858 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -661,11 +661,11 @@ static int __init lock_torture_init(void) for (i = 0; i < ARRAY_SIZE(torture_ops); i++) pr_alert(" %s", torture_ops[i]->name); pr_alert("\n"); - torture_init_end(); - return -EINVAL; + firsterr = -EINVAL; + goto unwind; } if (cxt.cur_ops->init) - cxt.cur_ops->init(); /* no "goto unwind" prior to this point!!! */ + cxt.cur_ops->init(); if (nwriters_stress >= 0) cxt.nrealwriters_stress = nwriters_stress; -- cgit v1.2.3 From d0164adc89f6bb374d304ffcc375c6d2652fe67d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 6 Nov 2015 16:28:21 -0800 Subject: mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd __GFP_WAIT has been used to identify atomic context in callers that hold spinlocks or are in interrupts. They are expected to be high priority and have access one of two watermarks lower than "min" which can be referred to as the "atomic reserve". __GFP_HIGH users get access to the first lower watermark and can be called the "high priority reserve". Over time, callers had a requirement to not block when fallback options were available. Some have abused __GFP_WAIT leading to a situation where an optimisitic allocation with a fallback option can access atomic reserves. This patch uses __GFP_ATOMIC to identify callers that are truely atomic, cannot sleep and have no alternative. High priority users continue to use __GFP_HIGH. __GFP_DIRECT_RECLAIM identifies callers that can sleep and are willing to enter direct reclaim. __GFP_KSWAPD_RECLAIM to identify callers that want to wake kswapd for background reclaim. __GFP_WAIT is redefined as a caller that is willing to enter direct reclaim and wake kswapd for background reclaim. This patch then converts a number of sites o __GFP_ATOMIC is used by callers that are high priority and have memory pools for those requests. GFP_ATOMIC uses this flag. o Callers that have a limited mempool to guarantee forward progress clear __GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall into this category where kswapd will still be woken but atomic reserves are not used as there is a one-entry mempool to guarantee progress. o Callers that are checking if they are non-blocking should use the helper gfpflags_allow_blocking() where possible. This is because checking for __GFP_WAIT as was done historically now can trigger false positives. Some exceptions like dm-crypt.c exist where the code intent is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to flag manipulations. o Callers that built their own GFP flags instead of starting with GFP_KERNEL and friends now also need to specify __GFP_KSWAPD_RECLAIM. The first key hazard to watch out for is callers that removed __GFP_WAIT and was depending on access to atomic reserves for inconspicuous reasons. In some cases it may be appropriate for them to use __GFP_HIGH. The second key hazard is callers that assembled their own combination of GFP flags instead of starting with something like GFP_KERNEL. They may now wish to specify __GFP_KSWAPD_RECLAIM. It's almost certainly harmless if it's missed in most cases as other activity will wake kswapd. Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: Christoph Lameter Cc: David Rientjes Cc: Vitaly Wool Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/balance | 14 ++++--- arch/arm/mm/dma-mapping.c | 6 +-- arch/arm/xen/mm.c | 2 +- arch/arm64/mm/dma-mapping.c | 4 +- arch/x86/kernel/pci-dma.c | 2 +- block/bio.c | 26 ++++++------ block/blk-core.c | 16 ++++---- block/blk-ioc.c | 2 +- block/blk-mq-tag.c | 2 +- block/blk-mq.c | 6 +-- drivers/block/drbd/drbd_receiver.c | 3 +- drivers/block/osdblk.c | 2 +- drivers/connector/connector.c | 3 +- drivers/firewire/core-cdev.c | 2 +- drivers/gpu/drm/i915/i915_gem.c | 2 +- drivers/infiniband/core/sa_query.c | 2 +- drivers/iommu/amd_iommu.c | 2 +- drivers/iommu/intel-iommu.c | 2 +- drivers/md/dm-crypt.c | 6 +-- drivers/md/dm-kcopyd.c | 2 +- drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c | 2 +- drivers/media/pci/solo6x10/solo6x10-v4l2.c | 2 +- drivers/media/pci/tw68/tw68-video.c | 2 +- drivers/mtd/mtdcore.c | 3 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 2 +- drivers/staging/android/ion/ion_system_heap.c | 2 +- .../lustre/include/linux/libcfs/libcfs_private.h | 2 +- drivers/usb/host/u132-hcd.c | 2 +- drivers/video/fbdev/vermilion/vermilion.c | 2 +- fs/btrfs/disk-io.c | 2 +- fs/btrfs/extent_io.c | 14 +++---- fs/btrfs/volumes.c | 4 +- fs/ext4/super.c | 2 +- fs/fscache/cookie.c | 2 +- fs/fscache/page.c | 6 +-- fs/jbd2/transaction.c | 4 +- fs/nfs/file.c | 6 +-- fs/xfs/xfs_qm.c | 2 +- include/linux/gfp.h | 46 ++++++++++++++++------ include/linux/skbuff.h | 6 +-- include/net/sock.h | 2 +- include/trace/events/gfpflags.h | 5 ++- kernel/audit.c | 6 +-- kernel/cgroup.c | 2 +- kernel/locking/lockdep.c | 2 +- kernel/power/snapshot.c | 2 +- kernel/smp.c | 2 +- lib/idr.c | 4 +- lib/radix-tree.c | 10 ++--- mm/backing-dev.c | 2 +- mm/dmapool.c | 2 +- mm/memcontrol.c | 6 +-- mm/mempool.c | 10 ++--- mm/migrate.c | 2 +- mm/page_alloc.c | 43 ++++++++++++-------- mm/slab.c | 18 ++++----- mm/slub.c | 10 ++--- mm/vmalloc.c | 2 +- mm/vmscan.c | 4 +- mm/zswap.c | 5 ++- net/core/skbuff.c | 8 ++-- net/core/sock.c | 6 ++- net/netlink/af_netlink.c | 2 +- net/rds/ib_recv.c | 4 +- net/rxrpc/ar-connection.c | 2 +- net/sctp/associola.c | 2 +- 66 files changed, 210 insertions(+), 172 deletions(-) (limited to 'kernel/locking') diff --git a/Documentation/vm/balance b/Documentation/vm/balance index c46e68cf9344..964595481af6 100644 --- a/Documentation/vm/balance +++ b/Documentation/vm/balance @@ -1,12 +1,14 @@ Started Jan 2000 by Kanoj Sarcar -Memory balancing is needed for non __GFP_WAIT as well as for non -__GFP_IO allocations. +Memory balancing is needed for !__GFP_ATOMIC and !__GFP_KSWAPD_RECLAIM as +well as for non __GFP_IO allocations. -There are two reasons to be requesting non __GFP_WAIT allocations: -the caller can not sleep (typically intr context), or does not want -to incur cost overheads of page stealing and possible swap io for -whatever reasons. +The first reason why a caller may avoid reclaim is that the caller can not +sleep due to holding a spinlock or is in interrupt context. The second may +be that the caller is willing to fail the allocation without incurring the +overhead of page reclaim. This may happen for opportunistic high-order +allocation requests that have order-0 fallback options. In such cases, +the caller may also wish to avoid waking kswapd. __GFP_IO allocation requests are made to prevent file system deadlocks. diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index ad4eb2d26e16..e62400e5fb99 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -651,12 +651,12 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, if (nommu()) addr = __alloc_simple_buffer(dev, size, gfp, &page); - else if (dev_get_cma_area(dev) && (gfp & __GFP_WAIT)) + else if (dev_get_cma_area(dev) && (gfp & __GFP_DIRECT_RECLAIM)) addr = __alloc_from_contiguous(dev, size, prot, &page, caller, want_vaddr); else if (is_coherent) addr = __alloc_simple_buffer(dev, size, gfp, &page); - else if (!(gfp & __GFP_WAIT)) + else if (!gfpflags_allow_blocking(gfp)) addr = __alloc_from_pool(size, &page); else addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, @@ -1363,7 +1363,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, *handle = DMA_ERROR_CODE; size = PAGE_ALIGN(size); - if (!(gfp & __GFP_WAIT)) + if (!gfpflags_allow_blocking(gfp)) return __iommu_alloc_atomic(dev, size, handle); /* diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index 7c34f7126b04..c5f9a9e3d1f3 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -25,7 +25,7 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order) { struct memblock_region *reg; - gfp_t flags = __GFP_NOWARN; + gfp_t flags = __GFP_NOWARN|__GFP_KSWAPD_RECLAIM; for_each_memblock(memory, reg) { if (reg->base < (phys_addr_t)0xffffffff) { diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 6320361d8d4c..bb4bf6a06ad6 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -100,7 +100,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, if (IS_ENABLED(CONFIG_ZONE_DMA) && dev->coherent_dma_mask <= DMA_BIT_MASK(32)) flags |= GFP_DMA; - if (dev_get_cma_area(dev) && (flags & __GFP_WAIT)) { + if (dev_get_cma_area(dev) && gfpflags_allow_blocking(flags)) { struct page *page; void *addr; @@ -148,7 +148,7 @@ static void *__dma_alloc(struct device *dev, size_t size, size = PAGE_ALIGN(size); - if (!coherent && !(flags & __GFP_WAIT)) { + if (!coherent && !gfpflags_allow_blocking(flags)) { struct page *page = NULL; void *addr = __alloc_from_pool(size, &page, flags); diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index cd99433b8ba1..6ba014c61d62 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -90,7 +90,7 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, again: page = NULL; /* CMA can be used only in the context which permits sleeping */ - if (flag & __GFP_WAIT) { + if (gfpflags_allow_blocking(flag)) { page = dma_alloc_from_contiguous(dev, count, get_order(size)); if (page && page_to_phys(page) + size > dma_mask) { dma_release_from_contiguous(dev, page, count); diff --git a/block/bio.c b/block/bio.c index ad3f276d74bc..4f184d938942 100644 --- a/block/bio.c +++ b/block/bio.c @@ -211,7 +211,7 @@ fallback: bvl = mempool_alloc(pool, gfp_mask); } else { struct biovec_slab *bvs = bvec_slabs + *idx; - gfp_t __gfp_mask = gfp_mask & ~(__GFP_WAIT | __GFP_IO); + gfp_t __gfp_mask = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_IO); /* * Make this allocation restricted and don't dump info on @@ -221,11 +221,11 @@ fallback: __gfp_mask |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN; /* - * Try a slab allocation. If this fails and __GFP_WAIT + * Try a slab allocation. If this fails and __GFP_DIRECT_RECLAIM * is set, retry with the 1-entry mempool */ bvl = kmem_cache_alloc(bvs->slab, __gfp_mask); - if (unlikely(!bvl && (gfp_mask & __GFP_WAIT))) { + if (unlikely(!bvl && (gfp_mask & __GFP_DIRECT_RECLAIM))) { *idx = BIOVEC_MAX_IDX; goto fallback; } @@ -395,12 +395,12 @@ static void punt_bios_to_rescuer(struct bio_set *bs) * If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is * backed by the @bs's mempool. * - * When @bs is not NULL, if %__GFP_WAIT is set then bio_alloc will always be - * able to allocate a bio. This is due to the mempool guarantees. To make this - * work, callers must never allocate more than 1 bio at a time from this pool. - * Callers that need to allocate more than 1 bio must always submit the - * previously allocated bio for IO before attempting to allocate a new one. - * Failure to do so can cause deadlocks under memory pressure. + * When @bs is not NULL, if %__GFP_DIRECT_RECLAIM is set then bio_alloc will + * always be able to allocate a bio. This is due to the mempool guarantees. + * To make this work, callers must never allocate more than 1 bio at a time + * from this pool. Callers that need to allocate more than 1 bio must always + * submit the previously allocated bio for IO before attempting to allocate + * a new one. Failure to do so can cause deadlocks under memory pressure. * * Note that when running under generic_make_request() (i.e. any block * driver), bios are not submitted until after you return - see the code in @@ -459,13 +459,13 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs) * We solve this, and guarantee forward progress, with a rescuer * workqueue per bio_set. If we go to allocate and there are * bios on current->bio_list, we first try the allocation - * without __GFP_WAIT; if that fails, we punt those bios we - * would be blocking to the rescuer workqueue before we retry - * with the original gfp_flags. + * without __GFP_DIRECT_RECLAIM; if that fails, we punt those + * bios we would be blocking to the rescuer workqueue before + * we retry with the original gfp_flags. */ if (current->bio_list && !bio_list_empty(current->bio_list)) - gfp_mask &= ~__GFP_WAIT; + gfp_mask &= ~__GFP_DIRECT_RECLAIM; p = mempool_alloc(bs->bio_pool, gfp_mask); if (!p && gfp_mask != saved_gfp) { diff --git a/block/blk-core.c b/block/blk-core.c index 89eec7965870..9e32f0868e36 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1206,8 +1206,8 @@ rq_starved: * @bio: bio to allocate request for (can be %NULL) * @gfp_mask: allocation mask * - * Get a free request from @q. If %__GFP_WAIT is set in @gfp_mask, this - * function keeps retrying under memory pressure and fails iff @q is dead. + * Get a free request from @q. If %__GFP_DIRECT_RECLAIM is set in @gfp_mask, + * this function keeps retrying under memory pressure and fails iff @q is dead. * * Must be called with @q->queue_lock held and, * Returns ERR_PTR on failure, with @q->queue_lock held. @@ -1227,7 +1227,7 @@ retry: if (!IS_ERR(rq)) return rq; - if (!(gfp_mask & __GFP_WAIT) || unlikely(blk_queue_dying(q))) { + if (!gfpflags_allow_blocking(gfp_mask) || unlikely(blk_queue_dying(q))) { blk_put_rl(rl); return rq; } @@ -1305,11 +1305,11 @@ EXPORT_SYMBOL(blk_get_request); * BUG. * * WARNING: When allocating/cloning a bio-chain, careful consideration should be - * given to how you allocate bios. In particular, you cannot use __GFP_WAIT for - * anything but the first bio in the chain. Otherwise you risk waiting for IO - * completion of a bio that hasn't been submitted yet, thus resulting in a - * deadlock. Alternatively bios should be allocated using bio_kmalloc() instead - * of bio_alloc(), as that avoids the mempool deadlock. + * given to how you allocate bios. In particular, you cannot use + * __GFP_DIRECT_RECLAIM for anything but the first bio in the chain. Otherwise + * you risk waiting for IO completion of a bio that hasn't been submitted yet, + * thus resulting in a deadlock. Alternatively bios should be allocated using + * bio_kmalloc() instead of bio_alloc(), as that avoids the mempool deadlock. * If possible a big IO should be split into smaller parts when allocation * fails. Partial allocation should not be an error, or you risk a live-lock. */ diff --git a/block/blk-ioc.c b/block/blk-ioc.c index 1a27f45ec776..381cb50a673c 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -289,7 +289,7 @@ struct io_context *get_task_io_context(struct task_struct *task, { struct io_context *ioc; - might_sleep_if(gfp_flags & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(gfp_flags)); do { task_lock(task); diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 60ac684c8b8c..a07ca3488d96 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -268,7 +268,7 @@ static int bt_get(struct blk_mq_alloc_data *data, if (tag != -1) return tag; - if (!(data->gfp & __GFP_WAIT)) + if (!gfpflags_allow_blocking(data->gfp)) return -1; bs = bt_wait_ptr(bt, hctx); diff --git a/block/blk-mq.c b/block/blk-mq.c index 1c27b3eaef64..68c0a3416b34 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -244,11 +244,11 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp, ctx = blk_mq_get_ctx(q); hctx = q->mq_ops->map_queue(q, ctx->cpu); - blk_mq_set_alloc_data(&alloc_data, q, gfp & ~__GFP_WAIT, + blk_mq_set_alloc_data(&alloc_data, q, gfp & ~__GFP_DIRECT_RECLAIM, reserved, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, rw); - if (!rq && (gfp & __GFP_WAIT)) { + if (!rq && (gfp & __GFP_DIRECT_RECLAIM)) { __blk_mq_run_hw_queue(hctx); blk_mq_put_ctx(ctx); @@ -1186,7 +1186,7 @@ static struct request *blk_mq_map_request(struct request_queue *q, ctx = blk_mq_get_ctx(q); hctx = q->mq_ops->map_queue(q, ctx->cpu); blk_mq_set_alloc_data(&alloc_data, q, - __GFP_WAIT|GFP_ATOMIC, false, ctx, hctx); + __GFP_WAIT|__GFP_HIGH, false, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, rw); ctx = alloc_data.ctx; hctx = alloc_data.hctx; diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index c097909c589c..b4b5680ac6ad 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -357,7 +357,8 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto } if (has_payload && data_size) { - page = drbd_alloc_pages(peer_device, nr_pages, (gfp_mask & __GFP_WAIT)); + page = drbd_alloc_pages(peer_device, nr_pages, + gfpflags_allow_blocking(gfp_mask)); if (!page) goto fail; } diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c index e22942596207..1b709a4e3b5e 100644 --- a/drivers/block/osdblk.c +++ b/drivers/block/osdblk.c @@ -271,7 +271,7 @@ static struct bio *bio_chain_clone(struct bio *old_chain, gfp_t gfpmask) goto err_out; tmp->bi_bdev = NULL; - gfpmask &= ~__GFP_WAIT; + gfpmask &= ~__GFP_DIRECT_RECLAIM; tmp->bi_next = NULL; if (!new_chain) diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index 30f522848c73..d7373ca69c99 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -124,7 +124,8 @@ int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 __group, if (group) return netlink_broadcast(dev->nls, skb, portid, group, gfp_mask); - return netlink_unicast(dev->nls, skb, portid, !(gfp_mask&__GFP_WAIT)); + return netlink_unicast(dev->nls, skb, portid, + !gfpflags_allow_blocking(gfp_mask)); } EXPORT_SYMBOL_GPL(cn_netlink_send_mult); diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 2a3973a7c441..36a7c2d89a01 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -486,7 +486,7 @@ static int ioctl_get_info(struct client *client, union ioctl_arg *arg) static int add_client_resource(struct client *client, struct client_resource *resource, gfp_t gfp_mask) { - bool preload = !!(gfp_mask & __GFP_WAIT); + bool preload = gfpflags_allow_blocking(gfp_mask); unsigned long flags; int ret; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 4d631a946481..d58cb9e034fe 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2215,7 +2215,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) */ mapping = file_inode(obj->base.filp)->i_mapping; gfp = mapping_gfp_mask(mapping); - gfp |= __GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD; + gfp |= __GFP_NORETRY | __GFP_NOWARN; gfp &= ~(__GFP_IO | __GFP_WAIT); sg = st->sgl; st->nents = 0; diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index 8c014b33d8e0..59ab264c99c4 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -1083,7 +1083,7 @@ static void init_mad(struct ib_sa_mad *mad, struct ib_mad_agent *agent) static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask) { - bool preload = !!(gfp_mask & __GFP_WAIT); + bool preload = gfpflags_allow_blocking(gfp_mask); unsigned long flags; int ret, id; diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 0d533bba4ad1..8b2be1e7714f 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2668,7 +2668,7 @@ static void *alloc_coherent(struct device *dev, size_t size, page = alloc_pages(flag | __GFP_NOWARN, get_order(size)); if (!page) { - if (!(flag & __GFP_WAIT)) + if (!gfpflags_allow_blocking(flag)) return NULL; page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT, diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 7cf80c1a8a16..f1042daef9ad 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -3647,7 +3647,7 @@ static void *intel_alloc_coherent(struct device *dev, size_t size, flags |= GFP_DMA32; } - if (flags & __GFP_WAIT) { + if (gfpflags_allow_blocking(flags)) { unsigned int count = size >> PAGE_SHIFT; page = dma_alloc_from_contiguous(dev, count, order); diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 3729b394432c..917d47e290ae 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -994,7 +994,7 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size) struct bio_vec *bvec; retry: - if (unlikely(gfp_mask & __GFP_WAIT)) + if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM)) mutex_lock(&cc->bio_alloc_lock); clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, cc->bs); @@ -1010,7 +1010,7 @@ retry: if (!page) { crypt_free_buffer_pages(cc, clone); bio_put(clone); - gfp_mask |= __GFP_WAIT; + gfp_mask |= __GFP_DIRECT_RECLAIM; goto retry; } @@ -1027,7 +1027,7 @@ retry: } return_clone: - if (unlikely(gfp_mask & __GFP_WAIT)) + if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM)) mutex_unlock(&cc->bio_alloc_lock); return clone; diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 3a7cade5e27d..1452ed9aacb4 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -244,7 +244,7 @@ static int kcopyd_get_pages(struct dm_kcopyd_client *kc, *pages = NULL; do { - pl = alloc_pl(__GFP_NOWARN | __GFP_NORETRY); + pl = alloc_pl(__GFP_NOWARN | __GFP_NORETRY | __GFP_KSWAPD_RECLAIM); if (unlikely(!pl)) { /* Use reserved pages */ pl = kc->pages; diff --git a/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c b/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c index 1bd2fd47421f..4432fd69b7cb 100644 --- a/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c +++ b/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c @@ -1297,7 +1297,7 @@ static struct solo_enc_dev *solo_enc_alloc(struct solo_dev *solo_dev, solo_enc->vidq.ops = &solo_enc_video_qops; solo_enc->vidq.mem_ops = &vb2_dma_sg_memops; solo_enc->vidq.drv_priv = solo_enc; - solo_enc->vidq.gfp_flags = __GFP_DMA32; + solo_enc->vidq.gfp_flags = __GFP_DMA32 | __GFP_KSWAPD_RECLAIM; solo_enc->vidq.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; solo_enc->vidq.buf_struct_size = sizeof(struct solo_vb2_buf); solo_enc->vidq.lock = &solo_enc->lock; diff --git a/drivers/media/pci/solo6x10/solo6x10-v4l2.c b/drivers/media/pci/solo6x10/solo6x10-v4l2.c index 26df903585d7..f7ce493b1fee 100644 --- a/drivers/media/pci/solo6x10/solo6x10-v4l2.c +++ b/drivers/media/pci/solo6x10/solo6x10-v4l2.c @@ -678,7 +678,7 @@ int solo_v4l2_init(struct solo_dev *solo_dev, unsigned nr) solo_dev->vidq.mem_ops = &vb2_dma_contig_memops; solo_dev->vidq.drv_priv = solo_dev; solo_dev->vidq.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; - solo_dev->vidq.gfp_flags = __GFP_DMA32; + solo_dev->vidq.gfp_flags = __GFP_DMA32 | __GFP_KSWAPD_RECLAIM; solo_dev->vidq.buf_struct_size = sizeof(struct solo_vb2_buf); solo_dev->vidq.lock = &solo_dev->lock; ret = vb2_queue_init(&solo_dev->vidq); diff --git a/drivers/media/pci/tw68/tw68-video.c b/drivers/media/pci/tw68/tw68-video.c index 4c3293dcddbc..46642ef9151b 100644 --- a/drivers/media/pci/tw68/tw68-video.c +++ b/drivers/media/pci/tw68/tw68-video.c @@ -979,7 +979,7 @@ int tw68_video_init2(struct tw68_dev *dev, int video_nr) dev->vidq.ops = &tw68_video_qops; dev->vidq.mem_ops = &vb2_dma_sg_memops; dev->vidq.drv_priv = dev; - dev->vidq.gfp_flags = __GFP_DMA32; + dev->vidq.gfp_flags = __GFP_DMA32 | __GFP_KSWAPD_RECLAIM; dev->vidq.buf_struct_size = sizeof(struct tw68_buf); dev->vidq.lock = &dev->lock; dev->vidq.min_buffers_needed = 2; diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 8bbbb751bf45..2dfb291a47c6 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -1188,8 +1188,7 @@ EXPORT_SYMBOL_GPL(mtd_writev); */ void *mtd_kmalloc_up_to(const struct mtd_info *mtd, size_t *size) { - gfp_t flags = __GFP_NOWARN | __GFP_WAIT | - __GFP_NORETRY | __GFP_NO_KSWAPD; + gfp_t flags = __GFP_NOWARN | __GFP_DIRECT_RECLAIM | __GFP_NORETRY; size_t min_alloc = max_t(size_t, mtd->writesize, PAGE_SIZE); void *kbuf; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 44173be5cbf0..f8d7a2f06950 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -691,7 +691,7 @@ static void *bnx2x_frag_alloc(const struct bnx2x_fastpath *fp, gfp_t gfp_mask) { if (fp->rx_frag_size) { /* GFP_KERNEL allocations are used only during initialization */ - if (unlikely(gfp_mask & __GFP_WAIT)) + if (unlikely(gfpflags_allow_blocking(gfp_mask))) return (void *)__get_free_page(gfp_mask); return netdev_alloc_frag(fp->rx_frag_size); diff --git a/drivers/staging/android/ion/ion_system_heap.c b/drivers/staging/android/ion/ion_system_heap.c index ada724aab3d5..d4c3e5512dd5 100644 --- a/drivers/staging/android/ion/ion_system_heap.c +++ b/drivers/staging/android/ion/ion_system_heap.c @@ -27,7 +27,7 @@ #include "ion_priv.h" static gfp_t high_order_gfp_flags = (GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN | - __GFP_NORETRY) & ~__GFP_WAIT; + __GFP_NORETRY) & ~__GFP_DIRECT_RECLAIM; static gfp_t low_order_gfp_flags = (GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN); static const unsigned int orders[] = {8, 4, 0}; static const int num_orders = ARRAY_SIZE(orders); diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h index 6af733de69ca..f0b0423a716b 100644 --- a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h +++ b/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h @@ -95,7 +95,7 @@ do { \ do { \ LASSERT(!in_interrupt() || \ ((size) <= LIBCFS_VMALLOC_SIZE && \ - ((mask) & __GFP_WAIT) == 0)); \ + !gfpflags_allow_blocking(mask))); \ } while (0) #define LIBCFS_ALLOC_POST(ptr, size) \ diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c index 0a94895a358d..692ccc69345e 100644 --- a/drivers/usb/host/u132-hcd.c +++ b/drivers/usb/host/u132-hcd.c @@ -2244,7 +2244,7 @@ static int u132_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, { struct u132 *u132 = hcd_to_u132(hcd); if (irqs_disabled()) { - if (__GFP_WAIT & mem_flags) { + if (gfpflags_allow_blocking(mem_flags)) { printk(KERN_ERR "invalid context for function that might sleep\n"); return -EINVAL; } diff --git a/drivers/video/fbdev/vermilion/vermilion.c b/drivers/video/fbdev/vermilion/vermilion.c index 6b70d7f62b2f..1c1e95a0b8fa 100644 --- a/drivers/video/fbdev/vermilion/vermilion.c +++ b/drivers/video/fbdev/vermilion/vermilion.c @@ -99,7 +99,7 @@ static int vmlfb_alloc_vram_area(struct vram_area *va, unsigned max_order, * below the first 16MB. */ - flags = __GFP_DMA | __GFP_HIGH; + flags = __GFP_DMA | __GFP_HIGH | __GFP_KSWAPD_RECLAIM; va->logical = __get_free_pages(flags, --max_order); } while (va->logical == 0 && max_order > min_order); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 1e60d00d4ea7..c339d561e596 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2572,7 +2572,7 @@ int open_ctree(struct super_block *sb, fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */ /* readahead state */ - INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); spin_lock_init(&fs_info->reada_lock); fs_info->thread_pool_size = min_t(unsigned long, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 3915c9473e94..032abfbebe76 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -594,7 +594,7 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, if (bits & (EXTENT_IOBITS | EXTENT_BOUNDARY)) clear = 1; again: - if (!prealloc && (mask & __GFP_WAIT)) { + if (!prealloc && gfpflags_allow_blocking(mask)) { /* * Don't care for allocation failure here because we might end * up not needing the pre-allocated extent state at all, which @@ -718,7 +718,7 @@ search_again: if (start > end) goto out; spin_unlock(&tree->lock); - if (mask & __GFP_WAIT) + if (gfpflags_allow_blocking(mask)) cond_resched(); goto again; } @@ -850,7 +850,7 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, bits |= EXTENT_FIRST_DELALLOC; again: - if (!prealloc && (mask & __GFP_WAIT)) { + if (!prealloc && gfpflags_allow_blocking(mask)) { prealloc = alloc_extent_state(mask); BUG_ON(!prealloc); } @@ -1028,7 +1028,7 @@ search_again: if (start > end) goto out; spin_unlock(&tree->lock); - if (mask & __GFP_WAIT) + if (gfpflags_allow_blocking(mask)) cond_resched(); goto again; } @@ -1076,7 +1076,7 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, btrfs_debug_check_extent_io_range(tree, start, end); again: - if (!prealloc && (mask & __GFP_WAIT)) { + if (!prealloc && gfpflags_allow_blocking(mask)) { /* * Best effort, don't worry if extent state allocation fails * here for the first iteration. We might have a cached state @@ -1253,7 +1253,7 @@ search_again: if (start > end) goto out; spin_unlock(&tree->lock); - if (mask & __GFP_WAIT) + if (gfpflags_allow_blocking(mask)) cond_resched(); first_iteration = false; goto again; @@ -4319,7 +4319,7 @@ int try_release_extent_mapping(struct extent_map_tree *map, u64 start = page_offset(page); u64 end = start + PAGE_CACHE_SIZE - 1; - if ((mask & __GFP_WAIT) && + if (gfpflags_allow_blocking(mask) && page->mapping->host->i_size > 16 * 1024 * 1024) { u64 len; while (start <= end) { diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6fc735869c18..e023919b4470 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -156,8 +156,8 @@ static struct btrfs_device *__alloc_device(void) spin_lock_init(&dev->reada_lock); atomic_set(&dev->reada_in_flight, 0); atomic_set(&dev->dev_stats_ccnt, 0); - INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_WAIT); - INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); + INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); return dev; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a63c7b0a10cf..49f6c78ee3af 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1058,7 +1058,7 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page, return 0; if (journal) return jbd2_journal_try_to_free_buffers(journal, page, - wait & ~__GFP_WAIT); + wait & ~__GFP_DIRECT_RECLAIM); return try_to_free_buffers(page); } diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index d403c69bee08..4304072161aa 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -111,7 +111,7 @@ struct fscache_cookie *__fscache_acquire_cookie( /* radix tree insertion won't use the preallocation pool unless it's * told it may not wait */ - INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); switch (cookie->def->type) { case FSCACHE_COOKIE_TYPE_INDEX: diff --git a/fs/fscache/page.c b/fs/fscache/page.c index 483bbc613bf0..79483b3d8c6f 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -58,7 +58,7 @@ bool release_page_wait_timeout(struct fscache_cookie *cookie, struct page *page) /* * decide whether a page can be released, possibly by cancelling a store to it - * - we're allowed to sleep if __GFP_WAIT is flagged + * - we're allowed to sleep if __GFP_DIRECT_RECLAIM is flagged */ bool __fscache_maybe_release_page(struct fscache_cookie *cookie, struct page *page, @@ -122,7 +122,7 @@ page_busy: * allocator as the work threads writing to the cache may all end up * sleeping on memory allocation, so we may need to impose a timeout * too. */ - if (!(gfp & __GFP_WAIT) || !(gfp & __GFP_FS)) { + if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS)) { fscache_stat(&fscache_n_store_vmscan_busy); return false; } @@ -132,7 +132,7 @@ page_busy: _debug("fscache writeout timeout page: %p{%lx}", page, page->index); - gfp &= ~__GFP_WAIT; + gfp &= ~__GFP_DIRECT_RECLAIM; goto try_again; } EXPORT_SYMBOL(__fscache_maybe_release_page); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 6b8338ec2464..89463eee6791 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1937,8 +1937,8 @@ out: * @journal: journal for operation * @page: to try and free * @gfp_mask: we use the mask to detect how hard should we try to release - * buffers. If __GFP_WAIT and __GFP_FS is set, we wait for commit code to - * release the buffers. + * buffers. If __GFP_DIRECT_RECLAIM and __GFP_FS is set, we wait for commit + * code to release the buffers. * * * For all the buffers on this page, diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 37f639d50af5..93e236429c5d 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -473,8 +473,8 @@ static int nfs_release_page(struct page *page, gfp_t gfp) dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page); /* Always try to initiate a 'commit' if relevant, but only - * wait for it if __GFP_WAIT is set. Even then, only wait 1 - * second and only if the 'bdi' is not congested. + * wait for it if the caller allows blocking. Even then, + * only wait 1 second and only if the 'bdi' is not congested. * Waiting indefinitely can cause deadlocks when the NFS * server is on this machine, when a new TCP connection is * needed and in other rare cases. There is no particular @@ -484,7 +484,7 @@ static int nfs_release_page(struct page *page, gfp_t gfp) if (mapping) { struct nfs_server *nfss = NFS_SERVER(mapping->host); nfs_commit_inode(mapping->host, 0); - if ((gfp & __GFP_WAIT) && + if (gfpflags_allow_blocking(gfp) && !bdi_write_congested(&nfss->backing_dev_info)) { wait_on_page_bit_killable_timeout(page, PG_private, HZ); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index eac9549efd52..587174fd4f2c 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -525,7 +525,7 @@ xfs_qm_shrink_scan( unsigned long freed; int error; - if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT)) + if ((sc->gfp_mask & (__GFP_FS|__GFP_DIRECT_RECLAIM)) != (__GFP_FS|__GFP_DIRECT_RECLAIM)) return 0; INIT_LIST_HEAD(&isol.buffers); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 440fca3e7e5d..b56e811b6f7c 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -29,12 +29,13 @@ struct vm_area_struct; #define ___GFP_NOMEMALLOC 0x10000u #define ___GFP_HARDWALL 0x20000u #define ___GFP_THISNODE 0x40000u -#define ___GFP_WAIT 0x80000u +#define ___GFP_ATOMIC 0x80000u #define ___GFP_NOACCOUNT 0x100000u #define ___GFP_NOTRACK 0x200000u -#define ___GFP_NO_KSWAPD 0x400000u +#define ___GFP_DIRECT_RECLAIM 0x400000u #define ___GFP_OTHER_NODE 0x800000u #define ___GFP_WRITE 0x1000000u +#define ___GFP_KSWAPD_RECLAIM 0x2000000u /* If the above are modified, __GFP_BITS_SHIFT may need updating */ /* @@ -71,7 +72,7 @@ struct vm_area_struct; * __GFP_MOVABLE: Flag that this page will be movable by the page migration * mechanism or reclaimed */ -#define __GFP_WAIT ((__force gfp_t)___GFP_WAIT) /* Can wait and reschedule? */ +#define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) /* Caller cannot wait or reschedule */ #define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) /* Should access emergency pools? */ #define __GFP_IO ((__force gfp_t)___GFP_IO) /* Can start physical IO? */ #define __GFP_FS ((__force gfp_t)___GFP_FS) /* Can call down to low-level FS? */ @@ -94,23 +95,37 @@ struct vm_area_struct; #define __GFP_NOACCOUNT ((__force gfp_t)___GFP_NOACCOUNT) /* Don't account to kmemcg */ #define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) /* Don't track with kmemcheck */ -#define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD) #define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */ #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) /* Allocator intends to dirty page */ +/* + * A caller that is willing to wait may enter direct reclaim and will + * wake kswapd to reclaim pages in the background until the high + * watermark is met. A caller may wish to clear __GFP_DIRECT_RECLAIM to + * avoid unnecessary delays when a fallback option is available but + * still allow kswapd to reclaim in the background. The kswapd flag + * can be cleared when the reclaiming of pages would cause unnecessary + * disruption. + */ +#define __GFP_WAIT ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) +#define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ +#define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ + /* * This may seem redundant, but it's a way of annotating false positives vs. * allocations that simply cannot be supported (e.g. page tables). */ #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK) -#define __GFP_BITS_SHIFT 25 /* Room for N __GFP_FOO bits */ +#define __GFP_BITS_SHIFT 26 /* Room for N __GFP_FOO bits */ #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) -/* This equals 0, but use constants in case they ever change */ -#define GFP_NOWAIT (GFP_ATOMIC & ~__GFP_HIGH) -/* GFP_ATOMIC means both !wait (__GFP_WAIT not set) and use emergency pool */ -#define GFP_ATOMIC (__GFP_HIGH) +/* + * GFP_ATOMIC callers can not sleep, need the allocation to succeed. + * A lower watermark is applied to allow access to "atomic reserves" + */ +#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) +#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) #define GFP_NOIO (__GFP_WAIT) #define GFP_NOFS (__GFP_WAIT | __GFP_IO) #define GFP_KERNEL (__GFP_WAIT | __GFP_IO | __GFP_FS) @@ -119,10 +134,10 @@ struct vm_area_struct; #define GFP_USER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL) #define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) #define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE) -#define GFP_IOFS (__GFP_IO | __GFP_FS) -#define GFP_TRANSHUGE (GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ - __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \ - __GFP_NO_KSWAPD) +#define GFP_IOFS (__GFP_IO | __GFP_FS | __GFP_KSWAPD_RECLAIM) +#define GFP_TRANSHUGE ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ + __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & \ + ~__GFP_KSWAPD_RECLAIM) /* This mask makes up all the page movable related flags */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) @@ -164,6 +179,11 @@ static inline int gfpflags_to_migratetype(const gfp_t gfp_flags) return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } +static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) +{ + return gfp_flags & __GFP_DIRECT_RECLAIM; +} + #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 24f4dfd94c51..4355129fff91 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1224,7 +1224,7 @@ static inline int skb_cloned(const struct sk_buff *skb) static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) { - might_sleep_if(pri & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); @@ -1308,7 +1308,7 @@ static inline int skb_shared(const struct sk_buff *skb) */ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) { - might_sleep_if(pri & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, pri); @@ -1344,7 +1344,7 @@ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) static inline struct sk_buff *skb_unshare(struct sk_buff *skb, gfp_t pri) { - might_sleep_if(pri & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, pri); diff --git a/include/net/sock.h b/include/net/sock.h index f570e75e3da9..bbf7c2cf15b4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2041,7 +2041,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, */ static inline struct page_frag *sk_page_frag(struct sock *sk) { - if (sk->sk_allocation & __GFP_WAIT) + if (gfpflags_allow_blocking(sk->sk_allocation)) return ¤t->task_frag; return &sk->sk_frag; diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h index d6fd8e5b14b7..dde6bf092c8a 100644 --- a/include/trace/events/gfpflags.h +++ b/include/trace/events/gfpflags.h @@ -20,7 +20,7 @@ {(unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \ {(unsigned long)GFP_NOIO, "GFP_NOIO"}, \ {(unsigned long)__GFP_HIGH, "GFP_HIGH"}, \ - {(unsigned long)__GFP_WAIT, "GFP_WAIT"}, \ + {(unsigned long)__GFP_ATOMIC, "GFP_ATOMIC"}, \ {(unsigned long)__GFP_IO, "GFP_IO"}, \ {(unsigned long)__GFP_COLD, "GFP_COLD"}, \ {(unsigned long)__GFP_NOWARN, "GFP_NOWARN"}, \ @@ -36,7 +36,8 @@ {(unsigned long)__GFP_RECLAIMABLE, "GFP_RECLAIMABLE"}, \ {(unsigned long)__GFP_MOVABLE, "GFP_MOVABLE"}, \ {(unsigned long)__GFP_NOTRACK, "GFP_NOTRACK"}, \ - {(unsigned long)__GFP_NO_KSWAPD, "GFP_NO_KSWAPD"}, \ + {(unsigned long)__GFP_DIRECT_RECLAIM, "GFP_DIRECT_RECLAIM"}, \ + {(unsigned long)__GFP_KSWAPD_RECLAIM, "GFP_KSWAPD_RECLAIM"}, \ {(unsigned long)__GFP_OTHER_NODE, "GFP_OTHER_NODE"} \ ) : "GFP_NOWAIT" diff --git a/kernel/audit.c b/kernel/audit.c index 8a056a32ded7..5ffcbd354a52 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1371,16 +1371,16 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, if (unlikely(audit_filter_type(type))) return NULL; - if (gfp_mask & __GFP_WAIT) { + if (gfp_mask & __GFP_DIRECT_RECLAIM) { if (audit_pid && audit_pid == current->pid) - gfp_mask &= ~__GFP_WAIT; + gfp_mask &= ~__GFP_DIRECT_RECLAIM; else reserve = 0; } while (audit_backlog_limit && skb_queue_len(&audit_skb_queue) > audit_backlog_limit + reserve) { - if (gfp_mask & __GFP_WAIT && audit_backlog_wait_time) { + if (gfp_mask & __GFP_DIRECT_RECLAIM && audit_backlog_wait_time) { long sleep_time; sleep_time = timeout_start + audit_backlog_wait_time - jiffies; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index b9d0cce3f9ce..f1603c153890 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -299,7 +299,7 @@ static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end, idr_preload(gfp_mask); spin_lock_bh(&cgroup_idr_lock); - ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_WAIT); + ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_DIRECT_RECLAIM); spin_unlock_bh(&cgroup_idr_lock); idr_preload_end(); return ret; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 4e49cc4c9952..deae3907ac1e 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2738,7 +2738,7 @@ static void __lockdep_trace_alloc(gfp_t gfp_mask, unsigned long flags) return; /* no reclaim without waiting on it */ - if (!(gfp_mask & __GFP_WAIT)) + if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) return; /* this guy won't enter reclaim */ diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 5235dd4e1e2f..3a970604308f 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1779,7 +1779,7 @@ alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem) while (to_alloc-- > 0) { struct page *page; - page = alloc_image_page(__GFP_HIGHMEM); + page = alloc_image_page(__GFP_HIGHMEM|__GFP_KSWAPD_RECLAIM); memory_bm_set_bit(bm, page_to_pfn(page)); } return nr_highmem; diff --git a/kernel/smp.c b/kernel/smp.c index 07854477c164..d903c02223af 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -669,7 +669,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), cpumask_var_t cpus; int cpu, ret; - might_sleep_if(gfp_flags & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(gfp_flags)); if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) { preempt_disable(); diff --git a/lib/idr.c b/lib/idr.c index 5335c43adf46..6098336df267 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -399,7 +399,7 @@ void idr_preload(gfp_t gfp_mask) * allocation guarantee. Disallow usage from those contexts. */ WARN_ON_ONCE(in_interrupt()); - might_sleep_if(gfp_mask & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(gfp_mask)); preempt_disable(); @@ -453,7 +453,7 @@ int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask) struct idr_layer *pa[MAX_IDR_LEVEL + 1]; int id; - might_sleep_if(gfp_mask & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(gfp_mask)); /* sanity checks */ if (WARN_ON_ONCE(start < 0)) diff --git a/lib/radix-tree.c b/lib/radix-tree.c index f9ebe1c82060..fcf5d98574ce 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -188,7 +188,7 @@ radix_tree_node_alloc(struct radix_tree_root *root) * preloading in the interrupt anyway as all the allocations have to * be atomic. So just do normal allocation when in interrupt. */ - if (!(gfp_mask & __GFP_WAIT) && !in_interrupt()) { + if (!gfpflags_allow_blocking(gfp_mask) && !in_interrupt()) { struct radix_tree_preload *rtp; /* @@ -249,7 +249,7 @@ radix_tree_node_free(struct radix_tree_node *node) * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without - * __GFP_WAIT being passed to INIT_RADIX_TREE(). + * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ static int __radix_tree_preload(gfp_t gfp_mask) { @@ -286,12 +286,12 @@ out: * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without - * __GFP_WAIT being passed to INIT_RADIX_TREE(). + * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ int radix_tree_preload(gfp_t gfp_mask) { /* Warn on non-sensical use... */ - WARN_ON_ONCE(!(gfp_mask & __GFP_WAIT)); + WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); return __radix_tree_preload(gfp_mask); } EXPORT_SYMBOL(radix_tree_preload); @@ -303,7 +303,7 @@ EXPORT_SYMBOL(radix_tree_preload); */ int radix_tree_maybe_preload(gfp_t gfp_mask) { - if (gfp_mask & __GFP_WAIT) + if (gfpflags_allow_blocking(gfp_mask)) return __radix_tree_preload(gfp_mask); /* Preloading doesn't help anything with this gfp mask, skip it */ preempt_disable(); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 619984fc07ec..8ed2ffd963c5 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -637,7 +637,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, { struct bdi_writeback *wb; - might_sleep_if(gfp & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(gfp)); if (!memcg_css->parent) return &bdi->wb; diff --git a/mm/dmapool.c b/mm/dmapool.c index 312a716fa14c..57312b5d6e12 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -326,7 +326,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, size_t offset; void *retval; - might_sleep_if(mem_flags & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(mem_flags)); spin_lock_irqsave(&pool->lock, flags); list_for_each_entry(page, &pool->page_list, page_list) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bc502e590366..05374f09339c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2046,7 +2046,7 @@ retry: if (unlikely(task_in_memcg_oom(current))) goto nomem; - if (!(gfp_mask & __GFP_WAIT)) + if (!gfpflags_allow_blocking(gfp_mask)) goto nomem; mem_cgroup_events(mem_over_limit, MEMCG_MAX, 1); @@ -4364,8 +4364,8 @@ static int mem_cgroup_do_precharge(unsigned long count) { int ret; - /* Try a single bulk charge without reclaim first */ - ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_WAIT, count); + /* Try a single bulk charge without reclaim first, kswapd may wake */ + ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_DIRECT_RECLAIM, count); if (!ret) { mc.precharge += count; return ret; diff --git a/mm/mempool.c b/mm/mempool.c index 4c533bc51d73..004d42b1dfaf 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -320,13 +320,13 @@ void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask) gfp_t gfp_temp; VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO); - might_sleep_if(gfp_mask & __GFP_WAIT); + might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM); gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */ gfp_mask |= __GFP_NORETRY; /* don't loop in __alloc_pages */ gfp_mask |= __GFP_NOWARN; /* failures are OK */ - gfp_temp = gfp_mask & ~(__GFP_WAIT|__GFP_IO); + gfp_temp = gfp_mask & ~(__GFP_DIRECT_RECLAIM|__GFP_IO); repeat_alloc: @@ -349,7 +349,7 @@ repeat_alloc: } /* - * We use gfp mask w/o __GFP_WAIT or IO for the first round. If + * We use gfp mask w/o direct reclaim or IO for the first round. If * alloc failed with that and @pool was empty, retry immediately. */ if (gfp_temp != gfp_mask) { @@ -358,8 +358,8 @@ repeat_alloc: goto repeat_alloc; } - /* We must not sleep if !__GFP_WAIT */ - if (!(gfp_mask & __GFP_WAIT)) { + /* We must not sleep if !__GFP_DIRECT_RECLAIM */ + if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) { spin_unlock_irqrestore(&pool->lock, flags); return NULL; } diff --git a/mm/migrate.c b/mm/migrate.c index 2834faba719a..e60379eb23f8 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1578,7 +1578,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page, (GFP_HIGHUSER_MOVABLE | __GFP_THISNODE | __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & - ~GFP_IOFS, 0); + ~(__GFP_IO | __GFP_FS), 0); return newpage; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 67390988881a..70461f3e3378 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -169,12 +169,12 @@ void pm_restrict_gfp_mask(void) WARN_ON(!mutex_is_locked(&pm_mutex)); WARN_ON(saved_gfp_mask); saved_gfp_mask = gfp_allowed_mask; - gfp_allowed_mask &= ~GFP_IOFS; + gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS); } bool pm_suspended_storage(void) { - if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS) + if ((gfp_allowed_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) return false; return true; } @@ -2183,7 +2183,7 @@ static bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) return false; if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) return false; - if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT)) + if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_DIRECT_RECLAIM)) return false; return should_fail(&fail_page_alloc.attr, 1 << order); @@ -2685,7 +2685,7 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...) if (test_thread_flag(TIF_MEMDIE) || (current->flags & (PF_MEMALLOC | PF_EXITING))) filter &= ~SHOW_MEM_FILTER_NODES; - if (in_interrupt() || !(gfp_mask & __GFP_WAIT)) + if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM)) filter &= ~SHOW_MEM_FILTER_NODES; if (fmt) { @@ -2945,7 +2945,6 @@ static inline int gfp_to_alloc_flags(gfp_t gfp_mask) { int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; - const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD)); /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH); @@ -2954,11 +2953,11 @@ gfp_to_alloc_flags(gfp_t gfp_mask) * The caller may dip into page reserves a bit more if the caller * cannot run direct reclaim, or if the caller has realtime scheduling * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will - * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH). + * set both ALLOC_HARDER (__GFP_ATOMIC) and ALLOC_HIGH (__GFP_HIGH). */ alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); - if (atomic) { + if (gfp_mask & __GFP_ATOMIC) { /* * Not worth trying to allocate harder for __GFP_NOMEMALLOC even * if it can't schedule. @@ -2995,11 +2994,16 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask) return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS); } +static inline bool is_thp_gfp_mask(gfp_t gfp_mask) +{ + return (gfp_mask & (GFP_TRANSHUGE | __GFP_KSWAPD_RECLAIM)) == GFP_TRANSHUGE; +} + static inline struct page * __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct alloc_context *ac) { - const gfp_t wait = gfp_mask & __GFP_WAIT; + bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM; struct page *page = NULL; int alloc_flags; unsigned long pages_reclaimed = 0; @@ -3019,16 +3023,24 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, return NULL; } + /* + * We also sanity check to catch abuse of atomic reserves being used by + * callers that are not in atomic context. + */ + if (WARN_ON_ONCE((gfp_mask & (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)) == + (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM))) + gfp_mask &= ~__GFP_ATOMIC; + /* * If this allocation cannot block and it is for a specific node, then * fail early. There's no need to wakeup kswapd or retry for a * speculative node-specific allocation. */ - if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !wait) + if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !can_direct_reclaim) goto nopage; retry: - if (!(gfp_mask & __GFP_NO_KSWAPD)) + if (gfp_mask & __GFP_KSWAPD_RECLAIM) wake_all_kswapds(order, ac); /* @@ -3071,8 +3083,8 @@ retry: } } - /* Atomic allocations - we can't balance anything */ - if (!wait) { + /* Caller is not willing to reclaim, we can't balance anything */ + if (!can_direct_reclaim) { /* * All existing users of the deprecated __GFP_NOFAIL are * blockable, so warn of any new users that actually allow this @@ -3102,7 +3114,7 @@ retry: goto got_pg; /* Checks for THP-specific high-order allocations */ - if ((gfp_mask & GFP_TRANSHUGE) == GFP_TRANSHUGE) { + if (is_thp_gfp_mask(gfp_mask)) { /* * If compaction is deferred for high-order allocations, it is * because sync compaction recently failed. If this is the case @@ -3137,8 +3149,7 @@ retry: * fault, so use asynchronous memory compaction for THP unless it is * khugepaged trying to collapse. */ - if ((gfp_mask & GFP_TRANSHUGE) != GFP_TRANSHUGE || - (current->flags & PF_KTHREAD)) + if (!is_thp_gfp_mask(gfp_mask) || (current->flags & PF_KTHREAD)) migration_mode = MIGRATE_SYNC_LIGHT; /* Try direct reclaim and then allocating */ @@ -3209,7 +3220,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, lockdep_trace_alloc(gfp_mask); - might_sleep_if(gfp_mask & __GFP_WAIT); + might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM); if (should_fail_alloc_page(gfp_mask, order)) return NULL; diff --git a/mm/slab.c b/mm/slab.c index 272e809404d5..a9ef77d19a9a 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1031,12 +1031,12 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) } /* - * Construct gfp mask to allocate from a specific node but do not invoke reclaim - * or warn about failures. + * Construct gfp mask to allocate from a specific node but do not direct reclaim + * or warn about failures. kswapd may still wake to reclaim in the background. */ static inline gfp_t gfp_exact_node(gfp_t flags) { - return (flags | __GFP_THISNODE | __GFP_NOWARN) & ~__GFP_WAIT; + return (flags | __GFP_THISNODE | __GFP_NOWARN) & ~__GFP_DIRECT_RECLAIM; } #endif @@ -2633,7 +2633,7 @@ static int cache_grow(struct kmem_cache *cachep, offset *= cachep->colour_off; - if (local_flags & __GFP_WAIT) + if (gfpflags_allow_blocking(local_flags)) local_irq_enable(); /* @@ -2663,7 +2663,7 @@ static int cache_grow(struct kmem_cache *cachep, cache_init_objs(cachep, page); - if (local_flags & __GFP_WAIT) + if (gfpflags_allow_blocking(local_flags)) local_irq_disable(); check_irq_off(); spin_lock(&n->list_lock); @@ -2677,7 +2677,7 @@ static int cache_grow(struct kmem_cache *cachep, opps1: kmem_freepages(cachep, page); failed: - if (local_flags & __GFP_WAIT) + if (gfpflags_allow_blocking(local_flags)) local_irq_disable(); return 0; } @@ -2869,7 +2869,7 @@ force_grow: static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep, gfp_t flags) { - might_sleep_if(flags & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(flags)); #if DEBUG kmem_flagcheck(cachep, flags); #endif @@ -3057,11 +3057,11 @@ retry: */ struct page *page; - if (local_flags & __GFP_WAIT) + if (gfpflags_allow_blocking(local_flags)) local_irq_enable(); kmem_flagcheck(cache, flags); page = kmem_getpages(cache, local_flags, numa_mem_id()); - if (local_flags & __GFP_WAIT) + if (gfpflags_allow_blocking(local_flags)) local_irq_disable(); if (page) { /* diff --git a/mm/slub.c b/mm/slub.c index 75a5fa92ac2a..97695622a858 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1265,7 +1265,7 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, { flags &= gfp_allowed_mask; lockdep_trace_alloc(flags); - might_sleep_if(flags & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(flags)); if (should_failslab(s->object_size, flags, s->flags)) return NULL; @@ -1353,7 +1353,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) flags &= gfp_allowed_mask; - if (flags & __GFP_WAIT) + if (gfpflags_allow_blocking(flags)) local_irq_enable(); flags |= s->allocflags; @@ -1363,8 +1363,8 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) * so we fall-back to the minimum order allocation. */ alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL; - if ((alloc_gfp & __GFP_WAIT) && oo_order(oo) > oo_order(s->min)) - alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~__GFP_WAIT; + if ((alloc_gfp & __GFP_DIRECT_RECLAIM) && oo_order(oo) > oo_order(s->min)) + alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~__GFP_DIRECT_RECLAIM; page = alloc_slab_page(s, alloc_gfp, node, oo); if (unlikely(!page)) { @@ -1424,7 +1424,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) page->frozen = 1; out: - if (flags & __GFP_WAIT) + if (gfpflags_allow_blocking(flags)) local_irq_disable(); if (!page) return NULL; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 9db9ef5e8481..7ee94dc10000 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1617,7 +1617,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, goto fail; } area->pages[i] = page; - if (gfp_mask & __GFP_WAIT) + if (gfpflags_allow_blocking(gfp_mask)) cond_resched(); } diff --git a/mm/vmscan.c b/mm/vmscan.c index e0cd7eed4e38..2aec4241b42a 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1476,7 +1476,7 @@ static int too_many_isolated(struct zone *zone, int file, * won't get blocked by normal direct-reclaimers, forming a circular * deadlock. */ - if ((sc->gfp_mask & GFP_IOFS) == GFP_IOFS) + if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) inactive >>= 3; return isolated > inactive; @@ -3791,7 +3791,7 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) /* * Do not scan if the allocation should not be delayed. */ - if (!(gfp_mask & __GFP_WAIT) || (current->flags & PF_MEMALLOC)) + if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC)) return ZONE_RECLAIM_NOSCAN; /* diff --git a/mm/zswap.c b/mm/zswap.c index 4043df7c672f..e54166d3732e 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -571,7 +571,7 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor) static struct zswap_pool *zswap_pool_create(char *type, char *compressor) { struct zswap_pool *pool; - gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN; + gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; pool = kzalloc(sizeof(*pool), GFP_KERNEL); if (!pool) { @@ -1011,7 +1011,8 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, /* store */ len = dlen + sizeof(struct zswap_header); ret = zpool_malloc(entry->pool->zpool, len, - __GFP_NORETRY | __GFP_NOWARN, &handle); + __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM, + &handle); if (ret == -ENOSPC) { zswap_reject_compress_poor++; goto put_dstmem; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index fab4599ba8b2..aa41e6dd6429 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -414,7 +414,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, len += NET_SKB_PAD; if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) || - (gfp_mask & (__GFP_WAIT | GFP_DMA))) { + (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); if (!skb) goto skb_fail; @@ -481,7 +481,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, len += NET_SKB_PAD + NET_IP_ALIGN; if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) || - (gfp_mask & (__GFP_WAIT | GFP_DMA))) { + (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); if (!skb) goto skb_fail; @@ -4452,7 +4452,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, return NULL; gfp_head = gfp_mask; - if (gfp_head & __GFP_WAIT) + if (gfp_head & __GFP_DIRECT_RECLAIM) gfp_head |= __GFP_REPEAT; *errcode = -ENOBUFS; @@ -4467,7 +4467,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, while (order) { if (npages >= 1 << order) { - page = alloc_pages((gfp_mask & ~__GFP_WAIT) | + page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY, diff --git a/net/core/sock.c b/net/core/sock.c index 7529eb9463be..1e4dd54bfb5a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1944,8 +1944,10 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp) pfrag->offset = 0; if (SKB_FRAG_PAGE_ORDER) { - pfrag->page = alloc_pages((gfp & ~__GFP_WAIT) | __GFP_COMP | - __GFP_NOWARN | __GFP_NORETRY, + /* Avoid direct reclaim but allow kswapd to wake */ + pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | + __GFP_COMP | __GFP_NOWARN | + __GFP_NORETRY, SKB_FRAG_PAGE_ORDER); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index fafe33bdb619..59651af8cc27 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2116,7 +2116,7 @@ int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid consume_skb(info.skb2); if (info.delivered) { - if (info.congested && (allocation & __GFP_WAIT)) + if (info.congested && gfpflags_allow_blocking(allocation)) yield(); return 0; } diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 96744b75db93..977fb86065b7 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -305,7 +305,7 @@ static int rds_ib_recv_refill_one(struct rds_connection *conn, gfp_t slab_mask = GFP_NOWAIT; gfp_t page_mask = GFP_NOWAIT; - if (gfp & __GFP_WAIT) { + if (gfp & __GFP_DIRECT_RECLAIM) { slab_mask = GFP_KERNEL; page_mask = GFP_HIGHUSER; } @@ -379,7 +379,7 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) struct ib_recv_wr *failed_wr; unsigned int posted = 0; int ret = 0; - bool can_wait = !!(gfp & __GFP_WAIT); + bool can_wait = !!(gfp & __GFP_DIRECT_RECLAIM); u32 pos; /* the goal here is to just make sure that someone, somewhere diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c index 692b3e67fb54..6c71ed1caf16 100644 --- a/net/rxrpc/ar-connection.c +++ b/net/rxrpc/ar-connection.c @@ -500,7 +500,7 @@ int rxrpc_connect_call(struct rxrpc_sock *rx, if (bundle->num_conns >= 20) { _debug("too many conns"); - if (!(gfp & __GFP_WAIT)) { + if (!gfpflags_allow_blocking(gfp)) { _leave(" = -EAGAIN"); return -EAGAIN; } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index b00f1f9611d6..559afd0ee7de 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1590,7 +1590,7 @@ int sctp_assoc_lookup_laddr(struct sctp_association *asoc, /* Set an association id for a given association */ int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp) { - bool preload = !!(gfp & __GFP_WAIT); + bool preload = gfpflags_allow_blocking(gfp); int ret; /* If the id is already assigned, keep it. */ -- cgit v1.2.3