diff options
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/div64.c | 19 | ||||
| -rw-r--r-- | lib/kobject.c | 2 | ||||
| -rw-r--r-- | lib/lru_cache.c | 56 | ||||
| -rw-r--r-- | lib/oid_registry.c | 5 | ||||
| -rw-r--r-- | lib/rwsem-spinlock.c | 38 | ||||
| -rw-r--r-- | lib/rwsem.c | 242 | ||||
| -rw-r--r-- | lib/scatterlist.c | 4 |
7 files changed, 193 insertions, 173 deletions
diff --git a/lib/div64.c b/lib/div64.c index 3af5728d95fd..a163b6caef73 100644 --- a/lib/div64.c +++ b/lib/div64.c @@ -79,10 +79,9 @@ EXPORT_SYMBOL(div_s64_rem); #endif /** - * div64_u64_rem - unsigned 64bit divide with 64bit divisor and 64bit remainder + * div64_u64 - unsigned 64bit divide with 64bit divisor * @dividend: 64bit dividend * @divisor: 64bit divisor - * @remainder: 64bit remainder * * This implementation is a modified version of the algorithm proposed * by the book 'Hacker's Delight'. The original source and full proof @@ -90,33 +89,27 @@ EXPORT_SYMBOL(div_s64_rem); * * 'http://www.hackersdelight.org/HDcode/newCode/divDouble.c.txt' */ -#ifndef div64_u64_rem -u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder) +#ifndef div64_u64 +u64 div64_u64(u64 dividend, u64 divisor) { u32 high = divisor >> 32; u64 quot; if (high == 0) { - u32 rem32; - quot = div_u64_rem(dividend, divisor, &rem32); - *remainder = rem32; + quot = div_u64(dividend, divisor); } else { int n = 1 + fls(high); quot = div_u64(dividend >> n, divisor >> n); if (quot != 0) quot--; - - *remainder = dividend - quot * divisor; - if (*remainder >= divisor) { + if ((dividend - quot * divisor) >= divisor) quot++; - *remainder -= divisor; - } } return quot; } -EXPORT_SYMBOL(div64_u64_rem); +EXPORT_SYMBOL(div64_u64); #endif /** diff --git a/lib/kobject.c b/lib/kobject.c index a65486613d79..b7e29a6056d3 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -529,7 +529,7 @@ struct kobject *kobject_get(struct kobject *kobj) return kobj; } -static struct kobject *kobject_get_unless_zero(struct kobject *kobj) +static struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj) { if (!kref_get_unless_zero(&kobj->kref)) kobj = NULL; diff --git a/lib/lru_cache.c b/lib/lru_cache.c index 8335d39d2ccd..4a83ecd03650 100644 --- a/lib/lru_cache.c +++ b/lib/lru_cache.c @@ -365,7 +365,13 @@ static int lc_unused_element_available(struct lru_cache *lc) return 0; } -static struct lc_element *__lc_get(struct lru_cache *lc, unsigned int enr, bool may_change) +/* used as internal flags to __lc_get */ +enum { + LC_GET_MAY_CHANGE = 1, + LC_GET_MAY_USE_UNCOMMITTED = 2, +}; + +static struct lc_element *__lc_get(struct lru_cache *lc, unsigned int enr, unsigned int flags) { struct lc_element *e; @@ -380,22 +386,31 @@ static struct lc_element *__lc_get(struct lru_cache *lc, unsigned int enr, bool * this enr is currently being pulled in already, * and will be available once the pending transaction * has been committed. */ - if (e && e->lc_new_number == e->lc_number) { + if (e) { + if (e->lc_new_number != e->lc_number) { + /* It has been found above, but on the "to_be_changed" + * list, not yet committed. Don't pull it in twice, + * wait for the transaction, then try again... + */ + if (!(flags & LC_GET_MAY_USE_UNCOMMITTED)) + RETURN(NULL); + /* ... unless the caller is aware of the implications, + * probably preparing a cumulative transaction. */ + ++e->refcnt; + ++lc->hits; + RETURN(e); + } + /* else: lc_new_number == lc_number; a real hit. */ ++lc->hits; if (e->refcnt++ == 0) lc->used++; list_move(&e->list, &lc->in_use); /* Not evictable... */ RETURN(e); } + /* e == NULL */ ++lc->misses; - if (!may_change) - RETURN(NULL); - - /* It has been found above, but on the "to_be_changed" list, not yet - * committed. Don't pull it in twice, wait for the transaction, then - * try again */ - if (e) + if (!(flags & LC_GET_MAY_CHANGE)) RETURN(NULL); /* To avoid races with lc_try_lock(), first, mark us dirty @@ -477,7 +492,27 @@ static struct lc_element *__lc_get(struct lru_cache *lc, unsigned int enr, bool */ struct lc_element *lc_get(struct lru_cache *lc, unsigned int enr) { - return __lc_get(lc, enr, 1); + return __lc_get(lc, enr, LC_GET_MAY_CHANGE); +} + +/** + * lc_get_cumulative - like lc_get; also finds to-be-changed elements + * @lc: the lru cache to operate on + * @enr: the label to look up + * + * Unlike lc_get this also returns the element for @enr, if it is belonging to + * a pending transaction, so the return values are like for lc_get(), + * plus: + * + * pointer to an element already on the "to_be_changed" list. + * In this case, the cache was already marked %LC_DIRTY. + * + * Caller needs to make sure that the pending transaction is completed, + * before proceeding to actually use this element. + */ +struct lc_element *lc_get_cumulative(struct lru_cache *lc, unsigned int enr) +{ + return __lc_get(lc, enr, LC_GET_MAY_CHANGE|LC_GET_MAY_USE_UNCOMMITTED); } /** @@ -648,3 +683,4 @@ EXPORT_SYMBOL(lc_seq_printf_stats); EXPORT_SYMBOL(lc_seq_dump_details); EXPORT_SYMBOL(lc_try_lock); EXPORT_SYMBOL(lc_is_used); +EXPORT_SYMBOL(lc_get_cumulative); diff --git a/lib/oid_registry.c b/lib/oid_registry.c index d8de11f45908..318f382a010d 100644 --- a/lib/oid_registry.c +++ b/lib/oid_registry.c @@ -9,6 +9,7 @@ * 2 of the Licence, or (at your option) any later version. */ +#include <linux/module.h> #include <linux/export.h> #include <linux/oid_registry.h> #include <linux/kernel.h> @@ -16,6 +17,10 @@ #include <linux/bug.h> #include "oid_registry_data.c" +MODULE_DESCRIPTION("OID Registry"); +MODULE_AUTHOR("Red Hat, Inc."); +MODULE_LICENSE("GPL"); + /** * look_up_OID - Find an OID registration for the specified data * @data: Binary representation of the OID diff --git a/lib/rwsem-spinlock.c b/lib/rwsem-spinlock.c index 7542afbb22b3..9be8a9144978 100644 --- a/lib/rwsem-spinlock.c +++ b/lib/rwsem-spinlock.c @@ -9,12 +9,15 @@ #include <linux/sched.h> #include <linux/export.h> +enum rwsem_waiter_type { + RWSEM_WAITING_FOR_WRITE, + RWSEM_WAITING_FOR_READ +}; + struct rwsem_waiter { struct list_head list; struct task_struct *task; - unsigned int flags; -#define RWSEM_WAITING_FOR_READ 0x00000001 -#define RWSEM_WAITING_FOR_WRITE 0x00000002 + enum rwsem_waiter_type type; }; int rwsem_is_locked(struct rw_semaphore *sem) @@ -67,26 +70,17 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wakewrite) waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); - if (!wakewrite) { - if (waiter->flags & RWSEM_WAITING_FOR_WRITE) - goto out; - goto dont_wake_writers; - } - - /* - * as we support write lock stealing, we can't set sem->activity - * to -1 here to indicate we get the lock. Instead, we wake it up - * to let it go get it again. - */ - if (waiter->flags & RWSEM_WAITING_FOR_WRITE) { - wake_up_process(waiter->task); + if (waiter->type == RWSEM_WAITING_FOR_WRITE) { + if (wakewrite) + /* Wake up a writer. Note that we do not grant it the + * lock - it will have to acquire it when it runs. */ + wake_up_process(waiter->task); goto out; } /* grant an infinite number of read locks to the front of the queue */ - dont_wake_writers: woken = 0; - while (waiter->flags & RWSEM_WAITING_FOR_READ) { + do { struct list_head *next = waiter->list.next; list_del(&waiter->list); @@ -96,10 +90,10 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wakewrite) wake_up_process(tsk); put_task_struct(tsk); woken++; - if (list_empty(&sem->wait_list)) + if (next == &sem->wait_list) break; waiter = list_entry(next, struct rwsem_waiter, list); - } + } while (waiter->type != RWSEM_WAITING_FOR_WRITE); sem->activity += woken; @@ -144,7 +138,7 @@ void __sched __down_read(struct rw_semaphore *sem) /* set up my own style of waitqueue */ waiter.task = tsk; - waiter.flags = RWSEM_WAITING_FOR_READ; + waiter.type = RWSEM_WAITING_FOR_READ; get_task_struct(tsk); list_add_tail(&waiter.list, &sem->wait_list); @@ -201,7 +195,7 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass) /* set up my own style of waitqueue */ tsk = current; waiter.task = tsk; - waiter.flags = RWSEM_WAITING_FOR_WRITE; + waiter.type = RWSEM_WAITING_FOR_WRITE; list_add_tail(&waiter.list, &sem->wait_list); /* wait for someone to release the lock */ diff --git a/lib/rwsem.c b/lib/rwsem.c index ad5e0df16ab4..19c5fa95e0b4 100644 --- a/lib/rwsem.c +++ b/lib/rwsem.c @@ -4,6 +4,7 @@ * Derived from arch/i386/kernel/semaphore.c * * Writer lock-stealing by Alex Shi <alex.shi@intel.com> + * and Michel Lespinasse <walken@google.com> */ #include <linux/rwsem.h> #include <linux/sched.h> @@ -30,21 +31,22 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name, EXPORT_SYMBOL(__init_rwsem); +enum rwsem_waiter_type { + RWSEM_WAITING_FOR_WRITE, + RWSEM_WAITING_FOR_READ +}; + struct rwsem_waiter { struct list_head list; struct task_struct *task; - unsigned int flags; -#define RWSEM_WAITING_FOR_READ 0x00000001 -#define RWSEM_WAITING_FOR_WRITE 0x00000002 + enum rwsem_waiter_type type; }; -/* Wake types for __rwsem_do_wake(). Note that RWSEM_WAKE_NO_ACTIVE and - * RWSEM_WAKE_READ_OWNED imply that the spinlock must have been kept held - * since the rwsem value was observed. - */ -#define RWSEM_WAKE_ANY 0 /* Wake whatever's at head of wait list */ -#define RWSEM_WAKE_NO_ACTIVE 1 /* rwsem was observed with no active thread */ -#define RWSEM_WAKE_READ_OWNED 2 /* rwsem was observed to be read owned */ +enum rwsem_wake_type { + RWSEM_WAKE_ANY, /* Wake whatever's at head of wait list */ + RWSEM_WAKE_READERS, /* Wake readers only */ + RWSEM_WAKE_READ_OWNED /* Waker thread holds the read lock */ +}; /* * handle the lock release when processes blocked on it that can now run @@ -57,46 +59,43 @@ struct rwsem_waiter { * - writers are only woken if downgrading is false */ static struct rw_semaphore * -__rwsem_do_wake(struct rw_semaphore *sem, int wake_type) +__rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type) { struct rwsem_waiter *waiter; struct task_struct *tsk; struct list_head *next; - signed long woken, loop, adjustment; + long oldcount, woken, loop, adjustment; waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); - if (!(waiter->flags & RWSEM_WAITING_FOR_WRITE)) - goto readers_only; - - if (wake_type == RWSEM_WAKE_READ_OWNED) - /* Another active reader was observed, so wakeup is not - * likely to succeed. Save the atomic op. - */ + if (waiter->type == RWSEM_WAITING_FOR_WRITE) { + if (wake_type == RWSEM_WAKE_ANY) + /* Wake writer at the front of the queue, but do not + * grant it the lock yet as we want other writers + * to be able to steal it. Readers, on the other hand, + * will block as they will notice the queued writer. + */ + wake_up_process(waiter->task); goto out; + } - /* Wake up the writing waiter and let the task grab the sem: */ - wake_up_process(waiter->task); - goto out; - - readers_only: - /* If we come here from up_xxxx(), another thread might have reached - * rwsem_down_failed_common() before we acquired the spinlock and - * woken up a waiter, making it now active. We prefer to check for - * this first in order to not spend too much time with the spinlock - * held if we're not going to be able to wake up readers in the end. - * - * Note that we do not need to update the rwsem count: any writer - * trying to acquire rwsem will run rwsem_down_write_failed() due - * to the waiting threads and block trying to acquire the spinlock. - * - * We use a dummy atomic update in order to acquire the cache line - * exclusively since we expect to succeed and run the final rwsem - * count adjustment pretty soon. + /* Writers might steal the lock before we grant it to the next reader. + * We prefer to do the first reader grant before counting readers + * so we can bail out early if a writer stole the lock. */ - if (wake_type == RWSEM_WAKE_ANY && - rwsem_atomic_update(0, sem) < RWSEM_WAITING_BIAS) - /* Someone grabbed the sem for write already */ - goto out; + adjustment = 0; + if (wake_type != RWSEM_WAKE_READ_OWNED) { + adjustment = RWSEM_ACTIVE_READ_BIAS; + try_reader_grant: + oldcount = rwsem_atomic_update(adjustment, sem) - adjustment; + if (unlikely(oldcount < RWSEM_WAITING_BIAS)) { + /* A writer stole the lock. Undo our reader grant. */ + if (rwsem_atomic_update(-adjustment, sem) & + RWSEM_ACTIVE_MASK) + goto out; + /* Last active locker left. Retry waking readers. */ + goto try_reader_grant; + } + } /* Grant an infinite number of read locks to the readers at the front * of the queue. Note we increment the 'active part' of the count by @@ -112,17 +111,19 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wake_type) waiter = list_entry(waiter->list.next, struct rwsem_waiter, list); - } while (waiter->flags & RWSEM_WAITING_FOR_READ); + } while (waiter->type != RWSEM_WAITING_FOR_WRITE); - adjustment = woken * RWSEM_ACTIVE_READ_BIAS; - if (waiter->flags & RWSEM_WAITING_FOR_READ) + adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment; + if (waiter->type != RWSEM_WAITING_FOR_WRITE) /* hit end of list above */ adjustment -= RWSEM_WAITING_BIAS; - rwsem_atomic_add(adjustment, sem); + if (adjustment) + rwsem_atomic_add(adjustment, sem); next = sem->wait_list.next; - for (loop = woken; loop > 0; loop--) { + loop = woken; + do { waiter = list_entry(next, struct rwsem_waiter, list); next = waiter->list.next; tsk = waiter->task; @@ -130,7 +131,7 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wake_type) waiter->task = NULL; wake_up_process(tsk); put_task_struct(tsk); - } + } while (--loop); sem->wait_list.next = next; next->prev = &sem->wait_list; @@ -139,60 +140,21 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wake_type) return sem; } -/* Try to get write sem, caller holds sem->wait_lock: */ -static int try_get_writer_sem(struct rw_semaphore *sem, - struct rwsem_waiter *waiter) -{ - struct rwsem_waiter *fwaiter; - long oldcount, adjustment; - - /* only steal when first waiter is writing */ - fwaiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); - if (!(fwaiter->flags & RWSEM_WAITING_FOR_WRITE)) - return 0; - - adjustment = RWSEM_ACTIVE_WRITE_BIAS; - /* Only one waiter in the queue: */ - if (fwaiter == waiter && waiter->list.next == &sem->wait_list) - adjustment -= RWSEM_WAITING_BIAS; - -try_again_write: - oldcount = rwsem_atomic_update(adjustment, sem) - adjustment; - if (!(oldcount & RWSEM_ACTIVE_MASK)) { - /* No active lock: */ - struct task_struct *tsk = waiter->task; - - list_del(&waiter->list); - smp_mb(); - put_task_struct(tsk); - tsk->state = TASK_RUNNING; - return 1; - } - /* some one grabbed the sem already */ - if (rwsem_atomic_update(-adjustment, sem) & RWSEM_ACTIVE_MASK) - return 0; - goto try_again_write; -} - /* - * wait for a lock to be granted + * wait for the read lock to be granted */ -static struct rw_semaphore __sched * -rwsem_down_failed_common(struct rw_semaphore *sem, - unsigned int flags, signed long adjustment) +struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) { + long count, adjustment = -RWSEM_ACTIVE_READ_BIAS; struct rwsem_waiter waiter; struct task_struct *tsk = current; - signed long count; - - set_task_state(tsk, TASK_UNINTERRUPTIBLE); /* set up my own style of waitqueue */ - raw_spin_lock_irq(&sem->wait_lock); waiter.task = tsk; - waiter.flags = flags; + waiter.type = RWSEM_WAITING_FOR_READ; get_task_struct(tsk); + raw_spin_lock_irq(&sem->wait_lock); if (list_empty(&sem->wait_list)) adjustment += RWSEM_WAITING_BIAS; list_add_tail(&waiter.list, &sem->wait_list); @@ -200,35 +162,24 @@ rwsem_down_failed_common(struct rw_semaphore *sem, /* we're now waiting on the lock, but no longer actively locking */ count = rwsem_atomic_update(adjustment, sem); - /* If there are no active locks, wake the front queued process(es) up. + /* If there are no active locks, wake the front queued process(es). * - * Alternatively, if we're called from a failed down_write(), there - * were already threads queued before us and there are no active - * writers, the lock must be read owned; so we try to wake any read - * locks that were queued ahead of us. */ - if (count == RWSEM_WAITING_BIAS) - sem = __rwsem_do_wake(sem, RWSEM_WAKE_NO_ACTIVE); - else if (count > RWSEM_WAITING_BIAS && - adjustment == -RWSEM_ACTIVE_WRITE_BIAS) - sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED); + * If there are no writers and we are first in the queue, + * wake our own waiter to join the existing active readers ! + */ + if (count == RWSEM_WAITING_BIAS || + (count > RWSEM_WAITING_BIAS && + adjustment != -RWSEM_ACTIVE_READ_BIAS)) + sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY); raw_spin_unlock_irq(&sem->wait_lock); /* wait to be given the lock */ - for (;;) { + while (true) { + set_task_state(tsk, TASK_UNINTERRUPTIBLE); if (!waiter.task) break; - - raw_spin_lock_irq(&sem->wait_lock); - /* Try to get the writer sem, may steal from the head writer: */ - if (flags == RWSEM_WAITING_FOR_WRITE) - if (try_get_writer_sem(sem, &waiter)) { - raw_spin_unlock_irq(&sem->wait_lock); - return sem; - } - raw_spin_unlock_irq(&sem->wait_lock); schedule(); - set_task_state(tsk, TASK_UNINTERRUPTIBLE); } tsk->state = TASK_RUNNING; @@ -237,21 +188,64 @@ rwsem_down_failed_common(struct rw_semaphore *sem, } /* - * wait for the read lock to be granted - */ -struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) -{ - return rwsem_down_failed_common(sem, RWSEM_WAITING_FOR_READ, - -RWSEM_ACTIVE_READ_BIAS); -} - -/* - * wait for the write lock to be granted + * wait until we successfully acquire the write lock */ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) { - return rwsem_down_failed_common(sem, RWSEM_WAITING_FOR_WRITE, - -RWSEM_ACTIVE_WRITE_BIAS); + long count, adjustment = -RWSEM_ACTIVE_WRITE_BIAS; + struct rwsem_waiter waiter; + struct task_struct *tsk = current; + + /* set up my own style of waitqueue */ + waiter.task = tsk; + waiter.type = RWSEM_WAITING_FOR_WRITE; + + raw_spin_lock_irq(&sem->wait_lock); + if (list_empty(&sem->wait_list)) + adjustment += RWSEM_WAITING_BIAS; + list_add_tail(&waiter.list, &sem->wait_list); + + /* we're now waiting on the lock, but no longer actively locking */ + count = rwsem_atomic_update(adjustment, sem); + + /* If there were already threads queued before us and there are no + * active writers, the lock must be read owned; so we try to wake + * any read locks that were queued ahead of us. */ + if (count > RWSEM_WAITING_BIAS && + adjustment == -RWSEM_ACTIVE_WRITE_BIAS) + sem = __rwsem_do_wake(sem, RWSEM_WAKE_READERS); + + /* wait until we successfully acquire the lock */ + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + while (true) { + if (!(count & RWSEM_ACTIVE_MASK)) { + /* Try acquiring the write lock. */ + count = RWSEM_ACTIVE_WRITE_BIAS; + if (!list_is_singular(&sem->wait_list)) + count += RWSEM_WAITING_BIAS; + + if (sem->count == RWSEM_WAITING_BIAS && + cmpxchg(&sem->count, RWSEM_WAITING_BIAS, count) == + RWSEM_WAITING_BIAS) + break; + } + + raw_spin_unlock_irq(&sem->wait_lock); + + /* Block until there are no active lockers. */ + do { + schedule(); + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + } while ((count = sem->count) & RWSEM_ACTIVE_MASK); + + raw_spin_lock_irq(&sem->wait_lock); + } + + list_del(&waiter.list); + raw_spin_unlock_irq(&sem->wait_lock); + tsk->state = TASK_RUNNING; + + return sem; } /* diff --git a/lib/scatterlist.c b/lib/scatterlist.c index b83c144d731f..a1cf8cae60e7 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -401,7 +401,6 @@ void __sg_page_iter_start(struct sg_page_iter *piter, piter->__pg_advance = 0; piter->__nents = nents; - piter->page = NULL; piter->sg = sglist; piter->sg_pgoffset = pgoffset; } @@ -426,7 +425,6 @@ bool __sg_page_iter_next(struct sg_page_iter *piter) if (!--piter->__nents || !piter->sg) return false; } - piter->page = nth_page(sg_page(piter->sg), piter->sg_pgoffset); return true; } @@ -496,7 +494,7 @@ bool sg_miter_next(struct sg_mapping_iter *miter) miter->__remaining = min_t(unsigned long, miter->__remaining, PAGE_SIZE - miter->__offset); } - miter->page = miter->piter.page; + miter->page = sg_page_iter_page(&miter->piter); miter->consumed = miter->length = miter->__remaining; if (miter->__flags & SG_MITER_ATOMIC) |