From: Keith Busch <kbusch@xxxxxxxxxx> Batched completions can clear multiple bits, but we're only decrementing the wait_cnt by one each time. This can cause waiters to never be woken, stalling IO. Use the batched count instead. Link: https://bugzilla.kernel.org/show_bug.cgi?id=215679 Signed-off-by: Keith Busch <kbusch@xxxxxxxxxx> --- v1->v2: Use atomic_try_cmpxchg instead of direct subtraction to prevent a race between two batched completions. Remove 'wait_cnt < 0' condition since it's not possible anymore. Repeat wake up while waiters exist and more bits are unaccounted. block/blk-mq-tag.c | 2 +- include/linux/sbitmap.h | 3 ++- lib/sbitmap.c | 32 ++++++++++++++++++-------------- 3 files changed, 21 insertions(+), 16 deletions(-) diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 8e3b36d1cb57..9eb968e14d31 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -196,7 +196,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) * other allocations on previous queue won't be starved. */ if (bt != bt_prev) - sbitmap_queue_wake_up(bt_prev); + sbitmap_queue_wake_up(bt_prev, 1); ws = bt_wait_ptr(bt, data->hctx); } while (1); diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 8f5a86e210b9..4d2d5205ab58 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -575,8 +575,9 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq); * sbitmap_queue_wake_up() - Wake up some of waiters in one waitqueue * on a &struct sbitmap_queue. * @sbq: Bitmap queue to wake up. + * @nr: Number of bits cleared. */ -void sbitmap_queue_wake_up(struct sbitmap_queue *sbq); +void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr); /** * sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 1f31147872e6..6fd3bc22c2e7 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -600,28 +600,33 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq) return NULL; } -static bool __sbq_wake_up(struct sbitmap_queue *sbq) +static bool __sbq_wake_up(struct sbitmap_queue *sbq, int *nr) { struct sbq_wait_state *ws; - unsigned int wake_batch; - int wait_cnt; + int wake_batch, wait_cnt, sub, cur; ws = sbq_wake_ptr(sbq); if (!ws) return false; - wait_cnt = atomic_dec_return(&ws->wait_cnt); + wake_batch = READ_ONCE(sbq->wake_batch); + do { + cur = atomic_read(&ws->wait_cnt); + sub = min3(wake_batch, *nr, cur); + wait_cnt = cur - sub; + } while (!atomic_try_cmpxchg(&ws->wait_cnt, &cur, wait_cnt)); + + *nr -= sub; + /* * For concurrent callers of this, callers should call this function * again to wakeup a new batch on a different 'ws'. */ - if (wait_cnt < 0 || !waitqueue_active(&ws->wait)) + if (!waitqueue_active(&ws->wait)) return true; if (wait_cnt > 0) - return false; - - wake_batch = READ_ONCE(sbq->wake_batch); + return *nr > 0; /* * Wake up first in case that concurrent callers decrease wait_cnt @@ -649,15 +654,14 @@ static bool __sbq_wake_up(struct sbitmap_queue *sbq) sbq_index_atomic_inc(&sbq->wake_index); atomic_set(&ws->wait_cnt, wake_batch); - return false; + return *nr > 0; } -void sbitmap_queue_wake_up(struct sbitmap_queue *sbq) +void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr) { - while (__sbq_wake_up(sbq)) + while (__sbq_wake_up(sbq, &nr)) ; } -EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up); static inline void sbitmap_update_cpu_hint(struct sbitmap *sb, int cpu, int tag) { @@ -694,7 +698,7 @@ void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset, atomic_long_andnot(mask, (atomic_long_t *) addr); smp_mb__after_atomic(); - sbitmap_queue_wake_up(sbq); + sbitmap_queue_wake_up(sbq, nr_tags); sbitmap_update_cpu_hint(&sbq->sb, raw_smp_processor_id(), tags[nr_tags - 1] - offset); } @@ -722,7 +726,7 @@ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, * waiter. See the comment on waitqueue_active(). */ smp_mb__after_atomic(); - sbitmap_queue_wake_up(sbq); + sbitmap_queue_wake_up(sbq, 1); sbitmap_update_cpu_hint(&sbq->sb, cpu, nr); } EXPORT_SYMBOL_GPL(sbitmap_queue_clear); -- 2.30.2
