fd2ef39cc9
Lockdep complains about lock inversion between ioc->lock and bfqd->lock:
bfqd -> ioc:
put_io_context+0x33/0x90 -> ioc->lock grabbed
blk_mq_free_request+0x51/0x140
blk_put_request+0xe/0x10
blk_attempt_req_merge+0x1d/0x30
elv_attempt_insert_merge+0x56/0xa0
blk_mq_sched_try_insert_merge+0x4b/0x60
bfq_insert_requests+0x9e/0x18c0 -> bfqd->lock grabbed
blk_mq_sched_insert_requests+0xd6/0x2b0
blk_mq_flush_plug_list+0x154/0x280
blk_finish_plug+0x40/0x60
ext4_writepages+0x696/0x1320
do_writepages+0x1c/0x80
__filemap_fdatawrite_range+0xd7/0x120
sync_file_range+0xac/0xf0
ioc->bfqd:
bfq_exit_icq+0xa3/0xe0 -> bfqd->lock grabbed
put_io_context_active+0x78/0xb0 -> ioc->lock grabbed
exit_io_context+0x48/0x50
do_exit+0x7e9/0xdd0
do_group_exit+0x54/0xc0
To avoid this inversion we change blk_mq_sched_try_insert_merge() to not
free the merged request but rather leave that upto the caller similarly
to blk_mq_sched_try_merge(). And in bfq_insert_requests() we make sure
to free all the merged requests after dropping bfqd->lock.
Fixes: aee69d78de ("block, bfq: introduce the BFQ-v0 I/O scheduler as an extra scheduler")
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Acked-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20210623093634.27879-3-jack@suse.cz
Signed-off-by: Jens Axboe <axboe@kernel.dk>
88 lines
2.5 KiB
C
88 lines
2.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef BLK_MQ_SCHED_H
|
|
#define BLK_MQ_SCHED_H
|
|
|
|
#include "blk-mq.h"
|
|
#include "blk-mq-tag.h"
|
|
|
|
#define MAX_SCHED_RQ (16 * BLKDEV_MAX_RQ)
|
|
|
|
void blk_mq_sched_assign_ioc(struct request *rq);
|
|
|
|
bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
|
|
unsigned int nr_segs, struct request **merged_request);
|
|
bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
|
|
unsigned int nr_segs);
|
|
bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq,
|
|
struct list_head *free);
|
|
void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx);
|
|
void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx);
|
|
|
|
void blk_mq_sched_insert_request(struct request *rq, bool at_head,
|
|
bool run_queue, bool async);
|
|
void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx,
|
|
struct blk_mq_ctx *ctx,
|
|
struct list_head *list, bool run_queue_async);
|
|
|
|
void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
|
|
|
|
int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e);
|
|
void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e);
|
|
void blk_mq_sched_free_requests(struct request_queue *q);
|
|
|
|
static inline bool
|
|
blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
|
|
unsigned int nr_segs)
|
|
{
|
|
if (blk_queue_nomerges(q) || !bio_mergeable(bio))
|
|
return false;
|
|
|
|
return __blk_mq_sched_bio_merge(q, bio, nr_segs);
|
|
}
|
|
|
|
static inline bool
|
|
blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
|
|
struct bio *bio)
|
|
{
|
|
struct elevator_queue *e = q->elevator;
|
|
|
|
if (e && e->type->ops.allow_merge)
|
|
return e->type->ops.allow_merge(q, rq, bio);
|
|
|
|
return true;
|
|
}
|
|
|
|
static inline void blk_mq_sched_completed_request(struct request *rq, u64 now)
|
|
{
|
|
struct elevator_queue *e = rq->q->elevator;
|
|
|
|
if (e && e->type->ops.completed_request)
|
|
e->type->ops.completed_request(rq, now);
|
|
}
|
|
|
|
static inline void blk_mq_sched_requeue_request(struct request *rq)
|
|
{
|
|
struct request_queue *q = rq->q;
|
|
struct elevator_queue *e = q->elevator;
|
|
|
|
if ((rq->rq_flags & RQF_ELVPRIV) && e && e->type->ops.requeue_request)
|
|
e->type->ops.requeue_request(rq);
|
|
}
|
|
|
|
static inline bool blk_mq_sched_has_work(struct blk_mq_hw_ctx *hctx)
|
|
{
|
|
struct elevator_queue *e = hctx->queue->elevator;
|
|
|
|
if (e && e->type->ops.has_work)
|
|
return e->type->ops.has_work(hctx);
|
|
|
|
return false;
|
|
}
|
|
|
|
static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx)
|
|
{
|
|
return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
|
|
}
|
|
|
|
#endif
|