fix queue freeze and limit locking order v3
Subsystems (9)
Christoph Hellwig
maintainerHi all,
this is my version of Damien's "Fix queue freeze and limit locking order". A lot looks very similar, but it was done independently based on the previous discussion.
Changes since v2:
- check for polling support under q_usage_counter
- improve a commit log
Changes since v1:
- more comment typo fixing
- fix loop as well
- make the poll sysfs attr show method more accurate
Changes since RFC:
- fix a bizzare virtio_blk bisection snafu
- set BLK_FEAT_POLL a little less eagerly for blk-mq
- drop the loop patch just adding a comment
- improve various commit logs and coments
Diffstat:
block/blk-core.c | 17 ++++- block/blk-integrity.c | 4 - block/blk-mq.c | 17 ----- block/blk-settings.c | 27 +++++++- block/blk-sysfs.c | 134 ++++++++++++++++++++--------------------- block/blk-zoned.c | 7 -- block/blk.h | 1 drivers/block/loop.c | 52 ++++++++++----- drivers/block/nbd.c | 17 ----- drivers/block/virtio_blk.c | 4 - drivers/nvme/host/core.c | 9 +- drivers/scsi/sd.c | 17 +---- drivers/scsi/sr.c | 5 - drivers/usb/storage/scsiglue.c | 5 - include/linux/blkdev.h | 5 - 15 files changed, 164 insertions(+), 157 deletions(-)
Christoph Hellwig
maintainerPATCH 1/11 block: fix docs for freezing of queue limits updates
queue_limits_commit_update is the function that needs to operate on a frozen queue, not queue_limits_start_update. Update the kerneldoc comments to reflect that.
--- block/blk-settings.c | 3 ++- include/linux/blkdev.h | 3 +-- 2 files changed, 3 insertions(+), 3 deletions(-)
block/blk-settings.c +2 -1
@@ -413,7 +413,8 @@ int blk_set_default_limits(struct queue_limits *lim)* @lim: limits to apply * * Apply the limits in @lim that were obtained from queue_limits_start_update() -* and updated by the caller to @q. +* and updated by the caller to @q. The caller must have frozen the queue or +* ensure that there are no outstanding I/Os by other means. * * Returns 0 if successful, else a negative error code. */
include/linux/blkdev.h +1 -2
@@ -944,8 +944,7 @@ static inline unsigned int blk_boundary_sectors_left(sector_t offset,* the caller can modify. The caller must call queue_limits_commit_update() * to finish the update. * -* Context: process context. The caller must have frozen the queue or ensured -* that there is outstanding I/O by other means. +* Context: process context. */ static inline struct queue_limits queue_limits_start_update (struct request_queue *q)
Signature · 1 line
2.45.2
Christoph Hellwig
maintainerPATCH 2/11 block: add a queue_limits_commit_update_frozen helper
In reply to Christoph HellwigAdd a helper that freezes the queue, updates the queue limits and unfreezes the queue and convert all open coded versions of that to the new helper.
--- block/blk-integrity.c | 4 +--- block/blk-settings.c | 24 ++++++++++++++++++++++++ block/blk-zoned.c | 7 +------ drivers/block/virtio_blk.c | 4 +--- drivers/scsi/sd.c | 17 +++++------------ drivers/scsi/sr.c | 5 +---- include/linux/blkdev.h | 2 ++ 7 files changed, 35 insertions(+), 28 deletions(-)
block/blk-integrity.c +1 -3
@@ -218,9 +218,7 @@ static ssize_t flag_store(struct device *dev, const char *page, size_t count,else lim.integrity.flags |= flag; -blk_mq_freeze_queue (q); - err =queue_limits_commit_update (q, &lim); -blk_mq_unfreeze_queue (q); + err =queue_limits_commit_update_frozen (q, &lim);if (err)return err;return count;
block/blk-settings.c +24 -0
@@ -444,6 +444,30 @@ int queue_limits_commit_update(struct request_queue *q, }EXPORT_SYMBOL_GPL (queue_limits_commit_update); +/** +* queue_limits_commit_update_frozen - commit an atomic update of queue limits +* @q: queue to update +* @lim: limits to apply +* +* Apply the limits in @lim that were obtained from queue_limits_start_update() +* and updated by the caller to @q. Freezes the queue before the updated and +* unfreezes it after. +* +* Returns 0 if successful, else a negative error code. +*/ +int queue_limits_commit_update_frozen (struct request_queue *q, +struct queue_limits *lim) +{ +int ret; + +blk_mq_freeze_queue (q); + ret =queue_limits_commit_update (q, lim); +blk_mq_unfreeze_queue (q); + +return ret; +} +EXPORT_SYMBOL_GPL (queue_limits_commit_update_frozen); +/** * queue_limits_set - apply queue limits to queue * @q: queue to update
block/blk-zoned.c +1 -6
@@ -1444,7 +1444,6 @@ static int disk_update_zone_resources(struct gendisk *disk,unsigned int nr_seq_zones, nr_conv_zones;unsigned int pool_size;struct queue_limits lim; -int ret; disk->nr_zones = args->nr_zones; disk->zone_capacity = args->zone_capacity;
@@ -1495,11 +1494,7 @@ static int disk_update_zone_resources(struct gendisk *disk, } commit: -blk_mq_freeze_queue (q); - ret =queue_limits_commit_update (q, &lim); -blk_mq_unfreeze_queue (q); - -return ret; +return queue_limits_commit_update_frozen (q, &lim); } static int blk_revalidate_conv_zone(struct blk_zone *zone, unsigned int idx,
drivers/block/virtio_blk.c +1 -3
@@ -1105,9 +1105,7 @@ cache_type_store(struct device *dev, struct device_attribute *attr, lim.features |=BLK_FEAT_WRITE_CACHE ; else lim.features &= ~BLK_FEAT_WRITE_CACHE; -blk_mq_freeze_queue (disk->queue); - i =queue_limits_commit_update (disk->queue, &lim); -blk_mq_unfreeze_queue (disk->queue); + i =queue_limits_commit_update_frozen (disk->queue, &lim);if (i)return i;return count;
drivers/scsi/sd.c +5 -12
@@ -177,9 +177,8 @@ cache_type_store(struct device *dev, struct device_attribute *attr, lim =queue_limits_start_update (sdkp->disk->queue);sd_set_flush_flag (sdkp, &lim); -blk_mq_freeze_queue (sdkp->disk->queue); - ret =queue_limits_commit_update (sdkp->disk->queue, &lim); -blk_mq_unfreeze_queue (sdkp->disk->queue); + ret =queue_limits_commit_update_frozen (sdkp->disk->queue, + &lim);if (ret)return ret;return count;
@@ -483,9 +482,7 @@ provisioning_mode_store(struct device *dev, struct device_attribute *attr, lim =queue_limits_start_update (sdkp->disk->queue);sd_config_discard (sdkp, &lim, mode); -blk_mq_freeze_queue (sdkp->disk->queue); - err =queue_limits_commit_update (sdkp->disk->queue, &lim); -blk_mq_unfreeze_queue (sdkp->disk->queue); + err =queue_limits_commit_update_frozen (sdkp->disk->queue, &lim);if (err)return err;return count;
@@ -594,9 +591,7 @@ max_write_same_blocks_store(struct device *dev, struct device_attribute *attr, lim =queue_limits_start_update (sdkp->disk->queue);sd_config_write_same (sdkp, &lim); -blk_mq_freeze_queue (sdkp->disk->queue); - err =queue_limits_commit_update (sdkp->disk->queue, &lim); -blk_mq_unfreeze_queue (sdkp->disk->queue); + err =queue_limits_commit_update_frozen (sdkp->disk->queue, &lim);if (err)return err;return count;
@@ -3803,9 +3798,7 @@ static int sd_revalidate_disk(struct gendisk *disk)sd_config_write_same (sdkp, &lim);kfree (buffer); -blk_mq_freeze_queue (sdkp->disk->queue); - err =queue_limits_commit_update (sdkp->disk->queue, &lim); -blk_mq_unfreeze_queue (sdkp->disk->queue); + err =queue_limits_commit_update_frozen (sdkp->disk->queue, &lim);if (err)return err;
drivers/scsi/sr.c +1 -4
@@ -797,10 +797,7 @@ static int get_sectorsize(struct scsi_cd *cd) lim =queue_limits_start_update (q); lim.logical_block_size = sector_size; -blk_mq_freeze_queue (q); - err =queue_limits_commit_update (q, &lim); -blk_mq_unfreeze_queue (q); -return err; +return queue_limits_commit_update_frozen (q, &lim); }static int get_capabilities (struct scsi_cd *cd)
include/linux/blkdev.h +2 -0
@@ -952,6 +952,8 @@ queue_limits_start_update(struct request_queue *q)mutex_lock (&q->limits_lock);return q->limits; } +int queue_limits_commit_update_frozen (struct request_queue *q, +struct queue_limits *lim);int queue_limits_commit_update (struct request_queue *q,struct queue_limits *lim);int queue_limits_set (struct request_queue *q,struct queue_limits *lim);
Signature · 1 line
2.45.2
Re: [PATCH 02/11] block: add a queue_limits_commit_update_frozen helper
Quoted 9 lines · Christoph Hellwig
Add a helper that freezes the queue, updates the queue limits and unfreezes the queue and convert all open coded versions of that to the new helper.
Signed-off-by Christoph Hellwig <[email protected]>Reviewed-by Ming Lei <[email protected]>Reviewed-by Damien Le Moal <[email protected]>Reviewed-by Nilay Shroff <[email protected]>Reviewed-by Johannes Thumshirn <[email protected]>
Apart from some nitpicking on the code comments, FWIW:
Quoted 30 lines
--- block/blk-integrity.c | 4 +--- block/blk-settings.c | 24 ++++++++++++++++++++++++ block/blk-zoned.c | 7 +------ drivers/block/virtio_blk.c | 4 +--- drivers/scsi/sd.c | 17 +++++------------ drivers/scsi/sr.c | 5 +---- include/linux/blkdev.h | 2 ++ 7 files changed, 35 insertions(+), 28 deletions(-)block/blk-integrity.c +1
-3@@ -218,9 +218,7 @@ static ssize_t flag_store(struct device *dev, const char *page, size_t count,else lim.integrity.flags |= flag; -blk_mq_freeze_queue (q); - err =queue_limits_commit_update (q, &lim); -blk_mq_unfreeze_queue (q); + err =queue_limits_commit_update_frozen (q, &lim);if (err)return err;return count;block/blk-settings.c +0
-0
block/blk-settings.c int queue_limits_commit_update(struct request_queue *q, · line 448
Quoted 5 lines
block/blk-settings.c +2
-0@@ -444,6 +444,30 @@ int queue_limits_commit_update(struct request_queue *q, }EXPORT_SYMBOL_GPL (queue_limits_commit_update); +/** +* queue_limits_commit_update_frozen - commit an atomic update of queue limits
nit: this has same brief description of queue_limits_commit_update(), but it does not do the same thing. I know that space is limited here for the comment, though.
block/blk-settings.c int queue_limits_commit_update(struct request_queue *q,
Quoted 5 lines
block/blk-settings.c +5
-0+* @q: queue to update +* @lim: limits to apply +* +* Apply the limits in @lim that were obtained from queue_limits_start_update() +* and updated by the caller to @q.
"updated by the caller to @q" - this sounds odd
Quoted 2 lines
Freezes the queue before the updated and
+ * unfreezes it after.
should that be "before the update"?
Quoted 16 lines
+ *
+ * Returns 0 if successful, else a negative error code.
+ */block/blk-settings.c +13
-0+int queue_limits_commit_update_frozen (struct request_queue *q, +struct queue_limits *lim) +{ +int ret; + +blk_mq_freeze_queue (q); + ret =queue_limits_commit_update (q, lim); +blk_mq_unfreeze_queue (q); + +return ret; +} +EXPORT_SYMBOL_GPL (queue_limits_commit_update_frozen); +
Christoph Hellwig
maintainerPATCH 3/11 block: check BLK_FEAT_POLL under q_usage_count
In reply to Christoph HellwigOtherwise feature reconfiguration can race with I/O submission.
Also drop the bio_clear_polled in the error path, as the flag does not matter for instant error completions, it is a left over from when we allowed polled I/O to proceed unpolled in this case.
--- block/blk-core.c | 22 ++++++++++++---------- block/blk-mq.c | 12 ++++++++++-- 2 files changed, 22 insertions(+), 12 deletions(-)
block/blk-core.c +12 -10
@@ -629,8 +629,14 @@ static void __submit_bio(struct bio *bio)blk_mq_submit_bio (bio); }else if (likely (bio_queue_enter (bio) ==0 )) {struct gendisk *disk = bio->bi_bdev->bd_disk; - - disk->fops->submit_bio (bio); + +if ((bio->bi_opf &REQ_POLLED ) && + !(disk->queue->limits.features &BLK_FEAT_POLL )) { + bio->bi_status =BLK_STS_NOTSUPP ; +bio_endio (bio); + }else { + disk->fops->submit_bio (bio); + }blk_queue_exit (disk->queue); }
@@ -805,12 +811,6 @@ void submit_bio_noacct(struct bio *bio) } } -if (!(q->limits.features &BLK_FEAT_POLL ) && - (bio->bi_opf &REQ_POLLED )) { -bio_clear_polled (bio); - goto not_supported; - } -switch (bio_op (bio)) {case REQ_OP_READ :break ;
@@ -935,7 +935,7 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)return 0 ; q =bdev_get_queue (bdev); -if (cookie ==BLK_QC_T_NONE || !(q->limits.features &BLK_FEAT_POLL )) +if (cookie ==BLK_QC_T_NONE )return 0 ;blk_flush_plug (current->plug, false);
@@ -951,7 +951,9 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)*/ if (!percpu_ref_tryget (&q->q_usage_counter))return 0 ; -if (queue_is_mq (q)) { +if (!(q->limits.features &BLK_FEAT_POLL )) { + ret =0 ; + }else if (queue_is_mq (q)) { ret =blk_mq_poll (q, cookie, iob, flags); }else {struct gendisk *disk = q->disk;
block/blk-mq.c +10 -2
@@ -3096,14 +3096,22 @@ void blk_mq_submit_bio(struct bio *bio) }/* -* Device reconfiguration may change logical block size, so alignment -* check has to be done with queue usage counter held +* Device reconfiguration may change logical block size or reduce the +* number of poll queues, so the checks for alignment and poll support +* have to be done with queue usage counter held. */ if (unlikely (bio_unaligned (bio, q))) {bio_io_error (bio); goto queue_exit; } +if ((bio->bi_opf &REQ_POLLED ) && + !(q->limits.features &BLK_FEAT_POLL )) { + bio->bi_status =BLK_STS_NOTSUPP ; +bio_endio (bio); + goto queue_exit; + } + bio =__bio_split_to_limits (bio, &q->limits, &nr_segs);if (!bio) goto queue_exit;
Signature · 1 line
2.45.2
Re: [PATCH 03/11] block: check BLK_FEAT_POLL under q_usage_count
Quoted 7 lines · Christoph Hellwig
Otherwise feature reconfiguration can race with I/O submission.
Also drop the
bio_clear_polledin the error path, as the flag does not matter for instant error completions, it is a left over from when we allowed polled I/O to proceed unpolled in this case.Signed-off-by Christoph Hellwig <[email protected]>
Thanks,
Ming
Re: [PATCH 03/11] block: check BLK_FEAT_POLL under q_usage_count
In reply to Christoph HellwigQuoted 7 lines · Christoph Hellwig
Otherwise feature reconfiguration can race with I/O submission.
Also drop the
bio_clear_polledin the error path, as the flag does not matter for instant error completions, it is a left over from when we allowed polled I/O to proceed unpolled in this case.Signed-off-by Christoph Hellwig <[email protected]>
Looks good to me:
Christoph Hellwig
maintainerPATCH 4/11 block: don't update BLK_FEAT_POLL in __blk_mq_update_nr_hw_queues
In reply to Christoph HellwigWhen __blk_mq_update_nr_hw_queues changes the number of tag sets, it might have to disable poll queues. Currently it does so by adjusting the BLK_FEAT_POLL, which is a bit against the intent of features that describe hardware / driver capabilities, but more importantly causes nasty lock order problems with the broadly held freeze when updating the number of hardware queues and the limits lock. Fix this by leaving BLK_FEAT_POLL alone, and instead check for the number of poll queues in the bio submission and poll handlers. While this adds extra work to the fast path, the variables are in cache lines used by these operations anyway, so it should be cheap enough.
--- block/blk-core.c | 7 +++---- block/blk-mq.c | 26 +++++--------------------- block/blk-mq.h | 6 ++++++ block/blk-sysfs.c | 9 ++++++++- 4 files changed, 22 insertions(+), 26 deletions(-)
block/blk-core.c +3 -4
@@ -951,14 +951,13 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)*/ if (!percpu_ref_tryget (&q->q_usage_counter))return 0 ; -if (!(q->limits.features &BLK_FEAT_POLL )) { - ret =0 ; - }else if (queue_is_mq (q)) { +if (queue_is_mq (q)) { ret =blk_mq_poll (q, cookie, iob, flags); }else {struct gendisk *disk = q->disk; -if (disk && disk->fops->poll_bio) +if ((q->limits.features &BLK_FEAT_POLL ) && disk && + disk->fops->poll_bio) ret = disk->fops->poll_bio (bio, iob, flags); }blk_queue_exit (q);
block/blk-mq.c +5 -21
@@ -3105,8 +3105,7 @@ void blk_mq_submit_bio(struct bio *bio) goto queue_exit; } -if ((bio->bi_opf &REQ_POLLED ) && - !(q->limits.features &BLK_FEAT_POLL )) { +if ((bio->bi_opf &REQ_POLLED ) && !blk_mq_can_poll (q)) { bio->bi_status =BLK_STS_NOTSUPP ;bio_endio (bio); goto queue_exit;
@@ -4328,12 +4327,6 @@ void blk_mq_release(struct request_queue *q)blk_mq_sysfs_deinit (q); } -static bool blk_mq_can_poll (struct blk_mq_tag_set *set) -{ -return set->nr_maps >HCTX_TYPE_POLL && - set->map[HCTX_TYPE_POLL ].nr_queues; -} -struct request_queue *blk_mq_alloc_queue (struct blk_mq_tag_set *set,struct queue_limits *lim,void *queuedata) {
@@ -4344,7 +4337,7 @@ struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,if (!lim) lim = &default_lim; lim->features |=BLK_FEAT_IO_STAT |BLK_FEAT_NOWAIT ; -if (blk_mq_can_poll (set)) +if (set->nr_maps >HCTX_TYPE_POLL ) lim->features |=BLK_FEAT_POLL ; q =blk_alloc_queue (lim, set->numa_node);
@@ -5032,8 +5025,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, fallback:blk_mq_update_queue_map (set);list_for_each_entry (q, &set->tag_list, tag_set_list) { -struct queue_limits lim; -blk_mq_realloc_hw_ctxs (set, q);if (q->nr_hw_queues != set->nr_hw_queues) {
@@ -5047,13 +5038,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, set->nr_hw_queues = prev_nr_hw_queues; goto fallback; } - lim =queue_limits_start_update (q); -if (blk_mq_can_poll (set)) - lim.features |=BLK_FEAT_POLL ; -else - lim.features &= ~BLK_FEAT_POLL ; -if (queue_limits_commit_update (q, &lim) <0 ) -pr_warn ("updating the poll flag failed\n" );blk_mq_map_swqueue (q); }
@@ -5113,9 +5097,9 @@ static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx,int blk_mq_poll (struct request_queue *q,blk_qc_t cookie,struct io_comp_batch *iob,unsigned int flags) { -struct blk_mq_hw_ctx *hctx =xa_load (&q->hctx_table, cookie); - -return blk_hctx_poll (q, hctx, iob, flags); +if (!blk_mq_can_poll (q)) +return 0 ; +return blk_hctx_poll (q,xa_load (&q->hctx_table, cookie), iob, flags); } int blk_rq_poll(struct request *rq, struct io_comp_batch *iob,
block/blk-mq.h +6 -0
@@ -448,4 +448,10 @@ do { \#define blk_mq_run_dispatch_ops (q, dispatch_ops) \ __blk_mq_run_dispatch_ops(q, true, dispatch_ops) \ +static inline bool blk_mq_can_poll (struct request_queue *q) +{ +return (q->limits.features &BLK_FEAT_POLL ) && + q->tag_set->map[HCTX_TYPE_POLL ].nr_queues; +} +#endif
block/blk-sysfs.c +8 -1
@@ -245,10 +245,17 @@ static ssize_t queue_##_name##_show(struct gendisk *disk, char *page) \ !!(disk->queue->limits.features & _feature)); \ } -QUEUE_SYSFS_FEATURE_SHOW (poll,BLK_FEAT_POLL );QUEUE_SYSFS_FEATURE_SHOW (fua,BLK_FEAT_FUA );QUEUE_SYSFS_FEATURE_SHOW (dax,BLK_FEAT_DAX ); +static ssize_t queue_poll_show (struct gendisk *disk,char *page) +{ +if (queue_is_mq (disk->queue)) +return sysfs_emit (page,"%u\n" ,blk_mq_can_poll (disk->queue)); +return sysfs_emit (page,"%u\n" , + !!(disk->queue->limits.features &BLK_FEAT_POLL )); +} +static ssize_t queue_zoned_show (struct gendisk *disk,char *page) {if (blk_queue_is_zoned (disk->queue))
Signature · 1 line
2.45.2
Re: [PATCH 04/11] block: don't update BLK_FEAT_POLL in __blk_mq_update_nr_hw_queues
Quoted 11 lines · Christoph Hellwig
When
__blk_mq_update_nr_hw_queueschanges the number of tag sets, it might have to disable poll queues. Currently it does so by adjusting theBLK_FEAT_POLL, which is a bit against the intent of features that describe hardware / driver capabilities, but more importantly causes nasty lock order problems with the broadly held freeze when updating the number of hardware queues and the limits lock. Fix this by leavingBLK_FEAT_POLLalone, and instead check for the number of poll queues in the bio submission and poll handlers. While this adds extra work to the fast path, the variables are in cache lines used by these operations anyway, so it should be cheap enough.
Quoted 4 lines
Fixes 8023e144f9d6 ("block: move the poll flag to queue_limits")Signed-off-by Christoph Hellwig <[email protected]>Reviewed-by Damien Le Moal <[email protected]>Reviewed-by Johannes Thumshirn <[email protected]>
Thanks,
Ming
Re: [PATCH 04/11] block: don't update BLK_FEAT_POLL in __blk_mq_update_nr_hw_queues
In reply to Christoph HellwigQuoted 11 lines · Christoph Hellwig
When
__blk_mq_update_nr_hw_queueschanges the number of tag sets, it might have to disable poll queues. Currently it does so by adjusting theBLK_FEAT_POLL, which is a bit against the intent of features that describe hardware / driver capabilities, but more importantly causes nasty lock order problems with the broadly held freeze when updating the number of hardware queues and the limits lock. Fix this by leavingBLK_FEAT_POLLalone, and instead check for the number of poll queues in the bio submission and poll handlers. While this adds extra work to the fast path, the variables are in cache lines used by these operations anyway, so it should be cheap enough.
Quoted 4 lines
Fixes 8023e144f9d6 ("block: move the poll flag to queue_limits")Signed-off-by Christoph Hellwig <[email protected]>Reviewed-by Damien Le Moal <[email protected]>Reviewed-by Johannes Thumshirn <[email protected]>
Looks good to me, also with this new change in v3, I re-tested use case:
When a driver announces the support of polled I/O during initialization and later resizing the queue so that there's no poll queue left. Both these cases works fine. So:
Christoph Hellwig
maintainerPATCH 5/11 block: add a store_limit operations for sysfs entries
In reply to Christoph HellwigDe-duplicate the code for updating queue limits by adding a store_limit method that allows having common code handle the actual queue limits update.
Note that this is a pure refactoring patch and does not address the existing freeze vs limits lock order problem in the refactored code, which will be addressed next.
--- block/blk-sysfs.c | 128 ++++++++++++++++++++++------------------------ 1 file changed, 61 insertions(+), 67 deletions(-)
block/blk-sysfs.c +61 -67
@@ -24,6 +24,8 @@ struct queue_sysfs_entry {struct attribute attr;ssize_t (*show)(struct gendisk *disk,char *page);ssize_t (*store)(struct gendisk *disk,const char *page,size_t count); +int (*store_limit)(struct gendisk *disk,const char *page, +size_t count,struct queue_limits *lim);void (*load_module)(struct gendisk *disk,const char *page,size_t count); };
@@ -153,13 +155,11 @@ QUEUE_SYSFS_SHOW_CONST(discard_zeroes_data, 0) QUEUE_SYSFS_SHOW_CONST(write_same_max, 0) QUEUE_SYSFS_SHOW_CONST(poll_delay, -1) -static ssize_t queue_max_discard_sectors_store (struct gendisk *disk, -const char *page,size_t count) +static int queue_max_discard_sectors_store (struct gendisk *disk, +const char *page,size_t count,struct queue_limits *lim) {unsigned long max_discard_bytes; -struct queue_limits lim;ssize_t ret; -int err; ret =queue_var_store (&max_discard_bytes, page, count);if (ret <0 )
@@ -171,38 +171,28 @@ static ssize_t queue_max_discard_sectors_store(struct gendisk *disk,if ((max_discard_bytes >>SECTOR_SHIFT ) >UINT_MAX )return -EINVAL ; - lim =queue_limits_start_update (disk->queue); - lim.max_user_discard_sectors = max_discard_bytes >>SECTOR_SHIFT ; - err =queue_limits_commit_update (disk->queue, &lim); -if (err) -return err; -return ret; + lim->max_user_discard_sectors = max_discard_bytes >>SECTOR_SHIFT ; +return 0 ; } -static ssize_t -queue_max_sectors_store (struct gendisk *disk,const char *page,size_t count) +static int +queue_max_sectors_store (struct gendisk *disk,const char *page,size_t count, +struct queue_limits *lim) {unsigned long max_sectors_kb; -struct queue_limits lim;ssize_t ret; -int err; ret =queue_var_store (&max_sectors_kb, page, count);if (ret <0 )return ret; - lim =queue_limits_start_update (disk->queue); - lim.max_user_sectors = max_sectors_kb <<1 ; - err =queue_limits_commit_update (disk->queue, &lim); -if (err) -return err; -return ret; + lim->max_user_sectors = max_sectors_kb <<1 ; +return 0 ; }static ssize_t queue_feature_store (struct gendisk *disk,const char *page, -size_t count,blk_features_t feature) +size_t count,struct queue_limits *lim,blk_features_t feature) { -struct queue_limits lim;unsigned long val;ssize_t ret;
@@ -210,15 +200,11 @@ static ssize_t queue_feature_store(struct gendisk *disk, const char *page,if (ret <0 )return ret; - lim =queue_limits_start_update (disk->queue);if (val) - lim.features |= feature; + lim->features |= feature;else - lim.features &= ~feature; - ret =queue_limits_commit_update (disk->queue, &lim); -if (ret) -return ret; -return count; + lim->features &= ~feature; +return 0 ; }#define QUEUE_SYSFS_FEATURE (_name, _feature) \
@@ -227,10 +213,10 @@ static ssize_t queue_##_name##_show(struct gendisk *disk, char *page) \return sysfs_emit (page,"%u\n" , \ !!(disk->queue->limits.features & _feature)); \ } \ -static ssize_t queue_##_name##_store(struct gendisk *disk, \ -const char *page,size_t count) \ +static int queue_##_name##_store(struct gendisk *disk, \ +const char *page,size_t count,struct queue_limits *lim) \ { \ -return queue_feature_store (disk, page, count, _feature); \ +return queue_feature_store (disk, page, count, lim, _feature); \ }QUEUE_SYSFS_FEATURE (rotational,BLK_FEAT_ROTATIONAL )
@@ -273,10 +259,9 @@ static ssize_t queue_iostats_passthrough_show(struct gendisk *disk, char *page)return queue_var_show (!!blk_queue_passthrough_stat (disk->queue), page); } -static ssize_t queue_iostats_passthrough_store (struct gendisk *disk, -const char *page,size_t count) +static int queue_iostats_passthrough_store (struct gendisk *disk, +const char *page,size_t count,struct queue_limits *lim) { -struct queue_limits lim;unsigned long ios;ssize_t ret;
@@ -284,18 +269,13 @@ static ssize_t queue_iostats_passthrough_store(struct gendisk *disk,if (ret <0 )return ret; - lim =queue_limits_start_update (disk->queue);if (ios) - lim.flags |=BLK_FLAG_IOSTATS_PASSTHROUGH ; + lim->flags |=BLK_FLAG_IOSTATS_PASSTHROUGH ;else - lim.flags &= ~BLK_FLAG_IOSTATS_PASSTHROUGH ; - - ret =queue_limits_commit_update (disk->queue, &lim); -if (ret) -return ret; - -return count; + lim->flags &= ~BLK_FLAG_IOSTATS_PASSTHROUGH ; +return 0 ; } +static ssize_t queue_nomerges_show (struct gendisk *disk,char *page) { return queue_var_show((blk_queue_nomerges(disk->queue) << 1) |
@@ -398,12 +378,10 @@ static ssize_t queue_wc_show(struct gendisk *disk, char *page)return sysfs_emit (page,"write through\n" ); } -static ssize_t queue_wc_store (struct gendisk *disk,const char *page, -size_t count) +static int queue_wc_store (struct gendisk *disk,const char *page, +size_t count,struct queue_limits *lim) { -struct queue_limits lim;bool disable; -int err;if (!strncmp (page,"write back" ,10 )) { disable = false;
@@ -414,15 +392,11 @@ static ssize_t queue_wc_store(struct gendisk *disk, const char *page,return -EINVAL ; } - lim =queue_limits_start_update (disk->queue);if (disable) - lim.flags |=BLK_FLAG_WRITE_CACHE_DISABLED ; + lim->flags |=BLK_FLAG_WRITE_CACHE_DISABLED ;else - lim.flags &= ~BLK_FLAG_WRITE_CACHE_DISABLED ; - err =queue_limits_commit_update (disk->queue, &lim); -if (err) -return err; -return count; + lim->flags &= ~BLK_FLAG_WRITE_CACHE_DISABLED ; +return 0 ; }#define QUEUE_RO_ENTRY (_prefix, _name) \
@@ -438,6 +412,13 @@ static struct queue_sysfs_entry _prefix##_entry = { \ .store = _prefix##_store, \ }; +#define QUEUE_LIM_RW_ENTRY (_prefix, _name) \ +static struct queue_sysfs_entry _prefix##_entry = { \ + .attr = { .name = _name, .mode = 0644 }, \ + .show = _prefix##_show, \ + .store_limit = _prefix##_store, \ +} +#define QUEUE_RW_LOAD_MODULE_ENTRY (_prefix, _name) \ static struct queue_sysfs_entry _prefix##_entry = { \ .attr = { .name = _name, .mode = 0644 }, \
@@ -448,7 +429,7 @@ static struct queue_sysfs_entry _prefix##_entry = { \QUEUE_RW_ENTRY (queue_requests,"nr_requests" );QUEUE_RW_ENTRY (queue_ra,"read_ahead_kb" ); -QUEUE_RW_ENTRY (queue_max_sectors,"max_sectors_kb" ); +QUEUE_LIM_RW_ENTRY (queue_max_sectors,"max_sectors_kb" );QUEUE_RO_ENTRY (queue_max_hw_sectors,"max_hw_sectors_kb" );QUEUE_RO_ENTRY (queue_max_segments,"max_segments" );QUEUE_RO_ENTRY (queue_max_integrity_segments,"max_integrity_segments" );
@@ -464,7 +445,7 @@ QUEUE_RO_ENTRY(queue_io_opt, "optimal_io_size");QUEUE_RO_ENTRY (queue_max_discard_segments,"max_discard_segments" );QUEUE_RO_ENTRY (queue_discard_granularity,"discard_granularity" );QUEUE_RO_ENTRY (queue_max_hw_discard_sectors,"discard_max_hw_bytes" ); -QUEUE_RW_ENTRY (queue_max_discard_sectors,"discard_max_bytes" ); +QUEUE_LIM_RW_ENTRY (queue_max_discard_sectors,"discard_max_bytes" );QUEUE_RO_ENTRY (queue_discard_zeroes_data,"discard_zeroes_data" );QUEUE_RO_ENTRY (queue_atomic_write_max_sectors,"atomic_write_max_bytes" );
@@ -484,11 +465,11 @@ QUEUE_RO_ENTRY(queue_max_open_zones, "max_open_zones");QUEUE_RO_ENTRY (queue_max_active_zones,"max_active_zones" );QUEUE_RW_ENTRY (queue_nomerges,"nomerges" ); -QUEUE_RW_ENTRY (queue_iostats_passthrough,"iostats_passthrough" ); +QUEUE_LIM_RW_ENTRY (queue_iostats_passthrough,"iostats_passthrough" );QUEUE_RW_ENTRY (queue_rq_affinity,"rq_affinity" );QUEUE_RW_ENTRY (queue_poll,"io_poll" );QUEUE_RW_ENTRY (queue_poll_delay,"io_poll_delay" ); -QUEUE_RW_ENTRY (queue_wc,"write_cache" ); +QUEUE_LIM_RW_ENTRY (queue_wc,"write_cache" );QUEUE_RO_ENTRY (queue_fua,"fua" );QUEUE_RO_ENTRY (queue_dax,"dax" );QUEUE_RW_ENTRY (queue_io_timeout,"io_timeout" );
@@ -501,10 +482,10 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = { .show = queue_logical_block_size_show, }; -QUEUE_RW_ENTRY (queue_rotational,"rotational" ); -QUEUE_RW_ENTRY (queue_iostats,"iostats" ); -QUEUE_RW_ENTRY (queue_add_random,"add_random" ); -QUEUE_RW_ENTRY (queue_stable_writes,"stable_writes" ); +QUEUE_LIM_RW_ENTRY (queue_rotational,"rotational" ); +QUEUE_LIM_RW_ENTRY (queue_iostats,"iostats" ); +QUEUE_LIM_RW_ENTRY (queue_add_random,"add_random" ); +QUEUE_LIM_RW_ENTRY (queue_stable_writes,"stable_writes" );#ifdef CONFIG_BLK_WBT static ssize_t queue_var_store64 (s64 *var,const char *page)
@@ -702,7 +683,7 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,struct request_queue *q = disk->queue;ssize_t res; -if (!entry->store) +if (!entry->store_limit && !entry->store)return -EIO ;/*
@@ -713,11 +694,24 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,if (entry->load_module) entry->load_module (disk, page, length); -blk_mq_freeze_queue (q);mutex_lock (&q->sysfs_lock); - res = entry->store (disk, page, length); -mutex_unlock (&q->sysfs_lock); +blk_mq_freeze_queue (q); +if (entry->store_limit) { +struct queue_limits lim =queue_limits_start_update (q); + + res = entry->store_limit (disk, page, length, &lim); +if (res <0 ) { +queue_limits_cancel_update (q); + }else { + res =queue_limits_commit_update (q, &lim); +if (!res) + res = length; + } + }else { + res = entry->store (disk, page, length); + }blk_mq_unfreeze_queue (q); +mutex_unlock (&q->sysfs_lock);return res; }
Signature · 1 line
2.45.2
Christoph Hellwig
maintainerPATCH 6/11 block: fix queue freeze vs limits lock order in sysfs store methods
In reply to Christoph Hellwigqueue_attr_store() always freezes a device queue before calling the attribute store operation. For attributes that control queue limits, the store operation will also lock the queue limits with a call to queue_limits_start_update(). However, some drivers (e.g. SCSI sd) may need to issue commands to a device to obtain limit values from the hardware with the queue limits locked. This creates a potential ABBA deadlock situation if a user attempts to modify a limit (thus freezing the device queue) while the device driver starts a revalidation of the device queue limits.
Avoid such deadlock by not freezing the queue before calling the ->store_limit() method in struct queue_sysfs_entry and instead use the queue_limits_commit_update_frozen helper to freeze the queue after taking the limits lock.
This also removes taking the sysfs lock for the store_limit method as it doesn't protect anything here, but creates even more nesting. Hopefully it will go away from the actual sysfs methods entirely soon.
(commit log adapted from a similar patch from Damien Le Moal)
--- block/blk-sysfs.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-)
block/blk-sysfs.c +10 -8
@@ -694,22 +694,24 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,if (entry->load_module) entry->load_module (disk, page, length); -mutex_lock (&q->sysfs_lock); -blk_mq_freeze_queue (q);if (entry->store_limit) {struct queue_limits lim =queue_limits_start_update (q); res = entry->store_limit (disk, page, length, &lim);if (res <0 ) {queue_limits_cancel_update (q); - }else { - res =queue_limits_commit_update (q, &lim); -if (!res) - res = length; +return res; } - }else { - res = entry->store (disk, page, length); + + res =queue_limits_commit_update_frozen (q, &lim); +if (res) +return res; +return length; } + +mutex_lock (&q->sysfs_lock); +blk_mq_freeze_queue (q); + res = entry->store (disk, page, length);blk_mq_unfreeze_queue (q);mutex_unlock (&q->sysfs_lock);return res;
Signature · 1 line
2.45.2
Re: [PATCH 06/11] block: fix queue freeze vs limits lock order in sysfs store methods
Quoted 10 lines · Christoph Hellwig
queue_attr_store()always freezes a device queue before calling the attribute store operation. For attributes that control queue limits, the store operation will also lock the queue limits with a call toqueue_limits_start_update(). However, some drivers (e.g. SCSI sd) may need to issue commands to a device to obtain limit values from the hardware with the queue limits locked. This creates a potential ABBA deadlock situation if a user attempts to modify a limit (thus freezing the device queue) while the device driver starts a revalidation of the device queue limits.
Quoted 8 lines
Avoid such deadlock by not freezing the queue before calling the ->store_limit() method in struct
queue_sysfs_entryand instead use thequeue_limits_commit_update_frozenhelper to freeze the queue after taking the limits lock.This also removes taking the sysfs lock for the
store_limitmethod as it doesn't protect anything here, but creates even more nesting. Hopefully it will go away from the actual sysfs methods entirely soon.
Do you mean that the sysfs_lock could be removed in future? I would have thought that queue limits lock could be used for the same thing, but I am probably failing to see some lock nesting/ordering issues...
Christoph Hellwig
maintainerRe: [PATCH 06/11] block: fix queue freeze vs limits lock order in sysfs store methods
Quoted 3 lines · John Garry
Do you mean that the
sysfs_lockcould be removed in future? I would have thought that queue limits lock could be used for the same thing, but I am probably failing to see some lock nesting/ordering issues...
More or less. Think about it: what does it even try to protect?
Readіng/writing sysfs files vs itself and file removal it serialized by sysfs/kernfs internally.
Any information tweaked in sysfs usually also has other places that can modify it. So we'll need a lock independent of sysfs for that anyway. A big part, buy by far all of that is covered by limits_lock.
Serializing creating/removing sysfs attribues is supposed to be serialized using sysfs_dir_lock, although that needs a careful audit.
It's also used to serialize a few debugfs things, but we'll need to look carefully for what exactly and switch that over to debugfs_mutex or something new.
And then there's a bunch of misc cruft that also needs a careful look.
Christoph Hellwig
maintainerPATCH 7/11 nvme: fix queue freeze vs limits lock order
In reply to Christoph HellwigMatch the locking order used by the core block code by only freezing the queue after taking the limits lock.
Unlike most queue updates this does not use the queue_limits_commit_update_frozen helper as the nvme driver want the queue frozen for more than just the limits update.
--- drivers/nvme/host/core.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
drivers/nvme/host/core.c +5 -4
@@ -2128,9 +2128,10 @@ static int nvme_update_ns_info_generic(struct nvme_ns *ns,struct queue_limits lim;int ret; -blk_mq_freeze_queue (ns->disk->queue); lim =queue_limits_start_update (ns->disk->queue);nvme_set_ctrl_limits (ns->ctrl, &lim); + +blk_mq_freeze_queue (ns->disk->queue); ret =queue_limits_commit_update (ns->disk->queue, &lim);set_disk_ro (ns->disk,nvme_ns_is_readonly (ns, info));blk_mq_unfreeze_queue (ns->disk->queue);
@@ -2177,12 +2178,12 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, goto out; } + lim =queue_limits_start_update (ns->disk->queue); +blk_mq_freeze_queue (ns->disk->queue); ns->head->lba_shift = id->lbaf[lbaf].ds; ns->head->nuse =le64_to_cpu (id->nuse); capacity =nvme_lba_to_sect (ns->head,le64_to_cpu (id->nsze)); - - lim =queue_limits_start_update (ns->disk->queue);nvme_set_ctrl_limits (ns->ctrl, &lim);nvme_configure_metadata (ns->ctrl, ns->head, id, nvm, info);nvme_set_chunk_sectors (ns, id, &lim);
@@ -2285,6 +2286,7 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)struct queue_limits *ns_lim = &ns->disk->queue->limits;struct queue_limits lim; + lim =queue_limits_start_update (ns->head->disk->queue);blk_mq_freeze_queue (ns->head->disk->queue);/* * queue_limits mixes values that are the hardware limitations
@@ -2301,7 +2303,6 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)* the splitting limits in to make sure we still obey possibly * lower limitations of other controllers. */ - lim =queue_limits_start_update (ns->head->disk->queue); lim.logical_block_size = ns_lim->logical_block_size; lim.physical_block_size = ns_lim->physical_block_size; lim.io_min = ns_lim->io_min;
Signature · 1 line
2.45.2
Christoph Hellwig
maintainerPATCH 8/11 nbd: fix queue freeze vs limits lock order
In reply to Christoph HellwigMatch the locking order used by the core block code by only freezing the queue after taking the limits lock using the queue_limits_commit_update_frozen helper.
This also allows removes the need for the separate __nbd_set_size helper, so remove it.
--- drivers/block/nbd.c | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-)
drivers/block/nbd.c +2 -15
@@ -327,8 +327,7 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock, nsock->sent =0 ; } -static int __nbd_set_size (struct nbd_device *nbd,loff_t bytesize, -loff_t blksize) +static int nbd_set_size (struct nbd_device *nbd,loff_t bytesize,loff_t blksize) {struct queue_limits lim;int error;
@@ -368,7 +367,7 @@ static int __nbd_set_size(struct nbd_device *nbd, loff_t bytesize, lim.logical_block_size = blksize; lim.physical_block_size = blksize; - error =queue_limits_commit_update (nbd->disk->queue, &lim); + error =queue_limits_commit_update_frozen (nbd->disk->queue, &lim);if (error)return error;
@@ -379,18 +378,6 @@ static int __nbd_set_size(struct nbd_device *nbd, loff_t bytesize,return 0 ; } -static int nbd_set_size (struct nbd_device *nbd,loff_t bytesize, -loff_t blksize) -{ -int error; - -blk_mq_freeze_queue (nbd->disk->queue); - error =__nbd_set_size (nbd, bytesize, blksize); -blk_mq_unfreeze_queue (nbd->disk->queue); - -return error; -} -static void nbd_complete_rq (struct request *req) {struct nbd_cmd *cmd =blk_mq_rq_to_pdu (req);
Signature · 1 line
2.45.2
Christoph Hellwig
maintainerPATCH 9/11 usb-storage: fix queue freeze vs limits lock order
In reply to Christoph HellwigMatch the locking order used by the core block code by only freezing the queue after taking the limits lock using the queue_limits_commit_update_frozen helper.
--- drivers/usb/storage/scsiglue.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-)
drivers/usb/storage/scsiglue.c +1 -4
@@ -592,12 +592,9 @@ static ssize_t max_sectors_store(struct device *dev, struct device_attribute *atif (sscanf (buf,"%hu" , &ms) <=0 )return -EINVAL ; -blk_mq_freeze_queue (sdev->request_queue); lim =queue_limits_start_update (sdev->request_queue); lim.max_hw_sectors = ms; - ret =queue_limits_commit_update (sdev->request_queue, &lim); -blk_mq_unfreeze_queue (sdev->request_queue); - + ret =queue_limits_commit_update_frozen (sdev->request_queue, &lim);if (ret)return ret;return count;
Signature · 1 line
2.45.2
Christoph Hellwig
maintainerPATCH 10/11 loop: refactor queue limits updates
In reply to Christoph HellwigReplace loop_reconfigure_limits with a slightly less encompassing loop_update_limits that expects the aller to acquire and commit the queue limits to prepare for sorting out the freeze vs limits lock ordering.
--- drivers/block/loop.c | 36 ++++++++++++++++++++---------------- 1 file changed, 20 insertions(+), 16 deletions(-)
drivers/block/loop.c +20 -16
@@ -977,12 +977,12 @@ static unsigned int loop_default_blocksize(struct loop_device *lo,return SECTOR_SIZE ; } -static int loop_reconfigure_limits (struct loop_device *lo,unsigned int bsize) +static void loop_update_limits (struct loop_device *lo,struct queue_limits *lim, +unsigned int bsize) {struct file *file = lo->lo_backing_file;struct inode *inode = file->f_mapping->host;struct block_device *backing_bdev =NULL ; -struct queue_limits lim;u32 granularity =0 , max_discard_sectors =0 ;if (S_ISBLK (inode->i_mode))
@@ -995,22 +995,20 @@ static int loop_reconfigure_limits(struct loop_device *lo, unsigned int bsize)loop_get_discard_config (lo, &granularity, &max_discard_sectors); - lim =queue_limits_start_update (lo->lo_queue); - lim.logical_block_size = bsize; - lim.physical_block_size = bsize; - lim.io_min = bsize; - lim.features &= ~(BLK_FEAT_WRITE_CACHE |BLK_FEAT_ROTATIONAL ); + lim->logical_block_size = bsize; + lim->physical_block_size = bsize; + lim->io_min = bsize; + lim->features &= ~(BLK_FEAT_WRITE_CACHE |BLK_FEAT_ROTATIONAL );if (file->f_op->fsync && !(lo->lo_flags &LO_FLAGS_READ_ONLY )) - lim.features |=BLK_FEAT_WRITE_CACHE ; + lim->features |=BLK_FEAT_WRITE_CACHE ;if (backing_bdev && !bdev_nonrot (backing_bdev)) - lim.features |=BLK_FEAT_ROTATIONAL ; - lim.max_hw_discard_sectors = max_discard_sectors; - lim.max_write_zeroes_sectors = max_discard_sectors; + lim->features |=BLK_FEAT_ROTATIONAL ; + lim->max_hw_discard_sectors = max_discard_sectors; + lim->max_write_zeroes_sectors = max_discard_sectors;if (max_discard_sectors) - lim.discard_granularity = granularity; + lim->discard_granularity = granularity;else - lim.discard_granularity =0 ; -return queue_limits_commit_update (lo->lo_queue, &lim); + lim->discard_granularity =0 ; } static int loop_configure(struct loop_device *lo, blk_mode_t mode,
@@ -1019,6 +1017,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, {struct file *file =fget (config->fd);struct address_space *mapping; +struct queue_limits lim;int error;loff_t size;bool partscan;
@@ -1090,7 +1089,9 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, lo->old_gfp_mask =mapping_gfp_mask (mapping);mapping_set_gfp_mask (mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); - error =loop_reconfigure_limits (lo, config->block_size); + lim =queue_limits_start_update (lo->lo_queue); +loop_update_limits (lo, &lim, config->block_size); + error =queue_limits_commit_update (lo->lo_queue, &lim);if (error) goto out_unlock;
@@ -1458,6 +1459,7 @@ static int loop_set_dio(struct loop_device *lo, unsigned long arg)static int loop_set_block_size (struct loop_device *lo,unsigned long arg) { +struct queue_limits lim;int err =0 ;if (lo->lo_state != Lo_bound)
@@ -1470,7 +1472,9 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)invalidate_bdev (lo->lo_device);blk_mq_freeze_queue (lo->lo_queue); - err =loop_reconfigure_limits (lo, arg); + lim =queue_limits_start_update (lo->lo_queue); +loop_update_limits (lo, &lim, arg); + err =queue_limits_commit_update (lo->lo_queue, &lim);loop_update_dio (lo);blk_mq_unfreeze_queue (lo->lo_queue);
Signature · 1 line
2.45.2
Re: [PATCH 10/11] loop: refactor queue limits updates
Quoted 9 lines · Christoph Hellwig
Replace
loop_reconfigure_limitswith a slightly less encompassingloop_update_limitsthat expects the aller to acquire and commit the queue limits to prepare for sorting out the freeze vs limits lock ordering.Signed-off-by Christoph Hellwig <[email protected]>Reviewed-by Ming Lei <[email protected]>Reviewed-by Damien Le Moal <[email protected]>Reviewed-by Johannes Thumshirn <[email protected]>
Maybe a typo: s/aller/caller/g, otherwise looks good to me:
Christoph Hellwig
maintainerPATCH 11/11 loop: fix queue freeze vs limits lock order
In reply to Christoph HellwigMatch the locking order used by the core block code by only freezing the queue after taking the limits lock using the queue_limits_commit_update_frozen helper and document the callers that do not freeze the queue at all.
--- drivers/block/loop.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-)
drivers/block/loop.c +16 -2
@@ -311,6 +311,13 @@ static void loop_clear_limits(struct loop_device *lo, int mode) lim.discard_granularity =0 ; } +/* +* XXX: this updates the queue limits without freezing the queue, which +* is against the locking protocol and dangerous. But we can't just +* freeze the queue as we're inside the ->queue_rq method here. So this +* should move out into a workqueue unless we get the file operations to +* advertise if they support specific fallocate operations. +*/ queue_limits_commit_update (lo->lo_queue, &lim); }
@@ -1091,6 +1098,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, lim =queue_limits_start_update (lo->lo_queue);loop_update_limits (lo, &lim, config->block_size); +/* No need to freeze the queue as the device isn't bound yet. */ error =queue_limits_commit_update (lo->lo_queue, &lim);if (error) goto out_unlock;
@@ -1151,7 +1159,12 @@ static void __loop_clr_fd(struct loop_device *lo) lo->lo_sizelimit =0 ;memset (lo->lo_file_name,0 ,LO_NAME_SIZE ); -/* reset the block size to the default */ +/* +* Reset the block size to the default. +* +* No queue freezing needed because this is called from the final +* ->release call only, so there can't be any outstanding I/O. +*/ lim =queue_limits_start_update (lo->lo_queue); lim.logical_block_size =SECTOR_SIZE ; lim.physical_block_size =SECTOR_SIZE ;
@@ -1471,9 +1484,10 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)sync_blockdev (lo->lo_device);invalidate_bdev (lo->lo_device); -blk_mq_freeze_queue (lo->lo_queue); lim =queue_limits_start_update (lo->lo_queue);loop_update_limits (lo, &lim, arg); + +blk_mq_freeze_queue (lo->lo_queue); err =queue_limits_commit_update (lo->lo_queue, &lim);loop_update_dio (lo);blk_mq_unfreeze_queue (lo->lo_queue);
Signature · 1 line
2.45.2
Martin K. Petersen
Reviewed-byChristoph,
Quoted 3 lines
this is my version of Damien's "Fix queue freeze and limit locking order". A lot looks very similar, but it was done independently based on the previous discussion.
With the minor editorial changes addressed:
Signature · 1 line
Martin K. Petersen Oracle Linux Engineering