From 59a55a63c24624c7ad268f12c8f82d142ef6a6d4 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 14 Mar 2024 15:24:13 +0100 Subject: fs,block: get holder during claim Now that we open block devices as files we need to deal with the realities that closing is a deferred operation. An operation on the block device such as e.g., freeze, thaw, or removal that runs concurrently with umount, tries to acquire a stable reference on the holder. The holder might already be gone though. Make that reliable by grabbing a passive reference to the holder during bdev_open() and releasing it during bdev_release(). Fixes: f3a608827d1f ("bdev: open block device as files") # mainline only Reported-by: Christoph Hellwig Link: https://lore.kernel.org/r/ZfEQQ9jZZVes0WCZ@infradead.org Reviewed-by: Jan Kara Reviewed-by: Christoph Hellwig Tested-by: Yi Zhang Reported-by: https://lore.kernel.org/r/CAHj4cs8tbDwKRwfS1=DmooP73ysM__xAb2PQc6XsAmWR+VuYmg@mail.gmail.com Link: https://lore.kernel.org/r/20240315-freibad-annehmbar-ca68c375af91@brauner Signed-off-by: Christian Brauner --- block/bdev.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'block') diff --git a/block/bdev.c b/block/bdev.c index e7adaaf1c219..7a5f611c3d2e 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -583,6 +583,9 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder, mutex_unlock(&bdev->bd_holder_lock); bd_clear_claiming(whole, holder); mutex_unlock(&bdev_lock); + + if (hops && hops->get_holder) + hops->get_holder(holder); } /** @@ -605,6 +608,7 @@ EXPORT_SYMBOL(bd_abort_claiming); static void bd_end_claim(struct block_device *bdev, void *holder) { struct block_device *whole = bdev_whole(bdev); + const struct blk_holder_ops *hops = bdev->bd_holder_ops; bool unblock = false; /* @@ -627,6 +631,9 @@ static void bd_end_claim(struct block_device *bdev, void *holder) whole->bd_holder = NULL; mutex_unlock(&bdev_lock); + if (hops && hops->put_holder) + hops->put_holder(holder); + /* * If this was the last claim, remove holder link and unblock evpoll if * it was a write holder. -- cgit v1.2.3 From dc53d9eac1db76fd27b1fcee1f64c840cf82b468 Mon Sep 17 00:00:00 2001 From: John Garry Date: Mon, 25 Mar 2024 08:35:01 +0000 Subject: block: Make blk_rq_set_mixed_merge() static Since commit 8e756373d7c8 ("block: Move bio merge related functions into blk-merge.c"), blk_rq_set_mixed_merge() has only been referenced in blk-merge.c, so make it static. Signed-off-by: John Garry Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20240325083501.2816408-1-john.g.garry@oracle.com Signed-off-by: Jens Axboe --- block/blk-merge.c | 2 +- block/blk.h | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'block') diff --git a/block/blk-merge.c b/block/blk-merge.c index 2a06fd33039d..4e3483a16b75 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -726,7 +726,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req, * which can be mixed are set in each bio and mark @rq as mixed * merged. */ -void blk_rq_set_mixed_merge(struct request *rq) +static void blk_rq_set_mixed_merge(struct request *rq) { blk_opf_t ff = rq->cmd_flags & REQ_FAILFAST_MASK; struct bio *bio; diff --git a/block/blk.h b/block/blk.h index 5cac4e29ae17..d9f584984bc4 100644 --- a/block/blk.h +++ b/block/blk.h @@ -339,7 +339,6 @@ int ll_back_merge_fn(struct request *req, struct bio *bio, bool blk_attempt_req_merge(struct request_queue *q, struct request *rq, struct request *next); unsigned int blk_recalc_rq_segments(struct request *rq); -void blk_rq_set_mixed_merge(struct request *rq); bool blk_rq_merge_ok(struct request *rq, struct bio *bio); enum elv_merge blk_try_merge(struct request *rq, struct bio *bio); -- cgit v1.2.3 From 038105a200689ae07eb9e804ca2295e628a45820 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 26 Mar 2024 07:07:45 +0100 Subject: block: don't reject too large max_user_sectors in blk_validate_limits We already cap down the actual max_sectors to the max of the hardware and user limit, so don't reject the configuration. Signed-off-by: Christoph Hellwig Reviewed-by: John Garry Reviewed-by: Damien Le Moal Link: https://lore.kernel.org/r/20240326060745.2349154-1-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-settings.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'block') diff --git a/block/blk-settings.c b/block/blk-settings.c index 3c7d8d638ab5..cdbaef159c4b 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -146,8 +146,7 @@ static int blk_validate_limits(struct queue_limits *lim) max_hw_sectors = min_not_zero(lim->max_hw_sectors, lim->max_dev_sectors); if (lim->max_user_sectors) { - if (lim->max_user_sectors > max_hw_sectors || - lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE) + if (lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE) return -EINVAL; lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors); } else { -- cgit v1.2.3 From 55251fbdf0146c252ceff146a1bb145546f3e034 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 28 Mar 2024 09:43:40 +0900 Subject: block: Do not force full zone append completion in req_bio_endio() This reverts commit 748dc0b65ec2b4b7b3dbd7befcc4a54fdcac7988. Partial zone append completions cannot be supported as there is no guarantees that the fragmented data will be written sequentially in the same manner as with a full command. Commit 748dc0b65ec2 ("block: fix partial zone append completion handling in req_bio_endio()") changed req_bio_endio() to always advance a partially failed BIO by its full length, but this can lead to incorrect accounting. So revert this change and let low level device drivers handle this case by always failing completely zone append operations. With this revert, users will still see an IO error for a partially completed zone append BIO. Fixes: 748dc0b65ec2 ("block: fix partial zone append completion handling in req_bio_endio()") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20240328004409.594888-2-dlemoal@kernel.org Signed-off-by: Jens Axboe --- block/blk-mq.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'block') diff --git a/block/blk-mq.c b/block/blk-mq.c index 555ada922cf0..32afb87efbd0 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -770,16 +770,11 @@ static void req_bio_endio(struct request *rq, struct bio *bio, /* * Partial zone append completions cannot be supported as the * BIO fragments may end up not being written sequentially. - * For such case, force the completed nbytes to be equal to - * the BIO size so that bio_advance() sets the BIO remaining - * size to 0 and we end up calling bio_endio() before returning. */ - if (bio->bi_iter.bi_size != nbytes) { + if (bio->bi_iter.bi_size != nbytes) bio->bi_status = BLK_STS_IOERR; - nbytes = bio->bi_iter.bi_size; - } else { + else bio->bi_iter.bi_sector = rq->__sector; - } } bio_advance(bio, nbytes); -- cgit v1.2.3