From db04e18dbb0146d3c753dc05f7233350375bbc48 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 19 Aug 2020 14:34:03 +0200 Subject: block: Make request_queue.rpm_status an enum request_queue.rpm_status is assigned values of the rpm_status enum only, so reflect that in its type. Note that including is (currently) a no-op, as it is already included through and , but it is better to play it safe. Signed-off-by: Geert Uytterhoeven Acked-by: Rafael J. Wysocki Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bb5636cc17b9..0a1730b30ad2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -24,6 +24,7 @@ #include #include #include +#include struct module; struct scsi_ioctl_command; @@ -458,7 +459,7 @@ struct request_queue { #ifdef CONFIG_PM struct device *dev; - int rpm_status; + enum rpm_status rpm_status; unsigned int nr_pending; #endif -- cgit v1.2.3 From 7b8917f5e29c377be1db5680249fe30e038cb3eb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 31 Aug 2020 20:02:33 +0200 Subject: block: remove the alignment_offset field from struct hd_struct The alignment offset is only used in slow path callers, so just calculate it on the fly. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0a1730b30ad2..ba1f5f5e11c6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1456,10 +1456,9 @@ static inline int bdev_alignment_offset(struct block_device *bdev) if (q->limits.misaligned) return -1; - if (bdev != bdev->bd_contains) - return bdev->bd_part->alignment_offset; - + return queue_limit_alignment_offset(&q->limits, + bdev->bd_part->start_sect); return q->limits.alignment_offset; } -- cgit v1.2.3 From 7cf34d97ab45203b975396393ded9d3867dfa8bf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 31 Aug 2020 20:02:34 +0200 Subject: block: remove the discard_alignment field from struct hd_struct The alignment offset is only used in slow path callers, so just calculate it on the fly. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ba1f5f5e11c6..d0d61bc81615 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1498,8 +1498,8 @@ static inline int bdev_discard_alignment(struct block_device *bdev) struct request_queue *q = bdev_get_queue(bdev); if (bdev != bdev->bd_contains) - return bdev->bd_part->discard_alignment; - + return queue_limit_discard_alignment(&q->limits, + bdev->bd_part->start_sect); return q->limits.discard_alignment; } -- cgit v1.2.3 From bccf5e26d99c28980bd6ced474422a1b18402263 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 19 Aug 2020 23:20:26 +0800 Subject: blk-mq: Record nr_active_requests per queue for when using shared sbitmap The per-hctx nr_active value can no longer be used to fairly assign a share of tag depth per request queue for when using a shared sbitmap, as it does not consider that the tags are shared tags over all hctx's. For this case, record the nr_active_requests per request_queue, and make the judgement based on that value. Co-developed-with: Kashyap Desai Signed-off-by: John Garry Tested-by: Don Brace #SCSI resv cmds patches used Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d0d61bc81615..6277aee2aeaa 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -485,6 +485,8 @@ struct request_queue { struct timer_list timeout; struct work_struct timeout_work; + atomic_t nr_active_requests_shared_sbitmap; + struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS); -- cgit v1.2.3 From f1b49fdc1c64db110aa1315831e5fe0f8599fa56 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 19 Aug 2020 23:20:27 +0800 Subject: blk-mq: Record active_queues_shared_sbitmap per tag_set for when using shared sbitmap For when using a shared sbitmap, no longer should the number of active request queues per hctx be relied on for when judging how to share the tag bitmap. Instead maintain the number of active request queues per tag_set, and make the judgement based on that. Originally-from: Kashyap Desai Signed-off-by: John Garry Tested-by: Don Brace #SCSI resv cmds patches used Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6277aee2aeaa..7d82959e7b86 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -618,6 +618,7 @@ struct request_queue { #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ #define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ #define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ +#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP)) -- cgit v1.2.3 From 384d87ef2c954fc58e6c5fd8253e4a1984f5fe02 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 4 Sep 2020 10:58:52 +0200 Subject: block: Do not discard buffers under a mounted filesystem Discarding blocks and buffers under a mounted filesystem is hardly anything admin wants to do. Usually it will confuse the filesystem and sometimes the loss of buffer_head state (including b_private field) can even cause crashes like: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 PGD 0 P4D 0 Oops: 0002 [#1] SMP PTI CPU: 4 PID: 203778 Comm: jbd2/dm-3-8 Kdump: loaded Tainted: G O --------- - - 4.18.0-147.5.0.5.h126.eulerosv2r9.x86_64 #1 Hardware name: Huawei RH2288H V3/BC11HGSA0, BIOS 1.57 08/11/2015 RIP: 0010:jbd2_journal_grab_journal_head+0x1b/0x40 [jbd2] ... Call Trace: __jbd2_journal_insert_checkpoint+0x23/0x70 [jbd2] jbd2_journal_commit_transaction+0x155f/0x1b60 [jbd2] kjournald2+0xbd/0x270 [jbd2] So if we don't have block device open with O_EXCL already, claim the block device while we truncate buffer cache. This makes sure any exclusive block device user (such as filesystem) cannot operate on the device while we are discarding buffer cache. Reported-by: Ye Bin Signed-off-by: Jan Kara Reviewed-by: Christoph Hellwig [axboe: fix !CONFIG_BLOCK error in truncate_bdev_range()] Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7d82959e7b86..37ec5a73d027 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1987,11 +1987,18 @@ void bdput(struct block_device *); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); +int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, + loff_t lend); int sync_blockdev(struct block_device *bdev); #else static inline void invalidate_bdev(struct block_device *bdev) { } +static inline int truncate_bdev_range(struct block_device *bdev, fmode_t mode, + loff_t lstart, loff_t lend) +{ + return 0; +} static inline int sync_blockdev(struct block_device *bdev) { return 0; -- cgit v1.2.3 From 7b26410b05f8c262688de8a689ba8e5d0c3cff01 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 31 Aug 2020 15:27:23 -0700 Subject: block: introduce part_[begin|end]_io_acct These functions can be used to enable iostat for partitions on devices like md, bcache. Signed-off-by: Song Liu Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 37ec5a73d027..5bd96fbab9b4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1933,6 +1933,11 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time); +unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part, + struct bio *bio); +void part_end_io_acct(struct hd_struct *part, struct bio *bio, + unsigned long start_time); + /** * bio_start_io_acct - start I/O accounting for bio based drivers * @bio: bio to start account for -- cgit v1.2.3 From 07d098e6bbad04030dab5b3e64149601fcb063ce Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Mon, 21 Sep 2020 22:32:49 -0400 Subject: block: allow 'chunk_sectors' to be non-power-of-2 It is possible, albeit more unlikely, for a block device to have a non power-of-2 for chunk_sectors (e.g. 10+2 RAID6 with 128K chunk_sectors, which results in a full-stripe size of 1280K. This causes the RAID6's io_opt to be advertised as 1280K, and a stacked device _could_ then be made to use a blocksize, aka chunk_sectors, that matches non power-of-2 io_opt of underlying RAID6 -- resulting in stacked device's chunk_sectors being a non power-of-2). Update blk_queue_chunk_sectors() and blk_max_size_offset() to accommodate drivers that need a non power-of-2 chunk_sectors. Reviewed-by: Ming Lei Reviewed-by: Martin K. Petersen Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5bd96fbab9b4..6e19a7aa1672 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1063,11 +1063,17 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, static inline unsigned int blk_max_size_offset(struct request_queue *q, sector_t offset) { - if (!q->limits.chunk_sectors) + unsigned int chunk_sectors = q->limits.chunk_sectors; + + if (!chunk_sectors) return q->limits.max_sectors; - return min(q->limits.max_sectors, (unsigned int)(q->limits.chunk_sectors - - (offset & (q->limits.chunk_sectors - 1)))); + if (likely(is_power_of_2(chunk_sectors))) + chunk_sectors -= offset & (chunk_sectors - 1); + else + chunk_sectors -= sector_div(offset, chunk_sectors); + + return min(q->limits.max_sectors, chunk_sectors); } static inline unsigned int blk_rq_get_max_sectors(struct request *rq, -- cgit v1.2.3 From 1fb1a2ad75e33e646d33e42b9ed17d879d472859 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 21 Sep 2020 09:19:58 +0200 Subject: block: mark blkdev_get static There are no users outside the core block code left now. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6e19a7aa1672..be5ef6f4ba19 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1981,7 +1981,6 @@ void blkdev_show(struct seq_file *seqf, off_t offset); #define BLKDEV_MAJOR_MAX 0 #endif -int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder); struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); -- cgit v1.2.3 From c2e4cd57cfa1f627b786c764d185fff85fd12be9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:34 +0200 Subject: block: lift setting the readahead size into the block layer Drivers shouldn't really mess with the readahead size, as that is a VM concept. Instead set it based on the optimal I/O size by lifting the algorithm from the md driver when registering the disk. Also set bdi->io_pages there as well by applying the same scheme based on max_sectors. To ensure the limits work well for stacking drivers a new helper is added to update the readahead limits from the block limits, which is also called from disk_stack_limits. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Jan Kara Reviewed-by: Mike Snitzer Reviewed-by: Martin K. Petersen Acked-by: Coly Li Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index be5ef6f4ba19..282f5ca424f1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1140,6 +1140,7 @@ extern void blk_queue_max_zone_append_sectors(struct request_queue *q, extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); +void blk_queue_update_readahead(struct request_queue *q); extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); -- cgit v1.2.3 From 1cb039f3dc1619eb795c54aad0a98fdb379b4237 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:38 +0200 Subject: bdi: replace BDI_CAP_STABLE_WRITES with a queue and a sb flag The BDI_CAP_STABLE_WRITES is one of the few bits of information in the backing_dev_info shared between the block drivers and the writeback code. To help untangling the dependency replace it with a queue flag and a superblock flag derived from it. This also helps with the case of e.g. a file system requiring stable writes due to its own checksumming, but not forcing it on other users of the block device like the swap code. One downside is that we an't support the stable_pages_required bdi attribute in sysfs anymore. It is replaced with a queue attribute which also is writable for easier testing. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 282f5ca424f1..8e77f12de522 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -606,6 +606,7 @@ struct request_queue { #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ +#define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ #define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ #define QUEUE_FLAG_WC 17 /* Write back caching */ #define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ @@ -635,6 +636,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_noxmerges(q) \ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) +#define blk_queue_stable_writes(q) \ + test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) -- cgit v1.2.3 From fa01b1e9733fd59ecb8b5b6d85dfb481d2025fbf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Sep 2020 07:40:57 +0200 Subject: block: add a bdev_is_partition helper Add a littler helper to make the somewhat arcane bd_contains checks a little more obvious. Signed-off-by: Christoph Hellwig Acked-by: Ulf Hansson Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8e77f12de522..33f283885ba5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1353,6 +1353,11 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, extern int blk_verify_command(unsigned char *cmd, fmode_t mode); +static inline bool bdev_is_partition(struct block_device *bdev) +{ + return bdev->bd_partno; +} + enum blk_default_limits { BLK_MAX_SEGMENTS = 128, BLK_SAFE_MAX_SECTORS = 255, @@ -1469,7 +1474,7 @@ static inline int bdev_alignment_offset(struct block_device *bdev) if (q->limits.misaligned) return -1; - if (bdev != bdev->bd_contains) + if (bdev_is_partition(bdev)) return queue_limit_alignment_offset(&q->limits, bdev->bd_part->start_sect); return q->limits.alignment_offset; @@ -1510,7 +1515,7 @@ static inline int bdev_discard_alignment(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); - if (bdev != bdev->bd_contains) + if (bdev_is_partition(bdev)) return queue_limit_discard_alignment(&q->limits, bdev->bd_part->start_sect); return q->limits.discard_alignment; -- cgit v1.2.3 From 021a24460dc28e7412aecfae89f60e1847e685c0 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 23 Sep 2020 16:06:51 -0400 Subject: block: add QUEUE_FLAG_NOWAIT Add QUEUE_FLAG_NOWAIT to allow a block device to advertise support for REQ_NOWAIT. Bio-based devices may set QUEUE_FLAG_NOWAIT where applicable. Update QUEUE_FLAG_MQ_DEFAULT to include QUEUE_FLAG_NOWAIT. Also update submit_bio_checks() to verify it is set for REQ_NOWAIT bios. Reported-by: Konstantin Khlebnikov Suggested-by: Christoph Hellwig Signed-off-by: Mike Snitzer Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 33f283885ba5..d5a3e1a4c2f7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -619,10 +619,12 @@ struct request_queue { #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ #define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ #define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ -#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ +#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ +#define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */ #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_SAME_COMP)) + (1 << QUEUE_FLAG_SAME_COMP) | \ + (1 << QUEUE_FLAG_NOWAIT)) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); @@ -664,6 +666,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) +#define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); -- cgit v1.2.3 From 10ed16662da9e28a33b6c991c36c6b323b03dd5b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 25 Sep 2020 18:06:18 +0200 Subject: block: add a bdget_part helper All remaining callers of bdget() outside of fs/block_dev.c want to get a reference to the struct block_device for a given struct hd_struct. Add a helper just for that and then mark bdget static. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d5a3e1a4c2f7..cf80e61b4c5e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -2003,7 +2003,7 @@ void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, void blkdev_put(struct block_device *bdev, fmode_t mode); struct block_device *I_BDEV(struct inode *inode); -struct block_device *bdget(dev_t); +struct block_device *bdget_part(struct hd_struct *part); struct block_device *bdgrab(struct block_device *bdev); void bdput(struct block_device *); -- cgit v1.2.3 From 0549e87c30ae0d43d7e10424f2222bcd8bbe986d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 1 Oct 2020 23:48:42 +0800 Subject: block: move 'q_usage_counter' into front of 'request_queue' The field of 'q_usage_counter' is always fetched in fast path of every block driver, and move it into front of 'request_queue', so it can be fetched into 1st cacheline of 'request_queue' instance. Signed-off-by: Ming Lei Tested-by: Veronika Kabatova Reviewed-by: Christoph Hellwig Cc: Sagi Grimberg Cc: Tejun Heo Cc: Christoph Hellwig Cc: Jens Axboe Cc: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cf80e61b4c5e..5fc940423e5a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -397,6 +397,8 @@ struct request_queue { struct request *last_merge; struct elevator_queue *elevator; + struct percpu_ref q_usage_counter; + struct blk_queue_stats *stats; struct rq_qos *rq_qos; @@ -569,7 +571,6 @@ struct request_queue { * percpu_ref_kill() and percpu_ref_reinit(). */ struct mutex mq_freeze_lock; - struct percpu_ref q_usage_counter; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; -- cgit v1.2.3 From 92cf2fd156b273879198bb1d7e58851f822c481f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 6 Oct 2020 09:07:17 +0200 Subject: block: remove the unused blk_integrity_merge_rq export Also move the definition from the public blkdev.h to the private block/blk.h header. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5fc940423e5a..6a6d9ea7420a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1664,8 +1664,6 @@ extern int blk_integrity_compare(struct gendisk *, struct gendisk *); extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, struct scatterlist *); extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); -extern bool blk_integrity_merge_rq(struct request_queue *, struct request *, - struct request *); extern bool blk_integrity_merge_bio(struct request_queue *, struct request *, struct bio *); @@ -1795,12 +1793,6 @@ static inline unsigned short queue_max_integrity_segments(const struct request_q { return 0; } -static inline bool blk_integrity_merge_rq(struct request_queue *rq, - struct request *r1, - struct request *r2) -{ - return true; -} static inline bool blk_integrity_merge_bio(struct request_queue *rq, struct request *r, struct bio *b) -- cgit v1.2.3 From d59da41998bc794441d7c039a059ed6eb0c2dc4d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 6 Oct 2020 09:07:18 +0200 Subject: block: remove the unused blk_integrity_merge_bio export Also move the definition from the public blkdev.h to the private block/blk.h header. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6a6d9ea7420a..cda786fa4341 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1664,8 +1664,6 @@ extern int blk_integrity_compare(struct gendisk *, struct gendisk *); extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, struct scatterlist *); extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); -extern bool blk_integrity_merge_bio(struct request_queue *, struct request *, - struct bio *); static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { @@ -1793,12 +1791,6 @@ static inline unsigned short queue_max_integrity_segments(const struct request_q { return 0; } -static inline bool blk_integrity_merge_bio(struct request_queue *rq, - struct request *r, - struct bio *b) -{ - return true; -} static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) -- cgit v1.2.3 From 6fcd669514794da08ce6bfa272b6ec9b33cb543d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Aug 2020 09:56:58 +0200 Subject: block: optimize blk_queue_zoned_model for !CONFIG_BLK_DEV_ZONED Always return BLK_ZONED_NONE if zoned device support is not enabled. This allows various compiler optimizations including the dead code elimination that we so like for avoiding ifdefs. Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Chaitanya Kulkarni Reviewed-by: Damien Le Moal --- include/linux/blkdev.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8e77f12de522..1b81b2766858 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -692,7 +692,9 @@ static inline bool queue_is_mq(struct request_queue *q) static inline enum blk_zoned_model blk_queue_zoned_model(struct request_queue *q) { - return q->limits.zoned; + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) + return q->limits.zoned; + return BLK_ZONED_NONE; } static inline bool blk_queue_is_zoned(struct request_queue *q) -- cgit v1.2.3 From fe6f0cdc49263ae61cd3d33399662808c2398e86 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 7 Oct 2020 21:35:08 +0900 Subject: block: soft limit zone-append sectors as well Martin rightfully noted that for normal filesystem IO we have soft limits in place, to prevent them from getting too big and not lead to unpredictable latencies. For zone append we only have the hardware limit in place. Cap the max sectors we submit via zone-append to the maximal number of sectors if the second limit is lower. Reported-by: Martin K. Petersen Signed-off-by: Johannes Thumshirn Reviewed-by: Damien Le Moal Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/linux-btrfs/yq1k0w8g3rw.fsf@ca-mkp.ca.oracle.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cda786fa4341..6bd667c34777 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1407,7 +1407,10 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q) { - return q->limits.max_zone_append_sectors; + + const struct queue_limits *l = &q->limits; + + return min(l->max_zone_append_sectors, l->max_sectors); } static inline unsigned queue_logical_block_size(const struct request_queue *q) -- cgit v1.2.3 From b296a6d53339a79082c1d2c1761e948e8b3def69 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 15 Oct 2020 20:10:21 -0700 Subject: kernel.h: split out min()/max() et al. helpers kernel.h is being used as a dump for all kinds of stuff for a long time. Here is the attempt to start cleaning it up by splitting out min()/max() et al. helpers. At the same time convert users in header and lib folder to use new header. Though for time being include new header back to kernel.h to avoid twisted indirected includes for other existing users. Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Cc: "Rafael J. Wysocki" Cc: Steven Rostedt Cc: Rasmus Villemoes Cc: Joe Perches Cc: Linus Torvalds Link: https://lkml.kernel.org/r/20200910164152.GA1891694@smile.fi.intel.com Signed-off-by: Linus Torvalds --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c09375e0a0eb..639cae2c158b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From e00adcadf3af7a8335026d71ab9f0e0a922191ac Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Nov 2020 11:00:11 +0100 Subject: block: add a new set_read_only method Add a new method to allow for driver-specific processing when setting or clearing the block device read-only state. This allows to replace the cumbersome and error-prone override of the whole ioctl implementation. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 639cae2c158b..5c1ba8a8d2bc 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1850,6 +1850,7 @@ struct block_device_operations { void (*unlock_native_capacity) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); + int (*set_read_only)(struct block_device *bdev, bool ro); /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, -- cgit v1.2.3 From a7cb3d2f09c8405aed59d97a7d02cebea43cd3c7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Nov 2020 11:00:18 +0100 Subject: block: remove __blkdev_driver_ioctl Just open code it in the few callers. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5c1ba8a8d2bc..05b346a68c2e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1867,8 +1867,6 @@ extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t, #define blkdev_compat_ptr_ioctl NULL #endif -extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, - unsigned long); extern int bdev_read_page(struct block_device *, sector_t, struct page *); extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); -- cgit v1.2.3 From 040f04bd2e825f1d80b14a0e0ac3d830339eb779 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Nov 2020 11:54:06 +0100 Subject: fs: simplify freeze_bdev/thaw_bdev Store the frozen superblock in struct block_device to avoid the awkward interface that can return a sb only used a cookie, an ERR_PTR or NULL. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Acked-by: Chao Yu [f2fs] Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 05b346a68c2e..12810a19edeb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -2020,7 +2020,7 @@ static inline int sync_blockdev(struct block_device *bdev) #endif int fsync_bdev(struct block_device *bdev); -struct super_block *freeze_bdev(struct block_device *bdev); -int thaw_bdev(struct block_device *bdev, struct super_block *sb); +int freeze_bdev(struct block_device *bdev); +int thaw_bdev(struct block_device *bdev); #endif /* _LINUX_BLKDEV_H */ -- cgit v1.2.3 From 4e7b5671c6a883d94b5428e1a9c141bbd56cb2a6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 23 Nov 2020 13:38:40 +0100 Subject: block: remove i_bdev Switch the block device lookup interfaces to directly work with a dev_t so that struct block_device references are only acquired by the blkdev_get variants (and the blk-cgroup special case). This means that we now don't need an extra reference in the inode and can generally simplify handling of struct block_device to keep the lookups contained in the core block layer code. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Acked-by: Tejun Heo Acked-by: Coly Li [bcache] Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 12810a19edeb..bdd7339bcda4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1973,7 +1973,7 @@ int bdev_read_only(struct block_device *bdev); int set_blocksize(struct block_device *bdev, int size); const char *bdevname(struct block_device *bdev, char *buffer); -struct block_device *lookup_bdev(const char *); +int lookup_bdev(const char *pathname, dev_t *dev); void blkdev_show(struct seq_file *seqf, off_t offset); -- cgit v1.2.3 From 22ae8ce8b89241c94ac00c237752c0ffa37ba5ae Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 26 Nov 2020 09:23:26 +0100 Subject: block: simplify bdev/disk lookup in blkdev_get To simplify block device lookup and a few other upcoming areas, make sure that we always have a struct block_device available for each disk and each partition, and only find existing block devices in bdget. The only downside of this is that each device and partition uses a little more memory. The upside will be that a lot of code can be simplified. With that all we need to look up the block device is to lookup the inode and do a few sanity checks on the gendisk, instead of the separate lookup for the gendisk. For blk-cgroup which wants to access a gendisk without opening it, a new blkdev_{get,put}_no_open low-level interface is added to replace the previous get_gendisk use. Note that the change to look up block device directly instead of the two step lookup using struct gendisk causes a subtile change in behavior: accessing a non-existing partition on an existing block device can now cause a call to request_module. That call is harmless, and in practice no recent system will access these nodes as they aren't created by udev and static /dev/ setups are unusual. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bdd7339bcda4..5d48b92f5e43 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1994,6 +1994,12 @@ void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, void *holder); void blkdev_put(struct block_device *bdev, fmode_t mode); +/* just for blk-cgroup, don't use elsewhere */ +struct block_device *blkdev_get_no_open(dev_t dev); +void blkdev_put_no_open(struct block_device *bdev); + +struct block_device *bdev_alloc(struct gendisk *disk, u8 partno); +void bdev_add(struct block_device *bdev, dev_t dev); struct block_device *I_BDEV(struct inode *inode); struct block_device *bdget_part(struct hd_struct *part); struct block_device *bdgrab(struct block_device *bdev); -- cgit v1.2.3 From 37c3fc9abb25cd767ad5b048358336ac89488c16 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 25 Nov 2020 21:20:08 +0100 Subject: block: simplify the block device claiming interface Stop passing the whole device as a separate argument given that it can be trivially deducted and cleanup the !holder debug check. Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5d48b92f5e43..43a25d855e04 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1988,10 +1988,8 @@ void blkdev_show(struct seq_file *seqf, off_t offset); struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder); struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); -int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole, - void *holder); -void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, - void *holder); +int bd_prepare_to_claim(struct block_device *bdev, void *holder); +void bd_abort_claiming(struct block_device *bdev, void *holder); void blkdev_put(struct block_device *bdev, fmode_t mode); /* just for blk-cgroup, don't use elsewhere */ -- cgit v1.2.3 From 29ff57c61094e7bbd921ab10b5a99dce9a0132e0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Nov 2020 09:34:24 +0100 Subject: block: move the start_sect field to struct block_device Move the start_sect field to struct block_device in preparation of killing struct hd_struct. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 43a25d855e04..619adea57098 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1488,7 +1488,7 @@ static inline int bdev_alignment_offset(struct block_device *bdev) return -1; if (bdev_is_partition(bdev)) return queue_limit_alignment_offset(&q->limits, - bdev->bd_part->start_sect); + bdev->bd_start_sect); return q->limits.alignment_offset; } @@ -1529,7 +1529,7 @@ static inline int bdev_discard_alignment(struct block_device *bdev) if (bdev_is_partition(bdev)) return queue_limit_discard_alignment(&q->limits, - bdev->bd_part->start_sect); + bdev->bd_start_sect); return q->limits.discard_alignment; } -- cgit v1.2.3 From 8446fe9255be821cb38ffd306d7e8edc4b9ea662 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Nov 2020 09:36:54 +0100 Subject: block: switch partition lookup to use struct block_device Use struct block_device to lookup partitions on a disk. This removes all usage of struct hd_struct from the I/O path. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Acked-by: Coly Li [bcache] Acked-by: Chao Yu [f2fs] Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 619adea57098..1d4be1fc6007 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -191,7 +191,7 @@ struct request { }; struct gendisk *rq_disk; - struct hd_struct *part; + struct block_device *part; #ifdef CONFIG_BLK_RQ_ALLOC_TIME /* Time that the first bio started allocating this request. */ u64 alloc_time_ns; @@ -1943,9 +1943,9 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time); -unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part, - struct bio *bio); -void part_end_io_acct(struct hd_struct *part, struct bio *bio, +unsigned long part_start_io_acct(struct gendisk *disk, + struct block_device **part, struct bio *bio); +void part_end_io_acct(struct block_device *part, struct bio *bio, unsigned long start_time); /** -- cgit v1.2.3 From 0d02129e76edf91cf04fabf1efbc3a9a1f1d729a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 27 Nov 2020 16:43:51 +0100 Subject: block: merge struct block_device and struct hd_struct Instead of having two structures that represent each block device with different life time rules, merge them into a single one. This also greatly simplifies the reference counting rules, as we can use the inode reference count as the main reference count for the new struct block_device, with the device model reference front ending it for device model interaction. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1d4be1fc6007..17cedf0dc83d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1999,7 +1999,6 @@ void blkdev_put_no_open(struct block_device *bdev); struct block_device *bdev_alloc(struct gendisk *disk, u8 partno); void bdev_add(struct block_device *bdev, dev_t dev); struct block_device *I_BDEV(struct inode *inode); -struct block_device *bdget_part(struct hd_struct *part); struct block_device *bdgrab(struct block_device *bdev); void bdput(struct block_device *); -- cgit v1.2.3 From 3ee16db390b42b8a21f2ad2ea2518f3469c6e532 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Mon, 30 Nov 2020 10:57:43 -0500 Subject: dm: fix IO splitting Commit 882ec4e609c1 ("dm table: stack 'chunk_sectors' limit to account for target-specific splitting") caused a couple regressions: 1) Using lcm_not_zero() when stacking chunk_sectors was a bug because chunk_sectors must reflect the most limited of all devices in the IO stack. 2) DM targets that set max_io_len but that do _not_ provide an .iterate_devices method no longer had there IO split properly. And commit 5091cdec56fa ("dm: change max_io_len() to use blk_max_size_offset()") also caused a regression where DM no longer supported varied (per target) IO splitting. The implication being the potential for severely reduced performance for IO stacks that use a DM target like dm-cache to hide performance limitations of a slower device (e.g. one that requires 4K IO splitting). Coming full circle: Fix all these issues by discontinuing stacking chunk_sectors up using ti->max_io_len in dm_calculate_queue_limits(), add optional chunk_sectors override argument to blk_max_size_offset() and update DM's max_io_len() to pass ti->max_io_len to its blk_max_size_offset() call. Passing in an optional chunk_sectors override to blk_max_size_offset() allows for code reuse of block's centralized calculation for max IO size based on provided offset and split boundary. Fixes: 882ec4e609c1 ("dm table: stack 'chunk_sectors' limit to account for target-specific splitting") Fixes: 5091cdec56fa ("dm: change max_io_len() to use blk_max_size_offset()") Cc: stable@vger.kernel.org Reported-by: John Dorminy Reported-by: Bruce Johnston Reported-by: Kirill Tkhai Reviewed-by: John Dorminy Signed-off-by: Mike Snitzer Reviewed-by: Jens Axboe --- include/linux/blkdev.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 639cae2c158b..24ae504cf77d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1073,11 +1073,12 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, * file system requests. */ static inline unsigned int blk_max_size_offset(struct request_queue *q, - sector_t offset) + sector_t offset, + unsigned int chunk_sectors) { - unsigned int chunk_sectors = q->limits.chunk_sectors; - - if (!chunk_sectors) + if (!chunk_sectors && q->limits.chunk_sectors) + chunk_sectors = q->limits.chunk_sectors; + else return q->limits.max_sectors; if (likely(is_power_of_2(chunk_sectors))) @@ -1101,7 +1102,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq, req_op(rq) == REQ_OP_SECURE_ERASE) return blk_queue_get_max_sectors(q, req_op(rq)); - return min(blk_max_size_offset(q, offset), + return min(blk_max_size_offset(q, offset, 0), blk_queue_get_max_sectors(q, req_op(rq))); } -- cgit v1.2.3 From 65f33b35722952fa076811d5686bfd8a611a80fa Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 4 Dec 2020 17:21:03 -0500 Subject: block: fix incorrect branching in blk_max_size_offset() If non-zero 'chunk_sectors' is passed in to blk_max_size_offset() that override will be incorrectly ignored. Old blk_max_size_offset() branching, prior to commit 3ee16db390b4, must be used only if passed 'chunk_sectors' override is zero. Fixes: 3ee16db390b4 ("dm: fix IO splitting") Cc: stable@vger.kernel.org # 5.9 Reported-by: John Dorminy Signed-off-by: Mike Snitzer --- include/linux/blkdev.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 24ae504cf77d..033eb5f73b65 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1076,10 +1076,12 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q, sector_t offset, unsigned int chunk_sectors) { - if (!chunk_sectors && q->limits.chunk_sectors) - chunk_sectors = q->limits.chunk_sectors; - else - return q->limits.max_sectors; + if (!chunk_sectors) { + if (q->limits.chunk_sectors) + chunk_sectors = q->limits.chunk_sectors; + else + return q->limits.max_sectors; + } if (likely(is_power_of_2(chunk_sectors))) chunk_sectors -= offset & (chunk_sectors - 1); -- cgit v1.2.3 From a4d34da715e3cb7e0741fe603dcd511bed067e00 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 8 Dec 2020 21:29:50 -0800 Subject: scsi: block: Remove RQF_PREEMPT and BLK_MQ_REQ_PREEMPT Remove flag RQF_PREEMPT and BLK_MQ_REQ_PREEMPT since these are no longer used by any kernel code. Link: https://lore.kernel.org/r/20201209052951.16136-8-bvanassche@acm.org Cc: Can Guo Cc: Stanley Chu Cc: Alan Stern Cc: Ming Lei Cc: Rafael J. Wysocki Cc: Martin Kepplinger Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Jens Axboe Reviewed-by: Can Guo Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/linux/blkdev.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 639cae2c158b..7d4b746f7e6a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -79,9 +79,6 @@ typedef __u32 __bitwise req_flags_t; #define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6)) /* don't call prep for this one */ #define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) -/* set for "ide_preempt" requests and also for requests for which the SCSI - "quiesce" state must be ignored. */ -#define RQF_PREEMPT ((__force req_flags_t)(1 << 8)) /* vaguely specified driver internal error. Ignored by the block layer */ #define RQF_FAILED ((__force req_flags_t)(1 << 10)) /* don't warn about errors */ @@ -430,8 +427,7 @@ struct request_queue { unsigned long queue_flags; /* * Number of contexts that have called blk_set_pm_only(). If this - * counter is above zero then only RQF_PM and RQF_PREEMPT requests are - * processed. + * counter is above zero then only RQF_PM requests are processed. */ atomic_t pm_only; -- cgit v1.2.3 From 52abca64fd9410ea6c9a3a74eab25663b403d7da Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 8 Dec 2020 21:29:51 -0800 Subject: scsi: block: Do not accept any requests while suspended blk_queue_enter() accepts BLK_MQ_REQ_PM requests independent of the runtime power management state. Now that SCSI domain validation no longer depends on this behavior, modify the behavior of blk_queue_enter() as follows: - Do not accept any requests while suspended. - Only process power management requests while suspending or resuming. Submitting BLK_MQ_REQ_PM requests to a device that is runtime suspended causes runtime-suspended devices not to resume as they should. The request which should cause a runtime resume instead gets issued directly, without resuming the device first. Of course the device can't handle it properly, the I/O fails, and the device remains suspended. The problem is fixed by checking that the queue's runtime-PM status isn't RPM_SUSPENDED before allowing a request to be issued, and queuing a runtime-resume request if it is. In particular, the inline blk_pm_request_resume() routine is renamed blk_pm_resume_queue() and the code is unified by merging the surrounding checks into the routine. If the queue isn't set up for runtime PM, or there currently is no restriction on allowed requests, the request is allowed. Likewise if the BLK_MQ_REQ_PM flag is set and the status isn't RPM_SUSPENDED. Otherwise a runtime resume is queued and the request is blocked until conditions are more suitable. [ bvanassche: modified commit message and removed Cc: stable because without the previous patches from this series this patch would break parallel SCSI domain validation + introduced queue_rpm_status() ] Link: https://lore.kernel.org/r/20201209052951.16136-9-bvanassche@acm.org Cc: Jens Axboe Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Can Guo Cc: Stanley Chu Cc: Ming Lei Cc: Rafael J. Wysocki Reported-and-tested-by: Martin Kepplinger Reviewed-by: Hannes Reinecke Reviewed-by: Can Guo Signed-off-by: Alan Stern Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/linux/blkdev.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7d4b746f7e6a..2b6fc3fb3a99 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -692,6 +692,18 @@ static inline bool queue_is_mq(struct request_queue *q) return q->mq_ops; } +#ifdef CONFIG_PM +static inline enum rpm_status queue_rpm_status(struct request_queue *q) +{ + return q->rpm_status; +} +#else +static inline enum rpm_status queue_rpm_status(struct request_queue *q) +{ + return RPM_ACTIVE; +} +#endif + static inline enum blk_zoned_model blk_queue_zoned_model(struct request_queue *q) { -- cgit v1.2.3