From 309dca309fc39a9e3c31b916393b74bd174fd74e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 24 Jan 2021 11:02:34 +0100 Subject: block: store a block_device pointer in struct bio Replace the gendisk pointer in struct bio with a pointer to the newly improved struct block device. From that the gendisk can be trivially accessed with an extra indirection, but it also allows to directly look up all information related to partition remapping. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f94ee3089e01..b55bd534b2e1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1967,7 +1967,8 @@ void part_end_io_acct(struct block_device *part, struct bio *bio, */ static inline unsigned long bio_start_io_acct(struct bio *bio) { - return disk_start_io_acct(bio->bi_disk, bio_sectors(bio), bio_op(bio)); + return disk_start_io_acct(bio->bi_bdev->bd_disk, bio_sectors(bio), + bio_op(bio)); } /** @@ -1977,7 +1978,7 @@ static inline unsigned long bio_start_io_acct(struct bio *bio) */ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) { - return disk_end_io_acct(bio->bi_disk, bio_op(bio), start_time); + return disk_end_io_acct(bio->bi_bdev->bd_disk, bio_op(bio), start_time); } int bdev_read_only(struct block_device *bdev); -- cgit v1.2.3 From 99dfc43ecbf67f12a06512918aaba61d55863efc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 24 Jan 2021 11:02:37 +0100 Subject: block: use ->bi_bdev for bio based I/O accounting Rework the I/O accounting for bio based drivers to use ->bi_bdev. This means all drivers can now simply use bio_start_io_acct to start accounting, and it will take partitions into account automatically. To end I/O account either bio_end_io_acct can be used if the driver never remaps I/O to a different device, or bio_end_io_acct_remapped if the driver did remap the I/O. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 21 ++++----------------- 1 file changed, 4 insertions(+), 17 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b55bd534b2e1..4526b9ef8edb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1954,22 +1954,9 @@ 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 block_device **part, struct bio *bio); -void part_end_io_acct(struct block_device *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 - * - * Returns the start time that should be passed back to bio_end_io_acct(). - */ -static inline unsigned long bio_start_io_acct(struct bio *bio) -{ - return disk_start_io_acct(bio->bi_bdev->bd_disk, bio_sectors(bio), - bio_op(bio)); -} +unsigned long bio_start_io_acct(struct bio *bio); +void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, + struct block_device *orig_bdev); /** * bio_end_io_acct - end I/O accounting for bio based drivers @@ -1978,7 +1965,7 @@ static inline unsigned long bio_start_io_acct(struct bio *bio) */ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) { - return disk_end_io_acct(bio->bi_bdev->bd_disk, bio_op(bio), start_time); + return bio_end_io_acct_remapped(bio, start_time, bio->bi_bdev); } int bdev_read_only(struct block_device *bdev); -- cgit v1.2.3 From 8eeed0b554b9fda61be05b17cbb0b89ea2cbbb65 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Mon, 25 Jan 2021 05:49:57 +0100 Subject: block: remove unnecessary argument from blk_execute_rq_nowait The 'q' is not used since commit a1ce35fa4985 ("block: remove dead elevator code"), also update the comment of the function. And more importantly it never really was needed to start with given that we can trivial derive it from struct request. Cc: target-devel@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: linux-ide@vger.kernel.org Cc: linux-mmc@vger.kernel.org Cc: linux-nvme@lists.infradead.org Cc: linux-nfs@vger.kernel.org Signed-off-by: Guoqing Jiang 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 4526b9ef8edb..623a61239429 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -950,7 +950,7 @@ extern int blk_rq_map_user_iov(struct request_queue *, struct request *, gfp_t); extern void blk_execute_rq(struct request_queue *, struct gendisk *, struct request *, int); -extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, +extern void blk_execute_rq_nowait(struct gendisk *, struct request *, int, rq_end_io_fn *); /* Helper to convert REQ_OP_XXX to its string format XXX */ -- cgit v1.2.3 From 684da7628d93bbdcfba9081b917d99f29ad04c23 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Mon, 25 Jan 2021 05:49:58 +0100 Subject: block: remove unnecessary argument from blk_execute_rq We can remove 'q' from blk_execute_rq as well after the previous change in blk_execute_rq_nowait. And more importantly it never really was needed to start with given that we can trivial derive it from struct request. Cc: linux-scsi@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: linux-ide@vger.kernel.org Cc: linux-mmc@vger.kernel.org Cc: linux-nvme@lists.infradead.org Cc: linux-nfs@vger.kernel.org Acked-by: Ulf Hansson # for mmc Signed-off-by: Guoqing Jiang Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 623a61239429..20f3706b6b2e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -948,8 +948,7 @@ extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, uns extern int blk_rq_map_user_iov(struct request_queue *, struct request *, struct rq_map_data *, const struct iov_iter *, gfp_t); -extern void blk_execute_rq(struct request_queue *, struct gendisk *, - struct request *, int); +extern void blk_execute_rq(struct gendisk *, struct request *, int); extern void blk_execute_rq_nowait(struct gendisk *, struct request *, int, rq_end_io_fn *); -- cgit v1.2.3 From 2c2b9fd6b496b3616e9b9537ea0258b3040914f3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 9 Jan 2021 12:13:32 +0100 Subject: block: unexport truncate_bdev_range truncate_bdev_range is only used in always built-in block layer code, so remove the export and the !CONFIG_BLOCK stub. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 20f3706b6b2e..2491e17b61c4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1999,21 +1999,16 @@ void bdev_add(struct block_device *bdev, dev_t dev); struct block_device *I_BDEV(struct inode *inode); struct block_device *bdgrab(struct block_device *bdev); void bdput(struct block_device *); +int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, + loff_t lend); #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 c6bf3f0e25f4c0f0ecce6cf8d1c589bd9d74d3cf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 26 Jan 2021 15:52:35 +0100 Subject: block: use an on-stack bio in blkdev_issue_flush There is no point in allocating memory for a synchronous flush. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Chaitanya Kulkarni Acked-by: Damien Le Moal 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 2491e17b61c4..0dea268bd61b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1288,7 +1288,7 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) !list_empty(&plug->cb_list)); } -int blkdev_issue_flush(struct block_device *, gfp_t); +int blkdev_issue_flush(struct block_device *bdev); long nr_blockdev_pages(void); #else /* CONFIG_BLOCK */ struct blk_plug { @@ -1316,7 +1316,7 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) return false; } -static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask) +static inline int blkdev_issue_flush(struct block_device *bdev) { return 0; } -- cgit v1.2.3 From a805a4fa4fa376bbc145762bb8b09caa2fa8af48 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 28 Jan 2021 13:47:30 +0900 Subject: block: introduce zone_write_granularity limit Per ZBC and ZAC specifications, host-managed SMR hard-disks mandate that all writes into sequential write required zones be aligned to the device physical block size. However, NVMe ZNS does not have this constraint and allows write operations into sequential zones to be aligned to the device logical block size. This inconsistency does not help with software portability across device types. To solve this, introduce the zone_write_granularity queue limit to indicate the alignment constraint, in bytes, of write operations into zones of a zoned block device. This new limit is exported as a read-only sysfs queue attribute and the helper blk_queue_zone_write_granularity() introduced for drivers to set this limit. The function blk_queue_set_zoned() is modified to set this new limit to the device logical block size by default. NVMe ZNS devices as well as zoned nullb devices use this default value as is. The scsi disk driver is modified to execute the blk_queue_zone_write_granularity() helper to set the zone write granularity of host-managed SMR disks to the disk physical block size. The accessor functions queue_zone_write_granularity() and bdev_zone_write_granularity() are also introduced. Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Chaitanya Kulkarni Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0dea268bd61b..9149f4a5adb3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -337,6 +337,7 @@ struct queue_limits { unsigned int max_zone_append_sectors; unsigned int discard_granularity; unsigned int discard_alignment; + unsigned int zone_write_granularity; unsigned short max_segments; unsigned short max_integrity_segments; @@ -1160,6 +1161,8 @@ extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); extern void blk_queue_max_zone_append_sectors(struct request_queue *q, unsigned int max_zone_append_sectors); extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); +void blk_queue_zone_write_granularity(struct request_queue *q, + unsigned int size); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); void blk_queue_update_readahead(struct request_queue *q); @@ -1473,6 +1476,18 @@ static inline int bdev_io_opt(struct block_device *bdev) return queue_io_opt(bdev_get_queue(bdev)); } +static inline unsigned int +queue_zone_write_granularity(const struct request_queue *q) +{ + return q->limits.zone_write_granularity; +} + +static inline unsigned int +bdev_zone_write_granularity(struct block_device *bdev) +{ + return queue_zone_write_granularity(bdev_get_queue(bdev)); +} + static inline int queue_alignment_offset(const struct request_queue *q) { if (q->limits.misaligned) -- cgit v1.2.3