From 3222d8c2a7f888bf38b845b125e9470b12108a4d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 25 Jan 2023 14:34:36 +0100 Subject: block: remove ->rw_page The ->rw_page method is a special purpose bypass of the usual bio handling path that is limited to single-page reads and writes and synchronous which causes a lot of extra code in the drivers, callers and the block layer. The only remaining user is the MM swap code. Switch that swap code to simply submit a single-vec on-stack bio an synchronously wait on it based on a newly added QUEUE_FLAG_SYNCHRONOUS flag set by the drivers that currently implement ->rw_page instead. While this touches one extra cache line and executes extra code, it simplifies the block layer and drivers and ensures that all feastures are properly supported by all drivers, e.g. right now ->rw_page bypassed cgroup writeback entirely. [akpm@linux-foundation.org: fix comment typo, per Dan] Link: https://lkml.kernel.org/r/20230125133436.447864-8-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Cc: Dave Jiang Cc: Ira Weiny Cc: Jens Axboe Cc: Keith Busch Cc: Minchan Kim Cc: Sergey Senozhatsky Cc: Vishal Verma Signed-off-by: Andrew Morton --- include/linux/blkdev.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 43d4e073b111..c5e59965b145 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -554,6 +554,7 @@ struct request_queue { #define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ +#define QUEUE_FLAG_SYNCHRONOUS 11 /* always completes in submit context */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ #define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ @@ -1250,6 +1251,12 @@ static inline bool bdev_nonrot(struct block_device *bdev) return blk_queue_nonrot(bdev_get_queue(bdev)); } +static inline bool bdev_synchronous(struct block_device *bdev) +{ + return test_bit(QUEUE_FLAG_SYNCHRONOUS, + &bdev_get_queue(bdev)->queue_flags); +} + static inline bool bdev_stable_writes(struct block_device *bdev) { return test_bit(QUEUE_FLAG_STABLE_WRITES, @@ -1382,7 +1389,6 @@ struct block_device_operations { unsigned int flags); int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); - int (*rw_page)(struct block_device *, sector_t, struct page *, enum req_op); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); unsigned int (*check_events) (struct gendisk *disk, @@ -1417,10 +1423,6 @@ extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t, #define blkdev_compat_ptr_ioctl NULL #endif -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 *); - static inline void blk_wake_io_task(struct task_struct *waiter) { /* -- cgit v1.2.3 From 9e0c7efa5ea231d85c0d41693a5115b3b971717c Mon Sep 17 00:00:00 2001 From: Juhyung Park Date: Fri, 3 Feb 2023 11:40:29 +0900 Subject: block: remove more NULL checks after bdev_get_queue() bdev_get_queue() never returns NULL. Several commits [1][2] have been made before to remove such superfluous checks, but some still remained. For places where bdev_get_queue() is called solely for NULL checks, it is removed entirely. [1] commit ec9fd2a13d74 ("blk-lib: don't check bdev_get_queue() NULL check") [2] commit fea127b36c93 ("block: remove superfluous check for request queue in bdev_is_zoned()") Signed-off-by: Juhyung Park Reviewed-by: Pankaj Raghav Link: https://lore.kernel.org/r/20230203024029.48260-1-qkrwngud825@gmail.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b9637d63e6f0..89dd9b02b45b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1276,12 +1276,7 @@ static inline bool bdev_nowait(struct block_device *bdev) static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return blk_queue_zoned_model(q); - - return BLK_ZONED_NONE; + return blk_queue_zoned_model(bdev_get_queue(bdev)); } static inline bool bdev_is_zoned(struct block_device *bdev) -- cgit v1.2.3 From 5f27571382ca42daa3e3d40d1b252bf18c2b61d2 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Thu, 23 Feb 2023 17:12:26 +0800 Subject: block: count 'ios' and 'sectors' when io is done for bio-based device While using iostat for raid, I observed very strange 'await' occasionally, and turns out it's due to that 'ios' and 'sectors' is counted in bdev_start_io_acct(), while 'nsecs' is counted in bdev_end_io_acct(). I'm not sure why they are ccounted like that but I think this behaviour is obviously wrong because user will get wrong disk stats. Fix the problem by counting 'ios' and 'sectors' when io is done, like what rq-based device does. Fixes: 394ffa503bc4 ("blk: introduce generic io stat accounting help function") Signed-off-by: Yu Kuai Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230223091226.1135678-1-yukuai1@huaweicloud.com 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 d1aee08f8c18..941304f17492 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1446,11 +1446,10 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -unsigned long bdev_start_io_acct(struct block_device *bdev, - unsigned int sectors, enum req_op op, +unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time); void bdev_end_io_acct(struct block_device *bdev, enum req_op op, - unsigned long start_time); + unsigned int sectors, unsigned long start_time); unsigned long bio_start_io_acct(struct bio *bio); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, -- cgit v1.2.3