From 0f00b82e5413571ed225ddbccad6882d7ea60bc7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Mar 2021 08:45:50 +0100 Subject: block: remove the revalidate_disk method No implementations left. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210308074550.422714-4-hch@lst.de 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 bc6bc8383b43..b4241f73f7a8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1870,7 +1870,6 @@ struct block_device_operations { unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); 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 */ -- cgit v1.2.3 From f06c609645ecd043c79380fac94145926603fb33 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 2 Apr 2021 19:17:46 +0200 Subject: block: remove the unused RQF_ALLOCED flag 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 bc6bc8383b43..158aefae1030 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -85,8 +85,6 @@ typedef __u32 __bitwise req_flags_t; #define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) /* account into disk and partition IO statistics */ #define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) -/* request came from our alloc pool */ -#define RQF_ALLOCED ((__force req_flags_t)(1 << 14)) /* runtime pm request */ #define RQF_PM ((__force req_flags_t)(1 << 15)) /* on IO scheduler merge hash */ -- cgit v1.2.3 From ce288e0535688cc3475a3c3d4d96624514c3550c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 31 Mar 2021 09:29:59 +0200 Subject: block: remove BLK_BOUNCE_ISA support Remove the BLK_BOUNCE_ISA support now that all users are gone. Signed-off-by: Christoph Hellwig Acked-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Link: https://lore.kernel.org/r/20210331073001.46776-7-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bc6bc8383b43..0dbb72ea3735 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -436,11 +436,6 @@ struct request_queue { */ int id; - /* - * queue needs bounce pages for pages above this limit - */ - gfp_t bounce_gfp; - spinlock_t queue_lock; /* @@ -847,7 +842,6 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn; * * BLK_BOUNCE_HIGH : bounce all highmem pages * BLK_BOUNCE_ANY : don't bounce anything - * BLK_BOUNCE_ISA : bounce pages above ISA DMA boundary */ #if BITS_PER_LONG == 32 @@ -856,7 +850,6 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn; #define BLK_BOUNCE_HIGH -1ULL #endif #define BLK_BOUNCE_ANY (-1ULL) -#define BLK_BOUNCE_ISA (DMA_BIT_MASK(24)) /* * default timeout for SG_IO if none specified -- cgit v1.2.3 From 9bb33f24abbd0fa2fadad01ec75438d7cc239189 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 31 Mar 2021 09:30:00 +0200 Subject: block: refactor the bounce buffering code Get rid of all the PFN arithmetics and just use an enum for the two remaining options, and use PageHighMem for the actual bounce decision. Add a fast path to entirely avoid the call for the common case of a queue not using the legacy bouncing code. Signed-off-by: Christoph Hellwig Acked-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Link: https://lore.kernel.org/r/20210331073001.46776-8-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 29 +++++++++++------------------ 1 file changed, 11 insertions(+), 18 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0dbb72ea3735..55cc8b96c844 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -313,8 +313,17 @@ enum blk_zoned_model { BLK_ZONED_HM, /* Host-managed zoned block device */ }; +/* + * BLK_BOUNCE_NONE: never bounce (default) + * BLK_BOUNCE_HIGH: bounce all highmem pages + */ +enum blk_bounce { + BLK_BOUNCE_NONE, + BLK_BOUNCE_HIGH, +}; + struct queue_limits { - unsigned long bounce_pfn; + enum blk_bounce bounce; unsigned long seg_boundary_mask; unsigned long virt_boundary_mask; @@ -835,22 +844,6 @@ static inline unsigned int blk_queue_depth(struct request_queue *q) return q->nr_requests; } -extern unsigned long blk_max_low_pfn, blk_max_pfn; - -/* - * standard bounce addresses: - * - * BLK_BOUNCE_HIGH : bounce all highmem pages - * BLK_BOUNCE_ANY : don't bounce anything - */ - -#if BITS_PER_LONG == 32 -#define BLK_BOUNCE_HIGH ((u64)blk_max_low_pfn << PAGE_SHIFT) -#else -#define BLK_BOUNCE_HIGH -1ULL -#endif -#define BLK_BOUNCE_ANY (-1ULL) - /* * default timeout for SG_IO if none specified */ @@ -1134,7 +1127,7 @@ extern void blk_abort_request(struct request *); * Access functions for manipulating queue properties */ extern void blk_cleanup_queue(struct request_queue *); -extern void blk_queue_bounce_limit(struct request_queue *, u64); +void blk_queue_bounce_limit(struct request_queue *q, enum blk_bounce limit); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); -- cgit v1.2.3 From 393bb12e00580aaa23356504eed38d8f5571153a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 31 Mar 2021 09:30:01 +0200 Subject: block: stop calling blk_queue_bounce for passthrough requests Instead of overloading the passthrough fast path with the deprecated block layer bounce buffering let the users that combine an old undermaintained driver with a highmem system pay the price by always falling back to copies in that case. Signed-off-by: Christoph Hellwig Acked-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Link: https://lore.kernel.org/r/20210331073001.46776-9-hch@lst.de 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 55cc8b96c844..d5d320da51f8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -909,7 +909,7 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, extern void blk_rq_unprep_clone(struct request *rq); extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); -extern int blk_rq_append_bio(struct request *rq, struct bio **bio); +int blk_rq_append_bio(struct request *rq, struct bio *bio); extern void blk_queue_split(struct bio **); extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t, -- cgit v1.2.3 From 907d52310024fae6632aabfc7e833decaf185e5f Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Thu, 1 Apr 2021 10:19:25 +0800 Subject: block: add queue_to_disk() to get gendisk from request_queue Sometimes we need to get the corresponding gendisk from request_queue. It is preferred that block drivers store private data in gendisk->private_data rather than request_queue->queuedata, e.g. see: commit c4a59c4e5db3 ("dm: stop using ->queuedata"). So if only request_queue is given, we need to get its corresponding gendisk to get the private data stored in that gendisk. Reviewed-by: Hannes Reinecke Reviewed-by: Mike Snitzer Signed-off-by: Jeffle Xu Signed-off-by: Ming Lei 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 d5d320da51f8..30d2090583ad 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -689,6 +689,8 @@ static inline bool blk_account_rq(struct request *rq) dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \ (dir), (attrs)) +#define queue_to_disk(q) (dev_to_disk(kobj_to_dev((q)->kobj.parent))) + static inline bool queue_is_mq(struct request_queue *q) { return q->mq_ops; -- cgit v1.2.3 From 8d663f34f8afcf5fc6a84c3cc4fa28cc84d58e39 Mon Sep 17 00:00:00 2001 From: Lin Feng Date: Thu, 15 Apr 2021 11:39:20 +0800 Subject: blk-mq: bypass IO scheduler's limit_depth for passthrough request Commit 01e99aeca39796003 ("blk-mq: insert passthrough request into hctx->dispatch directly") gives high priority to passthrough requests and bypass underlying IO scheduler. But as we allocate tag for such request it still runs io-scheduler's callback limit_depth, while we really want is to give full sbitmap-depth capabity to such request for acquiring available tag. blktrace shows PC requests(dmraid -s -c -i) hit bfq's limit_depth: 8,0 2 0 0.000000000 39952 1,0 m N bfq [bfq_limit_depth] wr_busy 0 sync 0 depth 8 8,0 2 1 0.000008134 39952 D R 4 [dmraid] 8,0 2 2 0.000021538 24 C R [0] 8,0 2 0 0.000035442 39952 1,0 m N bfq [bfq_limit_depth] wr_busy 0 sync 0 depth 8 8,0 2 3 0.000038813 39952 D R 24 [dmraid] 8,0 2 4 0.000044356 24 C R [0] This patch introduce a new wrapper to make code not that ugly. Signed-off-by: Lin Feng Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20210415033920.213963-1-linf@wangsu.com 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 30d2090583ad..f2e77ba97550 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -274,6 +274,12 @@ static inline bool bio_is_passthrough(struct bio *bio) return blk_op_is_scsi(op) || blk_op_is_private(op); } +static inline bool blk_op_is_passthrough(unsigned int op) +{ + return (blk_op_is_scsi(op & REQ_OP_MASK) || + blk_op_is_private(op & REQ_OP_MASK)); +} + static inline unsigned short req_get_ioprio(struct request *req) { return req->ioprio; -- cgit v1.2.3 From cd2c7545ae1beac3b6aae033c7f31193b3255946 Mon Sep 17 00:00:00 2001 From: Changheun Lee Date: Mon, 3 May 2021 18:52:03 +0900 Subject: bio: limit bio max size bio size can grow up to 4GB when muli-page bvec is enabled. but sometimes it would lead to inefficient behaviors. in case of large chunk direct I/O, - 32MB chunk read in user space - all pages for 32MB would be merged to a bio structure if the pages physical addresses are contiguous. it makes some delay to submit until merge complete. bio max size should be limited to a proper size. When 32MB chunk read with direct I/O option is coming from userspace, kernel behavior is below now in do_direct_IO() loop. it's timeline. | bio merge for 32MB. total 8,192 pages are merged. | total elapsed time is over 2ms. |------------------ ... ----------------------->| | 8,192 pages merged a bio. | at this time, first bio submit is done. | 1 bio is split to 32 read request and issue. |---------------> |---------------> |---------------> ...... |---------------> |--------------->| total 19ms elapsed to complete 32MB read done from device. | If bio max size is limited with 1MB, behavior is changed below. | bio merge for 1MB. 256 pages are merged for each bio. | total 32 bio will be made. | total elapsed time is over 2ms. it's same. | but, first bio submit timing is fast. about 100us. |--->|--->|--->|---> ... -->|--->|--->|--->|--->| | 256 pages merged a bio. | at this time, first bio submit is done. | and 1 read request is issued for 1 bio. |---------------> |---------------> |---------------> ...... |---------------> |--------------->| total 17ms elapsed to complete 32MB read done from device. | As a result, read request issue timing is faster if bio max size is limited. Current kernel behavior with multipage bvec, super large bio can be created. And it lead to delay first I/O request issue. Signed-off-by: Changheun Lee Reviewed-by: Bart Van Assche Link: https://lore.kernel.org/r/20210503095203.29076-1-nanich.lee@samsung.com 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 b91ba6207365..40c7c4d87aa1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -327,6 +327,8 @@ enum blk_bounce { }; struct queue_limits { + unsigned int bio_max_bytes; + enum blk_bounce bounce; unsigned long seg_boundary_mask; unsigned long virt_boundary_mask; -- cgit v1.2.3 From 4ee60ec156d91c315d1f62dfc1bc5799dcc6b473 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 6 May 2021 18:02:27 -0700 Subject: include: remove pagemap.h from blkdev.h My UEK-derived config has 1030 files depending on pagemap.h before this change. Afterwards, just 326 files need to be rebuilt when I touch pagemap.h. I think blkdev.h is probably included too widely, but untangling that dependency is harder and this solves my problem. x86 allmodconfig builds, but there may be implicit include problems on other architectures. Link: https://lkml.kernel.org/r/20210309195747.283796-1-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Dan Williams [nvdimm] Acked-by: Jens Axboe [block] Reviewed-by: Christoph Hellwig Acked-by: Coly Li [bcache] Acked-by: Martin K. Petersen [scsi] Reviewed-by: William Kucharski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 b91ba6207365..1255823b2bc0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From 35c820e71565d1fa835b82499359218b219828ac Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 8 May 2021 21:49:48 -0600 Subject: Revert "bio: limit bio max size" This reverts commit cd2c7545ae1beac3b6aae033c7f31193b3255946. Alex reports that the commit causes corruption with LUKS on ext4. Revert it for now so that this can be investigated properly. Link: https://lore.kernel.org/linux-block/1620493841.bxdq8r5haw.none@localhost/ Reported-by: Alex Xu (Hello71) 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 40c7c4d87aa1..b91ba6207365 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -327,8 +327,6 @@ enum blk_bounce { }; struct queue_limits { - unsigned int bio_max_bytes; - enum blk_bounce bounce; unsigned long seg_boundary_mask; unsigned long virt_boundary_mask; -- cgit v1.2.3