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 v1.3-18-gd494 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 --- block/blk-settings.c | 1 + drivers/block/brd.c | 1 + drivers/block/loop.c | 1 + drivers/md/bcache/super.c | 1 + drivers/nvdimm/btt.c | 1 + drivers/nvdimm/pmem.c | 1 + drivers/scsi/scsicam.c | 1 + include/linux/blkdev.h | 1 - include/linux/swap.h | 1 + 9 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-settings.c b/block/blk-settings.c index 9c009090c4b5..902c40d67120 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 6e622c1327ee..7562cf30b14e 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/block/loop.c b/drivers/block/loop.c index a370cde3ddd4..d58d68f3c7cd 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -53,6 +53,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 2b6d6e9cd680..bea8c4429ae8 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -16,6 +16,7 @@ #include "features.h" #include +#include #include #include #include diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 41aa1f01fc07..18a267d5073f 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 7daac795db39..ed10a8b66068 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include diff --git a/drivers/scsi/scsicam.c b/drivers/scsi/scsicam.c index f1553a453616..0ffdb8f2995f 100644 --- a/drivers/scsi/scsicam.c +++ b/drivers/scsi/scsicam.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include 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 diff --git a/include/linux/swap.h b/include/linux/swap.h index f69e0f67651d..144727041e78 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include -- cgit v1.3-18-gd494 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 --- block/bio.c | 13 ++----------- block/blk-settings.c | 5 ----- include/linux/bio.h | 4 +--- include/linux/blkdev.h | 2 -- 4 files changed, 3 insertions(+), 21 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/bio.c b/block/bio.c index 221dc56ba22f..44205dfb6b60 100644 --- a/block/bio.c +++ b/block/bio.c @@ -255,13 +255,6 @@ void bio_init(struct bio *bio, struct bio_vec *table, } EXPORT_SYMBOL(bio_init); -unsigned int bio_max_size(struct bio *bio) -{ - struct block_device *bdev = bio->bi_bdev; - - return bdev ? bdev->bd_disk->queue->limits.bio_max_bytes : UINT_MAX; -} - /** * bio_reset - reinitialize a bio * @bio: bio to reset @@ -873,7 +866,7 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page, struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; if (page_is_mergeable(bv, page, len, off, same_page)) { - if (bio->bi_iter.bi_size > bio_max_size(bio) - len) { + if (bio->bi_iter.bi_size > UINT_MAX - len) { *same_page = false; return false; } @@ -1002,7 +995,6 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt; unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt; - unsigned int bytes_left = bio_max_size(bio) - bio->bi_iter.bi_size; struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; struct page **pages = (struct page **)bv; bool same_page = false; @@ -1018,8 +1010,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2); pages += entries_left * (PAGE_PTRS_PER_BVEC - 1); - size = iov_iter_get_pages(iter, pages, bytes_left, nr_pages, - &offset); + size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset); if (unlikely(size <= 0)) return size ? size : -EFAULT; diff --git a/block/blk-settings.c b/block/blk-settings.c index c646503e55d2..9c009090c4b5 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -31,7 +31,6 @@ EXPORT_SYMBOL_GPL(blk_queue_rq_timeout); */ void blk_set_default_limits(struct queue_limits *lim) { - lim->bio_max_bytes = UINT_MAX; lim->max_segments = BLK_MAX_SEGMENTS; lim->max_discard_segments = 1; lim->max_integrity_segments = 0; @@ -140,10 +139,6 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto limits->logical_block_size >> SECTOR_SHIFT); limits->max_sectors = max_sectors; - if (check_shl_overflow(max_sectors, SECTOR_SHIFT, - &limits->bio_max_bytes)) - limits->bio_max_bytes = UINT_MAX; - q->backing_dev_info->io_pages = max_sectors >> (PAGE_SHIFT - 9); } EXPORT_SYMBOL(blk_queue_max_hw_sectors); diff --git a/include/linux/bio.h b/include/linux/bio.h index f1a99f0a240c..a0b4cfdf62a4 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -106,8 +106,6 @@ static inline void *bio_data(struct bio *bio) return NULL; } -extern unsigned int bio_max_size(struct bio *bio); - /** * bio_full - check if the bio is full * @bio: bio to check @@ -121,7 +119,7 @@ static inline bool bio_full(struct bio *bio, unsigned len) if (bio->bi_vcnt >= bio->bi_max_vecs) return true; - if (bio->bi_iter.bi_size > bio_max_size(bio) - len) + if (bio->bi_iter.bi_size > UINT_MAX - len) return true; return false; 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 v1.3-18-gd494 From 190515f610946db025cdedebde93958b725fb583 Mon Sep 17 00:00:00 2001 From: Lin Feng Date: Wed, 12 May 2021 18:01:24 +0800 Subject: blkdev.h: remove unused codes blk_account_rq Last users of blk_account_rq gone with patch commit a1ce35fa49852db ("block: remove dead elevator code") and now it gets no caller, it can be safely removed. Signed-off-by: Lin Feng Link: https://lore.kernel.org/r/20210512100124.173769-1-linf@wangsu.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b91ba6207365..26c3e368656f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -677,11 +677,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); -static inline bool blk_account_rq(struct request *rq) -{ - return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); -} - #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) -- cgit v1.3-18-gd494