From 48b5c1fbcd8c5bc6b91a56399a5257b801391dd8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 13 Nov 2021 14:03:26 -0700 Subject: block: only allocate poll_stats if there's a user of them This is essentially never used, yet it's about 1/3rd of the total queue size. Allocate it when needed, and don't embed it in the queue. Kill the queue flag for this while at it, since we can just check the assigned pointer now. Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig 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 bd4370baccca..74118e67f649 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -267,7 +267,7 @@ struct request_queue { int poll_nsec; struct blk_stat_callback *poll_cb; - struct blk_rq_stat poll_stat[BLK_MQ_POLL_STATS_BKTS]; + struct blk_rq_stat *poll_stat; struct timer_list timeout; struct work_struct timeout_work; @@ -397,7 +397,6 @@ struct request_queue { #define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ #define QUEUE_FLAG_DAX 19 /* device supports DAX */ #define QUEUE_FLAG_STATS 20 /* track IO start and completion times */ -#define QUEUE_FLAG_POLL_STATS 21 /* collecting stats for hybrid polling */ #define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */ #define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */ #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ -- cgit v1.2.3 From 72cd9df2ef788d88c138d51223a01ca6281f232d Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 23 Nov 2021 17:37:33 -0800 Subject: blk-crypto: remove blk_crypto_unregister() This function is trivial and is only used in one place. Having this function is misleading because it implies that blk_crypto_register() needs to be paired with blk_crypto_unregister(), which is not the case. Just set disk->queue->crypto_profile to NULL directly. Signed-off-by: Eric Biggers Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211124013733.347612-1-ebiggers@kernel.org Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 74118e67f649..0a4416ef4fbf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1170,8 +1170,6 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned lo bool blk_crypto_register(struct blk_crypto_profile *profile, struct request_queue *q); -void blk_crypto_unregister(struct request_queue *q); - #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline bool blk_crypto_register(struct blk_crypto_profile *profile, @@ -1180,8 +1178,6 @@ static inline bool blk_crypto_register(struct blk_crypto_profile *profile, return true; } -static inline void blk_crypto_unregister(struct request_queue *q) { } - #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ enum blk_unique_id { -- cgit v1.2.3 From 704b914f15fb7daaf517e3acc4bed472b50ca19e Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 3 Dec 2021 21:15:32 +0800 Subject: blk-mq: move srcu from blk_mq_hw_ctx to request_queue In case of BLK_MQ_F_BLOCKING, per-hctx srcu is used to protect dispatch critical area. However, this srcu instance stays at the end of hctx, and it often takes standalone cacheline, often cold. Inside srcu_read_lock() and srcu_read_unlock(), WRITE is always done on the indirect percpu variable which is allocated from heap instead of being embedded, srcu->srcu_idx is read only in srcu_read_lock(). It doesn't matter if srcu structure stays in hctx or request queue. So switch to per-request-queue srcu for protecting dispatch, and this way simplifies quiesce a lot, not mention quiesce is always done on the request queue wide. Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20211203131534.3668411-3-ming.lei@redhat.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0a4416ef4fbf..c80cfaefc0a8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -16,6 +16,7 @@ #include #include #include +#include struct module; struct request_queue; @@ -373,11 +374,18 @@ struct request_queue { * devices that do not have multiple independent access ranges. */ struct blk_independent_access_ranges *ia_ranges; + + /** + * @srcu: Sleepable RCU. Use as lock when type of the request queue + * is blocking (BLK_MQ_F_BLOCKING). Must be the last member + */ + struct srcu_struct srcu[]; }; /* Keep blk_queue_flag_name[] in sync with the definitions below */ #define QUEUE_FLAG_STOPPED 0 /* queue is stopped */ #define QUEUE_FLAG_DYING 1 /* queue being torn down */ +#define QUEUE_FLAG_HAS_SRCU 2 /* SRCU is allocated */ #define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 4 /* complete on same CPU-group */ #define QUEUE_FLAG_FAIL_IO 5 /* fake timeout */ @@ -415,6 +423,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) +#define blk_queue_has_srcu(q) test_bit(QUEUE_FLAG_HAS_SRCU, &(q)->queue_flags) #define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) #define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) -- cgit v1.2.3 From 37ae5a0f5287a52cf51242e76ccf198d02ffe495 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sat, 18 Dec 2021 18:41:56 +0900 Subject: block: use "unsigned long" for blk_validate_block_size(). Since lo_simple_ioctl(LOOP_SET_BLOCK_SIZE) and ioctl(NBD_SET_BLKSIZE) pass user-controlled "unsigned long arg" to blk_validate_block_size(), "unsigned long" should be used for validation. Signed-off-by: Tetsuo Handa Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/9ecbf057-4375-c2db-ab53-e4cc0dff953d@i-love.sakura.ne.jp 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 c80cfaefc0a8..bb5fb7282e6e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -45,7 +45,7 @@ struct blk_crypto_profile; */ #define BLKCG_MAX_POLS 6 -static inline int blk_validate_block_size(unsigned int bsize) +static inline int blk_validate_block_size(unsigned long bsize) { if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) return -EINVAL; -- cgit v1.2.3 From a16c7246368db8935652c805bc446928d0e1c0aa Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 22 Dec 2021 13:52:39 -0800 Subject: block: remove unnecessary trailing '\' While harmless, the blank line is certainly not intended to be part of the rq_list_for_each() macro. Remove it. Signed-off-by: Keith Busch Link: https://lore.kernel.org/r/20211222215239.1768164-1-kbusch@kernel.org 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 bb5fb7282e6e..22746b2d6825 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1363,7 +1363,7 @@ struct io_comp_batch { }) #define rq_list_for_each(listptr, pos) \ - for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) \ + for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) #define rq_list_next(rq) (rq)->rq_next #define rq_list_empty(list) ((list) == (struct request *) NULL) -- cgit v1.2.3 From edce22e19bfa86efa2522d041d6367f2f099e8ed Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 5 Jan 2022 09:05:15 -0800 Subject: block: move rq_list macros to blk-mq.h Move the request list macros to the header file that defines that struct they operate on. Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220105170518.3181469-2-kbusch@kernel.org Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 29 ----------------------------- 1 file changed, 29 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 22746b2d6825..9c95df26fc26 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1339,33 +1339,4 @@ struct io_comp_batch { #define DEFINE_IO_COMP_BATCH(name) struct io_comp_batch name = { } -#define rq_list_add(listptr, rq) do { \ - (rq)->rq_next = *(listptr); \ - *(listptr) = rq; \ -} while (0) - -#define rq_list_pop(listptr) \ -({ \ - struct request *__req = NULL; \ - if ((listptr) && *(listptr)) { \ - __req = *(listptr); \ - *(listptr) = __req->rq_next; \ - } \ - __req; \ -}) - -#define rq_list_peek(listptr) \ -({ \ - struct request *__req = NULL; \ - if ((listptr) && *(listptr)) \ - __req = *(listptr); \ - __req; \ -}) - -#define rq_list_for_each(listptr, pos) \ - for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) - -#define rq_list_next(rq) (rq)->rq_next -#define rq_list_empty(list) ((list) == (struct request *) NULL) - #endif /* _LINUX_BLKDEV_H */ -- cgit v1.2.3 From e45c47d1f94e0cc7b6b079fdb4bcce2995e2adc4 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 28 Jan 2022 10:58:39 -0500 Subject: block: add bio_start_io_acct_time() to control start_time bio_start_io_acct_time() interface is like bio_start_io_acct() that allows start_time to be passed in. This gives drivers the ability to defer starting accounting until after IO is issued (but possibily not entirely due to bio splitting). Reviewed-by: Christoph Hellwig Signed-off-by: Mike Snitzer Link: https://lore.kernel.org/r/20220128155841.39644-2-snitzer@redhat.com 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 9c95df26fc26..f35aea98bc35 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1258,6 +1258,7 @@ 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); +void bio_start_io_acct_time(struct bio *bio, 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, struct block_device *orig_bdev); -- cgit v1.2.3