From 5dd55749b79cdf471ca0966ad91541daebac3e2f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:56:54 +0100 Subject: nvme: let set_capacity_revalidate_and_notify update the bdev size There is no good reason to call revalidate_disk_size separately. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'drivers/nvme') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 9b01afcb7777..f6c6479da0e9 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2053,7 +2053,7 @@ static void nvme_update_disk_info(struct gendisk *disk, capacity = 0; } - set_capacity_revalidate_and_notify(disk, capacity, false); + set_capacity_revalidate_and_notify(disk, capacity, true); nvme_config_discard(disk, ns); nvme_config_write_zeroes(disk, ns); @@ -2134,7 +2134,6 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id) blk_stack_limits(&ns->head->disk->queue->limits, &ns->queue->limits, 0); blk_queue_update_readahead(ns->head->disk->queue); - nvme_update_bdev_size(ns->head->disk); blk_mq_unfreeze_queue(ns->head->disk->queue); } #endif @@ -3963,8 +3962,6 @@ out: */ if (ret && ret != -ENOMEM && !(ret > 0 && !(ret & NVME_SC_DNR))) nvme_ns_remove(ns); - else - revalidate_disk_size(ns->disk, true); } static void nvme_validate_or_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) -- cgit v1.2.3 From 449f4ec9892ebc2f37a7eae6d97db2cf7c65e09a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:56:56 +0100 Subject: block: remove the update_bdev parameter to set_capacity_revalidate_and_notify The update_bdev argument is always set to true, so remove it. Also rename the function to the slighly less verbose set_capacity_and_notify, as propagating the disk size to the block device isn't really revalidation. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Petr Vorel Signed-off-by: Jens Axboe --- block/genhd.c | 13 +++++-------- drivers/block/loop.c | 2 +- drivers/block/virtio_blk.c | 2 +- drivers/block/xen-blkfront.c | 2 +- drivers/nvme/host/core.c | 2 +- drivers/scsi/sd.c | 5 ++--- include/linux/genhd.h | 3 +-- 7 files changed, 12 insertions(+), 17 deletions(-) (limited to 'drivers/nvme') diff --git a/block/genhd.c b/block/genhd.c index ec2a24799cd9..4e039524f92b 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -47,17 +47,15 @@ static void disk_del_events(struct gendisk *disk); static void disk_release_events(struct gendisk *disk); /* - * Set disk capacity and notify if the size is not currently - * zero and will not be set to zero + * Set disk capacity and notify if the size is not currently zero and will not + * be set to zero. Returns true if a uevent was sent, otherwise false. */ -bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, - bool update_bdev) +bool set_capacity_and_notify(struct gendisk *disk, sector_t size) { sector_t capacity = get_capacity(disk); set_capacity(disk, size); - if (update_bdev) - revalidate_disk_size(disk, true); + revalidate_disk_size(disk, true); if (capacity != size && capacity != 0 && size != 0) { char *envp[] = { "RESIZE=1", NULL }; @@ -68,8 +66,7 @@ bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, return false; } - -EXPORT_SYMBOL_GPL(set_capacity_revalidate_and_notify); +EXPORT_SYMBOL_GPL(set_capacity_and_notify); /* * Format the device name of the indicated disk into the supplied buffer and diff --git a/drivers/block/loop.c b/drivers/block/loop.c index fcc5e32f0993..9a27d4f1c08a 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -251,7 +251,7 @@ loop_validate_block_size(unsigned short bsize) */ static void loop_set_size(struct loop_device *lo, loff_t size) { - if (!set_capacity_revalidate_and_notify(lo->lo_disk, size, true)) + if (!set_capacity_and_notify(lo->lo_disk, size)) kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index a314b9382442..3e812b4c32e6 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -470,7 +470,7 @@ static void virtblk_update_capacity(struct virtio_blk *vblk, bool resize) cap_str_10, cap_str_2); - set_capacity_revalidate_and_notify(vblk->disk, capacity, true); + set_capacity_and_notify(vblk->disk, capacity); } static void virtblk_config_changed_work(struct work_struct *work) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 48629d3433b4..79521e33d30e 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -2370,7 +2370,7 @@ static void blkfront_connect(struct blkfront_info *info) return; printk(KERN_INFO "Setting capacity to %Lu\n", sectors); - set_capacity_revalidate_and_notify(info->gd, sectors, true); + set_capacity_and_notify(info->gd, sectors); return; case BLKIF_STATE_SUSPENDED: diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f6c6479da0e9..6c144e748f8c 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2053,7 +2053,7 @@ static void nvme_update_disk_info(struct gendisk *disk, capacity = 0; } - set_capacity_revalidate_and_notify(disk, capacity, true); + set_capacity_and_notify(disk, capacity); nvme_config_discard(disk, ns); nvme_config_write_zeroes(disk, ns); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index e9b898a1a480..679c2c025047 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3261,8 +3261,7 @@ static int sd_revalidate_disk(struct gendisk *disk) sdkp->first_scan = 0; - set_capacity_revalidate_and_notify(disk, - logical_to_sectors(sdp, sdkp->capacity), true); + set_capacity_and_notify(disk, logical_to_sectors(sdp, sdkp->capacity)); sd_config_write_same(sdkp); kfree(buffer); @@ -3272,7 +3271,7 @@ static int sd_revalidate_disk(struct gendisk *disk) * capacity to 0. */ if (sd_zbc_revalidate_zones(sdkp)) - set_capacity_revalidate_and_notify(disk, 0, true); + set_capacity_and_notify(disk, 0); out: return 0; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 3cbc2781ef34..46553d6d6025 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -314,8 +314,7 @@ static inline int get_disk_ro(struct gendisk *disk) extern void disk_block_events(struct gendisk *disk); extern void disk_unblock_events(struct gendisk *disk); extern void disk_flush_events(struct gendisk *disk, unsigned int mask); -bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, - bool update_bdev); +bool set_capacity_and_notify(struct gendisk *disk, sector_t size); /* drivers/char/random.c */ extern void add_disk_randomness(struct gendisk *disk) __latent_entropy; -- cgit v1.2.3 From d17e66aadbe50b7207187d6b2293fc2ddaab2c99 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:57:05 +0100 Subject: nvme: use set_capacity_and_notify in nvme_set_queue_dying Use the block layer helper to update both the disk and block device sizes. Contrary to the name no notification is sent in this case, as a size 0 is special cased. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'drivers/nvme') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 6c144e748f8c..bc89e8659c40 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -93,16 +93,6 @@ static void nvme_put_subsystem(struct nvme_subsystem *subsys); static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, unsigned nsid); -static void nvme_update_bdev_size(struct gendisk *disk) -{ - struct block_device *bdev = bdget_disk(disk, 0); - - if (bdev) { - bd_set_nr_sectors(bdev, get_capacity(disk)); - bdput(bdev); - } -} - /* * Prepare a queue for teardown. * @@ -119,8 +109,7 @@ static void nvme_set_queue_dying(struct nvme_ns *ns) blk_set_queue_dying(ns->queue); blk_mq_unquiesce_queue(ns->queue); - set_capacity(ns->disk, 0); - nvme_update_bdev_size(ns->disk); + set_capacity_and_notify(ns->disk, 0); } static void nvme_queue_scan(struct nvme_ctrl *ctrl) -- cgit v1.2.3 From 8446fe9255be821cb38ffd306d7e8edc4b9ea662 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Nov 2020 09:36:54 +0100 Subject: block: switch partition lookup to use struct block_device Use struct block_device to lookup partitions on a disk. This removes all usage of struct hd_struct from the I/O path. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Acked-by: Coly Li [bcache] Acked-by: Chao Yu [f2fs] Signed-off-by: Jens Axboe --- block/bio.c | 4 +-- block/blk-core.c | 66 +++++++++++++++++--------------------- block/blk-flush.c | 2 +- block/blk-mq.c | 9 +++--- block/blk-mq.h | 7 ++-- block/blk.h | 4 +-- block/genhd.c | 57 +++++++++++++++++--------------- block/partitions/core.c | 7 ++-- drivers/block/drbd/drbd_receiver.c | 2 +- drivers/block/drbd/drbd_worker.c | 2 +- drivers/block/zram/zram_drv.c | 2 +- drivers/md/bcache/request.c | 4 +-- drivers/md/dm.c | 4 +-- drivers/md/md.c | 4 +-- drivers/nvme/target/admin-cmd.c | 20 ++++++------ fs/ext4/super.c | 18 ++++------- fs/ext4/sysfs.c | 10 ++---- fs/f2fs/f2fs.h | 2 +- fs/f2fs/super.c | 6 ++-- include/linux/blkdev.h | 8 ++--- include/linux/genhd.h | 4 +-- include/linux/part_stat.h | 17 +++++----- 22 files changed, 122 insertions(+), 137 deletions(-) (limited to 'drivers/nvme') diff --git a/block/bio.c b/block/bio.c index 669bb47a3198..ebb18136b86f 100644 --- a/block/bio.c +++ b/block/bio.c @@ -608,12 +608,12 @@ void bio_truncate(struct bio *bio, unsigned new_size) void guard_bio_eod(struct bio *bio) { sector_t maxsector; - struct hd_struct *part; + struct block_device *part; rcu_read_lock(); part = __disk_get_part(bio->bi_disk, bio->bi_partno); if (part) - maxsector = bdev_nr_sectors(part->bdev); + maxsector = bdev_nr_sectors(part); else maxsector = get_capacity(bio->bi_disk); rcu_read_unlock(); diff --git a/block/blk-core.c b/block/blk-core.c index 9ea70275fc1c..cee568389b7e 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -666,10 +666,9 @@ static int __init setup_fail_make_request(char *str) } __setup("fail_make_request=", setup_fail_make_request); -static bool should_fail_request(struct hd_struct *part, unsigned int bytes) +static bool should_fail_request(struct block_device *part, unsigned int bytes) { - return part->bdev->bd_make_it_fail && - should_fail(&fail_make_request, bytes); + return part->bd_make_it_fail && should_fail(&fail_make_request, bytes); } static int __init fail_make_request_debugfs(void) @@ -684,7 +683,7 @@ late_initcall(fail_make_request_debugfs); #else /* CONFIG_FAIL_MAKE_REQUEST */ -static inline bool should_fail_request(struct hd_struct *part, +static inline bool should_fail_request(struct block_device *part, unsigned int bytes) { return false; @@ -692,11 +691,11 @@ static inline bool should_fail_request(struct hd_struct *part, #endif /* CONFIG_FAIL_MAKE_REQUEST */ -static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) +static inline bool bio_check_ro(struct bio *bio, struct block_device *part) { const int op = bio_op(bio); - if (part->bdev->bd_read_only && op_is_write(op)) { + if (part->bd_read_only && op_is_write(op)) { char b[BDEVNAME_SIZE]; if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) @@ -704,7 +703,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) WARN_ONCE(1, "Trying to write to read-only block-device %s (partno %d)\n", - bio_devname(bio, b), part->partno); + bio_devname(bio, b), part->bd_partno); /* Older lvm-tools actually trigger this */ return false; } @@ -714,8 +713,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) static noinline int should_fail_bio(struct bio *bio) { - if (should_fail_request(bio->bi_disk->part0->bd_part, - bio->bi_iter.bi_size)) + if (should_fail_request(bio->bi_disk->part0, bio->bi_iter.bi_size)) return -EIO; return 0; } @@ -744,7 +742,7 @@ static inline int bio_check_eod(struct bio *bio, sector_t maxsector) */ static inline int blk_partition_remap(struct bio *bio) { - struct hd_struct *p; + struct block_device *p; int ret = -EIO; rcu_read_lock(); @@ -757,12 +755,12 @@ static inline int blk_partition_remap(struct bio *bio) goto out; if (bio_sectors(bio)) { - if (bio_check_eod(bio, bdev_nr_sectors(p->bdev))) + if (bio_check_eod(bio, bdev_nr_sectors(p))) goto out; - bio->bi_iter.bi_sector += p->bdev->bd_start_sect; - trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p), + bio->bi_iter.bi_sector += p->bd_start_sect; + trace_block_bio_remap(bio->bi_disk->queue, bio, p->bd_dev, bio->bi_iter.bi_sector - - p->bdev->bd_start_sect); + p->bd_start_sect); } bio->bi_partno = 0; ret = 0; @@ -832,7 +830,7 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio) if (unlikely(blk_partition_remap(bio))) goto end_io; } else { - if (unlikely(bio_check_ro(bio, bio->bi_disk->part0->bd_part))) + if (unlikely(bio_check_ro(bio, bio->bi_disk->part0))) goto end_io; if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk)))) goto end_io; @@ -1204,7 +1202,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request * return ret; if (rq->rq_disk && - should_fail_request(rq->rq_disk->part0->bd_part, blk_rq_bytes(rq))) + should_fail_request(rq->rq_disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; if (blk_crypto_insert_cloned_request(rq)) @@ -1263,17 +1261,18 @@ unsigned int blk_rq_err_bytes(const struct request *rq) } EXPORT_SYMBOL_GPL(blk_rq_err_bytes); -static void update_io_ticks(struct hd_struct *part, unsigned long now, bool end) +static void update_io_ticks(struct block_device *part, unsigned long now, + bool end) { unsigned long stamp; again: - stamp = READ_ONCE(part->bdev->bd_stamp); + stamp = READ_ONCE(part->bd_stamp); if (unlikely(stamp != now)) { - if (likely(cmpxchg(&part->bdev->bd_stamp, stamp, now) == stamp)) + if (likely(cmpxchg(&part->bd_stamp, stamp, now) == stamp)) __part_stat_add(part, io_ticks, end ? now - stamp : 1); } - if (part->partno) { - part = part_to_disk(part)->part0->bd_part; + if (part->bd_partno) { + part = bdev_whole(part); goto again; } } @@ -1282,11 +1281,9 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes) { if (req->part && blk_do_io_stat(req)) { const int sgrp = op_stat_group(req_op(req)); - struct hd_struct *part; part_stat_lock(); - part = req->part; - part_stat_add(part, sectors[sgrp], bytes >> 9); + part_stat_add(req->part, sectors[sgrp], bytes >> 9); part_stat_unlock(); } } @@ -1301,14 +1298,11 @@ void blk_account_io_done(struct request *req, u64 now) if (req->part && blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) { const int sgrp = op_stat_group(req_op(req)); - struct hd_struct *part; part_stat_lock(); - part = req->part; - - update_io_ticks(part, jiffies, true); - part_stat_inc(part, ios[sgrp]); - part_stat_add(part, nsecs[sgrp], now - req->start_time_ns); + update_io_ticks(req->part, jiffies, true); + part_stat_inc(req->part, ios[sgrp]); + part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns); part_stat_unlock(); } } @@ -1325,7 +1319,7 @@ void blk_account_io_start(struct request *rq) part_stat_unlock(); } -static unsigned long __part_start_io_acct(struct hd_struct *part, +static unsigned long __part_start_io_acct(struct block_device *part, unsigned int sectors, unsigned int op) { const int sgrp = op_stat_group(op); @@ -1341,7 +1335,7 @@ static unsigned long __part_start_io_acct(struct hd_struct *part, return now; } -unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part, +unsigned long part_start_io_acct(struct gendisk *disk, struct block_device **part, struct bio *bio) { *part = disk_map_sector_rcu(disk, bio->bi_iter.bi_sector); @@ -1353,11 +1347,11 @@ EXPORT_SYMBOL_GPL(part_start_io_acct); unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op) { - return __part_start_io_acct(disk->part0->bd_part, sectors, op); + return __part_start_io_acct(disk->part0, sectors, op); } EXPORT_SYMBOL(disk_start_io_acct); -static void __part_end_io_acct(struct hd_struct *part, unsigned int op, +static void __part_end_io_acct(struct block_device *part, unsigned int op, unsigned long start_time) { const int sgrp = op_stat_group(op); @@ -1371,7 +1365,7 @@ static void __part_end_io_acct(struct hd_struct *part, unsigned int op, part_stat_unlock(); } -void part_end_io_acct(struct hd_struct *part, struct bio *bio, +void part_end_io_acct(struct block_device *part, struct bio *bio, unsigned long start_time) { __part_end_io_acct(part, bio_op(bio), start_time); @@ -1381,7 +1375,7 @@ EXPORT_SYMBOL_GPL(part_end_io_acct); void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time) { - __part_end_io_acct(disk->part0->bd_part, op, start_time); + __part_end_io_acct(disk->part0, op, start_time); } EXPORT_SYMBOL(disk_end_io_acct); diff --git a/block/blk-flush.c b/block/blk-flush.c index fcd0a60574df..9507dcdd5881 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -139,7 +139,7 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front) static void blk_account_io_flush(struct request *rq) { - struct hd_struct *part = rq->rq_disk->part0->bd_part; + struct block_device *part = rq->rq_disk->part0; part_stat_lock(); part_stat_inc(part, ios[STAT_FLUSH]); diff --git a/block/blk-mq.c b/block/blk-mq.c index 55bcee5dc032..a2593748fa53 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -95,7 +95,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx, } struct mq_inflight { - struct hd_struct *part; + struct block_device *part; unsigned int inflight[2]; }; @@ -111,7 +111,8 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx, return true; } -unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part) +unsigned int blk_mq_in_flight(struct request_queue *q, + struct block_device *part) { struct mq_inflight mi = { .part = part }; @@ -120,8 +121,8 @@ unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part) return mi.inflight[0] + mi.inflight[1]; } -void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part, - unsigned int inflight[2]) +void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part, + unsigned int inflight[2]) { struct mq_inflight mi = { .part = part }; diff --git a/block/blk-mq.h b/block/blk-mq.h index a52703c98b77..c696515766c7 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -182,9 +182,10 @@ static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx) return hctx->nr_ctx && hctx->tags; } -unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part); -void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part, - unsigned int inflight[2]); +unsigned int blk_mq_in_flight(struct request_queue *q, + struct block_device *part); +void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part, + unsigned int inflight[2]); static inline void blk_mq_put_dispatch_budget(struct request_queue *q) { diff --git a/block/blk.h b/block/blk.h index 32ac41f7557f..d5bf8f3a0781 100644 --- a/block/blk.h +++ b/block/blk.h @@ -215,7 +215,7 @@ static inline void elevator_exit(struct request_queue *q, __elevator_exit(q, e); } -struct hd_struct *__disk_get_part(struct gendisk *disk, int partno); +struct block_device *__disk_get_part(struct gendisk *disk, int partno); ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf); @@ -348,7 +348,7 @@ void blk_queue_free_zone_bitmaps(struct request_queue *q); static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {} #endif -struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector); +struct block_device *disk_map_sector_rcu(struct gendisk *disk, sector_t sector); int blk_alloc_devt(struct hd_struct *part, dev_t *devt); void blk_free_devt(dev_t devt); diff --git a/block/genhd.c b/block/genhd.c index c35b03dac5e5..ed06466b305d 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -126,7 +126,7 @@ static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat) } } -static unsigned int part_in_flight(struct hd_struct *part) +static unsigned int part_in_flight(struct block_device *part) { unsigned int inflight = 0; int cpu; @@ -141,7 +141,8 @@ static unsigned int part_in_flight(struct hd_struct *part) return inflight; } -static void part_in_flight_rw(struct hd_struct *part, unsigned int inflight[2]) +static void part_in_flight_rw(struct block_device *part, + unsigned int inflight[2]) { int cpu; @@ -157,7 +158,7 @@ static void part_in_flight_rw(struct hd_struct *part, unsigned int inflight[2]) inflight[1] = 0; } -struct hd_struct *__disk_get_part(struct gendisk *disk, int partno) +struct block_device *__disk_get_part(struct gendisk *disk, int partno) { struct disk_part_tbl *ptbl = rcu_dereference(disk->part_tbl); @@ -182,15 +183,21 @@ struct hd_struct *__disk_get_part(struct gendisk *disk, int partno) */ struct hd_struct *disk_get_part(struct gendisk *disk, int partno) { + struct block_device *bdev; struct hd_struct *part; rcu_read_lock(); - part = __disk_get_part(disk, partno); - if (part) - get_device(part_to_dev(part)); + bdev = __disk_get_part(disk, partno); + if (!bdev) + goto fail; + part = bdev->bd_part; + if (!kobject_get_unless_zero(&part_to_dev(part)->kobj)) + goto fail; rcu_read_unlock(); - return part; +fail: + rcu_read_unlock(); + return NULL; } /** @@ -264,19 +271,19 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter) /* iterate to the next partition */ for (; piter->idx != end; piter->idx += inc) { - struct hd_struct *part; + struct block_device *part; part = rcu_dereference(ptbl->part[piter->idx]); if (!part) continue; - if (!bdev_nr_sectors(part->bdev) && + if (!bdev_nr_sectors(part) && !(piter->flags & DISK_PITER_INCL_EMPTY) && !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 && piter->idx == 0)) continue; - get_device(part_to_dev(part)); - piter->part = part; + get_device(part_to_dev(part->bd_part)); + piter->part = part->bd_part; piter->idx += inc; break; } @@ -303,10 +310,10 @@ void disk_part_iter_exit(struct disk_part_iter *piter) } EXPORT_SYMBOL_GPL(disk_part_iter_exit); -static inline int sector_in_part(struct hd_struct *part, sector_t sector) +static inline int sector_in_part(struct block_device *part, sector_t sector) { - return part->bdev->bd_start_sect <= sector && - sector < part->bdev->bd_start_sect + bdev_nr_sectors(part->bdev); + return part->bd_start_sect <= sector && + sector < part->bd_start_sect + bdev_nr_sectors(part); } /** @@ -324,10 +331,10 @@ static inline int sector_in_part(struct hd_struct *part, sector_t sector) * Found partition on success, part0 is returned if no partition matches * or the matched partition is being deleted. */ -struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) +struct block_device *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) { struct disk_part_tbl *ptbl; - struct hd_struct *part; + struct block_device *part; int i; rcu_read_lock(); @@ -346,7 +353,7 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) } } - part = disk->part0->bd_part; + part = disk->part0; out_unlock: rcu_read_unlock(); return part; @@ -882,7 +889,7 @@ void del_gendisk(struct gendisk *disk) kobject_put(disk->part0->bd_holder_dir); kobject_put(disk->slave_dir); - part_stat_set_all(disk->part0->bd_part, 0); + part_stat_set_all(disk->part0, 0); disk->part0->bd_stamp = 0; if (!sysfs_deprecated) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); @@ -1189,9 +1196,9 @@ ssize_t part_stat_show(struct device *dev, part_stat_read_all(p, &stat); if (queue_is_mq(q)) - inflight = blk_mq_in_flight(q, p); + inflight = blk_mq_in_flight(q, p->bdev); else - inflight = part_in_flight(p); + inflight = part_in_flight(p->bdev); return sprintf(buf, "%8lu %8lu %8llu %8u " @@ -1231,9 +1238,9 @@ ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, unsigned int inflight[2]; if (queue_is_mq(q)) - blk_mq_in_flight_rw(q, p, inflight); + blk_mq_in_flight_rw(q, p->bdev, inflight); else - part_in_flight_rw(p, inflight); + part_in_flight_rw(p->bdev, inflight); return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]); } @@ -1506,9 +1513,9 @@ static int diskstats_show(struct seq_file *seqf, void *v) while ((hd = disk_part_iter_next(&piter))) { part_stat_read_all(hd, &stat); if (queue_is_mq(gp->queue)) - inflight = blk_mq_in_flight(gp->queue, hd); + inflight = blk_mq_in_flight(gp->queue, hd->bdev); else - inflight = part_in_flight(hd); + inflight = part_in_flight(hd->bdev); seq_printf(seqf, "%4d %7d %s " "%lu %lu %lu %u " @@ -1626,7 +1633,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) goto out_bdput; ptbl = rcu_dereference_protected(disk->part_tbl, 1); - rcu_assign_pointer(ptbl->part[0], disk->part0->bd_part); + rcu_assign_pointer(ptbl->part[0], disk->part0); disk->minors = minors; rand_initialize_disk(disk); diff --git a/block/partitions/core.c b/block/partitions/core.c index 6d1fca193cbd..c2f6721633b8 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -298,12 +298,9 @@ void delete_partition(struct hd_struct *part) struct disk_part_tbl *ptbl = rcu_dereference_protected(disk->part_tbl, 1); - /* - * ->part_tbl is referenced in this part's release handler, so - * we have to hold the disk device - */ rcu_assign_pointer(ptbl->part[part->partno], NULL); rcu_assign_pointer(ptbl->last_lookup, NULL); + kobject_put(part->bdev->bd_holder_dir); device_del(part_to_dev(part)); @@ -421,7 +418,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno, /* everything is up and running, commence */ bdev_add(bdev, devt); - rcu_assign_pointer(ptbl->part[partno], p); + rcu_assign_pointer(ptbl->part[partno], bdev); /* suppress uevent if the disk suppresses it */ if (!dev_get_uevent_suppress(ddev)) diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 9e5c2fdfda36..09c86ef3f0fd 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -2802,7 +2802,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device) if (c_min_rate == 0) return false; - curr_events = (int)part_stat_read_accum(disk->part0->bd_part, sectors) - + curr_events = (int)part_stat_read_accum(disk->part0, sectors) - atomic_read(&device->rs_sect_ev); if (atomic_read(&device->ap_actlog_cnt) diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 343f56b86bb7..02044ab7f767 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -1679,7 +1679,7 @@ void drbd_rs_controller_reset(struct drbd_device *device) atomic_set(&device->rs_sect_ev, 0); device->rs_in_flight = 0; device->rs_last_events = - (int)part_stat_read_accum(disk->part0->bd_part, sectors); + (int)part_stat_read_accum(disk->part0, sectors); /* Updating the RCU protected object in place is necessary since this function gets called from atomic context. diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 6d84876a9cd0..dc8957d173d3 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1687,7 +1687,7 @@ static void zram_reset_device(struct zram *zram) zram->disksize = 0; set_capacity_and_notify(zram->disk, 0); - part_stat_set_all(zram->disk->part0->bd_part, 0); + part_stat_set_all(zram->disk->part0, 0); up_write(&zram->init_lock); /* I/O operation under all of CPU are done so let's free */ diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index afac8d07c1bd..85b1f2a9b72d 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -475,7 +475,7 @@ struct search { unsigned int read_dirty_data:1; unsigned int cache_missed:1; - struct hd_struct *part; + struct block_device *part; unsigned long start_time; struct btree_op op; @@ -1073,7 +1073,7 @@ struct detached_dev_io_private { unsigned long start_time; bio_end_io_t *bi_end_io; void *bi_private; - struct hd_struct *part; + struct block_device *part; }; static void detached_dev_end_io(struct bio *bio) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 1b2db4d530ea..176adcff56b3 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1607,7 +1607,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, * (by eliminating DM's splitting and just using bio_split) */ part_stat_lock(); - __dm_part_stat_sub(dm_disk(md)->part0->bd_part, + __dm_part_stat_sub(dm_disk(md)->part0, sectors[op_stat_group(bio_op(bio))], ci.sector_count); part_stat_unlock(); @@ -2242,7 +2242,7 @@ EXPORT_SYMBOL_GPL(dm_put); static bool md_in_flight_bios(struct mapped_device *md) { int cpu; - struct hd_struct *part = dm_disk(md)->part0->bd_part; + struct block_device *part = dm_disk(md)->part0; long sum = 0; for_each_possible_cpu(cpu) { diff --git a/drivers/md/md.c b/drivers/md/md.c index 3696c2d77a4d..0065736f05b4 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -464,7 +464,7 @@ struct md_io { bio_end_io_t *orig_bi_end_io; void *orig_bi_private; unsigned long start_time; - struct hd_struct *part; + struct block_device *part; }; static void md_end_io(struct bio *bio) @@ -8441,7 +8441,7 @@ static int is_mddev_idle(struct mddev *mddev, int init) rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) { struct gendisk *disk = rdev->bdev->bd_disk; - curr_events = (int)part_stat_read_accum(disk->part0->bd_part, sectors) - + curr_events = (int)part_stat_read_accum(disk->part0, sectors) - atomic_read(&disk->sync_io); /* sync IO will cause sync_io to increase before the disk_stats * as sync_io is counted when a request starts, and diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index dca34489a1dc..8d90235e4fcc 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -89,12 +89,12 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req, if (!ns->bdev) goto out; - host_reads = part_stat_read(ns->bdev->bd_part, ios[READ]); - data_units_read = DIV_ROUND_UP(part_stat_read(ns->bdev->bd_part, - sectors[READ]), 1000); - host_writes = part_stat_read(ns->bdev->bd_part, ios[WRITE]); - data_units_written = DIV_ROUND_UP(part_stat_read(ns->bdev->bd_part, - sectors[WRITE]), 1000); + host_reads = part_stat_read(ns->bdev, ios[READ]); + data_units_read = + DIV_ROUND_UP(part_stat_read(ns->bdev, sectors[READ]), 1000); + host_writes = part_stat_read(ns->bdev, ios[WRITE]); + data_units_written = + DIV_ROUND_UP(part_stat_read(ns->bdev, sectors[WRITE]), 1000); put_unaligned_le64(host_reads, &slog->host_reads[0]); put_unaligned_le64(data_units_read, &slog->data_units_read[0]); @@ -120,12 +120,12 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req, /* we don't have the right data for file backed ns */ if (!ns->bdev) continue; - host_reads += part_stat_read(ns->bdev->bd_part, ios[READ]); + host_reads += part_stat_read(ns->bdev, ios[READ]); data_units_read += DIV_ROUND_UP( - part_stat_read(ns->bdev->bd_part, sectors[READ]), 1000); - host_writes += part_stat_read(ns->bdev->bd_part, ios[WRITE]); + part_stat_read(ns->bdev, sectors[READ]), 1000); + host_writes += part_stat_read(ns->bdev, ios[WRITE]); data_units_written += DIV_ROUND_UP( - part_stat_read(ns->bdev->bd_part, sectors[WRITE]), 1000); + part_stat_read(ns->bdev, sectors[WRITE]), 1000); } put_unaligned_le64(host_reads, &slog->host_reads[0]); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6633b20224d5..c303a0ff0b17 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4048,9 +4048,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_sb = sb; sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; sbi->s_sb_block = sb_block; - if (sb->s_bdev->bd_part) - sbi->s_sectors_written_start = - part_stat_read(sb->s_bdev->bd_part, sectors[STAT_WRITE]); + sbi->s_sectors_written_start = + part_stat_read(sb->s_bdev, sectors[STAT_WRITE]); /* Cleanup superblock name */ strreplace(sb->s_id, '/', '!'); @@ -5509,15 +5508,10 @@ static int ext4_commit_super(struct super_block *sb, int sync) */ if (!(sb->s_flags & SB_RDONLY)) ext4_update_tstamp(es, s_wtime); - if (sb->s_bdev->bd_part) - es->s_kbytes_written = - cpu_to_le64(EXT4_SB(sb)->s_kbytes_written + - ((part_stat_read(sb->s_bdev->bd_part, - sectors[STAT_WRITE]) - - EXT4_SB(sb)->s_sectors_written_start) >> 1)); - else - es->s_kbytes_written = - cpu_to_le64(EXT4_SB(sb)->s_kbytes_written); + es->s_kbytes_written = + cpu_to_le64(EXT4_SB(sb)->s_kbytes_written + + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - + EXT4_SB(sb)->s_sectors_written_start) >> 1)); if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter)) ext4_free_blocks_count_set(es, EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive( diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 4e27fe6ed3ae..075aa3a19ff5 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -62,11 +62,8 @@ static ssize_t session_write_kbytes_show(struct ext4_sb_info *sbi, char *buf) { struct super_block *sb = sbi->s_buddy_cache->i_sb; - if (!sb->s_bdev->bd_part) - return snprintf(buf, PAGE_SIZE, "0\n"); return snprintf(buf, PAGE_SIZE, "%lu\n", - (part_stat_read(sb->s_bdev->bd_part, - sectors[STAT_WRITE]) - + (part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - sbi->s_sectors_written_start) >> 1); } @@ -74,12 +71,9 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_sb_info *sbi, char *buf) { struct super_block *sb = sbi->s_buddy_cache->i_sb; - if (!sb->s_bdev->bd_part) - return snprintf(buf, PAGE_SIZE, "0\n"); return snprintf(buf, PAGE_SIZE, "%llu\n", (unsigned long long)(sbi->s_kbytes_written + - ((part_stat_read(sb->s_bdev->bd_part, - sectors[STAT_WRITE]) - + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - EXT4_SB(sb)->s_sectors_written_start) >> 1))); } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index cb700d797296..49681a8d2b14 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1675,7 +1675,7 @@ static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi) * and the return value is in kbytes. s is of struct f2fs_sb_info. */ #define BD_PART_WRITTEN(s) \ -(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[STAT_WRITE]) - \ + (((u64)part_stat_read((s)->sb->s_bdev, sectors[STAT_WRITE]) - \ (s)->sectors_written_start) >> 1) static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index d4e7fab352ba..af9f449da64b 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3700,10 +3700,8 @@ try_onemore: } /* For write statistics */ - if (sb->s_bdev->bd_part) - sbi->sectors_written_start = - (u64)part_stat_read(sb->s_bdev->bd_part, - sectors[STAT_WRITE]); + sbi->sectors_written_start = + (u64)part_stat_read(sb->s_bdev, sectors[STAT_WRITE]); /* Read accumulated write IO statistics if exists */ seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 619adea57098..1d4be1fc6007 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -191,7 +191,7 @@ struct request { }; struct gendisk *rq_disk; - struct hd_struct *part; + struct block_device *part; #ifdef CONFIG_BLK_RQ_ALLOC_TIME /* Time that the first bio started allocating this request. */ u64 alloc_time_ns; @@ -1943,9 +1943,9 @@ 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 hd_struct **part, - struct bio *bio); -void part_end_io_acct(struct hd_struct *part, struct bio *bio, +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); /** diff --git a/include/linux/genhd.h b/include/linux/genhd.h index df7319da013c..fe6fee77e2b9 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -131,8 +131,8 @@ enum { struct disk_part_tbl { struct rcu_head rcu_head; int len; - struct hd_struct __rcu *last_lookup; - struct hd_struct __rcu *part[]; + struct block_device __rcu *last_lookup; + struct block_device __rcu *part[]; }; struct disk_events; diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index 680de036691e..d2558121d48c 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -25,26 +25,26 @@ struct disk_stats { #define part_stat_unlock() preempt_enable() #define part_stat_get_cpu(part, field, cpu) \ - (per_cpu_ptr((part)->bdev->bd_stats, (cpu))->field) + (per_cpu_ptr((part)->bd_stats, (cpu))->field) #define part_stat_get(part, field) \ part_stat_get_cpu(part, field, smp_processor_id()) #define part_stat_read(part, field) \ ({ \ - typeof((part)->bdev->bd_stats->field) res = 0; \ + typeof((part)->bd_stats->field) res = 0; \ unsigned int _cpu; \ for_each_possible_cpu(_cpu) \ - res += per_cpu_ptr((part)->bdev->bd_stats, _cpu)->field; \ + res += per_cpu_ptr((part)->bd_stats, _cpu)->field; \ res; \ }) -static inline void part_stat_set_all(struct hd_struct *part, int value) +static inline void part_stat_set_all(struct block_device *part, int value) { int i; for_each_possible_cpu(i) - memset(per_cpu_ptr(part->bdev->bd_stats, i), value, + memset(per_cpu_ptr(part->bd_stats, i), value, sizeof(struct disk_stats)); } @@ -54,13 +54,12 @@ static inline void part_stat_set_all(struct hd_struct *part, int value) part_stat_read(part, field[STAT_DISCARD])) #define __part_stat_add(part, field, addnd) \ - __this_cpu_add((part)->bdev->bd_stats->field, addnd) + __this_cpu_add((part)->bd_stats->field, addnd) #define part_stat_add(part, field, addnd) do { \ __part_stat_add((part), field, addnd); \ - if ((part)->partno) \ - __part_stat_add(part_to_disk((part))->part0->bd_part, \ - field, addnd); \ + if ((part)->bd_partno) \ + __part_stat_add(bdev_whole(part), field, addnd); \ } while (0) #define part_stat_dec(part, field) \ -- cgit v1.2.3 From 1c02fca620f7273b597591065d366e2cca948d8f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Dec 2020 17:21:38 +0100 Subject: block: remove the request_queue argument to the block_bio_remap tracepoint The request_queue can trivially be derived from the bio. Signed-off-by: Christoph Hellwig Reviewed-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Chaitanya Kulkarni Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-core.c | 2 +- drivers/md/dm.c | 3 +-- drivers/md/md-linear.c | 3 +-- drivers/md/md.c | 5 ++--- drivers/md/raid0.c | 4 ++-- drivers/md/raid1.c | 7 +++---- drivers/md/raid10.c | 6 ++---- drivers/md/raid5.c | 15 +++++++-------- drivers/nvme/host/multipath.c | 3 +-- include/trace/events/block.h | 8 +++----- kernel/trace/blktrace.c | 14 +++++--------- 11 files changed, 28 insertions(+), 42 deletions(-) (limited to 'drivers/nvme') diff --git a/block/blk-core.c b/block/blk-core.c index cb24654983e1..96e5fcd7f071 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -758,7 +758,7 @@ static inline int blk_partition_remap(struct bio *bio) if (bio_check_eod(bio, bdev_nr_sectors(p))) goto out; bio->bi_iter.bi_sector += p->bd_start_sect; - trace_block_bio_remap(bio->bi_disk->queue, bio, p->bd_dev, + trace_block_bio_remap(bio, p->bd_dev, bio->bi_iter.bi_sector - p->bd_start_sect); } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 9a5bd90779c7..5181907dc595 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1276,8 +1276,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio) break; case DM_MAPIO_REMAPPED: /* the bio has been remapped so dispatch it */ - trace_block_bio_remap(clone->bi_disk->queue, clone, - bio_dev(io->orig_bio), sector); + trace_block_bio_remap(clone, bio_dev(io->orig_bio), sector); ret = submit_bio_noacct(clone); break; case DM_MAPIO_KILL: diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index 98f1b4b2bdce..68cac7d19278 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -257,8 +257,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio) bio_endio(bio); } else { if (mddev->gendisk) - trace_block_bio_remap(bio->bi_disk->queue, - bio, disk_devt(mddev->gendisk), + trace_block_bio_remap(bio, disk_devt(mddev->gendisk), bio_sector); mddev_check_writesame(mddev, bio); mddev_check_write_zeroes(mddev, bio); diff --git a/drivers/md/md.c b/drivers/md/md.c index 0065736f05b4..c555be0a8dce 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8591,9 +8591,8 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, bio_chain(discard_bio, bio); bio_clone_blkg_association(discard_bio, bio); if (mddev->gendisk) - trace_block_bio_remap(bdev_get_queue(rdev->bdev), - discard_bio, disk_devt(mddev->gendisk), - bio->bi_iter.bi_sector); + trace_block_bio_remap(discard_bio, disk_devt(mddev->gendisk), + bio->bi_iter.bi_sector); submit_bio_noacct(discard_bio); } EXPORT_SYMBOL(md_submit_discard_bio); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 6f44177593a5..e5d7411cba9b 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -571,8 +571,8 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) tmp_dev->data_offset; if (mddev->gendisk) - trace_block_bio_remap(bio->bi_disk->queue, bio, - disk_devt(mddev->gendisk), bio_sector); + trace_block_bio_remap(bio, disk_devt(mddev->gendisk), + bio_sector); mddev_check_writesame(mddev, bio); mddev_check_write_zeroes(mddev, bio); submit_bio_noacct(bio); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 960d854c07f8..c0347997f6ff 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1305,8 +1305,8 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, read_bio->bi_private = r1_bio; if (mddev->gendisk) - trace_block_bio_remap(read_bio->bi_disk->queue, read_bio, - disk_devt(mddev->gendisk), r1_bio->sector); + trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk), + r1_bio->sector); submit_bio_noacct(read_bio); } @@ -1517,8 +1517,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, atomic_inc(&r1_bio->remaining); if (mddev->gendisk) - trace_block_bio_remap(mbio->bi_disk->queue, - mbio, disk_devt(mddev->gendisk), + trace_block_bio_remap(mbio, disk_devt(mddev->gendisk), r1_bio->sector); /* flush_pending_writes() needs access to the rdev so...*/ mbio->bi_disk = (void *)conf->mirrors[i].rdev; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index b7bca6703df8..a6f99fa0b32c 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1200,8 +1200,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, read_bio->bi_private = r10_bio; if (mddev->gendisk) - trace_block_bio_remap(read_bio->bi_disk->queue, - read_bio, disk_devt(mddev->gendisk), + trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk), r10_bio->sector); submit_bio_noacct(read_bio); return; @@ -1250,8 +1249,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, mbio->bi_private = r10_bio; if (conf->mddev->gendisk) - trace_block_bio_remap(mbio->bi_disk->queue, - mbio, disk_devt(conf->mddev->gendisk), + trace_block_bio_remap(mbio, disk_devt(conf->mddev->gendisk), r10_bio->sector); /* flush_pending_writes() needs access to the rdev so...*/ mbio->bi_disk = (void *)rdev; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 39343479ac2a..3a90cc0e43ca 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1222,9 +1222,9 @@ again: set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags); if (conf->mddev->gendisk) - trace_block_bio_remap(bi->bi_disk->queue, - bi, disk_devt(conf->mddev->gendisk), - sh->dev[i].sector); + trace_block_bio_remap(bi, + disk_devt(conf->mddev->gendisk), + sh->dev[i].sector); if (should_defer && op_is_write(op)) bio_list_add(&pending_bios, bi); else @@ -1272,9 +1272,9 @@ again: if (op == REQ_OP_DISCARD) rbi->bi_vcnt = 0; if (conf->mddev->gendisk) - trace_block_bio_remap(rbi->bi_disk->queue, - rbi, disk_devt(conf->mddev->gendisk), - sh->dev[i].sector); + trace_block_bio_remap(rbi, + disk_devt(conf->mddev->gendisk), + sh->dev[i].sector); if (should_defer && op_is_write(op)) bio_list_add(&pending_bios, rbi); else @@ -5468,8 +5468,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio) spin_unlock_irq(&conf->device_lock); if (mddev->gendisk) - trace_block_bio_remap(align_bi->bi_disk->queue, - align_bi, disk_devt(mddev->gendisk), + trace_block_bio_remap(align_bi, disk_devt(mddev->gendisk), raid_bio->bi_iter.bi_sector); submit_bio_noacct(align_bi); return 1; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 74896be40c17..106cf5c44ee7 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -312,8 +312,7 @@ blk_qc_t nvme_ns_head_submit_bio(struct bio *bio) if (likely(ns)) { bio->bi_disk = ns->disk; bio->bi_opf |= REQ_NVME_MPATH; - trace_block_bio_remap(bio->bi_disk->queue, bio, - disk_devt(ns->head->disk), + trace_block_bio_remap(bio, disk_devt(ns->head->disk), bio->bi_iter.bi_sector); ret = submit_bio_noacct(bio); } else if (nvme_available_path(head)) { diff --git a/include/trace/events/block.h b/include/trace/events/block.h index b415e4cba843..8fb89574d867 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -450,9 +450,8 @@ TRACE_EVENT(block_split, /** * block_bio_remap - map request for a logical device to the raw device - * @q: queue holding the operation * @bio: revised operation - * @dev: device for the operation + * @dev: original device for the operation * @from: original sector for the operation * * An operation for a logical device has been mapped to the @@ -460,10 +459,9 @@ TRACE_EVENT(block_split, */ TRACE_EVENT(block_bio_remap, - TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev, - sector_t from), + TP_PROTO(struct bio *bio, dev_t dev, sector_t from), - TP_ARGS(q, bio, dev, from), + TP_ARGS(bio, dev, from), TP_STRUCT__entry( __field( dev_t, dev ) diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 3ca6d62114f4..405637144a03 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -993,20 +993,16 @@ static void blk_add_trace_split(void *ignore, struct bio *bio, unsigned int pdu) /** * blk_add_trace_bio_remap - Add a trace for a bio-remap operation * @ignore: trace callback data parameter (not used) - * @q: queue the io is for * @bio: the source bio - * @dev: target device + * @dev: source device * @from: source sector * - * Description: - * Device mapper or raid target sometimes need to split a bio because - * it spans a stripe (or similar). Add a trace for that action. - * + * Called after a bio is remapped to a different device and/or sector. **/ -static void blk_add_trace_bio_remap(void *ignore, - struct request_queue *q, struct bio *bio, - dev_t dev, sector_t from) +static void blk_add_trace_bio_remap(void *ignore, struct bio *bio, dev_t dev, + sector_t from) { + struct request_queue *q = bio->bi_disk->queue; struct blk_trace *bt; struct blk_io_trace_remap r; -- cgit v1.2.3 From 88c9979334aa5ff8c814ddf578f3113ed6c5ce8e Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 3 Dec 2020 09:26:37 +0800 Subject: nvme-loop: use blk_mq_hctx_set_fq_lock_class to set loop's lock class Set nvme-loop's lock class via blk_mq_hctx_set_fq_lock_class for avoiding lockdep possible recursive locking, then we can remove the dynamically allocated lock class for each flush queue, finally we can avoid horrible SCSI probe delay. This way may not address situation in which one nvme-loop is backed on another nvme-loop. However, in reality, people seldom uses this way for test. Even though someone played in this way, it is just one recursive locking false positive, no real deadlock issue. Tested-by: Kashyap Desai Reported-by: Qian Cai Reviewed-by: Christoph Hellwig Cc: Sumit Saxena Cc: John Garry Cc: Kashyap Desai Cc: Bart Van Assche Cc: Hannes Reinecke Signed-off-by: Ming Lei Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- drivers/nvme/target/loop.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'drivers/nvme') diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index f6d81239be21..07806016c09d 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -211,6 +211,8 @@ static int nvme_loop_init_request(struct blk_mq_tag_set *set, (set == &ctrl->tag_set) ? hctx_idx + 1 : 0); } +static struct lock_class_key loop_hctx_fq_lock_key; + static int nvme_loop_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) { @@ -219,6 +221,14 @@ static int nvme_loop_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, BUG_ON(hctx_idx >= ctrl->ctrl.queue_count); + /* + * flush_end_io() can be called recursively for us, so use our own + * lock class key for avoiding lockdep possible recursive locking, + * then we can remove the dynamically allocated lock class for each + * flush queue, that way may cause horrible boot delay. + */ + blk_mq_hctx_set_fq_lock_class(hctx, &loop_hctx_fq_lock_key); + hctx->driver_data = queue; return 0; } -- cgit v1.2.3