From cb8432d650fe3be58bb962bc8e602dc405510327 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 26 Nov 2020 18:47:17 +0100 Subject: block: allocate struct hd_struct as part of struct bdev_inode Allocate hd_struct together with struct block_device to pre-load the lifetime rule changes in preparation of merging the two structures. Note that part0 was previously embedded into struct gendisk, but is a separate allocation now, and already points to the block_device instead of the hd_struct. The lifetime of struct gendisk is still controlled by the struct device embedded in the part0 hd_struct. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/blk-flush.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'block/blk-flush.c') diff --git a/block/blk-flush.c b/block/blk-flush.c index e32958f0b687..fcd0a60574df 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; + struct hd_struct *part = rq->rq_disk->part0->bd_part; part_stat_lock(); part_stat_inc(part, ios[STAT_FLUSH]); -- 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 'block/blk-flush.c') 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 fb01a2932e81a1fb2273f87ff92dc8172b8880ee Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 3 Dec 2020 09:26:36 +0800 Subject: blk-mq: add new API of blk_mq_hctx_set_fq_lock_class flush_end_io() may be called recursively from some driver, such as nvme-loop, so lockdep may complain 'possible recursive locking'. Commit b3c6a5997541("block: Fix a lockdep complaint triggered by request queue flushing") tried to address this issue by assigning dynamically allocated per-flush-queue lock class. This solution adds synchronize_rcu() for each hctx's release handler, and causes horrible SCSI MQ probe delay(more than half an hour on megaraid sas). Add new API of blk_mq_hctx_set_fq_lock_class() for these drivers, so we just need to use driver specific lock class for avoiding the lockdep warning of 'possible recursive locking'. Tested-by: Kashyap Desai Reported-by: Qian Cai 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 --- block/blk-flush.c | 25 +++++++++++++++++++++++++ include/linux/blk-mq.h | 3 +++ 2 files changed, 28 insertions(+) (limited to 'block/blk-flush.c') diff --git a/block/blk-flush.c b/block/blk-flush.c index 9507dcdd5881..bf51588762d8 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -490,3 +490,28 @@ void blk_free_flush_queue(struct blk_flush_queue *fq) kfree(fq->flush_rq); kfree(fq); } + +/* + * Allow driver to set its own lock class to fq->mq_flush_lock for + * avoiding lockdep complaint. + * + * flush_end_io() may be called recursively from some driver, such as + * nvme-loop, so lockdep may complain 'possible recursive locking' because + * all 'struct blk_flush_queue' instance share same mq_flush_lock lock class + * key. We need to assign different lock class for these driver's + * fq->mq_flush_lock for avoiding the lockdep warning. + * + * Use dynamically allocated lock class key for each 'blk_flush_queue' + * instance is over-kill, and more worse it introduces horrible boot delay + * issue because synchronize_rcu() is implied in lockdep_unregister_key which + * is called for each hctx release. SCSI probing may synchronously create and + * destroy lots of MQ request_queues for non-existent devices, and some robot + * test kernel always enable lockdep option. It is observed that more than half + * an hour is taken during SCSI MQ probe with per-fq lock class. + */ +void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, + struct lock_class_key *key) +{ + lockdep_set_class(&hctx->fq->mq_flush_lock, key); +} +EXPORT_SYMBOL_GPL(blk_mq_hctx_set_fq_lock_class); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 794b2a33a2c3..5f639240760e 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -5,6 +5,7 @@ #include #include #include +#include struct blk_mq_tags; struct blk_flush_queue; @@ -594,5 +595,7 @@ static inline void blk_mq_cleanup_rq(struct request *rq) } blk_qc_t blk_mq_submit_bio(struct bio *bio); +void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, + struct lock_class_key *key); #endif -- cgit v1.2.3 From 7aa390ec2d9db0cd6677d95d0b8f307f9c086770 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 3 Dec 2020 09:26:38 +0800 Subject: Revert "block: Fix a lockdep complaint triggered by request queue flushing" This reverts commit b3c6a59975415bde29cfd76ff1ab008edbf614a9. Now we can avoid nvme-loop lockdep warning of 'lockdep possible recursive locking' by nvme-loop's lock class, no need to apply dynamically allocated lock class key, so revert commit b3c6a5997541("block: Fix a lockdep complaint triggered by request queue flushing"). This way fixes horrible SCSI probe delay issue on megaraid_sas, and it is reported the whole probe may take more than half an hour. 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 --- block/blk-flush.c | 5 ----- block/blk.h | 1 - 2 files changed, 6 deletions(-) (limited to 'block/blk-flush.c') diff --git a/block/blk-flush.c b/block/blk-flush.c index bf51588762d8..996d5d03dade 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -69,7 +69,6 @@ #include #include #include -#include #include "blk.h" #include "blk-mq.h" @@ -469,9 +468,6 @@ struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size, INIT_LIST_HEAD(&fq->flush_queue[1]); INIT_LIST_HEAD(&fq->flush_data_in_flight); - lockdep_register_key(&fq->key); - lockdep_set_class(&fq->mq_flush_lock, &fq->key); - return fq; fail_rq: @@ -486,7 +482,6 @@ void blk_free_flush_queue(struct blk_flush_queue *fq) if (!fq) return; - lockdep_unregister_key(&fq->key); kfree(fq->flush_rq); kfree(fq); } diff --git a/block/blk.h b/block/blk.h index 98f0b1ae2641..d23d018fd2cd 100644 --- a/block/blk.h +++ b/block/blk.h @@ -25,7 +25,6 @@ struct blk_flush_queue { struct list_head flush_data_in_flight; struct request *flush_rq; - struct lock_class_key key; spinlock_t mq_flush_lock; }; -- cgit v1.2.3