From db04e18dbb0146d3c753dc05f7233350375bbc48 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 19 Aug 2020 14:34:03 +0200 Subject: block: Make request_queue.rpm_status an enum request_queue.rpm_status is assigned values of the rpm_status enum only, so reflect that in its type. Note that including is (currently) a no-op, as it is already included through and , but it is better to play it safe. Signed-off-by: Geert Uytterhoeven Acked-by: Rafael J. Wysocki Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bb5636cc17b9..0a1730b30ad2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -24,6 +24,7 @@ #include #include #include +#include struct module; struct scsi_ioctl_command; @@ -458,7 +459,7 @@ struct request_queue { #ifdef CONFIG_PM struct device *dev; - int rpm_status; + enum rpm_status rpm_status; unsigned int nr_pending; #endif -- cgit v1.2.3 From 611bee526b4a89d49f1b9914a770bfdc101d5fb5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 23 Aug 2020 11:10:41 +0200 Subject: block: replace bd_set_size with bd_set_nr_sectors Replace bd_set_size with a version that takes the number of sectors instead, as that fits most of the current and future callers much better. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- drivers/block/loop.c | 4 ++-- drivers/block/nbd.c | 7 ++++--- drivers/block/pktcdvd.c | 2 +- drivers/nvme/host/nvme.h | 2 +- fs/block_dev.c | 10 +++++----- include/linux/genhd.h | 2 +- 6 files changed, 14 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index d3394191e168..cb1191d6e945 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -253,7 +253,7 @@ static void loop_set_size(struct loop_device *lo, loff_t size) { struct block_device *bdev = lo->lo_device; - bd_set_size(bdev, size << SECTOR_SHIFT); + bd_set_nr_sectors(bdev, size); set_capacity_revalidate_and_notify(lo->lo_disk, size, false); } @@ -1251,7 +1251,7 @@ static int __loop_clr_fd(struct loop_device *lo, bool release) set_capacity(lo->lo_disk, 0); loop_sysfs_exit(lo); if (bdev) { - bd_set_size(bdev, 0); + bd_set_nr_sectors(bdev, 0); /* let user-space know about this change */ kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index edf8b632e3d2..a54f2d155a31 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -300,6 +300,7 @@ static void nbd_size_update(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; struct block_device *bdev = bdget_disk(nbd->disk, 0); + sector_t nr_sectors = config->bytesize >> 9; if (config->flags & NBD_FLAG_SEND_TRIM) { nbd->disk->queue->limits.discard_granularity = config->blksize; @@ -308,10 +309,10 @@ static void nbd_size_update(struct nbd_device *nbd) } blk_queue_logical_block_size(nbd->disk->queue, config->blksize); blk_queue_physical_block_size(nbd->disk->queue, config->blksize); - set_capacity(nbd->disk, config->bytesize >> 9); + set_capacity(nbd->disk, nr_sectors); if (bdev) { if (bdev->bd_disk) { - bd_set_size(bdev, config->bytesize); + bd_set_nr_sectors(bdev, nr_sectors); set_blocksize(bdev, config->blksize); } else bdev->bd_invalidated = 1; @@ -1138,7 +1139,7 @@ static void nbd_bdev_reset(struct block_device *bdev) { if (bdev->bd_openers > 1) return; - bd_set_size(bdev, 0); + bd_set_nr_sectors(bdev, 0); } static void nbd_parse_flags(struct nbd_device *nbd) diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 1034e445680c..17f2e6ff1223 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2192,7 +2192,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) set_capacity(pd->disk, lba << 2); set_capacity(pd->bdev->bd_disk, lba << 2); - bd_set_size(pd->bdev, (loff_t)lba << 11); + bd_set_nr_sectors(pd->bdev, lba << 2); q = bdev_get_queue(pd->bdev); if (write) { diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 2910f6caab7d..aab130f31e25 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -688,7 +688,7 @@ static inline void nvme_mpath_update_disk_size(struct gendisk *disk) struct block_device *bdev = bdget_disk(disk, 0); if (bdev) { - bd_set_size(bdev, get_capacity(disk) << SECTOR_SHIFT); + bd_set_nr_sectors(bdev, get_capacity(disk)); bdput(bdev); } } diff --git a/fs/block_dev.c b/fs/block_dev.c index 8ae833e00443..f52597172c8b 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1371,13 +1371,13 @@ int check_disk_change(struct block_device *bdev) EXPORT_SYMBOL(check_disk_change); -void bd_set_size(struct block_device *bdev, loff_t size) +void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors) { inode_lock(bdev->bd_inode); - i_size_write(bdev->bd_inode, size); + i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); inode_unlock(bdev->bd_inode); } -EXPORT_SYMBOL(bd_set_size); +EXPORT_SYMBOL(bd_set_nr_sectors); static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); @@ -1514,7 +1514,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder, } if (!ret) { - bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); + bd_set_nr_sectors(bdev, get_capacity(disk)); set_init_blocksize(bdev); } @@ -1542,7 +1542,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder, ret = -ENXIO; goto out_clear; } - bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9); + bd_set_nr_sectors(bdev, bdev->bd_part->nr_sects); set_init_blocksize(bdev); } diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 4ab853461dff..39025dc0397c 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -375,7 +375,7 @@ void unregister_blkdev(unsigned int major, const char *name); int revalidate_disk(struct gendisk *disk); int check_disk_change(struct block_device *bdev); int __invalidate_device(struct block_device *bdev, bool kill_dirty); -void bd_set_size(struct block_device *bdev, loff_t size); +void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors); /* for drivers/char/raw.c: */ int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); -- cgit v1.2.3 From c2b4bb8cb3741c0bacf3683e4c1ecd04c977ada3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 23 Aug 2020 11:10:42 +0200 Subject: block: fix locking for struct block_device size updates Two different callers use two different mutexes for updating the block device size, which obviously doesn't help to actually protect against concurrent updates from the different callers. In addition one of the locks, bd_mutex is rather prone to deadlocks with other parts of the block stack that use it for high level synchronization. Switch to using a new spinlock protecting just the size updates, as that is all we need, and make sure everyone does the update through the proper helper. This fixes a bug reported with the nvme revalidating disks during a hot removal operation, which can currently deadlock on bd_mutex. Reported-by: Xianting Tian Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- block/partitions/core.c | 4 ++-- drivers/block/aoe/aoecmd.c | 4 +--- drivers/md/dm.c | 15 ++------------- drivers/s390/block/dasd_ioctl.c | 9 ++------- fs/block_dev.c | 25 ++++++++++++++----------- include/linux/blk_types.h | 1 + 6 files changed, 22 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/block/partitions/core.c b/block/partitions/core.c index 5b4869c08fb3..b1c0b50ca92d 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -592,8 +592,8 @@ int bdev_resize_partition(struct block_device *bdev, int partno, if (partition_overlaps(bdev->bd_disk, start, length, partno)) goto out_unlock; - part_nr_sects_write(part, (sector_t)length); - i_size_write(bdevp->bd_inode, length << SECTOR_SHIFT); + part_nr_sects_write(part, length); + bd_set_nr_sectors(bdevp, length); ret = 0; out_unlock: diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 6dba41395155..313f0b946fe2 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -900,9 +900,7 @@ aoecmd_sleepwork(struct work_struct *work) ssize = get_capacity(d->gd); bd = bdget_disk(d->gd, 0); if (bd) { - inode_lock(bd->bd_inode); - i_size_write(bd->bd_inode, (loff_t)ssize<<9); - inode_unlock(bd->bd_inode); + bd_set_nr_sectors(bd, ssize); bdput(bd); } spin_lock_irq(&d->lock); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index fb0255d25e4b..3dedd9cc4fb6 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2097,18 +2097,6 @@ static void event_callback(void *context) dm_issue_global_event(); } -/* - * Protected by md->suspend_lock obtained by dm_swap_table(). - */ -static void __set_size(struct mapped_device *md, sector_t size) -{ - lockdep_assert_held(&md->suspend_lock); - - set_capacity(md->disk, size); - - i_size_write(md->bdev->bd_inode, (loff_t)size << SECTOR_SHIFT); -} - /* * Returns old map, which caller must destroy. */ @@ -2131,7 +2119,8 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, if (size != dm_get_size(md)) memset(&md->geometry, 0, sizeof(md->geometry)); - __set_size(md, size); + set_capacity(md->disk, size); + bd_set_nr_sectors(md->bdev, size); dm_table_event_callback(t, event_callback, md); diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index 777734d1b4e5..faaf5596e31c 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -55,10 +55,7 @@ dasd_ioctl_enable(struct block_device *bdev) dasd_enable_device(base); /* Formatting the dasd device can change the capacity. */ - mutex_lock(&bdev->bd_mutex); - i_size_write(bdev->bd_inode, - (loff_t)get_capacity(base->block->gdp) << 9); - mutex_unlock(&bdev->bd_mutex); + bd_set_nr_sectors(bdev, get_capacity(base->block->gdp)); dasd_put_device(base); return 0; } @@ -91,9 +88,7 @@ dasd_ioctl_disable(struct block_device *bdev) * Set i_size to zero, since read, write, etc. check against this * value. */ - mutex_lock(&bdev->bd_mutex); - i_size_write(bdev->bd_inode, 0); - mutex_unlock(&bdev->bd_mutex); + bd_set_nr_sectors(bdev, 0); dasd_put_device(base); return 0; } diff --git a/fs/block_dev.c b/fs/block_dev.c index f52597172c8b..08158bb2e76c 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -876,6 +876,7 @@ struct block_device *bdget(dev_t dev) bdev = &BDEV_I(inode)->bdev; if (inode->i_state & I_NEW) { + spin_lock_init(&bdev->bd_size_lock); bdev->bd_contains = NULL; bdev->bd_super = NULL; bdev->bd_inode = inode; @@ -1290,6 +1291,7 @@ static void check_disk_size_change(struct gendisk *disk, { loff_t disk_size, bdev_size; + spin_lock(&bdev->bd_size_lock); disk_size = (loff_t)get_capacity(disk) << 9; bdev_size = i_size_read(bdev->bd_inode); if (disk_size != bdev_size) { @@ -1299,11 +1301,15 @@ static void check_disk_size_change(struct gendisk *disk, disk->disk_name, bdev_size, disk_size); } i_size_write(bdev->bd_inode, disk_size); - if (bdev_size > disk_size && __invalidate_device(bdev, false)) + } + bdev->bd_invalidated = 0; + spin_unlock(&bdev->bd_size_lock); + + if (bdev_size > disk_size) { + if (__invalidate_device(bdev, false)) pr_warn("VFS: busy inodes on resized disk %s\n", disk->disk_name); } - bdev->bd_invalidated = 0; } /** @@ -1328,13 +1334,10 @@ int revalidate_disk(struct gendisk *disk) if (!(disk->flags & GENHD_FL_HIDDEN)) { struct block_device *bdev = bdget_disk(disk, 0); - if (!bdev) - return ret; - - mutex_lock(&bdev->bd_mutex); - check_disk_size_change(disk, bdev, ret == 0); - mutex_unlock(&bdev->bd_mutex); - bdput(bdev); + if (bdev) { + check_disk_size_change(disk, bdev, ret == 0); + bdput(bdev); + } } return ret; } @@ -1373,9 +1376,9 @@ EXPORT_SYMBOL(check_disk_change); void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors) { - inode_lock(bdev->bd_inode); + spin_lock(&bdev->bd_size_lock); i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); - inode_unlock(bdev->bd_inode); + spin_unlock(&bdev->bd_size_lock); } EXPORT_SYMBOL(bd_set_nr_sectors); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 4ecf4fed171f..5accc2549d22 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -38,6 +38,7 @@ struct block_device { /* number of times partitions within this device have been opened. */ unsigned bd_part_count; int bd_invalidated; + spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct gendisk * bd_disk; struct backing_dev_info *bd_bdi; -- cgit v1.2.3 From f3256075ba49d80835b601bfbff350a2140b2924 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 27 Aug 2020 17:37:45 +0200 Subject: block: remove the BIO_NULL_MAPPED flag We can simply use a boolean flag in the bio_map_data data structure instead. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-map.c | 9 +++++---- include/linux/blk_types.h | 1 - 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/block/blk-map.c b/block/blk-map.c index 6e804892d5ec..51e6195f878d 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -12,7 +12,8 @@ #include "blk.h" struct bio_map_data { - int is_our_pages; + bool is_our_pages : 1; + bool is_null_mapped : 1; struct iov_iter iter; struct iovec iov[]; }; @@ -108,7 +109,7 @@ static int bio_uncopy_user(struct bio *bio) struct bio_map_data *bmd = bio->bi_private; int ret = 0; - if (!bio_flagged(bio, BIO_NULL_MAPPED)) { + if (!bmd || !bmd->is_null_mapped) { /* * if we're in a workqueue, the request is orphaned, so * don't copy into a random user address space, just free @@ -158,7 +159,7 @@ static struct bio *bio_copy_user_iov(struct request_queue *q, * The caller provided iov might point to an on-stack or otherwise * shortlived one. */ - bmd->is_our_pages = map_data ? 0 : 1; + bmd->is_our_pages = !map_data; nr_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE); if (nr_pages > BIO_MAX_PAGES) @@ -234,7 +235,7 @@ static struct bio *bio_copy_user_iov(struct request_queue *q, bio->bi_private = bmd; if (map_data && map_data->null_mapped) - bio_set_flag(bio, BIO_NULL_MAPPED); + bmd->is_null_mapped = true; return bio; cleanup: if (!map_data) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 5accc2549d22..78b073956884 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -257,7 +257,6 @@ enum { BIO_CLONED, /* doesn't own data */ BIO_BOUNCED, /* bio is a bounce bio */ BIO_USER_MAPPED, /* contains user pages */ - BIO_NULL_MAPPED, /* contains invalid user pages */ BIO_WORKINGSET, /* contains userspace workingset pages */ BIO_QUIET, /* Make BIO Quiet */ BIO_CHAIN, /* chained bio, ->bi_remaining in effect */ -- cgit v1.2.3 From 3310eebafe6f9a872c1f757b3d822dafae9c0cd8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 27 Aug 2020 17:37:48 +0200 Subject: block: remove the BIO_USER_MAPPED flag Just check if there is private data, in which case the bio must have originated from bio_copy_user_iov. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-map.c | 10 ++++------ include/linux/blk_types.h | 1 - 2 files changed, 4 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/block/blk-map.c b/block/blk-map.c index 427962ac2f67..be118926ccf4 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -109,7 +109,7 @@ static int bio_uncopy_user(struct bio *bio) struct bio_map_data *bmd = bio->bi_private; int ret = 0; - if (!bmd || !bmd->is_null_mapped) { + if (!bmd->is_null_mapped) { /* * if we're in a workqueue, the request is orphaned, so * don't copy into a random user address space, just free @@ -307,8 +307,6 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, break; } - bio_set_flag(bio, BIO_USER_MAPPED); - /* * Subtle: if we end up needing to bounce a bio, it would normally * disappear when its bi_end_io is run. However, we need the original @@ -654,12 +652,12 @@ int blk_rq_unmap_user(struct bio *bio) if (unlikely(bio_flagged(bio, BIO_BOUNCED))) mapped_bio = bio->bi_private; - if (bio_flagged(mapped_bio, BIO_USER_MAPPED)) { - bio_unmap_user(mapped_bio); - } else { + if (bio->bi_private) { ret2 = bio_uncopy_user(mapped_bio); if (ret2 && !ret) ret = ret2; + } else { + bio_unmap_user(mapped_bio); } mapped_bio = bio; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 78b073956884..63a39e47fc60 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -256,7 +256,6 @@ enum { BIO_NO_PAGE_REF, /* don't put release vec pages */ BIO_CLONED, /* doesn't own data */ BIO_BOUNCED, /* bio is a bounce bio */ - BIO_USER_MAPPED, /* contains user pages */ BIO_WORKINGSET, /* contains userspace workingset pages */ BIO_QUIET, /* Make BIO Quiet */ BIO_CHAIN, /* chained bio, ->bi_remaining in effect */ -- cgit v1.2.3 From bdc6a287bc98e8f32bf52c9cb2d1bdf75975f5a0 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 28 Aug 2020 10:52:55 +0800 Subject: block: Move blk_mq_bio_list_merge() into blk-merge.c Move the blk_mq_bio_list_merge() into blk-merge.c and rename it as a generic name. Reviewed-by: Christoph Hellwig Signed-off-by: Baolin Wang Signed-off-by: Jens Axboe --- block/blk-merge.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ block/blk-mq-sched.c | 46 +--------------------------------------------- block/blk.h | 2 ++ block/kyber-iosched.c | 2 +- include/linux/blk-mq.h | 2 -- 5 files changed, 48 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/block/blk-merge.c b/block/blk-merge.c index 3aa2de57b57f..b09e9fc44236 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -1052,3 +1052,47 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, return false; } + +/* + * Iterate list of requests and see if we can merge this bio with any + * of them. + */ +bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, + struct bio *bio, unsigned int nr_segs) +{ + struct request *rq; + int checked = 8; + + list_for_each_entry_reverse(rq, list, queuelist) { + bool merged = false; + + if (!checked--) + break; + + if (!blk_rq_merge_ok(rq, bio)) + continue; + + switch (blk_try_merge(rq, bio)) { + case ELEVATOR_BACK_MERGE: + if (blk_mq_sched_allow_merge(q, rq, bio)) + merged = bio_attempt_back_merge(rq, bio, + nr_segs); + break; + case ELEVATOR_FRONT_MERGE: + if (blk_mq_sched_allow_merge(q, rq, bio)) + merged = bio_attempt_front_merge(rq, bio, + nr_segs); + break; + case ELEVATOR_DISCARD_MERGE: + merged = bio_attempt_discard_merge(q, rq, bio); + break; + default: + continue; + } + + return merged; + } + + return false; +} +EXPORT_SYMBOL_GPL(blk_bio_list_merge); diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index d2790e5b06d1..82acff96c093 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -391,50 +391,6 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, } EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge); -/* - * Iterate list of requests and see if we can merge this bio with any - * of them. - */ -bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, - struct bio *bio, unsigned int nr_segs) -{ - struct request *rq; - int checked = 8; - - list_for_each_entry_reverse(rq, list, queuelist) { - bool merged = false; - - if (!checked--) - break; - - if (!blk_rq_merge_ok(rq, bio)) - continue; - - switch (blk_try_merge(rq, bio)) { - case ELEVATOR_BACK_MERGE: - if (blk_mq_sched_allow_merge(q, rq, bio)) - merged = bio_attempt_back_merge(rq, bio, - nr_segs); - break; - case ELEVATOR_FRONT_MERGE: - if (blk_mq_sched_allow_merge(q, rq, bio)) - merged = bio_attempt_front_merge(rq, bio, - nr_segs); - break; - case ELEVATOR_DISCARD_MERGE: - merged = bio_attempt_discard_merge(q, rq, bio); - break; - default: - continue; - } - - return merged; - } - - return false; -} -EXPORT_SYMBOL_GPL(blk_mq_bio_list_merge); - /* * Reverse check our software queue for entries that we could potentially * merge with. Currently includes a hand-wavy stop count of 8, to not spend @@ -449,7 +405,7 @@ static bool blk_mq_attempt_merge(struct request_queue *q, lockdep_assert_held(&ctx->lock); - if (blk_mq_bio_list_merge(q, &ctx->rq_lists[type], bio, nr_segs)) { + if (blk_bio_list_merge(q, &ctx->rq_lists[type], bio, nr_segs)) { ctx->rq_merged++; return true; } diff --git a/block/blk.h b/block/blk.h index 49e2928a1632..d6152d20d4e2 100644 --- a/block/blk.h +++ b/block/blk.h @@ -177,6 +177,8 @@ bool bio_attempt_discard_merge(struct request_queue *q, struct request *req, struct bio *bio); bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs, struct request **same_queue_rq); +bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, + struct bio *bio, unsigned int nr_segs); void blk_account_io_start(struct request *req); void blk_account_io_done(struct request *req, u64 now); diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index a38c5ab103d1..6d4ba0e9688e 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -573,7 +573,7 @@ static bool kyber_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio, bool merged; spin_lock(&kcq->lock); - merged = blk_mq_bio_list_merge(hctx->queue, rq_list, bio, nr_segs); + merged = blk_bio_list_merge(hctx->queue, rq_list, bio, nr_segs); spin_unlock(&kcq->lock); return merged; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 9d2d5ad367a4..21a02e0577dd 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -489,8 +489,6 @@ void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); void blk_mq_complete_request(struct request *rq); bool blk_mq_complete_request_remote(struct request *rq); -bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, - struct bio *bio, unsigned int nr_segs); bool blk_mq_queue_stopped(struct request_queue *q); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); -- cgit v1.2.3 From 7b8917f5e29c377be1db5680249fe30e038cb3eb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 31 Aug 2020 20:02:33 +0200 Subject: block: remove the alignment_offset field from struct hd_struct The alignment offset is only used in slow path callers, so just calculate it on the fly. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/partitions/core.c | 7 ++++--- include/linux/blkdev.h | 5 ++--- include/linux/genhd.h | 1 - 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/block/partitions/core.c b/block/partitions/core.c index b1c0b50ca92d..94c2fb39e602 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -199,7 +199,10 @@ static ssize_t part_alignment_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hd_struct *p = dev_to_part(dev); - return sprintf(buf, "%llu\n", (unsigned long long)p->alignment_offset); + + return sprintf(buf, "%u\n", + queue_limit_alignment_offset(&part_to_disk(p)->queue->limits, + p->start_sect)); } static ssize_t part_discard_alignment_show(struct device *dev, @@ -405,8 +408,6 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno, pdev = part_to_dev(p); p->start_sect = start; - p->alignment_offset = - queue_limit_alignment_offset(&disk->queue->limits, start); p->discard_alignment = queue_limit_discard_alignment(&disk->queue->limits, start); p->nr_sects = len; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0a1730b30ad2..ba1f5f5e11c6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1456,10 +1456,9 @@ static inline int bdev_alignment_offset(struct block_device *bdev) if (q->limits.misaligned) return -1; - if (bdev != bdev->bd_contains) - return bdev->bd_part->alignment_offset; - + return queue_limit_alignment_offset(&q->limits, + bdev->bd_part->start_sect); return q->limits.alignment_offset; } diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 39025dc0397c..bfa411c80dbb 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -65,7 +65,6 @@ struct hd_struct { struct disk_stats __percpu *dkstats; struct percpu_ref ref; - sector_t alignment_offset; unsigned int discard_alignment; struct device __dev; struct kobject *holder_dir; -- cgit v1.2.3 From 7cf34d97ab45203b975396393ded9d3867dfa8bf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 31 Aug 2020 20:02:34 +0200 Subject: block: remove the discard_alignment field from struct hd_struct The alignment offset is only used in slow path callers, so just calculate it on the fly. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/partitions/core.c | 7 ++++--- include/linux/blkdev.h | 4 ++-- include/linux/genhd.h | 1 - 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/block/partitions/core.c b/block/partitions/core.c index 94c2fb39e602..e596a85bba1e 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -209,7 +209,10 @@ static ssize_t part_discard_alignment_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hd_struct *p = dev_to_part(dev); - return sprintf(buf, "%u\n", p->discard_alignment); + + return sprintf(buf, "%u\n", + queue_limit_discard_alignment(&part_to_disk(p)->queue->limits, + p->start_sect)); } static DEVICE_ATTR(partition, 0444, part_partition_show, NULL); @@ -408,8 +411,6 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno, pdev = part_to_dev(p); p->start_sect = start; - p->discard_alignment = - queue_limit_discard_alignment(&disk->queue->limits, start); p->nr_sects = len; p->partno = partno; p->policy = get_disk_ro(disk); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ba1f5f5e11c6..d0d61bc81615 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1498,8 +1498,8 @@ static inline int bdev_discard_alignment(struct block_device *bdev) struct request_queue *q = bdev_get_queue(bdev); if (bdev != bdev->bd_contains) - return bdev->bd_part->discard_alignment; - + return queue_limit_discard_alignment(&q->limits, + bdev->bd_part->start_sect); return q->limits.discard_alignment; } diff --git a/include/linux/genhd.h b/include/linux/genhd.h index bfa411c80dbb..9ea2ca31c278 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -65,7 +65,6 @@ struct hd_struct { struct disk_stats __percpu *dkstats; struct percpu_ref ref; - unsigned int discard_alignment; struct device __dev; struct kobject *holder_dir; int policy, partno; -- cgit v1.2.3 From 46d40cfad13ccbd0739019d754d46d8f93e1d5aa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 31 Aug 2020 20:02:35 +0200 Subject: block: remove an outdated comment on the bd_dev field kdev_t is long gone, so we don't need to comment a field isn't one.. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 63a39e47fc60..59d9150165c4 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -20,7 +20,7 @@ typedef void (bio_end_io_t) (struct bio *); struct bio_crypt_ctx; struct block_device { - dev_t bd_dev; /* not a kdev_t - it's a search key */ + dev_t bd_dev; int bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; -- cgit v1.2.3 From 1aa50d020c7148f5f0bde15ca80fe6f91a8c5a4e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 1 Sep 2020 14:52:44 -0400 Subject: blk-iocost: calculate iocg->usages[] from iocg->local_stat.usage_us Currently, iocg->usages[] which are used to guide inuse adjustments are calculated from vtime deltas. This, however, assumes that the hierarchical inuse weight at the time of calculation held for the entire period, which often isn't true and can lead to significant errors. Now that we have absolute usage information collected, we can derive iocg->usages[] from iocg->local_stat.usage_us so that inuse adjustment decisions are made based on actual absolute usage. The calculated usage is clamped between 1 and WEIGHT_ONE and WEIGHT_ONE is also used to signal saturation regardless of the current hierarchical inuse weight. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-iocost.c | 72 +++++++++++++++++++++++++++---------------- include/trace/events/iocost.h | 7 ++--- 2 files changed, 47 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/block/blk-iocost.c b/block/blk-iocost.c index f30f9b37fcf0..2496674bbbf4 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -476,14 +476,10 @@ struct ioc_gq { * `vtime_done` is the same but progressed on completion rather * than issue. The delta behind `vtime` represents the cost of * currently in-flight IOs. - * - * `last_vtime` is used to remember `vtime` at the end of the last - * period to calculate utilization. */ atomic64_t vtime; atomic64_t done_vtime; u64 abs_vdebt; - u64 last_vtime; /* * The period this iocg was last active in. Used for deactivation @@ -506,6 +502,9 @@ struct ioc_gq { struct hrtimer waitq_timer; struct hrtimer delay_timer; + /* timestamp at the latest activation */ + u64 activated_at; + /* statistics */ struct iocg_pcpu_stat __percpu *pcpu_stat; struct iocg_stat local_stat; @@ -514,6 +513,7 @@ struct ioc_gq { u64 last_stat_abs_vusage; /* usage is recorded as fractions of WEIGHT_ONE */ + u32 usage_delta_us; int usage_idx; u32 usages[NR_USAGE_SLOTS]; @@ -1159,7 +1159,7 @@ static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now) TRACE_IOCG_PATH(iocg_activate, iocg, now, last_period, cur_period, vtime); - iocg->last_vtime = vtime; + iocg->activated_at = now->now; if (ioc->running == IOC_IDLE) { ioc->running = IOC_RUNNING; @@ -1451,7 +1451,8 @@ static void iocg_flush_stat_one(struct ioc_gq *iocg, struct ioc_now *now) vusage_delta = abs_vusage - iocg->last_stat_abs_vusage; iocg->last_stat_abs_vusage = abs_vusage; - iocg->local_stat.usage_us += div64_u64(vusage_delta, now->vrate); + iocg->usage_delta_us = div64_u64(vusage_delta, now->vrate); + iocg->local_stat.usage_us += iocg->usage_delta_us; new_stat.usage_us = iocg->local_stat.usage_us + iocg->desc_stat.usage_us; @@ -1558,8 +1559,9 @@ static void ioc_timer_fn(struct timer_list *timer) /* calc usages and see whether some weights need to be moved around */ list_for_each_entry(iocg, &ioc->active_iocgs, active_list) { - u64 vdone, vtime, vusage, vmin; + u64 vdone, vtime, usage_us, vmin; u32 hw_active, hw_inuse, usage; + int uidx; /* * Collect unused and wind vtime closer to vnow to prevent @@ -1583,27 +1585,44 @@ static void ioc_timer_fn(struct timer_list *timer) time_before64(vdone, now.vnow - period_vtime)) nr_lagging++; - if (waitqueue_active(&iocg->waitq)) - vusage = now.vnow - iocg->last_vtime; - else if (time_before64(iocg->last_vtime, vtime)) - vusage = vtime - iocg->last_vtime; - else - vusage = 0; - - iocg->last_vtime += vusage; /* - * Factor in in-flight vtime into vusage to avoid - * high-latency completions appearing as idle. This should - * be done after the above ->last_time adjustment. + * Determine absolute usage factoring in pending and in-flight + * IOs to avoid stalls and high-latency completions appearing as + * idle. */ - vusage = max(vusage, vtime - vdone); - - /* calculate hweight based usage ratio and record */ - if (vusage) { - usage = DIV64_U64_ROUND_UP(vusage * hw_inuse, - period_vtime); - iocg->usage_idx = (iocg->usage_idx + 1) % NR_USAGE_SLOTS; - iocg->usages[iocg->usage_idx] = usage; + usage_us = iocg->usage_delta_us; + if (waitqueue_active(&iocg->waitq) && time_before64(vtime, now.vnow)) + usage_us += DIV64_U64_ROUND_UP( + cost_to_abs_cost(now.vnow - vtime, hw_inuse), + now.vrate); + if (vdone != vtime) { + u64 inflight_us = DIV64_U64_ROUND_UP( + cost_to_abs_cost(vtime - vdone, hw_inuse), + now.vrate); + usage_us = max(usage_us, inflight_us); + } + + /* convert to hweight based usage ratio and record */ + uidx = (iocg->usage_idx + 1) % NR_USAGE_SLOTS; + + if (time_after64(vtime, now.vnow - ioc->margins.min)) { + iocg->usage_idx = uidx; + iocg->usages[uidx] = WEIGHT_ONE; + } else if (usage_us) { + u64 started_at, dur; + + if (time_after64(iocg->activated_at, ioc->period_at)) + started_at = iocg->activated_at; + else + started_at = ioc->period_at; + + dur = max_t(u64, now.now - started_at, 1); + usage = clamp_t(u32, + DIV64_U64_ROUND_UP(usage_us * WEIGHT_ONE, dur), + 1, WEIGHT_ONE); + + iocg->usage_idx = uidx; + iocg->usages[uidx] = usage; } else { usage = 0; } @@ -1620,7 +1639,6 @@ static void ioc_timer_fn(struct timer_list *timer) /* throw away surplus vtime */ atomic64_add(delta, &iocg->vtime); atomic64_add(delta, &iocg->done_vtime); - iocg->last_vtime += delta; /* if usage is sufficiently low, maybe it can donate */ if (surplus_adjusted_hweight_inuse(usage, hw_inuse)) { iocg->has_surplus = true; diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h index c2f580fd371b..a905ecc0342f 100644 --- a/include/trace/events/iocost.h +++ b/include/trace/events/iocost.h @@ -26,7 +26,6 @@ TRACE_EVENT(iocost_iocg_activate, __field(u64, vrate) __field(u64, last_period) __field(u64, cur_period) - __field(u64, last_vtime) __field(u64, vtime) __field(u32, weight) __field(u32, inuse) @@ -42,7 +41,6 @@ TRACE_EVENT(iocost_iocg_activate, __entry->vrate = now->vrate; __entry->last_period = last_period; __entry->cur_period = cur_period; - __entry->last_vtime = iocg->last_vtime; __entry->vtime = vtime; __entry->weight = iocg->weight; __entry->inuse = iocg->inuse; @@ -51,13 +49,12 @@ TRACE_EVENT(iocost_iocg_activate, ), TP_printk("[%s:%s] now=%llu:%llu vrate=%llu " - "period=%llu->%llu vtime=%llu->%llu " + "period=%llu->%llu vtime=%llu " "weight=%u/%u hweight=%llu/%llu", __get_str(devname), __get_str(cgroup), __entry->now, __entry->vnow, __entry->vrate, __entry->last_period, __entry->cur_period, - __entry->last_vtime, __entry->vtime, - __entry->inuse, __entry->weight, + __entry->vtime, __entry->inuse, __entry->weight, __entry->hweight_inuse, __entry->hweight_active ) ); -- cgit v1.2.3 From 065655c862fedf4b04e1b28b83ca6f338d81cf0b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 1 Sep 2020 14:52:46 -0400 Subject: blk-iocost: decouple vrate adjustment from surplus transfers Budget donations are inaccurate and could take multiple periods to converge. To prevent triggering vrate adjustments while surplus transfers were catching up, vrate adjustment was suppressed if donations were increasing, which was indicated by non-zero nr_surpluses. This entangling won't be necessary with the scheduled rewrite of donation mechanism which will make it precise and immediate. Let's decouple the two in preparation. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-iocost.c | 19 +++++++------------ include/trace/events/iocost.h | 13 ++++--------- 2 files changed, 11 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/block/blk-iocost.c b/block/blk-iocost.c index c1cd66cfa2a8..a3889a8b0a33 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1508,7 +1508,7 @@ static void ioc_timer_fn(struct timer_list *timer) struct ioc_gq *iocg, *tiocg; struct ioc_now now; LIST_HEAD(surpluses); - int nr_surpluses = 0, nr_shortages = 0, nr_lagging = 0; + int nr_shortages = 0, nr_lagging = 0; u32 ppm_rthr = MILLION - ioc->params.qos[QOS_RPPM]; u32 ppm_wthr = MILLION - ioc->params.qos[QOS_WPPM]; u32 missed_ppm[2], rq_wait_pct; @@ -1640,10 +1640,8 @@ static void ioc_timer_fn(struct timer_list *timer) atomic64_add(delta, &iocg->vtime); atomic64_add(delta, &iocg->done_vtime); /* if usage is sufficiently low, maybe it can donate */ - if (surplus_adjusted_hweight_inuse(usage, hw_inuse)) { + if (surplus_adjusted_hweight_inuse(usage, hw_inuse)) list_add(&iocg->surplus_list, &surpluses); - nr_surpluses++; - } } else if (hw_inuse < hw_active) { u32 new_hwi, new_inuse; @@ -1673,7 +1671,7 @@ static void ioc_timer_fn(struct timer_list *timer) } } - if (!nr_shortages || !nr_surpluses) + if (!nr_shortages || list_empty(&surpluses)) goto skip_surplus_transfers; /* there are both shortages and surpluses, transfer surpluses */ @@ -1738,11 +1736,9 @@ skip_surplus_transfers: /* * If there are IOs spanning multiple periods, wait - * them out before pushing the device harder. If - * there are surpluses, let redistribution work it - * out first. + * them out before pushing the device harder. */ - if (!nr_lagging && !nr_surpluses) + if (!nr_lagging) ioc->busy_level--; } else { /* @@ -1796,15 +1792,14 @@ skip_surplus_transfers: } trace_iocost_ioc_vrate_adj(ioc, vrate, missed_ppm, rq_wait_pct, - nr_lagging, nr_shortages, - nr_surpluses); + nr_lagging, nr_shortages); atomic64_set(&ioc->vtime_rate, vrate); ioc_refresh_margins(ioc); } else if (ioc->busy_level != prev_busy_level || nr_lagging) { trace_iocost_ioc_vrate_adj(ioc, atomic64_read(&ioc->vtime_rate), missed_ppm, rq_wait_pct, nr_lagging, - nr_shortages, nr_surpluses); + nr_shortages); } ioc_refresh_params(ioc, false); diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h index a905ecc0342f..ee024fe8fef6 100644 --- a/include/trace/events/iocost.h +++ b/include/trace/events/iocost.h @@ -128,11 +128,9 @@ DEFINE_EVENT(iocg_inuse_update, iocost_inuse_reset, TRACE_EVENT(iocost_ioc_vrate_adj, TP_PROTO(struct ioc *ioc, u64 new_vrate, u32 *missed_ppm, - u32 rq_wait_pct, int nr_lagging, int nr_shortages, - int nr_surpluses), + u32 rq_wait_pct, int nr_lagging, int nr_shortages), - TP_ARGS(ioc, new_vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages, - nr_surpluses), + TP_ARGS(ioc, new_vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages), TP_STRUCT__entry ( __string(devname, ioc_name(ioc)) @@ -144,7 +142,6 @@ TRACE_EVENT(iocost_ioc_vrate_adj, __field(u32, rq_wait_pct) __field(int, nr_lagging) __field(int, nr_shortages) - __field(int, nr_surpluses) ), TP_fast_assign( @@ -157,15 +154,13 @@ TRACE_EVENT(iocost_ioc_vrate_adj, __entry->rq_wait_pct = rq_wait_pct; __entry->nr_lagging = nr_lagging; __entry->nr_shortages = nr_shortages; - __entry->nr_surpluses = nr_surpluses; ), - TP_printk("[%s] vrate=%llu->%llu busy=%d missed_ppm=%u:%u rq_wait_pct=%u lagging=%d shortages=%d surpluses=%d", + TP_printk("[%s] vrate=%llu->%llu busy=%d missed_ppm=%u:%u rq_wait_pct=%u lagging=%d shortages=%d", __get_str(devname), __entry->old_vrate, __entry->new_vrate, __entry->busy_level, __entry->read_missed_ppm, __entry->write_missed_ppm, - __entry->rq_wait_pct, __entry->nr_lagging, __entry->nr_shortages, - __entry->nr_surpluses + __entry->rq_wait_pct, __entry->nr_lagging, __entry->nr_shortages ) ); -- cgit v1.2.3 From 046037551721e8831f6718ac2149887f6bb1f802 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 1 Sep 2020 14:52:55 -0400 Subject: blk-iocost: restore inuse update tracepoints Update and restore the inuse update tracepoints. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-iocost.c | 16 ++++++++++++++++ include/trace/events/iocost.h | 6 +++--- 2 files changed, 19 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 0270a504e6b5..9366527d8c12 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1919,6 +1919,12 @@ static void transfer_surpluses(struct list_head *surpluses, struct ioc_now *now) inuse = DIV64_U64_ROUND_UP( parent->child_adjusted_sum * iocg->hweight_after_donation, parent->hweight_inuse); + + TRACE_IOCG_PATH(inuse_transfer, iocg, now, + iocg->inuse, inuse, + iocg->hweight_inuse, + iocg->hweight_after_donation); + __propagate_weights(iocg, iocg->active, inuse, true, now); } @@ -2076,6 +2082,10 @@ static void ioc_timer_fn(struct timer_list *timer) iocg->hweight_after_donation = new_hwi; list_add(&iocg->surplus_list, &surpluses); } else { + TRACE_IOCG_PATH(inuse_shortage, iocg, &now, + iocg->inuse, iocg->active, + iocg->hweight_inuse, new_hwi); + __propagate_weights(iocg, iocg->active, iocg->active, true, &now); nr_shortages++; @@ -2248,11 +2258,13 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, struct ioc *ioc = iocg->ioc; struct ioc_margins *margins = &ioc->margins; u32 adj_step = DIV_ROUND_UP(iocg->active * INUSE_ADJ_STEP_PCT, 100); + u32 __maybe_unused old_inuse = iocg->inuse, __maybe_unused old_hwi; u32 hwi; s64 margin; u64 cost, new_inuse; current_hweight(iocg, NULL, &hwi); + old_hwi = hwi; cost = abs_cost_to_cost(abs_cost, hwi); margin = now->vnow - vtime - cost; @@ -2287,6 +2299,10 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, iocg->inuse != iocg->active); spin_unlock_irq(&ioc->lock); + + TRACE_IOCG_PATH(inuse_adjust, iocg, now, + old_inuse, iocg->inuse, old_hwi, hwi); + return cost; } diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h index ee024fe8fef6..b350860d2e71 100644 --- a/include/trace/events/iocost.h +++ b/include/trace/events/iocost.h @@ -95,7 +95,7 @@ DECLARE_EVENT_CLASS(iocg_inuse_update, ) ); -DEFINE_EVENT(iocg_inuse_update, iocost_inuse_takeback, +DEFINE_EVENT(iocg_inuse_update, iocost_inuse_shortage, TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now, u32 old_inuse, u32 new_inuse, @@ -105,7 +105,7 @@ DEFINE_EVENT(iocg_inuse_update, iocost_inuse_takeback, old_hw_inuse, new_hw_inuse) ); -DEFINE_EVENT(iocg_inuse_update, iocost_inuse_giveaway, +DEFINE_EVENT(iocg_inuse_update, iocost_inuse_transfer, TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now, u32 old_inuse, u32 new_inuse, @@ -115,7 +115,7 @@ DEFINE_EVENT(iocg_inuse_update, iocost_inuse_giveaway, old_hw_inuse, new_hw_inuse) ); -DEFINE_EVENT(iocg_inuse_update, iocost_inuse_reset, +DEFINE_EVENT(iocg_inuse_update, iocost_inuse_adjust, TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now, u32 old_inuse, u32 new_inuse, -- cgit v1.2.3 From 9d3a39a5f1e45827b008fff1ee9cf3cac3409665 Mon Sep 17 00:00:00 2001 From: Khazhismel Kumykov Date: Mon, 24 Aug 2020 15:10:34 -0700 Subject: block: grant IOPRIO_CLASS_RT to CAP_SYS_NICE CAP_SYS_ADMIN is too broad, and ionice fits into CAP_SYS_NICE's grouping. Retain CAP_SYS_ADMIN permission for backwards compatibility. Signed-off-by: Khazhismel Kumykov Reviewed-by: Bart Van Assche Acked-by: Serge Hallyn Signed-off-by: Jens Axboe --- block/ioprio.c | 2 +- include/uapi/linux/capability.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/block/ioprio.c b/block/ioprio.c index 04ebd37966f1..364d2294ba90 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -69,7 +69,7 @@ int ioprio_check_cap(int ioprio) switch (class) { case IOPRIO_CLASS_RT: - if (!capable(CAP_SYS_ADMIN)) + if (!capable(CAP_SYS_NICE) && !capable(CAP_SYS_ADMIN)) return -EPERM; fallthrough; /* rt has prio field too */ diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index 395dd0df8d08..c6ca33034147 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -288,6 +288,8 @@ struct vfs_ns_cap_data { processes and setting the scheduling algorithm used by another process. */ /* Allow setting cpu affinity on other processes */ +/* Allow setting realtime ioprio class */ +/* Allow setting ioprio class on other processes */ #define CAP_SYS_NICE 23 -- cgit v1.2.3 From f4ad06f2bb8476548b08f89919ee65abc4e40212 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Sep 2020 17:57:42 +0200 Subject: block: rename bd_invalidated Replace bd_invalidate with a new BDEV_NEED_PART_SCAN flag in a bd_flags variable to better describe the condition. Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- block/genhd.c | 2 +- drivers/block/nbd.c | 8 ++++---- fs/block_dev.c | 10 +++++----- include/linux/blk_types.h | 4 +++- 4 files changed, 13 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/block/genhd.c b/block/genhd.c index 5fc6d82e6c68..a36be970b767 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -732,7 +732,7 @@ static void register_disk(struct device *parent, struct gendisk *disk, if (!bdev) goto exit; - bdev->bd_invalidated = 1; + set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); err = blkdev_get(bdev, FMODE_READ, NULL); if (err < 0) goto exit; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index a54f2d155a31..15eed210feef 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -315,7 +315,7 @@ static void nbd_size_update(struct nbd_device *nbd) bd_set_nr_sectors(bdev, nr_sectors); set_blocksize(bdev, config->blksize); } else - bdev->bd_invalidated = 1; + set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); bdput(bdev); } kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE); @@ -1322,7 +1322,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b return ret; if (max_part) - bdev->bd_invalidated = 1; + set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); mutex_unlock(&nbd->config_lock); ret = wait_event_interruptible(config->recv_wq, atomic_read(&config->recv_threads) == 0); @@ -1500,9 +1500,9 @@ static int nbd_open(struct block_device *bdev, fmode_t mode) refcount_set(&nbd->config_refs, 1); refcount_inc(&nbd->refs); mutex_unlock(&nbd->config_lock); - bdev->bd_invalidated = 1; + set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); } else if (nbd_disconnected(nbd->config)) { - bdev->bd_invalidated = 1; + set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); } out: mutex_unlock(&nbd_index_mutex); diff --git a/fs/block_dev.c b/fs/block_dev.c index 7e32398608c6..1e6441dbe840 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -881,7 +881,7 @@ struct block_device *bdget(dev_t dev) bdev->bd_super = NULL; bdev->bd_inode = inode; bdev->bd_part_count = 0; - bdev->bd_invalidated = 0; + bdev->bd_flags = 0; inode->i_mode = S_IFBLK; inode->i_rdev = dev; inode->i_bdev = bdev; @@ -1365,7 +1365,7 @@ int check_disk_change(struct block_device *bdev) if (__invalidate_device(bdev, true)) pr_warn("VFS: busy inodes on changed media %s\n", disk->disk_name); - bdev->bd_invalidated = 1; + set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); if (bdops->revalidate_disk) bdops->revalidate_disk(bdev->bd_disk); return 1; @@ -1390,7 +1390,7 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate) lockdep_assert_held(&bdev->bd_mutex); - bdev->bd_invalidated = 0; + clear_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); rescan: ret = blk_drop_partitions(bdev); @@ -1514,7 +1514,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder, * The latter is necessary to prevent ghost * partitions on a removed medium. */ - if (bdev->bd_invalidated && + if (test_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags) && (!ret || ret == -ENOMEDIUM)) bdev_disk_changed(bdev, ret == -ENOMEDIUM); @@ -1544,7 +1544,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder, if (bdev->bd_disk->fops->open) ret = bdev->bd_disk->fops->open(bdev, mode); /* the same as first opener case, read comment there */ - if (bdev->bd_invalidated && + if (test_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags) && (!ret || ret == -ENOMEDIUM)) bdev_disk_changed(bdev, ret == -ENOMEDIUM); if (ret) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 59d9150165c4..6ffa783e1633 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -19,6 +19,8 @@ struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); struct bio_crypt_ctx; +#define BDEV_NEED_PART_SCAN 0 + struct block_device { dev_t bd_dev; int bd_openers; @@ -37,7 +39,7 @@ struct block_device { struct hd_struct * bd_part; /* number of times partitions within this device have been opened. */ unsigned bd_part_count; - int bd_invalidated; + unsigned long bd_flags; spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct gendisk * bd_disk; struct backing_dev_info *bd_bdi; -- cgit v1.2.3 From 659e56ba864d37b7ee0a49cd432205b2a5ca815e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Sep 2020 17:57:43 +0200 Subject: block: add a new revalidate_disk_size helper revalidate_disk is a relative awkward helper for driver use, as it first calls an optional driver method and then updates the block device size, while most callers either don't need the method call at all, or want to keep state between the caller and the called method. Add a revalidate_disk_size helper that just performs the update of the block device size from the gendisk one, and switch all drivers that do not implement ->revalidate_disk to use the new helper instead of revalidate_disk() Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Reviewed-by: Johannes Thumshirn Acked-by: Song Liu Signed-off-by: Jens Axboe --- drivers/block/rbd.c | 2 +- drivers/block/rnbd/rnbd-clt.c | 10 ++-------- drivers/block/virtio_blk.c | 2 +- drivers/block/zram/zram_drv.c | 4 ++-- drivers/md/dm-raid.c | 2 +- drivers/md/md-cluster.c | 6 +++--- drivers/md/md-linear.c | 2 +- drivers/md/md.c | 10 +++++----- fs/block_dev.c | 42 +++++++++++++++++++++++++++++------------- include/linux/genhd.h | 1 + 10 files changed, 46 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 011539039693..5d3923c0997c 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4921,7 +4921,7 @@ static void rbd_dev_update_size(struct rbd_device *rbd_dev) size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE; dout("setting size to %llu sectors", (unsigned long long)size); set_capacity(rbd_dev->disk, size); - revalidate_disk(rbd_dev->disk); + revalidate_disk_size(rbd_dev->disk, true); } } diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index cc6a4e2587ae..157538fc8be5 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -102,18 +102,12 @@ static int rnbd_clt_set_dev_attr(struct rnbd_clt_dev *dev, static int rnbd_clt_change_capacity(struct rnbd_clt_dev *dev, size_t new_nsectors) { - int err = 0; - rnbd_clt_info(dev, "Device size changed from %zu to %zu sectors\n", dev->nsectors, new_nsectors); dev->nsectors = new_nsectors; set_capacity(dev->gd, dev->nsectors); - err = revalidate_disk(dev->gd); - if (err) - rnbd_clt_err(dev, - "Failed to change device size from %zu to %zu, err: %d\n", - dev->nsectors, new_nsectors, err); - return err; + revalidate_disk_size(dev->gd, true); + return 0; } static int process_msg_open_rsp(struct rnbd_clt_dev *dev, diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index ca63a41059d6..a314b9382442 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -598,7 +598,7 @@ static void virtblk_update_cache_mode(struct virtio_device *vdev) struct virtio_blk *vblk = vdev->priv; blk_queue_write_cache(vblk->disk->queue, writeback, false); - revalidate_disk(vblk->disk); + revalidate_disk_size(vblk->disk, true); } static const char *const virtblk_cache_types[] = { diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 9100ac36670a..a356275605b1 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1739,7 +1739,7 @@ static ssize_t disksize_store(struct device *dev, zram->disksize = disksize; set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT); - revalidate_disk(zram->disk); + revalidate_disk_size(zram->disk, true); up_write(&zram->init_lock); return len; @@ -1786,7 +1786,7 @@ static ssize_t reset_store(struct device *dev, /* Make sure all the pending I/O are finished */ fsync_bdev(bdev); zram_reset_device(zram); - revalidate_disk(zram->disk); + revalidate_disk_size(zram->disk, true); bdput(bdev); mutex_lock(&bdev->bd_mutex); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 8d2b835d7a10..56b723d012ac 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -701,7 +701,7 @@ static void rs_set_capacity(struct raid_set *rs) struct gendisk *gendisk = dm_disk(dm_table_get_md(rs->ti->table)); set_capacity(gendisk, rs->md.array_sectors); - revalidate_disk(gendisk); + revalidate_disk_size(gendisk, true); } /* diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index d50737ec4039..0580b51a156a 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -582,7 +582,7 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg) break; case CHANGE_CAPACITY: set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk(mddev->gendisk); + revalidate_disk_size(mddev->gendisk, true); break; case RESYNCING: set_bit(MD_RESYNCING_REMOTE, &mddev->recovery); @@ -1296,12 +1296,12 @@ static void update_size(struct mddev *mddev, sector_t old_dev_sectors) pr_err("%s:%d: failed to send CHANGE_CAPACITY msg\n", __func__, __LINE__); set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk(mddev->gendisk); + revalidate_disk_size(mddev->gendisk, true); } else { /* revert to previous sectors */ ret = mddev->pers->resize(mddev, old_dev_sectors); if (!ret) - revalidate_disk(mddev->gendisk); + revalidate_disk_size(mddev->gendisk, true); ret = __sendmsg(cinfo, &cmsg); if (ret) pr_err("%s:%d: failed to send METADATA_UPDATED msg\n", diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index c2ae9125c4c3..5ab22069b5be 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -202,7 +202,7 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev) md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); set_capacity(mddev->gendisk, mddev->array_sectors); mddev_resume(mddev); - revalidate_disk(mddev->gendisk); + revalidate_disk_size(mddev->gendisk, true); kfree_rcu(oldconf, rcu); return 0; } diff --git a/drivers/md/md.c b/drivers/md/md.c index 607278207023..9562ef598ae1 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5358,7 +5358,7 @@ array_size_store(struct mddev *mddev, const char *buf, size_t len) mddev->array_sectors = sectors; if (mddev->pers) { set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk(mddev->gendisk); + revalidate_disk_size(mddev->gendisk, true); } } mddev_unlock(mddev); @@ -6109,7 +6109,7 @@ int do_md_run(struct mddev *mddev) md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */ set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk(mddev->gendisk); + revalidate_disk_size(mddev->gendisk, true); clear_bit(MD_NOT_READY, &mddev->flags); mddev->changed = 1; kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE); @@ -6427,7 +6427,7 @@ static int do_md_stop(struct mddev *mddev, int mode, set_capacity(disk, 0); mutex_unlock(&mddev->open_mutex); mddev->changed = 1; - revalidate_disk(disk); + revalidate_disk_size(disk, true); if (mddev->ro) mddev->ro = 0; @@ -7259,7 +7259,7 @@ static int update_size(struct mddev *mddev, sector_t num_sectors) md_cluster_ops->update_size(mddev, old_dev_sectors); else if (mddev->queue) { set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk(mddev->gendisk); + revalidate_disk_size(mddev->gendisk, true); } } return rv; @@ -9018,7 +9018,7 @@ void md_do_sync(struct md_thread *thread) mddev_unlock(mddev); if (!mddev_is_clustered(mddev)) { set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk(mddev->gendisk); + revalidate_disk_size(mddev->gendisk, true); } } diff --git a/fs/block_dev.c b/fs/block_dev.c index 1e6441dbe840..9bfe37f394bd 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1311,6 +1311,34 @@ static void check_disk_size_change(struct gendisk *disk, } } +/** + * revalidate_disk_size - checks for disk size change and adjusts bdev size. + * @disk: struct gendisk to check + * @verbose: if %true log a message about a size change if there is any + * + * This routine checks to see if the bdev size does not match the disk size + * and adjusts it if it differs. When shrinking the bdev size, its all caches + * are freed. + */ +void revalidate_disk_size(struct gendisk *disk, bool verbose) +{ + struct block_device *bdev; + + /* + * Hidden disks don't have associated bdev so there's no point in + * revalidating them. + */ + if (disk->flags & GENHD_FL_HIDDEN) + return; + + bdev = bdget_disk(disk, 0); + if (bdev) { + check_disk_size_change(disk, bdev, verbose); + bdput(bdev); + } +} +EXPORT_SYMBOL(revalidate_disk_size); + /** * revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back * @disk: struct gendisk to be revalidated @@ -1325,19 +1353,7 @@ int revalidate_disk(struct gendisk *disk) if (disk->fops->revalidate_disk) ret = disk->fops->revalidate_disk(disk); - - /* - * Hidden disks don't have associated bdev so there's no point in - * revalidating it. - */ - if (!(disk->flags & GENHD_FL_HIDDEN)) { - struct block_device *bdev = bdget_disk(disk, 0); - - if (bdev) { - check_disk_size_change(disk, bdev, ret == 0); - bdput(bdev); - } - } + revalidate_disk_size(disk, ret == 0); return ret; } EXPORT_SYMBOL(revalidate_disk); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 9ea2ca31c278..f76c8baf6b7d 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -371,6 +371,7 @@ int register_blkdev(unsigned int major, const char *name); void unregister_blkdev(unsigned int major, const char *name); int revalidate_disk(struct gendisk *disk); +void revalidate_disk_size(struct gendisk *disk, bool verbose); int check_disk_change(struct block_device *bdev); int __invalidate_device(struct block_device *bdev, bool kill_dirty); void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors); -- cgit v1.2.3 From b8086d3f5a0e88b1912d55a158b8a6a43ad6604b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Sep 2020 17:57:44 +0200 Subject: block: use revalidate_disk_size in set_capacity_revalidate_and_notify Only virtio_blk and xen-blkfront set the revalidate argument to true, and both do not implement the ->revalidate_disk method. So switch to the helper that just updates the size instead. Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- block/genhd.c | 7 +++---- include/linux/genhd.h | 4 ++-- 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/block/genhd.c b/block/genhd.c index a36be970b767..081f1039d936 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -50,14 +50,13 @@ static void disk_release_events(struct gendisk *disk); * zero and will not be set to zero */ void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, - bool revalidate) + bool update_bdev) { sector_t capacity = get_capacity(disk); set_capacity(disk, size); - - if (revalidate) - revalidate_disk(disk); + if (update_bdev) + revalidate_disk_size(disk, true); if (capacity != size && capacity != 0 && size != 0) { char *envp[] = { "RESIZE=1", NULL }; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index f76c8baf6b7d..02a73198b289 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -313,8 +313,8 @@ 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); -extern void set_capacity_revalidate_and_notify(struct gendisk *disk, - sector_t size, bool revalidate); +void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, + bool update_bdev); extern unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask); /* drivers/char/random.c */ -- cgit v1.2.3 From de09077c89183cbc627d9393706343662da7f5a3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Sep 2020 17:57:48 +0200 Subject: block: remove revalidate_disk() Remove the now unused helper. Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Reviewed-by: Johannes Thumshirn Acked-by: Song Liu Signed-off-by: Jens Axboe --- drivers/md/md.h | 2 +- fs/block_dev.c | 19 ------------------- include/linux/genhd.h | 1 - 3 files changed, 1 insertion(+), 21 deletions(-) (limited to 'include') diff --git a/drivers/md/md.h b/drivers/md/md.h index d9c4e6b7e939..f9e2ccdd22c4 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -397,7 +397,7 @@ struct mddev { * These locks are separate due to conflicting interactions * with bdev->bd_mutex. * Lock ordering is: - * reconfig_mutex -> bd_mutex : e.g. do_md_run -> revalidate_disk + * reconfig_mutex -> bd_mutex * bd_mutex -> open_mutex: e.g. __blkdev_get -> md_open */ struct mutex open_mutex; diff --git a/fs/block_dev.c b/fs/block_dev.c index 9bfe37f394bd..9cb205405f9d 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1339,25 +1339,6 @@ void revalidate_disk_size(struct gendisk *disk, bool verbose) } EXPORT_SYMBOL(revalidate_disk_size); -/** - * revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back - * @disk: struct gendisk to be revalidated - * - * This routine is a wrapper for lower-level driver's revalidate_disk - * call-backs. It is used to do common pre and post operations needed - * for all revalidate_disk operations. - */ -int revalidate_disk(struct gendisk *disk) -{ - int ret = 0; - - if (disk->fops->revalidate_disk) - ret = disk->fops->revalidate_disk(disk); - revalidate_disk_size(disk, ret == 0); - return ret; -} -EXPORT_SYMBOL(revalidate_disk); - /* * This routine checks whether a removable media has been changed, * and invalidates all buffer-cache-entries in that case. This diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 02a73198b289..c618b27292fc 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -370,7 +370,6 @@ extern void blk_unregister_region(dev_t devt, unsigned long range); int register_blkdev(unsigned int major, const char *name); void unregister_blkdev(unsigned int major, const char *name); -int revalidate_disk(struct gendisk *disk); void revalidate_disk_size(struct gendisk *disk, bool verbose); int check_disk_change(struct block_device *bdev); int __invalidate_device(struct block_device *bdev, bool kill_dirty); -- cgit v1.2.3 From 51db1c37ee166159c5753ce8d64d6bacf113e0f0 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 19 Aug 2020 23:20:19 +0800 Subject: blk-mq: Rename BLK_MQ_F_TAG_SHARED as BLK_MQ_F_TAG_QUEUE_SHARED BLK_MQ_F_TAG_SHARED actually means that tags is shared among request queues, all of which should belong to LUNs attached to same HBA. So rename it to make the point explicitly. [jpg: rebase a few times, add rnbd-clt.c change] Suggested-by: Bart Van Assche Signed-off-by: Ming Lei Signed-off-by: John Garry Tested-by: Douglas Gilbert Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 2 +- block/blk-mq-tag.h | 6 +++--- block/blk-mq.c | 20 ++++++++++---------- drivers/block/rnbd/rnbd-clt.c | 2 +- include/linux/blk-mq.h | 2 +- 5 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 3f09bcb8a6fd..a4597febff69 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -240,7 +240,7 @@ static const char *const alloc_policy_name[] = { #define HCTX_FLAG_NAME(name) [ilog2(BLK_MQ_F_##name)] = #name static const char *const hctx_flag_name[] = { HCTX_FLAG_NAME(SHOULD_MERGE), - HCTX_FLAG_NAME(TAG_SHARED), + HCTX_FLAG_NAME(TAG_QUEUE_SHARED), HCTX_FLAG_NAME(BLOCKING), HCTX_FLAG_NAME(NO_SCHED), HCTX_FLAG_NAME(STACKING), diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index b1acac518c4e..918e2cee4f43 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -56,7 +56,7 @@ extern void __blk_mq_tag_idle(struct blk_mq_hw_ctx *); static inline bool blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { - if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) + if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) return false; return __blk_mq_tag_busy(hctx); @@ -64,7 +64,7 @@ static inline bool blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) { - if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) + if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) return; __blk_mq_tag_idle(hctx); @@ -79,7 +79,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, { unsigned int depth, users; - if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_SHARED)) + if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) return true; if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return true; diff --git a/block/blk-mq.c b/block/blk-mq.c index b3d2785eefe9..75031fa1709c 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1124,7 +1124,7 @@ static bool blk_mq_get_driver_tag(struct request *rq) if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_get_driver_tag(rq)) return false; - if ((hctx->flags & BLK_MQ_F_TAG_SHARED) && + if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) && !(rq->rq_flags & RQF_MQ_INFLIGHT)) { rq->rq_flags |= RQF_MQ_INFLIGHT; atomic_inc(&hctx->nr_active); @@ -1168,7 +1168,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, wait_queue_entry_t *wait; bool ret; - if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) { + if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) { blk_mq_sched_mark_restart_hctx(hctx); /* @@ -1420,7 +1420,7 @@ out: bool needs_restart; /* For non-shared tags, the RESTART check will suffice */ bool no_tag = prep == PREP_DISPATCH_NO_TAG && - (hctx->flags & BLK_MQ_F_TAG_SHARED); + (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED); bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET; blk_mq_release_budgets(q, nr_budgets); @@ -2668,7 +2668,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, spin_lock_init(&hctx->lock); INIT_LIST_HEAD(&hctx->dispatch); hctx->queue = q; - hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED; + hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED; INIT_LIST_HEAD(&hctx->hctx_list); @@ -2885,9 +2885,9 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared) queue_for_each_hw_ctx(q, hctx, i) { if (shared) - hctx->flags |= BLK_MQ_F_TAG_SHARED; + hctx->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; else - hctx->flags &= ~BLK_MQ_F_TAG_SHARED; + hctx->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; } } @@ -2913,7 +2913,7 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q) list_del(&q->tag_set_list); if (list_is_singular(&set->tag_list)) { /* just transitioned to unshared */ - set->flags &= ~BLK_MQ_F_TAG_SHARED; + set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; /* update existing queue */ blk_mq_update_tag_set_depth(set, false); } @@ -2930,12 +2930,12 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, * Check to see if we're transitioning to shared (from 1 to 2 queues). */ if (!list_empty(&set->tag_list) && - !(set->flags & BLK_MQ_F_TAG_SHARED)) { - set->flags |= BLK_MQ_F_TAG_SHARED; + !(set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) { + set->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; /* update existing queue */ blk_mq_update_tag_set_depth(set, true); } - if (set->flags & BLK_MQ_F_TAG_SHARED) + if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED) queue_set_hctx_shared(q, true); list_add_tail(&q->tag_set_list, &set->tag_list); diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index 157538fc8be5..d7a69741c0f6 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1174,7 +1174,7 @@ static int setup_mq_tags(struct rnbd_clt_session *sess) tag_set->queue_depth = sess->queue_depth; tag_set->numa_node = NUMA_NO_NODE; tag_set->flags = BLK_MQ_F_SHOULD_MERGE | - BLK_MQ_F_TAG_SHARED; + BLK_MQ_F_TAG_QUEUE_SHARED; tag_set->cmd_size = sizeof(struct rnbd_iu); tag_set->nr_hw_queues = num_online_cpus(); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 21a02e0577dd..982c4f92b63c 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -378,7 +378,7 @@ struct blk_mq_ops { enum { BLK_MQ_F_SHOULD_MERGE = 1 << 0, - BLK_MQ_F_TAG_SHARED = 1 << 1, + BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1, /* * Set when this device requires underlying blk-mq device for * completing IO: -- cgit v1.2.3 From 32bc15afed04bd73e29d713d8db47818d6aa89af Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 19 Aug 2020 23:20:24 +0800 Subject: blk-mq: Facilitate a shared sbitmap per tagset Some SCSI HBAs (such as HPSA, megaraid, mpt3sas, hisi_sas_v3 ..) support multiple reply queues with single hostwide tags. In addition, these drivers want to use interrupt assignment in pci_alloc_irq_vectors(PCI_IRQ_AFFINITY). However, as discussed in [0], CPU hotplug may cause in-flight IO completion to not be serviced when an interrupt is shutdown. That problem is solved in commit bf0beec0607d ("blk-mq: drain I/O when all CPUs in a hctx are offline"). However, to take advantage of that blk-mq feature, the HBA HW queuess are required to be mapped to that of the blk-mq hctx's; to do that, the HBA HW queues need to be exposed to the upper layer. In making that transition, the per-SCSI command request tags are no longer unique per Scsi host - they are just unique per hctx. As such, the HBA LLDD would have to generate this tag internally, which has a certain performance overhead. However another problem is that blk-mq assumes the host may accept (Scsi_host.can_queue * #hw queue) commands. In commit 6eb045e092ef ("scsi: core: avoid host-wide host_busy counter for scsi_mq"), the Scsi host busy counter was removed, which would stop the LLDD being sent more than .can_queue commands; however, it should still be ensured that the block layer does not issue more than .can_queue commands to the Scsi host. To solve this problem, introduce a shared sbitmap per blk_mq_tag_set, which may be requested at init time. New flag BLK_MQ_F_TAG_HCTX_SHARED should be set when requesting the tagset to indicate whether the shared sbitmap should be used. Even when BLK_MQ_F_TAG_HCTX_SHARED is set, a full set of tags and requests are still allocated per hctx; the reason for this is that if tags and requests were only allocated for a single hctx - like hctx0 - it may break block drivers which expect a request be associated with a specific hctx, i.e. not always hctx0. This will introduce extra memory usage. This change is based on work originally from Ming Lei in [1] and from Bart's suggestion in [2]. [0] https://lore.kernel.org/linux-block/alpine.DEB.2.21.1904051331270.1802@nanos.tec.linutronix.de/ [1] https://lore.kernel.org/linux-block/20190531022801.10003-1-ming.lei@redhat.com/ [2] https://lore.kernel.org/linux-block/ff77beff-5fd9-9f05-12b6-826922bace1f@huawei.com/T/#m3db0a602f095cbcbff27e9c884d6b4ae826144be Signed-off-by: John Garry Tested-by: Don Brace #SCSI resv cmds patches used Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- block/blk-mq-sched.c | 8 +++++--- block/blk-mq-tag.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++---- block/blk-mq-tag.h | 7 +++++++ block/blk-mq.c | 15 +++++++++++++++ block/blk-mq.h | 5 +++++ include/linux/blk-mq.h | 6 ++++++ 6 files changed, 85 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index edfc8ea805bc..86d5545342ff 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -560,7 +560,7 @@ static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { - unsigned int flags = set->flags; + unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; if (hctx->sched_tags) { blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx); @@ -574,7 +574,8 @@ static int blk_mq_sched_alloc_tags(struct request_queue *q, unsigned int hctx_idx) { struct blk_mq_tag_set *set = q->tag_set; - unsigned int flags = set->flags; + /* Clear HCTX_SHARED so tags are init'ed */ + unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; int ret; hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests, @@ -596,7 +597,8 @@ static void blk_mq_sched_tags_teardown(struct request_queue *q) int i; queue_for_each_hw_ctx(q, hctx, i) { - unsigned int flags = hctx->flags; + /* Clear HCTX_SHARED so tags are freed */ + unsigned int flags = hctx->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; if (hctx->sched_tags) { blk_mq_free_rq_map(hctx->sched_tags, flags); diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 77fbeae05745..c6d7ebc62bdb 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -197,7 +197,7 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ - if (rq && rq->q == hctx->queue) + if (rq && rq->q == hctx->queue && rq->mq_hctx == hctx) return iter_data->fn(hctx, rq, iter_data->data, reserved); return true; } @@ -450,6 +450,38 @@ free_bitmap_tags: return -ENOMEM; } +int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int flags) +{ + unsigned int depth = set->queue_depth - set->reserved_tags; + int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags); + bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR; + int i, node = set->numa_node; + + if (bt_alloc(&set->__bitmap_tags, depth, round_robin, node)) + return -ENOMEM; + if (bt_alloc(&set->__breserved_tags, set->reserved_tags, + round_robin, node)) + goto free_bitmap_tags; + + for (i = 0; i < set->nr_hw_queues; i++) { + struct blk_mq_tags *tags = set->tags[i]; + + tags->bitmap_tags = &set->__bitmap_tags; + tags->breserved_tags = &set->__breserved_tags; + } + + return 0; +free_bitmap_tags: + sbitmap_queue_free(&set->__bitmap_tags); + return -ENOMEM; +} + +void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set) +{ + sbitmap_queue_free(&set->__bitmap_tags); + sbitmap_queue_free(&set->__breserved_tags); +} + struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, unsigned int reserved_tags, int node, unsigned int flags) @@ -469,6 +501,9 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, tags->nr_tags = total_tags; tags->nr_reserved_tags = reserved_tags; + if (flags & BLK_MQ_F_TAG_HCTX_SHARED) + return tags; + if (blk_mq_init_bitmap_tags(tags, node, alloc_policy) < 0) { kfree(tags); return NULL; @@ -478,8 +513,10 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags) { - sbitmap_queue_free(&tags->__bitmap_tags); - sbitmap_queue_free(&tags->__breserved_tags); + if (!(flags & BLK_MQ_F_TAG_HCTX_SHARED)) { + sbitmap_queue_free(tags->bitmap_tags); + sbitmap_queue_free(tags->breserved_tags); + } kfree(tags); } @@ -498,7 +535,8 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, */ if (tdepth > tags->nr_tags) { struct blk_mq_tag_set *set = hctx->queue->tag_set; - unsigned int flags = set->flags; + /* Only sched tags can grow, so clear HCTX_SHARED flag */ + unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; struct blk_mq_tags *new; bool ret; @@ -537,6 +575,11 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, return 0; } +void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int size) +{ + sbitmap_queue_resize(&set->__bitmap_tags, size - set->reserved_tags); +} + /** * blk_mq_unique_tag() - return a tag that is unique queue-wide * @rq: request for which to compute a unique tag diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 5b6f25bd1966..8f4cce52ba2d 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -29,12 +29,19 @@ extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, int node, unsigned int flags); extern void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags); +extern int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, + unsigned int flags); +extern void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set); + extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag); extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tags, unsigned int depth, bool can_grow); +extern void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, + unsigned int size); + extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool); void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, void *priv); diff --git a/block/blk-mq.c b/block/blk-mq.c index 4982bb1d75db..5e8fe795edf1 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3441,11 +3441,21 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) if (ret) goto out_free_mq_map; + if (blk_mq_is_sbitmap_shared(set->flags)) { + if (blk_mq_init_shared_sbitmap(set, set->flags)) { + ret = -ENOMEM; + goto out_free_mq_rq_maps; + } + } + mutex_init(&set->tag_list_lock); INIT_LIST_HEAD(&set->tag_list); return 0; +out_free_mq_rq_maps: + for (i = 0; i < set->nr_hw_queues; i++) + blk_mq_free_map_and_requests(set, i); out_free_mq_map: for (i = 0; i < set->nr_maps; i++) { kfree(set->map[i].mq_map); @@ -3464,6 +3474,9 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set) for (i = 0; i < set->nr_hw_queues; i++) blk_mq_free_map_and_requests(set, i); + if (blk_mq_is_sbitmap_shared(set->flags)) + blk_mq_exit_shared_sbitmap(set); + for (j = 0; j < set->nr_maps; j++) { kfree(set->map[j].mq_map); set->map[j].mq_map = NULL; @@ -3500,6 +3513,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) if (!hctx->sched_tags) { ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr, false); + if (!ret && blk_mq_is_sbitmap_shared(set->flags)) + blk_mq_tag_resize_shared_sbitmap(set, nr); } else { ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags, nr, true); diff --git a/block/blk-mq.h b/block/blk-mq.h index b86e7fe47789..3acdb56065e1 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -159,6 +159,11 @@ struct blk_mq_alloc_data { struct blk_mq_hw_ctx *hctx; }; +static inline bool blk_mq_is_sbitmap_shared(unsigned int flags) +{ + return flags & BLK_MQ_F_TAG_HCTX_SHARED; +} + static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data) { if (data->q->elevator) diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 982c4f92b63c..df7b903ce7ae 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -231,6 +231,9 @@ enum hctx_type { * @flags: Zero or more BLK_MQ_F_* flags. * @driver_data: Pointer to data owned by the block driver that created this * tag set. + * @__bitmap_tags: A shared tags sbitmap, used over all hctx's + * @__breserved_tags: + * A shared reserved tags sbitmap, used over all hctx's * @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues * elements. * @tag_list_lock: Serializes tag_list accesses. @@ -250,6 +253,8 @@ struct blk_mq_tag_set { unsigned int flags; void *driver_data; + struct sbitmap_queue __bitmap_tags; + struct sbitmap_queue __breserved_tags; struct blk_mq_tags **tags; struct mutex tag_list_lock; @@ -384,6 +389,7 @@ enum { * completing IO: */ BLK_MQ_F_STACKING = 1 << 2, + BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3, BLK_MQ_F_BLOCKING = 1 << 5, BLK_MQ_F_NO_SCHED = 1 << 6, BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, -- cgit v1.2.3 From bccf5e26d99c28980bd6ced474422a1b18402263 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 19 Aug 2020 23:20:26 +0800 Subject: blk-mq: Record nr_active_requests per queue for when using shared sbitmap The per-hctx nr_active value can no longer be used to fairly assign a share of tag depth per request queue for when using a shared sbitmap, as it does not consider that the tags are shared tags over all hctx's. For this case, record the nr_active_requests per request_queue, and make the judgement based on that value. Co-developed-with: Kashyap Desai Signed-off-by: John Garry Tested-by: Don Brace #SCSI resv cmds patches used Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- block/blk-core.c | 2 ++ block/blk-mq.c | 4 ++-- block/blk-mq.h | 26 ++++++++++++++++++++++++-- include/linux/blkdev.h | 2 ++ 4 files changed, 30 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/block/blk-core.c b/block/blk-core.c index 9f2a99abeeb9..093649bd252e 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -543,6 +543,8 @@ struct request_queue *blk_alloc_queue(int node_id) q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK; q->node = node_id; + atomic_set(&q->nr_active_requests_shared_sbitmap, 0); + timer_setup(&q->backing_dev_info->laptop_mode_wb_timer, laptop_mode_timer_fn, 0); timer_setup(&q->timeout, blk_rq_timed_out_timer, 0); diff --git a/block/blk-mq.c b/block/blk-mq.c index 5e8fe795edf1..ffc5ad0c91b7 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -519,7 +519,7 @@ void blk_mq_free_request(struct request *rq) ctx->rq_completed[rq_is_sync(rq)]++; if (rq->rq_flags & RQF_MQ_INFLIGHT) - atomic_dec(&hctx->nr_active); + __blk_mq_dec_active_requests(hctx); if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq))) laptop_io_completion(q->backing_dev_info); @@ -1127,7 +1127,7 @@ static bool blk_mq_get_driver_tag(struct request *rq) if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) && !(rq->rq_flags & RQF_MQ_INFLIGHT)) { rq->rq_flags |= RQF_MQ_INFLIGHT; - atomic_inc(&hctx->nr_active); + __blk_mq_inc_active_requests(hctx); } hctx->tags->rqs[rq->tag] = rq; return true; diff --git a/block/blk-mq.h b/block/blk-mq.h index 56dc37c21908..25ec73078e95 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -199,6 +199,28 @@ static inline bool blk_mq_get_dispatch_budget(struct request_queue *q) return true; } +static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx) +{ + if (blk_mq_is_sbitmap_shared(hctx->flags)) + atomic_inc(&hctx->queue->nr_active_requests_shared_sbitmap); + else + atomic_inc(&hctx->nr_active); +} + +static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx) +{ + if (blk_mq_is_sbitmap_shared(hctx->flags)) + atomic_dec(&hctx->queue->nr_active_requests_shared_sbitmap); + else + atomic_dec(&hctx->nr_active); +} + +static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx) +{ + if (blk_mq_is_sbitmap_shared(hctx->flags)) + return atomic_read(&hctx->queue->nr_active_requests_shared_sbitmap); + return atomic_read(&hctx->nr_active); +} static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq) { @@ -207,7 +229,7 @@ static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, if (rq->rq_flags & RQF_MQ_INFLIGHT) { rq->rq_flags &= ~RQF_MQ_INFLIGHT; - atomic_dec(&hctx->nr_active); + __blk_mq_dec_active_requests(hctx); } } @@ -287,7 +309,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, * Allow at least some tags */ depth = max((bt->sb.depth + users - 1) / users, 4U); - return atomic_read(&hctx->nr_active) < depth; + return __blk_mq_active_requests(hctx) < depth; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d0d61bc81615..6277aee2aeaa 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -485,6 +485,8 @@ struct request_queue { struct timer_list timeout; struct work_struct timeout_work; + atomic_t nr_active_requests_shared_sbitmap; + struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS); -- cgit v1.2.3 From f1b49fdc1c64db110aa1315831e5fe0f8599fa56 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 19 Aug 2020 23:20:27 +0800 Subject: blk-mq: Record active_queues_shared_sbitmap per tag_set for when using shared sbitmap For when using a shared sbitmap, no longer should the number of active request queues per hctx be relied on for when judging how to share the tag bitmap. Instead maintain the number of active request queues per tag_set, and make the judgement based on that. Originally-from: Kashyap Desai Signed-off-by: John Garry Tested-by: Don Brace #SCSI resv cmds patches used Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 33 +++++++++++++++++++++++++-------- block/blk-mq.c | 2 ++ block/blk-mq.h | 16 +++++++++++++--- include/linux/blk-mq.h | 1 + include/linux/blkdev.h | 1 + 5 files changed, 42 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index c6d7ebc62bdb..c31c4a0478a5 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -23,9 +23,18 @@ */ bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { - if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) && - !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) - atomic_inc(&hctx->tags->active_queues); + if (blk_mq_is_sbitmap_shared(hctx->flags)) { + struct request_queue *q = hctx->queue; + struct blk_mq_tag_set *set = q->tag_set; + + if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) && + !test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) + atomic_inc(&set->active_queues_shared_sbitmap); + } else { + if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) && + !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) + atomic_inc(&hctx->tags->active_queues); + } return true; } @@ -47,11 +56,19 @@ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve) void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) { struct blk_mq_tags *tags = hctx->tags; - - if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) - return; - - atomic_dec(&tags->active_queues); + struct request_queue *q = hctx->queue; + struct blk_mq_tag_set *set = q->tag_set; + + if (blk_mq_is_sbitmap_shared(hctx->flags)) { + if (!test_and_clear_bit(QUEUE_FLAG_HCTX_ACTIVE, + &q->queue_flags)) + return; + atomic_dec(&set->active_queues_shared_sbitmap); + } else { + if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) + return; + atomic_dec(&tags->active_queues); + } blk_mq_tag_wakeup_all(tags, false); } diff --git a/block/blk-mq.c b/block/blk-mq.c index ffc5ad0c91b7..eff9d987f85b 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3442,6 +3442,8 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) goto out_free_mq_map; if (blk_mq_is_sbitmap_shared(set->flags)) { + atomic_set(&set->active_queues_shared_sbitmap, 0); + if (blk_mq_init_shared_sbitmap(set, set->flags)) { ret = -ENOMEM; goto out_free_mq_rq_maps; diff --git a/block/blk-mq.h b/block/blk-mq.h index 25ec73078e95..a52703c98b77 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -292,8 +292,6 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) return true; - if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) - return true; /* * Don't try dividing an ant @@ -301,7 +299,19 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, if (bt->sb.depth == 1) return true; - users = atomic_read(&hctx->tags->active_queues); + if (blk_mq_is_sbitmap_shared(hctx->flags)) { + struct request_queue *q = hctx->queue; + struct blk_mq_tag_set *set = q->tag_set; + + if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &q->queue_flags)) + return true; + users = atomic_read(&set->active_queues_shared_sbitmap); + } else { + if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) + return true; + users = atomic_read(&hctx->tags->active_queues); + } + if (!users) return true; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index df7b903ce7ae..8279c807e1f3 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -252,6 +252,7 @@ struct blk_mq_tag_set { unsigned int timeout; unsigned int flags; void *driver_data; + atomic_t active_queues_shared_sbitmap; struct sbitmap_queue __bitmap_tags; struct sbitmap_queue __breserved_tags; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6277aee2aeaa..7d82959e7b86 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -618,6 +618,7 @@ struct request_queue { #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ #define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ #define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ +#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP)) -- cgit v1.2.3 From b445547ec1bbd3e7bf4b1c142550942f70527d95 Mon Sep 17 00:00:00 2001 From: Kashyap Desai Date: Wed, 19 Aug 2020 23:20:28 +0800 Subject: blk-mq, elevator: Count requests per hctx to improve performance High CPU utilization on "native_queued_spin_lock_slowpath" due to lock contention is possible for mq-deadline and bfq IO schedulers when nr_hw_queues is more than one. It is because kblockd work queue can submit IO from all online CPUs (through blk_mq_run_hw_queues()) even though only one hctx has pending commands. The elevator callback .has_work for mq-deadline and bfq scheduler considers pending work if there are any IOs on request queue but it does not account hctx context. Add a per-hctx 'elevator_queued' count to the hctx to avoid triggering the elevator even though there are no requests queued. [jpg: Relocated atomic_dec() in dd_dispatch_request(), update commit message per Kashyap] Signed-off-by: Kashyap Desai Signed-off-by: Hannes Reinecke Signed-off-by: John Garry Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- block/bfq-iosched.c | 5 +++++ block/blk-mq.c | 1 + block/mq-deadline.c | 6 ++++++ include/linux/blk-mq.h | 4 ++++ 4 files changed, 16 insertions(+) (limited to 'include') diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 418ffd4b5552..a251b80d8ee5 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -4640,6 +4640,9 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx) { struct bfq_data *bfqd = hctx->queue->elevator->elevator_data; + if (!atomic_read(&hctx->elevator_queued)) + return false; + /* * Avoiding lock: a race on bfqd->busy_queues should cause at * most a call to dispatch for nothing @@ -5554,6 +5557,7 @@ static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx, rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); bfq_insert_request(hctx, rq, at_head); + atomic_inc(&hctx->elevator_queued); } } @@ -5933,6 +5937,7 @@ static void bfq_finish_requeue_request(struct request *rq) bfq_completed_request(bfqq, bfqd); bfq_finish_requeue_request_body(bfqq); + atomic_dec(&rq->mq_hctx->elevator_queued); spin_unlock_irqrestore(&bfqd->lock, flags); } else { diff --git a/block/blk-mq.c b/block/blk-mq.c index eff9d987f85b..4abb71459f94 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2660,6 +2660,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, goto free_hctx; atomic_set(&hctx->nr_active, 0); + atomic_set(&hctx->elevator_queued, 0); if (node == NUMA_NO_NODE) node = set->numa_node; hctx->numa_node = node; diff --git a/block/mq-deadline.c b/block/mq-deadline.c index b57470e154c8..800ac902809b 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -386,6 +386,8 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx) spin_lock(&dd->lock); rq = __dd_dispatch_request(dd); spin_unlock(&dd->lock); + if (rq) + atomic_dec(&rq->mq_hctx->elevator_queued); return rq; } @@ -533,6 +535,7 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); dd_insert_request(hctx, rq, at_head); + atomic_inc(&hctx->elevator_queued); } spin_unlock(&dd->lock); } @@ -579,6 +582,9 @@ static bool dd_has_work(struct blk_mq_hw_ctx *hctx) { struct deadline_data *dd = hctx->queue->elevator->elevator_data; + if (!atomic_read(&hctx->elevator_queued)) + return false; + return !list_empty_careful(&dd->dispatch) || !list_empty_careful(&dd->fifo_list[0]) || !list_empty_careful(&dd->fifo_list[1]); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 8279c807e1f3..b23eeca4d677 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -139,6 +139,10 @@ struct blk_mq_hw_ctx { * shared across request queues. */ atomic_t nr_active; + /** + * @elevator_queued: Number of queued requests on hctx. + */ + atomic_t elevator_queued; /** @cpuhp_online: List to store request if CPU is going to die */ struct hlist_node cpuhp_online; -- cgit v1.2.3 From 384d87ef2c954fc58e6c5fd8253e4a1984f5fe02 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 4 Sep 2020 10:58:52 +0200 Subject: block: Do not discard buffers under a mounted filesystem Discarding blocks and buffers under a mounted filesystem is hardly anything admin wants to do. Usually it will confuse the filesystem and sometimes the loss of buffer_head state (including b_private field) can even cause crashes like: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 PGD 0 P4D 0 Oops: 0002 [#1] SMP PTI CPU: 4 PID: 203778 Comm: jbd2/dm-3-8 Kdump: loaded Tainted: G O --------- - - 4.18.0-147.5.0.5.h126.eulerosv2r9.x86_64 #1 Hardware name: Huawei RH2288H V3/BC11HGSA0, BIOS 1.57 08/11/2015 RIP: 0010:jbd2_journal_grab_journal_head+0x1b/0x40 [jbd2] ... Call Trace: __jbd2_journal_insert_checkpoint+0x23/0x70 [jbd2] jbd2_journal_commit_transaction+0x155f/0x1b60 [jbd2] kjournald2+0xbd/0x270 [jbd2] So if we don't have block device open with O_EXCL already, claim the block device while we truncate buffer cache. This makes sure any exclusive block device user (such as filesystem) cannot operate on the device while we are discarding buffer cache. Reported-by: Ye Bin Signed-off-by: Jan Kara Reviewed-by: Christoph Hellwig [axboe: fix !CONFIG_BLOCK error in truncate_bdev_range()] Signed-off-by: Jens Axboe --- block/ioctl.c | 16 ++++++++++------ fs/block_dev.c | 37 +++++++++++++++++++++++++++++++++---- include/linux/blkdev.h | 7 +++++++ 3 files changed, 50 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/block/ioctl.c b/block/ioctl.c index bdb3bbb253d9..ae74d0409afa 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -112,8 +112,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, uint64_t range[2]; uint64_t start, len; struct request_queue *q = bdev_get_queue(bdev); - struct address_space *mapping = bdev->bd_inode->i_mapping; - + int err; if (!(mode & FMODE_WRITE)) return -EBADF; @@ -134,7 +133,11 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, if (start + len > i_size_read(bdev->bd_inode)) return -EINVAL; - truncate_inode_pages_range(mapping, start, start + len - 1); + + err = truncate_bdev_range(bdev, mode, start, start + len - 1); + if (err) + return err; + return blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, flags); } @@ -143,8 +146,8 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, unsigned long arg) { uint64_t range[2]; - struct address_space *mapping; uint64_t start, end, len; + int err; if (!(mode & FMODE_WRITE)) return -EBADF; @@ -166,8 +169,9 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, return -EINVAL; /* Invalidate the page cache, including dirty pages */ - mapping = bdev->bd_inode->i_mapping; - truncate_inode_pages_range(mapping, start, end); + err = truncate_bdev_range(bdev, mode, start, end); + if (err) + return err; return blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL, BLKDEV_ZERO_NOUNMAP); diff --git a/fs/block_dev.c b/fs/block_dev.c index 9cb205405f9d..c70c41ecba48 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -103,6 +103,35 @@ void invalidate_bdev(struct block_device *bdev) } EXPORT_SYMBOL(invalidate_bdev); +/* + * Drop all buffers & page cache for given bdev range. This function bails + * with error if bdev has other exclusive owner (such as filesystem). + */ +int truncate_bdev_range(struct block_device *bdev, fmode_t mode, + loff_t lstart, loff_t lend) +{ + struct block_device *claimed_bdev = NULL; + int err; + + /* + * If we don't hold exclusive handle for the device, upgrade to it + * while we discard the buffer cache to avoid discarding buffers + * under live filesystem. + */ + if (!(mode & FMODE_EXCL)) { + claimed_bdev = bdev->bd_contains; + err = bd_prepare_to_claim(bdev, claimed_bdev, + truncate_bdev_range); + if (err) + return err; + } + truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend); + if (claimed_bdev) + bd_abort_claiming(bdev, claimed_bdev, truncate_bdev_range); + return 0; +} +EXPORT_SYMBOL(truncate_bdev_range); + static void set_init_blocksize(struct block_device *bdev) { bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev)); @@ -1968,7 +1997,6 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, loff_t len) { struct block_device *bdev = I_BDEV(bdev_file_inode(file)); - struct address_space *mapping; loff_t end = start + len - 1; loff_t isize; int error; @@ -1996,8 +2024,9 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, return -EINVAL; /* Invalidate the page cache, including dirty pages. */ - mapping = bdev->bd_inode->i_mapping; - truncate_inode_pages_range(mapping, start, end); + error = truncate_bdev_range(bdev, file->f_mode, start, end); + if (error) + return error; switch (mode) { case FALLOC_FL_ZERO_RANGE: @@ -2024,7 +2053,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, * the caller will be given -EBUSY. The third argument is * inclusive, so the rounding here is safe. */ - return invalidate_inode_pages2_range(mapping, + return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping, start >> PAGE_SHIFT, end >> PAGE_SHIFT); } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7d82959e7b86..37ec5a73d027 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1987,11 +1987,18 @@ void bdput(struct block_device *); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); +int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, + loff_t lend); int sync_blockdev(struct block_device *bdev); #else static inline void invalidate_bdev(struct block_device *bdev) { } +static inline int truncate_bdev_range(struct block_device *bdev, fmode_t mode, + loff_t lstart, loff_t lend) +{ + return 0; +} static inline int sync_blockdev(struct block_device *bdev) { return 0; -- cgit v1.2.3 From 95f6f3a46fc4ee1a2b216a6b46bdf2b450f1877f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Sep 2020 16:53:29 +0200 Subject: block: add a bdev_check_media_change helper Like check_disk_changed, except that it does not call ->revalidate_disk but leaves that to the caller. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/genhd.c | 29 ++++++++++++++++++++++++++++- fs/block_dev.c | 17 +++-------------- include/linux/genhd.h | 2 +- 3 files changed, 32 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/block/genhd.c b/block/genhd.c index 081f1039d936..9d060e79eb31 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -2052,7 +2052,7 @@ void disk_flush_events(struct gendisk *disk, unsigned int mask) * CONTEXT: * Might sleep. */ -unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) +static unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) { struct disk_events *ev = disk->ev; unsigned int pending; @@ -2090,6 +2090,33 @@ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) return pending; } +/** + * bdev_check_media_change - check if a removable media has been changed + * @bdev: block device to check + * + * Check whether a removable media has been changed, and attempt to free all + * dentries and inodes and invalidates all block device page cache entries in + * that case. + * + * Returns %true if the block device changed, or %false if not. + */ +bool bdev_check_media_change(struct block_device *bdev) +{ + unsigned int events; + + events = disk_clear_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE | + DISK_EVENT_EJECT_REQUEST); + if (!(events & DISK_EVENT_MEDIA_CHANGE)) + return false; + + if (__invalidate_device(bdev, true)) + pr_warn("VFS: busy inodes on changed media %s\n", + bdev->bd_disk->disk_name); + set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); + return true; +} +EXPORT_SYMBOL(bdev_check_media_change); + /* * Separate this part out so that a different pointer for clearing_ptr can be * passed in for disk_clear_events. diff --git a/fs/block_dev.c b/fs/block_dev.c index c70c41ecba48..c6ac0bd22eca 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1379,21 +1379,10 @@ EXPORT_SYMBOL(revalidate_disk_size); */ int check_disk_change(struct block_device *bdev) { - struct gendisk *disk = bdev->bd_disk; - const struct block_device_operations *bdops = disk->fops; - unsigned int events; - - events = disk_clear_events(disk, DISK_EVENT_MEDIA_CHANGE | - DISK_EVENT_EJECT_REQUEST); - if (!(events & DISK_EVENT_MEDIA_CHANGE)) + if (!bdev_check_media_change(bdev)) return 0; - - if (__invalidate_device(bdev, true)) - pr_warn("VFS: busy inodes on changed media %s\n", - disk->disk_name); - set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); - if (bdops->revalidate_disk) - bdops->revalidate_disk(bdev->bd_disk); + if (bdev->bd_disk->fops->revalidate_disk) + bdev->bd_disk->fops->revalidate_disk(bdev->bd_disk); return 1; } diff --git a/include/linux/genhd.h b/include/linux/genhd.h index c618b27292fc..322d48a20772 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -315,7 +315,6 @@ extern void disk_unblock_events(struct gendisk *disk); extern void disk_flush_events(struct gendisk *disk, unsigned int mask); void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, bool update_bdev); -extern unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask); /* drivers/char/random.c */ extern void add_disk_randomness(struct gendisk *disk) __latent_entropy; @@ -372,6 +371,7 @@ void unregister_blkdev(unsigned int major, const char *name); void revalidate_disk_size(struct gendisk *disk, bool verbose); int check_disk_change(struct block_device *bdev); +bool bdev_check_media_change(struct block_device *bdev); int __invalidate_device(struct block_device *bdev, bool kill_dirty); void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors); -- cgit v1.2.3 From fec2cf607ba9305770436b1e5c485963a9f0a7bd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Sep 2020 16:53:42 +0200 Subject: ide-gd: stop using the disk events mechanism ide-gd is only using the disk events mechanism to be able to force an invalidation and partition scan on opening removable media. Just open code the logic without invoving the block layer. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- drivers/ide/ide-disk.c | 5 +---- drivers/ide/ide-floppy.c | 2 -- drivers/ide/ide-gd.c | 48 ++++++------------------------------------------ include/linux/ide.h | 2 -- 4 files changed, 7 insertions(+), 50 deletions(-) (limited to 'include') diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c index 1d3407d7e095..34b9441084f8 100644 --- a/drivers/ide/ide-disk.c +++ b/drivers/ide/ide-disk.c @@ -739,12 +739,9 @@ static void ide_disk_setup(ide_drive_t *drive) set_wcache(drive, 1); if ((drive->dev_flags & IDE_DFLAG_LBA) == 0 && - (drive->head == 0 || drive->head > 16)) { + (drive->head == 0 || drive->head > 16)) printk(KERN_ERR "%s: invalid geometry: %d physical heads?\n", drive->name, drive->head); - drive->dev_flags &= ~IDE_DFLAG_ATTACH; - } else - drive->dev_flags |= IDE_DFLAG_ATTACH; } static void ide_disk_flush(ide_drive_t *drive) diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c index af7503b47dbe..f5a2870aaf54 100644 --- a/drivers/ide/ide-floppy.c +++ b/drivers/ide/ide-floppy.c @@ -516,8 +516,6 @@ static void ide_floppy_setup(ide_drive_t *drive) (void) ide_floppy_get_capacity(drive); ide_proc_register_driver(drive, floppy->driver); - - drive->dev_flags |= IDE_DFLAG_ATTACH; } static void ide_floppy_flush(ide_drive_t *drive) diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c index 05c26986637b..661e2aa9c967 100644 --- a/drivers/ide/ide-gd.c +++ b/drivers/ide/ide-gd.c @@ -225,8 +225,12 @@ static int ide_gd_open(struct block_device *bdev, fmode_t mode) * and the door_lock is irrelevant at this point. */ drive->disk_ops->set_doorlock(drive, disk, 1); - drive->dev_flags |= IDE_DFLAG_MEDIA_CHANGED; - check_disk_change(bdev); + if (__invalidate_device(bdev, true)) + pr_warn("VFS: busy inodes on changed media %s\n", + bdev->bd_disk->disk_name); + drive->disk_ops->get_capacity(drive); + set_capacity(disk, ide_gd_capacity(drive)); + set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); } else if (drive->dev_flags & IDE_DFLAG_FORMAT_IN_PROGRESS) { ret = -EBUSY; goto out_put_idkp; @@ -284,32 +288,6 @@ static int ide_gd_getgeo(struct block_device *bdev, struct hd_geometry *geo) return 0; } -static unsigned int ide_gd_check_events(struct gendisk *disk, - unsigned int clearing) -{ - struct ide_disk_obj *idkp = ide_drv_g(disk, ide_disk_obj); - ide_drive_t *drive = idkp->drive; - bool ret; - - /* do not scan partitions twice if this is a removable device */ - if (drive->dev_flags & IDE_DFLAG_ATTACH) { - drive->dev_flags &= ~IDE_DFLAG_ATTACH; - return 0; - } - - /* - * The following is used to force revalidation on the first open on - * removeable devices, and never gets reported to userland as - * DISK_EVENT_FLAG_UEVENT isn't set in genhd->event_flags. - * This is intended as removable ide disk can't really detect - * MEDIA_CHANGE events. - */ - ret = drive->dev_flags & IDE_DFLAG_MEDIA_CHANGED; - drive->dev_flags &= ~IDE_DFLAG_MEDIA_CHANGED; - - return ret ? DISK_EVENT_MEDIA_CHANGE : 0; -} - static void ide_gd_unlock_native_capacity(struct gendisk *disk) { struct ide_disk_obj *idkp = ide_drv_g(disk, ide_disk_obj); @@ -320,18 +298,6 @@ static void ide_gd_unlock_native_capacity(struct gendisk *disk) disk_ops->unlock_native_capacity(drive); } -static int ide_gd_revalidate_disk(struct gendisk *disk) -{ - struct ide_disk_obj *idkp = ide_drv_g(disk, ide_disk_obj); - ide_drive_t *drive = idkp->drive; - - if (ide_gd_check_events(disk, 0)) - drive->disk_ops->get_capacity(drive); - - set_capacity(disk, ide_gd_capacity(drive)); - return 0; -} - static int ide_gd_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { @@ -364,9 +330,7 @@ static const struct block_device_operations ide_gd_ops = { .compat_ioctl = ide_gd_compat_ioctl, #endif .getgeo = ide_gd_getgeo, - .check_events = ide_gd_check_events, .unlock_native_capacity = ide_gd_unlock_native_capacity, - .revalidate_disk = ide_gd_revalidate_disk }; static int ide_gd_probe(ide_drive_t *drive) diff --git a/include/linux/ide.h b/include/linux/ide.h index a254841bd315..62653769509f 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -490,8 +490,6 @@ enum { IDE_DFLAG_NOPROBE = BIT(9), /* need to do check_media_change() */ IDE_DFLAG_REMOVABLE = BIT(10), - /* needed for removable devices */ - IDE_DFLAG_ATTACH = BIT(11), IDE_DFLAG_FORCED_GEOM = BIT(12), /* disallow setting unmask bit */ IDE_DFLAG_NO_UNMASK = BIT(13), -- cgit v1.2.3 From b92b53079aedbfb56bbb9ea360e5119fb563a2a1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Sep 2020 16:53:47 +0200 Subject: block: remove check_disk_change Remove the now unused check_disk_change helper. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- fs/block_dev.c | 20 -------------------- include/linux/genhd.h | 1 - 2 files changed, 21 deletions(-) (limited to 'include') diff --git a/fs/block_dev.c b/fs/block_dev.c index c6ac0bd22eca..0b34955b9e36 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1368,26 +1368,6 @@ void revalidate_disk_size(struct gendisk *disk, bool verbose) } EXPORT_SYMBOL(revalidate_disk_size); -/* - * This routine checks whether a removable media has been changed, - * and invalidates all buffer-cache-entries in that case. This - * is a relatively slow routine, so we have to try to minimize using - * it. Thus it is called only upon a 'mount' or 'open'. This - * is the best way of combining speed and utility, I think. - * People changing diskettes in the middle of an operation deserve - * to lose :-) - */ -int check_disk_change(struct block_device *bdev) -{ - if (!bdev_check_media_change(bdev)) - return 0; - if (bdev->bd_disk->fops->revalidate_disk) - bdev->bd_disk->fops->revalidate_disk(bdev->bd_disk); - return 1; -} - -EXPORT_SYMBOL(check_disk_change); - void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors) { spin_lock(&bdev->bd_size_lock); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 322d48a20772..1c97cf84f011 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -370,7 +370,6 @@ int register_blkdev(unsigned int major, const char *name); void unregister_blkdev(unsigned int major, const char *name); void revalidate_disk_size(struct gendisk *disk, bool verbose); -int check_disk_change(struct block_device *bdev); bool bdev_check_media_change(struct block_device *bdev); int __invalidate_device(struct block_device *bdev, bool kill_dirty); void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors); -- cgit v1.2.3 From 7b26410b05f8c262688de8a689ba8e5d0c3cff01 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 31 Aug 2020 15:27:23 -0700 Subject: block: introduce part_[begin|end]_io_acct These functions can be used to enable iostat for partitions on devices like md, bcache. Signed-off-by: Song Liu Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 39 +++++++++++++++++++++++++++++++++------ include/linux/blkdev.h | 5 +++++ 2 files changed, 38 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/block/blk-core.c b/block/blk-core.c index 093649bd252e..ca3f0f00c943 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1324,10 +1324,9 @@ void blk_account_io_start(struct request *rq) part_stat_unlock(); } -unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, - unsigned int op) +static unsigned long __part_start_io_acct(struct hd_struct *part, + unsigned int sectors, unsigned int op) { - struct hd_struct *part = &disk->part0; const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); @@ -1340,12 +1339,26 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, return now; } + +unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part, + struct bio *bio) +{ + *part = disk_map_sector_rcu(disk, bio->bi_iter.bi_sector); + + return __part_start_io_acct(*part, bio_sectors(bio), bio_op(bio)); +} +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, sectors, op); +} EXPORT_SYMBOL(disk_start_io_acct); -void disk_end_io_acct(struct gendisk *disk, unsigned int op, - unsigned long start_time) +static void __part_end_io_acct(struct hd_struct *part, unsigned int op, + unsigned long start_time) { - struct hd_struct *part = &disk->part0; const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); unsigned long duration = now - start_time; @@ -1356,6 +1369,20 @@ void disk_end_io_acct(struct gendisk *disk, unsigned int op, part_stat_local_dec(part, in_flight[op_is_write(op)]); part_stat_unlock(); } + +void part_end_io_acct(struct hd_struct *part, struct bio *bio, + unsigned long start_time) +{ + __part_end_io_acct(part, bio_op(bio), start_time); + hd_struct_put(part); +} +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, op, start_time); +} EXPORT_SYMBOL(disk_end_io_acct); /* diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 37ec5a73d027..5bd96fbab9b4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1933,6 +1933,11 @@ 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 start_time); + /** * bio_start_io_acct - start I/O accounting for bio based drivers * @bio: bio to start account for -- cgit v1.2.3 From 07d098e6bbad04030dab5b3e64149601fcb063ce Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Mon, 21 Sep 2020 22:32:49 -0400 Subject: block: allow 'chunk_sectors' to be non-power-of-2 It is possible, albeit more unlikely, for a block device to have a non power-of-2 for chunk_sectors (e.g. 10+2 RAID6 with 128K chunk_sectors, which results in a full-stripe size of 1280K. This causes the RAID6's io_opt to be advertised as 1280K, and a stacked device _could_ then be made to use a blocksize, aka chunk_sectors, that matches non power-of-2 io_opt of underlying RAID6 -- resulting in stacked device's chunk_sectors being a non power-of-2). Update blk_queue_chunk_sectors() and blk_max_size_offset() to accommodate drivers that need a non power-of-2 chunk_sectors. Reviewed-by: Ming Lei Reviewed-by: Martin K. Petersen Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- block/blk-settings.c | 10 ++++------ include/linux/blkdev.h | 12 +++++++++--- 2 files changed, 13 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/block/blk-settings.c b/block/blk-settings.c index b2e1a929a6db..5ea3de48afba 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -172,15 +172,13 @@ EXPORT_SYMBOL(blk_queue_max_hw_sectors); * * Description: * If a driver doesn't want IOs to cross a given chunk size, it can set - * this limit and prevent merging across chunks. Note that the chunk size - * must currently be a power-of-2 in sectors. Also note that the block - * layer must accept a page worth of data at any offset. So if the - * crossing of chunks is a hard limitation in the driver, it must still be - * prepared to split single page bios. + * this limit and prevent merging across chunks. Note that the block layer + * must accept a page worth of data at any offset. So if the crossing of + * chunks is a hard limitation in the driver, it must still be prepared + * to split single page bios. **/ void blk_queue_chunk_sectors(struct request_queue *q, unsigned int chunk_sectors) { - BUG_ON(!is_power_of_2(chunk_sectors)); q->limits.chunk_sectors = chunk_sectors; } EXPORT_SYMBOL(blk_queue_chunk_sectors); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5bd96fbab9b4..6e19a7aa1672 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1063,11 +1063,17 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, static inline unsigned int blk_max_size_offset(struct request_queue *q, sector_t offset) { - if (!q->limits.chunk_sectors) + unsigned int chunk_sectors = q->limits.chunk_sectors; + + if (!chunk_sectors) return q->limits.max_sectors; - return min(q->limits.max_sectors, (unsigned int)(q->limits.chunk_sectors - - (offset & (q->limits.chunk_sectors - 1)))); + if (likely(is_power_of_2(chunk_sectors))) + chunk_sectors -= offset & (chunk_sectors - 1); + else + chunk_sectors -= sector_div(offset, chunk_sectors); + + return min(q->limits.max_sectors, chunk_sectors); } static inline unsigned int blk_rq_get_max_sectors(struct request *rq, -- cgit v1.2.3 From 38430f0876fa8b9549ec434f569dce03e057c076 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 21 Sep 2020 09:19:45 +0200 Subject: block: move the NEED_PART_SCAN flag to struct gendisk We can only scan for partitions on the whole disk, so move the flag from struct block_device to struct gendisk. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/genhd.c | 4 ++-- drivers/block/nbd.c | 8 ++++---- drivers/ide/ide-gd.c | 2 +- fs/block_dev.c | 7 +++---- include/linux/blk_types.h | 4 +--- include/linux/genhd.h | 2 ++ 6 files changed, 13 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/block/genhd.c b/block/genhd.c index 9d060e79eb31..7b56203c90a3 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -731,7 +731,7 @@ static void register_disk(struct device *parent, struct gendisk *disk, if (!bdev) goto exit; - set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); + set_bit(GD_NEED_PART_SCAN, &disk->state); err = blkdev_get(bdev, FMODE_READ, NULL); if (err < 0) goto exit; @@ -2112,7 +2112,7 @@ bool bdev_check_media_change(struct block_device *bdev) if (__invalidate_device(bdev, true)) pr_warn("VFS: busy inodes on changed media %s\n", bdev->bd_disk->disk_name); - set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); + set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); return true; } EXPORT_SYMBOL(bdev_check_media_change); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 15eed210feef..2dca0aab0a9a 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -315,7 +315,7 @@ static void nbd_size_update(struct nbd_device *nbd) bd_set_nr_sectors(bdev, nr_sectors); set_blocksize(bdev, config->blksize); } else - set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); + set_bit(GD_NEED_PART_SCAN, &nbd->disk->state); bdput(bdev); } kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE); @@ -1322,7 +1322,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b return ret; if (max_part) - set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); + set_bit(GD_NEED_PART_SCAN, &nbd->disk->state); mutex_unlock(&nbd->config_lock); ret = wait_event_interruptible(config->recv_wq, atomic_read(&config->recv_threads) == 0); @@ -1500,9 +1500,9 @@ static int nbd_open(struct block_device *bdev, fmode_t mode) refcount_set(&nbd->config_refs, 1); refcount_inc(&nbd->refs); mutex_unlock(&nbd->config_lock); - set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); + set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); } else if (nbd_disconnected(nbd->config)) { - set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); + set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); } out: mutex_unlock(&nbd_index_mutex); diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c index 661e2aa9c967..e2b6c82586ce 100644 --- a/drivers/ide/ide-gd.c +++ b/drivers/ide/ide-gd.c @@ -230,7 +230,7 @@ static int ide_gd_open(struct block_device *bdev, fmode_t mode) bdev->bd_disk->disk_name); drive->disk_ops->get_capacity(drive); set_capacity(disk, ide_gd_capacity(drive)); - set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); + set_bit(GD_NEED_PART_SCAN, &disk->state); } else if (drive->dev_flags & IDE_DFLAG_FORMAT_IN_PROGRESS) { ret = -EBUSY; goto out_put_idkp; diff --git a/fs/block_dev.c b/fs/block_dev.c index 0b34955b9e36..1a9325f43157 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -910,7 +910,6 @@ struct block_device *bdget(dev_t dev) bdev->bd_super = NULL; bdev->bd_inode = inode; bdev->bd_part_count = 0; - bdev->bd_flags = 0; inode->i_mode = S_IFBLK; inode->i_rdev = dev; inode->i_bdev = bdev; @@ -1385,7 +1384,7 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate) lockdep_assert_held(&bdev->bd_mutex); - clear_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags); + clear_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); rescan: ret = blk_drop_partitions(bdev); @@ -1509,7 +1508,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder, * The latter is necessary to prevent ghost * partitions on a removed medium. */ - if (test_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags) && + if (test_bit(GD_NEED_PART_SCAN, &disk->state) && (!ret || ret == -ENOMEDIUM)) bdev_disk_changed(bdev, ret == -ENOMEDIUM); @@ -1539,7 +1538,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder, if (bdev->bd_disk->fops->open) ret = bdev->bd_disk->fops->open(bdev, mode); /* the same as first opener case, read comment there */ - if (test_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags) && + if (test_bit(GD_NEED_PART_SCAN, &disk->state) && (!ret || ret == -ENOMEDIUM)) bdev_disk_changed(bdev, ret == -ENOMEDIUM); if (ret) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 6ffa783e1633..eb20e28184ab 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -19,8 +19,6 @@ struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); struct bio_crypt_ctx; -#define BDEV_NEED_PART_SCAN 0 - struct block_device { dev_t bd_dev; int bd_openers; @@ -39,7 +37,7 @@ struct block_device { struct hd_struct * bd_part; /* number of times partitions within this device have been opened. */ unsigned bd_part_count; - unsigned long bd_flags; + spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct gendisk * bd_disk; struct backing_dev_info *bd_bdi; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 1c97cf84f011..38f23d757013 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -191,6 +191,8 @@ struct gendisk { void *private_data; int flags; + unsigned long state; +#define GD_NEED_PART_SCAN 0 struct rw_semaphore lookup_sem; struct kobject *slave_dir; -- cgit v1.2.3 From bb3247a399801ebba20bef101c89e563f5fe7f02 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 21 Sep 2020 09:19:55 +0200 Subject: PM: rewrite is_hibernate_resume_dev to not require an inode Just check the dev_t to help simplifying the code. Signed-off-by: Christoph Hellwig Acked-by: Rafael J. Wysocki Acked-by: Pavel Machek Signed-off-by: Jens Axboe --- fs/block_dev.c | 2 +- include/linux/suspend.h | 4 ++-- kernel/power/user.c | 12 ++++++------ 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/fs/block_dev.c b/fs/block_dev.c index 1a9325f43157..2898d69be6b3 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1885,7 +1885,7 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) if (bdev_read_only(I_BDEV(bd_inode))) return -EPERM; - if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode)) + if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode->i_rdev)) return -ETXTBSY; if (!iov_iter_count(from)) diff --git a/include/linux/suspend.h b/include/linux/suspend.h index cb9afad82a90..8af13ba60c7e 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -473,9 +473,9 @@ static inline int hibernate_quiet_exec(int (*func)(void *data), void *data) { #endif /* CONFIG_HIBERNATION */ #ifdef CONFIG_HIBERNATION_SNAPSHOT_DEV -int is_hibernate_resume_dev(const struct inode *); +int is_hibernate_resume_dev(dev_t dev); #else -static inline int is_hibernate_resume_dev(const struct inode *i) { return 0; } +static inline int is_hibernate_resume_dev(dev_t dev) { return 0; } #endif /* Hibernation and suspend events */ diff --git a/kernel/power/user.c b/kernel/power/user.c index d5eedc2baa2a..b5815685b944 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -35,12 +35,12 @@ static struct snapshot_data { bool ready; bool platform_support; bool free_bitmaps; - struct inode *bd_inode; + dev_t dev; } snapshot_state; -int is_hibernate_resume_dev(const struct inode *bd_inode) +int is_hibernate_resume_dev(dev_t dev) { - return hibernation_available() && snapshot_state.bd_inode == bd_inode; + return hibernation_available() && snapshot_state.dev == dev; } static int snapshot_open(struct inode *inode, struct file *filp) @@ -101,7 +101,7 @@ static int snapshot_open(struct inode *inode, struct file *filp) data->frozen = false; data->ready = false; data->platform_support = false; - data->bd_inode = NULL; + data->dev = 0; Unlock: unlock_system_sleep(); @@ -117,7 +117,7 @@ static int snapshot_release(struct inode *inode, struct file *filp) swsusp_free(); data = filp->private_data; - data->bd_inode = NULL; + data->dev = 0; free_all_swap_pages(data->swap); if (data->frozen) { pm_restore_gfp_mask(); @@ -245,7 +245,7 @@ static int snapshot_set_swap_area(struct snapshot_data *data, if (data->swap < 0) return -ENODEV; - data->bd_inode = bdev->bd_inode; + data->dev = bdev->bd_dev; bdput(bdev); return 0; } -- cgit v1.2.3 From 21bd900572f3708e281ea25f051fc92462eb1193 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 21 Sep 2020 09:19:56 +0200 Subject: mm: split swap_type_of swap_type_of is used for two entirely different purposes: (1) check what swap type a given device/offset corresponds to (2) find the first available swap device that can be written to Mixing both in a single function creates an unreadable mess. Create two separate functions instead, and switch both to pass a dev_t instead of a struct block_device to further simplify the code. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/swap.h | 3 ++- kernel/power/swap.c | 17 ++++++++--------- kernel/power/user.c | 16 ++++------------ mm/swapfile.c | 39 +++++++++++++++++++++------------------ 4 files changed, 35 insertions(+), 40 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 661046994db4..4340a7b6e7a1 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -467,7 +467,8 @@ extern int swapcache_prepare(swp_entry_t); extern void swap_free(swp_entry_t); extern void swapcache_free_entries(swp_entry_t *entries, int n); extern int free_swap_and_cache(swp_entry_t); -extern int swap_type_of(dev_t, sector_t, struct block_device **); +int swap_type_of(dev_t device, sector_t offset); +int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); extern sector_t map_swap_page(struct page *, struct block_device **); extern sector_t swapdev_block(int, pgoff_t); diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 01e2858b5fe3..9d3ffbfe08db 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -335,12 +335,17 @@ static int swsusp_swap_check(void) { int res; - res = swap_type_of(swsusp_resume_device, swsusp_resume_block, - &hib_resume_bdev); + if (swsusp_resume_device) + res = swap_type_of(swsusp_resume_device, swsusp_resume_block); + else + res = find_first_swap(&swsusp_resume_device); if (res < 0) return res; - root_swap = res; + + hib_resume_bdev = bdget(swsusp_resume_device); + if (!hib_resume_bdev) + return -ENOMEM; res = blkdev_get(hib_resume_bdev, FMODE_WRITE, NULL); if (res) return res; @@ -349,12 +354,6 @@ static int swsusp_swap_check(void) if (res < 0) blkdev_put(hib_resume_bdev, FMODE_WRITE); - /* - * Update the resume device to the one actually used, - * so the test_resume mode can use it in case it is - * invoked from hibernate() to test the snapshot. - */ - swsusp_resume_device = hib_resume_bdev->bd_dev; return res; } diff --git a/kernel/power/user.c b/kernel/power/user.c index b5815685b944..6510a8f7687f 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -69,8 +69,7 @@ static int snapshot_open(struct inode *inode, struct file *filp) memset(&data->handle, 0, sizeof(struct snapshot_handle)); if ((filp->f_flags & O_ACCMODE) == O_RDONLY) { /* Hibernating. The image device should be accessible. */ - data->swap = swsusp_resume_device ? - swap_type_of(swsusp_resume_device, 0, NULL) : -1; + data->swap = swap_type_of(swsusp_resume_device, 0); data->mode = O_RDONLY; data->free_bitmaps = false; error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls); @@ -210,7 +209,6 @@ struct compat_resume_swap_area { static int snapshot_set_swap_area(struct snapshot_data *data, void __user *argp) { - struct block_device *bdev; sector_t offset; dev_t swdev; @@ -237,16 +235,10 @@ static int snapshot_set_swap_area(struct snapshot_data *data, * User space encodes device types as two-byte values, * so we need to recode them */ - if (!swdev) { - data->swap = -1; - return -EINVAL; - } - data->swap = swap_type_of(swdev, offset, &bdev); + data->swap = swap_type_of(swdev, offset); if (data->swap < 0) - return -ENODEV; - - data->dev = bdev->bd_dev; - bdput(bdev); + return swdev ? -ENODEV : -EINVAL; + data->dev = swdev; return 0; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 7438c4affc75..b90f86920743 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1801,13 +1801,12 @@ int free_swap_and_cache(swp_entry_t entry) * * This is needed for the suspend to disk (aka swsusp). */ -int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) +int swap_type_of(dev_t device, sector_t offset) { - struct block_device *bdev = NULL; int type; - if (device) - bdev = bdget(device); + if (!device) + return -1; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { @@ -1816,30 +1815,34 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) if (!(sis->flags & SWP_WRITEOK)) continue; - if (!bdev) { - if (bdev_p) - *bdev_p = bdgrab(sis->bdev); - - spin_unlock(&swap_lock); - return type; - } - if (bdev == sis->bdev) { + if (device == sis->bdev->bd_dev) { struct swap_extent *se = first_se(sis); if (se->start_block == offset) { - if (bdev_p) - *bdev_p = bdgrab(sis->bdev); - spin_unlock(&swap_lock); - bdput(bdev); return type; } } } spin_unlock(&swap_lock); - if (bdev) - bdput(bdev); + return -ENODEV; +} +int find_first_swap(dev_t *device) +{ + int type; + + spin_lock(&swap_lock); + for (type = 0; type < nr_swapfiles; type++) { + struct swap_info_struct *sis = swap_info[type]; + + if (!(sis->flags & SWP_WRITEOK)) + continue; + *device = sis->bdev->bd_dev; + spin_unlock(&swap_lock); + return type; + } + spin_unlock(&swap_lock); return -ENODEV; } -- cgit v1.2.3 From 1fb1a2ad75e33e646d33e42b9ed17d879d472859 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 21 Sep 2020 09:19:58 +0200 Subject: block: mark blkdev_get static There are no users outside the core block code left now. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/block_dev.c | 3 +-- include/linux/blkdev.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/fs/block_dev.c b/fs/block_dev.c index 2898d69be6b3..6b9d19ffa5af 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1616,7 +1616,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder, * RETURNS: * 0 on success, -errno on failure. */ -int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder) +static int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder) { int ret, perm = 0; @@ -1637,7 +1637,6 @@ bdput: bdput(bdev); return ret; } -EXPORT_SYMBOL(blkdev_get); /** * blkdev_get_by_path - open a block device by name diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6e19a7aa1672..be5ef6f4ba19 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1981,7 +1981,6 @@ void blkdev_show(struct seq_file *seqf, off_t offset); #define BLKDEV_MAJOR_MAX 0 #endif -int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder); struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); -- cgit v1.2.3 From 402dd2cf46b177be5bcb138b7d7fd8f38aa130e4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:28 +0200 Subject: fs: remove the unused SB_I_MULTIROOT flag The last user of SB_I_MULTIROOT is disappeared with commit f2aedb713c28 ("NFS: Add fs_context support.") Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- fs/namei.c | 4 ++-- include/linux/fs.h | 1 - 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/fs/namei.c b/fs/namei.c index e99e2a9da0f7..f1eb8ccd2be9 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -568,8 +568,8 @@ static bool path_connected(struct vfsmount *mnt, struct dentry *dentry) { struct super_block *sb = mnt->mnt_sb; - /* Bind mounts and multi-root filesystems can have disconnected paths */ - if (!(sb->s_iflags & SB_I_MULTIROOT) && (mnt->mnt_root == sb->s_root)) + /* Bind mounts can have disconnected paths */ + if (mnt->mnt_root == sb->s_root) return true; return is_subdir(dentry, mnt->mnt_root); diff --git a/include/linux/fs.h b/include/linux/fs.h index 7519ae003a08..fbd74df5ce5f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1385,7 +1385,6 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ -#define SB_I_MULTIROOT 0x00000008 /* Multiple roots to the dentry tree */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ -- cgit v1.2.3 From c2e4cd57cfa1f627b786c764d185fff85fd12be9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:34 +0200 Subject: block: lift setting the readahead size into the block layer Drivers shouldn't really mess with the readahead size, as that is a VM concept. Instead set it based on the optimal I/O size by lifting the algorithm from the md driver when registering the disk. Also set bdi->io_pages there as well by applying the same scheme based on max_sectors. To ensure the limits work well for stacking drivers a new helper is added to update the readahead limits from the block limits, which is also called from disk_stack_limits. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Jan Kara Reviewed-by: Mike Snitzer Reviewed-by: Martin K. Petersen Acked-by: Coly Li Signed-off-by: Jens Axboe --- block/blk-settings.c | 18 ++++++++++++++++-- block/blk-sysfs.c | 2 ++ drivers/block/aoe/aoeblk.c | 1 - drivers/block/drbd/drbd_nl.c | 10 +--------- drivers/md/bcache/super.c | 3 --- drivers/md/dm-table.c | 3 +-- drivers/md/raid0.c | 16 ---------------- drivers/md/raid10.c | 24 +----------------------- drivers/md/raid5.c | 13 +------------ drivers/nvme/host/core.c | 1 + include/linux/blkdev.h | 1 + 11 files changed, 24 insertions(+), 68 deletions(-) (limited to 'include') diff --git a/block/blk-settings.c b/block/blk-settings.c index 5ea3de48afba..4f6eb4bb1723 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -372,6 +372,19 @@ void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset) } EXPORT_SYMBOL(blk_queue_alignment_offset); +void blk_queue_update_readahead(struct request_queue *q) +{ + /* + * For read-ahead of large files to be effective, we need to read ahead + * at least twice the optimal I/O size. + */ + q->backing_dev_info->ra_pages = + max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES); + q->backing_dev_info->io_pages = + queue_max_sectors(q) >> (PAGE_SHIFT - 9); +} +EXPORT_SYMBOL_GPL(blk_queue_update_readahead); + /** * blk_limits_io_min - set minimum request size for a device * @limits: the queue limits @@ -450,6 +463,8 @@ EXPORT_SYMBOL(blk_limits_io_opt); void blk_queue_io_opt(struct request_queue *q, unsigned int opt) { blk_limits_io_opt(&q->limits, opt); + q->backing_dev_info->ra_pages = + max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES); } EXPORT_SYMBOL(blk_queue_io_opt); @@ -631,8 +646,7 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, top, bottom); } - t->backing_dev_info->io_pages = - t->limits.max_sectors >> (PAGE_SHIFT - 9); + blk_queue_update_readahead(disk->queue); } EXPORT_SYMBOL(disk_stack_limits); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 81722cdcf0cb..869ed21a9edc 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -854,6 +854,8 @@ int blk_register_queue(struct gendisk *disk) percpu_ref_switch_to_percpu(&q->q_usage_counter); } + blk_queue_update_readahead(q); + ret = blk_trace_init_sysfs(dev); if (ret) return ret; diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index d8cfc233e64b..c34e71b0c4a9 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -406,7 +406,6 @@ aoeblk_gdalloc(void *vp) WARN_ON(d->gd); WARN_ON(d->flags & DEVFL_UP); blk_queue_max_hw_sectors(q, BLK_DEF_MAX_SECTORS); - q->backing_dev_info->ra_pages = SZ_2M / PAGE_SIZE; blk_queue_io_opt(q, SZ_2M); d->bufpool = mp; d->blkq = gd->queue = q; diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index aaff5bde3915..54a4930c04fe 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -1362,15 +1362,7 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi if (b) { blk_stack_limits(&q->limits, &b->limits, 0); - - if (q->backing_dev_info->ra_pages != - b->backing_dev_info->ra_pages) { - drbd_info(device, "Adjusting my ra_pages to backing device's (%lu -> %lu)\n", - q->backing_dev_info->ra_pages, - b->backing_dev_info->ra_pages); - q->backing_dev_info->ra_pages = - b->backing_dev_info->ra_pages; - } + blk_queue_update_readahead(q); } fixup_discard_if_not_supported(q); fixup_write_zeroes(device, q); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 48113005ed86..6bfa77167362 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1427,9 +1427,6 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) if (ret) return ret; - dc->disk.disk->queue->backing_dev_info->ra_pages = - max(dc->disk.disk->queue->backing_dev_info->ra_pages, - q->backing_dev_info->ra_pages); blk_queue_io_opt(dc->disk.disk->queue, max(queue_io_opt(dc->disk.disk->queue), queue_io_opt(q))); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 5edc3079e7c1..ef2757012f59 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1925,8 +1925,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, } #endif - /* Allow reads to exceed readahead limits */ - q->backing_dev_info->io_pages = limits->max_sectors >> (PAGE_SHIFT - 9); + blk_queue_update_readahead(q); } unsigned int dm_table_get_num_targets(struct dm_table *t) diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index f54a449f97aa..aa2d72791768 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -410,22 +410,6 @@ static int raid0_run(struct mddev *mddev) mdname(mddev), (unsigned long long)mddev->array_sectors); - if (mddev->queue) { - /* calculate the max read-ahead size. - * For read-ahead of large files to be effective, we need to - * readahead at least twice a whole stripe. i.e. number of devices - * multiplied by chunk size times 2. - * If an individual device has an ra_pages greater than the - * chunk size, then we will not drive that device as hard as it - * wants. We consider this a configuration error: a larger - * chunksize should be used in that case. - */ - int stripe = mddev->raid_disks * - (mddev->chunk_sectors << 9) / PAGE_SIZE; - if (mddev->queue->backing_dev_info->ra_pages < 2* stripe) - mddev->queue->backing_dev_info->ra_pages = 2* stripe; - } - dump_zones(mddev); ret = md_integrity_register(mddev); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 9956a04ac13b..5d1bdee313ec 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -3873,19 +3873,6 @@ static int raid10_run(struct mddev *mddev) mddev->resync_max_sectors = size; set_bit(MD_FAILFAST_SUPPORTED, &mddev->flags); - if (mddev->queue) { - int stripe = conf->geo.raid_disks * - ((mddev->chunk_sectors << 9) / PAGE_SIZE); - - /* Calculate max read-ahead size. - * We need to readahead at least twice a whole stripe.... - * maybe... - */ - stripe /= conf->geo.near_copies; - if (mddev->queue->backing_dev_info->ra_pages < 2 * stripe) - mddev->queue->backing_dev_info->ra_pages = 2 * stripe; - } - if (md_integrity_register(mddev)) goto out_free_conf; @@ -4723,17 +4710,8 @@ static void end_reshape(struct r10conf *conf) conf->reshape_safe = MaxSector; spin_unlock_irq(&conf->device_lock); - /* read-ahead size must cover two whole stripes, which is - * 2 * (datadisks) * chunksize where 'n' is the number of raid devices - */ - if (conf->mddev->queue) { - int stripe = conf->geo.raid_disks * - ((conf->mddev->chunk_sectors << 9) / PAGE_SIZE); - stripe /= conf->geo.near_copies; - if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe) - conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe; + if (conf->mddev->queue) raid10_set_io_opt(conf); - } conf->fullsync = 0; } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 9a7d1250894e..7ace1f76b147 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7522,8 +7522,6 @@ static int raid5_run(struct mddev *mddev) int data_disks = conf->previous_raid_disks - conf->max_degraded; int stripe = data_disks * ((mddev->chunk_sectors << 9) / PAGE_SIZE); - if (mddev->queue->backing_dev_info->ra_pages < 2 * stripe) - mddev->queue->backing_dev_info->ra_pages = 2 * stripe; chunk_size = mddev->chunk_sectors << 9; blk_queue_io_min(mddev->queue, chunk_size); @@ -8111,17 +8109,8 @@ static void end_reshape(struct r5conf *conf) spin_unlock_irq(&conf->device_lock); wake_up(&conf->wait_for_overlap); - /* read-ahead size must cover two whole stripes, which is - * 2 * (datadisks) * chunksize where 'n' is the number of raid devices - */ - if (conf->mddev->queue) { - int data_disks = conf->raid_disks - conf->max_degraded; - int stripe = data_disks * ((conf->chunk_sectors << 9) - / PAGE_SIZE); - if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe) - conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe; + if (conf->mddev->queue) raid5_set_io_opt(conf); - } } } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index ea1fa41fbba8..741c9bfa8e14 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2147,6 +2147,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) nvme_update_disk_info(ns->head->disk, 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); } #endif diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index be5ef6f4ba19..282f5ca424f1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1140,6 +1140,7 @@ extern void blk_queue_max_zone_append_sectors(struct request_queue *q, extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); +void blk_queue_update_readahead(struct request_queue *q); extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); -- cgit v1.2.3 From ed7b6b4f6e915cb0bc52d0000bcc63168867b6ac Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:35 +0200 Subject: bdi: remove BDI_CAP_CGROUP_WRITEBACK Just checking SB_I_CGROUPWB for cgroup writeback support is enough. Either the file system allocates its own bdi (e.g. btrfs), in which case it is known to support cgroup writeback, or the bdi comes from the block layer, which always supports cgroup writeback. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- block/blk-core.c | 1 - fs/btrfs/disk-io.c | 1 - include/linux/backing-dev.h | 8 +++----- 3 files changed, 3 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/block/blk-core.c b/block/blk-core.c index 865d39e5be2b..1cc4fa6bc7fe 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -538,7 +538,6 @@ struct request_queue *blk_alloc_queue(int node_id) if (!q->stats) goto fail_stats; - q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK; q->node = node_id; atomic_set(&q->nr_active_requests_shared_sbitmap, 0); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 047934cea25e..e24927bddd58 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3091,7 +3091,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_sb_buffer; } - sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK; sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super); sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 0b06b2d26c9a..52583b6f2ea0 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -123,7 +123,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. * - * BDI_CAP_CGROUP_WRITEBACK: Supports cgroup-aware writeback. * BDI_CAP_SYNCHRONOUS_IO: Device is so fast that asynchronous IO would be * inefficient. */ @@ -233,9 +232,9 @@ int inode_congested(struct inode *inode, int cong_bits); * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode * @inode: inode of interest * - * cgroup writeback requires support from both the bdi and filesystem. - * Also, both memcg and iocg have to be on the default hierarchy. Test - * whether all conditions are met. + * Cgroup writeback requires support from the filesystem. Also, both memcg and + * iocg have to be on the default hierarchy. Test whether all conditions are + * met. * * Note that the test result may change dynamically on the same inode * depending on how memcg and iocg are configured. @@ -247,7 +246,6 @@ static inline bool inode_cgwb_enabled(struct inode *inode) return cgroup_subsys_on_dfl(memory_cgrp_subsys) && cgroup_subsys_on_dfl(io_cgrp_subsys) && bdi_cap_account_dirty(bdi) && - (bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) && (inode->i_sb->s_iflags & SB_I_CGROUPWB); } -- cgit v1.2.3 From a8b456d01cd6b37191f14248f3e2bdbe5ce3a89e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:36 +0200 Subject: bdi: remove BDI_CAP_SYNCHRONOUS_IO BDI_CAP_SYNCHRONOUS_IO is only checked in the swap code, and used to decided if ->rw_page can be used on a block device. Just check up for the method instead. The only complication is that zram needs a second set of block_device_operations as it can switch between modes that actually support ->rw_page and those who don't. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- drivers/block/brd.c | 1 - drivers/block/zram/zram_drv.c | 19 +++++++++++++------ drivers/nvdimm/btt.c | 2 -- drivers/nvdimm/pmem.c | 1 - include/linux/backing-dev.h | 9 --------- mm/swapfile.c | 2 +- 6 files changed, 14 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 2723a70eb855..cc49a921339f 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -403,7 +403,6 @@ static struct brd_device *brd_alloc(int i) disk->flags = GENHD_FL_EXT_DEVT; sprintf(disk->disk_name, "ram%d", i); set_capacity(disk, rd_size * 2); - brd->brd_queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO; /* Tell the block layer that this is not a rotational device */ blk_queue_flag_set(QUEUE_FLAG_NONROT, brd->brd_queue); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 91ccfe444525..e21ca844d7c2 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -52,6 +52,9 @@ static unsigned int num_devices = 1; */ static size_t huge_class_size; +static const struct block_device_operations zram_devops; +static const struct block_device_operations zram_wb_devops; + static void zram_free_page(struct zram *zram, size_t index); static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, u32 index, int offset, struct bio *bio); @@ -408,8 +411,7 @@ static void reset_bdev(struct zram *zram) zram->backing_dev = NULL; zram->old_block_size = 0; zram->bdev = NULL; - zram->disk->queue->backing_dev_info->capabilities |= - BDI_CAP_SYNCHRONOUS_IO; + zram->disk->fops = &zram_devops; kvfree(zram->bitmap); zram->bitmap = NULL; } @@ -529,8 +531,7 @@ static ssize_t backing_dev_store(struct device *dev, * freely but in fact, IO is going on so finally could cause * use-after-free when the IO is really done. */ - zram->disk->queue->backing_dev_info->capabilities &= - ~BDI_CAP_SYNCHRONOUS_IO; + zram->disk->fops = &zram_wb_devops; up_write(&zram->init_lock); pr_info("setup backing device %s\n", file_name); @@ -1820,6 +1821,13 @@ static const struct block_device_operations zram_devops = { .owner = THIS_MODULE }; +static const struct block_device_operations zram_wb_devops = { + .open = zram_open, + .submit_bio = zram_submit_bio, + .swap_slot_free_notify = zram_slot_free_notify, + .owner = THIS_MODULE +}; + static DEVICE_ATTR_WO(compact); static DEVICE_ATTR_RW(disksize); static DEVICE_ATTR_RO(initstate); @@ -1947,8 +1955,7 @@ static int zram_add(void) if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE) blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX); - zram->disk->queue->backing_dev_info->capabilities |= - (BDI_CAP_STABLE_WRITES | BDI_CAP_SYNCHRONOUS_IO); + zram->disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; device_add_disk(NULL, zram->disk, zram_disk_attr_groups); strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor)); diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 0d710140bf93..12ff6f8784ac 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1537,8 +1537,6 @@ static int btt_blk_init(struct btt *btt) btt->btt_disk->private_data = btt; btt->btt_disk->queue = btt->btt_queue; btt->btt_disk->flags = GENHD_FL_EXT_DEVT; - btt->btt_disk->queue->backing_dev_info->capabilities |= - BDI_CAP_SYNCHRONOUS_IO; blk_queue_logical_block_size(btt->btt_queue, btt->sector_size); blk_queue_max_hw_sectors(btt->btt_queue, UINT_MAX); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 140cf3b9000c..1711fdfd8d28 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -475,7 +475,6 @@ static int pmem_attach_disk(struct device *dev, disk->queue = q; disk->flags = GENHD_FL_EXT_DEVT; disk->private_data = pmem; - disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO; nvdimm_namespace_disk_name(ndns, disk->disk_name); set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset) / 512); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 52583b6f2ea0..860ea33571bc 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -122,9 +122,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * BDI_CAP_NO_WRITEBACK: Don't write pages back * BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. - * - * BDI_CAP_SYNCHRONOUS_IO: Device is so fast that asynchronous IO would be - * inefficient. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 @@ -132,7 +129,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); #define BDI_CAP_STABLE_WRITES 0x00000008 #define BDI_CAP_STRICTLIMIT 0x00000010 #define BDI_CAP_CGROUP_WRITEBACK 0x00000020 -#define BDI_CAP_SYNCHRONOUS_IO 0x00000040 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) @@ -174,11 +170,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) long congestion_wait(int sync, long timeout); long wait_iff_congested(int sync, long timeout); -static inline bool bdi_cap_synchronous_io(struct backing_dev_info *bdi) -{ - return bdi->capabilities & BDI_CAP_SYNCHRONOUS_IO; -} - static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi) { return bdi->capabilities & BDI_CAP_STABLE_WRITES; diff --git a/mm/swapfile.c b/mm/swapfile.c index b90f86920743..96a7c47dd533 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3240,7 +3240,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (bdi_cap_stable_pages_required(inode_to_bdi(inode))) p->flags |= SWP_STABLE_WRITES; - if (bdi_cap_synchronous_io(inode_to_bdi(inode))) + if (p->bdev && p->bdev->bd_disk->fops->rw_page) p->flags |= SWP_SYNCHRONOUS_IO; if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) { -- cgit v1.2.3 From 1cb039f3dc1619eb795c54aad0a98fdb379b4237 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:38 +0200 Subject: bdi: replace BDI_CAP_STABLE_WRITES with a queue and a sb flag The BDI_CAP_STABLE_WRITES is one of the few bits of information in the backing_dev_info shared between the block drivers and the writeback code. To help untangling the dependency replace it with a queue flag and a superblock flag derived from it. This also helps with the case of e.g. a file system requiring stable writes due to its own checksumming, but not forcing it on other users of the block device like the swap code. One downside is that we an't support the stable_pages_required bdi attribute in sysfs anymore. It is replaced with a queue attribute which also is writable for easier testing. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- block/blk-integrity.c | 4 ++-- block/blk-mq-debugfs.c | 1 + block/blk-sysfs.c | 3 +++ drivers/block/rbd.c | 2 +- drivers/block/zram/zram_drv.c | 2 +- drivers/md/dm-table.c | 6 +++--- drivers/md/raid5.c | 8 ++++---- drivers/mmc/core/queue.c | 3 +-- drivers/nvme/host/core.c | 3 +-- drivers/nvme/host/multipath.c | 10 +++------- drivers/scsi/iscsi_tcp.c | 4 ++-- fs/super.c | 2 ++ include/linux/backing-dev.h | 6 ------ include/linux/blkdev.h | 3 +++ include/linux/fs.h | 1 + mm/backing-dev.c | 7 +++---- mm/page-writeback.c | 2 +- mm/swapfile.c | 2 +- 18 files changed, 33 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/block/blk-integrity.c b/block/blk-integrity.c index c03705cbb9c9..2b36a8f9b813 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -408,7 +408,7 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template bi->tuple_size = template->tuple_size; bi->tag_size = template->tag_size; - disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue); #ifdef CONFIG_BLK_INLINE_ENCRYPTION if (disk->queue->ksm) { @@ -428,7 +428,7 @@ EXPORT_SYMBOL(blk_integrity_register); */ void blk_integrity_unregister(struct gendisk *disk) { - disk->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES; + blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue); memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity)); } EXPORT_SYMBOL(blk_integrity_unregister); diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 645b7f800cb8..3094542e12ae 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -116,6 +116,7 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(SAME_FORCE), QUEUE_FLAG_NAME(DEAD), QUEUE_FLAG_NAME(INIT_DONE), + QUEUE_FLAG_NAME(STABLE_WRITES), QUEUE_FLAG_NAME(POLL), QUEUE_FLAG_NAME(WC), QUEUE_FLAG_NAME(FUA), diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 869ed21a9edc..76b54c7750b0 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -287,6 +287,7 @@ queue_##name##_store(struct request_queue *q, const char *page, size_t count) \ QUEUE_SYSFS_BIT_FNS(nonrot, NONROT, 1); QUEUE_SYSFS_BIT_FNS(random, ADD_RANDOM, 0); QUEUE_SYSFS_BIT_FNS(iostats, IO_STAT, 0); +QUEUE_SYSFS_BIT_FNS(stable_writes, STABLE_WRITES, 0); #undef QUEUE_SYSFS_BIT_FNS static ssize_t queue_zoned_show(struct request_queue *q, char *page) @@ -613,6 +614,7 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = { QUEUE_RW_ENTRY(queue_nonrot, "rotational"); QUEUE_RW_ENTRY(queue_iostats, "iostats"); QUEUE_RW_ENTRY(queue_random, "add_random"); +QUEUE_RW_ENTRY(queue_stable_writes, "stable_writes"); static struct attribute *queue_attrs[] = { &queue_requests_entry.attr, @@ -645,6 +647,7 @@ static struct attribute *queue_attrs[] = { &queue_nomerges_entry.attr, &queue_rq_affinity_entry.attr, &queue_iostats_entry.attr, + &queue_stable_writes_entry.attr, &queue_random_entry.attr, &queue_poll_entry.attr, &queue_wc_entry.attr, diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 5d3923c0997c..cf5b016358cd 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -5022,7 +5022,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) } if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC)) - q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q); /* * disk_release() expects a queue ref from add_disk() and will diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index e21ca844d7c2..bff3d4021c18 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1955,7 +1955,7 @@ static int zram_add(void) if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE) blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX); - zram->disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue); device_add_disk(NULL, zram->disk, zram_disk_attr_groups); strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor)); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index ef2757012f59..405d7cf10eb9 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1815,7 +1815,7 @@ static int device_requires_stable_pages(struct dm_target *ti, { struct request_queue *q = bdev_get_queue(dev->bdev); - return q && bdi_cap_stable_pages_required(q->backing_dev_info); + return q && blk_queue_stable_writes(q); } /* @@ -1900,9 +1900,9 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, * because they do their own checksumming. */ if (dm_table_requires_stable_pages(t)) - q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q); else - q->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES; + blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q); /* * Determine whether or not this queue's I/O timings contribute diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 7ace1f76b147..d589d26c86ea 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6638,14 +6638,14 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len) if (!conf) err = -ENODEV; else if (new != conf->skip_copy) { + struct request_queue *q = mddev->queue; + mddev_suspend(mddev); conf->skip_copy = new; if (new) - mddev->queue->backing_dev_info->capabilities |= - BDI_CAP_STABLE_WRITES; + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q); else - mddev->queue->backing_dev_info->capabilities &= - ~BDI_CAP_STABLE_WRITES; + blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q); mddev_resume(mddev); } mddev_unlock(mddev); diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 6c022ef0f84d..80fe3852ce0f 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -472,8 +472,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card) } if (mmc_host_is_spi(host) && host->use_spi_crc) - mq->queue->backing_dev_info->capabilities |= - BDI_CAP_STABLE_WRITES; + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, mq->queue); mq->queue->queuedata = mq; blk_queue_rq_timeout(mq->queue, 60 * HZ); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 741c9bfa8e14..c190c56bf702 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3926,8 +3926,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) goto out_free_ns; if (ctrl->opts && ctrl->opts->data_digest) - ns->queue->backing_dev_info->capabilities - |= BDI_CAP_STABLE_WRITES; + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue); blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue); if (ctrl->ops->flags & NVME_F_PCI_P2PDMA) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index d4ba736c6c89..74896be40c17 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -673,13 +673,9 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id) nvme_mpath_set_live(ns); } - if (bdi_cap_stable_pages_required(ns->queue->backing_dev_info)) { - struct gendisk *disk = ns->head->disk; - - if (disk) - disk->queue->backing_dev_info->capabilities |= - BDI_CAP_STABLE_WRITES; - } + if (blk_queue_stable_writes(ns->queue) && ns->head->disk) + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, + ns->head->disk->queue); } void nvme_mpath_remove_disk(struct nvme_ns_head *head) diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index b5dd1caae5e9..a622f334c933 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -962,8 +962,8 @@ static int iscsi_sw_tcp_slave_configure(struct scsi_device *sdev) struct iscsi_conn *conn = session->leadconn; if (conn->datadgst_en) - sdev->request_queue->backing_dev_info->capabilities - |= BDI_CAP_STABLE_WRITES; + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, + sdev->request_queue); blk_queue_dma_alignment(sdev->request_queue, 0); return 0; } diff --git a/fs/super.c b/fs/super.c index 904459b35119..a51c2083cd6b 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1256,6 +1256,8 @@ static int set_bdev_super(struct super_block *s, void *data) s->s_dev = s->s_bdev->bd_dev; s->s_bdi = bdi_get(s->s_bdev->bd_bdi); + if (blk_queue_stable_writes(s->s_bdev->bd_disk->queue)) + s->s_iflags |= SB_I_STABLE_WRITES; return 0; } diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 860ea33571bc..5da4ea3dd0cc 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -126,7 +126,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 #define BDI_CAP_NO_ACCT_WB 0x00000004 -#define BDI_CAP_STABLE_WRITES 0x00000008 #define BDI_CAP_STRICTLIMIT 0x00000010 #define BDI_CAP_CGROUP_WRITEBACK 0x00000020 @@ -170,11 +169,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) long congestion_wait(int sync, long timeout); long wait_iff_congested(int sync, long timeout); -static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi) -{ - return bdi->capabilities & BDI_CAP_STABLE_WRITES; -} - static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi) { return !(bdi->capabilities & BDI_CAP_NO_WRITEBACK); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 282f5ca424f1..8e77f12de522 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -606,6 +606,7 @@ struct request_queue { #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ +#define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ #define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ #define QUEUE_FLAG_WC 17 /* Write back caching */ #define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ @@ -635,6 +636,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_noxmerges(q) \ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) +#define blk_queue_stable_writes(q) \ + test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) diff --git a/include/linux/fs.h b/include/linux/fs.h index fbd74df5ce5f..222465b7cf41 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1385,6 +1385,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ +#define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 2dac3be61271..8e3802bf03a9 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -204,10 +204,9 @@ static ssize_t stable_pages_required_show(struct device *dev, struct device_attribute *attr, char *page) { - struct backing_dev_info *bdi = dev_get_drvdata(dev); - - return snprintf(page, PAGE_SIZE-1, "%d\n", - bdi_cap_stable_pages_required(bdi) ? 1 : 0); + dev_warn_once(dev, + "the stable_pages_required attribute has been removed. Use the stable_writes queue attribute instead.\n"); + return snprintf(page, PAGE_SIZE-1, "%d\n", 0); } static DEVICE_ATTR_RO(stable_pages_required); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 4e4ddd67b71e..e9c36521461a 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2849,7 +2849,7 @@ EXPORT_SYMBOL_GPL(wait_on_page_writeback); */ void wait_for_stable_page(struct page *page) { - if (bdi_cap_stable_pages_required(inode_to_bdi(page->mapping->host))) + if (page->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES) wait_on_page_writeback(page); } EXPORT_SYMBOL_GPL(wait_for_stable_page); diff --git a/mm/swapfile.c b/mm/swapfile.c index 96a7c47dd533..65ef407512b5 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3237,7 +3237,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) goto bad_swap_unlock_inode; } - if (bdi_cap_stable_pages_required(inode_to_bdi(inode))) + if (p->bdev && blk_queue_stable_writes(p->bdev->bd_disk->queue)) p->flags |= SWP_STABLE_WRITES; if (p->bdev && p->bdev->bd_disk->fops->rw_page) -- cgit v1.2.3 From 823423ef55f4d9c470b1edc9c5b5c93d06abfaae Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:39 +0200 Subject: bdi: invert BDI_CAP_NO_ACCT_WB Replace BDI_CAP_NO_ACCT_WB with a positive BDI_CAP_WRITEBACK_ACCT to make the checks more obvious. Also remove the pointless bdi_cap_account_writeback wrapper that just obsfucates the check. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- fs/fuse/inode.c | 3 ++- include/linux/backing-dev.h | 13 +++---------- mm/backing-dev.c | 1 + mm/page-writeback.c | 4 ++-- 4 files changed, 8 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 17b00670fb53..581329203d68 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1050,7 +1050,8 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb) return err; /* fuse does it's own writeback accounting */ - sb->s_bdi->capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT; + sb->s_bdi->capabilities &= ~BDI_CAP_WRITEBACK_ACCT; + sb->s_bdi->capabilities |= BDI_CAP_STRICTLIMIT; /* * For a single fuse filesystem use max 1% of dirty + diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 5da4ea3dd0cc..b217344a2c63 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -120,17 +120,17 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * * BDI_CAP_NO_ACCT_DIRTY: Dirty pages shouldn't contribute to accounting * BDI_CAP_NO_WRITEBACK: Don't write pages back - * BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages + * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 -#define BDI_CAP_NO_ACCT_WB 0x00000004 +#define BDI_CAP_WRITEBACK_ACCT 0x00000004 #define BDI_CAP_STRICTLIMIT 0x00000010 #define BDI_CAP_CGROUP_WRITEBACK 0x00000020 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ - (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) + (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY) extern struct backing_dev_info noop_backing_dev_info; @@ -179,13 +179,6 @@ static inline bool bdi_cap_account_dirty(struct backing_dev_info *bdi) return !(bdi->capabilities & BDI_CAP_NO_ACCT_DIRTY); } -static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi) -{ - /* Paranoia: BDI_CAP_NO_WRITEBACK implies BDI_CAP_NO_ACCT_WB */ - return !(bdi->capabilities & (BDI_CAP_NO_ACCT_WB | - BDI_CAP_NO_WRITEBACK)); -} - static inline bool mapping_cap_writeback_dirty(struct address_space *mapping) { return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host)); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 8e3802bf03a9..df18f0088dd3 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -745,6 +745,7 @@ struct backing_dev_info *bdi_alloc(int node_id) kfree(bdi); return NULL; } + bdi->capabilities = BDI_CAP_WRITEBACK_ACCT; bdi->ra_pages = VM_READAHEAD_PAGES; bdi->io_pages = VM_READAHEAD_PAGES; return bdi; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index e9c36521461a..0139f9622a92 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2738,7 +2738,7 @@ int test_clear_page_writeback(struct page *page) if (ret) { __xa_clear_mark(&mapping->i_pages, page_index(page), PAGECACHE_TAG_WRITEBACK); - if (bdi_cap_account_writeback(bdi)) { + if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); dec_wb_stat(wb, WB_WRITEBACK); @@ -2791,7 +2791,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) PAGECACHE_TAG_WRITEBACK); xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); - if (bdi_cap_account_writeback(bdi)) + if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); /* -- cgit v1.2.3 From f56753ac2a90810726334df04d735e9f8f5a32d9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 08:51:40 +0200 Subject: bdi: replace BDI_CAP_NO_{WRITEBACK,ACCT_DIRTY} with a single flag Replace the two negative flags that are always used together with a single positive flag that indicates the writeback capability instead of two related non-capabilities. Also remove the pointless wrappers to just check the flag. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- fs/9p/vfs_file.c | 2 +- fs/fs-writeback.c | 7 ++++--- include/linux/backing-dev.h | 48 ++++++++++----------------------------------- mm/backing-dev.c | 6 ++---- mm/filemap.c | 4 ++-- mm/memcontrol.c | 2 +- mm/memory-failure.c | 2 +- mm/migrate.c | 2 +- mm/mmap.c | 2 +- mm/page-writeback.c | 12 ++++++------ 10 files changed, 29 insertions(+), 58 deletions(-) (limited to 'include') diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 3576123d8299..6ecf863bfa2f 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -625,7 +625,7 @@ static void v9fs_mmap_vm_close(struct vm_area_struct *vma) inode = file_inode(vma->vm_file); - if (!mapping_cap_writeback_dirty(inode->i_mapping)) + if (!mapping_can_writeback(inode->i_mapping)) wbc.nr_to_write = 0; might_sleep(); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 149227160ff0..d4f84a2fe087 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2321,7 +2321,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) wb = locked_inode_to_wb_and_lock_list(inode); - WARN(bdi_cap_writeback_dirty(wb->bdi) && + WARN((wb->bdi->capabilities & BDI_CAP_WRITEBACK) && !test_bit(WB_registered, &wb->state), "bdi-%s not registered\n", bdi_dev_name(wb->bdi)); @@ -2346,7 +2346,8 @@ void __mark_inode_dirty(struct inode *inode, int flags) * to make sure background write-back happens * later. */ - if (bdi_cap_writeback_dirty(wb->bdi) && wakeup_bdi) + if (wakeup_bdi && + (wb->bdi->capabilities & BDI_CAP_WRITEBACK)) wb_wakeup_delayed(wb); return; } @@ -2581,7 +2582,7 @@ int write_inode_now(struct inode *inode, int sync) .range_end = LLONG_MAX, }; - if (!mapping_cap_writeback_dirty(inode->i_mapping)) + if (!mapping_can_writeback(inode->i_mapping)) wbc.nr_to_write = 0; might_sleep(); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index b217344a2c63..44df4fcef65c 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -110,27 +110,14 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); /* * Flags in backing_dev_info::capability * - * The first three flags control whether dirty pages will contribute to the - * VM's accounting and whether writepages() should be called for dirty pages - * (something that would not, for example, be appropriate for ramfs) - * - * WARNING: these flags are closely related and should not normally be - * used separately. The BDI_CAP_NO_ACCT_AND_WRITEBACK combines these - * three flags into a single convenience macro. - * - * BDI_CAP_NO_ACCT_DIRTY: Dirty pages shouldn't contribute to accounting - * BDI_CAP_NO_WRITEBACK: Don't write pages back - * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages - * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. + * BDI_CAP_WRITEBACK: Supports dirty page writeback, and dirty pages + * should contribute to accounting + * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages + * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold */ -#define BDI_CAP_NO_ACCT_DIRTY 0x00000001 -#define BDI_CAP_NO_WRITEBACK 0x00000002 -#define BDI_CAP_WRITEBACK_ACCT 0x00000004 -#define BDI_CAP_STRICTLIMIT 0x00000010 -#define BDI_CAP_CGROUP_WRITEBACK 0x00000020 - -#define BDI_CAP_NO_ACCT_AND_WRITEBACK \ - (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY) +#define BDI_CAP_WRITEBACK (1 << 0) +#define BDI_CAP_WRITEBACK_ACCT (1 << 1) +#define BDI_CAP_STRICTLIMIT (1 << 2) extern struct backing_dev_info noop_backing_dev_info; @@ -169,24 +156,9 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) long congestion_wait(int sync, long timeout); long wait_iff_congested(int sync, long timeout); -static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi) -{ - return !(bdi->capabilities & BDI_CAP_NO_WRITEBACK); -} - -static inline bool bdi_cap_account_dirty(struct backing_dev_info *bdi) -{ - return !(bdi->capabilities & BDI_CAP_NO_ACCT_DIRTY); -} - -static inline bool mapping_cap_writeback_dirty(struct address_space *mapping) -{ - return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host)); -} - -static inline bool mapping_cap_account_dirty(struct address_space *mapping) +static inline bool mapping_can_writeback(struct address_space *mapping) { - return bdi_cap_account_dirty(inode_to_bdi(mapping->host)); + return inode_to_bdi(mapping->host)->capabilities & BDI_CAP_WRITEBACK; } static inline int bdi_sched_wait(void *word) @@ -223,7 +195,7 @@ static inline bool inode_cgwb_enabled(struct inode *inode) return cgroup_subsys_on_dfl(memory_cgrp_subsys) && cgroup_subsys_on_dfl(io_cgrp_subsys) && - bdi_cap_account_dirty(bdi) && + (bdi->capabilities & BDI_CAP_WRITEBACK) && (inode->i_sb->s_iflags & SB_I_CGROUPWB); } diff --git a/mm/backing-dev.c b/mm/backing-dev.c index df18f0088dd3..408d5051d05b 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -14,9 +14,7 @@ #include #include -struct backing_dev_info noop_backing_dev_info = { - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, -}; +struct backing_dev_info noop_backing_dev_info; EXPORT_SYMBOL_GPL(noop_backing_dev_info); static struct class *bdi_class; @@ -745,7 +743,7 @@ struct backing_dev_info *bdi_alloc(int node_id) kfree(bdi); return NULL; } - bdi->capabilities = BDI_CAP_WRITEBACK_ACCT; + bdi->capabilities = BDI_CAP_WRITEBACK | BDI_CAP_WRITEBACK_ACCT; bdi->ra_pages = VM_READAHEAD_PAGES; bdi->io_pages = VM_READAHEAD_PAGES; return bdi; diff --git a/mm/filemap.c b/mm/filemap.c index 1aaea26556cc..6c2a0139e22f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -414,7 +414,7 @@ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, .range_end = end, }; - if (!mapping_cap_writeback_dirty(mapping) || + if (!mapping_can_writeback(mapping) || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) return 0; @@ -1702,7 +1702,7 @@ repeat: no_page: if (!page && (fgp_flags & FGP_CREAT)) { int err; - if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping)) + if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) gfp_mask |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) gfp_mask &= ~__GFP_FS; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b807952b4d43..d2352f76d651 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5643,7 +5643,7 @@ static int mem_cgroup_move_account(struct page *page, if (PageDirty(page)) { struct address_space *mapping = page_mapping(page); - if (mapping_cap_account_dirty(mapping)) { + if (mapping_can_writeback(mapping)) { __mod_lruvec_state(from_vec, NR_FILE_DIRTY, -nr_pages); __mod_lruvec_state(to_vec, NR_FILE_DIRTY, diff --git a/mm/memory-failure.c b/mm/memory-failure.c index f1aa6433f404..a1e73943445e 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1006,7 +1006,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, */ mapping = page_mapping(hpage); if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping && - mapping_cap_writeback_dirty(mapping)) { + mapping_can_writeback(mapping)) { if (page_mkclean(hpage)) { SetPageDirty(hpage); } else { diff --git a/mm/migrate.c b/mm/migrate.c index 34a842a8eb6a..9d2f42a3a162 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -503,7 +503,7 @@ int migrate_page_move_mapping(struct address_space *mapping, __dec_lruvec_state(old_lruvec, NR_SHMEM); __inc_lruvec_state(new_lruvec, NR_SHMEM); } - if (dirty && mapping_cap_account_dirty(mapping)) { + if (dirty && mapping_can_writeback(mapping)) { __dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY); __dec_zone_state(oldzone, NR_ZONE_WRITE_PENDING); __inc_node_state(newzone->zone_pgdat, NR_FILE_DIRTY); diff --git a/mm/mmap.c b/mm/mmap.c index 40248d84ad5f..1fc0e92be4ba 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1666,7 +1666,7 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) /* Can the mapping track the dirty pages? */ return vma->vm_file && vma->vm_file->f_mapping && - mapping_cap_account_dirty(vma->vm_file->f_mapping); + mapping_can_writeback(vma->vm_file->f_mapping); } /* diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0139f9622a92..358d6f28c627 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1882,7 +1882,7 @@ void balance_dirty_pages_ratelimited(struct address_space *mapping) int ratelimit; int *p; - if (!bdi_cap_account_dirty(bdi)) + if (!(bdi->capabilities & BDI_CAP_WRITEBACK)) return; if (inode_cgwb_enabled(inode)) @@ -2423,7 +2423,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) trace_writeback_dirty_page(page, mapping); - if (mapping_cap_account_dirty(mapping)) { + if (mapping_can_writeback(mapping)) { struct bdi_writeback *wb; inode_attach_wb(inode, page); @@ -2450,7 +2450,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) void account_page_cleaned(struct page *page, struct address_space *mapping, struct bdi_writeback *wb) { - if (mapping_cap_account_dirty(mapping)) { + if (mapping_can_writeback(mapping)) { dec_lruvec_page_state(page, NR_FILE_DIRTY); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); dec_wb_stat(wb, WB_RECLAIMABLE); @@ -2513,7 +2513,7 @@ void account_page_redirty(struct page *page) { struct address_space *mapping = page->mapping; - if (mapping && mapping_cap_account_dirty(mapping)) { + if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; @@ -2625,7 +2625,7 @@ void __cancel_dirty_page(struct page *page) { struct address_space *mapping = page_mapping(page); - if (mapping_cap_account_dirty(mapping)) { + if (mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; @@ -2665,7 +2665,7 @@ int clear_page_dirty_for_io(struct page *page) VM_BUG_ON_PAGE(!PageLocked(page), page); - if (mapping && mapping_cap_account_dirty(mapping)) { + if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; -- cgit v1.2.3 From fa01b1e9733fd59ecb8b5b6d85dfb481d2025fbf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Sep 2020 07:40:57 +0200 Subject: block: add a bdev_is_partition helper Add a littler helper to make the somewhat arcane bd_contains checks a little more obvious. Signed-off-by: Christoph Hellwig Acked-by: Ulf Hansson Signed-off-by: Jens Axboe --- block/blk-lib.c | 2 +- block/ioctl.c | 4 ++-- block/scsi_ioctl.c | 2 +- drivers/ide/ide-ioctls.c | 4 ++-- drivers/md/dm-table.c | 2 +- drivers/mmc/core/block.c | 2 +- drivers/s390/block/dasd_ioctl.c | 8 ++++---- fs/nfsd/blocklayout.c | 4 ++-- include/linux/blkdev.h | 9 +++++++-- kernel/trace/blktrace.c | 2 +- 10 files changed, 22 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/block/blk-lib.c b/block/blk-lib.c index 0d1811e57ac7..e90614fd8d6a 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -64,7 +64,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, return -EINVAL; /* In case the discard request is in a partition */ - if (bdev->bd_partno) + if (bdev_is_partition(bdev)) part_offset = bdev->bd_part->start_sect; while (nr_sects) { diff --git a/block/ioctl.c b/block/ioctl.c index 06262c28f0c6..3fbc382eb926 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -23,7 +23,7 @@ static int blkpg_do_ioctl(struct block_device *bdev, return -EACCES; if (copy_from_user(&p, upart, sizeof(struct blkpg_partition))) return -EFAULT; - if (bdev != bdev->bd_contains) + if (bdev_is_partition(bdev)) return -EINVAL; if (p.pno <= 0) @@ -94,7 +94,7 @@ static int blkdev_reread_part(struct block_device *bdev) { int ret; - if (!disk_part_scan_enabled(bdev->bd_disk) || bdev != bdev->bd_contains) + if (!disk_part_scan_enabled(bdev->bd_disk) || bdev_is_partition(bdev)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EACCES; diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 4421e61c1af1..d4abd1ed5a2d 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -852,7 +852,7 @@ EXPORT_SYMBOL(scsi_cmd_ioctl); int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd) { - if (bd && bd == bd->bd_contains) + if (bd && !bdev_is_partition(bd)) return 0; if (capable(CAP_SYS_RAWIO)) diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c index 09491098047b..58994da10c06 100644 --- a/drivers/ide/ide-ioctls.c +++ b/drivers/ide/ide-ioctls.c @@ -49,7 +49,7 @@ read_val: return err >= 0 ? put_user_long(err, arg) : err; set_val: - if (bdev != bdev->bd_contains) + if (bdev_is_partition(bdev)) err = -EINVAL; else { if (!capable(CAP_SYS_ADMIN)) @@ -257,7 +257,7 @@ int generic_ide_ioctl(ide_drive_t *drive, struct block_device *bdev, switch (cmd) { case HDIO_OBSOLETE_IDENTITY: case HDIO_GET_IDENTITY: - if (bdev != bdev->bd_contains) + if (bdev_is_partition(bdev)) return -EINVAL; return ide_get_identity_ioctl(drive, cmd, argp); case HDIO_GET_NICE: diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 405d7cf10eb9..12d909044c10 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -903,7 +903,7 @@ static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev, struct request_queue *q = bdev_get_queue(bdev); /* request-based cannot stack on partitions! */ - if (bdev != bdev->bd_contains) + if (bdev_is_partition(bdev)) return false; return queue_is_mq(q); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index fa313b634135..8d3df0be0355 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -723,7 +723,7 @@ static int mmc_blk_check_blkdev(struct block_device *bdev) * whole block device, not on a partition. This prevents overspray * between sibling partitions. */ - if ((!capable(CAP_SYS_RAWIO)) || (bdev != bdev->bd_contains)) + if (!capable(CAP_SYS_RAWIO) || bdev_is_partition(bdev)) return -EPERM; return 0; } diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index faaf5596e31c..cb6427fb9f3d 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -277,7 +277,7 @@ dasd_ioctl_format(struct block_device *bdev, void __user *argp) dasd_put_device(base); return -EFAULT; } - if (bdev != bdev->bd_contains) { + if (bdev_is_partition(bdev)) { pr_warn("%s: The specified DASD is a partition and cannot be formatted\n", dev_name(&base->cdev->dev)); dasd_put_device(base); @@ -304,7 +304,7 @@ static int dasd_ioctl_check_format(struct block_device *bdev, void __user *argp) base = dasd_device_from_gendisk(bdev->bd_disk); if (!base) return -ENODEV; - if (bdev != bdev->bd_contains) { + if (bdev_is_partition(bdev)) { pr_warn("%s: The specified DASD is a partition and cannot be checked\n", dev_name(&base->cdev->dev)); rc = -EINVAL; @@ -362,7 +362,7 @@ static int dasd_ioctl_release_space(struct block_device *bdev, void __user *argp rc = -EROFS; goto out_err; } - if (bdev != bdev->bd_contains) { + if (bdev_is_partition(bdev)) { pr_warn("%s: The specified DASD is a partition and tracks cannot be released\n", dev_name(&base->cdev->dev)); rc = -EINVAL; @@ -540,7 +540,7 @@ dasd_ioctl_set_ro(struct block_device *bdev, void __user *argp) if (!capable(CAP_SYS_ADMIN)) return -EACCES; - if (bdev != bdev->bd_contains) + if (bdev_is_partition(bdev)) // ro setting is not allowed for partitions return -EINVAL; if (get_user(intval, (int __user *)argp)) diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index 311e5ce80cfc..a07c39c94bbd 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -170,7 +170,7 @@ nfsd4_block_proc_getdeviceinfo(struct super_block *sb, struct nfs4_client *clp, struct nfsd4_getdeviceinfo *gdp) { - if (sb->s_bdev != sb->s_bdev->bd_contains) + if (bdev_is_partition(sb->s_bdev)) return nfserr_inval; return nfserrno(nfsd4_block_get_device_info_simple(sb, gdp)); } @@ -382,7 +382,7 @@ nfsd4_scsi_proc_getdeviceinfo(struct super_block *sb, struct nfs4_client *clp, struct nfsd4_getdeviceinfo *gdp) { - if (sb->s_bdev != sb->s_bdev->bd_contains) + if (bdev_is_partition(sb->s_bdev)) return nfserr_inval; return nfserrno(nfsd4_block_get_device_info_scsi(sb, clp, gdp)); } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8e77f12de522..33f283885ba5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1353,6 +1353,11 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, extern int blk_verify_command(unsigned char *cmd, fmode_t mode); +static inline bool bdev_is_partition(struct block_device *bdev) +{ + return bdev->bd_partno; +} + enum blk_default_limits { BLK_MAX_SEGMENTS = 128, BLK_SAFE_MAX_SECTORS = 255, @@ -1469,7 +1474,7 @@ static inline int bdev_alignment_offset(struct block_device *bdev) if (q->limits.misaligned) return -1; - if (bdev != bdev->bd_contains) + if (bdev_is_partition(bdev)) return queue_limit_alignment_offset(&q->limits, bdev->bd_part->start_sect); return q->limits.alignment_offset; @@ -1510,7 +1515,7 @@ static inline int bdev_discard_alignment(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); - if (bdev != bdev->bd_contains) + if (bdev_is_partition(bdev)) return queue_limit_discard_alignment(&q->limits, bdev->bd_part->start_sect); return q->limits.discard_alignment; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index c0887f32f647..ec874ea04092 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -527,7 +527,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, * and scsi-generic block devices we create a temporary new debugfs * directory that will be removed once the trace ends. */ - if (bdev && bdev == bdev->bd_contains) + if (bdev && !bdev_is_partition(bdev)) dir = q->debugfs_dir; else bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root); -- cgit v1.2.3 From 021a24460dc28e7412aecfae89f60e1847e685c0 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 23 Sep 2020 16:06:51 -0400 Subject: block: add QUEUE_FLAG_NOWAIT Add QUEUE_FLAG_NOWAIT to allow a block device to advertise support for REQ_NOWAIT. Bio-based devices may set QUEUE_FLAG_NOWAIT where applicable. Update QUEUE_FLAG_MQ_DEFAULT to include QUEUE_FLAG_NOWAIT. Also update submit_bio_checks() to verify it is set for REQ_NOWAIT bios. Reported-by: Konstantin Khlebnikov Suggested-by: Christoph Hellwig Signed-off-by: Mike Snitzer Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 4 ++-- include/linux/blkdev.h | 7 +++++-- 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/block/blk-core.c b/block/blk-core.c index 1cc4fa6bc7fe..4884f1e7451b 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -814,9 +814,9 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio) /* * For a REQ_NOWAIT based request, return -EOPNOTSUPP - * if queue is not a request based queue. + * if queue does not support NOWAIT. */ - if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) + if ((bio->bi_opf & REQ_NOWAIT) && !blk_queue_nowait(q)) goto not_supported; if (should_fail_bio(bio)) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 33f283885ba5..d5a3e1a4c2f7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -619,10 +619,12 @@ struct request_queue { #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ #define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ #define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ -#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ +#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ +#define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */ #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_SAME_COMP)) + (1 << QUEUE_FLAG_SAME_COMP) | \ + (1 << QUEUE_FLAG_NOWAIT)) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); @@ -664,6 +666,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) +#define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); -- cgit v1.2.3 From 6abc49468eeaad2dd481779906aaa29605139087 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 23 Sep 2020 16:06:52 -0400 Subject: dm: add support for REQ_NOWAIT and enable it for linear target Add DM target feature flag DM_TARGET_NOWAIT which advertises that target works with REQ_NOWAIT bios. Add dm_table_supports_nowait() and update dm_table_set_restrictions() to set/clear QUEUE_FLAG_NOWAIT accordingly. Signed-off-by: Konstantin Khlebnikov Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- drivers/md/dm-linear.c | 5 +++-- drivers/md/dm-table.c | 32 ++++++++++++++++++++++++++++++++ drivers/md/dm.c | 4 +++- include/linux/device-mapper.h | 6 ++++++ 4 files changed, 44 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index e1db43446327..00774b5d7668 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -228,10 +228,11 @@ static struct target_type linear_target = { .name = "linear", .version = {1, 4, 0}, #ifdef CONFIG_BLK_DEV_ZONED - .features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_ZONED_HM, + .features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT | + DM_TARGET_ZONED_HM, .report_zones = linear_report_zones, #else - .features = DM_TARGET_PASSES_INTEGRITY, + .features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT, #endif .module = THIS_MODULE, .ctr = linear_ctr, diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 12d909044c10..07c319e98581 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1748,6 +1748,33 @@ static bool dm_table_supports_write_zeroes(struct dm_table *t) return true; } +static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + struct request_queue *q = bdev_get_queue(dev->bdev); + + return q && !blk_queue_nowait(q); +} + +static bool dm_table_supports_nowait(struct dm_table *t) +{ + struct dm_target *ti; + unsigned i = 0; + + while (i < dm_table_get_num_targets(t)) { + ti = dm_table_get_target(t, i++); + + if (!dm_target_supports_nowait(ti->type)) + return false; + + if (!ti->type->iterate_devices || + ti->type->iterate_devices(ti, device_not_nowait_capable, NULL)) + return false; + } + + return true; +} + static int device_not_discard_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { @@ -1850,6 +1877,11 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, */ q->limits = *limits; + if (dm_table_supports_nowait(t)) + blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q); + else + blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q); + if (!dm_table_supports_discards(t)) { blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); /* Must also clear discard limits... */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 3dedd9cc4fb6..59b0687f9235 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1802,7 +1802,9 @@ static blk_qc_t dm_submit_bio(struct bio *bio) if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) { dm_put_live_table(md, srcu_idx); - if (!(bio->bi_opf & REQ_RAHEAD)) + if (bio->bi_opf & REQ_NOWAIT) + bio_wouldblock_error(bio); + else if (!(bio->bi_opf & REQ_RAHEAD)) queue_io(md, bio); else bio_io_error(bio); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 93096e524e43..d6f8d4ba8d48 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -252,6 +252,12 @@ struct target_type { #define DM_TARGET_ZONED_HM 0x00000040 #define dm_target_supports_zoned_hm(type) ((type)->features & DM_TARGET_ZONED_HM) +/* + * A target handles REQ_NOWAIT + */ +#define DM_TARGET_NOWAIT 0x00000080 +#define dm_target_supports_nowait(type) ((type)->features & DM_TARGET_NOWAIT) + struct dm_target { struct dm_table *table; struct target_type *type; -- cgit v1.2.3 From c5a6561b8d99ea7d8df21308249ce05bce3dd466 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 17 Sep 2020 20:44:56 -0400 Subject: iocost: add iocg_forgive_debt tracepoint Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-iocost.c | 12 ++++++++++++ include/trace/events/iocost.h | 41 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+) (limited to 'include') diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 9b1f94499432..328ae805e85f 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2046,12 +2046,24 @@ static void ioc_forgive_debts(struct ioc *ioc, u64 usage_us_sum, int nr_debtors, ioc->dfgv_period_rem = do_div(nr_cycles, DFGV_PERIOD); list_for_each_entry(iocg, &ioc->active_iocgs, active_list) { + u64 __maybe_unused old_debt, __maybe_unused old_delay; + if (!iocg->abs_vdebt) continue; + spin_lock(&iocg->waitq.lock); + + old_debt = iocg->abs_vdebt; + old_delay = iocg->delay; + iocg->abs_vdebt >>= nr_cycles; iocg->delay = 0; /* kick_waitq will recalc */ iocg_kick_waitq(iocg, true, now); + + TRACE_IOCG_PATH(iocg_forgive_debt, iocg, now, usage_pct, + old_debt, iocg->abs_vdebt, + old_delay, iocg->delay); + spin_unlock(&iocg->waitq.lock); } } diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h index b350860d2e71..0b6869980ba2 100644 --- a/include/trace/events/iocost.h +++ b/include/trace/events/iocost.h @@ -164,6 +164,47 @@ TRACE_EVENT(iocost_ioc_vrate_adj, ) ); +TRACE_EVENT(iocost_iocg_forgive_debt, + + TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now, + u32 usage_pct, u64 old_debt, u64 new_debt, + u64 old_delay, u64 new_delay), + + TP_ARGS(iocg, path, now, usage_pct, + old_debt, new_debt, old_delay, new_delay), + + TP_STRUCT__entry ( + __string(devname, ioc_name(iocg->ioc)) + __string(cgroup, path) + __field(u64, now) + __field(u64, vnow) + __field(u32, usage_pct) + __field(u64, old_debt) + __field(u64, new_debt) + __field(u64, old_delay) + __field(u64, new_delay) + ), + + TP_fast_assign( + __assign_str(devname, ioc_name(iocg->ioc)); + __assign_str(cgroup, path); + __entry->now = now->now; + __entry->vnow = now->vnow; + __entry->usage_pct = usage_pct; + __entry->old_debt = old_debt; + __entry->new_debt = new_debt; + __entry->old_delay = old_delay; + __entry->new_delay = new_delay; + ), + + TP_printk("[%s:%s] now=%llu:%llu usage=%u debt=%llu->%llu delay=%llu->%llu", + __get_str(devname), __get_str(cgroup), + __entry->now, __entry->vnow, __entry->usage_pct, + __entry->old_debt, __entry->new_debt, + __entry->old_delay, __entry->new_delay + ) +); + #endif /* _TRACE_BLK_IOCOST_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 10ed16662da9e28a33b6c991c36c6b323b03dd5b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 25 Sep 2020 18:06:18 +0200 Subject: block: add a bdget_part helper All remaining callers of bdget() outside of fs/block_dev.c want to get a reference to the struct block_device for a given struct hd_struct. Add a helper just for that and then mark bdget static. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/genhd.c | 2 +- block/partitions/core.c | 2 +- fs/block_dev.c | 9 ++++++--- include/linux/blkdev.h | 2 +- kernel/trace/blktrace.c | 9 ++------- 5 files changed, 11 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/block/genhd.c b/block/genhd.c index e5f17f022ec7..0a273211fec2 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1048,7 +1048,7 @@ struct block_device *bdget_disk(struct gendisk *disk, int partno) part = disk_get_part(disk, partno); if (part) - bdev = bdget(part_devt(part)); + bdev = bdget_part(part); disk_put_part(part); return bdev; diff --git a/block/partitions/core.c b/block/partitions/core.c index dd6811422a87..5309e0f44ba3 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -580,7 +580,7 @@ int bdev_resize_partition(struct block_device *bdev, int partno, return -ENXIO; ret = -ENOMEM; - bdevp = bdget(part_devt(part)); + bdevp = bdget_part(part); if (!bdevp) goto out_put_part; diff --git a/fs/block_dev.c b/fs/block_dev.c index 6b9d19ffa5af..9e84b1928b94 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -891,7 +891,7 @@ static int bdev_set(struct inode *inode, void *data) return 0; } -struct block_device *bdget(dev_t dev) +static struct block_device *bdget(dev_t dev) { struct block_device *bdev; struct inode *inode; @@ -920,8 +920,6 @@ struct block_device *bdget(dev_t dev) return bdev; } -EXPORT_SYMBOL(bdget); - /** * bdgrab -- Grab a reference to an already referenced block device * @bdev: Block device to grab a reference to. @@ -933,6 +931,11 @@ struct block_device *bdgrab(struct block_device *bdev) } EXPORT_SYMBOL(bdgrab); +struct block_device *bdget_part(struct hd_struct *part) +{ + return bdget(part_devt(part)); +} + long nr_blockdev_pages(void) { struct inode *inode; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d5a3e1a4c2f7..cf80e61b4c5e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -2003,7 +2003,7 @@ void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, void blkdev_put(struct block_device *bdev, fmode_t mode); struct block_device *I_BDEV(struct inode *inode); -struct block_device *bdget(dev_t); +struct block_device *bdget_part(struct hd_struct *part); struct block_device *bdgrab(struct block_device *bdev); void bdput(struct block_device *); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index ec874ea04092..f1022945e346 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1827,13 +1827,11 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct hd_struct *p = dev_to_part(dev); + struct block_device *bdev = bdget_part(dev_to_part(dev)); struct request_queue *q; - struct block_device *bdev; struct blk_trace *bt; ssize_t ret = -ENXIO; - bdev = bdget(part_devt(p)); if (bdev == NULL) goto out; @@ -1875,7 +1873,6 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, { struct block_device *bdev; struct request_queue *q; - struct hd_struct *p; struct blk_trace *bt; u64 value; ssize_t ret = -EINVAL; @@ -1895,9 +1892,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, goto out; ret = -ENXIO; - - p = dev_to_part(dev); - bdev = bdget(part_devt(p)); + bdev = bdget_part(dev_to_part(dev)); if (bdev == NULL) goto out; -- cgit v1.2.3 From 07560151db960d26b425410d6fd778e6757a5da2 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 15 Sep 2020 20:53:13 -0700 Subject: block: make bio_crypt_clone() able to fail bio_crypt_clone() assumes its gfp_mask argument always includes __GFP_DIRECT_RECLAIM, so that the mempool_alloc() will always succeed. However, bio_crypt_clone() might be called with GFP_ATOMIC via setup_clone() in drivers/md/dm-rq.c, or with GFP_NOWAIT via kcryptd_io_read() in drivers/md/dm-crypt.c. Neither case is currently reachable with a bio that actually has an encryption context. However, it's fragile to rely on this. Just make bio_crypt_clone() able to fail, analogous to bio_integrity_clone(). Reported-by: Miaohe Lin Signed-off-by: Eric Biggers Reviewed-by: Mike Snitzer Reviewed-by: Satya Tangirala Cc: Satya Tangirala Signed-off-by: Jens Axboe --- block/bio.c | 20 +++++++++----------- block/blk-crypto.c | 5 ++++- block/bounce.c | 19 +++++++++---------- drivers/md/dm.c | 7 ++++--- include/linux/blk-crypto.h | 20 ++++++++++++++++---- 5 files changed, 42 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/block/bio.c b/block/bio.c index a9931f23d933..b42e046b12eb 100644 --- a/block/bio.c +++ b/block/bio.c @@ -713,20 +713,18 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs) __bio_clone_fast(b, bio); - bio_crypt_clone(b, bio, gfp_mask); + if (bio_crypt_clone(b, bio, gfp_mask) < 0) + goto err_put; - if (bio_integrity(bio)) { - int ret; - - ret = bio_integrity_clone(b, bio, gfp_mask); - - if (ret < 0) { - bio_put(b); - return NULL; - } - } + if (bio_integrity(bio) && + bio_integrity_clone(b, bio, gfp_mask) < 0) + goto err_put; return b; + +err_put: + bio_put(b); + return NULL; } EXPORT_SYMBOL(bio_clone_fast); diff --git a/block/blk-crypto.c b/block/blk-crypto.c index 2d5e60023b08..a3f27a19067c 100644 --- a/block/blk-crypto.c +++ b/block/blk-crypto.c @@ -95,10 +95,13 @@ void __bio_crypt_free_ctx(struct bio *bio) bio->bi_crypt_context = NULL; } -void __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask) +int __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask) { dst->bi_crypt_context = mempool_alloc(bio_crypt_ctx_pool, gfp_mask); + if (!dst->bi_crypt_context) + return -ENOMEM; *dst->bi_crypt_context = *src->bi_crypt_context; + return 0; } EXPORT_SYMBOL_GPL(__bio_crypt_clone); diff --git a/block/bounce.c b/block/bounce.c index 431be88a0240..162a6eee8999 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -267,22 +267,21 @@ static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask, break; } - bio_crypt_clone(bio, bio_src, gfp_mask); + if (bio_crypt_clone(bio, bio_src, gfp_mask) < 0) + goto err_put; - if (bio_integrity(bio_src)) { - int ret; - - ret = bio_integrity_clone(bio, bio_src, gfp_mask); - if (ret < 0) { - bio_put(bio); - return NULL; - } - } + if (bio_integrity(bio_src) && + bio_integrity_clone(bio, bio_src, gfp_mask) < 0) + goto err_put; bio_clone_blkg_association(bio, bio_src); blkcg_bio_issue_init(bio); return bio; + +err_put: + bio_put(bio); + return NULL; } static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 59b0687f9235..e959cd74cd4b 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1326,14 +1326,15 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio, sector_t sector, unsigned len) { struct bio *clone = &tio->clone; + int r; __bio_clone_fast(clone, bio); - bio_crypt_clone(clone, bio, GFP_NOIO); + r = bio_crypt_clone(clone, bio, GFP_NOIO); + if (r < 0) + return r; if (bio_integrity(bio)) { - int r; - if (unlikely(!dm_target_has_integrity(tio->ti->type) && !dm_target_passes_integrity(tio->ti->type))) { DMWARN("%s: the target %s doesn't support integrity data.", diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h index e82342907f2b..69b24fe92cbf 100644 --- a/include/linux/blk-crypto.h +++ b/include/linux/blk-crypto.h @@ -112,12 +112,24 @@ static inline bool bio_has_crypt_ctx(struct bio *bio) #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ -void __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask); -static inline void bio_crypt_clone(struct bio *dst, struct bio *src, - gfp_t gfp_mask) +int __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask); +/** + * bio_crypt_clone - clone bio encryption context + * @dst: destination bio + * @src: source bio + * @gfp_mask: memory allocation flags + * + * If @src has an encryption context, clone it to @dst. + * + * Return: 0 on success, -ENOMEM if out of memory. -ENOMEM is only possible if + * @gfp_mask doesn't include %__GFP_DIRECT_RECLAIM. + */ +static inline int bio_crypt_clone(struct bio *dst, struct bio *src, + gfp_t gfp_mask) { if (bio_has_crypt_ctx(src)) - __bio_crypt_clone(dst, src, gfp_mask); + return __bio_crypt_clone(dst, src, gfp_mask); + return 0; } #endif /* __LINUX_BLK_CRYPTO_H */ -- cgit v1.2.3 From 2b0d3d3e4fcfb19d10f9a82910b8f0f05c56ee3e Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 1 Oct 2020 23:48:41 +0800 Subject: percpu_ref: reduce memory footprint of percpu_ref in fast path 'struct percpu_ref' is often embedded into one user structure, and the instance is usually referenced in fast path, however actually only 'percpu_count_ptr' is needed in fast path. So move other fields into one new structure of 'percpu_ref_data', and allocate it dynamically via kzalloc(), then memory footprint of 'percpu_ref' in fast path is reduced a lot and becomes suitable to put into hot cacheline of user structure. Signed-off-by: Ming Lei Tested-by: Veronika Kabatova Reviewed-by: Christoph Hellwig Acked-by: Tejun Heo Cc: Sagi Grimberg Cc: Tejun Heo Cc: Christoph Hellwig Cc: Jens Axboe Cc: Bart Van Assche Signed-off-by: Jens Axboe --- drivers/infiniband/sw/rdmavt/mr.c | 2 +- include/linux/percpu-refcount.h | 52 +++++++-------- lib/percpu-refcount.c | 131 ++++++++++++++++++++++++++++---------- 3 files changed, 123 insertions(+), 62 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c index 2f7c25fea44a..8490fdb9c91e 100644 --- a/drivers/infiniband/sw/rdmavt/mr.c +++ b/drivers/infiniband/sw/rdmavt/mr.c @@ -499,7 +499,7 @@ static int rvt_check_refs(struct rvt_mregion *mr, const char *t) rvt_pr_err(rdi, "%s timeout mr %p pd %p lkey %x refcount %ld\n", t, mr, mr->pd, mr->lkey, - atomic_long_read(&mr->refcount.count)); + atomic_long_read(&mr->refcount.data->count)); rvt_get_mr(mr); return -EBUSY; } diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 87d8a38bdea1..16c35a728b4c 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -92,18 +92,30 @@ enum { PERCPU_REF_ALLOW_REINIT = 1 << 2, }; -struct percpu_ref { +struct percpu_ref_data { atomic_long_t count; - /* - * The low bit of the pointer indicates whether the ref is in percpu - * mode; if set, then get/put will manipulate the atomic_t. - */ - unsigned long percpu_count_ptr; percpu_ref_func_t *release; percpu_ref_func_t *confirm_switch; bool force_atomic:1; bool allow_reinit:1; struct rcu_head rcu; + struct percpu_ref *ref; +}; + +struct percpu_ref { + /* + * The low bit of the pointer indicates whether the ref is in percpu + * mode; if set, then get/put will manipulate the atomic_t. + */ + unsigned long percpu_count_ptr; + + /* + * 'percpu_ref' is often embedded into user structure, and only + * 'percpu_count_ptr' is required in fast path, move other fields + * into 'percpu_ref_data', so we can reduce memory footprint in + * fast path. + */ + struct percpu_ref_data *data; }; int __must_check percpu_ref_init(struct percpu_ref *ref, @@ -118,6 +130,7 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); void percpu_ref_resurrect(struct percpu_ref *ref); void percpu_ref_reinit(struct percpu_ref *ref); +bool percpu_ref_is_zero(struct percpu_ref *ref); /** * percpu_ref_kill - drop the initial ref @@ -191,7 +204,7 @@ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr) if (__ref_is_percpu(ref, &percpu_count)) this_cpu_add(*percpu_count, nr); else - atomic_long_add(nr, &ref->count); + atomic_long_add(nr, &ref->data->count); rcu_read_unlock(); } @@ -231,7 +244,7 @@ static inline bool percpu_ref_tryget_many(struct percpu_ref *ref, this_cpu_add(*percpu_count, nr); ret = true; } else { - ret = atomic_long_add_unless(&ref->count, nr, 0); + ret = atomic_long_add_unless(&ref->data->count, nr, 0); } rcu_read_unlock(); @@ -279,7 +292,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) this_cpu_inc(*percpu_count); ret = true; } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { - ret = atomic_long_inc_not_zero(&ref->count); + ret = atomic_long_inc_not_zero(&ref->data->count); } rcu_read_unlock(); @@ -305,8 +318,8 @@ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr) if (__ref_is_percpu(ref, &percpu_count)) this_cpu_sub(*percpu_count, nr); - else if (unlikely(atomic_long_sub_and_test(nr, &ref->count))) - ref->release(ref); + else if (unlikely(atomic_long_sub_and_test(nr, &ref->data->count))) + ref->data->release(ref); rcu_read_unlock(); } @@ -339,21 +352,4 @@ static inline bool percpu_ref_is_dying(struct percpu_ref *ref) return ref->percpu_count_ptr & __PERCPU_REF_DEAD; } -/** - * percpu_ref_is_zero - test whether a percpu refcount reached zero - * @ref: percpu_ref to test - * - * Returns %true if @ref reached zero. - * - * This function is safe to call as long as @ref is between init and exit. - */ -static inline bool percpu_ref_is_zero(struct percpu_ref *ref) -{ - unsigned long __percpu *percpu_count; - - if (__ref_is_percpu(ref, &percpu_count)) - return false; - return !atomic_long_read(&ref->count); -} - #endif diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c index 0ba686b8fe57..b6350d13538a 100644 --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -4,6 +4,7 @@ #include #include #include +#include #include /* @@ -64,18 +65,25 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, size_t align = max_t(size_t, 1 << __PERCPU_REF_FLAG_BITS, __alignof__(unsigned long)); unsigned long start_count = 0; + struct percpu_ref_data *data; ref->percpu_count_ptr = (unsigned long) __alloc_percpu_gfp(sizeof(unsigned long), align, gfp); if (!ref->percpu_count_ptr) return -ENOMEM; - ref->force_atomic = flags & PERCPU_REF_INIT_ATOMIC; - ref->allow_reinit = flags & PERCPU_REF_ALLOW_REINIT; + data = kzalloc(sizeof(*ref->data), gfp); + if (!data) { + free_percpu((void __percpu *)ref->percpu_count_ptr); + return -ENOMEM; + } + + data->force_atomic = flags & PERCPU_REF_INIT_ATOMIC; + data->allow_reinit = flags & PERCPU_REF_ALLOW_REINIT; if (flags & (PERCPU_REF_INIT_ATOMIC | PERCPU_REF_INIT_DEAD)) { ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC; - ref->allow_reinit = true; + data->allow_reinit = true; } else { start_count += PERCPU_COUNT_BIAS; } @@ -85,14 +93,28 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, else start_count++; - atomic_long_set(&ref->count, start_count); + atomic_long_set(&data->count, start_count); - ref->release = release; - ref->confirm_switch = NULL; + data->release = release; + data->confirm_switch = NULL; + data->ref = ref; + ref->data = data; return 0; } EXPORT_SYMBOL_GPL(percpu_ref_init); +static void __percpu_ref_exit(struct percpu_ref *ref) +{ + unsigned long __percpu *percpu_count = percpu_count_ptr(ref); + + if (percpu_count) { + /* non-NULL confirm_switch indicates switching in progress */ + WARN_ON_ONCE(ref->data->confirm_switch); + free_percpu(percpu_count); + ref->percpu_count_ptr = __PERCPU_REF_ATOMIC_DEAD; + } +} + /** * percpu_ref_exit - undo percpu_ref_init() * @ref: percpu_ref to exit @@ -105,27 +127,36 @@ EXPORT_SYMBOL_GPL(percpu_ref_init); */ void percpu_ref_exit(struct percpu_ref *ref) { - unsigned long __percpu *percpu_count = percpu_count_ptr(ref); + struct percpu_ref_data *data = ref->data; + unsigned long flags; - if (percpu_count) { - /* non-NULL confirm_switch indicates switching in progress */ - WARN_ON_ONCE(ref->confirm_switch); - free_percpu(percpu_count); - ref->percpu_count_ptr = __PERCPU_REF_ATOMIC_DEAD; - } + __percpu_ref_exit(ref); + + if (!data) + return; + + spin_lock_irqsave(&percpu_ref_switch_lock, flags); + ref->percpu_count_ptr |= atomic_long_read(&ref->data->count) << + __PERCPU_REF_FLAG_BITS; + ref->data = NULL; + spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); + + kfree(data); } EXPORT_SYMBOL_GPL(percpu_ref_exit); static void percpu_ref_call_confirm_rcu(struct rcu_head *rcu) { - struct percpu_ref *ref = container_of(rcu, struct percpu_ref, rcu); + struct percpu_ref_data *data = container_of(rcu, + struct percpu_ref_data, rcu); + struct percpu_ref *ref = data->ref; - ref->confirm_switch(ref); - ref->confirm_switch = NULL; + data->confirm_switch(ref); + data->confirm_switch = NULL; wake_up_all(&percpu_ref_switch_waitq); - if (!ref->allow_reinit) - percpu_ref_exit(ref); + if (!data->allow_reinit) + __percpu_ref_exit(ref); /* drop ref from percpu_ref_switch_to_atomic() */ percpu_ref_put(ref); @@ -133,7 +164,9 @@ static void percpu_ref_call_confirm_rcu(struct rcu_head *rcu) static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu) { - struct percpu_ref *ref = container_of(rcu, struct percpu_ref, rcu); + struct percpu_ref_data *data = container_of(rcu, + struct percpu_ref_data, rcu); + struct percpu_ref *ref = data->ref; unsigned long __percpu *percpu_count = percpu_count_ptr(ref); unsigned long count = 0; int cpu; @@ -142,7 +175,7 @@ static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu) count += *per_cpu_ptr(percpu_count, cpu); pr_debug("global %lu percpu %lu\n", - atomic_long_read(&ref->count), count); + atomic_long_read(&data->count), count); /* * It's crucial that we sum the percpu counters _before_ adding the sum @@ -156,11 +189,11 @@ static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu) * reaching 0 before we add the percpu counts. But doing it at the same * time is equivalent and saves us atomic operations: */ - atomic_long_add((long)count - PERCPU_COUNT_BIAS, &ref->count); + atomic_long_add((long)count - PERCPU_COUNT_BIAS, &data->count); - WARN_ONCE(atomic_long_read(&ref->count) <= 0, + WARN_ONCE(atomic_long_read(&data->count) <= 0, "percpu ref (%ps) <= 0 (%ld) after switching to atomic", - ref->release, atomic_long_read(&ref->count)); + data->release, atomic_long_read(&data->count)); /* @ref is viewed as dead on all CPUs, send out switch confirmation */ percpu_ref_call_confirm_rcu(rcu); @@ -186,10 +219,11 @@ static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref, * Non-NULL ->confirm_switch is used to indicate that switching is * in progress. Use noop one if unspecified. */ - ref->confirm_switch = confirm_switch ?: percpu_ref_noop_confirm_switch; + ref->data->confirm_switch = confirm_switch ?: + percpu_ref_noop_confirm_switch; percpu_ref_get(ref); /* put after confirmation */ - call_rcu(&ref->rcu, percpu_ref_switch_to_atomic_rcu); + call_rcu(&ref->data->rcu, percpu_ref_switch_to_atomic_rcu); } static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref) @@ -202,10 +236,10 @@ static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref) if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC)) return; - if (WARN_ON_ONCE(!ref->allow_reinit)) + if (WARN_ON_ONCE(!ref->data->allow_reinit)) return; - atomic_long_add(PERCPU_COUNT_BIAS, &ref->count); + atomic_long_add(PERCPU_COUNT_BIAS, &ref->data->count); /* * Restore per-cpu operation. smp_store_release() is paired @@ -223,6 +257,8 @@ static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref) static void __percpu_ref_switch_mode(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch) { + struct percpu_ref_data *data = ref->data; + lockdep_assert_held(&percpu_ref_switch_lock); /* @@ -230,10 +266,10 @@ static void __percpu_ref_switch_mode(struct percpu_ref *ref, * its completion. If the caller ensures that ATOMIC switching * isn't in progress, this function can be called from any context. */ - wait_event_lock_irq(percpu_ref_switch_waitq, !ref->confirm_switch, + wait_event_lock_irq(percpu_ref_switch_waitq, !data->confirm_switch, percpu_ref_switch_lock); - if (ref->force_atomic || (ref->percpu_count_ptr & __PERCPU_REF_DEAD)) + if (data->force_atomic || (ref->percpu_count_ptr & __PERCPU_REF_DEAD)) __percpu_ref_switch_to_atomic(ref, confirm_switch); else __percpu_ref_switch_to_percpu(ref); @@ -266,7 +302,7 @@ void percpu_ref_switch_to_atomic(struct percpu_ref *ref, spin_lock_irqsave(&percpu_ref_switch_lock, flags); - ref->force_atomic = true; + ref->data->force_atomic = true; __percpu_ref_switch_mode(ref, confirm_switch); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); @@ -284,7 +320,7 @@ EXPORT_SYMBOL_GPL(percpu_ref_switch_to_atomic); void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref) { percpu_ref_switch_to_atomic(ref, NULL); - wait_event(percpu_ref_switch_waitq, !ref->confirm_switch); + wait_event(percpu_ref_switch_waitq, !ref->data->confirm_switch); } EXPORT_SYMBOL_GPL(percpu_ref_switch_to_atomic_sync); @@ -312,7 +348,7 @@ void percpu_ref_switch_to_percpu(struct percpu_ref *ref) spin_lock_irqsave(&percpu_ref_switch_lock, flags); - ref->force_atomic = false; + ref->data->force_atomic = false; __percpu_ref_switch_mode(ref, NULL); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); @@ -344,7 +380,8 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref, spin_lock_irqsave(&percpu_ref_switch_lock, flags); WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_DEAD, - "%s called more than once on %ps!", __func__, ref->release); + "%s called more than once on %ps!", __func__, + ref->data->release); ref->percpu_count_ptr |= __PERCPU_REF_DEAD; __percpu_ref_switch_mode(ref, confirm_kill); @@ -354,6 +391,34 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref, } EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm); +/** + * percpu_ref_is_zero - test whether a percpu refcount reached zero + * @ref: percpu_ref to test + * + * Returns %true if @ref reached zero. + * + * This function is safe to call as long as @ref is between init and exit. + */ +bool percpu_ref_is_zero(struct percpu_ref *ref) +{ + unsigned long __percpu *percpu_count; + unsigned long count, flags; + + if (__ref_is_percpu(ref, &percpu_count)) + return false; + + /* protect us from being destroyed */ + spin_lock_irqsave(&percpu_ref_switch_lock, flags); + if (ref->data) + count = atomic_long_read(&ref->data->count); + else + count = ref->percpu_count_ptr >> __PERCPU_REF_FLAG_BITS; + spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); + + return count == 0; +} +EXPORT_SYMBOL_GPL(percpu_ref_is_zero); + /** * percpu_ref_reinit - re-initialize a percpu refcount * @ref: perpcu_ref to re-initialize -- cgit v1.2.3 From 0549e87c30ae0d43d7e10424f2222bcd8bbe986d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 1 Oct 2020 23:48:42 +0800 Subject: block: move 'q_usage_counter' into front of 'request_queue' The field of 'q_usage_counter' is always fetched in fast path of every block driver, and move it into front of 'request_queue', so it can be fetched into 1st cacheline of 'request_queue' instance. Signed-off-by: Ming Lei Tested-by: Veronika Kabatova Reviewed-by: Christoph Hellwig Cc: Sagi Grimberg Cc: Tejun Heo Cc: Christoph Hellwig Cc: Jens Axboe Cc: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cf80e61b4c5e..5fc940423e5a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -397,6 +397,8 @@ struct request_queue { struct request *last_merge; struct elevator_queue *elevator; + struct percpu_ref q_usage_counter; + struct blk_queue_stats *stats; struct rq_qos *rq_qos; @@ -569,7 +571,6 @@ struct request_queue { * percpu_ref_kill() and percpu_ref_reinit(). */ struct mutex mq_freeze_lock; - struct percpu_ref q_usage_counter; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; -- cgit v1.2.3 From 92cf2fd156b273879198bb1d7e58851f822c481f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 6 Oct 2020 09:07:17 +0200 Subject: block: remove the unused blk_integrity_merge_rq export Also move the definition from the public blkdev.h to the private block/blk.h header. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-integrity.c | 1 - block/blk.h | 8 ++++++++ include/linux/blkdev.h | 8 -------- 3 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 2b36a8f9b813..a262e069eb3f 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -183,7 +183,6 @@ bool blk_integrity_merge_rq(struct request_queue *q, struct request *req, return true; } -EXPORT_SYMBOL(blk_integrity_merge_rq); bool blk_integrity_merge_bio(struct request_queue *q, struct request *req, struct bio *bio) diff --git a/block/blk.h b/block/blk.h index c08762e10b04..ba4e8ac538cd 100644 --- a/block/blk.h +++ b/block/blk.h @@ -120,6 +120,9 @@ static inline bool bio_integrity_endio(struct bio *bio) return true; } +bool blk_integrity_merge_rq(struct request_queue *, struct request *, + struct request *); + static inline bool integrity_req_gap_back_merge(struct request *req, struct bio *next) { @@ -143,6 +146,11 @@ static inline bool integrity_req_gap_front_merge(struct request *req, void blk_integrity_add(struct gendisk *); void blk_integrity_del(struct gendisk *); #else /* CONFIG_BLK_DEV_INTEGRITY */ +static inline bool blk_integrity_merge_rq(struct request_queue *rq, + struct request *r1, struct request *r2) +{ + return true; +} static inline bool integrity_req_gap_back_merge(struct request *req, struct bio *next) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5fc940423e5a..6a6d9ea7420a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1664,8 +1664,6 @@ extern int blk_integrity_compare(struct gendisk *, struct gendisk *); extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, struct scatterlist *); extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); -extern bool blk_integrity_merge_rq(struct request_queue *, struct request *, - struct request *); extern bool blk_integrity_merge_bio(struct request_queue *, struct request *, struct bio *); @@ -1795,12 +1793,6 @@ static inline unsigned short queue_max_integrity_segments(const struct request_q { return 0; } -static inline bool blk_integrity_merge_rq(struct request_queue *rq, - struct request *r1, - struct request *r2) -{ - return true; -} static inline bool blk_integrity_merge_bio(struct request_queue *rq, struct request *r, struct bio *b) -- cgit v1.2.3 From d59da41998bc794441d7c039a059ed6eb0c2dc4d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 6 Oct 2020 09:07:18 +0200 Subject: block: remove the unused blk_integrity_merge_bio export Also move the definition from the public blkdev.h to the private block/blk.h header. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-integrity.c | 1 - block/blk.h | 7 +++++++ include/linux/blkdev.h | 8 -------- 3 files changed, 7 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/block/blk-integrity.c b/block/blk-integrity.c index a262e069eb3f..410da060d1f5 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -211,7 +211,6 @@ bool blk_integrity_merge_bio(struct request_queue *q, struct request *req, return true; } -EXPORT_SYMBOL(blk_integrity_merge_bio); struct integrity_sysfs_entry { struct attribute attr; diff --git a/block/blk.h b/block/blk.h index ba4e8ac538cd..8fcb146d3003 100644 --- a/block/blk.h +++ b/block/blk.h @@ -122,6 +122,8 @@ static inline bool bio_integrity_endio(struct bio *bio) bool blk_integrity_merge_rq(struct request_queue *, struct request *, struct request *); +bool blk_integrity_merge_bio(struct request_queue *, struct request *, + struct bio *); static inline bool integrity_req_gap_back_merge(struct request *req, struct bio *next) @@ -151,6 +153,11 @@ static inline bool blk_integrity_merge_rq(struct request_queue *rq, { return true; } +static inline bool blk_integrity_merge_bio(struct request_queue *rq, + struct request *r, struct bio *b) +{ + return true; +} static inline bool integrity_req_gap_back_merge(struct request *req, struct bio *next) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6a6d9ea7420a..cda786fa4341 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1664,8 +1664,6 @@ extern int blk_integrity_compare(struct gendisk *, struct gendisk *); extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, struct scatterlist *); extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); -extern bool blk_integrity_merge_bio(struct request_queue *, struct request *, - struct bio *); static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { @@ -1793,12 +1791,6 @@ static inline unsigned short queue_max_integrity_segments(const struct request_q { return 0; } -static inline bool blk_integrity_merge_bio(struct request_queue *rq, - struct request *r, - struct bio *b) -{ - return true; -} static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) -- cgit v1.2.3 From fe6f0cdc49263ae61cd3d33399662808c2398e86 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 7 Oct 2020 21:35:08 +0900 Subject: block: soft limit zone-append sectors as well Martin rightfully noted that for normal filesystem IO we have soft limits in place, to prevent them from getting too big and not lead to unpredictable latencies. For zone append we only have the hardware limit in place. Cap the max sectors we submit via zone-append to the maximal number of sectors if the second limit is lower. Reported-by: Martin K. Petersen Signed-off-by: Johannes Thumshirn Reviewed-by: Damien Le Moal Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/linux-btrfs/yq1k0w8g3rw.fsf@ca-mkp.ca.oracle.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cda786fa4341..6bd667c34777 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1407,7 +1407,10 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q) { - return q->limits.max_zone_append_sectors; + + const struct queue_limits *l = &q->limits; + + return min(l->max_zone_append_sectors, l->max_sectors); } static inline unsigned queue_logical_block_size(const struct request_queue *q) -- cgit v1.2.3 From 8858e8d98d5457ba23bcd0d99ce23e272b8b09a1 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 9 Oct 2020 18:07:14 +0900 Subject: block: fix uapi blkzoned.h comments Update the kdoc comments for struct blk_zone (capacity field description missing) and for struct blk_zone_report (flags field description missing). Signed-off-by: Damien Le Moal Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/uapi/linux/blkzoned.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index 42c3366cc25f..656a326821a2 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -93,12 +93,15 @@ enum blk_zone_report_flags { * @non_seq: Flag indicating that the zone is using non-sequential resources * (for host-aware zoned block devices only). * @reset: Flag indicating that a zone reset is recommended. - * @reserved: Padding to 64 B to match the ZBC/ZAC defined zone descriptor size. + * @resv: Padding for 8B alignment. + * @capacity: Zone usable capacity in 512 B sector units + * @reserved: Padding to 64 B to match the ZBC, ZAC and ZNS defined zone + * descriptor size. * - * start, len and wp use the regular 512 B sector unit, regardless of the - * device logical block size. The overall structure size is 64 B to match the - * ZBC/ZAC defined zone descriptor and allow support for future additional - * zone information. + * start, len, capacity and wp use the regular 512 B sector unit, regardless + * of the device logical block size. The overall structure size is 64 B to + * match the ZBC, ZAC and ZNS defined zone descriptor and allow support for + * future additional zone information. */ struct blk_zone { __u64 start; /* Zone start sector */ @@ -118,7 +121,7 @@ struct blk_zone { * * @sector: starting sector of report * @nr_zones: IN maximum / OUT actual - * @reserved: padding to 16 byte alignment + * @flags: one or more flags as defined by enum blk_zone_report_flags. * @zones: Space to hold @nr_zones @zones entries on reply. * * The array of at most @nr_zones must follow this structure in memory. -- cgit v1.2.3