From 118cf084adb3964d06e1667cf7d702e56e5cd2c5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Nov 2020 11:00:13 +0100 Subject: md: implement ->set_read_only to hook into BLKROSET processing Implement the ->set_read_only method instead of parsing the actual ioctl command. Signed-off-by: Christoph Hellwig Acked-by: Song Liu Signed-off-by: Jens Axboe --- drivers/md/md.c | 62 ++++++++++++++++++++++++++++----------------------------- 1 file changed, 31 insertions(+), 31 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/md.c b/drivers/md/md.c index 98bac4f304ae..96d31336ad43 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -7480,7 +7480,6 @@ static inline bool md_ioctl_valid(unsigned int cmd) { switch (cmd) { case ADD_NEW_DISK: - case BLKROSET: case GET_ARRAY_INFO: case GET_BITMAP_FILE: case GET_DISK_INFO: @@ -7507,7 +7506,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, int err = 0; void __user *argp = (void __user *)arg; struct mddev *mddev = NULL; - int ro; bool did_set_md_closing = false; if (!md_ioctl_valid(cmd)) @@ -7687,35 +7685,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, goto unlock; } break; - - case BLKROSET: - if (get_user(ro, (int __user *)(arg))) { - err = -EFAULT; - goto unlock; - } - err = -EINVAL; - - /* if the bdev is going readonly the value of mddev->ro - * does not matter, no writes are coming - */ - if (ro) - goto unlock; - - /* are we are already prepared for writes? */ - if (mddev->ro != 1) - goto unlock; - - /* transitioning to readauto need only happen for - * arrays that call md_write_start - */ - if (mddev->pers) { - err = restart_array(mddev); - if (err == 0) { - mddev->ro = 2; - set_disk_ro(mddev->gendisk, 0); - } - } - goto unlock; } /* @@ -7809,6 +7778,36 @@ static int md_compat_ioctl(struct block_device *bdev, fmode_t mode, } #endif /* CONFIG_COMPAT */ +static int md_set_read_only(struct block_device *bdev, bool ro) +{ + struct mddev *mddev = bdev->bd_disk->private_data; + int err; + + err = mddev_lock(mddev); + if (err) + return err; + + if (!mddev->raid_disks && !mddev->external) { + err = -ENODEV; + goto out_unlock; + } + + /* + * Transitioning to read-auto need only happen for arrays that call + * md_write_start and which are not ready for writes yet. + */ + if (!ro && mddev->ro == 1 && mddev->pers) { + err = restart_array(mddev); + if (err) + goto out_unlock; + mddev->ro = 2; + } + +out_unlock: + mddev_unlock(mddev); + return err; +} + static int md_open(struct block_device *bdev, fmode_t mode) { /* @@ -7886,6 +7885,7 @@ const struct block_device_operations md_fops = #endif .getgeo = md_getgeo, .check_events = md_check_events, + .set_read_only = md_set_read_only, }; static int md_thread(void *arg) -- cgit v1.2.3 From a7cb3d2f09c8405aed59d97a7d02cebea43cd3c7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Nov 2020 11:00:18 +0100 Subject: block: remove __blkdev_driver_ioctl Just open code it in the few callers. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/ioctl.c | 25 +++++-------------------- drivers/block/pktcdvd.c | 6 ++++-- drivers/md/bcache/request.c | 5 +++-- drivers/md/dm.c | 5 ++++- include/linux/blkdev.h | 2 -- 5 files changed, 16 insertions(+), 27 deletions(-) (limited to 'drivers/md') diff --git a/block/ioctl.c b/block/ioctl.c index 04255dc5f3bf..6b785181344f 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -219,23 +219,6 @@ static int compat_put_ulong(compat_ulong_t __user *argp, compat_ulong_t val) } #endif -int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode, - unsigned cmd, unsigned long arg) -{ - struct gendisk *disk = bdev->bd_disk; - - if (disk->fops->ioctl) - return disk->fops->ioctl(bdev, mode, cmd, arg); - - return -ENOTTY; -} -/* - * For the record: _GPL here is only because somebody decided to slap it - * on the previous export. Sheer idiocy, since it wasn't copyrightable - * at all and could be open-coded without any exports by anybody who cares. - */ -EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl); - #ifdef CONFIG_COMPAT /* * This is the equivalent of compat_ptr_ioctl(), to be used by block @@ -594,10 +577,12 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, } ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp); - if (ret == -ENOIOCTLCMD) - return __blkdev_driver_ioctl(bdev, mode, cmd, arg); + if (ret != -ENOIOCTLCMD) + return ret; - return ret; + if (!bdev->bd_disk->fops->ioctl) + return -ENOTTY; + return bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg); } EXPORT_SYMBOL_GPL(blkdev_ioctl); /* for /dev/raw */ diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 467dbd06b7cd..ef1c1f094ea4 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2584,9 +2584,11 @@ static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, case CDROM_LAST_WRITTEN: case CDROM_SEND_PACKET: case SCSI_IOCTL_SEND_COMMAND: - ret = __blkdev_driver_ioctl(pd->bdev, mode, cmd, arg); + if (!bdev->bd_disk->fops->ioctl) + ret = -ENOTTY; + else + ret = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg); break; - default: pkt_dbg(2, pd, "Unknown ioctl (%x)\n", cmd); ret = -ENOTTY; diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 214326383145..afac8d07c1bd 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -1230,8 +1230,9 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, if (dc->io_disable) return -EIO; - - return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg); + if (!dc->bdev->bd_disk->fops->ioctl) + return -ENOTTY; + return dc->bdev->bd_disk->fops->ioctl(dc->bdev, mode, cmd, arg); } void bch_cached_dev_request_init(struct cached_dev *dc) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index c18fc2548518..6db395c3d28b 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -570,7 +570,10 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, } } - r = __blkdev_driver_ioctl(bdev, mode, cmd, arg); + if (!bdev->bd_disk->fops->ioctl) + r = -ENOTTY; + else + r = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg); out: dm_unprepare_ioctl(md, srcu_idx); return r; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5c1ba8a8d2bc..05b346a68c2e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1867,8 +1867,6 @@ extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t, #define blkdev_compat_ptr_ioctl NULL #endif -extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, - unsigned long); extern int bdev_read_page(struct block_device *, sector_t, struct page *); extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); -- cgit v1.2.3 From 28144f9998e047a9bac31421914335c6bc6eaa67 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Oct 2020 15:58:34 +0100 Subject: md: use __register_blkdev to allocate devices on demand Use the simpler mechanism attached to major_name to allocate a md device when a currently unregistered minor is accessed. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Acked-by: Song Liu Signed-off-by: Jens Axboe --- drivers/md/md.c | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/md.c b/drivers/md/md.c index 96d31336ad43..3c79243e9d07 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5765,11 +5765,12 @@ static int md_alloc(dev_t dev, char *name) return error; } -static struct kobject *md_probe(dev_t dev, int *part, void *data) +static void md_probe(dev_t dev) { + if (MAJOR(dev) == MD_MAJOR && MINOR(dev) >= 512) + return; if (create_on_open) md_alloc(dev, NULL); - return NULL; } static int add_named_array(const char *val, const struct kernel_param *kp) @@ -6535,7 +6536,7 @@ static void autorun_devices(int part) break; } - md_probe(dev, NULL, NULL); + md_probe(dev); mddev = mddev_find(dev); if (!mddev || !mddev->gendisk) { if (mddev) @@ -9567,18 +9568,15 @@ static int __init md_init(void) if (!md_rdev_misc_wq) goto err_rdev_misc_wq; - if ((ret = register_blkdev(MD_MAJOR, "md")) < 0) + ret = __register_blkdev(MD_MAJOR, "md", md_probe); + if (ret < 0) goto err_md; - if ((ret = register_blkdev(0, "mdp")) < 0) + ret = __register_blkdev(0, "mdp", md_probe); + if (ret < 0) goto err_mdp; mdp_major = ret; - blk_register_region(MKDEV(MD_MAJOR, 0), 512, THIS_MODULE, - md_probe, NULL, NULL); - blk_register_region(MKDEV(mdp_major, 0), 1UL< Date: Mon, 16 Nov 2020 15:57:03 +0100 Subject: dm: use set_capacity_and_notify Use set_capacity_and_notify to set the size of both the disk and block device. This also gets the uevent notifications for the resize for free. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- drivers/md/dm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 6db395c3d28b..54739f1b579b 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1974,8 +1974,7 @@ 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_capacity(md->disk, size); - bd_set_nr_sectors(md->bdev, size); + set_capacity_and_notify(md->disk, size); dm_table_event_callback(t, event_callback, md); -- cgit v1.2.3 From dc2985a8d583abe232e5882df9c8b67ac0d523e8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:57:10 +0100 Subject: dm-raid: use set_capacity_and_notify Use set_capacity_and_notify to set the size of both the disk and block device. This also gets the uevent notifications for the resize for free. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- drivers/md/dm-raid.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 9c1f7c4de65b..294f34d2d61b 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -700,8 +700,7 @@ 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_size(gendisk, true); + set_capacity_and_notify(gendisk, rs->md.array_sectors); } /* -- cgit v1.2.3 From 2c247c5169b50d58f63c0e82a58f457343e49d10 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:57:11 +0100 Subject: md: use set_capacity_and_notify Use set_capacity_and_notify to set the size of both the disk and block device. This also gets the uevent notifications for the resize for free. Signed-off-by: Christoph Hellwig Acked-by: Song Liu Signed-off-by: Jens Axboe --- drivers/md/md-cluster.c | 6 ++---- drivers/md/md-linear.c | 3 +-- drivers/md/md.c | 24 ++++++++++-------------- 3 files changed, 13 insertions(+), 20 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 4aaf4820b6f6..87442dc59f6c 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -581,8 +581,7 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg) process_metadata_update(mddev, msg); break; case CHANGE_CAPACITY: - set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk_size(mddev->gendisk, true); + set_capacity_and_notify(mddev->gendisk, mddev->array_sectors); break; case RESYNCING: set_bit(MD_RESYNCING_REMOTE, &mddev->recovery); @@ -1296,8 +1295,7 @@ static void update_size(struct mddev *mddev, sector_t old_dev_sectors) if (ret) pr_err("%s:%d: failed to send CHANGE_CAPACITY msg\n", __func__, __LINE__); - set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk_size(mddev->gendisk, true); + set_capacity_and_notify(mddev->gendisk, mddev->array_sectors); } else { /* revert to previous sectors */ ret = mddev->pers->resize(mddev, old_dev_sectors); diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index 5ab22069b5be..98f1b4b2bdce 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -200,9 +200,8 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev) "copied raid_disks doesn't match mddev->raid_disks"); rcu_assign_pointer(mddev->private, newconf); md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); - set_capacity(mddev->gendisk, mddev->array_sectors); + set_capacity_and_notify(mddev->gendisk, mddev->array_sectors); mddev_resume(mddev); - 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 3c79243e9d07..b2edf5e0f965 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5355,10 +5355,9 @@ array_size_store(struct mddev *mddev, const char *buf, size_t len) if (!err) { mddev->array_sectors = sectors; - if (mddev->pers) { - set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk_size(mddev->gendisk, true); - } + if (mddev->pers) + set_capacity_and_notify(mddev->gendisk, + mddev->array_sectors); } mddev_unlock(mddev); return err ?: len; @@ -6108,8 +6107,7 @@ int do_md_run(struct mddev *mddev) md_wakeup_thread(mddev->thread); md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */ - set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk_size(mddev->gendisk, true); + set_capacity_and_notify(mddev->gendisk, mddev->array_sectors); clear_bit(MD_NOT_READY, &mddev->flags); mddev->changed = 1; kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE); @@ -6424,10 +6422,9 @@ static int do_md_stop(struct mddev *mddev, int mode, if (rdev->raid_disk >= 0) sysfs_unlink_rdev(mddev, rdev); - set_capacity(disk, 0); + set_capacity_and_notify(disk, 0); mutex_unlock(&mddev->open_mutex); mddev->changed = 1; - revalidate_disk_size(disk, true); if (mddev->ro) mddev->ro = 0; @@ -7258,8 +7255,8 @@ static int update_size(struct mddev *mddev, sector_t num_sectors) if (mddev_is_clustered(mddev)) md_cluster_ops->update_size(mddev, old_dev_sectors); else if (mddev->queue) { - set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk_size(mddev->gendisk, true); + set_capacity_and_notify(mddev->gendisk, + mddev->array_sectors); } } return rv; @@ -9036,10 +9033,9 @@ void md_do_sync(struct md_thread *thread) mddev_lock_nointr(mddev); md_set_array_sectors(mddev, mddev->pers->size(mddev, 0, 0)); mddev_unlock(mddev); - if (!mddev_is_clustered(mddev)) { - set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk_size(mddev->gendisk, true); - } + if (!mddev_is_clustered(mddev)) + set_capacity_and_notify(mddev->gendisk, + mddev->array_sectors); } spin_lock(&mddev->lock); -- cgit v1.2.3 From 94d91e7f8c221260790a482373d347ea85efb7b3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:57:12 +0100 Subject: md: remove a spurious call to revalidate_disk_size in update_size None of the ->resize methods updates the disk size, so calling revalidate_disk_size here won't do anything. Signed-off-by: Christoph Hellwig Acked-by: Song Liu Signed-off-by: Jens Axboe --- drivers/md/md-cluster.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 87442dc59f6c..35e2690c1803 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -1299,8 +1299,6 @@ static void update_size(struct mddev *mddev, sector_t old_dev_sectors) } else { /* revert to previous sectors */ ret = mddev->pers->resize(mddev, old_dev_sectors); - if (!ret) - revalidate_disk_size(mddev->gendisk, true); ret = __sendmsg(cinfo, &cmsg); if (ret) pr_err("%s:%d: failed to send METADATA_UPDATED msg\n", -- cgit v1.2.3 From 040f04bd2e825f1d80b14a0e0ac3d830339eb779 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Nov 2020 11:54:06 +0100 Subject: fs: simplify freeze_bdev/thaw_bdev Store the frozen superblock in struct block_device to avoid the awkward interface that can return a sb only used a cookie, an ERR_PTR or NULL. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Acked-by: Chao Yu [f2fs] Signed-off-by: Jens Axboe --- drivers/md/dm-core.h | 5 ----- drivers/md/dm.c | 20 ++++++-------------- fs/block_dev.c | 37 +++++++++++++++---------------------- fs/buffer.c | 2 +- fs/ext4/ioctl.c | 2 +- fs/f2fs/file.c | 14 +++++--------- fs/xfs/xfs_fsops.c | 7 ++----- include/linux/blk_types.h | 1 + include/linux/blkdev.h | 4 ++-- 9 files changed, 33 insertions(+), 59 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index d522093cb39d..aace147effca 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -96,11 +96,6 @@ struct mapped_device { */ struct workqueue_struct *wq; - /* - * freeze/thaw support require holding onto a super block - */ - struct super_block *frozen_sb; - /* forced geometry settings */ struct hd_geometry geometry; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 54739f1b579b..50541d336c71 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2392,27 +2392,19 @@ static int lock_fs(struct mapped_device *md) { int r; - WARN_ON(md->frozen_sb); + WARN_ON(test_bit(DMF_FROZEN, &md->flags)); - md->frozen_sb = freeze_bdev(md->bdev); - if (IS_ERR(md->frozen_sb)) { - r = PTR_ERR(md->frozen_sb); - md->frozen_sb = NULL; - return r; - } - - set_bit(DMF_FROZEN, &md->flags); - - return 0; + r = freeze_bdev(md->bdev); + if (!r) + set_bit(DMF_FROZEN, &md->flags); + return r; } static void unlock_fs(struct mapped_device *md) { if (!test_bit(DMF_FROZEN, &md->flags)) return; - - thaw_bdev(md->bdev, md->frozen_sb); - md->frozen_sb = NULL; + thaw_bdev(md->bdev); clear_bit(DMF_FROZEN, &md->flags); } diff --git a/fs/block_dev.c b/fs/block_dev.c index d8664f5c1ff6..33c29106c989 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -548,55 +548,47 @@ EXPORT_SYMBOL(fsync_bdev); * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze * actually. */ -struct super_block *freeze_bdev(struct block_device *bdev) +int freeze_bdev(struct block_device *bdev) { struct super_block *sb; int error = 0; mutex_lock(&bdev->bd_fsfreeze_mutex); - if (++bdev->bd_fsfreeze_count > 1) { - /* - * We don't even need to grab a reference - the first call - * to freeze_bdev grab an active reference and only the last - * thaw_bdev drops it. - */ - sb = get_super(bdev); - if (sb) - drop_super(sb); - mutex_unlock(&bdev->bd_fsfreeze_mutex); - return sb; - } + if (++bdev->bd_fsfreeze_count > 1) + goto done; sb = get_active_super(bdev); if (!sb) - goto out; + goto sync; if (sb->s_op->freeze_super) error = sb->s_op->freeze_super(sb); else error = freeze_super(sb); + deactivate_super(sb); + if (error) { - deactivate_super(sb); bdev->bd_fsfreeze_count--; - mutex_unlock(&bdev->bd_fsfreeze_mutex); - return ERR_PTR(error); + goto done; } - deactivate_super(sb); - out: + bdev->bd_fsfreeze_sb = sb; + +sync: sync_blockdev(bdev); +done: mutex_unlock(&bdev->bd_fsfreeze_mutex); - return sb; /* thaw_bdev releases s->s_umount */ + return error; } EXPORT_SYMBOL(freeze_bdev); /** * thaw_bdev -- unlock filesystem * @bdev: blockdevice to unlock - * @sb: associated superblock * * Unlocks the filesystem and marks it writeable again after freeze_bdev(). */ -int thaw_bdev(struct block_device *bdev, struct super_block *sb) +int thaw_bdev(struct block_device *bdev) { + struct super_block *sb; int error = -EINVAL; mutex_lock(&bdev->bd_fsfreeze_mutex); @@ -607,6 +599,7 @@ int thaw_bdev(struct block_device *bdev, struct super_block *sb) if (--bdev->bd_fsfreeze_count > 0) goto out; + sb = bdev->bd_fsfreeze_sb; if (!sb) goto out; diff --git a/fs/buffer.c b/fs/buffer.c index 23f645657488..a7595ada9400 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -523,7 +523,7 @@ repeat: void emergency_thaw_bdev(struct super_block *sb) { - while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb)) + while (sb->s_bdev && !thaw_bdev(sb->s_bdev)) printk(KERN_WARNING "Emergency Thaw on %pg\n", sb->s_bdev); } diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index f0381876a7e5..524e13432447 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -624,7 +624,7 @@ static int ext4_shutdown(struct super_block *sb, unsigned long arg) case EXT4_GOING_FLAGS_DEFAULT: freeze_bdev(sb->s_bdev); set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); - thaw_bdev(sb->s_bdev, sb); + thaw_bdev(sb->s_bdev); break; case EXT4_GOING_FLAGS_LOGFLUSH: set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index ee861c6d9ff0..a9fc482a0e60 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2230,16 +2230,12 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) switch (in) { case F2FS_GOING_DOWN_FULLSYNC: - sb = freeze_bdev(sb->s_bdev); - if (IS_ERR(sb)) { - ret = PTR_ERR(sb); + ret = freeze_bdev(sb->s_bdev); + if (ret) goto out; - } - if (sb) { - f2fs_stop_checkpoint(sbi, false); - set_sbi_flag(sbi, SBI_IS_SHUTDOWN); - thaw_bdev(sb->s_bdev, sb); - } + f2fs_stop_checkpoint(sbi, false); + set_sbi_flag(sbi, SBI_IS_SHUTDOWN); + thaw_bdev(sb->s_bdev); break; case F2FS_GOING_DOWN_METASYNC: /* do checkpoint only */ diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index ef1d5bb88b93..b7c5783a031c 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -433,13 +433,10 @@ xfs_fs_goingdown( { switch (inflags) { case XFS_FSOP_GOING_FLAGS_DEFAULT: { - struct super_block *sb = freeze_bdev(mp->m_super->s_bdev); - - if (sb && !IS_ERR(sb)) { + if (!freeze_bdev(mp->m_super->s_bdev)) { xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT); - thaw_bdev(sb->s_bdev, sb); + thaw_bdev(mp->m_super->s_bdev); } - break; } case XFS_FSOP_GOING_FLAGS_LOGFLUSH: diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index d9b69bbde5cc..ebfb4e7c1fd1 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -46,6 +46,7 @@ struct block_device { int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; + struct super_block *bd_fsfreeze_sb; } __randomize_layout; /* diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 05b346a68c2e..12810a19edeb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -2020,7 +2020,7 @@ static inline int sync_blockdev(struct block_device *bdev) #endif int fsync_bdev(struct block_device *bdev); -struct super_block *freeze_bdev(struct block_device *bdev); -int thaw_bdev(struct block_device *bdev, struct super_block *sb); +int freeze_bdev(struct block_device *bdev); +int thaw_bdev(struct block_device *bdev); #endif /* _LINUX_BLKDEV_H */ -- cgit v1.2.3 From 47d951023a242bb159534573a4a76fef9a31dc9b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 7 Nov 2020 09:30:05 +0100 Subject: dm: simplify flush_bio initialization in __send_empty_flush We don't really need the struct block_device to initialize a bio. So switch from using bio_set_dev to manually setting up bi_disk (bi_partno will always be zero and has been cleared by bio_init already). Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Acked-by: Mike Snitzer Signed-off-by: Jens Axboe --- drivers/md/dm.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 50541d336c71..ab0a8335f098 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1422,18 +1422,12 @@ static int __send_empty_flush(struct clone_info *ci) */ bio_init(&flush_bio, NULL, 0); flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC; + flush_bio.bi_disk = ci->io->md->disk; + bio_associate_blkg(&flush_bio); + ci->bio = &flush_bio; ci->sector_count = 0; - /* - * Empty flush uses a statically initialized bio, as the base for - * cloning. However, blkg association requires that a bdev is - * associated with a gendisk, which doesn't happen until the bdev is - * opened. So, blkg association is done at issue time of the flush - * rather than when the device is created in alloc_dev(). - */ - bio_set_dev(ci->bio, ci->io->md->bdev); - BUG_ON(bio_has_data(ci->bio)); while ((ti = dm_table_get_target(ci->map, target_nr++))) __send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL); -- cgit v1.2.3 From b0519b542303bc167d22bf11dadd3f18d37dbfe2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 27 Nov 2020 16:21:42 +0100 Subject: dm: remove the block_device reference in struct mapped_device Get rid of the long-lasting struct block_device reference in struct mapped_device. The only remaining user is the freeze code, where we can trivially look up the block device at freeze time and release the reference at thaw time. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Acked-by: Mike Snitzer Signed-off-by: Jens Axboe --- drivers/md/dm-core.h | 2 -- drivers/md/dm.c | 25 ++++++++++++++----------- 2 files changed, 14 insertions(+), 13 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index aace147effca..086d293c2b03 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -102,8 +102,6 @@ struct mapped_device { /* kobject and completion */ struct dm_kobject_holder kobj_holder; - struct block_device *bdev; - struct dm_stats stats; /* for blk-mq request-based DM support */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index ab0a8335f098..48051db006f3 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1744,11 +1744,6 @@ static void cleanup_mapped_device(struct mapped_device *md) cleanup_srcu_struct(&md->io_barrier); - if (md->bdev) { - bdput(md->bdev); - md->bdev = NULL; - } - mutex_destroy(&md->suspend_lock); mutex_destroy(&md->type_lock); mutex_destroy(&md->table_devices_lock); @@ -1840,10 +1835,6 @@ static struct mapped_device *alloc_dev(int minor) if (!md->wq) goto bad; - md->bdev = bdget_disk(md->disk, 0); - if (!md->bdev) - goto bad; - dm_stats_init(&md->stats); /* Populate the mapping, nobody knows we exist yet */ @@ -2384,11 +2375,16 @@ out: */ static int lock_fs(struct mapped_device *md) { + struct block_device *bdev; int r; WARN_ON(test_bit(DMF_FROZEN, &md->flags)); - r = freeze_bdev(md->bdev); + bdev = bdget_disk(md->disk, 0); + if (!bdev) + return -ENOMEM; + r = freeze_bdev(bdev); + bdput(bdev); if (!r) set_bit(DMF_FROZEN, &md->flags); return r; @@ -2396,9 +2392,16 @@ static int lock_fs(struct mapped_device *md) static void unlock_fs(struct mapped_device *md) { + struct block_device *bdev; + if (!test_bit(DMF_FROZEN, &md->flags)) return; - thaw_bdev(md->bdev); + + bdev = bdget_disk(md->disk, 0); + if (!bdev) + return; + thaw_bdev(bdev); + bdput(bdev); clear_bit(DMF_FROZEN, &md->flags); } -- cgit v1.2.3 From 8d65269fe8065fee889bca5b204d711b0695a8f6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 17 Nov 2020 08:18:55 +0100 Subject: block: add a bdev_kobj helper Add a little helper to find the kobject for a struct block_device. Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Acked-by: Tejun Heo Acked-by: Coly Li [bcache] Acked-by: David Sterba [btrfs] Signed-off-by: Jens Axboe --- drivers/md/bcache/super.c | 7 ++----- drivers/md/md.c | 4 +--- fs/block_dev.c | 6 +++--- fs/btrfs/sysfs.c | 15 +++------------ include/linux/blk_types.h | 3 +++ 5 files changed, 12 insertions(+), 23 deletions(-) (limited to 'drivers/md') diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 46a00134a36a..a6a5e21e4fd1 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1447,8 +1447,7 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk, goto err; err = "error creating kobject"; - if (kobject_add(&dc->disk.kobj, &part_to_dev(bdev->bd_part)->kobj, - "bcache")) + if (kobject_add(&dc->disk.kobj, bdev_kobj(bdev), "bcache")) goto err; if (bch_cache_accounting_add_kobjs(&dc->accounting, &dc->disk.kobj)) goto err; @@ -2342,9 +2341,7 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk, goto err; } - if (kobject_add(&ca->kobj, - &part_to_dev(bdev->bd_part)->kobj, - "bcache")) { + if (kobject_add(&ca->kobj, bdev_kobj(bdev), "bcache")) { err = "error calling kobject_add"; ret = -ENOMEM; goto out; diff --git a/drivers/md/md.c b/drivers/md/md.c index b2edf5e0f965..7ce6047c856e 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2414,7 +2414,6 @@ EXPORT_SYMBOL(md_integrity_add_rdev); static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) { char b[BDEVNAME_SIZE]; - struct kobject *ko; int err; /* prevent duplicates */ @@ -2477,9 +2476,8 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) if ((err = kobject_add(&rdev->kobj, &mddev->kobj, "dev-%s", b))) goto fail; - ko = &part_to_dev(rdev->bdev->bd_part)->kobj; /* failure here is OK */ - err = sysfs_create_link(&rdev->kobj, ko, "block"); + err = sysfs_create_link(&rdev->kobj, bdev_kobj(rdev->bdev), "block"); rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state"); rdev->sysfs_unack_badblocks = sysfs_get_dirent_safe(rdev->kobj.sd, "unacknowledged_bad_blocks"); diff --git a/fs/block_dev.c b/fs/block_dev.c index 33c29106c989..c5755150c6be 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1242,7 +1242,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) holder->disk = disk; holder->refcnt = 1; - ret = add_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj); + ret = add_symlink(disk->slave_dir, bdev_kobj(bdev)); if (ret) goto out_free; @@ -1259,7 +1259,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) goto out_unlock; out_del: - del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj); + del_symlink(disk->slave_dir, bdev_kobj(bdev)); out_free: kfree(holder); out_unlock: @@ -1287,7 +1287,7 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) holder = bd_find_holder_disk(bdev, disk); if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) { - del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj); + del_symlink(disk->slave_dir, bdev_kobj(bdev)); del_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj); kobject_put(bdev->bd_part->holder_dir); diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 279d9262b676..24b6c6dc6900 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1232,8 +1232,6 @@ int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info, void btrfs_sysfs_remove_device(struct btrfs_device *device) { - struct hd_struct *disk; - struct kobject *disk_kobj; struct kobject *devices_kobj; /* @@ -1243,11 +1241,8 @@ void btrfs_sysfs_remove_device(struct btrfs_device *device) devices_kobj = device->fs_info->fs_devices->devices_kobj; ASSERT(devices_kobj); - if (device->bdev) { - disk = device->bdev->bd_part; - disk_kobj = &part_to_dev(disk)->kobj; - sysfs_remove_link(devices_kobj, disk_kobj->name); - } + if (device->bdev) + sysfs_remove_link(devices_kobj, bdev_kobj(device->bdev)->name); if (device->devid_kobj.state_initialized) { kobject_del(&device->devid_kobj); @@ -1353,11 +1348,7 @@ int btrfs_sysfs_add_device(struct btrfs_device *device) nofs_flag = memalloc_nofs_save(); if (device->bdev) { - struct hd_struct *disk; - struct kobject *disk_kobj; - - disk = device->bdev->bd_part; - disk_kobj = &part_to_dev(disk)->kobj; + struct kobject *disk_kobj = bdev_kobj(device->bdev); ret = sysfs_create_link(devices_kobj, disk_kobj, disk_kobj->name); if (ret) { diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index ebfb4e7c1fd1..9698f459cc65 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -49,6 +49,9 @@ struct block_device { struct super_block *bd_fsfreeze_sb; } __randomize_layout; +#define bdev_kobj(_bdev) \ + (&part_to_dev((_bdev)->bd_part)->kobj) + /* * Block error status values. See block/blk-core:blk_errors for the details. * Alpha cannot write a byte atomically, so we need to use 32-bit value. -- cgit v1.2.3 From 4e7b5671c6a883d94b5428e1a9c141bbd56cb2a6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 23 Nov 2020 13:38:40 +0100 Subject: block: remove i_bdev Switch the block device lookup interfaces to directly work with a dev_t so that struct block_device references are only acquired by the blkdev_get variants (and the blk-cgroup special case). This means that we now don't need an extra reference in the inode and can generally simplify handling of struct block_device to keep the lookups contained in the core block layer code. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Acked-by: Tejun Heo Acked-by: Coly Li [bcache] Signed-off-by: Jens Axboe --- block/ioctl.c | 3 +- drivers/block/loop.c | 8 +- drivers/md/bcache/super.c | 20 +-- drivers/md/dm-table.c | 9 +- drivers/mtd/mtdsuper.c | 17 +-- drivers/target/target_core_file.c | 6 +- drivers/usb/gadget/function/storage_common.c | 8 +- fs/block_dev.c | 196 +++++++-------------------- fs/btrfs/volumes.c | 13 +- fs/inode.c | 3 - fs/internal.h | 7 +- fs/io_uring.c | 10 +- fs/pipe.c | 5 +- fs/quota/quota.c | 19 ++- fs/statfs.c | 2 +- fs/super.c | 44 +++--- include/linux/blkdev.h | 2 +- include/linux/fs.h | 1 - 18 files changed, 121 insertions(+), 252 deletions(-) (limited to 'drivers/md') diff --git a/block/ioctl.c b/block/ioctl.c index 0c09bb7a6ff3..a6d8171221c7 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -590,8 +590,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) { int ret; void __user *argp = compat_ptr(arg); - struct inode *inode = file->f_mapping->host; - struct block_device *bdev = inode->i_bdev; + struct block_device *bdev = I_BDEV(file->f_mapping->host); struct gendisk *disk = bdev->bd_disk; fmode_t mode = file->f_mode; loff_t size; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index b42c728620c9..26c7aafba7c5 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -675,10 +675,10 @@ static int loop_validate_file(struct file *file, struct block_device *bdev) while (is_loop_device(f)) { struct loop_device *l; - if (f->f_mapping->host->i_bdev == bdev) + if (f->f_mapping->host->i_rdev == bdev->bd_dev) return -EBADF; - l = f->f_mapping->host->i_bdev->bd_disk->private_data; + l = I_BDEV(f->f_mapping->host)->bd_disk->private_data; if (l->lo_state != Lo_bound) { return -EINVAL; } @@ -885,9 +885,7 @@ static void loop_config_discard(struct loop_device *lo) * file-backed loop devices: discarded regions read back as zero. */ if (S_ISBLK(inode->i_mode) && !lo->lo_encrypt_key_size) { - struct request_queue *backingq; - - backingq = bdev_get_queue(inode->i_bdev); + struct request_queue *backingq = bdev_get_queue(I_BDEV(inode)); max_discard_sectors = backingq->limits.max_write_zeroes_sectors; granularity = backingq->limits.discard_granularity ?: diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index a6a5e21e4fd1..c55d3c58a7ef 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -2380,38 +2380,38 @@ kobj_attribute_write(register, register_bcache); kobj_attribute_write(register_quiet, register_bcache); kobj_attribute_write(pendings_cleanup, bch_pending_bdevs_cleanup); -static bool bch_is_open_backing(struct block_device *bdev) +static bool bch_is_open_backing(dev_t dev) { struct cache_set *c, *tc; struct cached_dev *dc, *t; list_for_each_entry_safe(c, tc, &bch_cache_sets, list) list_for_each_entry_safe(dc, t, &c->cached_devs, list) - if (dc->bdev == bdev) + if (dc->bdev->bd_dev == dev) return true; list_for_each_entry_safe(dc, t, &uncached_devices, list) - if (dc->bdev == bdev) + if (dc->bdev->bd_dev == dev) return true; return false; } -static bool bch_is_open_cache(struct block_device *bdev) +static bool bch_is_open_cache(dev_t dev) { struct cache_set *c, *tc; list_for_each_entry_safe(c, tc, &bch_cache_sets, list) { struct cache *ca = c->cache; - if (ca->bdev == bdev) + if (ca->bdev->bd_dev == dev) return true; } return false; } -static bool bch_is_open(struct block_device *bdev) +static bool bch_is_open(dev_t dev) { - return bch_is_open_cache(bdev) || bch_is_open_backing(bdev); + return bch_is_open_cache(dev) || bch_is_open_backing(dev); } struct async_reg_args { @@ -2535,9 +2535,11 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, sb); if (IS_ERR(bdev)) { if (bdev == ERR_PTR(-EBUSY)) { - bdev = lookup_bdev(strim(path)); + dev_t dev; + mutex_lock(&bch_register_lock); - if (!IS_ERR(bdev) && bch_is_open(bdev)) + if (lookup_bdev(strim(path), &dev) == 0 && + bch_is_open(dev)) err = "device already registered"; else err = "device busy"; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index ce543b761be7..dea677721710 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -348,16 +348,9 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode, dev_t dm_get_dev_t(const char *path) { dev_t dev; - struct block_device *bdev; - bdev = lookup_bdev(path); - if (IS_ERR(bdev)) + if (lookup_bdev(path, &dev)) dev = name_to_dev_t(path); - else { - dev = bdev->bd_dev; - bdput(bdev); - } - return dev; } EXPORT_SYMBOL_GPL(dm_get_dev_t); diff --git a/drivers/mtd/mtdsuper.c b/drivers/mtd/mtdsuper.c index c3e2098372f2..38b6aa849c63 100644 --- a/drivers/mtd/mtdsuper.c +++ b/drivers/mtd/mtdsuper.c @@ -120,8 +120,8 @@ int get_tree_mtd(struct fs_context *fc, struct fs_context *fc)) { #ifdef CONFIG_BLOCK - struct block_device *bdev; - int ret, major; + dev_t dev; + int ret; #endif int mtdnr; @@ -169,20 +169,15 @@ int get_tree_mtd(struct fs_context *fc, /* try the old way - the hack where we allowed users to mount * /dev/mtdblock$(n) but didn't actually _use_ the blockdev */ - bdev = lookup_bdev(fc->source); - if (IS_ERR(bdev)) { - ret = PTR_ERR(bdev); + ret = lookup_bdev(fc->source, &dev); + if (ret) { errorf(fc, "MTD: Couldn't look up '%s': %d", fc->source, ret); return ret; } pr_debug("MTDSB: lookup_bdev() returned 0\n"); - major = MAJOR(bdev->bd_dev); - mtdnr = MINOR(bdev->bd_dev); - bdput(bdev); - - if (major == MTD_BLOCK_MAJOR) - return mtd_get_sb_by_nr(fc, mtdnr, fill_super); + if (MAJOR(dev) == MTD_BLOCK_MAJOR) + return mtd_get_sb_by_nr(fc, MINOR(dev), fill_super); #endif /* CONFIG_BLOCK */ diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 7143d03f0e02..b0cb5b95e892 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -133,10 +133,10 @@ static int fd_configure_device(struct se_device *dev) */ inode = file->f_mapping->host; if (S_ISBLK(inode->i_mode)) { - struct request_queue *q = bdev_get_queue(inode->i_bdev); + struct request_queue *q = bdev_get_queue(I_BDEV(inode)); unsigned long long dev_size; - fd_dev->fd_block_size = bdev_logical_block_size(inode->i_bdev); + fd_dev->fd_block_size = bdev_logical_block_size(I_BDEV(inode)); /* * Determine the number of bytes from i_size_read() minus * one (1) logical sector from underlying struct block_device @@ -559,7 +559,7 @@ fd_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb) if (S_ISBLK(inode->i_mode)) { /* The backend is block device, use discard */ - struct block_device *bdev = inode->i_bdev; + struct block_device *bdev = I_BDEV(inode); struct se_device *dev = cmd->se_dev; ret = blkdev_issue_discard(bdev, diff --git a/drivers/usb/gadget/function/storage_common.c b/drivers/usb/gadget/function/storage_common.c index f7e6c42558eb..b859a158a414 100644 --- a/drivers/usb/gadget/function/storage_common.c +++ b/drivers/usb/gadget/function/storage_common.c @@ -204,7 +204,7 @@ int fsg_lun_open(struct fsg_lun *curlun, const char *filename) if (!(filp->f_mode & FMODE_WRITE)) ro = 1; - inode = file_inode(filp); + inode = filp->f_mapping->host; if ((!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))) { LINFO(curlun, "invalid file type: %s\n", filename); goto out; @@ -221,7 +221,7 @@ int fsg_lun_open(struct fsg_lun *curlun, const char *filename) if (!(filp->f_mode & FMODE_CAN_WRITE)) ro = 1; - size = i_size_read(inode->i_mapping->host); + size = i_size_read(inode); if (size < 0) { LINFO(curlun, "unable to find file size: %s\n", filename); rc = (int) size; @@ -231,8 +231,8 @@ int fsg_lun_open(struct fsg_lun *curlun, const char *filename) if (curlun->cdrom) { blksize = 2048; blkbits = 11; - } else if (inode->i_bdev) { - blksize = bdev_logical_block_size(inode->i_bdev); + } else if (S_ISBLK(inode->i_mode)) { + blksize = bdev_logical_block_size(I_BDEV(inode)); blkbits = blksize_bits(blksize); } else { blksize = 512; diff --git a/fs/block_dev.c b/fs/block_dev.c index 2b8c0586314f..6d6e4d50834c 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -883,7 +883,6 @@ static struct block_device *bdget(dev_t dev) bdev->bd_dev = dev; inode->i_mode = S_IFBLK; inode->i_rdev = dev; - inode->i_bdev = bdev; inode->i_data.a_ops = &def_blk_aops; mapping_set_gfp_mask(&inode->i_data, GFP_USER); unlock_new_inode(inode); @@ -928,67 +927,8 @@ void bdput(struct block_device *bdev) { iput(bdev->bd_inode); } - EXPORT_SYMBOL(bdput); -static struct block_device *bd_acquire(struct inode *inode) -{ - struct block_device *bdev; - - spin_lock(&bdev_lock); - bdev = inode->i_bdev; - if (bdev && !inode_unhashed(bdev->bd_inode)) { - bdgrab(bdev); - spin_unlock(&bdev_lock); - return bdev; - } - spin_unlock(&bdev_lock); - - /* - * i_bdev references block device inode that was already shut down - * (corresponding device got removed). Remove the reference and look - * up block device inode again just in case new device got - * reestablished under the same device number. - */ - if (bdev) - bd_forget(inode); - - bdev = bdget(inode->i_rdev); - if (bdev) { - spin_lock(&bdev_lock); - if (!inode->i_bdev) { - /* - * We take an additional reference to bd_inode, - * and it's released in clear_inode() of inode. - * So, we can access it via ->i_mapping always - * without igrab(). - */ - bdgrab(bdev); - inode->i_bdev = bdev; - inode->i_mapping = bdev->bd_inode->i_mapping; - } - spin_unlock(&bdev_lock); - } - return bdev; -} - -/* Call when you free inode */ - -void bd_forget(struct inode *inode) -{ - struct block_device *bdev = NULL; - - spin_lock(&bdev_lock); - if (!sb_is_blkdev_sb(inode->i_sb)) - bdev = inode->i_bdev; - inode->i_bdev = NULL; - inode->i_mapping = &inode->i_data; - spin_unlock(&bdev_lock); - - if (bdev) - bdput(bdev); -} - /** * bd_may_claim - test whether a block device can be claimed * @bdev: block device of interest @@ -1497,38 +1437,45 @@ static int __blkdev_get(struct block_device *bdev, struct gendisk *disk, } /** - * blkdev_get - open a block device - * @bdev: block_device to open + * blkdev_get_by_dev - open a block device by device number + * @dev: device number of block device to open * @mode: FMODE_* mask * @holder: exclusive holder identifier * - * Open @bdev with @mode. If @mode includes %FMODE_EXCL, @bdev is - * open with exclusive access. Specifying %FMODE_EXCL with %NULL - * @holder is invalid. Exclusive opens may nest for the same @holder. + * Open the block device described by device number @dev. If @mode includes + * %FMODE_EXCL, the block device is opened with exclusive access. Specifying + * %FMODE_EXCL with a %NULL @holder is invalid. Exclusive opens may nest for + * the same @holder. * - * On success, the reference count of @bdev is unchanged. On failure, - * @bdev is put. + * Use this interface ONLY if you really do not have anything better - i.e. when + * you are behind a truly sucky interface and all you are given is a device + * number. Everything else should use blkdev_get_by_path(). * * CONTEXT: * Might sleep. * * RETURNS: - * 0 on success, -errno on failure. + * Reference to the block_device on success, ERR_PTR(-errno) on failure. */ -static int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder) +struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) { struct block_device *claiming; bool unblock_events = true; + struct block_device *bdev; struct gendisk *disk; int partno; int ret; ret = devcgroup_check_permission(DEVCG_DEV_BLOCK, - imajor(bdev->bd_inode), iminor(bdev->bd_inode), + MAJOR(dev), MINOR(dev), ((mode & FMODE_READ) ? DEVCG_ACC_READ : 0) | ((mode & FMODE_WRITE) ? DEVCG_ACC_WRITE : 0)); if (ret) - goto bdput; + return ERR_PTR(ret); + + bdev = bdget(dev); + if (!bdev) + return ERR_PTR(-ENOMEM); /* * If we lost a race with 'disk' being deleted, try again. See md.c. @@ -1589,10 +1536,13 @@ put_disk: if (ret == -ERESTARTSYS) goto retry; bdput: - if (ret) + if (ret) { bdput(bdev); - return ret; + return ERR_PTR(ret); + } + return bdev; } +EXPORT_SYMBOL(blkdev_get_by_dev); /** * blkdev_get_by_path - open a block device by name @@ -1600,32 +1550,30 @@ bdput: * @mode: FMODE_* mask * @holder: exclusive holder identifier * - * Open the blockdevice described by the device file at @path. @mode - * and @holder are identical to blkdev_get(). - * - * On success, the returned block_device has reference count of one. + * Open the block device described by the device file at @path. If @mode + * includes %FMODE_EXCL, the block device is opened with exclusive access. + * Specifying %FMODE_EXCL with a %NULL @holder is invalid. Exclusive opens may + * nest for the same @holder. * * CONTEXT: * Might sleep. * * RETURNS: - * Pointer to block_device on success, ERR_PTR(-errno) on failure. + * Reference to the block_device on success, ERR_PTR(-errno) on failure. */ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder) { struct block_device *bdev; - int err; - - bdev = lookup_bdev(path); - if (IS_ERR(bdev)) - return bdev; + dev_t dev; + int error; - err = blkdev_get(bdev, mode, holder); - if (err) - return ERR_PTR(err); + error = lookup_bdev(path, &dev); + if (error) + return ERR_PTR(error); - if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) { + bdev = blkdev_get_by_dev(dev, mode, holder); + if (!IS_ERR(bdev) && (mode & FMODE_WRITE) && bdev_read_only(bdev)) { blkdev_put(bdev, mode); return ERR_PTR(-EACCES); } @@ -1634,45 +1582,6 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, } EXPORT_SYMBOL(blkdev_get_by_path); -/** - * blkdev_get_by_dev - open a block device by device number - * @dev: device number of block device to open - * @mode: FMODE_* mask - * @holder: exclusive holder identifier - * - * Open the blockdevice described by device number @dev. @mode and - * @holder are identical to blkdev_get(). - * - * Use it ONLY if you really do not have anything better - i.e. when - * you are behind a truly sucky interface and all you are given is a - * device number. _Never_ to be used for internal purposes. If you - * ever need it - reconsider your API. - * - * On success, the returned block_device has reference count of one. - * - * CONTEXT: - * Might sleep. - * - * RETURNS: - * Pointer to block_device on success, ERR_PTR(-errno) on failure. - */ -struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) -{ - struct block_device *bdev; - int err; - - bdev = bdget(dev); - if (!bdev) - return ERR_PTR(-ENOMEM); - - err = blkdev_get(bdev, mode, holder); - if (err) - return ERR_PTR(err); - - return bdev; -} -EXPORT_SYMBOL(blkdev_get_by_dev); - static int blkdev_open(struct inode * inode, struct file * filp) { struct block_device *bdev; @@ -1694,14 +1603,12 @@ static int blkdev_open(struct inode * inode, struct file * filp) if ((filp->f_flags & O_ACCMODE) == 3) filp->f_mode |= FMODE_WRITE_IOCTL; - bdev = bd_acquire(inode); - if (bdev == NULL) - return -ENOMEM; - + bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp); + if (IS_ERR(bdev)) + return PTR_ERR(bdev); filp->f_mapping = bdev->bd_inode->i_mapping; filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping); - - return blkdev_get(bdev, filp->f_mode, filp); + return 0; } static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) @@ -2010,37 +1917,32 @@ const struct file_operations def_blk_fops = { * namespace if possible and return it. Return ERR_PTR(error) * otherwise. */ -struct block_device *lookup_bdev(const char *pathname) +int lookup_bdev(const char *pathname, dev_t *dev) { - struct block_device *bdev; struct inode *inode; struct path path; int error; if (!pathname || !*pathname) - return ERR_PTR(-EINVAL); + return -EINVAL; error = kern_path(pathname, LOOKUP_FOLLOW, &path); if (error) - return ERR_PTR(error); + return error; inode = d_backing_inode(path.dentry); error = -ENOTBLK; if (!S_ISBLK(inode->i_mode)) - goto fail; + goto out_path_put; error = -EACCES; if (!may_open_dev(&path)) - goto fail; - error = -ENOMEM; - bdev = bd_acquire(inode); - if (!bdev) - goto fail; -out: + goto out_path_put; + + *dev = inode->i_rdev; + error = 0; +out_path_put: path_put(&path); - return bdev; -fail: - bdev = ERR_PTR(error); - goto out; + return error; } EXPORT_SYMBOL(lookup_bdev); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a6406b3b8c2b..fbc4b58228f7 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -929,16 +929,16 @@ static noinline struct btrfs_device *device_list_add(const char *path, * make sure it's the same device if the device is mounted */ if (device->bdev) { - struct block_device *path_bdev; + int error; + dev_t path_dev; - path_bdev = lookup_bdev(path); - if (IS_ERR(path_bdev)) { + error = lookup_bdev(path, &path_dev); + if (error) { mutex_unlock(&fs_devices->device_list_mutex); - return ERR_CAST(path_bdev); + return ERR_PTR(error); } - if (device->bdev != path_bdev) { - bdput(path_bdev); + if (device->bdev->bd_dev != path_dev) { mutex_unlock(&fs_devices->device_list_mutex); btrfs_warn_in_rcu(device->fs_info, "duplicate device %s devid %llu generation %llu scanned by %s (%d)", @@ -947,7 +947,6 @@ static noinline struct btrfs_device *device_list_add(const char *path, task_pid_nr(current)); return ERR_PTR(-EEXIST); } - bdput(path_bdev); btrfs_info_in_rcu(device->fs_info, "devid %llu device path %s changed to %s scanned by %s (%d)", devid, rcu_str_deref(device->name), diff --git a/fs/inode.c b/fs/inode.c index 9d78c37b00b8..cb008acf0efd 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -155,7 +155,6 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_bytes = 0; inode->i_generation = 0; inode->i_pipe = NULL; - inode->i_bdev = NULL; inode->i_cdev = NULL; inode->i_link = NULL; inode->i_dir_seq = 0; @@ -580,8 +579,6 @@ static void evict(struct inode *inode) truncate_inode_pages_final(&inode->i_data); clear_inode(inode); } - if (S_ISBLK(inode->i_mode) && inode->i_bdev) - bd_forget(inode); if (S_ISCHR(inode->i_mode) && inode->i_cdev) cd_forget(inode); diff --git a/fs/internal.h b/fs/internal.h index 47be21dfeebe..53f890446e75 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -25,7 +25,6 @@ extern void __init bdev_cache_init(void); extern int __sync_blockdev(struct block_device *bdev, int wait); void iterate_bdevs(void (*)(struct block_device *, void *), void *); void emergency_thaw_bdev(struct super_block *sb); -void bd_forget(struct inode *inode); #else static inline void bdev_cache_init(void) { @@ -43,9 +42,6 @@ static inline int emergency_thaw_bdev(struct super_block *sb) { return 0; } -static inline void bd_forget(struct inode *inode) -{ -} #endif /* CONFIG_BLOCK */ /* @@ -114,8 +110,7 @@ extern struct file *alloc_empty_file_noaccount(int, const struct cred *); */ extern int reconfigure_super(struct fs_context *); extern bool trylock_super(struct super_block *sb); -struct super_block *__get_super(struct block_device *bdev, bool excl); -extern struct super_block *user_get_super(dev_t); +struct super_block *user_get_super(dev_t, bool excl); void put_super(struct super_block *sb); extern bool mount_capable(struct fs_context *); diff --git a/fs/io_uring.c b/fs/io_uring.c index 4ead291b2976..8f13c0417f94 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2716,11 +2716,7 @@ static struct file *__io_file_get(struct io_submit_state *state, int fd) static bool io_bdev_nowait(struct block_device *bdev) { -#ifdef CONFIG_BLOCK return !bdev || blk_queue_nowait(bdev_get_queue(bdev)); -#else - return true; -#endif } /* @@ -2733,14 +2729,16 @@ static bool io_file_supports_async(struct file *file, int rw) umode_t mode = file_inode(file)->i_mode; if (S_ISBLK(mode)) { - if (io_bdev_nowait(file->f_inode->i_bdev)) + if (IS_ENABLED(CONFIG_BLOCK) && + io_bdev_nowait(I_BDEV(file->f_mapping->host))) return true; return false; } if (S_ISCHR(mode) || S_ISSOCK(mode)) return true; if (S_ISREG(mode)) { - if (io_bdev_nowait(file->f_inode->i_sb->s_bdev) && + if (IS_ENABLED(CONFIG_BLOCK) && + io_bdev_nowait(file->f_inode->i_sb->s_bdev) && file->f_op != &io_uring_fops) return true; return false; diff --git a/fs/pipe.c b/fs/pipe.c index 0ac197658a2d..c5989cfd564d 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1342,9 +1342,8 @@ out_revert_acct: } /* - * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same - * location, so checking ->i_pipe is not enough to verify that this is a - * pipe. + * Note that i_pipe and i_cdev share the same location, so checking ->i_pipe is + * not enough to verify that this is a pipe. */ struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) { diff --git a/fs/quota/quota.c b/fs/quota/quota.c index f3d32b0d9008..6d16b2be5ac4 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -866,17 +866,18 @@ static bool quotactl_cmd_onoff(int cmd) static struct super_block *quotactl_block(const char __user *special, int cmd) { #ifdef CONFIG_BLOCK - struct block_device *bdev; struct super_block *sb; struct filename *tmp = getname(special); bool excl = false, thawed = false; + int error; + dev_t dev; if (IS_ERR(tmp)) return ERR_CAST(tmp); - bdev = lookup_bdev(tmp->name); + error = lookup_bdev(tmp->name, &dev); putname(tmp); - if (IS_ERR(bdev)) - return ERR_CAST(bdev); + if (error) + return ERR_PTR(error); if (quotactl_cmd_onoff(cmd)) { excl = true; @@ -886,8 +887,10 @@ static struct super_block *quotactl_block(const char __user *special, int cmd) } retry: - sb = __get_super(bdev, excl); - if (thawed && sb && sb->s_writers.frozen != SB_UNFROZEN) { + sb = user_get_super(dev, excl); + if (!sb) + return ERR_PTR(-ENODEV); + if (thawed && sb->s_writers.frozen != SB_UNFROZEN) { if (excl) up_write(&sb->s_umount); else @@ -897,10 +900,6 @@ retry: put_super(sb); goto retry; } - - bdput(bdev); - if (!sb) - return ERR_PTR(-ENODEV); return sb; #else diff --git a/fs/statfs.c b/fs/statfs.c index 59f33752c131..68cb07788750 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -235,7 +235,7 @@ SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, size_t, sz, struct statfs64 __user static int vfs_ustat(dev_t dev, struct kstatfs *sbuf) { - struct super_block *s = user_get_super(dev); + struct super_block *s = user_get_super(dev, false); int err; if (!s) return -EINVAL; diff --git a/fs/super.c b/fs/super.c index 343e5c1e538d..2c6cdea2ab2d 100644 --- a/fs/super.c +++ b/fs/super.c @@ -740,7 +740,14 @@ void iterate_supers_type(struct file_system_type *type, EXPORT_SYMBOL(iterate_supers_type); -struct super_block *__get_super(struct block_device *bdev, bool excl) +/** + * get_super - get the superblock of a device + * @bdev: device to get the superblock for + * + * Scans the superblock list and finds the superblock of the file system + * mounted on the device given. %NULL is returned if no match is found. + */ +struct super_block *get_super(struct block_device *bdev) { struct super_block *sb; @@ -755,17 +762,11 @@ rescan: if (sb->s_bdev == bdev) { sb->s_count++; spin_unlock(&sb_lock); - if (!excl) - down_read(&sb->s_umount); - else - down_write(&sb->s_umount); + down_read(&sb->s_umount); /* still alive? */ if (sb->s_root && (sb->s_flags & SB_BORN)) return sb; - if (!excl) - up_read(&sb->s_umount); - else - up_write(&sb->s_umount); + up_read(&sb->s_umount); /* nope, got unmounted */ spin_lock(&sb_lock); __put_super(sb); @@ -776,19 +777,6 @@ rescan: return NULL; } -/** - * get_super - get the superblock of a device - * @bdev: device to get the superblock for - * - * Scans the superblock list and finds the superblock of the file system - * mounted on the device given. %NULL is returned if no match is found. - */ -struct super_block *get_super(struct block_device *bdev) -{ - return __get_super(bdev, false); -} -EXPORT_SYMBOL(get_super); - /** * get_active_super - get an active reference to the superblock of a device * @bdev: device to get the superblock for @@ -820,7 +808,7 @@ restart: return NULL; } -struct super_block *user_get_super(dev_t dev) +struct super_block *user_get_super(dev_t dev, bool excl) { struct super_block *sb; @@ -832,11 +820,17 @@ rescan: if (sb->s_dev == dev) { sb->s_count++; spin_unlock(&sb_lock); - down_read(&sb->s_umount); + if (excl) + down_write(&sb->s_umount); + else + down_read(&sb->s_umount); /* still alive? */ if (sb->s_root && (sb->s_flags & SB_BORN)) return sb; - up_read(&sb->s_umount); + if (excl) + up_write(&sb->s_umount); + else + up_read(&sb->s_umount); /* nope, got unmounted */ spin_lock(&sb_lock); __put_super(sb); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 12810a19edeb..bdd7339bcda4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1973,7 +1973,7 @@ int bdev_read_only(struct block_device *bdev); int set_blocksize(struct block_device *bdev, int size); const char *bdevname(struct block_device *bdev, char *buffer); -struct block_device *lookup_bdev(const char *); +int lookup_bdev(const char *pathname, dev_t *dev); void blkdev_show(struct seq_file *seqf, off_t offset); diff --git a/include/linux/fs.h b/include/linux/fs.h index a61df0dd4f19..b0b358309657 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -696,7 +696,6 @@ struct inode { struct list_head i_devices; union { struct pipe_inode_info *i_pipe; - struct block_device *i_bdev; struct cdev *i_cdev; char *i_link; unsigned i_dir_seq; -- cgit v1.2.3 From a782483cc1f875355690625d8253a232f2581418 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 26 Nov 2020 18:43:37 +0100 Subject: block: remove the nr_sects field in struct hd_struct Now that the hd_struct always has a block device attached to it, there is no need for having two size field that just get out of sync. Additionally the field in hd_struct did not use proper serialization, possibly allowing for torn writes. By only using the block_device field this problem also gets fixed. Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Acked-by: Coly Li [bcache] Acked-by: Chao Yu [f2fs] Signed-off-by: Jens Axboe --- block/bio.c | 4 +-- block/blk-core.c | 2 +- block/blk.h | 53 --------------------------- block/genhd.c | 59 +++++++++++++++++------------- block/partitions/core.c | 17 +++++---- drivers/block/loop.c | 1 - drivers/block/nbd.c | 2 +- drivers/block/xen-blkback/common.h | 4 +-- drivers/md/bcache/super.c | 2 +- drivers/s390/block/dasd_ioctl.c | 4 +-- drivers/target/target_core_pscsi.c | 5 ++- fs/block_dev.c | 73 ++------------------------------------ fs/f2fs/super.c | 2 +- fs/pstore/blk.c | 2 +- include/linux/genhd.h | 29 ++++----------- kernel/trace/blktrace.c | 2 +- 16 files changed, 67 insertions(+), 194 deletions(-) (limited to 'drivers/md') diff --git a/block/bio.c b/block/bio.c index fa01bef35bb1..669bb47a3198 100644 --- a/block/bio.c +++ b/block/bio.c @@ -613,8 +613,8 @@ void guard_bio_eod(struct bio *bio) rcu_read_lock(); part = __disk_get_part(bio->bi_disk, bio->bi_partno); if (part) - maxsector = part_nr_sects_read(part); - else + maxsector = bdev_nr_sectors(part->bdev); + else maxsector = get_capacity(bio->bi_disk); rcu_read_unlock(); diff --git a/block/blk-core.c b/block/blk-core.c index 2db8bda43b6e..988f45094a38 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -755,7 +755,7 @@ static inline int blk_partition_remap(struct bio *bio) goto out; if (bio_sectors(bio)) { - if (bio_check_eod(bio, part_nr_sects_read(p))) + if (bio_check_eod(bio, bdev_nr_sectors(p->bdev))) goto out; bio->bi_iter.bi_sector += p->start_sect; trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p), diff --git a/block/blk.h b/block/blk.h index c4839abcfa27..09cee7024fb4 100644 --- a/block/blk.h +++ b/block/blk.h @@ -387,59 +387,6 @@ static inline void hd_free_part(struct hd_struct *part) percpu_ref_exit(&part->ref); } -/* - * Any access of part->nr_sects which is not protected by partition - * bd_mutex or gendisk bdev bd_mutex, should be done using this - * accessor function. - * - * Code written along the lines of i_size_read() and i_size_write(). - * CONFIG_PREEMPTION case optimizes the case of UP kernel with preemption - * on. - */ -static inline sector_t part_nr_sects_read(struct hd_struct *part) -{ -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - sector_t nr_sects; - unsigned seq; - do { - seq = read_seqcount_begin(&part->nr_sects_seq); - nr_sects = part->nr_sects; - } while (read_seqcount_retry(&part->nr_sects_seq, seq)); - return nr_sects; -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) - sector_t nr_sects; - - preempt_disable(); - nr_sects = part->nr_sects; - preempt_enable(); - return nr_sects; -#else - return part->nr_sects; -#endif -} - -/* - * Should be called with mutex lock held (typically bd_mutex) of partition - * to provide mutual exlusion among writers otherwise seqcount might be - * left in wrong state leaving the readers spinning infinitely. - */ -static inline void part_nr_sects_write(struct hd_struct *part, sector_t size) -{ -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - preempt_disable(); - write_seqcount_begin(&part->nr_sects_seq); - part->nr_sects = size; - write_seqcount_end(&part->nr_sects_seq); - preempt_enable(); -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) - preempt_disable(); - part->nr_sects = size; - preempt_enable(); -#else - part->nr_sects = size; -#endif -} - int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, unsigned int max_sectors, bool *same_page); diff --git a/block/genhd.c b/block/genhd.c index bf8fa82f135f..c65f485b9db5 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -40,6 +40,16 @@ static void disk_add_events(struct gendisk *disk); static void disk_del_events(struct gendisk *disk); static void disk_release_events(struct gendisk *disk); +void set_capacity(struct gendisk *disk, sector_t sectors) +{ + struct block_device *bdev = disk->part0.bdev; + + spin_lock(&bdev->bd_size_lock); + i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); + spin_unlock(&bdev->bd_size_lock); +} +EXPORT_SYMBOL(set_capacity); + /* * Set disk capacity and notify if the size is not currently zero and will not * be set to zero. Returns true if a uevent was sent, otherwise false. @@ -47,18 +57,30 @@ static void disk_release_events(struct gendisk *disk); bool set_capacity_and_notify(struct gendisk *disk, sector_t size) { sector_t capacity = get_capacity(disk); + char *envp[] = { "RESIZE=1", NULL }; set_capacity(disk, size); - revalidate_disk_size(disk, true); - if (capacity != size && capacity != 0 && size != 0) { - char *envp[] = { "RESIZE=1", NULL }; + /* + * Only print a message and send a uevent if the gendisk is user visible + * and alive. This avoids spamming the log and udev when setting the + * initial capacity during probing. + */ + if (size == capacity || + (disk->flags & (GENHD_FL_UP | GENHD_FL_HIDDEN)) != GENHD_FL_UP) + return false; - kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); - return true; - } + pr_info("%s: detected capacity change from %lld to %lld\n", + disk->disk_name, size, capacity); - return false; + /* + * Historically we did not send a uevent for changes to/from an empty + * device. + */ + if (!capacity || !size) + return false; + kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); + return true; } EXPORT_SYMBOL_GPL(set_capacity_and_notify); @@ -247,7 +269,7 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter) part = rcu_dereference(ptbl->part[piter->idx]); if (!part) continue; - if (!part_nr_sects_read(part) && + if (!bdev_nr_sectors(part->bdev) && !(piter->flags & DISK_PITER_INCL_EMPTY) && !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 && piter->idx == 0)) @@ -284,7 +306,7 @@ EXPORT_SYMBOL_GPL(disk_part_iter_exit); static inline int sector_in_part(struct hd_struct *part, sector_t sector) { return part->start_sect <= sector && - sector < part->start_sect + part_nr_sects_read(part); + sector < part->start_sect + bdev_nr_sectors(part->bdev); } /** @@ -986,8 +1008,8 @@ void __init printk_all_partitions(void) printk("%s%s %10llu %s %s", is_part0 ? "" : " ", bdevt_str(part_devt(part), devt_buf), - (unsigned long long)part_nr_sects_read(part) >> 1 - , disk_name(disk, part->partno, name_buf), + bdev_nr_sectors(part->bdev) >> 1, + disk_name(disk, part->partno, name_buf), part->info ? part->info->uuid : ""); if (is_part0) { if (dev->parent && dev->parent->driver) @@ -1079,7 +1101,7 @@ static int show_partition(struct seq_file *seqf, void *v) while ((part = disk_part_iter_next(&piter))) seq_printf(seqf, "%4d %7d %10llu %s\n", MAJOR(part_devt(part)), MINOR(part_devt(part)), - (unsigned long long)part_nr_sects_read(part) >> 1, + bdev_nr_sectors(part->bdev) >> 1, disk_name(sgp, part->partno, buf)); disk_part_iter_exit(&piter); @@ -1161,8 +1183,7 @@ ssize_t part_size_show(struct device *dev, { struct hd_struct *p = dev_to_part(dev); - return sprintf(buf, "%llu\n", - (unsigned long long)part_nr_sects_read(p)); + return sprintf(buf, "%llu\n", bdev_nr_sectors(p->bdev)); } ssize_t part_stat_show(struct device *dev, @@ -1618,16 +1639,6 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) ptbl = rcu_dereference_protected(disk->part_tbl, 1); rcu_assign_pointer(ptbl->part[0], &disk->part0); - /* - * set_capacity() and get_capacity() currently don't use - * seqcounter to read/update the part0->nr_sects. Still init - * the counter as we can read the sectors in IO submission - * patch using seqence counters. - * - * TODO: Ideally set_capacity() and get_capacity() should be - * converted to make use of bd_mutex and sequence counters. - */ - hd_sects_seq_init(&disk->part0); if (hd_ref_init(&disk->part0)) goto out_free_bdstats; diff --git a/block/partitions/core.c b/block/partitions/core.c index 696bd9ff63c6..bcfa8215bd5e 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -85,6 +85,13 @@ static int (*check_part[])(struct parsed_partitions *) = { NULL }; +static void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors) +{ + spin_lock(&bdev->bd_size_lock); + i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); + spin_unlock(&bdev->bd_size_lock); +} + static struct parsed_partitions *allocate_partitions(struct gendisk *hd) { struct parsed_partitions *state; @@ -295,7 +302,7 @@ static void hd_struct_free_work(struct work_struct *work) put_device(disk_to_dev(disk)); part->start_sect = 0; - part->nr_sects = 0; + bdev_set_nr_sectors(part->bdev, 0); part_stat_set_all(part, 0); put_device(part_to_dev(part)); } @@ -412,11 +419,10 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno, goto out_free_stats; p->bdev = bdev; - hd_sects_seq_init(p); pdev = part_to_dev(p); p->start_sect = start; - p->nr_sects = len; + bdev_set_nr_sectors(bdev, len); p->partno = partno; p->policy = get_disk_ro(disk); @@ -509,7 +515,7 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start, disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY); while ((part = disk_part_iter_next(&piter))) { if (part->partno == skip_partno || - start >= part->start_sect + part->nr_sects || + start >= part->start_sect + bdev_nr_sectors(part->bdev) || start + length <= part->start_sect) continue; overlap = true; @@ -600,8 +606,7 @@ 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, length); - bd_set_nr_sectors(bdevp, length); + bdev_set_nr_sectors(bdevp, length); ret = 0; out_unlock: diff --git a/drivers/block/loop.c b/drivers/block/loop.c index d643c67be6ac..d2ce1ddc192d 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1241,7 +1241,6 @@ 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_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 45b0423ef2c5..014683968ce1 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1132,7 +1132,7 @@ static void nbd_bdev_reset(struct block_device *bdev) { if (bdev->bd_openers > 1) return; - bd_set_nr_sectors(bdev, 0); + set_capacity(bdev->bd_disk, 0); } static void nbd_parse_flags(struct nbd_device *nbd) diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index c6ea5d38c509..0762db247b41 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -358,9 +358,7 @@ struct pending_req { }; -#define vbd_sz(_v) ((_v)->bdev->bd_part ? \ - (_v)->bdev->bd_part->nr_sects : \ - get_capacity((_v)->bdev->bd_disk)) +#define vbd_sz(_v) bdev_nr_sectors((_v)->bdev) #define xen_blkif_get(_b) (atomic_inc(&(_b)->refcnt)) #define xen_blkif_put(_b) \ diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index c55d3c58a7ef..04fa40868fbe 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1408,7 +1408,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) q->limits.raid_partial_stripes_expensive; ret = bcache_device_init(&dc->disk, block_size, - dc->bdev->bd_part->nr_sects - dc->sb.data_offset, + bdev_nr_sectors(dc->bdev) - dc->sb.data_offset, dc->bdev, &bcache_cached_ops); if (ret) return ret; diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index 3359559517bf..304eba1acf16 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -54,8 +54,6 @@ dasd_ioctl_enable(struct block_device *bdev) return -ENODEV; dasd_enable_device(base); - /* Formatting the dasd device can change the capacity. */ - bd_set_nr_sectors(bdev, get_capacity(base->block->gdp)); dasd_put_device(base); return 0; } @@ -88,7 +86,7 @@ dasd_ioctl_disable(struct block_device *bdev) * Set i_size to zero, since read, write, etc. check against this * value. */ - bd_set_nr_sectors(bdev, 0); + set_capacity(bdev->bd_disk, 0); dasd_put_device(base); return 0; } diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 4e37fa9b409d..7994f27e4527 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -1029,9 +1029,8 @@ static sector_t pscsi_get_blocks(struct se_device *dev) { struct pscsi_dev_virt *pdv = PSCSI_DEV(dev); - if (pdv->pdv_bd && pdv->pdv_bd->bd_part) - return pdv->pdv_bd->bd_part->nr_sects; - + if (pdv->pdv_bd) + return bdev_nr_sectors(pdv->pdv_bd); return 0; } diff --git a/fs/block_dev.c b/fs/block_dev.c index a5b6955a841f..31ee5a857f71 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1208,70 +1208,6 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); #endif -/** - * check_disk_size_change - checks for disk size change and adjusts bdev size. - * @disk: struct gendisk to check - * @bdev: struct bdev to adjust. - * @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. - */ -static void check_disk_size_change(struct gendisk *disk, - struct block_device *bdev, bool verbose) -{ - 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) { - if (verbose) { - printk(KERN_INFO - "%s: detected capacity change from %lld to %lld\n", - disk->disk_name, bdev_size, disk_size); - } - i_size_write(bdev->bd_inode, disk_size); - } - spin_unlock(&bdev->bd_size_lock); -} - -/** - * 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); - } -} - -void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors) -{ - spin_lock(&bdev->bd_size_lock); - i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); - spin_unlock(&bdev->bd_size_lock); -} -EXPORT_SYMBOL(bd_set_nr_sectors); - static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); int bdev_disk_changed(struct block_device *bdev, bool invalidate) @@ -1305,8 +1241,6 @@ rescan: disk->fops->revalidate_disk(disk); } - check_disk_size_change(disk, bdev, !invalidate); - if (get_capacity(disk)) { ret = blk_add_partitions(disk, bdev); if (ret == -EAGAIN) @@ -1349,10 +1283,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) if (disk->fops->open) ret = disk->fops->open(bdev, mode); - if (!ret) { - bd_set_nr_sectors(bdev, get_capacity(disk)); + if (!ret) set_init_blocksize(bdev); - } /* * If the device is invalidated, rescan partition @@ -1381,13 +1313,12 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) bdev->bd_part = disk_get_part(disk, bdev->bd_partno); if (!(disk->flags & GENHD_FL_UP) || - !bdev->bd_part || !bdev->bd_part->nr_sects) { + !bdev->bd_part || !bdev_nr_sectors(bdev)) { __blkdev_put(whole, mode, 1); bdput(whole); ret = -ENXIO; goto out_clear; } - bd_set_nr_sectors(bdev, bdev->bd_part->nr_sects); set_init_blocksize(bdev); } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 00eff2f51807..d4e7fab352ba 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3151,7 +3151,7 @@ static int f2fs_report_zone_cb(struct blk_zone *zone, unsigned int idx, static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) { struct block_device *bdev = FDEV(devi).bdev; - sector_t nr_sectors = bdev->bd_part->nr_sects; + sector_t nr_sectors = bdev_nr_sectors(bdev); struct f2fs_report_zones_args rep_zone_arg; int ret; diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c index fcd5563dde06..777a26f7bbe2 100644 --- a/fs/pstore/blk.c +++ b/fs/pstore/blk.c @@ -245,7 +245,7 @@ static struct block_device *psblk_get_bdev(void *holder, return bdev; } - nr_sects = part_nr_sects_read(bdev->bd_part); + nr_sects = bdev_nr_sectors(bdev); if (!nr_sects) { pr_err("not enough space for '%s'\n", blkdev); blkdev_put(bdev, mode); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 6ba91ee54cb2..30d4785b7df8 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -52,15 +52,6 @@ struct partition_meta_info { struct hd_struct { sector_t start_sect; - /* - * nr_sects is protected by sequence counter. One might extend a - * partition while IO is happening to it and update of nr_sects - * can be non-atomic on 32bit machines with 64bit sector_t. - */ - sector_t nr_sects; -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - seqcount_t nr_sects_seq; -#endif unsigned long stamp; struct disk_stats __percpu *dkstats; struct percpu_ref ref; @@ -254,13 +245,6 @@ static inline void disk_put_part(struct hd_struct *part) put_device(part_to_dev(part)); } -static inline void hd_sects_seq_init(struct hd_struct *p) -{ -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - seqcount_init(&p->nr_sects_seq); -#endif -} - /* * Smarter partition iterator without context limits. */ @@ -318,13 +302,15 @@ static inline sector_t get_start_sect(struct block_device *bdev) { return bdev->bd_part->start_sect; } -static inline sector_t get_capacity(struct gendisk *disk) + +static inline sector_t bdev_nr_sectors(struct block_device *bdev) { - return disk->part0.nr_sects; + return i_size_read(bdev->bd_inode) >> 9; } -static inline void set_capacity(struct gendisk *disk, sector_t size) + +static inline sector_t get_capacity(struct gendisk *disk) { - disk->part0.nr_sects = size; + return bdev_nr_sectors(disk->part0.bdev); } int bdev_disk_changed(struct block_device *bdev, bool invalidate); @@ -358,10 +344,9 @@ int __register_blkdev(unsigned int major, const char *name, __register_blkdev(major, name, NULL) void unregister_blkdev(unsigned int major, const char *name); -void revalidate_disk_size(struct gendisk *disk, bool verbose); 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); +void set_capacity(struct gendisk *disk, sector_t size); /* for drivers/char/raw.c: */ int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index f1022945e346..7076d588a50d 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -465,7 +465,7 @@ static void blk_trace_setup_lba(struct blk_trace *bt, if (part) { bt->start_lba = part->start_sect; - bt->end_lba = part->start_sect + part->nr_sects; + bt->end_lba = part->start_sect + bdev_nr_sectors(bdev); } else { bt->start_lba = 0; bt->end_lba = -1ULL; -- cgit v1.2.3 From cb8432d650fe3be58bb962bc8e602dc405510327 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 26 Nov 2020 18:47:17 +0100 Subject: block: allocate struct hd_struct as part of struct bdev_inode Allocate hd_struct together with struct block_device to pre-load the lifetime rule changes in preparation of merging the two structures. Note that part0 was previously embedded into struct gendisk, but is a separate allocation now, and already points to the block_device instead of the hd_struct. The lifetime of struct gendisk is still controlled by the struct device embedded in the part0 hd_struct. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/blk-core.c | 16 ++++----- block/blk-flush.c | 2 +- block/blk-merge.c | 2 -- block/blk.h | 21 ------------ block/genhd.c | 50 +++++++++++----------------- block/partitions/core.c | 67 ++++---------------------------------- drivers/block/drbd/drbd_receiver.c | 2 +- drivers/block/drbd/drbd_worker.c | 3 +- drivers/block/zram/zram_drv.c | 2 +- drivers/md/dm.c | 4 +-- drivers/md/md.c | 2 +- fs/block_dev.c | 39 +++++++--------------- include/linux/blk_types.h | 2 +- include/linux/genhd.h | 14 ++++---- include/linux/part_stat.h | 4 +-- 15 files changed, 61 insertions(+), 169 deletions(-) (limited to 'drivers/md') diff --git a/block/blk-core.c b/block/blk-core.c index d64ffcb6f9ae..9ea70275fc1c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -714,7 +714,8 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) static noinline int should_fail_bio(struct bio *bio) { - if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size)) + if (should_fail_request(bio->bi_disk->part0->bd_part, + bio->bi_iter.bi_size)) return -EIO; return 0; } @@ -831,7 +832,7 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio) if (unlikely(blk_partition_remap(bio))) goto end_io; } else { - if (unlikely(bio_check_ro(bio, &bio->bi_disk->part0))) + if (unlikely(bio_check_ro(bio, bio->bi_disk->part0->bd_part))) goto end_io; if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk)))) goto end_io; @@ -1203,7 +1204,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request * return ret; if (rq->rq_disk && - should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq))) + should_fail_request(rq->rq_disk->part0->bd_part, blk_rq_bytes(rq))) return BLK_STS_IOERR; if (blk_crypto_insert_cloned_request(rq)) @@ -1272,7 +1273,7 @@ again: __part_stat_add(part, io_ticks, end ? now - stamp : 1); } if (part->partno) { - part = &part_to_disk(part)->part0; + part = part_to_disk(part)->part0->bd_part; goto again; } } @@ -1309,8 +1310,6 @@ void blk_account_io_done(struct request *req, u64 now) part_stat_inc(part, ios[sgrp]); part_stat_add(part, nsecs[sgrp], now - req->start_time_ns); part_stat_unlock(); - - hd_struct_put(part); } } @@ -1354,7 +1353,7 @@ 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); + return __part_start_io_acct(disk->part0->bd_part, sectors, op); } EXPORT_SYMBOL(disk_start_io_acct); @@ -1376,14 +1375,13 @@ 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); + __part_end_io_acct(disk->part0->bd_part, op, start_time); } EXPORT_SYMBOL(disk_end_io_acct); diff --git a/block/blk-flush.c b/block/blk-flush.c index e32958f0b687..fcd0a60574df 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -139,7 +139,7 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front) static void blk_account_io_flush(struct request *rq) { - struct hd_struct *part = &rq->rq_disk->part0; + struct hd_struct *part = rq->rq_disk->part0->bd_part; part_stat_lock(); part_stat_inc(part, ios[STAT_FLUSH]); diff --git a/block/blk-merge.c b/block/blk-merge.c index bcf5e4580603..cb351ab9b77d 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -683,8 +683,6 @@ static void blk_account_io_merge_request(struct request *req) part_stat_lock(); part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); part_stat_unlock(); - - hd_struct_put(req->part); } } diff --git a/block/blk.h b/block/blk.h index 0bd4b58bcbaf..32ac41f7557f 100644 --- a/block/blk.h +++ b/block/blk.h @@ -363,27 +363,6 @@ int bdev_del_partition(struct block_device *bdev, int partno); int bdev_resize_partition(struct block_device *bdev, int partno, sector_t start, sector_t length); int disk_expand_part_tbl(struct gendisk *disk, int target); -int hd_ref_init(struct hd_struct *part); - -/* no need to get/put refcount of part0 */ -static inline int hd_struct_try_get(struct hd_struct *part) -{ - if (part->partno) - return percpu_ref_tryget_live(&part->ref); - return 1; -} - -static inline void hd_struct_put(struct hd_struct *part) -{ - if (part->partno) - percpu_ref_put(&part->ref); -} - -static inline void hd_free_part(struct hd_struct *part) -{ - bdput(part->bdev); - percpu_ref_exit(&part->ref); -} int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, diff --git a/block/genhd.c b/block/genhd.c index 2db1204920a9..c35b03dac5e5 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -42,7 +42,7 @@ static void disk_release_events(struct gendisk *disk); void set_capacity(struct gendisk *disk, sector_t sectors) { - struct block_device *bdev = disk->part0.bdev; + struct block_device *bdev = disk->part0; spin_lock(&bdev->bd_size_lock); i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); @@ -318,9 +318,7 @@ static inline int sector_in_part(struct hd_struct *part, sector_t sector) * primarily used for stats accounting. * * CONTEXT: - * RCU read locked. The returned partition pointer is always valid - * because its refcount is grabbed except for part0, which lifetime - * is same with the disk. + * RCU read locked. * * RETURNS: * Found partition on success, part0 is returned if no partition matches @@ -336,26 +334,19 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) ptbl = rcu_dereference(disk->part_tbl); part = rcu_dereference(ptbl->last_lookup); - if (part && sector_in_part(part, sector) && hd_struct_try_get(part)) + if (part && sector_in_part(part, sector)) goto out_unlock; for (i = 1; i < ptbl->len; i++) { part = rcu_dereference(ptbl->part[i]); if (part && sector_in_part(part, sector)) { - /* - * only live partition can be cached for lookup, - * so use-after-free on cached & deleting partition - * can be avoided - */ - if (!hd_struct_try_get(part)) - break; rcu_assign_pointer(ptbl->last_lookup, part); goto out_unlock; } } - part = &disk->part0; + part = disk->part0->bd_part; out_unlock: rcu_read_unlock(); return part; @@ -681,8 +672,8 @@ static void register_disk(struct device *parent, struct gendisk *disk, */ pm_runtime_set_memalloc_noio(ddev, true); - disk->part0.bdev->bd_holder_dir = - kobject_create_and_add("holders", &ddev->kobj); + disk->part0->bd_holder_dir = + kobject_create_and_add("holders", &ddev->kobj); disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj); if (disk->flags & GENHD_FL_HIDDEN) { @@ -748,7 +739,7 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, disk->flags |= GENHD_FL_UP; - retval = blk_alloc_devt(&disk->part0, &devt); + retval = blk_alloc_devt(disk->part0->bd_part, &devt); if (retval) { WARN_ON(1); return; @@ -775,7 +766,7 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, ret = bdi_register(bdi, "%u:%u", MAJOR(devt), MINOR(devt)); WARN_ON(ret); bdi_set_owner(bdi, dev); - bdev_add(disk->part0.bdev, devt); + bdev_add(disk->part0, devt); } register_disk(parent, disk, groups); if (register_queue) @@ -888,11 +879,11 @@ void del_gendisk(struct gendisk *disk) blk_unregister_queue(disk); - kobject_put(disk->part0.bdev->bd_holder_dir); + kobject_put(disk->part0->bd_holder_dir); kobject_put(disk->slave_dir); - part_stat_set_all(&disk->part0, 0); - disk->part0.bdev->bd_stamp = 0; + part_stat_set_all(disk->part0->bd_part, 0); + disk->part0->bd_stamp = 0; if (!sysfs_deprecated) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); @@ -1005,7 +996,7 @@ void __init printk_all_partitions(void) */ disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0); while ((part = disk_part_iter_next(&piter))) { - bool is_part0 = part == &disk->part0; + bool is_part0 = part == disk->part0->bd_part; printk("%s%s %10llu %s %s", is_part0 ? "" : " ", bdevt_str(part_devt(part), devt_buf), @@ -1460,7 +1451,7 @@ static void disk_release(struct device *dev) disk_release_events(disk); kfree(disk->random); disk_replace_part_tbl(disk, NULL); - hd_free_part(&disk->part0); + bdput(disk->part0); if (disk->queue) blk_put_queue(disk->queue); kfree(disk); @@ -1626,8 +1617,8 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) if (!disk) return NULL; - disk->part0.bdev = bdev_alloc(disk, 0); - if (!disk->part0.bdev) + disk->part0 = bdev_alloc(disk, 0); + if (!disk->part0) goto out_free_disk; disk->node_id = node_id; @@ -1635,10 +1626,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) goto out_bdput; ptbl = rcu_dereference_protected(disk->part_tbl, 1); - rcu_assign_pointer(ptbl->part[0], &disk->part0); - - if (hd_ref_init(&disk->part0)) - goto out_bdput; + rcu_assign_pointer(ptbl->part[0], disk->part0->bd_part); disk->minors = minors; rand_initialize_disk(disk); @@ -1648,7 +1636,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) return disk; out_bdput: - bdput(disk->part0.bdev); + bdput(disk->part0); out_free_disk: kfree(disk); return NULL; @@ -1687,9 +1675,9 @@ void set_disk_ro(struct gendisk *disk, int flag) struct disk_part_iter piter; struct hd_struct *part; - if (disk->part0.bdev->bd_read_only != flag) { + if (disk->part0->bd_read_only != flag) { set_disk_ro_uevent(disk, flag); - disk->part0.bdev->bd_read_only = flag; + disk->part0->bd_read_only = flag; } disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY); diff --git a/block/partitions/core.c b/block/partitions/core.c index 060c1be13cd8..6d1fca193cbd 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -265,9 +265,9 @@ static const struct attribute_group *part_attr_groups[] = { static void part_release(struct device *dev) { struct hd_struct *p = dev_to_part(dev); + blk_free_devt(dev->devt); - hd_free_part(p); - kfree(p); + bdput(p->bdev); } static int part_uevent(struct device *dev, struct kobj_uevent_env *env) @@ -288,46 +288,6 @@ struct device_type part_type = { .uevent = part_uevent, }; -static void hd_struct_free_work(struct work_struct *work) -{ - struct hd_struct *part = - container_of(to_rcu_work(work), struct hd_struct, rcu_work); - struct gendisk *disk = part_to_disk(part); - - /* - * Release the disk reference acquired in delete_partition here. - * We can't release it in hd_struct_free because the final put_device - * needs process context and thus can't be run directly from a - * percpu_ref ->release handler. - */ - put_device(disk_to_dev(disk)); - - part->bdev->bd_start_sect = 0; - bdev_set_nr_sectors(part->bdev, 0); - part_stat_set_all(part, 0); - put_device(part_to_dev(part)); -} - -static void hd_struct_free(struct percpu_ref *ref) -{ - struct hd_struct *part = container_of(ref, struct hd_struct, ref); - struct gendisk *disk = part_to_disk(part); - struct disk_part_tbl *ptbl = - rcu_dereference_protected(disk->part_tbl, 1); - - rcu_assign_pointer(ptbl->last_lookup, NULL); - - INIT_RCU_WORK(&part->rcu_work, hd_struct_free_work); - queue_rcu_work(system_wq, &part->rcu_work); -} - -int hd_ref_init(struct hd_struct *part) -{ - if (percpu_ref_init(&part->ref, hd_struct_free, 0, GFP_KERNEL)) - return -ENOMEM; - return 0; -} - /* * Must be called either with bd_mutex held, before a disk can be opened or * after all disk users are gone. @@ -342,8 +302,8 @@ void delete_partition(struct hd_struct *part) * ->part_tbl is referenced in this part's release handler, so * we have to hold the disk device */ - get_device(disk_to_dev(disk)); rcu_assign_pointer(ptbl->part[part->partno], NULL); + rcu_assign_pointer(ptbl->last_lookup, NULL); kobject_put(part->bdev->bd_holder_dir); device_del(part_to_dev(part)); @@ -353,7 +313,7 @@ void delete_partition(struct hd_struct *part) */ remove_inode_hash(part->bdev->bd_inode); - percpu_ref_kill(&part->ref); + put_device(part_to_dev(part)); } static ssize_t whole_disk_show(struct device *dev, @@ -406,15 +366,11 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno, if (ptbl->part[partno]) return ERR_PTR(-EBUSY); - p = kzalloc(sizeof(*p), GFP_KERNEL); - if (!p) - return ERR_PTR(-EBUSY); - bdev = bdev_alloc(disk, partno); if (!bdev) - goto out_free; - p->bdev = bdev; + return ERR_PTR(-ENOMEM); + p = bdev->bd_part; pdev = part_to_dev(p); bdev->bd_start_sect = start; @@ -463,13 +419,6 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno, goto out_del; } - err = hd_ref_init(p); - if (err) { - if (flags & ADDPART_FLAG_WHOLEDISK) - goto out_remove_file; - goto out_del; - } - /* everything is up and running, commence */ bdev_add(bdev, devt); rcu_assign_pointer(ptbl->part[partno], p); @@ -481,11 +430,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno, out_bdput: bdput(bdev); -out_free: - kfree(p); return ERR_PTR(err); -out_remove_file: - device_remove_file(pdev, &dev_attr_whole_disk); out_del: kobject_put(bdev->bd_holder_dir); device_del(pdev); diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index dc333dbe5232..9e5c2fdfda36 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -2802,7 +2802,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device) if (c_min_rate == 0) return false; - curr_events = (int)part_stat_read_accum(&disk->part0, sectors) - + curr_events = (int)part_stat_read_accum(disk->part0->bd_part, sectors) - atomic_read(&device->rs_sect_ev); if (atomic_read(&device->ap_actlog_cnt) diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index ba56f3f05312..343f56b86bb7 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -1678,7 +1678,8 @@ void drbd_rs_controller_reset(struct drbd_device *device) atomic_set(&device->rs_sect_in, 0); atomic_set(&device->rs_sect_ev, 0); device->rs_in_flight = 0; - device->rs_last_events = (int)part_stat_read_accum(&disk->part0, sectors); + device->rs_last_events = + (int)part_stat_read_accum(disk->part0->bd_part, sectors); /* Updating the RCU protected object in place is necessary since this function gets called from atomic context. diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index b5f68951c9d2..6d84876a9cd0 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1687,7 +1687,7 @@ static void zram_reset_device(struct zram *zram) zram->disksize = 0; set_capacity_and_notify(zram->disk, 0); - part_stat_set_all(&zram->disk->part0, 0); + part_stat_set_all(zram->disk->part0->bd_part, 0); up_write(&zram->init_lock); /* I/O operation under all of CPU are done so let's free */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 48051db006f3..1b2db4d530ea 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1607,7 +1607,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, * (by eliminating DM's splitting and just using bio_split) */ part_stat_lock(); - __dm_part_stat_sub(&dm_disk(md)->part0, + __dm_part_stat_sub(dm_disk(md)->part0->bd_part, sectors[op_stat_group(bio_op(bio))], ci.sector_count); part_stat_unlock(); @@ -2242,7 +2242,7 @@ EXPORT_SYMBOL_GPL(dm_put); static bool md_in_flight_bios(struct mapped_device *md) { int cpu; - struct hd_struct *part = &dm_disk(md)->part0; + struct hd_struct *part = dm_disk(md)->part0->bd_part; long sum = 0; for_each_possible_cpu(cpu) { diff --git a/drivers/md/md.c b/drivers/md/md.c index 7ce6047c856e..3696c2d77a4d 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8441,7 +8441,7 @@ static int is_mddev_idle(struct mddev *mddev, int init) rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) { struct gendisk *disk = rdev->bdev->bd_disk; - curr_events = (int)part_stat_read_accum(&disk->part0, sectors) - + curr_events = (int)part_stat_read_accum(disk->part0->bd_part, sectors) - atomic_read(&disk->sync_io); /* sync IO will cause sync_io to increase before the disk_stats * as sync_io is counted when a request starts, and diff --git a/fs/block_dev.c b/fs/block_dev.c index 381c22426f43..61cf33b6284f 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -39,6 +39,7 @@ struct bdev_inode { struct block_device bdev; + struct hd_struct hd; struct inode vfs_inode; }; @@ -886,6 +887,9 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) iput(inode); return NULL; } + bdev->bd_part = &BDEV_I(inode)->hd; + memset(bdev->bd_part, 0, sizeof(*bdev->bd_part)); + bdev->bd_part->bdev = bdev; return bdev; } @@ -1280,15 +1284,10 @@ EXPORT_SYMBOL_GPL(bdev_disk_changed); static int __blkdev_get(struct block_device *bdev, fmode_t mode) { struct gendisk *disk = bdev->bd_disk; - int ret; + int ret = 0; if (!bdev->bd_openers) { if (!bdev_is_partition(bdev)) { - ret = -ENXIO; - bdev->bd_part = disk_get_part(disk, 0); - if (!bdev->bd_part) - goto out_clear; - ret = 0; if (disk->fops->open) ret = disk->fops->open(bdev, mode); @@ -1307,7 +1306,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) bdev_disk_changed(bdev, ret == -ENOMEDIUM); if (ret) - goto out_clear; + return ret; } else { struct block_device *whole = bdget_disk(disk, 0); @@ -1316,18 +1315,16 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) if (ret) { mutex_unlock(&whole->bd_mutex); bdput(whole); - goto out_clear; + return ret; } whole->bd_part_count++; mutex_unlock(&whole->bd_mutex); - bdev->bd_part = disk_get_part(disk, bdev->bd_partno); if (!(disk->flags & GENHD_FL_UP) || - !bdev->bd_part || !bdev_nr_sectors(bdev)) { + !bdev_nr_sectors(bdev)) { __blkdev_put(whole, mode, 1); bdput(whole); - ret = -ENXIO; - goto out_clear; + return -ENXIO; } set_init_blocksize(bdev); } @@ -1336,7 +1333,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info); } else { if (!bdev_is_partition(bdev)) { - ret = 0; if (bdev->bd_disk->fops->open) ret = bdev->bd_disk->fops->open(bdev, mode); /* the same as first opener case, read comment there */ @@ -1349,11 +1345,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) } bdev->bd_openers++; return 0; - - out_clear: - disk_put_part(bdev->bd_part); - bdev->bd_part = NULL; - return ret; } struct block_device *blkdev_get_no_open(dev_t dev) @@ -1580,18 +1571,12 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) sync_blockdev(bdev); kill_bdev(bdev); bdev_write_inode(bdev); - - if (!bdev_is_partition(bdev) && disk->fops->release) - disk->fops->release(disk, mode); - - disk_put_part(bdev->bd_part); - bdev->bd_part = NULL; if (bdev_is_partition(bdev)) victim = bdev_whole(bdev); - } else { - if (!bdev_is_partition(bdev) && disk->fops->release) - disk->fops->release(disk, mode); } + + if (!bdev_is_partition(bdev) && disk->fops->release) + disk->fops->release(disk, mode); mutex_unlock(&bdev->bd_mutex); if (victim) { __blkdev_put(victim, mode, 1); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 758cf71c9aa2..6edea5c16259 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -59,7 +59,7 @@ struct block_device { } __randomize_layout; #define bdev_whole(_bdev) \ - ((_bdev)->bd_disk->part0.bdev) + ((_bdev)->bd_disk->part0) #define bdev_kobj(_bdev) \ (&part_to_dev((_bdev)->bd_part)->kobj) diff --git a/include/linux/genhd.h b/include/linux/genhd.h index dcbf9ef7610e..df7319da013c 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -19,11 +19,12 @@ #include #include -#define dev_to_disk(device) container_of((device), struct gendisk, part0.__dev) #define dev_to_part(device) container_of((device), struct hd_struct, __dev) -#define disk_to_dev(disk) (&(disk)->part0.__dev) #define part_to_dev(part) (&((part)->__dev)) +#define dev_to_disk(device) (dev_to_part(device)->bdev->bd_disk) +#define disk_to_dev(disk) (part_to_dev((disk)->part0->bd_part)) + extern const struct device_type disk_type; extern struct device_type part_type; extern struct class block_class; @@ -51,12 +52,9 @@ struct partition_meta_info { }; struct hd_struct { - struct percpu_ref ref; - struct block_device *bdev; struct device __dev; int partno; - struct rcu_work rcu_work; }; /** @@ -168,7 +166,7 @@ struct gendisk { * helpers. */ struct disk_part_tbl __rcu *part_tbl; - struct hd_struct part0; + struct block_device *part0; const struct block_device_operations *fops; struct request_queue *queue; @@ -278,7 +276,7 @@ extern void set_disk_ro(struct gendisk *disk, int flag); static inline int get_disk_ro(struct gendisk *disk) { - return disk->part0.bdev->bd_read_only; + return disk->part0->bd_read_only; } extern void disk_block_events(struct gendisk *disk); @@ -302,7 +300,7 @@ static inline sector_t bdev_nr_sectors(struct block_device *bdev) static inline sector_t get_capacity(struct gendisk *disk) { - return bdev_nr_sectors(disk->part0.bdev); + return bdev_nr_sectors(disk->part0); } int bdev_disk_changed(struct block_device *bdev, bool invalidate); diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index 87ad60106e1d..680de036691e 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -59,8 +59,8 @@ static inline void part_stat_set_all(struct hd_struct *part, int value) #define part_stat_add(part, field, addnd) do { \ __part_stat_add((part), field, addnd); \ if ((part)->partno) \ - __part_stat_add(&part_to_disk((part))->part0, \ - field, addnd); \ + __part_stat_add(part_to_disk((part))->part0->bd_part, \ + field, addnd); \ } while (0) #define part_stat_dec(part, field) \ -- cgit v1.2.3 From 8446fe9255be821cb38ffd306d7e8edc4b9ea662 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Nov 2020 09:36:54 +0100 Subject: block: switch partition lookup to use struct block_device Use struct block_device to lookup partitions on a disk. This removes all usage of struct hd_struct from the I/O path. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Acked-by: Coly Li [bcache] Acked-by: Chao Yu [f2fs] Signed-off-by: Jens Axboe --- block/bio.c | 4 +-- block/blk-core.c | 66 +++++++++++++++++--------------------- block/blk-flush.c | 2 +- block/blk-mq.c | 9 +++--- block/blk-mq.h | 7 ++-- block/blk.h | 4 +-- block/genhd.c | 57 +++++++++++++++++--------------- block/partitions/core.c | 7 ++-- drivers/block/drbd/drbd_receiver.c | 2 +- drivers/block/drbd/drbd_worker.c | 2 +- drivers/block/zram/zram_drv.c | 2 +- drivers/md/bcache/request.c | 4 +-- drivers/md/dm.c | 4 +-- drivers/md/md.c | 4 +-- drivers/nvme/target/admin-cmd.c | 20 ++++++------ fs/ext4/super.c | 18 ++++------- fs/ext4/sysfs.c | 10 ++---- fs/f2fs/f2fs.h | 2 +- fs/f2fs/super.c | 6 ++-- include/linux/blkdev.h | 8 ++--- include/linux/genhd.h | 4 +-- include/linux/part_stat.h | 17 +++++----- 22 files changed, 122 insertions(+), 137 deletions(-) (limited to 'drivers/md') diff --git a/block/bio.c b/block/bio.c index 669bb47a3198..ebb18136b86f 100644 --- a/block/bio.c +++ b/block/bio.c @@ -608,12 +608,12 @@ void bio_truncate(struct bio *bio, unsigned new_size) void guard_bio_eod(struct bio *bio) { sector_t maxsector; - struct hd_struct *part; + struct block_device *part; rcu_read_lock(); part = __disk_get_part(bio->bi_disk, bio->bi_partno); if (part) - maxsector = bdev_nr_sectors(part->bdev); + maxsector = bdev_nr_sectors(part); else maxsector = get_capacity(bio->bi_disk); rcu_read_unlock(); diff --git a/block/blk-core.c b/block/blk-core.c index 9ea70275fc1c..cee568389b7e 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -666,10 +666,9 @@ static int __init setup_fail_make_request(char *str) } __setup("fail_make_request=", setup_fail_make_request); -static bool should_fail_request(struct hd_struct *part, unsigned int bytes) +static bool should_fail_request(struct block_device *part, unsigned int bytes) { - return part->bdev->bd_make_it_fail && - should_fail(&fail_make_request, bytes); + return part->bd_make_it_fail && should_fail(&fail_make_request, bytes); } static int __init fail_make_request_debugfs(void) @@ -684,7 +683,7 @@ late_initcall(fail_make_request_debugfs); #else /* CONFIG_FAIL_MAKE_REQUEST */ -static inline bool should_fail_request(struct hd_struct *part, +static inline bool should_fail_request(struct block_device *part, unsigned int bytes) { return false; @@ -692,11 +691,11 @@ static inline bool should_fail_request(struct hd_struct *part, #endif /* CONFIG_FAIL_MAKE_REQUEST */ -static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) +static inline bool bio_check_ro(struct bio *bio, struct block_device *part) { const int op = bio_op(bio); - if (part->bdev->bd_read_only && op_is_write(op)) { + if (part->bd_read_only && op_is_write(op)) { char b[BDEVNAME_SIZE]; if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) @@ -704,7 +703,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) WARN_ONCE(1, "Trying to write to read-only block-device %s (partno %d)\n", - bio_devname(bio, b), part->partno); + bio_devname(bio, b), part->bd_partno); /* Older lvm-tools actually trigger this */ return false; } @@ -714,8 +713,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) static noinline int should_fail_bio(struct bio *bio) { - if (should_fail_request(bio->bi_disk->part0->bd_part, - bio->bi_iter.bi_size)) + if (should_fail_request(bio->bi_disk->part0, bio->bi_iter.bi_size)) return -EIO; return 0; } @@ -744,7 +742,7 @@ static inline int bio_check_eod(struct bio *bio, sector_t maxsector) */ static inline int blk_partition_remap(struct bio *bio) { - struct hd_struct *p; + struct block_device *p; int ret = -EIO; rcu_read_lock(); @@ -757,12 +755,12 @@ static inline int blk_partition_remap(struct bio *bio) goto out; if (bio_sectors(bio)) { - if (bio_check_eod(bio, bdev_nr_sectors(p->bdev))) + if (bio_check_eod(bio, bdev_nr_sectors(p))) goto out; - bio->bi_iter.bi_sector += p->bdev->bd_start_sect; - trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p), + bio->bi_iter.bi_sector += p->bd_start_sect; + trace_block_bio_remap(bio->bi_disk->queue, bio, p->bd_dev, bio->bi_iter.bi_sector - - p->bdev->bd_start_sect); + p->bd_start_sect); } bio->bi_partno = 0; ret = 0; @@ -832,7 +830,7 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio) if (unlikely(blk_partition_remap(bio))) goto end_io; } else { - if (unlikely(bio_check_ro(bio, bio->bi_disk->part0->bd_part))) + if (unlikely(bio_check_ro(bio, bio->bi_disk->part0))) goto end_io; if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk)))) goto end_io; @@ -1204,7 +1202,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request * return ret; if (rq->rq_disk && - should_fail_request(rq->rq_disk->part0->bd_part, blk_rq_bytes(rq))) + should_fail_request(rq->rq_disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; if (blk_crypto_insert_cloned_request(rq)) @@ -1263,17 +1261,18 @@ unsigned int blk_rq_err_bytes(const struct request *rq) } EXPORT_SYMBOL_GPL(blk_rq_err_bytes); -static void update_io_ticks(struct hd_struct *part, unsigned long now, bool end) +static void update_io_ticks(struct block_device *part, unsigned long now, + bool end) { unsigned long stamp; again: - stamp = READ_ONCE(part->bdev->bd_stamp); + stamp = READ_ONCE(part->bd_stamp); if (unlikely(stamp != now)) { - if (likely(cmpxchg(&part->bdev->bd_stamp, stamp, now) == stamp)) + if (likely(cmpxchg(&part->bd_stamp, stamp, now) == stamp)) __part_stat_add(part, io_ticks, end ? now - stamp : 1); } - if (part->partno) { - part = part_to_disk(part)->part0->bd_part; + if (part->bd_partno) { + part = bdev_whole(part); goto again; } } @@ -1282,11 +1281,9 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes) { if (req->part && blk_do_io_stat(req)) { const int sgrp = op_stat_group(req_op(req)); - struct hd_struct *part; part_stat_lock(); - part = req->part; - part_stat_add(part, sectors[sgrp], bytes >> 9); + part_stat_add(req->part, sectors[sgrp], bytes >> 9); part_stat_unlock(); } } @@ -1301,14 +1298,11 @@ void blk_account_io_done(struct request *req, u64 now) if (req->part && blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) { const int sgrp = op_stat_group(req_op(req)); - struct hd_struct *part; part_stat_lock(); - part = req->part; - - update_io_ticks(part, jiffies, true); - part_stat_inc(part, ios[sgrp]); - part_stat_add(part, nsecs[sgrp], now - req->start_time_ns); + update_io_ticks(req->part, jiffies, true); + part_stat_inc(req->part, ios[sgrp]); + part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns); part_stat_unlock(); } } @@ -1325,7 +1319,7 @@ void blk_account_io_start(struct request *rq) part_stat_unlock(); } -static unsigned long __part_start_io_acct(struct hd_struct *part, +static unsigned long __part_start_io_acct(struct block_device *part, unsigned int sectors, unsigned int op) { const int sgrp = op_stat_group(op); @@ -1341,7 +1335,7 @@ static unsigned long __part_start_io_acct(struct hd_struct *part, return now; } -unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part, +unsigned long part_start_io_acct(struct gendisk *disk, struct block_device **part, struct bio *bio) { *part = disk_map_sector_rcu(disk, bio->bi_iter.bi_sector); @@ -1353,11 +1347,11 @@ EXPORT_SYMBOL_GPL(part_start_io_acct); unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op) { - return __part_start_io_acct(disk->part0->bd_part, sectors, op); + return __part_start_io_acct(disk->part0, sectors, op); } EXPORT_SYMBOL(disk_start_io_acct); -static void __part_end_io_acct(struct hd_struct *part, unsigned int op, +static void __part_end_io_acct(struct block_device *part, unsigned int op, unsigned long start_time) { const int sgrp = op_stat_group(op); @@ -1371,7 +1365,7 @@ static void __part_end_io_acct(struct hd_struct *part, unsigned int op, part_stat_unlock(); } -void part_end_io_acct(struct hd_struct *part, struct bio *bio, +void part_end_io_acct(struct block_device *part, struct bio *bio, unsigned long start_time) { __part_end_io_acct(part, bio_op(bio), start_time); @@ -1381,7 +1375,7 @@ EXPORT_SYMBOL_GPL(part_end_io_acct); void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time) { - __part_end_io_acct(disk->part0->bd_part, op, start_time); + __part_end_io_acct(disk->part0, op, start_time); } EXPORT_SYMBOL(disk_end_io_acct); diff --git a/block/blk-flush.c b/block/blk-flush.c index fcd0a60574df..9507dcdd5881 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -139,7 +139,7 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front) static void blk_account_io_flush(struct request *rq) { - struct hd_struct *part = rq->rq_disk->part0->bd_part; + struct block_device *part = rq->rq_disk->part0; part_stat_lock(); part_stat_inc(part, ios[STAT_FLUSH]); diff --git a/block/blk-mq.c b/block/blk-mq.c index 55bcee5dc032..a2593748fa53 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -95,7 +95,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx, } struct mq_inflight { - struct hd_struct *part; + struct block_device *part; unsigned int inflight[2]; }; @@ -111,7 +111,8 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx, return true; } -unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part) +unsigned int blk_mq_in_flight(struct request_queue *q, + struct block_device *part) { struct mq_inflight mi = { .part = part }; @@ -120,8 +121,8 @@ unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part) return mi.inflight[0] + mi.inflight[1]; } -void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part, - unsigned int inflight[2]) +void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part, + unsigned int inflight[2]) { struct mq_inflight mi = { .part = part }; diff --git a/block/blk-mq.h b/block/blk-mq.h index a52703c98b77..c696515766c7 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -182,9 +182,10 @@ static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx) return hctx->nr_ctx && hctx->tags; } -unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part); -void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part, - unsigned int inflight[2]); +unsigned int blk_mq_in_flight(struct request_queue *q, + struct block_device *part); +void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part, + unsigned int inflight[2]); static inline void blk_mq_put_dispatch_budget(struct request_queue *q) { diff --git a/block/blk.h b/block/blk.h index 32ac41f7557f..d5bf8f3a0781 100644 --- a/block/blk.h +++ b/block/blk.h @@ -215,7 +215,7 @@ static inline void elevator_exit(struct request_queue *q, __elevator_exit(q, e); } -struct hd_struct *__disk_get_part(struct gendisk *disk, int partno); +struct block_device *__disk_get_part(struct gendisk *disk, int partno); ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf); @@ -348,7 +348,7 @@ void blk_queue_free_zone_bitmaps(struct request_queue *q); static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {} #endif -struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector); +struct block_device *disk_map_sector_rcu(struct gendisk *disk, sector_t sector); int blk_alloc_devt(struct hd_struct *part, dev_t *devt); void blk_free_devt(dev_t devt); diff --git a/block/genhd.c b/block/genhd.c index c35b03dac5e5..ed06466b305d 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -126,7 +126,7 @@ static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat) } } -static unsigned int part_in_flight(struct hd_struct *part) +static unsigned int part_in_flight(struct block_device *part) { unsigned int inflight = 0; int cpu; @@ -141,7 +141,8 @@ static unsigned int part_in_flight(struct hd_struct *part) return inflight; } -static void part_in_flight_rw(struct hd_struct *part, unsigned int inflight[2]) +static void part_in_flight_rw(struct block_device *part, + unsigned int inflight[2]) { int cpu; @@ -157,7 +158,7 @@ static void part_in_flight_rw(struct hd_struct *part, unsigned int inflight[2]) inflight[1] = 0; } -struct hd_struct *__disk_get_part(struct gendisk *disk, int partno) +struct block_device *__disk_get_part(struct gendisk *disk, int partno) { struct disk_part_tbl *ptbl = rcu_dereference(disk->part_tbl); @@ -182,15 +183,21 @@ struct hd_struct *__disk_get_part(struct gendisk *disk, int partno) */ struct hd_struct *disk_get_part(struct gendisk *disk, int partno) { + struct block_device *bdev; struct hd_struct *part; rcu_read_lock(); - part = __disk_get_part(disk, partno); - if (part) - get_device(part_to_dev(part)); + bdev = __disk_get_part(disk, partno); + if (!bdev) + goto fail; + part = bdev->bd_part; + if (!kobject_get_unless_zero(&part_to_dev(part)->kobj)) + goto fail; rcu_read_unlock(); - return part; +fail: + rcu_read_unlock(); + return NULL; } /** @@ -264,19 +271,19 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter) /* iterate to the next partition */ for (; piter->idx != end; piter->idx += inc) { - struct hd_struct *part; + struct block_device *part; part = rcu_dereference(ptbl->part[piter->idx]); if (!part) continue; - if (!bdev_nr_sectors(part->bdev) && + if (!bdev_nr_sectors(part) && !(piter->flags & DISK_PITER_INCL_EMPTY) && !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 && piter->idx == 0)) continue; - get_device(part_to_dev(part)); - piter->part = part; + get_device(part_to_dev(part->bd_part)); + piter->part = part->bd_part; piter->idx += inc; break; } @@ -303,10 +310,10 @@ void disk_part_iter_exit(struct disk_part_iter *piter) } EXPORT_SYMBOL_GPL(disk_part_iter_exit); -static inline int sector_in_part(struct hd_struct *part, sector_t sector) +static inline int sector_in_part(struct block_device *part, sector_t sector) { - return part->bdev->bd_start_sect <= sector && - sector < part->bdev->bd_start_sect + bdev_nr_sectors(part->bdev); + return part->bd_start_sect <= sector && + sector < part->bd_start_sect + bdev_nr_sectors(part); } /** @@ -324,10 +331,10 @@ static inline int sector_in_part(struct hd_struct *part, sector_t sector) * Found partition on success, part0 is returned if no partition matches * or the matched partition is being deleted. */ -struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) +struct block_device *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) { struct disk_part_tbl *ptbl; - struct hd_struct *part; + struct block_device *part; int i; rcu_read_lock(); @@ -346,7 +353,7 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) } } - part = disk->part0->bd_part; + part = disk->part0; out_unlock: rcu_read_unlock(); return part; @@ -882,7 +889,7 @@ void del_gendisk(struct gendisk *disk) kobject_put(disk->part0->bd_holder_dir); kobject_put(disk->slave_dir); - part_stat_set_all(disk->part0->bd_part, 0); + part_stat_set_all(disk->part0, 0); disk->part0->bd_stamp = 0; if (!sysfs_deprecated) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); @@ -1189,9 +1196,9 @@ ssize_t part_stat_show(struct device *dev, part_stat_read_all(p, &stat); if (queue_is_mq(q)) - inflight = blk_mq_in_flight(q, p); + inflight = blk_mq_in_flight(q, p->bdev); else - inflight = part_in_flight(p); + inflight = part_in_flight(p->bdev); return sprintf(buf, "%8lu %8lu %8llu %8u " @@ -1231,9 +1238,9 @@ ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, unsigned int inflight[2]; if (queue_is_mq(q)) - blk_mq_in_flight_rw(q, p, inflight); + blk_mq_in_flight_rw(q, p->bdev, inflight); else - part_in_flight_rw(p, inflight); + part_in_flight_rw(p->bdev, inflight); return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]); } @@ -1506,9 +1513,9 @@ static int diskstats_show(struct seq_file *seqf, void *v) while ((hd = disk_part_iter_next(&piter))) { part_stat_read_all(hd, &stat); if (queue_is_mq(gp->queue)) - inflight = blk_mq_in_flight(gp->queue, hd); + inflight = blk_mq_in_flight(gp->queue, hd->bdev); else - inflight = part_in_flight(hd); + inflight = part_in_flight(hd->bdev); seq_printf(seqf, "%4d %7d %s " "%lu %lu %lu %u " @@ -1626,7 +1633,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) goto out_bdput; ptbl = rcu_dereference_protected(disk->part_tbl, 1); - rcu_assign_pointer(ptbl->part[0], disk->part0->bd_part); + rcu_assign_pointer(ptbl->part[0], disk->part0); disk->minors = minors; rand_initialize_disk(disk); diff --git a/block/partitions/core.c b/block/partitions/core.c index 6d1fca193cbd..c2f6721633b8 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -298,12 +298,9 @@ void delete_partition(struct hd_struct *part) struct disk_part_tbl *ptbl = rcu_dereference_protected(disk->part_tbl, 1); - /* - * ->part_tbl is referenced in this part's release handler, so - * we have to hold the disk device - */ rcu_assign_pointer(ptbl->part[part->partno], NULL); rcu_assign_pointer(ptbl->last_lookup, NULL); + kobject_put(part->bdev->bd_holder_dir); device_del(part_to_dev(part)); @@ -421,7 +418,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno, /* everything is up and running, commence */ bdev_add(bdev, devt); - rcu_assign_pointer(ptbl->part[partno], p); + rcu_assign_pointer(ptbl->part[partno], bdev); /* suppress uevent if the disk suppresses it */ if (!dev_get_uevent_suppress(ddev)) diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 9e5c2fdfda36..09c86ef3f0fd 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -2802,7 +2802,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device) if (c_min_rate == 0) return false; - curr_events = (int)part_stat_read_accum(disk->part0->bd_part, sectors) - + curr_events = (int)part_stat_read_accum(disk->part0, sectors) - atomic_read(&device->rs_sect_ev); if (atomic_read(&device->ap_actlog_cnt) diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 343f56b86bb7..02044ab7f767 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -1679,7 +1679,7 @@ void drbd_rs_controller_reset(struct drbd_device *device) atomic_set(&device->rs_sect_ev, 0); device->rs_in_flight = 0; device->rs_last_events = - (int)part_stat_read_accum(disk->part0->bd_part, sectors); + (int)part_stat_read_accum(disk->part0, sectors); /* Updating the RCU protected object in place is necessary since this function gets called from atomic context. diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 6d84876a9cd0..dc8957d173d3 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1687,7 +1687,7 @@ static void zram_reset_device(struct zram *zram) zram->disksize = 0; set_capacity_and_notify(zram->disk, 0); - part_stat_set_all(zram->disk->part0->bd_part, 0); + part_stat_set_all(zram->disk->part0, 0); up_write(&zram->init_lock); /* I/O operation under all of CPU are done so let's free */ diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index afac8d07c1bd..85b1f2a9b72d 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -475,7 +475,7 @@ struct search { unsigned int read_dirty_data:1; unsigned int cache_missed:1; - struct hd_struct *part; + struct block_device *part; unsigned long start_time; struct btree_op op; @@ -1073,7 +1073,7 @@ struct detached_dev_io_private { unsigned long start_time; bio_end_io_t *bi_end_io; void *bi_private; - struct hd_struct *part; + struct block_device *part; }; static void detached_dev_end_io(struct bio *bio) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 1b2db4d530ea..176adcff56b3 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1607,7 +1607,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, * (by eliminating DM's splitting and just using bio_split) */ part_stat_lock(); - __dm_part_stat_sub(dm_disk(md)->part0->bd_part, + __dm_part_stat_sub(dm_disk(md)->part0, sectors[op_stat_group(bio_op(bio))], ci.sector_count); part_stat_unlock(); @@ -2242,7 +2242,7 @@ EXPORT_SYMBOL_GPL(dm_put); static bool md_in_flight_bios(struct mapped_device *md) { int cpu; - struct hd_struct *part = dm_disk(md)->part0->bd_part; + struct block_device *part = dm_disk(md)->part0; long sum = 0; for_each_possible_cpu(cpu) { diff --git a/drivers/md/md.c b/drivers/md/md.c index 3696c2d77a4d..0065736f05b4 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -464,7 +464,7 @@ struct md_io { bio_end_io_t *orig_bi_end_io; void *orig_bi_private; unsigned long start_time; - struct hd_struct *part; + struct block_device *part; }; static void md_end_io(struct bio *bio) @@ -8441,7 +8441,7 @@ static int is_mddev_idle(struct mddev *mddev, int init) rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) { struct gendisk *disk = rdev->bdev->bd_disk; - curr_events = (int)part_stat_read_accum(disk->part0->bd_part, sectors) - + curr_events = (int)part_stat_read_accum(disk->part0, sectors) - atomic_read(&disk->sync_io); /* sync IO will cause sync_io to increase before the disk_stats * as sync_io is counted when a request starts, and diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index dca34489a1dc..8d90235e4fcc 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -89,12 +89,12 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req, if (!ns->bdev) goto out; - host_reads = part_stat_read(ns->bdev->bd_part, ios[READ]); - data_units_read = DIV_ROUND_UP(part_stat_read(ns->bdev->bd_part, - sectors[READ]), 1000); - host_writes = part_stat_read(ns->bdev->bd_part, ios[WRITE]); - data_units_written = DIV_ROUND_UP(part_stat_read(ns->bdev->bd_part, - sectors[WRITE]), 1000); + host_reads = part_stat_read(ns->bdev, ios[READ]); + data_units_read = + DIV_ROUND_UP(part_stat_read(ns->bdev, sectors[READ]), 1000); + host_writes = part_stat_read(ns->bdev, ios[WRITE]); + data_units_written = + DIV_ROUND_UP(part_stat_read(ns->bdev, sectors[WRITE]), 1000); put_unaligned_le64(host_reads, &slog->host_reads[0]); put_unaligned_le64(data_units_read, &slog->data_units_read[0]); @@ -120,12 +120,12 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req, /* we don't have the right data for file backed ns */ if (!ns->bdev) continue; - host_reads += part_stat_read(ns->bdev->bd_part, ios[READ]); + host_reads += part_stat_read(ns->bdev, ios[READ]); data_units_read += DIV_ROUND_UP( - part_stat_read(ns->bdev->bd_part, sectors[READ]), 1000); - host_writes += part_stat_read(ns->bdev->bd_part, ios[WRITE]); + part_stat_read(ns->bdev, sectors[READ]), 1000); + host_writes += part_stat_read(ns->bdev, ios[WRITE]); data_units_written += DIV_ROUND_UP( - part_stat_read(ns->bdev->bd_part, sectors[WRITE]), 1000); + part_stat_read(ns->bdev, sectors[WRITE]), 1000); } put_unaligned_le64(host_reads, &slog->host_reads[0]); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6633b20224d5..c303a0ff0b17 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4048,9 +4048,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_sb = sb; sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; sbi->s_sb_block = sb_block; - if (sb->s_bdev->bd_part) - sbi->s_sectors_written_start = - part_stat_read(sb->s_bdev->bd_part, sectors[STAT_WRITE]); + sbi->s_sectors_written_start = + part_stat_read(sb->s_bdev, sectors[STAT_WRITE]); /* Cleanup superblock name */ strreplace(sb->s_id, '/', '!'); @@ -5509,15 +5508,10 @@ static int ext4_commit_super(struct super_block *sb, int sync) */ if (!(sb->s_flags & SB_RDONLY)) ext4_update_tstamp(es, s_wtime); - if (sb->s_bdev->bd_part) - es->s_kbytes_written = - cpu_to_le64(EXT4_SB(sb)->s_kbytes_written + - ((part_stat_read(sb->s_bdev->bd_part, - sectors[STAT_WRITE]) - - EXT4_SB(sb)->s_sectors_written_start) >> 1)); - else - es->s_kbytes_written = - cpu_to_le64(EXT4_SB(sb)->s_kbytes_written); + es->s_kbytes_written = + cpu_to_le64(EXT4_SB(sb)->s_kbytes_written + + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - + EXT4_SB(sb)->s_sectors_written_start) >> 1)); if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter)) ext4_free_blocks_count_set(es, EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive( diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 4e27fe6ed3ae..075aa3a19ff5 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -62,11 +62,8 @@ static ssize_t session_write_kbytes_show(struct ext4_sb_info *sbi, char *buf) { struct super_block *sb = sbi->s_buddy_cache->i_sb; - if (!sb->s_bdev->bd_part) - return snprintf(buf, PAGE_SIZE, "0\n"); return snprintf(buf, PAGE_SIZE, "%lu\n", - (part_stat_read(sb->s_bdev->bd_part, - sectors[STAT_WRITE]) - + (part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - sbi->s_sectors_written_start) >> 1); } @@ -74,12 +71,9 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_sb_info *sbi, char *buf) { struct super_block *sb = sbi->s_buddy_cache->i_sb; - if (!sb->s_bdev->bd_part) - return snprintf(buf, PAGE_SIZE, "0\n"); return snprintf(buf, PAGE_SIZE, "%llu\n", (unsigned long long)(sbi->s_kbytes_written + - ((part_stat_read(sb->s_bdev->bd_part, - sectors[STAT_WRITE]) - + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - EXT4_SB(sb)->s_sectors_written_start) >> 1))); } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index cb700d797296..49681a8d2b14 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1675,7 +1675,7 @@ static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi) * and the return value is in kbytes. s is of struct f2fs_sb_info. */ #define BD_PART_WRITTEN(s) \ -(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[STAT_WRITE]) - \ + (((u64)part_stat_read((s)->sb->s_bdev, sectors[STAT_WRITE]) - \ (s)->sectors_written_start) >> 1) static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index d4e7fab352ba..af9f449da64b 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3700,10 +3700,8 @@ try_onemore: } /* For write statistics */ - if (sb->s_bdev->bd_part) - sbi->sectors_written_start = - (u64)part_stat_read(sb->s_bdev->bd_part, - sectors[STAT_WRITE]); + sbi->sectors_written_start = + (u64)part_stat_read(sb->s_bdev, sectors[STAT_WRITE]); /* Read accumulated write IO statistics if exists */ seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 619adea57098..1d4be1fc6007 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -191,7 +191,7 @@ struct request { }; struct gendisk *rq_disk; - struct hd_struct *part; + struct block_device *part; #ifdef CONFIG_BLK_RQ_ALLOC_TIME /* Time that the first bio started allocating this request. */ u64 alloc_time_ns; @@ -1943,9 +1943,9 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time); -unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part, - struct bio *bio); -void part_end_io_acct(struct hd_struct *part, struct bio *bio, +unsigned long part_start_io_acct(struct gendisk *disk, + struct block_device **part, struct bio *bio); +void part_end_io_acct(struct block_device *part, struct bio *bio, unsigned long start_time); /** diff --git a/include/linux/genhd.h b/include/linux/genhd.h index df7319da013c..fe6fee77e2b9 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -131,8 +131,8 @@ enum { struct disk_part_tbl { struct rcu_head rcu_head; int len; - struct hd_struct __rcu *last_lookup; - struct hd_struct __rcu *part[]; + struct block_device __rcu *last_lookup; + struct block_device __rcu *part[]; }; struct disk_events; diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index 680de036691e..d2558121d48c 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -25,26 +25,26 @@ struct disk_stats { #define part_stat_unlock() preempt_enable() #define part_stat_get_cpu(part, field, cpu) \ - (per_cpu_ptr((part)->bdev->bd_stats, (cpu))->field) + (per_cpu_ptr((part)->bd_stats, (cpu))->field) #define part_stat_get(part, field) \ part_stat_get_cpu(part, field, smp_processor_id()) #define part_stat_read(part, field) \ ({ \ - typeof((part)->bdev->bd_stats->field) res = 0; \ + typeof((part)->bd_stats->field) res = 0; \ unsigned int _cpu; \ for_each_possible_cpu(_cpu) \ - res += per_cpu_ptr((part)->bdev->bd_stats, _cpu)->field; \ + res += per_cpu_ptr((part)->bd_stats, _cpu)->field; \ res; \ }) -static inline void part_stat_set_all(struct hd_struct *part, int value) +static inline void part_stat_set_all(struct block_device *part, int value) { int i; for_each_possible_cpu(i) - memset(per_cpu_ptr(part->bdev->bd_stats, i), value, + memset(per_cpu_ptr(part->bd_stats, i), value, sizeof(struct disk_stats)); } @@ -54,13 +54,12 @@ static inline void part_stat_set_all(struct hd_struct *part, int value) part_stat_read(part, field[STAT_DISCARD])) #define __part_stat_add(part, field, addnd) \ - __this_cpu_add((part)->bdev->bd_stats->field, addnd) + __this_cpu_add((part)->bd_stats->field, addnd) #define part_stat_add(part, field, addnd) do { \ __part_stat_add((part), field, addnd); \ - if ((part)->partno) \ - __part_stat_add(part_to_disk((part))->part0->bd_part, \ - field, addnd); \ + if ((part)->bd_partno) \ + __part_stat_add(bdev_whole(part), field, addnd); \ } while (0) #define part_stat_dec(part, field) \ -- cgit v1.2.3 From 977115c0f664e016a6b2774d4f97116ade23d732 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 26 Nov 2020 10:41:07 +0100 Subject: block: stop using bdget_disk for partition 0 We can just dereference the point in struct gendisk instead. Also remove the now unused export. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/genhd.c | 1 - drivers/block/nbd.c | 4 +--- drivers/block/xen-blkfront.c | 20 +++++--------------- drivers/block/zram/zram_drv.c | 14 ++------------ drivers/md/dm.c | 16 ++-------------- drivers/s390/block/dasd_ioctl.c | 5 ++--- fs/block_dev.c | 2 +- 7 files changed, 13 insertions(+), 49 deletions(-) (limited to 'drivers/md') diff --git a/block/genhd.c b/block/genhd.c index 0fabfc90b8e4..b84b8671e627 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -930,7 +930,6 @@ struct block_device *bdget_disk(struct gendisk *disk, int partno) return bdev; } -EXPORT_SYMBOL(bdget_disk); /* * print a full list of all partitions - intended for places where the root diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 014683968ce1..92f84ed0ba9e 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1488,12 +1488,10 @@ out: static void nbd_release(struct gendisk *disk, fmode_t mode) { struct nbd_device *nbd = disk->private_data; - struct block_device *bdev = bdget_disk(disk, 0); if (test_bit(NBD_RT_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) && - bdev->bd_openers == 0) + disk->part0->bd_openers == 0) nbd_disconnect_and_put(nbd); - bdput(bdev); nbd_config_put(nbd); nbd_put(nbd); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 79521e33d30e..188e0b47534b 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -2153,7 +2153,7 @@ static void blkfront_closing(struct blkfront_info *info) } if (info->gd) - bdev = bdget_disk(info->gd, 0); + bdev = bdgrab(info->gd->part0); mutex_unlock(&info->mutex); @@ -2518,7 +2518,7 @@ static int blkfront_remove(struct xenbus_device *xbdev) disk = info->gd; if (disk) - bdev = bdget_disk(disk, 0); + bdev = bdgrab(disk->part0); info->xbdev = NULL; mutex_unlock(&info->mutex); @@ -2595,19 +2595,11 @@ out: static void blkif_release(struct gendisk *disk, fmode_t mode) { struct blkfront_info *info = disk->private_data; - struct block_device *bdev; struct xenbus_device *xbdev; mutex_lock(&blkfront_mutex); - - bdev = bdget_disk(disk, 0); - - if (!bdev) { - WARN(1, "Block device %s yanked out from us!\n", disk->disk_name); + if (disk->part0->bd_openers) goto out_mutex; - } - if (bdev->bd_openers) - goto out; /* * Check if we have been instructed to close. We will have @@ -2619,7 +2611,7 @@ static void blkif_release(struct gendisk *disk, fmode_t mode) if (xbdev && xbdev->state == XenbusStateClosing) { /* pending switch to state closed */ - dev_info(disk_to_dev(bdev->bd_disk), "releasing disk\n"); + dev_info(disk_to_dev(disk), "releasing disk\n"); xlvbd_release_gendisk(info); xenbus_frontend_closed(info->xbdev); } @@ -2628,14 +2620,12 @@ static void blkif_release(struct gendisk *disk, fmode_t mode) if (!xbdev) { /* sudden device removal */ - dev_info(disk_to_dev(bdev->bd_disk), "releasing disk\n"); + dev_info(disk_to_dev(disk), "releasing disk\n"); xlvbd_release_gendisk(info); disk->private_data = NULL; free_info(info); } -out: - bdput(bdev); out_mutex: mutex_unlock(&blkfront_mutex); } diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index dc8957d173d3..b0701bae6e98 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1760,15 +1760,12 @@ static ssize_t reset_store(struct device *dev, return -EINVAL; zram = dev_to_zram(dev); - bdev = bdget_disk(zram->disk, 0); - if (!bdev) - return -ENOMEM; + bdev = zram->disk->part0; mutex_lock(&bdev->bd_mutex); /* Do not reset an active device or claimed device */ if (bdev->bd_openers || zram->claim) { mutex_unlock(&bdev->bd_mutex); - bdput(bdev); return -EBUSY; } @@ -1779,7 +1776,6 @@ static ssize_t reset_store(struct device *dev, /* Make sure all the pending I/O are finished */ fsync_bdev(bdev); zram_reset_device(zram); - bdput(bdev); mutex_lock(&bdev->bd_mutex); zram->claim = false; @@ -1965,16 +1961,11 @@ out_free_dev: static int zram_remove(struct zram *zram) { - struct block_device *bdev; - - bdev = bdget_disk(zram->disk, 0); - if (!bdev) - return -ENOMEM; + struct block_device *bdev = zram->disk->part0; mutex_lock(&bdev->bd_mutex); if (bdev->bd_openers || zram->claim) { mutex_unlock(&bdev->bd_mutex); - bdput(bdev); return -EBUSY; } @@ -1986,7 +1977,6 @@ static int zram_remove(struct zram *zram) /* Make sure all the pending I/O are finished */ fsync_bdev(bdev); zram_reset_device(zram); - bdput(bdev); pr_info("Removed device: %s\n", zram->disk->disk_name); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 176adcff56b3..ed7e836efbcd 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2375,16 +2375,11 @@ out: */ static int lock_fs(struct mapped_device *md) { - struct block_device *bdev; int r; WARN_ON(test_bit(DMF_FROZEN, &md->flags)); - bdev = bdget_disk(md->disk, 0); - if (!bdev) - return -ENOMEM; - r = freeze_bdev(bdev); - bdput(bdev); + r = freeze_bdev(md->disk->part0); if (!r) set_bit(DMF_FROZEN, &md->flags); return r; @@ -2392,16 +2387,9 @@ static int lock_fs(struct mapped_device *md) static void unlock_fs(struct mapped_device *md) { - struct block_device *bdev; - if (!test_bit(DMF_FROZEN, &md->flags)) return; - - bdev = bdget_disk(md->disk, 0); - if (!bdev) - return; - thaw_bdev(bdev); - bdput(bdev); + thaw_bdev(md->disk->part0); clear_bit(DMF_FROZEN, &md->flags); } diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index 304eba1acf16..9f6424408946 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -220,9 +220,8 @@ dasd_format(struct dasd_block *block, struct format_data_t *fdata) * enabling the device later. */ if (fdata->start_unit == 0) { - struct block_device *bdev = bdget_disk(block->gdp, 0); - bdev->bd_inode->i_blkbits = blksize_bits(fdata->blksize); - bdput(bdev); + block->gdp->part0->bd_inode->i_blkbits = + blksize_bits(fdata->blksize); } rc = base->discipline->format_device(base, fdata, 1); diff --git a/fs/block_dev.c b/fs/block_dev.c index a9905d8fd02b..9e56ee1f2652 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1299,7 +1299,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) if (ret) return ret; } else { - struct block_device *whole = bdget_disk(disk, 0); + struct block_device *whole = bdgrab(disk->part0); mutex_lock_nested(&whole->bd_mutex, 1); ret = __blkdev_get(whole, mode); -- cgit v1.2.3 From eb6f7f7cd3af0f67ce57b21fab1bc64beb643581 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Dec 2020 17:21:37 +0100 Subject: block: remove the request_queue argument to the block_split tracepoint The request_queue can trivially be derived from the bio. Signed-off-by: Christoph Hellwig Reviewed-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Chaitanya Kulkarni Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-merge.c | 2 +- drivers/md/dm.c | 2 +- include/trace/events/block.h | 14 ++++++-------- kernel/trace/blktrace.c | 5 ++--- 4 files changed, 10 insertions(+), 13 deletions(-) (limited to 'drivers/md') diff --git a/block/blk-merge.c b/block/blk-merge.c index 1a46d5bbd399..4071daa88a5e 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -338,7 +338,7 @@ void __blk_queue_split(struct bio **bio, unsigned int *nr_segs) split->bi_opf |= REQ_NOMERGE; bio_chain(split, *bio); - trace_block_split(q, split, (*bio)->bi_iter.bi_sector); + trace_block_split(split, (*bio)->bi_iter.bi_sector); submit_bio_noacct(*bio); *bio = split; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index ed7e836efbcd..9a5bd90779c7 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1612,7 +1612,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, part_stat_unlock(); bio_chain(b, bio); - trace_block_split(md->queue, b, bio->bi_iter.bi_sector); + trace_block_split(b, bio->bi_iter.bi_sector); ret = submit_bio_noacct(bio); break; } diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 506c29dc7c76..b415e4cba843 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -411,21 +411,19 @@ DEFINE_EVENT(block_unplug, block_unplug, /** * block_split - split a single bio struct into two bio structs - * @q: queue containing the bio * @bio: block operation being split * @new_sector: The starting sector for the new bio * - * The bio request @bio in request queue @q needs to be split into two - * bio requests. The newly created @bio request starts at - * @new_sector. This split may be required due to hardware limitation - * such as operation crossing device boundaries in a RAID system. + * The bio request @bio needs to be split into two bio requests. The newly + * created @bio request starts at @new_sector. This split may be required due to + * hardware limitations such as operation crossing device boundaries in a RAID + * system. */ TRACE_EVENT(block_split, - TP_PROTO(struct request_queue *q, struct bio *bio, - unsigned int new_sector), + TP_PROTO(struct bio *bio, unsigned int new_sector), - TP_ARGS(q, bio, new_sector), + TP_ARGS(bio, new_sector), TP_STRUCT__entry( __field( dev_t, dev ) diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 7ab88e00c157..3ca6d62114f4 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -970,10 +970,9 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q, rcu_read_unlock(); } -static void blk_add_trace_split(void *ignore, - struct request_queue *q, struct bio *bio, - unsigned int pdu) +static void blk_add_trace_split(void *ignore, struct bio *bio, unsigned int pdu) { + struct request_queue *q = bio->bi_disk->queue; struct blk_trace *bt; rcu_read_lock(); -- cgit v1.2.3 From 1c02fca620f7273b597591065d366e2cca948d8f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Dec 2020 17:21:38 +0100 Subject: block: remove the request_queue argument to the block_bio_remap tracepoint The request_queue can trivially be derived from the bio. Signed-off-by: Christoph Hellwig Reviewed-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Chaitanya Kulkarni Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-core.c | 2 +- drivers/md/dm.c | 3 +-- drivers/md/md-linear.c | 3 +-- drivers/md/md.c | 5 ++--- drivers/md/raid0.c | 4 ++-- drivers/md/raid1.c | 7 +++---- drivers/md/raid10.c | 6 ++---- drivers/md/raid5.c | 15 +++++++-------- drivers/nvme/host/multipath.c | 3 +-- include/trace/events/block.h | 8 +++----- kernel/trace/blktrace.c | 14 +++++--------- 11 files changed, 28 insertions(+), 42 deletions(-) (limited to 'drivers/md') diff --git a/block/blk-core.c b/block/blk-core.c index cb24654983e1..96e5fcd7f071 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -758,7 +758,7 @@ static inline int blk_partition_remap(struct bio *bio) if (bio_check_eod(bio, bdev_nr_sectors(p))) goto out; bio->bi_iter.bi_sector += p->bd_start_sect; - trace_block_bio_remap(bio->bi_disk->queue, bio, p->bd_dev, + trace_block_bio_remap(bio, p->bd_dev, bio->bi_iter.bi_sector - p->bd_start_sect); } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 9a5bd90779c7..5181907dc595 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1276,8 +1276,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio) break; case DM_MAPIO_REMAPPED: /* the bio has been remapped so dispatch it */ - trace_block_bio_remap(clone->bi_disk->queue, clone, - bio_dev(io->orig_bio), sector); + trace_block_bio_remap(clone, bio_dev(io->orig_bio), sector); ret = submit_bio_noacct(clone); break; case DM_MAPIO_KILL: diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index 98f1b4b2bdce..68cac7d19278 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -257,8 +257,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio) bio_endio(bio); } else { if (mddev->gendisk) - trace_block_bio_remap(bio->bi_disk->queue, - bio, disk_devt(mddev->gendisk), + trace_block_bio_remap(bio, disk_devt(mddev->gendisk), bio_sector); mddev_check_writesame(mddev, bio); mddev_check_write_zeroes(mddev, bio); diff --git a/drivers/md/md.c b/drivers/md/md.c index 0065736f05b4..c555be0a8dce 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8591,9 +8591,8 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, bio_chain(discard_bio, bio); bio_clone_blkg_association(discard_bio, bio); if (mddev->gendisk) - trace_block_bio_remap(bdev_get_queue(rdev->bdev), - discard_bio, disk_devt(mddev->gendisk), - bio->bi_iter.bi_sector); + trace_block_bio_remap(discard_bio, disk_devt(mddev->gendisk), + bio->bi_iter.bi_sector); submit_bio_noacct(discard_bio); } EXPORT_SYMBOL(md_submit_discard_bio); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 6f44177593a5..e5d7411cba9b 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -571,8 +571,8 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) tmp_dev->data_offset; if (mddev->gendisk) - trace_block_bio_remap(bio->bi_disk->queue, bio, - disk_devt(mddev->gendisk), bio_sector); + trace_block_bio_remap(bio, disk_devt(mddev->gendisk), + bio_sector); mddev_check_writesame(mddev, bio); mddev_check_write_zeroes(mddev, bio); submit_bio_noacct(bio); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 960d854c07f8..c0347997f6ff 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1305,8 +1305,8 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, read_bio->bi_private = r1_bio; if (mddev->gendisk) - trace_block_bio_remap(read_bio->bi_disk->queue, read_bio, - disk_devt(mddev->gendisk), r1_bio->sector); + trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk), + r1_bio->sector); submit_bio_noacct(read_bio); } @@ -1517,8 +1517,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, atomic_inc(&r1_bio->remaining); if (mddev->gendisk) - trace_block_bio_remap(mbio->bi_disk->queue, - mbio, disk_devt(mddev->gendisk), + trace_block_bio_remap(mbio, disk_devt(mddev->gendisk), r1_bio->sector); /* flush_pending_writes() needs access to the rdev so...*/ mbio->bi_disk = (void *)conf->mirrors[i].rdev; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index b7bca6703df8..a6f99fa0b32c 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1200,8 +1200,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, read_bio->bi_private = r10_bio; if (mddev->gendisk) - trace_block_bio_remap(read_bio->bi_disk->queue, - read_bio, disk_devt(mddev->gendisk), + trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk), r10_bio->sector); submit_bio_noacct(read_bio); return; @@ -1250,8 +1249,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, mbio->bi_private = r10_bio; if (conf->mddev->gendisk) - trace_block_bio_remap(mbio->bi_disk->queue, - mbio, disk_devt(conf->mddev->gendisk), + trace_block_bio_remap(mbio, disk_devt(conf->mddev->gendisk), r10_bio->sector); /* flush_pending_writes() needs access to the rdev so...*/ mbio->bi_disk = (void *)rdev; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 39343479ac2a..3a90cc0e43ca 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1222,9 +1222,9 @@ again: set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags); if (conf->mddev->gendisk) - trace_block_bio_remap(bi->bi_disk->queue, - bi, disk_devt(conf->mddev->gendisk), - sh->dev[i].sector); + trace_block_bio_remap(bi, + disk_devt(conf->mddev->gendisk), + sh->dev[i].sector); if (should_defer && op_is_write(op)) bio_list_add(&pending_bios, bi); else @@ -1272,9 +1272,9 @@ again: if (op == REQ_OP_DISCARD) rbi->bi_vcnt = 0; if (conf->mddev->gendisk) - trace_block_bio_remap(rbi->bi_disk->queue, - rbi, disk_devt(conf->mddev->gendisk), - sh->dev[i].sector); + trace_block_bio_remap(rbi, + disk_devt(conf->mddev->gendisk), + sh->dev[i].sector); if (should_defer && op_is_write(op)) bio_list_add(&pending_bios, rbi); else @@ -5468,8 +5468,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio) spin_unlock_irq(&conf->device_lock); if (mddev->gendisk) - trace_block_bio_remap(align_bi->bi_disk->queue, - align_bi, disk_devt(mddev->gendisk), + trace_block_bio_remap(align_bi, disk_devt(mddev->gendisk), raid_bio->bi_iter.bi_sector); submit_bio_noacct(align_bi); return 1; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 74896be40c17..106cf5c44ee7 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -312,8 +312,7 @@ blk_qc_t nvme_ns_head_submit_bio(struct bio *bio) if (likely(ns)) { bio->bi_disk = ns->disk; bio->bi_opf |= REQ_NVME_MPATH; - trace_block_bio_remap(bio->bi_disk->queue, bio, - disk_devt(ns->head->disk), + trace_block_bio_remap(bio, disk_devt(ns->head->disk), bio->bi_iter.bi_sector); ret = submit_bio_noacct(bio); } else if (nvme_available_path(head)) { diff --git a/include/trace/events/block.h b/include/trace/events/block.h index b415e4cba843..8fb89574d867 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -450,9 +450,8 @@ TRACE_EVENT(block_split, /** * block_bio_remap - map request for a logical device to the raw device - * @q: queue holding the operation * @bio: revised operation - * @dev: device for the operation + * @dev: original device for the operation * @from: original sector for the operation * * An operation for a logical device has been mapped to the @@ -460,10 +459,9 @@ TRACE_EVENT(block_split, */ TRACE_EVENT(block_bio_remap, - TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev, - sector_t from), + TP_PROTO(struct bio *bio, dev_t dev, sector_t from), - TP_ARGS(q, bio, dev, from), + TP_ARGS(bio, dev, from), TP_STRUCT__entry( __field( dev_t, dev ) diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 3ca6d62114f4..405637144a03 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -993,20 +993,16 @@ static void blk_add_trace_split(void *ignore, struct bio *bio, unsigned int pdu) /** * blk_add_trace_bio_remap - Add a trace for a bio-remap operation * @ignore: trace callback data parameter (not used) - * @q: queue the io is for * @bio: the source bio - * @dev: target device + * @dev: source device * @from: source sector * - * Description: - * Device mapper or raid target sometimes need to split a bio because - * it spans a stripe (or similar). Add a trace for that action. - * + * Called after a bio is remapped to a different device and/or sector. **/ -static void blk_add_trace_bio_remap(void *ignore, - struct request_queue *q, struct bio *bio, - dev_t dev, sector_t from) +static void blk_add_trace_bio_remap(void *ignore, struct bio *bio, dev_t dev, + sector_t from) { + struct request_queue *q = bio->bi_disk->queue; struct blk_trace *bt; struct blk_io_trace_remap r; -- cgit v1.2.3 From a54895fa057c67700270777f7661d8d3c7fda88a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Dec 2020 17:21:39 +0100 Subject: block: remove the request_queue to argument request based tracepoints The request_queue can trivially be derived from the request. Signed-off-by: Christoph Hellwig Reviewed-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Chaitanya Kulkarni Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-merge.c | 2 +- block/blk-mq-sched.c | 2 +- block/blk-mq.c | 8 ++++---- drivers/md/dm-rq.c | 2 +- drivers/s390/scsi/zfcp_fsf.c | 3 +-- include/linux/blktrace_api.h | 5 ++--- include/trace/events/block.h | 30 ++++++++++++------------------ kernel/trace/blktrace.c | 44 +++++++++++++++++--------------------------- 8 files changed, 39 insertions(+), 57 deletions(-) (limited to 'drivers/md') diff --git a/block/blk-merge.c b/block/blk-merge.c index 4071daa88a5e..7497d86fff38 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -799,7 +799,7 @@ static struct request *attempt_merge(struct request_queue *q, */ blk_account_io_merge_request(next); - trace_block_rq_merge(q, next); + trace_block_rq_merge(next); /* * ownership of bio passed from next to req, return 'next' for diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index d1eafe2c045c..deff4e826e23 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -386,7 +386,7 @@ EXPORT_SYMBOL_GPL(blk_mq_sched_try_insert_merge); void blk_mq_sched_request_inserted(struct request *rq) { - trace_block_rq_insert(rq->q, rq); + trace_block_rq_insert(rq); } EXPORT_SYMBOL_GPL(blk_mq_sched_request_inserted); diff --git a/block/blk-mq.c b/block/blk-mq.c index 21e2b4b6b742..cf3916e2852f 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -733,7 +733,7 @@ void blk_mq_start_request(struct request *rq) { struct request_queue *q = rq->q; - trace_block_rq_issue(q, rq); + trace_block_rq_issue(rq); if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) { rq->io_start_time_ns = ktime_get_ns(); @@ -760,7 +760,7 @@ static void __blk_mq_requeue_request(struct request *rq) blk_mq_put_driver_tag(rq); - trace_block_rq_requeue(q, rq); + trace_block_rq_requeue(rq); rq_qos_requeue(q, rq); if (blk_mq_request_started(rq)) { @@ -1821,7 +1821,7 @@ static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx, lockdep_assert_held(&ctx->lock); - trace_block_rq_insert(hctx->queue, rq); + trace_block_rq_insert(rq); if (at_head) list_add(&rq->queuelist, &ctx->rq_lists[type]); @@ -1878,7 +1878,7 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, */ list_for_each_entry(rq, list, queuelist) { BUG_ON(rq->mq_ctx != ctx); - trace_block_rq_insert(hctx->queue, rq); + trace_block_rq_insert(rq); } spin_lock(&ctx->lock); diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 729a72ec30cc..13b4385f4d5a 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -397,7 +397,7 @@ static int map_request(struct dm_rq_target_io *tio) } /* The target has remapped the I/O so dispatch it */ - trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)), + trace_block_rq_remap(clone, disk_devt(dm_disk(md)), blk_rq_pos(rq)); ret = dm_dispatch_clone_request(clone, rq); if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) { diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index 6cb963a06777..37d450f46952 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -2359,8 +2359,7 @@ static void zfcp_fsf_req_trace(struct zfcp_fsf_req *req, struct scsi_cmnd *scsi) } } - blk_add_driver_data(scsi->request->q, scsi->request, &blktrc, - sizeof(blktrc)); + blk_add_driver_data(scsi->request, &blktrc, sizeof(blktrc)); } /** diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 3b6ff5902edc..05556573b896 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -75,8 +75,7 @@ static inline bool blk_trace_note_message_enabled(struct request_queue *q) return ret; } -extern void blk_add_driver_data(struct request_queue *q, struct request *rq, - void *data, size_t len); +extern void blk_add_driver_data(struct request *rq, void *data, size_t len); extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, char __user *arg); @@ -90,7 +89,7 @@ extern struct attribute_group blk_trace_attr_group; #else /* !CONFIG_BLK_DEV_IO_TRACE */ # define blk_trace_ioctl(bdev, cmd, arg) (-ENOTTY) # define blk_trace_shutdown(q) do { } while (0) -# define blk_add_driver_data(q, rq, data, len) do {} while (0) +# define blk_add_driver_data(rq, data, len) do {} while (0) # define blk_trace_setup(q, name, dev, bdev, arg) (-ENOTTY) # define blk_trace_startstop(q, start) (-ENOTTY) # define blk_trace_remove(q) (-ENOTTY) diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 8fb89574d867..0d782663a005 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -64,7 +64,6 @@ DEFINE_EVENT(block_buffer, block_dirty_buffer, /** * block_rq_requeue - place block IO request back on a queue - * @q: queue holding operation * @rq: block IO operation request * * The block operation request @rq is being placed back into queue @@ -73,9 +72,9 @@ DEFINE_EVENT(block_buffer, block_dirty_buffer, */ TRACE_EVENT(block_rq_requeue, - TP_PROTO(struct request_queue *q, struct request *rq), + TP_PROTO(struct request *rq), - TP_ARGS(q, rq), + TP_ARGS(rq), TP_STRUCT__entry( __field( dev_t, dev ) @@ -147,9 +146,9 @@ TRACE_EVENT(block_rq_complete, DECLARE_EVENT_CLASS(block_rq, - TP_PROTO(struct request_queue *q, struct request *rq), + TP_PROTO(struct request *rq), - TP_ARGS(q, rq), + TP_ARGS(rq), TP_STRUCT__entry( __field( dev_t, dev ) @@ -181,7 +180,6 @@ DECLARE_EVENT_CLASS(block_rq, /** * block_rq_insert - insert block operation request into queue - * @q: target queue * @rq: block IO operation request * * Called immediately before block operation request @rq is inserted @@ -191,14 +189,13 @@ DECLARE_EVENT_CLASS(block_rq, */ DEFINE_EVENT(block_rq, block_rq_insert, - TP_PROTO(struct request_queue *q, struct request *rq), + TP_PROTO(struct request *rq), - TP_ARGS(q, rq) + TP_ARGS(rq) ); /** * block_rq_issue - issue pending block IO request operation to device driver - * @q: queue holding operation * @rq: block IO operation operation request * * Called when block operation request @rq from queue @q is sent to a @@ -206,14 +203,13 @@ DEFINE_EVENT(block_rq, block_rq_insert, */ DEFINE_EVENT(block_rq, block_rq_issue, - TP_PROTO(struct request_queue *q, struct request *rq), + TP_PROTO(struct request *rq), - TP_ARGS(q, rq) + TP_ARGS(rq) ); /** * block_rq_merge - merge request with another one in the elevator - * @q: queue holding operation * @rq: block IO operation operation request * * Called when block operation request @rq from queue @q is merged to another @@ -221,9 +217,9 @@ DEFINE_EVENT(block_rq, block_rq_issue, */ DEFINE_EVENT(block_rq, block_rq_merge, - TP_PROTO(struct request_queue *q, struct request *rq), + TP_PROTO(struct request *rq), - TP_ARGS(q, rq) + TP_ARGS(rq) ); /** @@ -491,7 +487,6 @@ TRACE_EVENT(block_bio_remap, /** * block_rq_remap - map request for a block operation request - * @q: queue holding the operation * @rq: block IO operation request * @dev: device for the operation * @from: original sector for the operation @@ -502,10 +497,9 @@ TRACE_EVENT(block_bio_remap, */ TRACE_EVENT(block_rq_remap, - TP_PROTO(struct request_queue *q, struct request *rq, dev_t dev, - sector_t from), + TP_PROTO(struct request *rq, dev_t dev, sector_t from), - TP_ARGS(q, rq, dev, from), + TP_ARGS(rq, dev, from), TP_STRUCT__entry( __field( dev_t, dev ) diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 405637144a03..7839a78205c2 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -795,12 +795,12 @@ static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) #endif static u64 -blk_trace_request_get_cgid(struct request_queue *q, struct request *rq) +blk_trace_request_get_cgid(struct request *rq) { if (!rq->bio) return 0; /* Use the first bio */ - return blk_trace_bio_get_cgid(q, rq->bio); + return blk_trace_bio_get_cgid(rq->q, rq->bio); } /* @@ -841,40 +841,35 @@ static void blk_add_trace_rq(struct request *rq, int error, rcu_read_unlock(); } -static void blk_add_trace_rq_insert(void *ignore, - struct request_queue *q, struct request *rq) +static void blk_add_trace_rq_insert(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT, - blk_trace_request_get_cgid(q, rq)); + blk_trace_request_get_cgid(rq)); } -static void blk_add_trace_rq_issue(void *ignore, - struct request_queue *q, struct request *rq) +static void blk_add_trace_rq_issue(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE, - blk_trace_request_get_cgid(q, rq)); + blk_trace_request_get_cgid(rq)); } -static void blk_add_trace_rq_merge(void *ignore, - struct request_queue *q, struct request *rq) +static void blk_add_trace_rq_merge(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_BACKMERGE, - blk_trace_request_get_cgid(q, rq)); + blk_trace_request_get_cgid(rq)); } -static void blk_add_trace_rq_requeue(void *ignore, - struct request_queue *q, - struct request *rq) +static void blk_add_trace_rq_requeue(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE, - blk_trace_request_get_cgid(q, rq)); + blk_trace_request_get_cgid(rq)); } static void blk_add_trace_rq_complete(void *ignore, struct request *rq, int error, unsigned int nr_bytes) { blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE, - blk_trace_request_get_cgid(rq->q, rq)); + blk_trace_request_get_cgid(rq)); } /** @@ -1037,16 +1032,14 @@ static void blk_add_trace_bio_remap(void *ignore, struct bio *bio, dev_t dev, * Add a trace for that action. * **/ -static void blk_add_trace_rq_remap(void *ignore, - struct request_queue *q, - struct request *rq, dev_t dev, +static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev, sector_t from) { struct blk_trace *bt; struct blk_io_trace_remap r; rcu_read_lock(); - bt = rcu_dereference(q->blk_trace); + bt = rcu_dereference(rq->q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; @@ -1058,13 +1051,12 @@ static void blk_add_trace_rq_remap(void *ignore, __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rq_data_dir(rq), 0, BLK_TA_REMAP, 0, - sizeof(r), &r, blk_trace_request_get_cgid(q, rq)); + sizeof(r), &r, blk_trace_request_get_cgid(rq)); rcu_read_unlock(); } /** * blk_add_driver_data - Add binary message with driver-specific data - * @q: queue the io is for * @rq: io request * @data: driver-specific data * @len: length of driver-specific data @@ -1073,14 +1065,12 @@ static void blk_add_trace_rq_remap(void *ignore, * Some drivers might want to write driver-specific data per request. * **/ -void blk_add_driver_data(struct request_queue *q, - struct request *rq, - void *data, size_t len) +void blk_add_driver_data(struct request *rq, void *data, size_t len) { struct blk_trace *bt; rcu_read_lock(); - bt = rcu_dereference(q->blk_trace); + bt = rcu_dereference(rq->q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; @@ -1088,7 +1078,7 @@ void blk_add_driver_data(struct request_queue *q, __blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0, BLK_TA_DRV_DATA, 0, len, data, - blk_trace_request_get_cgid(q, rq)); + blk_trace_request_get_cgid(rq)); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blk_add_driver_data); -- cgit v1.2.3