diff options
Diffstat (limited to 'block/bdev.c')
| -rw-r--r-- | block/bdev.c | 739 |
1 files changed, 533 insertions, 206 deletions
diff --git a/block/bdev.c b/block/bdev.c index 979e28a46b98..b8fbb9576110 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -24,12 +24,16 @@ #include <linux/pseudo_fs.h> #include <linux/uio.h> #include <linux/namei.h> +#include <linux/security.h> #include <linux/part_stat.h> #include <linux/uaccess.h> #include <linux/stat.h> #include "../fs/internal.h" #include "blk.h" +/* Should we allow writing to mounted block devices? */ +static bool bdev_allow_write_mounted = IS_ENABLED(CONFIG_BLK_DEV_WRITE_MOUNTED); + struct bdev_inode { struct block_device bdev; struct inode vfs_inode; @@ -40,19 +44,30 @@ static inline struct bdev_inode *BDEV_I(struct inode *inode) return container_of(inode, struct bdev_inode, vfs_inode); } +static inline struct inode *BD_INODE(struct block_device *bdev) +{ + return &container_of(bdev, struct bdev_inode, bdev)->vfs_inode; +} + struct block_device *I_BDEV(struct inode *inode) { return &BDEV_I(inode)->bdev; } EXPORT_SYMBOL(I_BDEV); +struct block_device *file_bdev(struct file *bdev_file) +{ + return I_BDEV(bdev_file->f_mapping->host); +} +EXPORT_SYMBOL(file_bdev); + static void bdev_write_inode(struct block_device *bdev) { - struct inode *inode = bdev->bd_inode; + struct inode *inode = BD_INODE(bdev); int ret; spin_lock(&inode->i_lock); - while (inode->i_state & I_DIRTY) { + while (inode_state_read(inode) & I_DIRTY) { spin_unlock(&inode->i_lock); ret = write_inode_now(inode, true); if (ret) @@ -67,7 +82,7 @@ static void bdev_write_inode(struct block_device *bdev) /* Kill _all_ buffers and pagecache , dirty or not.. */ static void kill_bdev(struct block_device *bdev) { - struct address_space *mapping = bdev->bd_inode->i_mapping; + struct address_space *mapping = bdev->bd_mapping; if (mapping_empty(mapping)) return; @@ -79,7 +94,7 @@ static void kill_bdev(struct block_device *bdev) /* Invalidate clean unused buffers and pagecache. */ void invalidate_bdev(struct block_device *bdev) { - struct address_space *mapping = bdev->bd_inode->i_mapping; + struct address_space *mapping = bdev->bd_mapping; if (mapping->nrpages) { invalidate_bh_lrus(); @@ -107,7 +122,7 @@ int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode, goto invalidate; } - truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend); + truncate_inode_pages_range(bdev->bd_mapping, lstart, lend); if (!(mode & BLK_OPEN_EXCL)) bd_abort_claiming(bdev, truncate_bdev_range); return 0; @@ -117,7 +132,7 @@ invalidate: * Someone else has handle exclusively open. Try invalidating instead. * The 'end' argument is inclusive so the rounding is safe. */ - return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping, + return invalidate_inode_pages2_range(bdev->bd_mapping, lstart >> PAGE_SHIFT, lend >> PAGE_SHIFT); } @@ -125,43 +140,107 @@ invalidate: static void set_init_blocksize(struct block_device *bdev) { unsigned int bsize = bdev_logical_block_size(bdev); - loff_t size = i_size_read(bdev->bd_inode); + loff_t size = i_size_read(BD_INODE(bdev)); while (bsize < PAGE_SIZE) { if (size & bsize) break; bsize <<= 1; } - bdev->bd_inode->i_blkbits = blksize_bits(bsize); + BD_INODE(bdev)->i_blkbits = blksize_bits(bsize); + mapping_set_folio_min_order(BD_INODE(bdev)->i_mapping, + get_order(bsize)); } -int set_blocksize(struct block_device *bdev, int size) +/** + * bdev_validate_blocksize - check that this block size is acceptable + * @bdev: blockdevice to check + * @block_size: block size to check + * + * For block device users that do not use buffer heads or the block device + * page cache, make sure that this block size can be used with the device. + * + * Return: On success zero is returned, negative error code on failure. + */ +int bdev_validate_blocksize(struct block_device *bdev, int block_size) { - /* Size must be a power of two, and between 512 and PAGE_SIZE */ - if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size)) + if (blk_validate_block_size(block_size)) return -EINVAL; /* Size cannot be smaller than the size supported by the device */ - if (size < bdev_logical_block_size(bdev)) + if (block_size < bdev_logical_block_size(bdev)) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL_GPL(bdev_validate_blocksize); + +int set_blocksize(struct file *file, int size) +{ + struct inode *inode = file->f_mapping->host; + struct block_device *bdev = I_BDEV(inode); + int ret; + + ret = bdev_validate_blocksize(bdev, size); + if (ret) + return ret; + + if (!file->private_data) return -EINVAL; /* Don't change the size if it is same as current */ - if (bdev->bd_inode->i_blkbits != blksize_bits(size)) { + if (inode->i_blkbits != blksize_bits(size)) { + /* + * Flush and truncate the pagecache before we reconfigure the + * mapping geometry because folio sizes are variable now. If a + * reader has already allocated a folio whose size is smaller + * than the new min_order but invokes readahead after the new + * min_order becomes visible, readahead will think there are + * "zero" blocks per folio and crash. Take the inode and + * invalidation locks to avoid racing with + * read/write/fallocate. + */ + inode_lock(inode); + filemap_invalidate_lock(inode->i_mapping); + sync_blockdev(bdev); - bdev->bd_inode->i_blkbits = blksize_bits(size); kill_bdev(bdev); + + inode->i_blkbits = blksize_bits(size); + mapping_set_folio_min_order(inode->i_mapping, get_order(size)); + kill_bdev(bdev); + filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); } return 0; } EXPORT_SYMBOL(set_blocksize); +static int sb_validate_large_blocksize(struct super_block *sb, int size) +{ + const char *err_str = NULL; + + if (!(sb->s_type->fs_flags & FS_LBS)) + err_str = "not supported by filesystem"; + else if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + err_str = "is only supported with CONFIG_TRANSPARENT_HUGEPAGE"; + + if (!err_str) + return 0; + + pr_warn_ratelimited("%s: block size(%d) > page size(%lu) %s\n", + sb->s_type->name, size, PAGE_SIZE, err_str); + return -EINVAL; +} + int sb_set_blocksize(struct super_block *sb, int size) { - if (set_blocksize(sb->s_bdev, size)) + if (size > PAGE_SIZE && sb_validate_large_blocksize(sb, size)) return 0; - /* If we get here, we know size is power of two - * and it's value is between 512 and PAGE_SIZE */ + if (set_blocksize(sb->s_bdev_file, size)) + return 0; + /* If we get here, we know size is validated */ sb->s_blocksize = size; sb->s_blocksize_bits = blksize_bits(size); return sb->s_blocksize; @@ -169,7 +248,7 @@ int sb_set_blocksize(struct super_block *sb, int size) EXPORT_SYMBOL(sb_set_blocksize); -int sb_min_blocksize(struct super_block *sb, int size) +int __must_check sb_min_blocksize(struct super_block *sb, int size) { int minsize = bdev_logical_block_size(sb->s_bdev); if (size < minsize) @@ -183,7 +262,7 @@ int sync_blockdev_nowait(struct block_device *bdev) { if (!bdev) return 0; - return filemap_flush(bdev->bd_inode->i_mapping); + return filemap_flush(bdev->bd_mapping); } EXPORT_SYMBOL_GPL(sync_blockdev_nowait); @@ -195,121 +274,107 @@ int sync_blockdev(struct block_device *bdev) { if (!bdev) return 0; - return filemap_write_and_wait(bdev->bd_inode->i_mapping); + return filemap_write_and_wait(bdev->bd_mapping); } EXPORT_SYMBOL(sync_blockdev); int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend) { - return filemap_write_and_wait_range(bdev->bd_inode->i_mapping, + return filemap_write_and_wait_range(bdev->bd_mapping, lstart, lend); } EXPORT_SYMBOL(sync_blockdev_range); -/* - * Write out and wait upon all dirty data associated with this - * device. Filesystem data as well as the underlying block - * device. Takes the superblock lock. - */ -int fsync_bdev(struct block_device *bdev) -{ - struct super_block *sb = get_super(bdev); - if (sb) { - int res = sync_filesystem(sb); - drop_super(sb); - return res; - } - return sync_blockdev(bdev); -} -EXPORT_SYMBOL(fsync_bdev); - /** - * freeze_bdev - lock a filesystem and force it into a consistent state + * bdev_freeze - lock a filesystem and force it into a consistent state * @bdev: blockdevice to lock * * If a superblock is found on this device, we take the s_umount semaphore * on it to make sure nobody unmounts until the snapshot creation is done. * The reference counter (bd_fsfreeze_count) guarantees that only the last * unfreeze process can unfreeze the frozen filesystem actually when multiple - * freeze requests arrive simultaneously. It counts up in freeze_bdev() and - * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze + * freeze requests arrive simultaneously. It counts up in bdev_freeze() and + * count down in bdev_thaw(). When it becomes 0, thaw_bdev() will unfreeze * actually. + * + * Return: On success zero is returned, negative error code on failure. */ -int freeze_bdev(struct block_device *bdev) +int bdev_freeze(struct block_device *bdev) { - struct super_block *sb; int error = 0; mutex_lock(&bdev->bd_fsfreeze_mutex); - if (++bdev->bd_fsfreeze_count > 1) - goto done; - - sb = get_active_super(bdev); - if (!sb) - 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) { - bdev->bd_fsfreeze_count--; - goto done; + if (atomic_inc_return(&bdev->bd_fsfreeze_count) > 1) { + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return 0; } - bdev->bd_fsfreeze_sb = sb; -sync: - sync_blockdev(bdev); -done: + mutex_lock(&bdev->bd_holder_lock); + if (bdev->bd_holder_ops && bdev->bd_holder_ops->freeze) { + error = bdev->bd_holder_ops->freeze(bdev); + lockdep_assert_not_held(&bdev->bd_holder_lock); + } else { + mutex_unlock(&bdev->bd_holder_lock); + error = sync_blockdev(bdev); + } + + if (error) + atomic_dec(&bdev->bd_fsfreeze_count); + mutex_unlock(&bdev->bd_fsfreeze_mutex); return error; } -EXPORT_SYMBOL(freeze_bdev); +EXPORT_SYMBOL(bdev_freeze); /** - * thaw_bdev - unlock filesystem + * bdev_thaw - unlock filesystem * @bdev: blockdevice to unlock * - * Unlocks the filesystem and marks it writeable again after freeze_bdev(). + * Unlocks the filesystem and marks it writeable again after bdev_freeze(). + * + * Return: On success zero is returned, negative error code on failure. */ -int thaw_bdev(struct block_device *bdev) +int bdev_thaw(struct block_device *bdev) { - struct super_block *sb; - int error = -EINVAL; + int error = -EINVAL, nr_freeze; mutex_lock(&bdev->bd_fsfreeze_mutex); - if (!bdev->bd_fsfreeze_count) + + /* + * If this returns < 0 it means that @bd_fsfreeze_count was + * already 0 and no decrement was performed. + */ + nr_freeze = atomic_dec_if_positive(&bdev->bd_fsfreeze_count); + if (nr_freeze < 0) goto out; error = 0; - if (--bdev->bd_fsfreeze_count > 0) + if (nr_freeze > 0) goto out; - sb = bdev->bd_fsfreeze_sb; - if (!sb) - goto out; + mutex_lock(&bdev->bd_holder_lock); + if (bdev->bd_holder_ops && bdev->bd_holder_ops->thaw) { + error = bdev->bd_holder_ops->thaw(bdev); + lockdep_assert_not_held(&bdev->bd_holder_lock); + } else { + mutex_unlock(&bdev->bd_holder_lock); + } - if (sb->s_op->thaw_super) - error = sb->s_op->thaw_super(sb); - else - error = thaw_super(sb); if (error) - bdev->bd_fsfreeze_count++; - else - bdev->bd_fsfreeze_sb = NULL; + atomic_inc(&bdev->bd_fsfreeze_count); out: mutex_unlock(&bdev->bd_fsfreeze_mutex); return error; } -EXPORT_SYMBOL(thaw_bdev); +EXPORT_SYMBOL(bdev_thaw); /* * pseudo-fs */ static __cacheline_aligned_in_smp DEFINE_MUTEX(bdev_lock); -static struct kmem_cache * bdev_cachep __read_mostly; +static struct kmem_cache *bdev_cachep __ro_after_init; static struct inode *bdev_alloc_inode(struct super_block *sb) { @@ -318,6 +383,11 @@ static struct inode *bdev_alloc_inode(struct super_block *sb) if (!ei) return NULL; memset(&ei->bdev, 0, sizeof(ei->bdev)); + + if (security_bdev_alloc(&ei->bdev)) { + kmem_cache_free(bdev_cachep, ei); + return NULL; + } return &ei->vfs_inode; } @@ -327,6 +397,7 @@ static void bdev_free_inode(struct inode *inode) free_percpu(bdev->bd_stats); kfree(bdev->bd_meta_info); + security_bdev_free(bdev); if (!bdev_is_partition(bdev)) { if (bdev->bd_disk && bdev->bd_disk->bdi) @@ -358,7 +429,7 @@ static const struct super_operations bdev_sops = { .statfs = simple_statfs, .alloc_inode = bdev_alloc_inode, .free_inode = bdev_free_inode, - .drop_inode = generic_delete_inode, + .drop_inode = inode_just_drop, .evict_inode = bdev_evict_inode, }; @@ -378,25 +449,25 @@ static struct file_system_type bd_type = { .kill_sb = kill_anon_super, }; -struct super_block *blockdev_superblock __read_mostly; +struct super_block *blockdev_superblock __ro_after_init; +static struct vfsmount *blockdev_mnt __ro_after_init; EXPORT_SYMBOL_GPL(blockdev_superblock); void __init bdev_cache_init(void) { int err; - static struct vfsmount *bd_mnt; bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD|SLAB_ACCOUNT|SLAB_PANIC), + SLAB_ACCOUNT|SLAB_PANIC), init_once); err = register_filesystem(&bd_type); if (err) panic("Cannot register bdev pseudo-fs"); - bd_mnt = kern_mount(&bd_type); - if (IS_ERR(bd_mnt)) + blockdev_mnt = kern_mount(&bd_type); + if (IS_ERR(blockdev_mnt)) panic("Cannot create bdev pseudo-fs"); - blockdev_superblock = bd_mnt->mnt_sb; /* For writeback */ + blockdev_superblock = blockdev_mnt->mnt_sb; /* For writeback */ } struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) @@ -416,13 +487,11 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) mutex_init(&bdev->bd_fsfreeze_mutex); spin_lock_init(&bdev->bd_size_lock); mutex_init(&bdev->bd_holder_lock); - bdev->bd_partno = partno; - bdev->bd_inode = inode; + atomic_set(&bdev->__bd_flags, partno); + bdev->bd_mapping = &inode->i_data; bdev->bd_queue = disk->queue; - if (partno) - bdev->bd_has_submit_bio = disk->part0->bd_has_submit_bio; - else - bdev->bd_has_submit_bio = false; + if (partno && bdev_test_flag(disk->part0, BD_HAS_SUBMIT_BIO)) + bdev_set_flag(bdev, BD_HAS_SUBMIT_BIO); bdev->bd_stats = alloc_percpu(struct disk_stats); if (!bdev->bd_stats) { iput(inode); @@ -435,17 +504,30 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) 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); + i_size_write(BD_INODE(bdev), (loff_t)sectors << SECTOR_SHIFT); bdev->bd_nr_sectors = sectors; spin_unlock(&bdev->bd_size_lock); } void bdev_add(struct block_device *bdev, dev_t dev) { + struct inode *inode = BD_INODE(bdev); + if (bdev_stable_writes(bdev)) + mapping_set_stable_writes(bdev->bd_mapping); bdev->bd_dev = dev; - bdev->bd_inode->i_rdev = dev; - bdev->bd_inode->i_ino = dev; - insert_inode_hash(bdev->bd_inode); + inode->i_rdev = dev; + inode->i_ino = dev; + insert_inode_hash(inode); +} + +void bdev_unhash(struct block_device *bdev) +{ + remove_inode_hash(BD_INODE(bdev)); +} + +void bdev_drop(struct block_device *bdev) +{ + iput(BD_INODE(bdev)); } long nr_blockdev_pages(void) @@ -531,7 +613,7 @@ retry: /* if claiming is already in progress, wait for it to finish */ if (whole->bd_claiming) { - wait_queue_head_t *wq = bit_waitqueue(&whole->bd_claiming, 0); + wait_queue_head_t *wq = __var_waitqueue(&whole->bd_claiming); DEFINE_WAIT(wait); prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); @@ -554,7 +636,7 @@ static void bd_clear_claiming(struct block_device *whole, void *holder) /* tell others that we're done */ BUG_ON(whole->bd_claiming != holder); whole->bd_claiming = NULL; - wake_up_bit(&whole->bd_claiming, 0); + wake_up_var(&whole->bd_claiming); } /** @@ -623,7 +705,7 @@ static void bd_end_claim(struct block_device *bdev, void *holder) bdev->bd_holder = NULL; bdev->bd_holder_ops = NULL; mutex_unlock(&bdev->bd_holder_lock); - if (bdev->bd_write_holder) + if (bdev_test_flag(bdev, BD_WRITE_HOLDER)) unblock = true; } if (!whole->bd_holders) @@ -636,7 +718,7 @@ static void bd_end_claim(struct block_device *bdev, void *holder) */ if (unblock) { disk_unblock_events(bdev->bd_disk); - bdev->bd_write_holder = false; + bdev_clear_flag(bdev, BD_WRITE_HOLDER); } } @@ -648,6 +730,14 @@ static void blkdev_flush_mapping(struct block_device *bdev) bdev_write_inode(bdev); } +static void blkdev_put_whole(struct block_device *bdev) +{ + if (atomic_dec_and_test(&bdev->bd_openers)) + blkdev_flush_mapping(bdev); + if (bdev->bd_disk->fops->release) + bdev->bd_disk->fops->release(bdev->bd_disk); +} + static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode) { struct gendisk *disk = bdev->bd_disk; @@ -666,20 +756,21 @@ static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode) if (!atomic_read(&bdev->bd_openers)) set_init_blocksize(bdev); - if (test_bit(GD_NEED_PART_SCAN, &disk->state)) - bdev_disk_changed(disk, false); atomic_inc(&bdev->bd_openers); + if (test_bit(GD_NEED_PART_SCAN, &disk->state)) { + /* + * Only return scanning errors if we are called from contexts + * that explicitly want them, e.g. the BLKRRPART ioctl. + */ + ret = bdev_disk_changed(disk, false); + if (ret && (mode & BLK_OPEN_STRICT_SCAN)) { + blkdev_put_whole(bdev); + return ret; + } + } return 0; } -static void blkdev_put_whole(struct block_device *bdev) -{ - if (atomic_dec_and_test(&bdev->bd_openers)) - blkdev_flush_mapping(bdev); - if (bdev->bd_disk->fops->release) - bdev->bd_disk->fops->release(bdev->bd_disk); -} - static int blkdev_get_part(struct block_device *part, blk_mode_t mode) { struct gendisk *disk = part->bd_disk; @@ -705,6 +796,31 @@ out_blkdev_put: return ret; } +int bdev_permission(dev_t dev, blk_mode_t mode, void *holder) +{ + int ret; + + ret = devcgroup_check_permission(DEVCG_DEV_BLOCK, + MAJOR(dev), MINOR(dev), + ((mode & BLK_OPEN_READ) ? DEVCG_ACC_READ : 0) | + ((mode & BLK_OPEN_WRITE) ? DEVCG_ACC_WRITE : 0)); + if (ret) + return ret; + + /* Blocking writes requires exclusive opener */ + if (mode & BLK_OPEN_RESTRICT_WRITES && !holder) + return -EINVAL; + + /* + * We're using error pointers to indicate to ->release() when we + * failed to open that block device. Also this doesn't make sense. + */ + if (WARN_ON_ONCE(IS_ERR(holder))) + return -EINVAL; + + return 0; +} + static void blkdev_put_part(struct block_device *part) { struct block_device *whole = bdev_whole(part); @@ -716,13 +832,13 @@ static void blkdev_put_part(struct block_device *part) blkdev_put_whole(whole); } -struct block_device *blkdev_get_no_open(dev_t dev) +struct block_device *blkdev_get_no_open(dev_t dev, bool autoload) { struct block_device *bdev; struct inode *inode; inode = ilookup(blockdev_superblock, dev); - if (!inode && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) { + if (!inode && autoload && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) { blk_request_module(dev); inode = ilookup(blockdev_superblock, dev); if (inode) @@ -744,58 +860,101 @@ void blkdev_put_no_open(struct block_device *bdev) { put_device(&bdev->bd_device); } - + +static bool bdev_writes_blocked(struct block_device *bdev) +{ + return bdev->bd_writers < 0; +} + +static void bdev_block_writes(struct block_device *bdev) +{ + bdev->bd_writers--; +} + +static void bdev_unblock_writes(struct block_device *bdev) +{ + bdev->bd_writers++; +} + +static bool bdev_may_open(struct block_device *bdev, blk_mode_t mode) +{ + if (bdev_allow_write_mounted) + return true; + /* Writes blocked? */ + if (mode & BLK_OPEN_WRITE && bdev_writes_blocked(bdev)) + return false; + if (mode & BLK_OPEN_RESTRICT_WRITES && bdev->bd_writers > 0) + return false; + return true; +} + +static void bdev_claim_write_access(struct block_device *bdev, blk_mode_t mode) +{ + if (bdev_allow_write_mounted) + return; + + /* Claim exclusive or shared write access. */ + if (mode & BLK_OPEN_RESTRICT_WRITES) + bdev_block_writes(bdev); + else if (mode & BLK_OPEN_WRITE) + bdev->bd_writers++; +} + +static inline bool bdev_unclaimed(const struct file *bdev_file) +{ + return bdev_file->private_data == BDEV_I(bdev_file->f_mapping->host); +} + +static void bdev_yield_write_access(struct file *bdev_file) +{ + struct block_device *bdev; + + if (bdev_allow_write_mounted) + return; + + if (bdev_unclaimed(bdev_file)) + return; + + bdev = file_bdev(bdev_file); + + if (bdev_file->f_mode & FMODE_WRITE_RESTRICTED) + bdev_unblock_writes(bdev); + else if (bdev_file->f_mode & FMODE_WRITE) + bdev->bd_writers--; +} + /** - * blkdev_get_by_dev - open a block device by device number - * @dev: device number of block device to open + * bdev_open - open a block device + * @bdev: block device to open * @mode: open mode (BLK_OPEN_*) * @holder: exclusive holder identifier * @hops: holder operations + * @bdev_file: file for the block device * - * Open the block device described by device number @dev. If @holder is not - * %NULL, the block device is opened with exclusive access. Exclusive opens may - * nest for the same @holder. - * - * 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(). + * Open the block device. If @holder is not %NULL, the block device is opened + * with exclusive access. Exclusive opens may nest for the same @holder. * * CONTEXT: * Might sleep. * * RETURNS: - * Reference to the block_device on success, ERR_PTR(-errno) on failure. + * zero on success, -errno on failure. */ -struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, - const struct blk_holder_ops *hops) +int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder, + const struct blk_holder_ops *hops, struct file *bdev_file) { bool unblock_events = true; - struct block_device *bdev; - struct gendisk *disk; + struct gendisk *disk = bdev->bd_disk; int ret; - ret = devcgroup_check_permission(DEVCG_DEV_BLOCK, - MAJOR(dev), MINOR(dev), - ((mode & BLK_OPEN_READ) ? DEVCG_ACC_READ : 0) | - ((mode & BLK_OPEN_WRITE) ? DEVCG_ACC_WRITE : 0)); - if (ret) - return ERR_PTR(ret); - - bdev = blkdev_get_no_open(dev); - if (!bdev) - return ERR_PTR(-ENXIO); - disk = bdev->bd_disk; - if (holder) { mode |= BLK_OPEN_EXCL; ret = bd_prepare_to_claim(bdev, holder, hops); if (ret) - goto put_blkdev; + return ret; } else { - if (WARN_ON_ONCE(mode & BLK_OPEN_EXCL)) { - ret = -EIO; - goto put_blkdev; - } + if (WARN_ON_ONCE(mode & BLK_OPEN_EXCL)) + return -EIO; } disk_block_events(disk); @@ -806,12 +965,16 @@ struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, goto abort_claiming; if (!try_module_get(disk->fops->owner)) goto abort_claiming; + ret = -EBUSY; + if (!bdev_may_open(bdev, mode)) + goto put_module; if (bdev_is_partition(bdev)) ret = blkdev_get_part(bdev, mode); else ret = blkdev_get_whole(bdev, mode); if (ret) goto put_module; + bdev_claim_write_access(bdev, mode); if (holder) { bd_finish_claiming(bdev, holder, hops); @@ -822,9 +985,10 @@ struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, * writeable reference is too fragile given the way @mode is * used in blkdev_get/put(). */ - if ((mode & BLK_OPEN_WRITE) && !bdev->bd_write_holder && + if ((mode & BLK_OPEN_WRITE) && + !bdev_test_flag(bdev, BD_WRITE_HOLDER) && (disk->event_flags & DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE)) { - bdev->bd_write_holder = true; + bdev_set_flag(bdev, BD_WRITE_HOLDER); unblock_events = false; } } @@ -832,7 +996,18 @@ struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, if (unblock_events) disk_unblock_events(disk); - return bdev; + + bdev_file->f_flags |= O_LARGEFILE; + bdev_file->f_mode |= FMODE_CAN_ODIRECT; + if (bdev_nowait(bdev)) + bdev_file->f_mode |= FMODE_NOWAIT; + if (mode & BLK_OPEN_RESTRICT_WRITES) + bdev_file->f_mode |= FMODE_WRITE_RESTRICTED; + bdev_file->f_mapping = bdev->bd_mapping; + bdev_file->f_wb_err = filemap_sample_wb_err(bdev_file->f_mapping); + bdev_file->private_data = holder; + + return 0; put_module: module_put(disk->fops->owner); abort_claiming: @@ -840,33 +1015,80 @@ abort_claiming: bd_abort_claiming(bdev, holder); mutex_unlock(&disk->open_mutex); disk_unblock_events(disk); -put_blkdev: - blkdev_put_no_open(bdev); - return ERR_PTR(ret); + return ret; } -EXPORT_SYMBOL(blkdev_get_by_dev); -/** - * blkdev_get_by_path - open a block device by name - * @path: path to the block device to open - * @mode: open mode (BLK_OPEN_*) - * @holder: exclusive holder identifier - * @hops: holder operations - * - * Open the block device described by the device file at @path. If @holder is - * not %NULL, the block device is opened with exclusive access. Exclusive opens - * may nest for the same @holder. - * - * CONTEXT: - * Might sleep. +/* + * If BLK_OPEN_WRITE_IOCTL is set then this is a historical quirk + * associated with the floppy driver where it has allowed ioctls if the + * file was opened for writing, but does not allow reads or writes. + * Make sure that this quirk is reflected in @f_flags. * - * RETURNS: - * Reference to the block_device on success, ERR_PTR(-errno) on failure. + * It can also happen if a block device is opened as O_RDWR | O_WRONLY. */ -struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode, - void *holder, const struct blk_holder_ops *hops) +static unsigned blk_to_file_flags(blk_mode_t mode) +{ + unsigned int flags = 0; + + if ((mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) == + (BLK_OPEN_READ | BLK_OPEN_WRITE)) + flags |= O_RDWR; + else if (mode & BLK_OPEN_WRITE_IOCTL) + flags |= O_RDWR | O_WRONLY; + else if (mode & BLK_OPEN_WRITE) + flags |= O_WRONLY; + else if (mode & BLK_OPEN_READ) + flags |= O_RDONLY; /* homeopathic, because O_RDONLY is 0 */ + else + WARN_ON_ONCE(true); + + if (mode & BLK_OPEN_NDELAY) + flags |= O_NDELAY; + + return flags; +} + +struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, + const struct blk_holder_ops *hops) { + struct file *bdev_file; struct block_device *bdev; + unsigned int flags; + int ret; + + ret = bdev_permission(dev, mode, holder); + if (ret) + return ERR_PTR(ret); + + bdev = blkdev_get_no_open(dev, true); + if (!bdev) + return ERR_PTR(-ENXIO); + + flags = blk_to_file_flags(mode); + bdev_file = alloc_file_pseudo_noaccount(BD_INODE(bdev), + blockdev_mnt, "", flags | O_LARGEFILE, &def_blk_fops); + if (IS_ERR(bdev_file)) { + blkdev_put_no_open(bdev); + return bdev_file; + } + ihold(BD_INODE(bdev)); + + ret = bdev_open(bdev, mode, holder, hops, bdev_file); + if (ret) { + /* We failed to open the block device. Let ->release() know. */ + bdev_file->private_data = ERR_PTR(ret); + fput(bdev_file); + return ERR_PTR(ret); + } + return bdev_file; +} +EXPORT_SYMBOL(bdev_file_open_by_dev); + +struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode, + void *holder, + const struct blk_holder_ops *hops) +{ + struct file *file; dev_t dev; int error; @@ -874,20 +1096,42 @@ struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode, if (error) return ERR_PTR(error); - bdev = blkdev_get_by_dev(dev, mode, holder, hops); - if (!IS_ERR(bdev) && (mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) { - blkdev_put(bdev, holder); - return ERR_PTR(-EACCES); + file = bdev_file_open_by_dev(dev, mode, holder, hops); + if (!IS_ERR(file) && (mode & BLK_OPEN_WRITE)) { + if (bdev_read_only(file_bdev(file))) { + fput(file); + file = ERR_PTR(-EACCES); + } } - return bdev; + return file; +} +EXPORT_SYMBOL(bdev_file_open_by_path); + +static inline void bd_yield_claim(struct file *bdev_file) +{ + struct block_device *bdev = file_bdev(bdev_file); + void *holder = bdev_file->private_data; + + lockdep_assert_held(&bdev->bd_disk->open_mutex); + + if (WARN_ON_ONCE(IS_ERR_OR_NULL(holder))) + return; + + if (!bdev_unclaimed(bdev_file)) + bd_end_claim(bdev, holder); } -EXPORT_SYMBOL(blkdev_get_by_path); -void blkdev_put(struct block_device *bdev, void *holder) +void bdev_release(struct file *bdev_file) { + struct block_device *bdev = file_bdev(bdev_file); + void *holder = bdev_file->private_data; struct gendisk *disk = bdev->bd_disk; + /* We failed to open that block device. */ + if (IS_ERR(holder)) + goto put_no_open; + /* * Sync early if it looks like we're the last one. If someone else * opens the block device between now and the decrement of bd_openers @@ -899,8 +1143,10 @@ void blkdev_put(struct block_device *bdev, void *holder) sync_blockdev(bdev); mutex_lock(&disk->open_mutex); + bdev_yield_write_access(bdev_file); + if (holder) - bd_end_claim(bdev, holder); + bd_yield_claim(bdev_file); /* * Trigger event checking and tell drivers to flush MEDIA_CHANGE @@ -916,9 +1162,42 @@ void blkdev_put(struct block_device *bdev, void *holder) mutex_unlock(&disk->open_mutex); module_put(disk->fops->owner); +put_no_open: blkdev_put_no_open(bdev); } -EXPORT_SYMBOL(blkdev_put); + +/** + * bdev_fput - yield claim to the block device and put the file + * @bdev_file: open block device + * + * Yield claim on the block device and put the file. Ensure that the + * block device can be reclaimed before the file is closed which is a + * deferred operation. + */ +void bdev_fput(struct file *bdev_file) +{ + if (WARN_ON_ONCE(bdev_file->f_op != &def_blk_fops)) + return; + + if (bdev_file->private_data) { + struct block_device *bdev = file_bdev(bdev_file); + struct gendisk *disk = bdev->bd_disk; + + mutex_lock(&disk->open_mutex); + bdev_yield_write_access(bdev_file); + bd_yield_claim(bdev_file); + /* + * Tell release we already gave up our hold on the + * device and if write restrictions are available that + * we already gave up write access to the device. + */ + bdev_file->private_data = BDEV_I(bdev_file->f_mapping->host); + mutex_unlock(&disk->open_mutex); + } + + fput(bdev_file); +} +EXPORT_SYMBOL(bdev_fput); /** * lookup_bdev() - Look up a struct block_device by name. @@ -960,26 +1239,38 @@ out_path_put: } EXPORT_SYMBOL(lookup_bdev); -int __invalidate_device(struct block_device *bdev, bool kill_dirty) +/** + * bdev_mark_dead - mark a block device as dead + * @bdev: block device to operate on + * @surprise: indicate a surprise removal + * + * Tell the file system that this devices or media is dead. If @surprise is set + * to %true the device or media is already gone, if not we are preparing for an + * orderly removal. + * + * This calls into the file system, which then typicall syncs out all dirty data + * and writes back inodes and then invalidates any cached data in the inodes on + * the file system. In addition we also invalidate the block device mapping. + */ +void bdev_mark_dead(struct block_device *bdev, bool surprise) { - struct super_block *sb = get_super(bdev); - int res = 0; - - if (sb) { - /* - * no need to lock the super, get_super holds the - * read mutex so the filesystem cannot go away - * under us (->put_super runs with the write lock - * hold). - */ - shrink_dcache_sb(sb); - res = invalidate_inodes(sb, kill_dirty); - drop_super(sb); + mutex_lock(&bdev->bd_holder_lock); + if (bdev->bd_holder_ops && bdev->bd_holder_ops->mark_dead) + bdev->bd_holder_ops->mark_dead(bdev, surprise); + else { + mutex_unlock(&bdev->bd_holder_lock); + sync_blockdev(bdev); } + invalidate_bdev(bdev); - return res; } -EXPORT_SYMBOL(__invalidate_device); +/* + * New drivers should not use this directly. There are some drivers however + * that needs this for historical reasons. For example, the DASD driver has + * historically had a shutdown to offline mode that doesn't actually remove the + * gendisk that otherwise looks a lot like a safe device removal. + */ +EXPORT_SYMBOL_GPL(bdev_mark_dead); void sync_bdevs(bool wait) { @@ -991,7 +1282,7 @@ void sync_bdevs(bool wait) struct block_device *bdev; spin_lock(&inode->i_lock); - if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) || + if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE | I_NEW) || mapping->nrpages == 0) { spin_unlock(&inode->i_lock); continue; @@ -1034,23 +1325,59 @@ void sync_bdevs(bool wait) } /* - * Handle STATX_DIOALIGN for block devices. - * - * Note that the inode passed to this is the inode of a block device node file, - * not the block device's internal inode. Therefore it is *not* valid to use - * I_BDEV() here; the block device has to be looked up by i_rdev instead. + * Handle STATX_{DIOALIGN, WRITE_ATOMIC} for block devices. */ -void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) +void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask) { struct block_device *bdev; - bdev = blkdev_get_no_open(inode->i_rdev); + /* + * Note that d_backing_inode() returns the block device node inode, not + * the block device's internal inode. Therefore it is *not* valid to + * use I_BDEV() here; the block device has to be looked up by i_rdev + * instead. + */ + bdev = blkdev_get_no_open(d_backing_inode(path->dentry)->i_rdev, false); if (!bdev) return; - stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; - stat->dio_offset_align = bdev_logical_block_size(bdev); - stat->result_mask |= STATX_DIOALIGN; + if (request_mask & STATX_DIOALIGN) { + stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; + stat->dio_offset_align = bdev_logical_block_size(bdev); + stat->result_mask |= STATX_DIOALIGN; + } + + if (request_mask & STATX_WRITE_ATOMIC && bdev_can_atomic_write(bdev)) { + struct request_queue *bd_queue = bdev->bd_queue; + + generic_fill_statx_atomic_writes(stat, + queue_atomic_write_unit_min_bytes(bd_queue), + queue_atomic_write_unit_max_bytes(bd_queue), + 0); + } + + stat->blksize = bdev_io_min(bdev); blkdev_put_no_open(bdev); } + +bool disk_live(struct gendisk *disk) +{ + return !inode_unhashed(BD_INODE(disk->part0)); +} +EXPORT_SYMBOL_GPL(disk_live); + +unsigned int block_size(struct block_device *bdev) +{ + return 1 << BD_INODE(bdev)->i_blkbits; +} +EXPORT_SYMBOL_GPL(block_size); + +static int __init setup_bdev_allow_write_mounted(char *str) +{ + if (kstrtobool(str, &bdev_allow_write_mounted)) + pr_warn("Invalid option string for bdev_allow_write_mounted:" + " '%s'\n", str); + return 1; +} +__setup("bdev_allow_write_mounted=", setup_bdev_allow_write_mounted); |