diff options
48 files changed, 224 insertions, 254 deletions
diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index f2b44c2400c6..92bffcc6747a 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -1134,3 +1134,10 @@ superblock of the main block device, i.e., the one stored in sb->s_bdev. Block device freezing now works for any block device owned by a given superblock, not just the main block device. The get_active_super() helper and bd_fsfreeze_sb pointer are gone. + +--- + +**mandatory** + +set_blocksize() takes opened struct file instead of struct block_device now +and it *must* be opened exclusive. diff --git a/block/bdev.c b/block/bdev.c index 2af3dca56f3d..5a03c93ba222 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -43,6 +43,11 @@ 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; @@ -57,7 +62,7 @@ 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); @@ -76,7 +81,7 @@ 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; @@ -88,7 +93,7 @@ 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(); @@ -116,7 +121,7 @@ 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; @@ -126,7 +131,7 @@ 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); } @@ -134,18 +139,21 @@ 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); } -int set_blocksize(struct block_device *bdev, int size) +int set_blocksize(struct file *file, int size) { + struct inode *inode = file->f_mapping->host; + struct block_device *bdev = I_BDEV(inode); + /* Size must be a power of two, and between 512 and PAGE_SIZE */ if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size)) return -EINVAL; @@ -154,10 +162,13 @@ int set_blocksize(struct block_device *bdev, int size) if (size < bdev_logical_block_size(bdev)) return -EINVAL; + 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)) { sync_blockdev(bdev); - bdev->bd_inode->i_blkbits = blksize_bits(size); + inode->i_blkbits = blksize_bits(size); kill_bdev(bdev); } return 0; @@ -167,7 +178,7 @@ EXPORT_SYMBOL(set_blocksize); int sb_set_blocksize(struct super_block *sb, int size) { - if (set_blocksize(sb->s_bdev, size)) + if (set_blocksize(sb->s_bdev_file, size)) return 0; /* If we get here, we know size is power of two * and it's value is between 512 and PAGE_SIZE */ @@ -192,7 +203,7 @@ 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); @@ -204,13 +215,13 @@ 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); @@ -412,7 +423,7 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) spin_lock_init(&bdev->bd_size_lock); mutex_init(&bdev->bd_holder_lock); bdev->bd_partno = partno; - bdev->bd_inode = inode; + bdev->bd_mapping = &inode->i_data; bdev->bd_queue = disk->queue; if (partno) bdev->bd_has_submit_bio = disk->part0->bd_has_submit_bio; @@ -430,19 +441,30 @@ 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_inode->i_mapping); + 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) @@ -917,7 +939,7 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder, 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_inode->i_mapping; + 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; @@ -979,13 +1001,13 @@ struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, return ERR_PTR(-ENXIO); flags = blk_to_file_flags(mode); - bdev_file = alloc_file_pseudo_noaccount(bdev->bd_inode, + 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(bdev->bd_inode); + ihold(BD_INODE(bdev)); ret = bdev_open(bdev, mode, holder, hops, bdev_file); if (ret) { @@ -1260,6 +1282,18 @@ void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) 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)) diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 48e5e3bbb89c..57d367ada1f2 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -416,7 +416,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode, op = REQ_OP_ZONE_RESET; /* Invalidate the page cache, including dirty pages. */ - filemap_invalidate_lock(bdev->bd_inode->i_mapping); + filemap_invalidate_lock(bdev->bd_mapping); ret = blkdev_truncate_zone_range(bdev, mode, &zrange); if (ret) goto fail; @@ -438,7 +438,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode, fail: if (cmd == BLKRESETZONE) - filemap_invalidate_unlock(bdev->bd_inode->i_mapping); + filemap_invalidate_unlock(bdev->bd_mapping); return ret; } diff --git a/block/blk.h b/block/blk.h index 6e94c10af798..189bc25beb50 100644 --- a/block/blk.h +++ b/block/blk.h @@ -499,6 +499,8 @@ static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, struct block_device *bdev_alloc(struct gendisk *disk, u8 partno); void bdev_add(struct block_device *bdev, dev_t dev); +void bdev_unhash(struct block_device *bdev); +void bdev_drop(struct block_device *bdev); int blk_alloc_ext_minor(void); void blk_free_ext_minor(unsigned int minor); diff --git a/block/fops.c b/block/fops.c index 7a163f7fe2d8..376265935714 100644 --- a/block/fops.c +++ b/block/fops.c @@ -663,8 +663,8 @@ static ssize_t blkdev_buffered_write(struct kiocb *iocb, struct iov_iter *from) static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; - struct block_device *bdev = I_BDEV(file->f_mapping->host); - struct inode *bd_inode = bdev->bd_inode; + struct inode *bd_inode = bdev_file_inode(file); + struct block_device *bdev = I_BDEV(bd_inode); loff_t size = bdev_nr_bytes(bdev); size_t shorted = 0; ssize_t ret; diff --git a/block/genhd.c b/block/genhd.c index 7f39fbe60753..0519097afa35 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -653,7 +653,7 @@ void del_gendisk(struct gendisk *disk) */ mutex_lock(&disk->open_mutex); xa_for_each(&disk->part_tbl, idx, part) - remove_inode_hash(part->bd_inode); + bdev_unhash(part); mutex_unlock(&disk->open_mutex); /* @@ -742,7 +742,7 @@ void invalidate_disk(struct gendisk *disk) struct block_device *bdev = disk->part0; invalidate_bdev(bdev); - bdev->bd_inode->i_mapping->wb_err = 0; + bdev->bd_mapping->wb_err = 0; set_capacity(disk, 0); } EXPORT_SYMBOL(invalidate_disk); @@ -1191,7 +1191,7 @@ static void disk_release(struct device *dev) if (test_bit(GD_ADDED, &disk->state) && disk->fops->free_disk) disk->fops->free_disk(disk); - iput(disk->part0->bd_inode); /* frees the disk */ + bdev_drop(disk->part0); /* frees the disk */ } static int block_uevent(const struct device *dev, struct kobj_uevent_env *env) @@ -1379,7 +1379,7 @@ out_erase_part0: out_destroy_part_tbl: xa_destroy(&disk->part_tbl); disk->part0->bd_disk = NULL; - iput(disk->part0->bd_inode); + bdev_drop(disk->part0); out_free_bdi: bdi_put(disk->bdi); out_free_bioset: diff --git a/block/ioctl.c b/block/ioctl.c index c7db3bd2d653..515f75fd0d83 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -96,7 +96,6 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode, unsigned long arg) { unsigned int bs_mask = bdev_logical_block_size(bdev) - 1; - struct inode *inode = bdev->bd_inode; uint64_t range[2], start, len, end; struct bio *prev = NULL, *bio; sector_t sector, nr_sects; @@ -126,7 +125,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode, end > bdev_nr_bytes(bdev)) return -EINVAL; - filemap_invalidate_lock(inode->i_mapping); + filemap_invalidate_lock(bdev->bd_mapping); err = truncate_bdev_range(bdev, mode, start, start + len - 1); if (err) goto fail; @@ -157,7 +156,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode, out_unplug: blk_finish_plug(&plug); fail: - filemap_invalidate_unlock(inode->i_mapping); + filemap_invalidate_unlock(bdev->bd_mapping); return err; } @@ -182,12 +181,12 @@ static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode, if (start + len > bdev_nr_bytes(bdev)) return -EINVAL; - filemap_invalidate_lock(bdev->bd_inode->i_mapping); + filemap_invalidate_lock(bdev->bd_mapping); err = truncate_bdev_range(bdev, mode, start, start + len - 1); if (!err) err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9, GFP_KERNEL); - filemap_invalidate_unlock(bdev->bd_inode->i_mapping); + filemap_invalidate_unlock(bdev->bd_mapping); return err; } @@ -197,7 +196,6 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode, { uint64_t range[2]; uint64_t start, end, len; - struct inode *inode = bdev->bd_inode; int err; if (!(mode & BLK_OPEN_WRITE)) @@ -220,7 +218,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode, return -EINVAL; /* Invalidate the page cache, including dirty pages */ - filemap_invalidate_lock(inode->i_mapping); + filemap_invalidate_lock(bdev->bd_mapping); err = truncate_bdev_range(bdev, mode, start, end); if (err) goto fail; @@ -229,7 +227,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode, BLKDEV_ZERO_NOUNMAP); fail: - filemap_invalidate_unlock(inode->i_mapping); + filemap_invalidate_unlock(bdev->bd_mapping); return err; } @@ -503,11 +501,14 @@ static int compat_hdio_getgeo(struct block_device *bdev, #endif /* set the logical block size */ -static int blkdev_bszset(struct block_device *bdev, blk_mode_t mode, +static int blkdev_bszset(struct file *file, blk_mode_t mode, int __user *argp) { + // this one might be file_inode(file)->i_rdev - a rare valid + // use of file_inode() for those. + dev_t dev = I_BDEV(file->f_mapping->host)->bd_dev; + struct file *excl_file; int ret, n; - struct file *file; if (!capable(CAP_SYS_ADMIN)) return -EACCES; @@ -517,13 +518,13 @@ static int blkdev_bszset(struct block_device *bdev, blk_mode_t mode, return -EFAULT; if (mode & BLK_OPEN_EXCL) - return set_blocksize(bdev, n); + return set_blocksize(file, n); - file = bdev_file_open_by_dev(bdev->bd_dev, mode, &bdev, NULL); - if (IS_ERR(file)) + excl_file = bdev_file_open_by_dev(dev, mode, &dev, NULL); + if (IS_ERR(excl_file)) return -EBUSY; - ret = set_blocksize(bdev, n); - fput(file); + ret = set_blocksize(excl_file, n); + fput(excl_file); return ret; } @@ -652,7 +653,7 @@ long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */ return put_int(argp, block_size(bdev)); case BLKBSZSET: - return blkdev_bszset(bdev, mode, argp); + return blkdev_bszset(file, mode, argp); case BLKGETSIZE64: return put_u64(argp, bdev_nr_bytes(bdev)); @@ -712,7 +713,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */ return put_int(argp, bdev_logical_block_size(bdev)); case BLKBSZSET_32: - return blkdev_bszset(bdev, mode, argp); + return blkdev_bszset(file, mode, argp); case BLKGETSIZE64_32: return put_u64(argp, bdev_nr_bytes(bdev)); diff --git a/block/partitions/core.c b/block/partitions/core.c index 37b5f92d07fe..84023b82e5a1 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -243,7 +243,7 @@ static const struct attribute_group *part_attr_groups[] = { static void part_release(struct device *dev) { put_disk(dev_to_bdev(dev)->bd_disk); - iput(dev_to_bdev(dev)->bd_inode); + bdev_drop(dev_to_bdev(dev)); } static int part_uevent(const struct device *dev, struct kobj_uevent_env *env) @@ -469,7 +469,7 @@ int bdev_del_partition(struct gendisk *disk, int partno) * Just delete the partition and invalidate it. */ - remove_inode_hash(part->bd_inode); + bdev_unhash(part); invalidate_bdev(part); drop_partition(part); ret = 0; @@ -652,7 +652,7 @@ rescan: * it cannot be looked up any more even when openers * still hold references. */ - remove_inode_hash(part->bd_inode); + bdev_unhash(part); /* * If @disk->open_partitions isn't elevated but there's @@ -701,7 +701,7 @@ EXPORT_SYMBOL_GPL(bdev_disk_changed); void *read_part_sector(struct parsed_partitions *state, sector_t n, Sector *p) { - struct address_space *mapping = state->disk->part0->bd_inode->i_mapping; + struct address_space *mapping = state->disk->part0->bd_mapping; struct folio *folio; if (n >= get_capacity(state->disk)) { diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 21728e9ea5c3..8a2ce8070010 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2215,6 +2215,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, bool write) } dev_info(ddev, "%lukB available on disc\n", lba << 1); } + set_blocksize(bdev_file, CD_FRAMESIZE); return 0; @@ -2278,11 +2279,6 @@ static int pkt_open(struct gendisk *disk, blk_mode_t mode) ret = pkt_open_dev(pd, mode & BLK_OPEN_WRITE); if (ret) goto out_dec; - /* - * needed here as well, since ext2 (among others) may change - * the blocksize at mount time - */ - set_blocksize(disk->part0, CD_FRAMESIZE); } mutex_unlock(&ctl_mutex); mutex_unlock(&pktcdvd_mutex); @@ -2526,7 +2522,6 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) __module_get(THIS_MODULE); pd->bdev_file = bdev_file; - set_blocksize(file_bdev(bdev_file), CD_FRAMESIZE); atomic_set(&pd->cdrw.pending_bios, 0); pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->disk->disk_name); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 4cf38f7d3e0a..3acd7006ad2c 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -426,11 +426,10 @@ static void reset_bdev(struct zram *zram) if (!zram->backing_dev) return; - fput(zram->bdev_file); /* hope filp_close flush all of IO */ filp_close(zram->backing_dev, NULL); zram->backing_dev = NULL; - zram->bdev_file = NULL; + zram->bdev = NULL; zram->disk->fops = &zram_devops; kvfree(zram->bitmap); zram->bitmap = NULL; @@ -473,10 +472,8 @@ static ssize_t backing_dev_store(struct device *dev, size_t sz; struct file *backing_dev = NULL; struct inode *inode; - struct address_space *mapping; unsigned int bitmap_sz; unsigned long nr_pages, *bitmap = NULL; - struct file *bdev_file = NULL; int err; struct zram *zram = dev_to_zram(dev); @@ -497,15 +494,14 @@ static ssize_t backing_dev_store(struct device *dev, if (sz > 0 && file_name[sz - 1] == '\n') file_name[sz - 1] = 0x00; - backing_dev = filp_open(file_name, O_RDWR|O_LARGEFILE, 0); + backing_dev = filp_open(file_name, O_RDWR | O_LARGEFILE | O_EXCL, 0); if (IS_ERR(backing_dev)) { err = PTR_ERR(backing_dev); backing_dev = NULL; goto out; } - mapping = backing_dev->f_mapping; - inode = mapping->host; + inode = backing_dev->f_mapping->host; /* Support only block device in this moment */ if (!S_ISBLK(inode->i_mode)) { @@ -513,14 +509,6 @@ static ssize_t backing_dev_store(struct device *dev, goto out; } - bdev_file = bdev_file_open_by_dev(inode->i_rdev, - BLK_OPEN_READ | BLK_OPEN_WRITE, zram, NULL); - if (IS_ERR(bdev_file)) { - err = PTR_ERR(bdev_file); - bdev_file = NULL; - goto out; - } - nr_pages = i_size_read(inode) >> PAGE_SHIFT; bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long); bitmap = kvzalloc(bitmap_sz, GFP_KERNEL); @@ -531,7 +519,7 @@ static ssize_t backing_dev_store(struct device *dev, reset_bdev(zram); - zram->bdev_file = bdev_file; + zram->bdev = I_BDEV(inode); zram->backing_dev = backing_dev; zram->bitmap = bitmap; zram->nr_pages = nr_pages; @@ -544,9 +532,6 @@ static ssize_t backing_dev_store(struct device *dev, out: kvfree(bitmap); - if (bdev_file) - fput(bdev_file); - if (backing_dev) filp_close(backing_dev, NULL); @@ -587,7 +572,7 @@ static void read_from_bdev_async(struct zram *zram, struct page *page, { struct bio *bio; - bio = bio_alloc(file_bdev(zram->bdev_file), 1, parent->bi_opf, GFP_NOIO); + bio = bio_alloc(zram->bdev, 1, parent->bi_opf, GFP_NOIO); bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9); __bio_add_page(bio, page, PAGE_SIZE, 0); bio_chain(bio, parent); @@ -703,7 +688,7 @@ static ssize_t writeback_store(struct device *dev, continue; } - bio_init(&bio, file_bdev(zram->bdev_file), &bio_vec, 1, + bio_init(&bio, zram->bdev, &bio_vec, 1, REQ_OP_WRITE | REQ_SYNC); bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9); __bio_add_page(&bio, page, PAGE_SIZE, 0); @@ -785,7 +770,7 @@ static void zram_sync_read(struct work_struct *work) struct bio_vec bv; struct bio bio; - bio_init(&bio, file_bdev(zw->zram->bdev_file), &bv, 1, REQ_OP_READ); + bio_init(&bio, zw->zram->bdev, &bv, 1, REQ_OP_READ); bio.bi_iter.bi_sector = zw->entry * (PAGE_SIZE >> 9); __bio_add_page(&bio, zw->page, PAGE_SIZE, 0); zw->error = submit_bio_wait(&bio); diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 37bf29f34d26..35e322144629 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -132,7 +132,7 @@ struct zram { spinlock_t wb_limit_lock; bool wb_limit_enable; u64 bd_wb_limit; - struct file *bdev_file; + struct block_device *bdev; unsigned long *bitmap; unsigned long nr_pages; #endif diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index cba09660148a..4d11fc664cb0 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -171,7 +171,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev, struct page *page; unsigned int i; - page = read_cache_page_gfp(bdev->bd_inode->i_mapping, + page = read_cache_page_gfp(bdev->bd_mapping, SB_OFFSET >> PAGE_SHIFT, GFP_KERNEL); if (IS_ERR(page)) return "IO error"; @@ -2555,10 +2555,6 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, if (IS_ERR(bdev_file)) goto out_free_sb; - err = "failed to set blocksize"; - if (set_blocksize(file_bdev(bdev_file), 4096)) - goto out_blkdev_put; - err = read_super(sb, file_bdev(bdev_file), &sb_disk); if (err) goto out_blkdev_put; diff --git a/drivers/md/dm-vdo/dm-vdo-target.c b/drivers/md/dm-vdo/dm-vdo-target.c index 5a4b0a927f56..b423bec6458b 100644 --- a/drivers/md/dm-vdo/dm-vdo-target.c +++ b/drivers/md/dm-vdo/dm-vdo-target.c @@ -878,7 +878,7 @@ static int parse_device_config(int argc, char **argv, struct dm_target *ti, } if (config->version == 0) { - u64 device_size = i_size_read(config->owned_device->bdev->bd_inode); + u64 device_size = bdev_nr_bytes(config->owned_device->bdev); config->physical_blocks = device_size / VDO_BLOCK_SIZE; } @@ -1011,7 +1011,7 @@ static void vdo_status(struct dm_target *ti, status_type_t status_type, static block_count_t __must_check get_underlying_device_block_count(const struct vdo *vdo) { - return i_size_read(vdo_get_backing_device(vdo)->bd_inode) / VDO_BLOCK_SIZE; + return bdev_nr_bytes(vdo_get_backing_device(vdo)) / VDO_BLOCK_SIZE; } static int __must_check process_vdo_message_locked(struct vdo *vdo, unsigned int argc, diff --git a/drivers/md/dm-vdo/indexer/io-factory.c b/drivers/md/dm-vdo/indexer/io-factory.c index 515765d35794..1bee9d63dc0a 100644 --- a/drivers/md/dm-vdo/indexer/io-factory.c +++ b/drivers/md/dm-vdo/indexer/io-factory.c @@ -90,7 +90,7 @@ void uds_put_io_factory(struct io_factory *factory) size_t uds_get_writable_size(struct io_factory *factory) { - return i_size_read(factory->bdev->bd_inode); + return bdev_nr_bytes(factory->bdev); } /* Create a struct dm_bufio_client for an index region starting at offset. */ diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c index caacdc0a3819..b06c8dd51562 100644 --- a/drivers/mtd/devices/block2mtd.c +++ b/drivers/mtd/devices/block2mtd.c @@ -265,6 +265,7 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size, struct file *bdev_file; struct block_device *bdev; struct block2mtd_dev *dev; + loff_t size; char *name; if (!devname) @@ -291,7 +292,8 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size, goto err_free_block2mtd; } - if ((long)bdev->bd_inode->i_size % erase_size) { + size = bdev_nr_bytes(bdev); + if ((long)size % erase_size) { pr_err("erasesize must be a divisor of device size\n"); goto err_free_block2mtd; } @@ -309,7 +311,7 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size, dev->mtd.name = name; - dev->mtd.size = bdev->bd_inode->i_size & PAGE_MASK; + dev->mtd.size = size & PAGE_MASK; dev->mtd.erasesize = erase_size; dev->mtd.writesize = 1; dev->mtd.writebufsize = PAGE_SIZE; diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index 7e0ed7032f76..eb5dcbe37230 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -215,7 +215,7 @@ dasd_format(struct dasd_block *block, struct format_data_t *fdata) * enabling the device later. */ if (fdata->start_unit == 0) { - block->gdp->part0->bd_inode->i_blkbits = + block->gdp->part0->bd_mapping->host->i_blkbits = blksize_bits(fdata->blksize); } diff --git a/drivers/scsi/scsicam.c b/drivers/scsi/scsicam.c index e2c7d8ef205f..dd69342bbe78 100644 --- a/drivers/scsi/scsicam.c +++ b/drivers/scsi/scsicam.c @@ -32,7 +32,7 @@ */ unsigned char *scsi_bios_ptable(struct block_device *dev) { - struct address_space *mapping = bdev_whole(dev)->bd_inode->i_mapping; + struct address_space *mapping = bdev_whole(dev)->bd_mapping; unsigned char *res = NULL; struct folio *folio; diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h index 5cf885b09986..5d2c470a49ac 100644 --- a/fs/bcachefs/util.h +++ b/fs/bcachefs/util.h @@ -445,11 +445,6 @@ static inline unsigned fract_exp_two(unsigned x, unsigned fract_bits) void bch2_bio_map(struct bio *bio, void *base, size_t); int bch2_bio_alloc_pages(struct bio *, size_t, gfp_t); -static inline sector_t bdev_sectors(struct block_device *bdev) -{ - return bdev->bd_inode->i_size >> 9; -} - #define closure_bio_submit(bio, cl) \ do { \ closure_get(cl); \ diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 7696beec4c21..7130040d92ab 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -316,7 +316,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); device->dev_stats_valid = 1; - set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); + set_blocksize(bdev_file, BTRFS_BDEV_BLOCKSIZE); device->fs_devices = fs_devices; ret = btrfs_get_dev_zone_info(device, false); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index a91a8056758a..1b20b3e390df 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3656,7 +3656,7 @@ struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev, struct btrfs_super_block *super; struct page *page; u64 bytenr, bytenr_orig; - struct address_space *mapping = bdev->bd_inode->i_mapping; + struct address_space *mapping = bdev->bd_mapping; int ret; bytenr_orig = btrfs_sb_offset(copy_num); @@ -3743,7 +3743,7 @@ static int write_dev_supers(struct btrfs_device *device, struct btrfs_super_block *sb, int max_mirrors) { struct btrfs_fs_info *fs_info = device->fs_info; - struct address_space *mapping = device->bdev->bd_inode->i_mapping; + struct address_space *mapping = device->bdev->bd_mapping; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); int i; int ret; @@ -3861,7 +3861,7 @@ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors) device->commit_total_bytes) break; - folio = filemap_get_folio(device->bdev->bd_inode->i_mapping, + folio = filemap_get_folio(device->bdev->bd_mapping, bytenr >> PAGE_SHIFT); /* If the folio has been removed, then we know it completed. */ if (IS_ERR(folio)) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b6a701011fb0..c39145e8c4ad 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -482,10 +482,12 @@ btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder, if (flush) sync_blockdev(bdev); - ret = set_blocksize(bdev, BTRFS_BDEV_BLOCKSIZE); - if (ret) { - fput(*bdev_file); - goto error; + if (holder) { + ret = set_blocksize(*bdev_file, BTRFS_BDEV_BLOCKSIZE); + if (ret) { + fput(*bdev_file); + goto error; + } } invalidate_bdev(bdev); *disk_super = btrfs_read_dev_super(bdev); @@ -498,6 +500,7 @@ btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder, return 0; error: + *disk_super = NULL; *bdev_file = NULL; return ret; } @@ -1287,7 +1290,7 @@ static struct btrfs_super_block *btrfs_read_disk_super(struct block_device *bdev return ERR_PTR(-EINVAL); /* pull in the page with our super */ - page = read_cache_page_gfp(bdev->bd_inode->i_mapping, index, GFP_KERNEL); + page = read_cache_page_gfp(bdev->bd_mapping, index, GFP_KERNEL); if (IS_ERR(page)) return ERR_CAST(page); @@ -2714,7 +2717,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); clear_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); device->dev_stats_valid = 1; - set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); + set_blocksize(device->bdev_file, BTRFS_BDEV_BLOCKSIZE); if (seeding_dev) { btrfs_clear_sb_rdonly(sb); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 4cba80b34387..9b43fa493219 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -118,7 +118,7 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones, return -ENOENT; } else if (full[0] && full[1]) { /* Compare two super blocks */ - struct address_space *mapping = bdev->bd_inode->i_mapping; + struct address_space *mapping = bdev->bd_mapping; struct page *page[BTRFS_NR_SB_LOG_ZONES]; struct btrfs_super_block *super[BTRFS_NR_SB_LOG_ZONES]; int i; diff --git a/fs/buffer.c b/fs/buffer.c index ed698caa8834..8c19e705b9c3 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -189,8 +189,8 @@ EXPORT_SYMBOL(end_buffer_write_sync); static struct buffer_head * __find_get_block_slow(struct block_device *bdev, sector_t block) { - struct inode *bd_inode = bdev->bd_inode; - struct address_space *bd_mapping = bd_inode->i_mapping; + struct address_space *bd_mapping = bdev->bd_mapping; + const int blkbits = bd_mapping->host->i_blkbits; struct buffer_head *ret = NULL; pgoff_t index; struct buffer_head *bh; @@ -199,7 +199,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) int all_mapped = 1; static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); - index = ((loff_t)block << bd_inode->i_blkbits) / PAGE_SIZE; + index = ((loff_t)block << blkbits) / PAGE_SIZE; folio = __filemap_get_folio(bd_mapping, index, FGP_ACCESSED, 0); if (IS_ERR(folio)) goto out; @@ -233,7 +233,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) (unsigned long long)block, (unsigned long long)bh->b_blocknr, bh->b_state, bh->b_size, bdev, - 1 << bd_inode->i_blkbits); + 1 << blkbits); } out_unlock: spin_unlock(&bd_mapping->i_private_lock); @@ -1041,12 +1041,12 @@ static sector_t folio_init_buffers(struct folio *folio, static bool grow_dev_folio(struct block_device *bdev, sector_t block, pgoff_t index, unsigned size, gfp_t gfp) { - struct inode *inode = bdev->bd_inode; + struct address_space *mapping = bdev->bd_mapping; struct folio *folio; struct buffer_head *bh; sector_t end_block = 0; - folio = __filemap_get_folio(inode->i_mapping, index, + folio = __filemap_get_folio(mapping, index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (IS_ERR(folio)) return false; @@ -1080,10 +1080,10 @@ static bool grow_dev_folio(struct block_device *bdev, sector_t block, * lock to be atomic wrt __find_get_block(), which does not * run under the folio lock. */ - spin_lock(&inode->i_mapping->i_private_lock); + spin_lock(&mapping->i_private_lock); link_dev_buffers(folio, bh); end_block = folio_init_buffers(folio, bdev, size); - spin_unlock(&inode->i_mapping->i_private_lock); + spin_unlock(&mapping->i_private_lock); unlock: folio_unlock(folio); folio_put(folio); @@ -1486,7 +1486,7 @@ struct buffer_head *__bread_gfp(struct block_device *bdev, sector_t block, { struct buffer_head *bh; - gfp |= mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS); + gfp |= mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS); /* * Prefer looping in the allocator rather than here, at least that @@ -1719,16 +1719,16 @@ EXPORT_SYMBOL(create_empty_buffers); */ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len) { - struct inode *bd_inode = bdev->bd_inode; - struct address_space *bd_mapping = bd_inode->i_mapping; + struct address_space *bd_mapping = bdev->bd_mapping; + const int blkbits = bd_mapping->host->i_blkbits; struct folio_batch fbatch; - pgoff_t index = ((loff_t)block << bd_inode->i_blkbits) / PAGE_SIZE; + pgoff_t index = ((loff_t)block << blkbits) / PAGE_SIZE; pgoff_t end; int i, count; struct buffer_head *bh; struct buffer_head *head; - end = ((loff_t)(block + len - 1) << bd_inode->i_blkbits) / PAGE_SIZE; + end = ((loff_t)(block + len - 1) << blkbits) / PAGE_SIZE; folio_batch_init(&fbatch); while (filemap_get_folios(bd_mapping, &index, end, &fbatch)) { count = folio_batch_count(&fbatch); diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 9901057a15ba..460690ca0174 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -183,7 +183,7 @@ static int next_buffer; static void *cramfs_blkdev_read(struct super_block *sb, unsigned int offset, unsigned int len) { - struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; + struct address_space *mapping = sb->s_bdev->bd_mapping; struct file_ra_state ra = {}; struct page *pages[BLKS_PER_BUF]; unsigned i, blocknr, buffer; diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 52524bd9698b..5fc03c1e2757 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -29,11 +29,9 @@ void erofs_put_metabuf(struct erofs_buf *buf) * Derive the block size from inode->i_blkbits to make compatible with * anonymous inode in fscache mode. */ -void *erofs_bread(struct erofs_buf *buf, erofs_blk_t blkaddr, +void *erofs_bread(struct erofs_buf *buf, erofs_off_t offset, enum erofs_kmap_type type) { - struct inode *inode = buf->inode; - erofs_off_t offset = (erofs_off_t)blkaddr << inode->i_blkbits; pgoff_t index = offset >> PAGE_SHIFT; struct page *page = buf->page; struct folio *folio; @@ -43,7 +41,7 @@ void *erofs_bread(struct erofs_buf *buf, erofs_blk_t blkaddr, erofs_put_metabuf(buf); nofs_flag = memalloc_nofs_save(); - folio = read_cache_folio(inode->i_mapping, index, NULL, NULL); + folio = read_cache_folio(buf->mapping, index, NULL, NULL); memalloc_nofs_restore(nofs_flag); if (IS_ERR(folio)) return folio; @@ -68,16 +66,16 @@ void *erofs_bread(struct erofs_buf *buf, erofs_blk_t blkaddr, void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb) { if (erofs_is_fscache_mode(sb)) - buf->inode = EROFS_SB(sb)->s_fscache->inode; + buf->mapping = EROFS_SB(sb)->s_fscache->inode->i_mapping; else - buf->inode = sb->s_bdev->bd_inode; + buf->mapping = sb->s_bdev->bd_mapping; } void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, erofs_blk_t blkaddr, enum erofs_kmap_type type) { erofs_init_metabuf(buf, sb); - return erofs_bread(buf, blkaddr, type); + return erofs_bread(buf, erofs_pos(sb, blkaddr), type); } static int erofs_map_blocks_flatmode(struct inode *inode, diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c index b80abec0531a..2193a6710c8f 100644 --- a/fs/erofs/dir.c +++ b/fs/erofs/dir.c @@ -58,12 +58,12 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx) int err = 0; bool initial = true; - buf.inode = dir; + buf.mapping = dir->i_mapping; while (ctx->pos < dirsize) { struct erofs_dirent *de; unsigned int nameoff, maxsize; - de = erofs_bread(&buf, i, EROFS_KMAP); + de = erofs_bread(&buf, erofs_pos(sb, i), EROFS_KMAP); if (IS_ERR(de)) { erofs_err(sb, "fail to readdir of logical block %u of nid %llu", i, EROFS_I(dir)->nid); diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 21def866a482..00bbb288c08c 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -216,7 +216,7 @@ enum erofs_kmap_type { }; struct erofs_buf { - struct inode *inode; + struct address_space *mapping; struct page *page; void *base; enum erofs_kmap_type kmap_type; @@ -402,7 +402,7 @@ void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, erofs_off_t *offset, int *lengthp); void erofs_unmap_metabuf(struct erofs_buf *buf); void erofs_put_metabuf(struct erofs_buf *buf); -void *erofs_bread(struct erofs_buf *buf, erofs_blk_t blkaddr, +void *erofs_bread(struct erofs_buf *buf, erofs_off_t offset, enum erofs_kmap_type type); void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb); void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c index f0110a78acb2..c94d0c1608a8 100644 --- a/fs/erofs/namei.c +++ b/fs/erofs/namei.c @@ -99,8 +99,8 @@ static void *erofs_find_target_block(struct erofs_buf *target, struct erofs_buf buf = __EROFS_BUF_INITIALIZER; struct erofs_dirent *de; - buf.inode = dir; - de = erofs_bread(&buf, mid, EROFS_KMAP); + buf.mapping = dir->i_mapping; + de = erofs_bread(&buf, erofs_pos(dir->i_sb, mid), EROFS_KMAP); if (!IS_ERR(de)) { const int nameoff = nameoff_from_disk(de->nameoff, bsz); const int ndirents = nameoff / sizeof(*de); @@ -171,7 +171,7 @@ int erofs_namei(struct inode *dir, const struct qstr *name, erofs_nid_t *nid, qn.name = name->name; qn.end = name->name + name->len; - buf.inode = dir; + buf.mapping = dir->i_mapping; ndirents = 0; de = erofs_find_target_block(&buf, dir, &qn, &ndirents); diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 044c79229a78..348ef1660e50 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -132,11 +132,11 @@ void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, int len, i, cnt; *offset = round_up(*offset, 4); - ptr = erofs_bread(buf, erofs_blknr(sb, *offset), EROFS_KMAP); + ptr = erofs_bread(buf, *offset, EROFS_KMAP); if (IS_ERR(ptr)) return ptr; - len = le16_to_cpu(*(__le16 *)&ptr[erofs_blkoff(sb, *offset)]); + len = le16_to_cpu(*(__le16 *)ptr); if (!len) len = U16_MAX + 1; buffer = kmalloc(len, GFP_KERNEL); @@ -148,12 +148,12 @@ void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, for (i = 0; i < len; i += cnt) { cnt = min_t(int, sb->s_blocksize - erofs_blkoff(sb, *offset), len - i); - ptr = erofs_bread(buf, erofs_blknr(sb, *offset), EROFS_KMAP); + ptr = erofs_bread(buf, *offset, EROFS_KMAP); if (IS_ERR(ptr)) { kfree(buffer); return ptr; } - memcpy(buffer + i, ptr + erofs_blkoff(sb, *offset), cnt); + memcpy(buffer + i, ptr, cnt); *offset += cnt; } return buffer; diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index b58316b49a43..a90d7d649739 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -81,13 +81,13 @@ static int erofs_init_inode_xattrs(struct inode *inode) it.pos = erofs_iloc(inode) + vi->inode_isize; /* read in shared xattr array (non-atomic, see kmalloc below) */ - it.kaddr = erofs_bread(&it.buf, erofs_blknr(sb, it.pos), EROFS_KMAP); + it.kaddr = erofs_bread(&it.buf, it.pos, EROFS_KMAP); if (IS_ERR(it.kaddr)) { ret = PTR_ERR(it.kaddr); goto out_unlock; } - ih = it.kaddr + erofs_blkoff(sb, it.pos); + ih = it.kaddr; vi->xattr_name_filter = le32_to_cpu(ih->h_name_filter); vi->xattr_shared_count = ih->h_shared_count; vi->xattr_shared_xattrs = kmalloc_array(vi->xattr_shared_count, @@ -102,16 +102,14 @@ static int erofs_init_inode_xattrs(struct inode *inode) it.pos += sizeof(struct erofs_xattr_ibody_header); for (i = 0; i < vi->xattr_shared_count; ++i) { - it.kaddr = erofs_bread(&it.buf, erofs_blknr(sb, it.pos), - EROFS_KMAP); + it.kaddr = erofs_bread(&it.buf, it.pos, EROFS_KMAP); if (IS_ERR(it.kaddr)) { kfree(vi->xattr_shared_xattrs); vi->xattr_shared_xattrs = NULL; ret = PTR_ERR(it.kaddr); goto out_unlock; } - vi->xattr_shared_xattrs[i] = le32_to_cpu(*(__le32 *) - (it.kaddr + erofs_blkoff(sb, it.pos))); + vi->xattr_shared_xattrs[i] = le32_to_cpu(*(__le32 *)it.kaddr); it.pos += sizeof(__le32); } erofs_put_metabuf(&it.buf); @@ -185,12 +183,11 @@ static int erofs_xattr_copy_to_buffer(struct erofs_xattr_iter *it, void *src; for (processed = 0; processed < len; processed += slice) { - it->kaddr = erofs_bread(&it->buf, erofs_blknr(sb, it->pos), - EROFS_KMAP); + it->kaddr = erofs_bread(&it->buf, it->pos, EROFS_KMAP); if (IS_ERR(it->kaddr)) return PTR_ERR(it->kaddr); - src = it->kaddr + erofs_blkoff(sb, it->pos); + src = it->kaddr; slice = min_t(unsigned int, sb->s_blocksize - erofs_blkoff(sb, it->pos), len - processed); memcpy(it->buffer + it->buffer_ofs, src, slice); @@ -208,8 +205,7 @@ static int erofs_listxattr_foreach(struct erofs_xattr_iter *it) int err; /* 1. handle xattr entry */ - entry = *(struct erofs_xattr_entry *) - (it->kaddr + erofs_blkoff(it->sb, it->pos)); + entry = *(struct erofs_xattr_entry *)it->kaddr; it->pos += sizeof(struct erofs_xattr_entry); base_index = entry.e_name_index; @@ -259,8 +255,7 @@ static int erofs_getxattr_foreach(struct erofs_xattr_iter *it) unsigned int slice, processed, value_sz; /* 1. handle xattr entry */ - entry = *(struct erofs_xattr_entry *) - (it->kaddr + erofs_blkoff(sb, it->pos)); + entry = *(struct erofs_xattr_entry *)it->kaddr; it->pos += sizeof(struct erofs_xattr_entry); value_sz = le16_to_cpu(entry.e_value_size); @@ -291,8 +286,7 @@ static int erofs_getxattr_foreach(struct erofs_xattr_iter *it) /* 2. handle xattr name */ for (processed = 0; processed < entry.e_name_len; processed += slice) { - it->kaddr = erofs_bread(&it->buf, erofs_blknr(sb, it->pos), - EROFS_KMAP); + it->kaddr = erofs_bread(&it->buf, it->pos, EROFS_KMAP); if (IS_ERR(it->kaddr)) return PTR_ERR(it->kaddr); @@ -300,7 +294,7 @@ static int erofs_getxattr_foreach(struct erofs_xattr_iter *it) sb->s_blocksize - erofs_blkoff(sb, it->pos), entry.e_name_len - processed); if (memcmp(it->name.name + it->infix_len + processed, - it->kaddr + erofs_blkoff(sb, it->pos), slice)) + it->kaddr, slice)) return -ENOATTR; it->pos += slice; } @@ -336,13 +330,11 @@ static int erofs_xattr_iter_inline(struct erofs_xattr_iter *it, it->pos = erofs_iloc(inode) + vi->inode_isize + xattr_header_sz; while (remaining) { - it->kaddr = erofs_bread(&it->buf, erofs_blknr(it->sb, it->pos), - EROFS_KMAP); + it->kaddr = erofs_bread(&it->buf, it->pos, EROFS_KMAP); if (IS_ERR(it->kaddr)) return PTR_ERR(it->kaddr); - entry_sz = erofs_xattr_entry_size(it->kaddr + - erofs_blkoff(it->sb, it->pos)); + entry_sz = erofs_xattr_entry_size(it->kaddr); /* xattr on-disk corruption: xattr entry beyond xattr_isize */ if (remaining < entry_sz) { DBG_BUGON(1); @@ -375,8 +367,7 @@ static int erofs_xattr_iter_shared(struct erofs_xattr_iter *it, for (i = 0; i < vi->xattr_shared_count; ++i) { it->pos = erofs_pos(sb, sbi->xattr_blkaddr) + vi->xattr_shared_xattrs[i] * sizeof(__le32); - it->kaddr = erofs_bread(&it->buf, erofs_blknr(sb, it->pos), - EROFS_KMAP); + it->kaddr = erofs_bread(&it->buf, it->pos, EROFS_KMAP); if (IS_ERR(it->kaddr)) return PTR_ERR(it->kaddr); @@ -492,7 +483,7 @@ int erofs_xattr_prefixes_init(struct super_block *sb) return -ENOMEM; if (sbi->packed_inode) - buf.inode = sbi->packed_inode; + buf.mapping = sbi->packed_inode->i_mapping; else erofs_init_metabuf(&buf, sb); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 3216b920d369..283c9c3a611d 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -936,16 +936,16 @@ static int z_erofs_read_fragment(struct super_block *sb, struct page *page, if (!packed_inode) return -EFSCORRUPTED; - buf.inode = packed_inode; + buf.mapping = packed_inode->i_mapping; for (; cur < end; cur += cnt, pos += cnt) { cnt = min_t(unsigned int, end - cur, sb->s_blocksize - erofs_blkoff(sb, pos)); - src = erofs_bread(&buf, erofs_blknr(sb, pos), EROFS_KMAP); + src = erofs_bread(&buf, pos, EROFS_KMAP); if (IS_ERR(src)) { erofs_put_metabuf(&buf); return PTR_ERR(src); } - memcpy_to_page(page, cur, src + erofs_blkoff(sb, pos), cnt); + memcpy_to_page(page, cur, src, cnt); } erofs_put_metabuf(&buf); return 0; diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 3985f8c33f95..ff4514e4626b 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -192,7 +192,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) (PAGE_SHIFT - inode->i_blkbits); if (!ra_has_index(&file->f_ra, index)) page_cache_sync_readahead( - sb->s_bdev->bd_inode->i_mapping, + sb->s_bdev->bd_mapping, &file->f_ra, file, index, 1); file->f_ra.prev_pos = (loff_t)index << PAGE_SHIFT; diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 5d8055161acd..da4a82456383 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -206,7 +206,7 @@ static void ext4_journal_abort_handle(const char *caller, unsigned int line, static void ext4_check_bdev_write_error(struct super_block *sb) { - struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; + struct address_space *mapping = sb->s_bdev->bd_mapping; struct ext4_sb_info *sbi = EXT4_SB(sb); int err; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 893ab80dafba..c682fb927b64 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -244,7 +244,7 @@ static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb, struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block, blk_opf_t op_flags) { - gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_inode->i_mapping, + gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping, ~__GFP_FS) | __GFP_MOVABLE; return __ext4_sb_bread_gfp(sb, block, op_flags, gfp); @@ -253,7 +253,7 @@ struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block, struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb, sector_t block) { - gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_inode->i_mapping, + gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping, ~__GFP_FS); return __ext4_sb_bread_gfp(sb, block, 0, gfp); @@ -492,22 +492,6 @@ static void ext4_maybe_update_superblock(struct super_block *sb) schedule_work(&EXT4_SB(sb)->s_sb_upd_work); } -/* - * The del_gendisk() function uninitializes the disk-specific data - * structures, including the bdi structure, without telling anyone - * else. Once this happens, any attempt to call mark_buffer_dirty() - * (for example, by ext4_commit_super), will cause a kernel OOPS. - * This is a kludge to prevent these oops until we can put in a proper - * hook in del_gendisk() to inform the VFS and file system layers. - */ -static int block_device_ejected(struct super_block *sb) -{ - struct inode *bd_inode = sb->s_bdev->bd_inode; - struct backing_dev_info *bdi = inode_to_bdi(bd_inode); - - return bdi->dev == NULL; -} - static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) { struct super_block *sb = journal->j_private; @@ -5563,7 +5547,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) * used to detect the metadata async write error. */ spin_lock_init(&sbi->s_bdev_wb_lock); - errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err, + errseq_check_and_advance(&sb->s_bdev->bd_mapping->wb_err, &sbi->s_bdev_wb_err); EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS; ext4_orphan_cleanup(sb, es); @@ -5866,7 +5850,7 @@ static struct file *ext4_get_journal_blkdev(struct super_block *sb, sb_block = EXT4_MIN_BLOCK_SIZE / blocksize; offset = EXT4_MIN_BLOCK_SIZE % blocksize; - set_blocksize(bdev, blocksize); + set_blocksize(bdev_file, blocksize); bh = __bread(bdev, sb_block, blocksize); if (!bh) { ext4_msg(sb, KERN_ERR, "couldn't read superblock of " @@ -6164,8 +6148,6 @@ static int ext4_commit_super(struct super_block *sb) if (!sbh) return -EINVAL; - if (block_device_ejected(sb)) - return -ENODEV; ext4_update_super(sb); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 9f11fc1e79eb..4ea6c8bfb4e6 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1267,7 +1267,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, mapping = gfs2_glock2aspace(gl); if (mapping) { mapping->a_ops = &gfs2_meta_aops; - mapping->host = s->s_bdev->bd_inode; + mapping->host = s->s_bdev->bd_mapping->host; mapping->flags = 0; mapping_set_gfp_mask(mapping, GFP_NOFS); mapping->i_private_data = NULL; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 227edbaddfbc..05975ec76d35 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -114,7 +114,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) address_space_init_once(mapping); mapping->a_ops = &gfs2_rgrp_aops; - mapping->host = sb->s_bdev->bd_inode; + mapping->host = sb->s_bdev->bd_mapping->host; mapping->flags = 0; mapping_set_gfp_mask(mapping, GFP_NOFS); mapping->i_private_data = NULL; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index b6c114c11b97..03c4b9214f56 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -2009,7 +2009,7 @@ static int __jbd2_journal_erase(journal_t *journal, unsigned int flags) byte_count = (block_stop - block_start + 1) * journal->j_blocksize; - truncate_inode_pages_range(journal->j_dev->bd_inode->i_mapping, + truncate_inode_pages_range(journal->j_dev->bd_mapping, byte_start, byte_stop); if (flags & JBD2_JOURNAL_FLUSH_DISCARD) { diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 8654ab8ad534..6be7dd423fbd 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2784,7 +2784,7 @@ int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root) if (!nilfs->ns_writer) return -ENOMEM; - inode_attach_wb(nilfs->ns_bdev->bd_inode, NULL); + inode_attach_wb(nilfs->ns_bdev->bd_mapping->host, NULL); err = nilfs_segctor_start_thread(nilfs->ns_writer); if (unlikely(err)) diff --git a/fs/pidfs.c b/fs/pidfs.c index a63d5d24aa02..dbb9d854d1c5 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -169,6 +169,24 @@ static int pidfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, return -EOPNOTSUPP; } + +/* + * User space expects pidfs inodes to have no file type in st_mode. + * + * In particular, 'lsof' has this legacy logic: + * + * type = s->st_mode & S_IFMT; + * switch (type) { + * ... + * case 0: + * if (!strcmp(p, "anon_inode")) + * Lf->ntype = Ntype = N_ANON_INODE; + * + * to detect our old anon_inode logic. + * + * Rather than mess with our internal sane inode data, just fix it + * up here in getattr() by masking off the format bits. + */ static int pidfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) @@ -176,6 +194,7 @@ static int pidfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct inode *inode = d_inode(path->dentry); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); + stat->mode &= ~S_IFMT; return 0; } @@ -199,12 +218,13 @@ static const struct super_operations pidfs_sops = { .statfs = simple_statfs, }; +/* + * 'lsof' has knowledge of out historical anon_inode use, and expects + * the pidfs dentry name to start with 'anon_inode'. + */ static char *pidfs_dname(struct dentry *dentry, char *buffer, int buflen) { - struct inode *inode = d_inode(dentry); - struct pid *pid = inode->i_private; - - return dynamic_dname(buffer, buflen, "pidfd:[%llu]", pid->ino); + return dynamic_dname(buffer, buflen, "anon_inode:[pidfd]"); } static const struct dentry_operations pidfs_dentry_operations = { diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index e539ccd39e1e..e477ee0ff35d 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -2626,8 +2626,7 @@ static int journal_init_dev(struct super_block *super, MAJOR(jdev), MINOR(jdev), result); return result; } else if (jdev != super->s_dev) - set_blocksize(file_bdev(journal->j_bdev_file), - super->s_blocksize); + set_blocksize(journal->j_bdev_file, super->s_blocksize); return 0; } @@ -2643,7 +2642,7 @@ static int journal_init_dev(struct super_block *super, return result; } - set_blocksize(file_bdev(journal->j_bdev_file), super->s_blocksize); + set_blocksize(journal->j_bdev_file, super->s_blocksize); reiserfs_info(super, "journal_init_dev: journal device: %pg\n", file_bdev(journal->j_bdev_file)); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 8a0151e23f3d..aa4dbda7b536 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -2046,7 +2046,7 @@ xfs_setsize_buftarg( btp->bt_meta_sectorsize = sectorsize; btp->bt_meta_sectormask = sectorsize - 1; - if (set_blocksize(btp->bt_bdev, sectorsize)) { + if (set_blocksize(btp->bt_bdev_file, sectorsize)) { xfs_warn(btp->bt_mount, "Cannot set_blocksize to %u on device %pg", sectorsize, btp->bt_bdev); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 25dbf1097085..d88c0a009483 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -50,7 +50,7 @@ struct block_device { bool bd_write_holder; bool bd_has_submit_bio; dev_t bd_dev; - struct inode *bd_inode; /* will die */ + struct address_space *bd_mapping; /* page cache */ atomic_t bd_openers; spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index fd5951dd6b7d..c78f500c27b0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -212,11 +212,6 @@ struct gendisk { struct blk_independent_access_ranges *ia_ranges; }; -static inline bool disk_live(struct gendisk *disk) -{ - return !inode_unhashed(disk->part0->bd_inode); -} - /** * disk_openers - returns how many openers are there for a disk * @disk: disk to check @@ -1371,11 +1366,6 @@ static inline unsigned int blksize_bits(unsigned int size) return order_base_2(size >> SECTOR_SHIFT) + SECTOR_SHIFT; } -static inline unsigned int block_size(struct block_device *bdev) -{ - return 1 << bdev->bd_inode->i_blkbits; -} - int kblockd_schedule_work(struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); @@ -1481,7 +1471,7 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) } int bdev_read_only(struct block_device *bdev); -int set_blocksize(struct block_device *bdev, int size); +int set_blocksize(struct file *file, int size); int lookup_bdev(const char *pathname, dev_t *dev); @@ -1543,6 +1533,8 @@ void blkdev_put_no_open(struct block_device *bdev); struct block_device *I_BDEV(struct inode *inode); struct block_device *file_bdev(struct file *bdev_file); +bool disk_live(struct gendisk *disk); +unsigned int block_size(struct block_device *bdev); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index a1c0bdd0cca6..e022e40b099e 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -364,7 +364,7 @@ static inline struct buffer_head *getblk_unmovable(struct block_device *bdev, { gfp_t gfp; - gfp = mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS); + gfp = mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS); gfp |= __GFP_NOFAIL; return bdev_getblk(bdev, block, size, gfp); @@ -375,7 +375,7 @@ static inline struct buffer_head *__getblk(struct block_device *bdev, { gfp_t gfp; - gfp = mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS); + gfp = mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS); gfp |= __GFP_MOVABLE | __GFP_NOFAIL; return bdev_getblk(bdev, block, size, gfp); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d8787a3c6a9e..ab04c1c27fae 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1694,7 +1694,7 @@ static inline void jbd2_journal_abort_handle(handle_t *handle) static inline void jbd2_init_fs_dev_write_error(journal_t *journal) { - struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping; + struct address_space *mapping = journal->j_fs_dev->bd_mapping; /* * Save the original wb_err value of client fs's bdev mapping which @@ -1705,7 +1705,7 @@ static inline void jbd2_init_fs_dev_write_error(journal_t *journal) static inline int jbd2_check_fs_dev_write_error(journal_t *journal) { - struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping; + struct address_space *mapping = journal->j_fs_dev->bd_mapping; return errseq_check(&mapping->wb_err, READ_ONCE(journal->j_fs_dev_wb_err)); diff --git a/include/linux/swap.h b/include/linux/swap.h index 6b672a67ae5d..bd450023b9a4 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -310,10 +310,8 @@ struct swap_info_struct { unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ - struct file *bdev_file; /* open handle of the bdev */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ - unsigned int old_block_size; /* seldom referenced */ struct completion comp; /* seldom referenced */ spinlock_t lock; /* * protect map scan related fields like diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 5bc04bfe2db1..d9abb7ab031d 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -368,11 +368,7 @@ static int swsusp_swap_check(void) if (IS_ERR(hib_resume_bdev_file)) return PTR_ERR(hib_resume_bdev_file); - res = set_blocksize(file_bdev(hib_resume_bdev_file), PAGE_SIZE); - if (res < 0) - fput(hib_resume_bdev_file); - - return res; + return 0; } /** @@ -1574,7 +1570,6 @@ int swsusp_check(bool exclusive) hib_resume_bdev_file = bdev_file_open_by_dev(swsusp_resume_device, BLK_OPEN_READ, holder, NULL); if (!IS_ERR(hib_resume_bdev_file)) { - set_blocksize(file_bdev(hib_resume_bdev_file), PAGE_SIZE); clear_page(swsusp_header); error = hib_submit_io(REQ_OP_READ, swsusp_resume_block, swsusp_header, NULL); diff --git a/mm/swapfile.c b/mm/swapfile.c index f6ca215fb92f..b3e5e384e330 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2469,7 +2469,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) struct inode *inode; struct filename *pathname; int err, found = 0; - unsigned int old_block_size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -2582,7 +2581,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) } swap_file = p->swap_file; - old_block_size = p->old_block_size; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; @@ -2605,11 +2603,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) exit_swap_address_space(p->type); inode = mapping->host; - if (p->bdev_file) { - set_blocksize(p->bdev, old_block_size); - fput(p->bdev_file); - p->bdev_file = NULL; - } inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; @@ -2835,21 +2828,8 @@ static struct swap_info_struct *alloc_swap_info(void) static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) { - int error; - if (S_ISBLK(inode->i_mode)) { - p->bdev_file = bdev_file_open_by_dev(inode->i_rdev, - BLK_OPEN_READ | BLK_OPEN_WRITE, p, NULL); - if (IS_ERR(p->bdev_file)) { - error = PTR_ERR(p->bdev_file); - p->bdev_file = NULL; - return error; - } - p->bdev = file_bdev(p->bdev_file); - p->old_block_size = block_size(p->bdev); - error = set_blocksize(p->bdev, PAGE_SIZE); - if (error < 0) - return error; + p->bdev = I_BDEV(inode); /* * Zoned block devices contain zones that have a sequential * write only restriction. Hence zoned block devices are not @@ -3090,7 +3070,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) name = NULL; goto bad_swap; } - swap_file = file_open_name(name, O_RDWR|O_LARGEFILE, 0); + swap_file = file_open_name(name, O_RDWR | O_LARGEFILE | O_EXCL, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; @@ -3289,11 +3269,6 @@ bad_swap: p->percpu_cluster = NULL; free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; - if (p->bdev_file) { - set_blocksize(p->bdev, p->old_block_size); - fput(p->bdev_file); - p->bdev_file = NULL; - } inode = NULL; destroy_swap_extents(p); swap_cgroup_swapoff(p->type); |