fs: support freeze/thaw/mark_dead/sync with shared devices

fs/btrfs/dev-replace.c

@@ -247,8 +247,8 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 		return -EINVAL;
 	}
 
-	bdev_file = bdev_file_open_by_path(device_path, BLK_OPEN_WRITE,
-					   fs_info->sb, &fs_holder_ops);
+	bdev_file = fs_bdev_file_open_by_path(device_path, BLK_OPEN_WRITE,
+					      fs_info->sb, fs_info->sb);
 	if (IS_ERR(bdev_file)) {
 		btrfs_err(fs_info, "target device %s is invalid!", device_path);
 		return PTR_ERR(bdev_file);
@@ -325,7 +325,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	return 0;
 
 error:
-	bdev_fput(bdev_file);
+	fs_bdev_file_release(bdev_file, fs_info->sb);
 	return ret;
 }
 

fs/btrfs/ioctl.c

@@ -2579,7 +2579,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 err_drop:
 	mnt_drop_write_file(file);
 	if (bdev_file)
-		bdev_fput(bdev_file);
+		fs_bdev_file_release(bdev_file, fs_info->sb);
 out:
 	btrfs_put_dev_args_from_path(&args);
 	kfree(vol_args);
@@ -2630,7 +2630,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 
 	mnt_drop_write_file(file);
 	if (bdev_file)
-		bdev_fput(bdev_file);
+		fs_bdev_file_release(bdev_file, fs_info->sb);
 out:
 	btrfs_put_dev_args_from_path(&args);
 out_free:

fs/btrfs/volumes.c

@@ -480,7 +480,12 @@ btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder,
 	struct block_device *bdev;
 	int ret;
 
-	*bdev_file = bdev_file_open_by_path(device_path, flags, holder, &fs_holder_ops);
+	if (holder)
+		*bdev_file = fs_bdev_file_open_by_path(device_path, flags,
+						       holder, holder);
+	else
+		*bdev_file = bdev_file_open_by_path(device_path, flags, NULL,
+						    NULL);
 
 	if (IS_ERR(*bdev_file)) {
 		ret = PTR_ERR(*bdev_file);
@@ -495,15 +500,18 @@ btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder,
 	if (holder) {
 		ret = set_blocksize(*bdev_file, BTRFS_BDEV_BLOCKSIZE);
 		if (ret) {
-			bdev_fput(*bdev_file);
+			fs_bdev_file_release(*bdev_file, holder);
 			goto error;
 		}
 	}
 	invalidate_bdev(bdev);
 	*disk_super = btrfs_read_disk_super(bdev, 0, false);
 	if (IS_ERR(*disk_super)) {
 		ret = PTR_ERR(*disk_super);
-		bdev_fput(*bdev_file);
+		if (holder)
+			fs_bdev_file_release(*bdev_file, holder);
+		else
+			bdev_fput(*bdev_file);
 		goto error;
 	}
 
@@ -727,7 +735,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 
 error_free_page:
 	btrfs_release_disk_super(disk_super);
-	bdev_fput(bdev_file);
+	fs_bdev_file_release(bdev_file, holder);
 
 	return -EINVAL;
 }
@@ -1082,7 +1090,7 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices,
 			continue;
 
 		if (device->bdev_file) {
-			bdev_fput(device->bdev_file);
+			fs_bdev_file_release(device->bdev_file, fs_devices->fs_info->sb);
 			device->bdev = NULL;
 			device->bdev_file = NULL;
 			fs_devices->open_devices--;
@@ -1129,7 +1137,7 @@ static void btrfs_close_bdev(struct btrfs_device *device)
 		invalidate_bdev(device->bdev);
 	}
 
-	bdev_fput(device->bdev_file);
+	fs_bdev_file_release(device->bdev_file, device->fs_info->sb);
 }
 
 static void btrfs_close_one_device(struct btrfs_device *device)
@@ -2820,8 +2828,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	if (sb_rdonly(sb) && !fs_devices->seeding)
 		return -EROFS;
 
-	bdev_file = bdev_file_open_by_path(device_path, BLK_OPEN_WRITE,
-					   fs_info->sb, &fs_holder_ops);
+	bdev_file = fs_bdev_file_open_by_path(device_path, BLK_OPEN_WRITE,
+					      fs_info->sb, fs_info->sb);
 	if (IS_ERR(bdev_file))
 		return PTR_ERR(bdev_file);
 
@@ -3045,7 +3053,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 error_free_device:
 	btrfs_free_device(device);
 error:
-	bdev_fput(bdev_file);
+	fs_bdev_file_release(bdev_file, fs_info->sb);
 	if (locked) {
 		mutex_unlock(&uuid_mutex);
 		up_write(&sb->s_umount);

fs/erofs/data.c

@@ -69,6 +69,9 @@ int erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb,
 {
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
 
+	if (erofs_is_shutdown(sb))
+		return -EIO;
+
 	buf->file = NULL;
 	if (in_metabox) {
 		if (unlikely(!sbi->metabox_inode))
@@ -236,6 +239,9 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 		}
 		up_read(&devs->rwsem);
 	}
+	if (erofs_is_shutdown(sb) ||
+	    (map->m_dif && READ_ONCE(map->m_dif->dead)))
+		return -EIO;
 	return 0;
 }
 

fs/erofs/internal.h

@@ -48,6 +48,7 @@ struct erofs_device_info {
 
 	erofs_blk_t blocks;
 	erofs_blk_t uniaddr;
+	bool dead;		/* backing device gone; fence I/O */
 };
 
 enum {
@@ -104,6 +105,7 @@ struct erofs_xattr_prefix_item {
 struct erofs_sb_info {
 	struct erofs_device_info dif0;
 	struct erofs_mount_opts opt;	/* options */
+	unsigned long flags;		/* see EROFS_SB_* */
 #ifdef CONFIG_EROFS_FS_ZIP
 	/* list for all registered superblocks, mainly for shrinker */
 	struct list_head list;
@@ -195,6 +197,14 @@ static inline bool erofs_is_fscache_mode(struct super_block *sb)
 			!erofs_is_fileio_mode(EROFS_SB(sb)) && !sb->s_bdev;
 }
 
+/* erofs_sb_info->flags */
+#define EROFS_SB_SHUTDOWN	0	/* primary device gone; fail all I/O */
+
+static inline bool erofs_is_shutdown(struct super_block *sb)
+{
+	return test_bit(EROFS_SB_SHUTDOWN, &EROFS_SB(sb)->flags);
+}
+
 enum {
 	EROFS_ZIP_CACHE_DISABLED,
 	EROFS_ZIP_CACHE_READAHEAD,

fs/erofs/super.c

@@ -153,8 +153,8 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 	} else if (!sbi->devs->flatdev) {
 		file = erofs_is_fileio_mode(sbi) ?
 				filp_open(dif->path, O_RDONLY | O_LARGEFILE, 0) :
-				bdev_file_open_by_path(dif->path,
-						BLK_OPEN_READ, sb->s_type, NULL);
+				fs_bdev_file_open_by_path(dif->path,
+						BLK_OPEN_READ, sb->s_type, sb);
 		if (IS_ERR(file)) {
 			if (file == ERR_PTR(-ENOTBLK))
 				return -EINVAL;
@@ -843,30 +843,36 @@ static int erofs_fc_reconfigure(struct fs_context *fc)
 
 static int erofs_release_device_info(int id, void *ptr, void *data)
 {
+	struct super_block *sb = data;
 	struct erofs_device_info *dif = ptr;
 
 	fs_put_dax(dif->dax_dev, NULL);
-	if (dif->file)
-		fput(dif->file);
+	if (dif->file) {
+		if (S_ISBLK(file_inode(dif->file)->i_mode))
+			fs_bdev_file_release(dif->file, sb);
+		else
+			fput(dif->file);
+	}
 	erofs_fscache_unregister_cookie(dif->fscache);
 	dif->fscache = NULL;
 	kfree(dif->path);
 	kfree(dif);
 	return 0;
 }
 
-static void erofs_free_dev_context(struct erofs_dev_context *devs)
+static void erofs_free_dev_context(struct erofs_dev_context *devs,
+				   struct super_block *sb)
 {
 	if (!devs)
 		return;
-	idr_for_each(&devs->tree, &erofs_release_device_info, NULL);
+	idr_for_each(&devs->tree, &erofs_release_device_info, sb);
 	idr_destroy(&devs->tree);
 	kfree(devs);
 }
 
-static void erofs_sb_free(struct erofs_sb_info *sbi)
+static void erofs_sb_free(struct erofs_sb_info *sbi, struct super_block *sb)
 {
-	erofs_free_dev_context(sbi->devs);
+	erofs_free_dev_context(sbi->devs, sb);
 	kfree(sbi->fsid);
 	kfree_sensitive(sbi->domain_id);
 	if (sbi->dif0.file)
@@ -879,8 +885,13 @@ static void erofs_fc_free(struct fs_context *fc)
 {
 	struct erofs_sb_info *sbi = fc->s_fs_info;
 
-	if (sbi) /* free here if an error occurs before transferring to sb */
-		erofs_sb_free(sbi);
+	/*
+	 * Freed here only if an error occurs before the sb is set up; at that
+	 * point no block-backed device has been claimed (that happens in
+	 * fill_super), so the NULL sb never reaches fs_bdev_file_release().
+	 */
+	if (sbi)
+		erofs_sb_free(sbi, NULL);
 }
 
 static const struct fs_context_operations erofs_context_ops = {
@@ -936,7 +947,7 @@ static void erofs_kill_sb(struct super_block *sb)
 	erofs_drop_internal_inodes(sbi);
 	fs_put_dax(sbi->dif0.dax_dev, NULL);
 	erofs_fscache_unregister_fs(sb);
-	erofs_sb_free(sbi);
+	erofs_sb_free(sbi, sb);
 	sb->s_fs_info = NULL;
 }
 
@@ -948,7 +959,7 @@ static void erofs_put_super(struct super_block *sb)
 	erofs_shrinker_unregister(sb);
 	erofs_xattr_prefixes_cleanup(sb);
 	erofs_drop_internal_inodes(sbi);
-	erofs_free_dev_context(sbi->devs);
+	erofs_free_dev_context(sbi->devs, sb);
 	sbi->devs = NULL;
 	erofs_fscache_unregister_fs(sb);
 }
@@ -1121,13 +1132,44 @@ static void erofs_evict_inode(struct inode *inode)
 	clear_inode(inode);
 }
 
+/*
+ * A blob device may back several erofs superblocks; fence only the affected
+ * one and keep the rest of the mount alive.  The primary device falls back to
+ * the generic teardown (return non-zero).
+ */
+static int erofs_remove_bdev(struct super_block *sb, struct block_device *bdev)
+{
+	struct erofs_dev_context *devs = EROFS_SB(sb)->devs;
+	struct erofs_device_info *dif;
+	int id;
+
+	if (bdev == sb->s_bdev)
+		return 1;
+
+	down_read(&devs->rwsem);
+	idr_for_each_entry(&devs->tree, dif, id) {
+		if (dif->file && S_ISBLK(file_inode(dif->file)->i_mode) &&
+		    file_bdev(dif->file)->bd_dev == bdev->bd_dev)
+			WRITE_ONCE(dif->dead, true);
+	}
+	up_read(&devs->rwsem);
+	return 0;
+}
+
+static void erofs_shutdown(struct super_block *sb)
+{
+	set_bit(EROFS_SB_SHUTDOWN, &EROFS_SB(sb)->flags);
+}
+
 const struct super_operations erofs_sops = {
 	.put_super = erofs_put_super,
 	.alloc_inode = erofs_alloc_inode,
 	.free_inode = erofs_free_inode,
 	.evict_inode = erofs_evict_inode,
 	.statfs = erofs_statfs,
 	.show_options = erofs_show_options,
+	.remove_bdev = erofs_remove_bdev,
+	.shutdown = erofs_shutdown,
 };
 
 module_init(erofs_module_init);

fs/erofs/zdata.c

@@ -1698,11 +1698,15 @@ static void z_erofs_submit_queue(struct z_erofs_frontend *f,
 			continue;
 		}
 
-		/* no device id here, thus it will always succeed */
 		mdev = (struct erofs_map_dev) {
 			.m_pa = round_down(pcl->pos, sb->s_blocksize),
 		};
-		(void)erofs_map_dev(sb, &mdev);
+		if (erofs_map_dev(sb, &mdev)) {
+			/* the backing device is gone; fail the batch */
+			q[JQ_SUBMIT]->eio = true;
+			qtail[JQ_SUBMIT] = &pcl->next;
+			continue;
+		}
 
 		cur = mdev.m_pa;
 		end = round_up(cur + pcl->pageofs_in + pcl->pclustersize,
@@ -1786,7 +1790,7 @@ static void z_erofs_submit_queue(struct z_erofs_frontend *f,
 	 * although background is preferred, no one is pending for submission.
 	 * don't issue decompression but drop it directly instead.
 	 */
-	if (!*force_fg && !nr_bios) {
+	if (!*force_fg && !nr_bios && !q[JQ_SUBMIT]->eio) {
 		kvfree(q[JQ_SUBMIT]);
 		return;
 	}

fs/ext4/super.c

@@ -5793,7 +5793,7 @@ failed_mount8: __maybe_unused
 	brelse(sbi->s_sbh);
 	if (sbi->s_journal_bdev_file) {
 		invalidate_bdev(file_bdev(sbi->s_journal_bdev_file));
-		bdev_fput(sbi->s_journal_bdev_file);
+		fs_bdev_file_release(sbi->s_journal_bdev_file, sb);
 	}
 out_fail:
 	invalidate_bdev(sb->s_bdev);
@@ -5972,9 +5972,9 @@ static struct file *ext4_get_journal_blkdev(struct super_block *sb,
 	struct ext4_super_block *es;
 	int errno;
 
-	bdev_file = bdev_file_open_by_dev(j_dev,
+	bdev_file = fs_bdev_file_open_by_dev(j_dev,
 		BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES,
-		sb, &fs_holder_ops);
+		sb, sb);
 	if (IS_ERR(bdev_file)) {
 		ext4_msg(sb, KERN_ERR,
 			 "failed to open journal device unknown-block(%u,%u) %ld",
@@ -6034,7 +6034,7 @@ static struct file *ext4_get_journal_blkdev(struct super_block *sb,
 out_bh:
 	brelse(bh);
 out_bdev:
-	bdev_fput(bdev_file);
+	fs_bdev_file_release(bdev_file, sb);
 	return ERR_PTR(errno);
 }
 
@@ -6073,7 +6073,7 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb,
 out_journal:
 	ext4_journal_destroy(EXT4_SB(sb), journal);
 out_bdev:
-	bdev_fput(bdev_file);
+	fs_bdev_file_release(bdev_file, sb);
 	return ERR_PTR(errno);
 }
 
@@ -7492,7 +7492,7 @@ static void ext4_kill_sb(struct super_block *sb)
 	kill_block_super(sb);
 
 	if (bdev_file)
-		bdev_fput(bdev_file);
+		fs_bdev_file_release(bdev_file, sb);
 }
 
 static struct file_system_type ext4_fs_type = {