Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
"In addition to bug fixes and cleanups, there are two new features for
ext4 in 5.14:

- Allow applications to poll on changes to
/sys/fs/ext4/*/errors_count

- Add the ioctl EXT4_IOC_CHECKPOINT which allows the journal to be
checkpointed, truncated and discarded or zero'ed"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (32 commits)
jbd2: export jbd2_journal_[un]register_shrinker()
ext4: notify sysfs on errors_count value change
fs: remove bdev_try_to_free_page callback
ext4: remove bdev_try_to_free_page() callback
jbd2: simplify journal_clean_one_cp_list()
jbd2,ext4: add a shrinker to release checkpointed buffers
jbd2: remove redundant buffer io error checks
jbd2: don't abort the journal when freeing buffers
jbd2: ensure abort the journal if detect IO error when writing original buffer back
jbd2: remove the out label in __jbd2_journal_remove_checkpoint()
ext4: no need to verify new add extent block
jbd2: clean up misleading comments for jbd2_fc_release_bufs
ext4: add check to prevent attempting to resize an fs with sparse_super2
ext4: consolidate checks for resize of bigalloc into ext4_resize_begin
ext4: remove duplicate definition of ext4_xattr_ibody_inline_set()
ext4: fsmap: fix the block/inode bitmap comment
ext4: fix comment for s_hash_unsigned
ext4: use local variable ei instead of EXT4_I() macro
ext4: fix avefreec in find_group_orlov
ext4: correct the cache_nr in tracepoint ext4_es_shrink_exit
...

Documentation/filesystems/ext4/journal.rst

···
 --------------
 
 Introduced in ext3, the ext4 filesystem employs a journal to protect the
-filesystem against corruption in the case of a system crash. A small
-continuous region of disk (default 128MiB) is reserved inside the
-filesystem as a place to land “important” data writes on-disk as quickly
-as possible. Once the important data transaction is fully written to the
-disk and flushed from the disk write cache, a record of the data being
-committed is also written to the journal. At some later point in time,
-the journal code writes the transactions to their final locations on
-disk (this could involve a lot of seeking or a lot of small
+filesystem against metadata inconsistencies in the case of a system crash. Up
+to 10,240,000 file system blocks (see man mke2fs(8) for more details on journal
+size limits) can be reserved inside the filesystem as a place to land
+“important” data writes on-disk as quickly as possible. Once the important
+data transaction is fully written to the disk and flushed from the disk write
+cache, a record of the data being committed is also written to the journal. At
+some later point in time, the journal code writes the transactions to their
+final locations on disk (this could involve a lot of seeking or a lot of small
 read-write-erases) before erasing the commit record. Should the system
 crash during the second slow write, the journal can be replayed all the
 way to the latest commit record, guaranteeing the atomicity of whatever
···
 replay of last inode 11 tag. Thus, by converting a non-idempotent procedure
 into a series of idempotent outcomes, fast commits ensured idempotence during
 the replay.
+
+Journal Checkpoint
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Checkpointing the journal ensures all transactions and their associated buffers
+are submitted to the disk. In-progress transactions are waited upon and included
+in the checkpoint. Checkpointing is used internally during critical updates to
+the filesystem including journal recovery, filesystem resizing, and freeing of
+the journal_t structure.
+
+A journal checkpoint can be triggered from userspace via the ioctl
+EXT4_IOC_CHECKPOINT. This ioctl takes a single, u64 argument for flags.
+Currently, three flags are supported. First, EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN
+can be used to verify input to the ioctl. It returns error if there is any
+invalid input, otherwise it returns success without performing
+any checkpointing. This can be used to check whether the ioctl exists on a
+system and to verify there are no issues with arguments or flags. The
+other two flags are EXT4_IOC_CHECKPOINT_FLAG_DISCARD and
+EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT. These flags cause the journal blocks to be
+discarded or zero-filled, respectively, after the journal checkpoint is
+complete. EXT4_IOC_CHECKPOINT_FLAG_DISCARD and EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT
+cannot both be set. The ioctl may be useful when snapshotting a system or for
+complying with content deletion SLOs.

fs/block_dev.c

···
 }
 EXPORT_SYMBOL_GPL(blkdev_read_iter);
 
-/*
- * Try to release a page associated with block device when the system
- * is under memory pressure.
- */
-static int blkdev_releasepage(struct page *page, gfp_t wait)
-{
-	struct super_block *super = BDEV_I(page->mapping->host)->bdev.bd_super;
-
-	if (super && super->s_op->bdev_try_to_free_page)
-		return super->s_op->bdev_try_to_free_page(super, page, wait);
-
-	return try_to_free_buffers(page);
-}
-
 static int blkdev_writepages(struct address_space *mapping,
 			     struct writeback_control *wbc)
 {
···
 	.write_begin	= blkdev_write_begin,
 	.write_end	= blkdev_write_end,
 	.writepages	= blkdev_writepages,
-	.releasepage	= blkdev_releasepage,
 	.direct_IO	= blkdev_direct_IO,
 	.migratepage	= buffer_migrate_page_norefs,
 	.is_dirty_writeback = buffer_check_dirty_writeback,

fs/ext4/ext4.h

···
 #define EXT4_IOC_CLEAR_ES_CACHE		_IO('f', 40)
 #define EXT4_IOC_GETSTATE		_IOW('f', 41, __u32)
 #define EXT4_IOC_GET_ES_CACHE		_IOWR('f', 42, struct fiemap)
+#define EXT4_IOC_CHECKPOINT		_IOW('f', 43, __u32)
 
 #define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32)
 
···
 #define EXT4_STATE_FLAG_NEW		0x00000002
 #define EXT4_STATE_FLAG_NEWENTRY	0x00000004
 #define EXT4_STATE_FLAG_DA_ALLOC_CLOSE	0x00000008
+
+/* flags for ioctl EXT4_IOC_CHECKPOINT */
+#define EXT4_IOC_CHECKPOINT_FLAG_DISCARD	0x1
+#define EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT	0x2
+#define EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN	0x4
+#define EXT4_IOC_CHECKPOINT_FLAG_VALID		(EXT4_IOC_CHECKPOINT_FLAG_DISCARD | \
+						EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT | \
+						EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN)
 
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /*
···
 	unsigned int s_inode_goal;
 	u32 s_hash_seed[4];
 	int s_def_hash_version;
-	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
+	int s_hash_unsigned;	/* 3 if hash should be unsigned, 0 if not */
 	struct percpu_counter s_freeclusters_counter;
 	struct percpu_counter s_freeinodes_counter;
 	struct percpu_counter s_dirs_counter;
···
 	struct kobject s_kobj;
 	struct completion s_kobj_unregister;
 	struct super_block *s_sb;
+	struct buffer_head *s_mmp_bh;
 
 	/* Journaling */
 	struct journal_s *s_journal;
···
 extern const struct inode_operations ext4_fast_symlink_inode_operations;
 
 /* sysfs.c */
+extern void ext4_notify_error_sysfs(struct ext4_sb_info *sbi);
 extern int ext4_register_sysfs(struct super_block *sb);
 extern void ext4_unregister_sysfs(struct super_block *sb);
 extern int __init ext4_init_sysfs(void);
···
 /* mmp.c */
 extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
 
+/* mmp.c */
+extern void ext4_stop_mmpd(struct ext4_sb_info *sbi);
+
 /* verity.c */
 extern const struct fsverity_operations ext4_verityops;
 
···
 	 * have to read the block because we may read the old data
 	 * successfully.
 	 */
-	if (!buffer_uptodate(bh) && buffer_write_io_error(bh))
+	if (buffer_write_io_error(bh))
 		set_buffer_uptodate(bh);
 	return buffer_uptodate(bh);
 }

fs/ext4/extents.c

···
 	eh->eh_entries = 0;
 	eh->eh_magic = EXT4_EXT_MAGIC;
 	eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0));
+	eh->eh_generation = 0;
 	ext4_mark_inode_dirty(handle, inode);
 }
 
···
 	neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0));
 	neh->eh_magic = EXT4_EXT_MAGIC;
 	neh->eh_depth = 0;
+	neh->eh_generation = 0;
 
 	/* move remainder of path[depth] to the new leaf */
 	if (unlikely(path[depth].p_hdr->eh_entries !=
···
 		neh->eh_magic = EXT4_EXT_MAGIC;
 		neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0));
 		neh->eh_depth = cpu_to_le16(depth - i);
+		neh->eh_generation = 0;
 		fidx = EXT_FIRST_INDEX(neh);
 		fidx->ei_block = border;
 		ext4_idx_store_pblock(fidx, oldblock);
···
 	neh->eh_magic = EXT4_EXT_MAGIC;
 	ext4_extent_block_csum_set(inode, neh);
 	set_buffer_uptodate(bh);
+	set_buffer_verified(bh);
 	unlock_buffer(bh);
 
 	err = ext4_handle_dirty_metadata(handle, inode, bh);

fs/ext4/extents_status.c

···
 	ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt);
 	trace_ext4_es_shrink_scan_enter(sbi->s_sb, nr_to_scan, ret);
 
-	if (!nr_to_scan)
-		return ret;
-
 	nr_shrunk = __es_shrink(sbi, nr_to_scan, NULL);
 
+	ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt);
 	trace_ext4_es_shrink_scan_exit(sbi->s_sb, nr_shrunk, ret);
 	return nr_shrunk;
 }

fs/ext4/fsmap.h

···
 #define EXT4_FMR_OWN_INODES	FMR_OWNER('X', 5) /* inodes */
 #define EXT4_FMR_OWN_GDT	FMR_OWNER('f', 1) /* group descriptors */
 #define EXT4_FMR_OWN_RESV_GDT	FMR_OWNER('f', 2) /* reserved gdt blocks */
-#define EXT4_FMR_OWN_BLKBM	FMR_OWNER('f', 3) /* inode bitmap */
-#define EXT4_FMR_OWN_INOBM	FMR_OWNER('f', 4) /* block bitmap */
+#define EXT4_FMR_OWN_BLKBM	FMR_OWNER('f', 3) /* block bitmap */
+#define EXT4_FMR_OWN_INOBM	FMR_OWNER('f', 4) /* inode bitmap */
 
 #endif /* __EXT4_FSMAP_H__ */

fs/ext4/ialloc.c

···
  *
  * We always try to spread first-level directories.
  *
- * If there are blockgroups with both free inodes and free blocks counts
+ * If there are blockgroups with both free inodes and free clusters counts
  * not worse than average we return one with smallest directory count.
  * Otherwise we simply return a random group.
  *
···
  * It's OK to put directory into a group unless
  * it has too many directories already (max_dirs) or
  * it has too few free inodes left (min_inodes) or
- * it has too few free blocks left (min_blocks) or
+ * it has too few free clusters left (min_clusters) or
  * Parent's group is preferred, if it doesn't satisfy these
  * conditions we search cyclically through the rest. If none
  * of the groups look good we just look for a group with more
···
 	ext4_group_t real_ngroups = ext4_get_groups_count(sb);
 	int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
 	unsigned int freei, avefreei, grp_free;
-	ext4_fsblk_t freeb, avefreec;
+	ext4_fsblk_t freec, avefreec;
 	unsigned int ndirs;
 	int max_dirs, min_inodes;
 	ext4_grpblk_t min_clusters;
···
 
 	freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
 	avefreei = freei / ngroups;
-	freeb = EXT4_C2B(sbi,
-		percpu_counter_read_positive(&sbi->s_freeclusters_counter));
-	avefreec = freeb;
+	freec = percpu_counter_read_positive(&sbi->s_freeclusters_counter);
+	avefreec = freec;
 	do_div(avefreec, ngroups);
 	ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
 

fs/ext4/inline.c

···
 /*
  * write the buffer to the inline inode.
  * If 'create' is set, we don't need to do the extra copy in the xattr
- * value since it is already handled by ext4_xattr_ibody_inline_set.
+ * value since it is already handled by ext4_xattr_ibody_set.
  * That saves us one memcpy.
  */
 static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
···
 
 	BUG_ON(!is.s.not_found);
 
-	error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
+	error = ext4_xattr_ibody_set(handle, inode, &i, &is);
 	if (error) {
 		if (error == -ENOSPC)
 			ext4_clear_inode_state(inode,
···
 	i.value = value;
 	i.value_len = len;
 
-	error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
+	error = ext4_xattr_ibody_set(handle, inode, &i, &is);
 	if (error)
 		goto out;
 
···
 	if (error)
 		goto out;
 
-	error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
+	error = ext4_xattr_ibody_set(handle, inode, &i, &is);
 	if (error)
 		goto out;
 
···
 			i.value = value;
 			i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ?
 					i_size - EXT4_MIN_INLINE_DATA_SIZE : 0;
-			err = ext4_xattr_ibody_inline_set(handle, inode,
-							  &i, &is);
+			err = ext4_xattr_ibody_set(handle, inode, &i, &is);
 			if (err)
 				goto out_error;
 		}

fs/ext4/inode.c

···
 	ei->i_reserved_data_blocks -= used;
 	percpu_counter_sub(&sbi->s_dirtyclusters_counter, used);
 
-	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+	spin_unlock(&ei->i_block_reservation_lock);
 
 	/* Update quota subsystem for data blocks */
 	if (quota_claim)
···
 		ext4_clear_inode_state(inode, EXT4_STATE_JDATA);
 		journal = EXT4_JOURNAL(inode);
 		jbd2_journal_lock_updates(journal);
-		err = jbd2_journal_flush(journal);
+		err = jbd2_journal_flush(journal, 0);
 		jbd2_journal_unlock_updates(journal);
 
 		if (err)
···
 	 * i_disksize out to i_size. This could be beyond where direct I/O is
 	 * happening and thus expose allocated blocks to direct I/O reads.
 	 */
-	else if ((map->m_lblk * (1 << blkbits)) >= i_size_read(inode))
+	else if (((loff_t)map->m_lblk << blkbits) >= i_size_read(inode))
 		m_flags = EXT4_GET_BLOCKS_CREATE;
 	else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		m_flags = EXT4_GET_BLOCKS_IO_CREATE_EXT;
···
 	if (val)
 		ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
 	else {
-		err = jbd2_journal_flush(journal);
+		err = jbd2_journal_flush(journal, 0);
 		if (err < 0) {
 			jbd2_journal_unlock_updates(journal);
 			percpu_up_write(&sbi->s_writepages_rwsem);

fs/ext4/ioctl.c

···
 	info.gi_sb = sb;
 	info.gi_data = arg;
 	error = ext4_getfsmap(sb, &xhead, ext4_getfsmap_format, &info);
-	if (error == EXT4_QUERY_RANGE_ABORT) {
-		error = 0;
+	if (error == EXT4_QUERY_RANGE_ABORT)
 		aborted = true;
-	} else if (error)
+	else if (error)
 		return error;
 
 	/* If we didn't abort, set the "last" flag in the last fmx */
···
 	if (err)
 		return err;
 
-	if (ext4_has_feature_bigalloc(sb)) {
-		ext4_msg(sb, KERN_ERR,
-			 "Online resizing not supported with bigalloc");
-		err = -EOPNOTSUPP;
-		goto group_add_out;
-	}
-
 	err = mnt_want_write_file(file);
 	if (err)
 		goto group_add_out;
···
 	err = ext4_group_add(sb, input);
 	if (EXT4_SB(sb)->s_journal) {
 		jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
-		err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+		err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
 		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
 	}
 	if (err == 0)
···
 	return error;
 }
 
+static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg)
+{
+	int err = 0;
+	__u32 flags = 0;
+	unsigned int flush_flags = 0;
+	struct super_block *sb = file_inode(filp)->i_sb;
+	struct request_queue *q;
+
+	if (copy_from_user(&flags, (__u32 __user *)arg,
+				sizeof(__u32)))
+		return -EFAULT;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* check for invalid bits set */
+	if ((flags & ~EXT4_IOC_CHECKPOINT_FLAG_VALID) ||
+				((flags & JBD2_JOURNAL_FLUSH_DISCARD) &&
+				(flags & JBD2_JOURNAL_FLUSH_ZEROOUT)))
+		return -EINVAL;
+
+	if (!EXT4_SB(sb)->s_journal)
+		return -ENODEV;
+
+	if (flags & ~JBD2_JOURNAL_FLUSH_VALID)
+		return -EINVAL;
+
+	q = bdev_get_queue(EXT4_SB(sb)->s_journal->j_dev);
+	if (!q)
+		return -ENXIO;
+	if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !blk_queue_discard(q))
+		return -EOPNOTSUPP;
+
+	if (flags & EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN)
+		return 0;
+
+	if (flags & EXT4_IOC_CHECKPOINT_FLAG_DISCARD)
+		flush_flags |= JBD2_JOURNAL_FLUSH_DISCARD;
+
+	if (flags & EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT) {
+		flush_flags |= JBD2_JOURNAL_FLUSH_ZEROOUT;
+		pr_info_ratelimited("warning: checkpointing journal with EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT can be slow");
+	}
+
+	jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
+	err = jbd2_journal_flush(EXT4_SB(sb)->s_journal, flush_flags);
+	jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+
+	return err;
+}
+
 static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
···
 			goto group_extend_out;
 		}
 
-		if (ext4_has_feature_bigalloc(sb)) {
-			ext4_msg(sb, KERN_ERR,
-				 "Online resizing not supported with bigalloc");
-			err = -EOPNOTSUPP;
-			goto group_extend_out;
-		}
-
 		err = mnt_want_write_file(filp);
 		if (err)
 			goto group_extend_out;
···
 		err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
 		if (EXT4_SB(sb)->s_journal) {
 			jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
-			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
 			jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
 		}
 		if (err == 0)
···
 		if (EXT4_SB(sb)->s_journal) {
 			ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE);
 			jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
-			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
 			jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
 		}
 		if (err == 0)
···
 		return fsverity_ioctl_read_metadata(filp,
 						    (const void __user *)arg);
 
+	case EXT4_IOC_CHECKPOINT:
+		return ext4_ioctl_checkpoint(filp, arg);
+
 	default:
 		return -ENOTTY;
 	}
···
 	case EXT4_IOC_CLEAR_ES_CACHE:
 	case EXT4_IOC_GETSTATE:
 	case EXT4_IOC_GET_ES_CACHE:
+	case EXT4_IOC_CHECKPOINT:
 		break;
 	default:
 		return -ENOIOCTLCMD;

fs/ext4/mmp.c

···
  */
 static int kmmpd(void *data)
 {
-	struct super_block *sb = ((struct mmpd_data *) data)->sb;
-	struct buffer_head *bh = ((struct mmpd_data *) data)->bh;
+	struct super_block *sb = (struct super_block *) data;
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	struct buffer_head *bh = EXT4_SB(sb)->s_mmp_bh;
 	struct mmp_struct *mmp;
 	ext4_fsblk_t mmp_block;
 	u32 seq = 0;
···
 	retval = write_mmp_block(sb, bh);
 
 exit_thread:
-	EXT4_SB(sb)->s_mmp_tsk = NULL;
-	kfree(data);
-	brelse(bh);
 	return retval;
+}
+
+void ext4_stop_mmpd(struct ext4_sb_info *sbi)
+{
+	if (sbi->s_mmp_tsk) {
+		kthread_stop(sbi->s_mmp_tsk);
+		brelse(sbi->s_mmp_bh);
+		sbi->s_mmp_tsk = NULL;
+	}
 }
 
 /*
···
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
 	struct buffer_head *bh = NULL;
 	struct mmp_struct *mmp = NULL;
-	struct mmpd_data *mmpd_data;
 	u32 seq;
 	unsigned int mmp_check_interval = le16_to_cpu(es->s_mmp_update_interval);
 	unsigned int wait_time = 0;
···
 		goto failed;
 	}
 
-	mmpd_data = kmalloc(sizeof(*mmpd_data), GFP_KERNEL);
-	if (!mmpd_data) {
-		ext4_warning(sb, "not enough memory for mmpd_data");
-		goto failed;
-	}
-	mmpd_data->sb = sb;
-	mmpd_data->bh = bh;
+	EXT4_SB(sb)->s_mmp_bh = bh;
 
 	/*
 	 * Start a kernel thread to update the MMP block periodically.
 	 */
-	EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%.*s",
+	EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, sb, "kmmpd-%.*s",
 					     (int)sizeof(mmp->mmp_bdevname),
 					     bdevname(bh->b_bdev,
 						      mmp->mmp_bdevname));
 	if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) {
 		EXT4_SB(sb)->s_mmp_tsk = NULL;
-		kfree(mmpd_data);
 		ext4_warning(sb, "Unable to create kmmpd thread for %s.",
 			     sb->s_id);
 		goto failed;

fs/ext4/namei.c

···
 
 			/* Which index block gets the new entry? */
 			if (at - entries >= icount1) {
-				frame->at = at = at - entries - icount1 + entries2;
+				frame->at = at - entries - icount1 + entries2;
 				frame->entries = entries = entries2;
 				swap(frame->bh, bh2);
 			}

fs/ext4/resize.c

···
 		return -EPERM;
 	}
 
+	if (ext4_has_feature_bigalloc(sb)) {
+		ext4_msg(sb, KERN_ERR, "Online resizing not supported with bigalloc");
+		return -EOPNOTSUPP;
+	}
+	if (ext4_has_feature_sparse_super2(sb)) {
+		ext4_msg(sb, KERN_ERR, "Online resizing not supported with sparse_super2");
+		return -EOPNOTSUPP;
+	}
+
 	if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING,
 				  &EXT4_SB(sb)->s_ext4_flags))
 		ret = -EBUSY;

fs/ext4/super.c

···
 			goto write_directly;
 		}
 		jbd2_journal_stop(handle);
+		ext4_notify_error_sysfs(sbi);
 		return;
 	}
 write_directly:
···
 	 * out and hope for the best.
 	 */
 	ext4_commit_super(sbi->s_sb);
+	ext4_notify_error_sysfs(sbi);
 }
 
 #define ext4_error_ratelimit(sb)					\
···
 	ext4_unregister_sysfs(sb);
 
 	if (sbi->s_journal) {
+		jbd2_journal_unregister_shrinker(sbi->s_journal);
 		aborted = is_journal_aborted(sbi->s_journal);
 		err = jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
···
 	ext4_xattr_destroy_cache(sbi->s_ea_block_cache);
 	sbi->s_ea_block_cache = NULL;
 
-	if (sbi->s_mmp_tsk)
-		kthread_stop(sbi->s_mmp_tsk);
+	ext4_stop_mmpd(sbi);
+
 	brelse(sbi->s_sbh);
 	sb->s_fs_info = NULL;
 	/*
···
 
 	trace_ext4_nfs_commit_metadata(inode);
 	return ext4_write_inode(inode, &wbc);
-}
-
-/*
- * Try to release metadata pages (indirect blocks, directories) which are
- * mapped via the block device.  Since these pages could have journal heads
- * which would prevent try_to_free_buffers() from freeing them, we must use
- * jbd2 layer's try_to_free_buffers() function to release them.
- */
-static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
-				 gfp_t wait)
-{
-	journal_t *journal = EXT4_SB(sb)->s_journal;
-
-	WARN_ON(PageChecked(page));
-	if (!page_has_buffers(page))
-		return 0;
-	if (journal)
-		return jbd2_journal_try_to_free_buffers(journal, page);
-
-	return try_to_free_buffers(page);
 }
 
 #ifdef CONFIG_FS_ENCRYPTION
···
 	.quota_write	= ext4_quota_write,
 	.get_dquots	= ext4_get_dquots,
 #endif
-	.bdev_try_to_free_page = bdev_try_to_free_page,
 };
 
 static const struct export_operations ext4_export_ops = {
···
 			inode_lock(inode);
 			truncate_inode_pages(inode->i_mapping, inode->i_size);
 			ret = ext4_truncate(inode);
-			if (ret)
+			if (ret) {
+				/*
+				 * We need to clean up the in-core orphan list
+				 * manually if ext4_truncate() failed to get a
+				 * transaction handle.
+				 */
+				ext4_orphan_del(NULL, inode);
 				ext4_std_error(inode->i_sb, ret);
+			}
 			inode_unlock(inode);
 			nr_truncates++;
 		} else {
···
 			ext4_msg(sb, KERN_ERR,
 			       "unable to initialize "
 			       "flex_bg meta info!");
+			ret = -ENOMEM;
 			goto failed_mount6;
 		}
 
···
 	sbi->s_ea_block_cache = NULL;
 
 	if (sbi->s_journal) {
+		jbd2_journal_unregister_shrinker(sbi->s_journal);
 		jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
 	}
···
 failed_mount3:
 	flush_work(&sbi->s_error_work);
 	del_timer_sync(&sbi->s_err_report);
-	if (sbi->s_mmp_tsk)
-		kthread_stop(sbi->s_mmp_tsk);
+	ext4_stop_mmpd(sbi);
 failed_mount2:
 	rcu_read_lock();
 	group_desc = rcu_dereference(sbi->s_group_desc);
···
 		ext4_commit_super(sb);
 	}
 
+	err = jbd2_journal_register_shrinker(journal);
+	if (err) {
+		EXT4_SB(sb)->s_journal = NULL;
+		goto err_out;
+	}
+
 	return 0;
 
 err_out:
···
 		return 0;
 	}
 	jbd2_journal_lock_updates(journal);
-	err = jbd2_journal_flush(journal);
+	err = jbd2_journal_flush(journal, 0);
 	if (err < 0)
 		goto out;
 
···
 		 * Don't clear the needs_recovery flag if we failed to
 		 * flush the journal.
 		 */
-		error = jbd2_journal_flush(journal);
+		error = jbd2_journal_flush(journal, 0);
 		if (error < 0)
 			goto out;
 
···
 				 */
 				ext4_mark_recovery_complete(sb, es);
 			}
-			if (sbi->s_mmp_tsk)
-				kthread_stop(sbi->s_mmp_tsk);
+			ext4_stop_mmpd(sbi);
 		} else {
 			/* Make sure we can mount this feature set readwrite */
 			if (ext4_has_feature_readonly(sb) ||
···
 		 * otherwise be livelocked...
 		 */
 		jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
-		err = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+		err = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
 		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
 		if (err)
 			return err;

fs/ext4/sysfs.c

···
 	.release	= (void (*)(struct kobject *))kfree,
 };
 
+void ext4_notify_error_sysfs(struct ext4_sb_info *sbi)
+{
+	sysfs_notify(&sbi->s_kobj, NULL, "errors_count");
+}
+
 static struct kobject *ext4_root;
 
 static struct kobject *ext4_feat;

fs/ext4/xattr.c

···
 	return 0;
 }
 
-int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
-				struct ext4_xattr_info *i,
-				struct ext4_xattr_ibody_find *is)
-{
-	struct ext4_xattr_ibody_header *header;
-	struct ext4_xattr_search *s = &is->s;
-	int error;
-
-	if (EXT4_I(inode)->i_extra_isize == 0)
-		return -ENOSPC;
-	error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */);
-	if (error)
-		return error;
-	header = IHDR(inode, ext4_raw_inode(&is->iloc));
-	if (!IS_LAST_ENTRY(s->first)) {
-		header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
-		ext4_set_inode_state(inode, EXT4_STATE_XATTR);
-	} else {
-		header->h_magic = cpu_to_le32(0);
-		ext4_clear_inode_state(inode, EXT4_STATE_XATTR);
-	}
-	return 0;
-}
-
-static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
+int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
 				struct ext4_xattr_info *i,
 				struct ext4_xattr_ibody_find *is)
 {

fs/ext4/xattr.h

···
 extern int ext4_xattr_ibody_get(struct inode *inode, int name_index,
 				const char *name,
 				void *buffer, size_t buffer_size);
-extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
-				       struct ext4_xattr_info *i,
-				       struct ext4_xattr_ibody_find *is);
+extern int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
+				struct ext4_xattr_info *i,
+				struct ext4_xattr_ibody_find *is);
 
 extern struct mb_cache *ext4_xattr_create_cache(void);
 extern void ext4_xattr_destroy_cache(struct mb_cache *);

fs/jbd2/checkpoint.c

···
 }
 
 /*
- * Try to release a checkpointed buffer from its transaction.
- * Returns 1 if we released it and 2 if we also released the
- * whole transaction.
+ * Check a checkpoint buffer could be release or not.
  *
  * Requires j_list_lock
  */
-static int __try_to_free_cp_buf(struct journal_head *jh)
+static inline bool __cp_buffer_busy(struct journal_head *jh)
 {
-	int ret = 0;
 	struct buffer_head *bh = jh2bh(jh);
 
-	if (jh->b_transaction == NULL && !buffer_locked(bh) &&
-	    !buffer_dirty(bh) && !buffer_write_io_error(bh)) {
-		JBUFFER_TRACE(jh, "remove from checkpoint list");
-		ret = __jbd2_journal_remove_checkpoint(jh) + 1;
-	}
-	return ret;
+	return (jh->b_transaction || buffer_locked(bh) || buffer_dirty(bh));
 }
 
 /*
···
 	 * OK, we need to start writing disk blocks.  Take one transaction
 	 * and write it.
 	 */
-	result = 0;
 	spin_lock(&journal->j_list_lock);
 	if (!journal->j_checkpoint_transactions)
 		goto out;
···
 			goto restart;
 		}
 		if (!buffer_dirty(bh)) {
-			if (unlikely(buffer_write_io_error(bh)) && !result)
-				result = -EIO;
 			BUFFER_TRACE(bh, "remove from checkpoint");
 			if (__jbd2_journal_remove_checkpoint(jh))
 				/* The transaction was released; we're done */
···
 			spin_lock(&journal->j_list_lock);
 			goto restart2;
 		}
-		if (unlikely(buffer_write_io_error(bh)) && !result)
-			result = -EIO;
 
 		/*
 		 * Now in whatever state the buffer currently is, we
···
 	}
 out:
 	spin_unlock(&journal->j_list_lock);
-	if (result < 0)
-		jbd2_journal_abort(journal, result);
-	else
-		result = jbd2_cleanup_journal_tail(journal);
+	result = jbd2_cleanup_journal_tail(journal);
 
 	return (result < 0) ? result : 0;
 }
···
 {
 	struct journal_head *last_jh;
 	struct journal_head *next_jh = jh;
-	int ret;
 
 	if (!jh)
 		return 0;
···
 	do {
 		jh = next_jh;
 		next_jh = jh->b_cpnext;
-		if (!destroy)
-			ret = __try_to_free_cp_buf(jh);
-		else
-			ret = __jbd2_journal_remove_checkpoint(jh) + 1;
-		if (!ret)
+
+		if (!destroy && __cp_buffer_busy(jh))
 			return 0;
-		if (ret == 2)
+
+		if (__jbd2_journal_remove_checkpoint(jh))
 			return 1;
 		/*
 		 * This function only frees up some memory
···
 	} while (jh != last_jh);
 
 	return 0;
+}
+
+/*
+ * journal_shrink_one_cp_list
+ *
+ * Find 'nr_to_scan' written-back checkpoint buffers in the given list
+ * and try to release them. If the whole transaction is released, set
+ * the 'released' parameter. Return the number of released checkpointed
+ * buffers.
+ *
+ * Called with j_list_lock held.
+ */
+static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,
+						unsigned long *nr_to_scan,
+						bool *released)
+{
+	struct journal_head *last_jh;
+	struct journal_head *next_jh = jh;
+	unsigned long nr_freed = 0;
+	int ret;
+
+	if (!jh || *nr_to_scan == 0)
+		return 0;
+
+	last_jh = jh->b_cpprev;
+	do {
+		jh = next_jh;
+		next_jh = jh->b_cpnext;
+
+		(*nr_to_scan)--;
+		if (__cp_buffer_busy(jh))
+			continue;
+
+		nr_freed++;
+		ret = __jbd2_journal_remove_checkpoint(jh);
+		if (ret) {
+			*released = true;
+			break;
+		}
+
+		if (need_resched())
+			break;
+	} while (jh != last_jh && *nr_to_scan);
+
+	return nr_freed;
+}
+
+/*
+ * jbd2_journal_shrink_checkpoint_list
+ *
+ * Find 'nr_to_scan' written-back checkpoint buffers in the journal
+ * and try to release them. Return the number of released checkpointed
+ * buffers.
+ *
+ * Called with j_list_lock held.
+ */
+unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal,
+						  unsigned long *nr_to_scan)
+{
+	transaction_t *transaction, *last_transaction, *next_transaction;
+	bool released;
+	tid_t first_tid = 0, last_tid = 0, next_tid = 0;
+	tid_t tid = 0;
+	unsigned long nr_freed = 0;
+	unsigned long nr_scanned = *nr_to_scan;
+
+again:
+	spin_lock(&journal->j_list_lock);
+	if (!journal->j_checkpoint_transactions) {
+		spin_unlock(&journal->j_list_lock);
+		goto out;
+	}
+
+	/*
+	 * Get next shrink transaction, resume previous scan or start
+	 * over again. If some others do checkpoint and drop transaction
+	 * from the checkpoint list, we ignore saved j_shrink_transaction
+	 * and start over unconditionally.
+	 */
+	if (journal->j_shrink_transaction)
+		transaction = journal->j_shrink_transaction;
+	else
+		transaction = journal->j_checkpoint_transactions;
+
+	if (!first_tid)
+		first_tid = transaction->t_tid;
+	last_transaction = journal->j_checkpoint_transactions->t_cpprev;
+	next_transaction = transaction;
+	last_tid = last_transaction->t_tid;
+	do {
+		transaction = next_transaction;
+		next_transaction = transaction->t_cpnext;
+		tid = transaction->t_tid;
+		released = false;
+
+		nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_list,
+						       nr_to_scan, &released);
+		if (*nr_to_scan == 0)
+			break;
+		if (need_resched() || spin_needbreak(&journal->j_list_lock))
+			break;
+		if (released)
+			continue;
+
+		nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_io_list,
+						       nr_to_scan, &released);
+		if (*nr_to_scan == 0)
+			break;
+		if (need_resched() || spin_needbreak(&journal->j_list_lock))
+			break;
+	} while (transaction != last_transaction);
+
+	if (transaction != last_transaction) {
+		journal->j_shrink_transaction = next_transaction;
+		next_tid = next_transaction->t_tid;
+	} else {
+		journal->j_shrink_transaction = NULL;
+		next_tid = 0;
+	}
+
+	spin_unlock(&journal->j_list_lock);
+	cond_resched();
+
+	if (*nr_to_scan && next_tid)
+		goto again;
+out:
+	nr_scanned -= *nr_to_scan;
+	trace_jbd2_shrink_checkpoint_list(journal, first_tid, tid, last_tid,
+					  nr_freed, nr_scanned, next_tid);
+
+	return nr_freed;
 }
 
 /*
···
 	struct transaction_chp_stats_s *stats;
 	transaction_t *transaction;
 	journal_t *journal;
-	int ret = 0;
+	struct buffer_head *bh = jh2bh(jh);
 
 	JBUFFER_TRACE(jh, "entry");
 
-	if ((transaction = jh->b_cp_transaction) == NULL) {
+	transaction = jh->b_cp_transaction;
+	if (!transaction) {
 		JBUFFER_TRACE(jh, "not on transaction");
-		goto out;
+		return 0;
 	}
 	journal = transaction->t_journal;
 
 	JBUFFER_TRACE(jh, "removing from transaction");
+
+	/*
+	 * If we have failed to write the buffer out to disk, the filesystem
+	 * may become inconsistent. We cannot abort the journal here since
+	 * we hold j_list_lock and we have to be careful about races with
+	 * jbd2_journal_destroy(). So mark the writeback IO error in the
+	 * journal here and we abort the journal later from a better context.
+	 */
+	if (buffer_write_io_error(bh))
+		set_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags);
+
 	__buffer_unlink(jh);
 	jh->b_cp_transaction = NULL;
+	percpu_counter_dec(&journal->j_jh_shrink_count);
 	jbd2_journal_put_journal_head(jh);
 
-	if (transaction->t_checkpoint_list != NULL ||
-	    transaction->t_checkpoint_io_list != NULL)
-		goto out;
+	/* Is this transaction empty? */
+	if (transaction->t_checkpoint_list || transaction->t_checkpoint_io_list)
+		return 0;
 
 	/*
 	 * There is one special case to worry about: if we have just pulled the
···
 	 * See the comment at the end of jbd2_journal_commit_transaction().
 	 */
 	if (transaction->t_state != T_FINISHED)
-		goto out;
+		return 0;
 
-	/* OK, that was the last buffer for the transaction: we can now
-	   safely remove this transaction from the log */
+	/*
+	 * OK, that was the last buffer for the transaction, we can now
+	 * safely remove this transaction from the log.
+	 */
 	stats = &transaction->t_chp_stats;
 	if (stats->cs_chp_time)
 		stats->cs_chp_time = jbd2_time_diff(stats->cs_chp_time,
···
 
 	__jbd2_journal_drop_transaction(journal, transaction);
 	jbd2_journal_free_transaction(transaction);
-	ret = 1;
-out:
-	return ret;
+	return 1;
 }
 
 /*
···
 		jh->b_cpnext->b_cpprev = jh;
 	}
 	transaction->t_checkpoint_list = jh;
+	percpu_counter_inc(&transaction->t_journal->j_jh_shrink_count);
 }
 
 /*
···
 void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transaction)
 {
 	assert_spin_locked(&journal->j_list_lock);
+
+	journal->j_shrink_transaction = NULL;
 	if (transaction->t_cpnext) {
 		transaction->t_cpnext->t_cpprev = transaction->t_cpprev;
 		transaction->t_cpprev->t_cpnext = transaction->t_cpnext;

fs/jbd2/journal.c

···
 }
 EXPORT_SYMBOL(jbd2_fc_wait_bufs);
 
-/*
- * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf
- * for completion.
- */
 int jbd2_fc_release_bufs(journal_t *journal)
 {
 	struct buffer_head *bh;
···
 
 	j_fc_off = journal->j_fc_off;
 
-	/*
-	 * Wait in reverse order to minimize chances of us being woken up before
-	 * all IOs have completed
-	 */
 	for (i = j_fc_off - 1; i >= 0; i--) {
 		bh = journal->j_fc_wbuf[i];
 		if (!bh)
···
 
 	if (is_journal_aborted(journal))
 		return -EIO;
+	if (test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags)) {
+		jbd2_journal_abort(journal, -EIO);
+		return -EIO;
+	}
 
 	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
 	jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n",
···
 	write_unlock(&journal->j_state_lock);
 }
 
+/**
+ * __jbd2_journal_erase() - Discard or zeroout journal blocks (excluding superblock)
+ * @journal: The journal to erase.
+ * @flags: A discard/zeroout request is sent for each physically contigous
+ *	region of the journal. Either JBD2_JOURNAL_FLUSH_DISCARD or
+ *	JBD2_JOURNAL_FLUSH_ZEROOUT must be set to determine which operation
+ *	to perform.
+ *
+ * Note: JBD2_JOURNAL_FLUSH_ZEROOUT attempts to use hardware offload. Zeroes
+ * will be explicitly written if no hardware offload is available, see
+ * blkdev_issue_zeroout for more details.
+ */
+static int __jbd2_journal_erase(journal_t *journal, unsigned int flags)
+{
+	int err = 0;
+	unsigned long block, log_offset; /* logical */
+	unsigned long long phys_block, block_start, block_stop; /* physical */
+	loff_t byte_start, byte_stop, byte_count;
+	struct request_queue *q = bdev_get_queue(journal->j_dev);
+
+	/* flags must be set to either discard or zeroout */
+	if ((flags & ~JBD2_JOURNAL_FLUSH_VALID) || !flags ||
+			((flags & JBD2_JOURNAL_FLUSH_DISCARD) &&
+			(flags & JBD2_JOURNAL_FLUSH_ZEROOUT)))
+		return -EINVAL;
+
+	if (!q)
+		return -ENXIO;
+
+	if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !blk_queue_discard(q))
+		return -EOPNOTSUPP;
+
+	/*
+	 * lookup block mapping and issue discard/zeroout for each
+	 * contiguous region
+	 */
+	log_offset = be32_to_cpu(journal->j_superblock->s_first);
+	block_start =  ~0ULL;
+	for (block = log_offset; block < journal->j_total_len; block++) {
+		err = jbd2_journal_bmap(journal, block, &phys_block);
+		if (err) {
+			pr_err("JBD2: bad block at offset %lu", block);
+			return err;
+		}
+
+		if (block_start == ~0ULL) {
+			block_start = phys_block;
+			block_stop = block_start - 1;
+		}
+
+		/*
+		 * last block not contiguous with current block,
+		 * process last contiguous region and return to this block on
+		 * next loop
+		 */
+		if (phys_block != block_stop + 1) {
+			block--;
+		} else {
+			block_stop++;
+			/*
+			 * if this isn't the last block of journal,
+			 * no need to process now because next block may also
+			 * be part of this contiguous region
+			 */
+			if (block != journal->j_total_len - 1)
+				continue;
+		}
+
+		/*
+		 * end of contiguous region or this is last block of journal,
+		 * take care of the region
+		 */
+		byte_start = block_start * journal->j_blocksize;
+		byte_stop = block_stop * journal->j_blocksize;
+		byte_count = (block_stop - block_start + 1) *
+				journal->j_blocksize;
+
+		truncate_inode_pages_range(journal->j_dev->bd_inode->i_mapping,
+				byte_start, byte_stop);
+
+		if (flags & JBD2_JOURNAL_FLUSH_DISCARD) {
+			err = blkdev_issue_discard(journal->j_dev,
+					byte_start >> SECTOR_SHIFT,
+					byte_count >> SECTOR_SHIFT,
+					GFP_NOFS, 0);
+		} else if (flags & JBD2_JOURNAL_FLUSH_ZEROOUT) {
+			err = blkdev_issue_zeroout(journal->j_dev,
+					byte_start >> SECTOR_SHIFT,
+					byte_count >> SECTOR_SHIFT,
+					GFP_NOFS, 0);
+		}
+
+		if (unlikely(err != 0)) {
+			pr_err("JBD2: (error %d) unable to wipe journal at physical blocks %llu - %llu",
+					err, block_start, block_stop);
+			return err;
+		}
+
+		/* reset start and stop after processing a region */
+		block_start = ~0ULL;
+	}
+
+	return blkdev_issue_flush(journal->j_dev);
+}
 
 /**
  * jbd2_journal_update_sb_errno() - Update error in the journal.
···
 }
 
 /**
+ * jbd2_journal_shrink_scan()
+ *
+ * Scan the checkpointed buffer on the checkpoint list and release the
+ * journal_head.
+ */
+static unsigned long jbd2_journal_shrink_scan(struct shrinker *shrink,
+					      struct shrink_control *sc)
+{
+	journal_t *journal = container_of(shrink, journal_t, j_shrinker);
+	unsigned long nr_to_scan = sc->nr_to_scan;
+	unsigned long nr_shrunk;
+	unsigned long count;
+
+	count = percpu_counter_read_positive(&journal->j_jh_shrink_count);
+	trace_jbd2_shrink_scan_enter(journal, sc->nr_to_scan, count);
+
+	nr_shrunk = jbd2_journal_shrink_checkpoint_list(journal, &nr_to_scan);
+
+	count = percpu_counter_read_positive(&journal->j_jh_shrink_count);
+	trace_jbd2_shrink_scan_exit(journal, nr_to_scan, nr_shrunk, count);
+
+	return nr_shrunk;
+}
+
+/**
+ * jbd2_journal_shrink_count()
+ *
+ * Count the number of checkpoint buffers on the checkpoint list.
+ */
+static unsigned long jbd2_journal_shrink_count(struct shrinker *shrink,
+					       struct shrink_control *sc)
+{
+	journal_t *journal = container_of(shrink, journal_t, j_shrinker);
+	unsigned long count;
+
+	count = percpu_counter_read_positive(&journal->j_jh_shrink_count);
+	trace_jbd2_shrink_count(journal, sc->nr_to_scan, count);
+
+	return count;
+}
+
+/**
+ * jbd2_journal_register_shrinker()
+ * @journal: Journal to act on.
+ *
+ * Init a percpu counter to record the checkpointed buffers on the checkpoint
+ * list and register a shrinker to release their journal_head.
+ */
+int jbd2_journal_register_shrinker(journal_t *journal)
+{
+	int err;
+
+	journal->j_shrink_transaction = NULL;
+
+	err = percpu_counter_init(&journal->j_jh_shrink_count, 0, GFP_KERNEL);
+	if (err)
+		return err;
+
+	journal->j_shrinker.scan_objects = jbd2_journal_shrink_scan;
+	journal->j_shrinker.count_objects = jbd2_journal_shrink_count;
+	journal->j_shrinker.seeks = DEFAULT_SEEKS;
+	journal->j_shrinker.batch = journal->j_max_transaction_buffers;
+
+	err = register_shrinker(&journal->j_shrinker);
+	if (err) {
+		percpu_counter_destroy(&journal->j_jh_shrink_count);
+		return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_journal_register_shrinker);
+
+/**
+ * jbd2_journal_unregister_shrinker()
+ * @journal: Journal to act on.
+ *
+ * Unregister the checkpointed buffer shrinker and destroy the percpu counter.
+ */
+void jbd2_journal_unregister_shrinker(journal_t *journal)
+{
+	percpu_counter_destroy(&journal->j_jh_shrink_count);
+	unregister_shrinker(&journal->j_shrinker);
+}
+EXPORT_SYMBOL(jbd2_journal_unregister_shrinker);
+
+/**
  * jbd2_journal_destroy() - Release a journal_t structure.
  * @journal: Journal to act on.
  *
···
 	J_ASSERT(journal->j_checkpoint_transactions == NULL);
 	spin_unlock(&journal->j_list_lock);
 
+	/*
+	 * OK, all checkpoint transactions have been checked, now check the
+	 * write out io error flag and abort the journal if some buffer failed
+	 * to write back to the original location, otherwise the filesystem
+	 * may become inconsistent.
+	 */
+	if (!is_journal_aborted(journal) &&
+	    test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags))
+		jbd2_journal_abort(journal, -EIO);
+
 	if (journal->j_sb_buffer) {
 		if (!is_journal_aborted(journal)) {
 			mutex_lock_io(&journal->j_checkpoint_mutex);
···
 			err = -EIO;
 		brelse(journal->j_sb_buffer);
 	}
+
+	jbd2_journal_unregister_shrinker(journal);
 
 	if (journal->j_proc_entry)
 		jbd2_stats_proc_exit(journal);
···
 /**
  * jbd2_journal_flush() - Flush journal
  * @journal: Journal to act on.
+ * @flags: optional operation on the journal blocks after the flush (see below)
  *
  * Flush all data for a given journal to disk and empty the journal.
  * Filesystems can use this when remounting readonly to ensure that
- * recovery does not need to happen on remount.
+ * recovery does not need to happen on remount. Optionally, a discard or zeroout
+ * can be issued on the journal blocks after flushing.
+ *
+ * flags:
+ *	JBD2_JOURNAL_FLUSH_DISCARD: issues discards for the journal blocks
+ *	JBD2_JOURNAL_FLUSH_ZEROOUT: issues zeroouts for the journal blocks
  */
-
-int jbd2_journal_flush(journal_t *journal)
+int jbd2_journal_flush(journal_t *journal, unsigned int flags)
 {
 	int err = 0;
 	transaction_t *transaction = NULL;
···
 	 * commits of data to the journal will restore the current
 	 * s_start value. */
 	jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA);
+
+	if (flags)
+		err = __jbd2_journal_erase(journal, flags);
+
 	mutex_unlock(&journal->j_checkpoint_mutex);
 	write_lock(&journal->j_state_lock);
 	J_ASSERT(!journal->j_running_transaction);

fs/jbd2/transaction.c

···
 {
 	struct buffer_head *head;
 	struct buffer_head *bh;
-	bool has_write_io_error = false;
 	int ret = 0;
 
 	J_ASSERT(PageLocked(page));
···
 		jbd2_journal_put_journal_head(jh);
 		if (buffer_jbd(bh))
 			goto busy;
-
-		/*
-		 * If we free a metadata buffer which has been failed to
-		 * write out, the jbd2 checkpoint procedure will not detect
-		 * this failure and may lead to filesystem inconsistency
-		 * after cleanup journal tail.
-		 */
-		if (buffer_write_io_error(bh)) {
-			pr_err("JBD2: Error while async write back metadata bh %llu.",
-			       (unsigned long long)bh->b_blocknr);
-			has_write_io_error = true;
-		}
 	} while ((bh = bh->b_this_page) != head);
 
 	ret = try_to_free_buffers(page);
-
 busy:
-	if (has_write_io_error)
-		jbd2_journal_abort(journal, -EIO);
-
 	return ret;
 }
 

fs/ocfs2/alloc.c

···
 	 * Then truncate log will be replayed resulting in cluster double free.
 	 */
 	jbd2_journal_lock_updates(journal->j_journal);
-	status = jbd2_journal_flush(journal->j_journal);
+	status = jbd2_journal_flush(journal->j_journal, 0);
 	jbd2_journal_unlock_updates(journal->j_journal);
 	if (status < 0) {
 		mlog_errno(status);

fs/ocfs2/journal.c

···
 	}
 
 	jbd2_journal_lock_updates(journal->j_journal);
-	status = jbd2_journal_flush(journal->j_journal);
+	status = jbd2_journal_flush(journal->j_journal, 0);
 	jbd2_journal_unlock_updates(journal->j_journal);
 	if (status < 0) {
 		up_write(&journal->j_trans_barrier);
···
 
 	if (ocfs2_mount_local(osb)) {
 		jbd2_journal_lock_updates(journal->j_journal);
-		status = jbd2_journal_flush(journal->j_journal);
+		status = jbd2_journal_flush(journal->j_journal, 0);
 		jbd2_journal_unlock_updates(journal->j_journal);
 		if (status < 0)
 			mlog_errno(status);
···
 
 	if (replayed) {
 		jbd2_journal_lock_updates(journal->j_journal);
-		status = jbd2_journal_flush(journal->j_journal);
+		status = jbd2_journal_flush(journal->j_journal, 0);
 		jbd2_journal_unlock_updates(journal->j_journal);
 		if (status < 0)
 			mlog_errno(status);
···
 
 	/* wipe the journal */
 	jbd2_journal_lock_updates(journal);
-	status = jbd2_journal_flush(journal);
+	status = jbd2_journal_flush(journal, 0);
 	jbd2_journal_unlock_updates(journal);
 	if (status < 0)
 		mlog_errno(status);

include/linux/fs.h

···
 	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
 	struct dquot **(*get_dquots)(struct inode *);
 #endif
-	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
 	long (*nr_cached_objects)(struct super_block *,
 				  struct shrink_control *);
 	long (*free_cached_objects)(struct super_block *,

include/linux/jbd2.h

···
 	unsigned long		j_flags;
 
 	/**
+	 * @j_atomic_flags: Atomic journaling state flags.
+	 */
+	unsigned long		j_atomic_flags;
+
+	/**
 	 * @j_errno:
 	 *
 	 * Is there an outstanding uncleared error on the journal (from a prior
···
 	 * @j_checkpoint_mutex.  [j_checkpoint_mutex]
 	 */
 	struct buffer_head	*j_chkpt_bhs[JBD2_NR_BATCH];
+
+	/**
+	 * @j_shrinker:
+	 *
+	 * Journal head shrinker, reclaim buffer's journal head which
+	 * has been written back.
+	 */
+	struct shrinker		j_shrinker;
+
+	/**
+	 * @j_jh_shrink_count:
+	 *
+	 * Number of journal buffers on the checkpoint list. [j_list_lock]
+	 */
+	struct percpu_counter	j_jh_shrink_count;
+
+	/**
+	 * @j_shrink_transaction:
+	 *
+	 * Record next transaction will shrink on the checkpoint list.
+	 * [j_list_lock]
+	 */
+	transaction_t		*j_shrink_transaction;
 
 	/**
 	 * @j_head:
···
 						 * mode */
 #define JBD2_FAST_COMMIT_ONGOING	0x100	/* Fast commit is ongoing */
 #define JBD2_FULL_COMMIT_ONGOING	0x200	/* Full commit is ongoing */
+#define JBD2_JOURNAL_FLUSH_DISCARD	0x0001
+#define JBD2_JOURNAL_FLUSH_ZEROOUT	0x0002
+#define JBD2_JOURNAL_FLUSH_VALID	(JBD2_JOURNAL_FLUSH_DISCARD | \
+					JBD2_JOURNAL_FLUSH_ZEROOUT)
+
+/*
+ * Journal atomic flag definitions
+ */
+#define JBD2_CHECKPOINT_IO_ERROR	0x001	/* Detect io error while writing
+						 * buffer back to disk */
 
 /*
  * Function declarations for the journaling transaction and buffer
···
 
 /* Checkpoint list management */
 void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy);
+unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan);
 int __jbd2_journal_remove_checkpoint(struct journal_head *);
 void jbd2_journal_destroy_checkpoint(journal_t *journal);
 void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *);
···
 				struct page *, unsigned int, unsigned int);
 extern int	 jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page);
 extern int	 jbd2_journal_stop(handle_t *);
-extern int	 jbd2_journal_flush (journal_t *);
+extern int	 jbd2_journal_flush(journal_t *journal, unsigned int flags);
 extern void	 jbd2_journal_lock_updates (journal_t *);
 extern void	 jbd2_journal_unlock_updates (journal_t *);
 
···
 		   (journal_t *, unsigned long, unsigned long, unsigned long);
 extern void	   jbd2_journal_clear_features
 		   (journal_t *, unsigned long, unsigned long, unsigned long);
+extern int	   jbd2_journal_register_shrinker(journal_t *journal);
+extern void	   jbd2_journal_unregister_shrinker(journal_t *journal);
 extern int	   jbd2_journal_load       (journal_t *journal);
 extern int	   jbd2_journal_destroy    (journal_t *);
 extern int	   jbd2_journal_recover    (journal_t *journal);

include/trace/events/jbd2.h

···
 		__entry->stall_ms)
 );
 
+DECLARE_EVENT_CLASS(jbd2_journal_shrink,
+
+	TP_PROTO(journal_t *journal, unsigned long nr_to_scan,
+		 unsigned long count),
+
+	TP_ARGS(journal, nr_to_scan, count),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(unsigned long, nr_to_scan)
+		__field(unsigned long, count)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->nr_to_scan	= nr_to_scan;
+		__entry->count		= count;
+	),
+
+	TP_printk("dev %d,%d nr_to_scan %lu count %lu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->nr_to_scan, __entry->count)
+);
+
+DEFINE_EVENT(jbd2_journal_shrink, jbd2_shrink_count,
+
+	TP_PROTO(journal_t *journal, unsigned long nr_to_scan, unsigned long count),
+
+	TP_ARGS(journal, nr_to_scan, count)
+);
+
+DEFINE_EVENT(jbd2_journal_shrink, jbd2_shrink_scan_enter,
+
+	TP_PROTO(journal_t *journal, unsigned long nr_to_scan, unsigned long count),
+
+	TP_ARGS(journal, nr_to_scan, count)
+);
+
+TRACE_EVENT(jbd2_shrink_scan_exit,
+
+	TP_PROTO(journal_t *journal, unsigned long nr_to_scan,
+		 unsigned long nr_shrunk, unsigned long count),
+
+	TP_ARGS(journal, nr_to_scan, nr_shrunk, count),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(unsigned long, nr_to_scan)
+		__field(unsigned long, nr_shrunk)
+		__field(unsigned long, count)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->nr_to_scan	= nr_to_scan;
+		__entry->nr_shrunk	= nr_shrunk;
+		__entry->count		= count;
+	),
+
+	TP_printk("dev %d,%d nr_to_scan %lu nr_shrunk %lu count %lu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->nr_to_scan, __entry->nr_shrunk,
+		  __entry->count)
+);
+
+TRACE_EVENT(jbd2_shrink_checkpoint_list,
+
+	TP_PROTO(journal_t *journal, tid_t first_tid, tid_t tid, tid_t last_tid,
+		 unsigned long nr_freed, unsigned long nr_scanned,
+		 tid_t next_tid),
+
+	TP_ARGS(journal, first_tid, tid, last_tid, nr_freed,
+		nr_scanned, next_tid),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(tid_t, first_tid)
+		__field(tid_t, tid)
+		__field(tid_t, last_tid)
+		__field(unsigned long, nr_freed)
+		__field(unsigned long, nr_scanned)
+		__field(tid_t, next_tid)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->first_tid	= first_tid;
+		__entry->tid		= tid;
+		__entry->last_tid	= last_tid;
+		__entry->nr_freed	= nr_freed;
+		__entry->nr_scanned	= nr_scanned;
+		__entry->next_tid	= next_tid;
+	),
+
+	TP_printk("dev %d,%d shrink transaction %u-%u(%u) freed %lu "
+		  "scanned %lu next transaction %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->first_tid, __entry->tid, __entry->last_tid,
+		  __entry->nr_freed, __entry->nr_scanned, __entry->next_tid)
+);
+
 #endif /* _TRACE_JBD2_H */
 
 /* This part must be outside protection */