Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: fix kconfig typo and extra whitespace
  ext4: fix build failure without procfs
  ext4: add an option to control error handling on file data
  jbd2: don't dirty original metadata buffer on abort
  ext4: add checks for errors from jbd2
  jbd2: fix error handling for checkpoint io
  jbd2: abort when failed to log metadata buffers

Documentation/filesystems/ext4.txt

@@ -223,6 +223,11 @@ errors=remount-ro(*)	Remount the filesystem read-only on an error.
 errors=continue		Keep going on a filesystem error.
 errors=panic		Panic and halt the machine if an error occurs.
 
+data_err=ignore(*)	Just print an error message if an error occurs
+			in a file data buffer in ordered mode.
+data_err=abort		Abort the journal if an error occurs in a file
+			data buffer in ordered mode.
+
 grpid			Give objects the same group ID as their creator.
 bsdgroups
 

fs/Kconfig

@@ -170,7 +170,7 @@ config EXT4DEV_COMPAT
 	help
 	  Starting with 2.6.28, the name of the ext4 filesystem was
 	  renamed from ext4dev to ext4.  Unfortunately there are some
-	  lagecy userspace programs (such as klibc's fstype) have
+	  legacy userspace programs (such as klibc's fstype) have
 	  "ext4dev" hardcoded.
 
 	  To enable backwards compatibility so that systems that are

fs/ext4/ext4.h

@@ -540,6 +540,8 @@ do {									       \
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
 #define EXT4_MOUNT_I_VERSION            0x2000000 /* i_version support */
 #define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
+#define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
+
 /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */
 #ifndef _LINUX_EXT2_FS_H
 #define clear_opt(o, opt)		o &= ~EXT4_MOUNT_##opt

fs/ext4/ioctl.c

@@ -192,7 +192,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	case EXT4_IOC_GROUP_EXTEND: {
 		ext4_fsblk_t n_blocks_count;
 		struct super_block *sb = inode->i_sb;
-		int err;
+		int err, err2;
 
 		if (!capable(CAP_SYS_RESOURCE))
 			return -EPERM;
@@ -206,8 +206,10 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 		err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
 		jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
-		jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+		err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
 		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+		if (err == 0)
+			err = err2;
 		mnt_drop_write(filp->f_path.mnt);
 
 		return err;
@@ -215,7 +217,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	case EXT4_IOC_GROUP_ADD: {
 		struct ext4_new_group_data input;
 		struct super_block *sb = inode->i_sb;
-		int err;
+		int err, err2;
 
 		if (!capable(CAP_SYS_RESOURCE))
 			return -EPERM;
@@ -230,8 +232,10 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 		err = ext4_group_add(sb, &input);
 		jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
-		jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+		err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
 		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+		if (err == 0)
+			err = err2;
 		mnt_drop_write(filp->f_path.mnt);
 
 		return err;

fs/ext4/super.c

@@ -507,7 +507,8 @@ static void ext4_put_super(struct super_block *sb)
 	ext4_mb_release(sb);
 	ext4_ext_release(sb);
 	ext4_xattr_put_super(sb);
-	jbd2_journal_destroy(sbi->s_journal);
+	if (jbd2_journal_destroy(sbi->s_journal) < 0)
+		ext4_abort(sb, __func__, "Couldn't clean up the journal");
 	sbi->s_journal = NULL;
 	if (!(sb->s_flags & MS_RDONLY)) {
 		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
@@ -777,6 +778,9 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_printf(seq, ",inode_readahead_blks=%u",
 			   sbi->s_inode_readahead_blks);
 
+	if (test_opt(sb, DATA_ERR_ABORT))
+		seq_puts(seq, ",data_err=abort");
+
 	ext4_show_quota_options(seq, sb);
 	return 0;
 }
@@ -906,6 +910,7 @@ enum {
 	Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
 	Opt_journal_checksum, Opt_journal_async_commit,
 	Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
+	Opt_data_err_abort, Opt_data_err_ignore,
 	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
 	Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
@@ -952,6 +957,8 @@ static match_table_t tokens = {
 	{Opt_data_journal, "data=journal"},
 	{Opt_data_ordered, "data=ordered"},
 	{Opt_data_writeback, "data=writeback"},
+	{Opt_data_err_abort, "data_err=abort"},
+	{Opt_data_err_ignore, "data_err=ignore"},
 	{Opt_offusrjquota, "usrjquota="},
 	{Opt_usrjquota, "usrjquota=%s"},
 	{Opt_offgrpjquota, "grpjquota="},
@@ -1186,6 +1193,12 @@ static int parse_options(char *options, struct super_block *sb,
 				sbi->s_mount_opt |= data_opt;
 			}
 			break;
+		case Opt_data_err_abort:
+			set_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+			break;
+		case Opt_data_err_ignore:
+			clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+			break;
 #ifdef CONFIG_QUOTA
 		case Opt_usrjquota:
 			qtype = USRQUOTA;
@@ -2218,6 +2231,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
+#ifdef CONFIG_PROC_FS
 	if (ext4_proc_root)
 		sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
 
@@ -2225,6 +2239,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		proc_create_data("inode_readahead_blks", 0644, sbi->s_proc,
 				 &ext4_ui_proc_fops,
 				 &sbi->s_inode_readahead_blks);
+#endif
 
 	bgl_lock_init(&sbi->s_blockgroup_lock);
 
@@ -2534,6 +2549,10 @@ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal)
 		journal->j_flags |= JBD2_BARRIER;
 	else
 		journal->j_flags &= ~JBD2_BARRIER;
+	if (test_opt(sb, DATA_ERR_ABORT))
+		journal->j_flags |= JBD2_ABORT_ON_SYNCDATA_ERR;
+	else
+		journal->j_flags &= ~JBD2_ABORT_ON_SYNCDATA_ERR;
 	spin_unlock(&journal->j_state_lock);
 }
 
@@ -2853,7 +2872,9 @@ static void ext4_mark_recovery_complete(struct super_block *sb,
 	journal_t *journal = EXT4_SB(sb)->s_journal;
 
 	jbd2_journal_lock_updates(journal);
-	jbd2_journal_flush(journal);
+	if (jbd2_journal_flush(journal) < 0)
+		goto out;
+
 	lock_super(sb);
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER) &&
 	    sb->s_flags & MS_RDONLY) {
@@ -2862,6 +2883,8 @@ static void ext4_mark_recovery_complete(struct super_block *sb,
 		ext4_commit_super(sb, es, 1);
 	}
 	unlock_super(sb);
+
+out:
 	jbd2_journal_unlock_updates(journal);
 }
 
@@ -2962,7 +2985,13 @@ static void ext4_write_super_lockfs(struct super_block *sb)
 
 		/* Now we set up the journal barrier. */
 		jbd2_journal_lock_updates(journal);
-		jbd2_journal_flush(journal);
+
+		/*
+		 * We don't want to clear needs_recovery flag when we failed
+		 * to flush the journal.
+		 */
+		if (jbd2_journal_flush(journal) < 0)
+			return;
 
 		/* Journal blocked and flushed, clear needs_recovery flag. */
 		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
@@ -3402,8 +3431,12 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 		 * otherwise be livelocked...
 		 */
 		jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
-		jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+		err = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
 		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+		if (err) {
+			path_put(&nd.path);
+			return err;
+		}
 	}
 
 	err = vfs_quota_on_path(sb, type, format_id, &nd.path);

fs/jbd2/checkpoint.c

@@ -94,7 +94,8 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
 	int ret = 0;
 	struct buffer_head *bh = jh2bh(jh);
 
-	if (jh->b_jlist == BJ_None && !buffer_locked(bh) && !buffer_dirty(bh)) {
+	if (jh->b_jlist == BJ_None && !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;
 		jbd_unlock_bh_state(bh);
@@ -176,21 +177,25 @@ static void jbd_sync_bh(journal_t *journal, struct buffer_head *bh)
  * buffers. Note that we take the buffers in the opposite ordering
  * from the one in which they were submitted for IO.
  *
+ * Return 0 on success, and return <0 if some buffers have failed
+ * to be written out.
+ *
  * Called with j_list_lock held.
  */
-static void __wait_cp_io(journal_t *journal, transaction_t *transaction)
+static int __wait_cp_io(journal_t *journal, transaction_t *transaction)
 {
 	struct journal_head *jh;
 	struct buffer_head *bh;
 	tid_t this_tid;
 	int released = 0;
+	int ret = 0;
 
 	this_tid = transaction->t_tid;
 restart:
 	/* Did somebody clean up the transaction in the meanwhile? */
 	if (journal->j_checkpoint_transactions != transaction ||
 			transaction->t_tid != this_tid)
-		return;
+		return ret;
 	while (!released && transaction->t_checkpoint_io_list) {
 		jh = transaction->t_checkpoint_io_list;
 		bh = jh2bh(jh);
@@ -210,6 +215,9 @@ static void __wait_cp_io(journal_t *journal, transaction_t *transaction)
 			spin_lock(&journal->j_list_lock);
 			goto restart;
 		}
+		if (unlikely(buffer_write_io_error(bh)))
+			ret = -EIO;
+
 		/*
 		 * Now in whatever state the buffer currently is, we know that
 		 * it has been written out and so we can drop it from the list
@@ -219,6 +227,8 @@ static void __wait_cp_io(journal_t *journal, transaction_t *transaction)
 		jbd2_journal_remove_journal_head(bh);
 		__brelse(bh);
 	}
+
+	return ret;
 }
 
 #define NR_BATCH	64
@@ -242,7 +252,8 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
  * Try to flush one buffer from the checkpoint list to disk.
  *
  * Return 1 if something happened which requires us to abort the current
- * scan of the checkpoint list.
+ * scan of the checkpoint list.  Return <0 if the buffer has failed to
+ * be written out.
  *
  * Called with j_list_lock held and drops it if 1 is returned
  * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
@@ -274,6 +285,9 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 		jbd2_log_wait_commit(journal, tid);
 		ret = 1;
 	} else if (!buffer_dirty(bh)) {
+		ret = 1;
+		if (unlikely(buffer_write_io_error(bh)))
+			ret = -EIO;
 		J_ASSERT_JH(jh, !buffer_jbddirty(bh));
 		BUFFER_TRACE(bh, "remove from checkpoint");
 		__jbd2_journal_remove_checkpoint(jh);
@@ -281,7 +295,6 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 		jbd_unlock_bh_state(bh);
 		jbd2_journal_remove_journal_head(bh);
 		__brelse(bh);
-		ret = 1;
 	} else {
 		/*
 		 * Important: we are about to write the buffer, and
@@ -314,6 +327,7 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
  * to disk. We submit larger chunks of data at once.
  *
  * The journal should be locked before calling this function.
+ * Called with j_checkpoint_mutex held.
  */
 int jbd2_log_do_checkpoint(journal_t *journal)
 {
@@ -339,6 +353,7 @@ int jbd2_log_do_checkpoint(journal_t *journal)
 	 * 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;
@@ -357,7 +372,7 @@ int jbd2_log_do_checkpoint(journal_t *journal)
 		int batch_count = 0;
 		struct buffer_head *bhs[NR_BATCH];
 		struct journal_head *jh;
-		int retry = 0;
+		int retry = 0, err;
 
 		while (!retry && transaction->t_checkpoint_list) {
 			struct buffer_head *bh;
@@ -371,6 +386,8 @@ int jbd2_log_do_checkpoint(journal_t *journal)
 			}
 			retry = __process_buffer(journal, jh, bhs, &batch_count,
 						 transaction);
+			if (retry < 0 && !result)
+				result = retry;
 			if (!retry && (need_resched() ||
 				spin_needbreak(&journal->j_list_lock))) {
 				spin_unlock(&journal->j_list_lock);
@@ -395,14 +412,18 @@ int jbd2_log_do_checkpoint(journal_t *journal)
 		 * Now we have cleaned up the first transaction's checkpoint
 		 * list. Let's clean up the second one
 		 */
-		__wait_cp_io(journal, transaction);
+		err = __wait_cp_io(journal, transaction);
+		if (!result)
+			result = err;
 	}
 out:
 	spin_unlock(&journal->j_list_lock);
-	result = jbd2_cleanup_journal_tail(journal);
 	if (result < 0)
-		return result;
-	return 0;
+		jbd2_journal_abort(journal, result);
+	else
+		result = jbd2_cleanup_journal_tail(journal);
+
+	return (result < 0) ? result : 0;
 }
 
 /*
@@ -418,8 +439,9 @@ int jbd2_log_do_checkpoint(journal_t *journal)
  * This is the only part of the journaling code which really needs to be
  * aware of transaction aborts.  Checkpointing involves writing to the
  * main filesystem area rather than to the journal, so it can proceed
- * even in abort state, but we must not update the journal superblock if
- * we have an abort error outstanding.
+ * even in abort state, but we must not update the super block if
+ * checkpointing may have failed.  Otherwise, we would lose some metadata
+ * buffers which should be written-back to the filesystem.
  */
 
 int jbd2_cleanup_journal_tail(journal_t *journal)
@@ -428,6 +450,9 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
 	tid_t		first_tid;
 	unsigned long	blocknr, freed;
 
+	if (is_journal_aborted(journal))
+		return 1;
+
 	/* OK, work out the oldest transaction remaining in the log, and
 	 * the log block it starts at.
 	 *

fs/jbd2/commit.c

@@ -504,9 +504,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		jh = commit_transaction->t_buffers;
 
 		/* If we're in abort mode, we just un-journal the buffer and
-		   release it for background writing. */
+		   release it. */
 
 		if (is_journal_aborted(journal)) {
+			clear_buffer_jbddirty(jh2bh(jh));
 			JBUFFER_TRACE(jh, "journal is aborting: refile");
 			jbd2_journal_refile_buffer(journal, jh);
 			/* If that was the last one, we need to clean up
@@ -683,6 +684,8 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		printk(KERN_WARNING
 			"JBD2: Detected IO errors while flushing file data "
 		       "on %s\n", journal->j_devname);
+		if (journal->j_flags & JBD2_ABORT_ON_SYNCDATA_ERR)
+			jbd2_journal_abort(journal, err);
 		err = 0;
 	}
 
@@ -783,6 +786,9 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		/* AKPM: bforget here */
 	}
 
+	if (err)
+		jbd2_journal_abort(journal, err);
+
 	jbd_debug(3, "JBD: commit phase 5\n");
 
 	if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
@@ -881,6 +887,8 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		if (buffer_jbddirty(bh)) {
 			JBUFFER_TRACE(jh, "add to new checkpointing trans");
 			__jbd2_journal_insert_checkpoint(jh, commit_transaction);
+			if (is_journal_aborted(journal))
+				clear_buffer_jbddirty(bh);
 			JBUFFER_TRACE(jh, "refile for checkpoint writeback");
 			__jbd2_journal_refile_buffer(jh);
 			jbd_unlock_bh_state(bh);

fs/jbd2/journal.c

@@ -1451,9 +1451,12 @@ int jbd2_journal_load(journal_t *journal)
  *
  * Release a journal_t structure once it is no longer in use by the
  * journaled object.
+ * Return <0 if we couldn't clean up the journal.
  */
-void jbd2_journal_destroy(journal_t *journal)
+int jbd2_journal_destroy(journal_t *journal)
 {
+	int err = 0;
+
 	/* Wait for the commit thread to wake up and die. */
 	journal_kill_thread(journal);
 
@@ -1476,11 +1479,16 @@ void jbd2_journal_destroy(journal_t *journal)
 	J_ASSERT(journal->j_checkpoint_transactions == NULL);
 	spin_unlock(&journal->j_list_lock);
 
+	if (journal->j_sb_buffer) {
+		if (!is_journal_aborted(journal)) {
 			/* We can now mark the journal as empty. */
 			journal->j_tail = 0;
-	journal->j_tail_sequence = ++journal->j_transaction_sequence;
-	if (journal->j_sb_buffer) {
+			journal->j_tail_sequence =
+				++journal->j_transaction_sequence;
 			jbd2_journal_update_superblock(journal, 1);
+		} else {
+			err = -EIO;
+		}
 		brelse(journal->j_sb_buffer);
 	}
 
@@ -1492,6 +1500,8 @@ void jbd2_journal_destroy(journal_t *journal)
 		jbd2_journal_destroy_revoke(journal);
 	kfree(journal->j_wbuf);
 	kfree(journal);
+
+	return err;
 }
 
 
@@ -1717,10 +1727,16 @@ int jbd2_journal_flush(journal_t *journal)
 	spin_lock(&journal->j_list_lock);
 	while (!err && journal->j_checkpoint_transactions != NULL) {
 		spin_unlock(&journal->j_list_lock);
+		mutex_lock(&journal->j_checkpoint_mutex);
 		err = jbd2_log_do_checkpoint(journal);
+		mutex_unlock(&journal->j_checkpoint_mutex);
 		spin_lock(&journal->j_list_lock);
 	}
 	spin_unlock(&journal->j_list_lock);
+
+	if (is_journal_aborted(journal))
+		return -EIO;
+
 	jbd2_cleanup_journal_tail(journal);
 
 	/* Finally, mark the journal as really needing no recovery.
@@ -1742,7 +1758,7 @@ int jbd2_journal_flush(journal_t *journal)
 	J_ASSERT(journal->j_head == journal->j_tail);
 	J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence);
 	spin_unlock(&journal->j_state_lock);
-	return err;
+	return 0;
 }
 
 /**

fs/jbd2/recovery.c

@@ -225,7 +225,7 @@ do {									\
  */
 int jbd2_journal_recover(journal_t *journal)
 {
-	int			err;
+	int			err, err2;
 	journal_superblock_t *	sb;
 
 	struct recovery_info	info;
@@ -263,7 +263,10 @@ int jbd2_journal_recover(journal_t *journal)
 	journal->j_transaction_sequence = ++info.end_transaction;
 
 	jbd2_journal_clear_revoke(journal);
-	sync_blockdev(journal->j_fs_dev);
+	err2 = sync_blockdev(journal->j_fs_dev);
+	if (!err)
+		err = err2;
+
 	return err;
 }
 

include/linux/jbd2.h

@@ -967,6 +967,9 @@ struct journal_s
 #define JBD2_FLUSHED	0x008	/* The journal superblock has been flushed */
 #define JBD2_LOADED	0x010	/* The journal superblock has been loaded */
 #define JBD2_BARRIER	0x020	/* Use IDE barriers */
+#define JBD2_ABORT_ON_SYNCDATA_ERR	0x040	/* Abort the journal on file
+						 * data write error in ordered
+						 * mode */
 
 /*
  * Function declarations for the journaling transaction and buffer
@@ -1060,7 +1063,7 @@ extern void	   jbd2_journal_clear_features
 		   (journal_t *, unsigned long, unsigned long, unsigned long);
 extern int	   jbd2_journal_create     (journal_t *);
 extern int	   jbd2_journal_load       (journal_t *journal);
-extern void	   jbd2_journal_destroy    (journal_t *);
+extern int	   jbd2_journal_destroy    (journal_t *);
 extern int	   jbd2_journal_recover    (journal_t *journal);
 extern int	   jbd2_journal_wipe       (journal_t *, int);
 extern int	   jbd2_journal_skip_recovery	(journal_t *);