Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "Ext4 regression and bug fixes"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: inline jbd2_journal_[un]register_shrinker()
  ext4: fix flags validity checking for EXT4_IOC_CHECKPOINT
  ext4: fix possible UAF when remounting r/o a mmp-protected file system
  ext4: use ext4_grp_locked_error in mb_find_extent
  ext4: fix WARN_ON_ONCE(!buffer_uptodate) after an error writing the superblock
  Revert "ext4: consolidate checks for resize of bigalloc into ext4_resize_begin"

9 files changed, 115 insertions, 132 deletions

diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index be799040a4154a..b96ecba918990b 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -327,6 +327,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 
 	set_buffer_meta(bh);
 	set_buffer_prio(bh);
+	set_buffer_uptodate(bh);
 	if (ext4_handle_valid(handle)) {
 		err = jbd2_journal_dirty_metadata(handle, bh);
 		/* Errors can only happen due to aborted journal or a nasty bug */
@@ -355,7 +356,6 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 					 err);
 		}
 	} else {
-		set_buffer_uptodate(bh);
 		if (inode)
 			mark_buffer_dirty_inode(bh, inode);
 		else
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index e27f34bceb8dd3..6eed6170aded67 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -692,6 +692,13 @@ static long ext4_ioctl_group_add(struct file *file,
 	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;
@@ -816,7 +823,7 @@ static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg)
 	if (!EXT4_SB(sb)->s_journal)
 		return -ENODEV;
 
-	if (flags & ~JBD2_JOURNAL_FLUSH_VALID)
+	if (flags & ~EXT4_IOC_CHECKPOINT_FLAG_VALID)
 		return -EINVAL;
 
 	q = bdev_get_queue(EXT4_SB(sb)->s_journal->j_dev);
@@ -914,6 +921,13 @@ setversion_out:
 			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;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index c2c22c2baac0b7..089c958aa2c34f 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1909,10 +1909,11 @@ static int mb_find_extent(struct ext4_buddy *e4b, int block,
 	if (ex->fe_start + ex->fe_len > EXT4_CLUSTERS_PER_GROUP(e4b->bd_sb)) {
 		/* Should never happen! (but apparently sometimes does?!?) */
 		WARN_ON(1);
-		ext4_error(e4b->bd_sb, "corruption or bug in mb_find_extent "
-			   "block=%d, order=%d needed=%d ex=%u/%d/%d@%u",
-			   block, order, needed, ex->fe_group, ex->fe_start,
-			   ex->fe_len, ex->fe_logical);
+		ext4_grp_locked_error(e4b->bd_sb, e4b->bd_group, 0, 0,
+			"corruption or bug in mb_find_extent "
+			"block=%d, order=%d needed=%d ex=%u/%d/%d@%u",
+			block, order, needed, ex->fe_group, ex->fe_start,
+			ex->fe_len, ex->fe_logical);
 		ex->fe_len = 0;
 		ex->fe_start = 0;
 		ex->fe_group = 0;
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 6cb598b549ca16..bc364c119af6ac 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -156,7 +156,12 @@ static int kmmpd(void *data)
 	memcpy(mmp->mmp_nodename, init_utsname()->nodename,
 	       sizeof(mmp->mmp_nodename));
 
-	while (!kthread_should_stop()) {
+	while (!kthread_should_stop() && !sb_rdonly(sb)) {
+		if (!ext4_has_feature_mmp(sb)) {
+			ext4_warning(sb, "kmmpd being stopped since MMP feature"
+				     " has been disabled.");
+			goto wait_to_exit;
+		}
 		if (++seq > EXT4_MMP_SEQ_MAX)
 			seq = 1;
 
@@ -177,16 +182,6 @@ static int kmmpd(void *data)
 			failed_writes++;
 		}
 
-		if (!(le32_to_cpu(es->s_feature_incompat) &
-		    EXT4_FEATURE_INCOMPAT_MMP)) {
-			ext4_warning(sb, "kmmpd being stopped since MMP feature"
-				     " has been disabled.");
-			goto exit_thread;
-		}
-
-		if (sb_rdonly(sb))
-			break;
-
 		diff = jiffies - last_update_time;
 		if (diff < mmp_update_interval * HZ)
 			schedule_timeout_interruptible(mmp_update_interval *
@@ -207,7 +202,7 @@ static int kmmpd(void *data)
 				ext4_error_err(sb, -retval,
 					       "error reading MMP data: %d",
 					       retval);
-				goto exit_thread;
+				goto wait_to_exit;
 			}
 
 			mmp_check = (struct mmp_struct *)(bh_check->b_data);
@@ -221,7 +216,7 @@ static int kmmpd(void *data)
 				ext4_error_err(sb, EBUSY, "abort");
 				put_bh(bh_check);
 				retval = -EBUSY;
-				goto exit_thread;
+				goto wait_to_exit;
 			}
 			put_bh(bh_check);
 		}
@@ -244,7 +239,13 @@ static int kmmpd(void *data)
 
 	retval = write_mmp_block(sb, bh);
 
-exit_thread:
+wait_to_exit:
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (!kthread_should_stop())
+			schedule();
+	}
+	set_current_state(TASK_RUNNING);
 	return retval;
 }
 
@@ -391,5 +392,3 @@ failed:
 	brelse(bh);
 	return 1;
 }
-
-
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index fc885914c88a3d..7a9f1adef67980 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -74,10 +74,6 @@ int ext4_resize_begin(struct super_block *sb)
 		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;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 20344633bdd9f4..dfa09a277b56fb 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -705,15 +705,23 @@ static void flush_stashed_error_work(struct work_struct *work)
 	 * ext4 error handling code during handling of previous errors.
 	 */
 	if (!sb_rdonly(sbi->s_sb) && journal) {
+		struct buffer_head *sbh = sbi->s_sbh;
 		handle = jbd2_journal_start(journal, 1);
 		if (IS_ERR(handle))
 			goto write_directly;
-		if (jbd2_journal_get_write_access(handle, sbi->s_sbh)) {
+		if (jbd2_journal_get_write_access(handle, sbh)) {
 			jbd2_journal_stop(handle);
 			goto write_directly;
 		}
 		ext4_update_super(sbi->s_sb);
-		if (jbd2_journal_dirty_metadata(handle, sbi->s_sbh)) {
+		if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) {
+			ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to "
+				 "superblock detected");
+			clear_buffer_write_io_error(sbh);
+			set_buffer_uptodate(sbh);
+		}
+
+		if (jbd2_journal_dirty_metadata(handle, sbh)) {
 			jbd2_journal_stop(handle);
 			goto write_directly;
 		}
@@ -1176,7 +1184,6 @@ static void ext4_put_super(struct super_block *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;
@@ -5168,7 +5175,6 @@ failed_mount_wq:
 	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;
 	}
@@ -5494,12 +5500,6 @@ static int ext4_load_journal(struct super_block *sb,
 		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:
@@ -5985,7 +5985,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 				 */
 				ext4_mark_recovery_complete(sb, es);
 			}
-			ext4_stop_mmpd(sbi);
 		} else {
 			/* Make sure we can mount this feature set readwrite */
 			if (ext4_has_feature_readonly(sb) ||
@@ -6099,6 +6098,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks)
 		ext4_release_system_zone(sb);
 
+	if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb))
+		ext4_stop_mmpd(sbi);
+
 	/*
 	 * Some options can be enabled by ext4 and/or by VFS mount flag
 	 * either way we need to make sure it matches in both *flags and
@@ -6132,6 +6134,8 @@ restore_opts:
 	for (i = 0; i < EXT4_MAXQUOTAS; i++)
 		kfree(to_free[i]);
 #endif
+	if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb))
+		ext4_stop_mmpd(sbi);
 	kfree(orig_data);
 	return err;
 }
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 51d1eb2ffeb950..746132998c577f 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -701,7 +701,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 
 	__buffer_unlink(jh);
 	jh->b_cp_transaction = NULL;
-	percpu_counter_dec(&journal->j_jh_shrink_count);
+	percpu_counter_dec(&journal->j_checkpoint_jh_count);
 	jbd2_journal_put_journal_head(jh);
 
 	/* Is this transaction empty? */
@@ -764,7 +764,7 @@ void __jbd2_journal_insert_checkpoint(struct journal_head *jh,
 		jh->b_cpnext->b_cpprev = jh;
 	}
 	transaction->t_checkpoint_list = jh;
-	percpu_counter_inc(&transaction->t_journal->j_jh_shrink_count);
+	percpu_counter_inc(&transaction->t_journal->j_checkpoint_jh_count);
 }
 
 /*
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 152880c298cab6..35302bc192eb93 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1283,6 +1283,48 @@ static int jbd2_min_tag_size(void)
 	return sizeof(journal_block_tag_t) - 4;
 }
 
+/**
+ * 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_checkpoint_jh_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_checkpoint_jh_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_checkpoint_jh_count);
+	trace_jbd2_shrink_count(journal, sc->nr_to_scan, count);
+
+	return count;
+}
+
 /*
  * Management for journal control blocks: functions to create and
  * destroy journal_t structures, and to initialise and read existing
@@ -1361,9 +1403,23 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	journal->j_sb_buffer = bh;
 	journal->j_superblock = (journal_superblock_t *)bh->b_data;
 
+	journal->j_shrink_transaction = NULL;
+	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;
+
+	if (percpu_counter_init(&journal->j_checkpoint_jh_count, 0, GFP_KERNEL))
+		goto err_cleanup;
+
+	if (register_shrinker(&journal->j_shrinker)) {
+		percpu_counter_destroy(&journal->j_checkpoint_jh_count);
+		goto err_cleanup;
+	}
 	return journal;
 
 err_cleanup:
+	brelse(journal->j_sb_buffer);
 	kfree(journal->j_wbuf);
 	jbd2_journal_destroy_revoke(journal);
 	kfree(journal);
@@ -2051,93 +2107,6 @@ recovery_error:
 }
 
 /**
- * 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.
  *
@@ -2209,8 +2178,10 @@ int jbd2_journal_destroy(journal_t *journal)
 		brelse(journal->j_sb_buffer);
 	}
 
-	jbd2_journal_unregister_shrinker(journal);
-
+	if (journal->j_shrinker.flags & SHRINKER_REGISTERED) {
+		percpu_counter_destroy(&journal->j_checkpoint_jh_count);
+		unregister_shrinker(&journal->j_shrinker);
+	}
 	if (journal->j_proc_entry)
 		jbd2_stats_proc_exit(journal);
 	iput(journal->j_inode);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 6cc03532156276..fd933c45281af8 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -918,11 +918,11 @@ struct journal_s
 	struct shrinker		j_shrinker;
 
 	/**
-	 * @j_jh_shrink_count:
+	 * @j_checkpoint_jh_count:
 	 *
 	 * Number of journal buffers on the checkpoint list. [j_list_lock]
 	 */
-	struct percpu_counter	j_jh_shrink_count;
+	struct percpu_counter	j_checkpoint_jh_count;
 
 	/**
 	 * @j_shrink_transaction:
@@ -1556,8 +1556,6 @@ extern int	   jbd2_journal_set_features
 		   (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);