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

Pull ext4 bugfixes from Ted Ts'o:
 "More bug fixes for ext4 -- most importantly, a fix for a bug
  introduced in 3.15 that can end up triggering a file system corruption
  error after a journal replay.

  It shouldn't lead to any actual data corruption, but it is scary and
  can force file systems to be remounted read-only, etc"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: fix potential null pointer dereference in ext4_free_inode
  ext4: fix a potential deadlock in __ext4_es_shrink()
  ext4: revert commit which was causing fs corruption after journal replays
  ext4: disable synchronous transaction batching if max_batch_time==0
  ext4: clarify ext4_error message in ext4_mb_generate_buddy_error()
  ext4: clarify error count warning messages
  ext4: fix unjournalled bg descriptor while initializing inode bitmap

5 files changed, 44 insertions, 45 deletions

diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 3f5c188953a..0b7e28e7eaa 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -966,10 +966,10 @@ retry:
 			continue;
 		}
 
-		if (ei->i_es_lru_nr == 0 || ei == locked_ei)
+		if (ei->i_es_lru_nr == 0 || ei == locked_ei ||
+		    !write_trylock(&ei->i_es_lock))
 			continue;
 
-		write_lock(&ei->i_es_lock);
 		shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan);
 		if (ei->i_es_lru_nr == 0)
 			list_del_init(&ei->i_es_lru);
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index a87455df38b..5b87fc36aab 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -338,7 +338,7 @@ out:
 			fatal = err;
 	} else {
 		ext4_error(sb, "bit already cleared for inode %lu", ino);
-		if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+		if (gdp && !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
 			int count;
 			count = ext4_free_inodes_count(sb, gdp);
 			percpu_counter_sub(&sbi->s_freeinodes_counter,
@@ -874,6 +874,13 @@ got:
 		goto out;
 	}
 
+	BUFFER_TRACE(group_desc_bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, group_desc_bh);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto out;
+	}
+
 	/* We may have to initialize the block bitmap if it isn't already */
 	if (ext4_has_group_desc_csum(sb) &&
 	    gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
@@ -910,13 +917,6 @@ got:
 		}
 	}
 
-	BUFFER_TRACE(group_desc_bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, group_desc_bh);
-	if (err) {
-		ext4_std_error(sb, err);
-		goto out;
-	}
-
 	/* Update the relevant bg descriptor fields */
 	if (ext4_has_group_desc_csum(sb)) {
 		int free;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 7f72f50a8fa..2dcb936be90 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -752,8 +752,8 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 
 	if (free != grp->bb_free) {
 		ext4_grp_locked_error(sb, group, 0, 0,
-				      "%u clusters in bitmap, %u in gd; "
-				      "block bitmap corrupt.",
+				      "block bitmap and bg descriptor "
+				      "inconsistent: %u vs %u free clusters",
 				      free, grp->bb_free);
 		/*
 		 * If we intend to continue, we consider group descriptor
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b9b9aabfb4d..6df7bc611db 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1525,8 +1525,6 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
 		sbi->s_commit_interval = HZ * arg;
 	} else if (token == Opt_max_batch_time) {
-		if (arg == 0)
-			arg = EXT4_DEF_MAX_BATCH_TIME;
 		sbi->s_max_batch_time = arg;
 	} else if (token == Opt_min_batch_time) {
 		sbi->s_min_batch_time = arg;
@@ -2809,10 +2807,11 @@ static void print_daily_error_info(unsigned long arg)
 	es = sbi->s_es;
 
 	if (es->s_error_count)
-		ext4_msg(sb, KERN_NOTICE, "error count: %u",
+		/* fsck newer than v1.41.13 is needed to clean this condition. */
+		ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u",
 			 le32_to_cpu(es->s_error_count));
 	if (es->s_first_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): initial error at %u: %.*s:%d",
+		printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d",
 		       sb->s_id, le32_to_cpu(es->s_first_error_time),
 		       (int) sizeof(es->s_first_error_func),
 		       es->s_first_error_func,
@@ -2826,7 +2825,7 @@ static void print_daily_error_info(unsigned long arg)
 		printk("\n");
 	}
 	if (es->s_last_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): last error at %u: %.*s:%d",
+		printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
 		       sb->s_id, le32_to_cpu(es->s_last_error_time),
 		       (int) sizeof(es->s_last_error_func),
 		       es->s_last_error_func,
@@ -3880,38 +3879,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			goto failed_mount2;
 		}
 	}
-
-	/*
-	 * set up enough so that it can read an inode,
-	 * and create new inode for buddy allocator
-	 */
-	sbi->s_gdb_count = db_count;
-	if (!test_opt(sb, NOLOAD) &&
-	    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
-		sb->s_op = &ext4_sops;
-	else
-		sb->s_op = &ext4_nojournal_sops;
-
-	ext4_ext_init(sb);
-	err = ext4_mb_init(sb);
-	if (err) {
-		ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
-			 err);
-		goto failed_mount2;
-	}
-
 	if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
 		ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
-		goto failed_mount2a;
+		goto failed_mount2;
 	}
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
 		if (!ext4_fill_flex_info(sb)) {
 			ext4_msg(sb, KERN_ERR,
 			       "unable to initialize "
 			       "flex_bg meta info!");
-			goto failed_mount2a;
+			goto failed_mount2;
 		}
 
+	sbi->s_gdb_count = db_count;
 	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
 	spin_lock_init(&sbi->s_next_gen_lock);
 
@@ -3946,6 +3926,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_stripe = ext4_get_stripe_size(sbi);
 	sbi->s_extent_max_zeroout_kb = 32;
 
+	/*
+	 * set up enough so that it can read an inode
+	 */
+	if (!test_opt(sb, NOLOAD) &&
+	    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
+		sb->s_op = &ext4_sops;
+	else
+		sb->s_op = &ext4_nojournal_sops;
 	sb->s_export_op = &ext4_export_ops;
 	sb->s_xattr = ext4_xattr_handlers;
 #ifdef CONFIG_QUOTA
@@ -4135,13 +4123,21 @@ no_journal:
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for "
 			 "reserved pool", ext4_calculate_resv_clusters(sb));
-		goto failed_mount5;
+		goto failed_mount4a;
 	}
 
 	err = ext4_setup_system_zone(sb);
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "failed to initialize system "
 			 "zone (%d)", err);
+		goto failed_mount4a;
+	}
+
+	ext4_ext_init(sb);
+	err = ext4_mb_init(sb);
+	if (err) {
+		ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
+			 err);
 		goto failed_mount5;
 	}
 
@@ -4218,8 +4214,11 @@ failed_mount8:
 failed_mount7:
 	ext4_unregister_li_request(sb);
 failed_mount6:
-	ext4_release_system_zone(sb);
+	ext4_mb_release(sb);
 failed_mount5:
+	ext4_ext_release(sb);
+	ext4_release_system_zone(sb);
+failed_mount4a:
 	dput(sb->s_root);
 	sb->s_root = NULL;
 failed_mount4:
@@ -4243,14 +4242,11 @@ failed_mount3:
 	percpu_counter_destroy(&sbi->s_extent_cache_cnt);
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
-failed_mount2a:
-	ext4_mb_release(sb);
 failed_mount2:
 	for (i = 0; i < db_count; i++)
 		brelse(sbi->s_group_desc[i]);
 	ext4_kvfree(sbi->s_group_desc);
 failed_mount:
-	ext4_ext_release(sb);
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
 	if (sbi->s_proc) {
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 38cfcf5f6fc..6f0f590cc5a 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1588,9 +1588,12 @@ int jbd2_journal_stop(handle_t *handle)
 	 * to perform a synchronous write.  We do this to detect the
 	 * case where a single process is doing a stream of sync
 	 * writes.  No point in waiting for joiners in that case.
+	 *
+	 * Setting max_batch_time to 0 disables this completely.
 	 */
 	pid = current->pid;
-	if (handle->h_sync && journal->j_last_sync_writer != pid) {
+	if (handle->h_sync && journal->j_last_sync_writer != pid &&
+	    journal->j_max_batch_time) {
 		u64 commit_time, trans_time;
 
 		journal->j_last_sync_writer = pid;