Merge tag 'ext4_for_linus-7.0-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 fixes from Ted Ts'o:

 - Update the MAINTAINERS file to add reviewers for the ext4 file system

 - Add a test issue an ext4 warning (not a WARN_ON) if there are still
   dirty pages attached to an evicted inode.

 - Fix a number of Syzkaller issues

 - Fix memory leaks on error paths

 - Replace some BUG and WARN with EFSCORRUPTED reporting

 - Fix a potential crash when disabling discard via remount followed by
   an immediate unmount. (Found by Sashiko)

 - Fix a corner case which could lead to allocating blocks for an
   indirect-mapped inode block numbers > 2**32

 - Fix a race when reallocating a freed inode that could result in a
   deadlock

 - Fix a user-after-free in update_super_work when racing with umount

 - Fix build issues when trying to build ext4's kunit tests as a module

 - Fix a bug where ext4_split_extent_zeroout() could fail to pass back
   an error from ext4_ext_dirty()

 - Avoid allocating blocks from a corrupted block group in
   ext4_mb_find_by_goal()

 - Fix a percpu_counters list corruption BUG triggered by an ext4
   extents kunit

 - Fix a potetial crash caused by the fast commit flush path potentially
   accessing the jinode structure before it is fully initialized

 - Fix fsync(2) in no-journal mode to make sure the dirtied inode is
   write to storage

 - Fix a bug when in no-journal mode, when ext4 tries to avoid using
   recently deleted inodes, if lazy itable initialization is enabled,
   can lead to an unitialized inode getting skipped and triggering an
   e2fsck complaint

 - Fix journal credit calculation when setting an xattr when both the
   encryption and ea_inode feeatures are enabled

 - Fix corner cases which could result in stale xarray tags after
   writeback

 - Fix generic/475 failures caused by ENOSPC errors while creating a
   symlink when the system crashes resulting to a file system
   inconsistency when replaying the fast commit journal

* tag 'ext4_for_linus-7.0-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (27 commits)
  ext4: always drain queued discard work in ext4_mb_release()
  ext4: handle wraparound when searching for blocks for indirect mapped blocks
  ext4: skip split extent recovery on corruption
  ext4: fix iloc.bh leak in ext4_fc_replay_inode() error paths
  ext4: fix deadlock on inode reallocation
  ext4: fix use-after-free in update_super_work when racing with umount
  ext4: fix the might_sleep() warnings in kvfree()
  ext4: reject mount if bigalloc with s_first_data_block != 0
  ext4: fix extents-test.c is not compiled when EXT4_KUNIT_TESTS=M
  ext4: fix mballoc-test.c is not compiled when EXT4_KUNIT_TESTS=M
  ext4: introduce EXPORT_SYMBOL_FOR_EXT4_TEST() helper
  jbd2: gracefully abort on checkpointing state corruptions
  ext4: avoid infinite loops caused by residual data
  ext4: validate p_idx bounds in ext4_ext_correct_indexes
  ext4: test if inode's all dirty pages are submitted to disk
  ext4: minor fix for ext4_split_extent_zeroout()
  ext4: avoid allocate block from corrupted group in ext4_mb_find_by_goal()
  ext4: kunit: extents-test: lix percpu_counters list corruption
  ext4: publish jinode after initialization
  ext4: replace BUG_ON with proper error handling in ext4_read_inline_folio
  ...

1 files changed, 31 insertions, 6 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 43f680c750ae..a34efb44e73d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1254,12 +1254,10 @@ static void ext4_group_desc_free(struct ext4_sb_info *sbi)
 	struct buffer_head **group_desc;
 	int i;
 
-	rcu_read_lock();
-	group_desc = rcu_dereference(sbi->s_group_desc);
+	group_desc = rcu_access_pointer(sbi->s_group_desc);
 	for (i = 0; i < sbi->s_gdb_count; i++)
 		brelse(group_desc[i]);
 	kvfree(group_desc);
-	rcu_read_unlock();
 }
 
 static void ext4_flex_groups_free(struct ext4_sb_info *sbi)
@@ -1267,14 +1265,12 @@ static void ext4_flex_groups_free(struct ext4_sb_info *sbi)
 	struct flex_groups **flex_groups;
 	int i;
 
-	rcu_read_lock();
-	flex_groups = rcu_dereference(sbi->s_flex_groups);
+	flex_groups = rcu_access_pointer(sbi->s_flex_groups);
 	if (flex_groups) {
 		for (i = 0; i < sbi->s_flex_groups_allocated; i++)
 			kvfree(flex_groups[i]);
 		kvfree(flex_groups);
 	}
-	rcu_read_unlock();
 }
 
 static void ext4_put_super(struct super_block *sb)
@@ -1527,6 +1523,27 @@ void ext4_clear_inode(struct inode *inode)
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 	ext4_discard_preallocations(inode);
+	/*
+	 * We must remove the inode from the hash before ext4_free_inode()
+	 * clears the bit in inode bitmap as otherwise another process reusing
+	 * the inode will block in insert_inode_hash() waiting for inode
+	 * eviction to complete while holding transaction handle open, but
+	 * ext4_evict_inode() still running for that inode could block waiting
+	 * for transaction commit if the inode is marked as IS_SYNC => deadlock.
+	 *
+	 * Removing the inode from the hash here is safe. There are two cases
+	 * to consider:
+	 * 1) The inode still has references to it (i_nlink > 0). In that case
+	 * we are keeping the inode and once we remove the inode from the hash,
+	 * iget() can create the new inode structure for the same inode number
+	 * and we are fine with that as all IO on behalf of the inode is
+	 * finished.
+	 * 2) We are deleting the inode (i_nlink == 0). In that case inode
+	 * number cannot be reused until ext4_free_inode() clears the bit in
+	 * the inode bitmap, at which point all IO is done and reuse is fine
+	 * again.
+	 */
+	remove_inode_hash(inode);
 	ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
 	dquot_drop(inode);
 	if (EXT4_I(inode)->jinode) {
@@ -3633,6 +3650,13 @@ int ext4_feature_set_ok(struct super_block *sb, int readonly)
 			 "extents feature\n");
 		return 0;
 	}
+	if (ext4_has_feature_bigalloc(sb) &&
+	    le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) {
+		ext4_msg(sb, KERN_WARNING,
+			 "bad geometry: bigalloc file system with non-zero "
+			 "first_data_block\n");
+		return 0;
+	}
 
 #if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2)
 	if (!readonly && (ext4_has_feature_quota(sb) ||
@@ -5403,6 +5427,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 
 	timer_setup(&sbi->s_err_report, print_daily_error_info, 0);
 	spin_lock_init(&sbi->s_error_lock);
+	mutex_init(&sbi->s_error_notify_mutex);
 	INIT_WORK(&sbi->s_sb_upd_work, update_super_work);
 
 	err = ext4_group_desc_init(sb, es, logical_sb_block, &first_not_zeroed);