Many cleanups and bug fixes in ext4, especially for the fast commit

feature.  Also some performance improvements; in particular, improving
 IOPS and throughput on fast devices running Async Direct I/O by up to
 20% by optimizing jbd2_transaction_committed().
 -----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCAAdFiEEK2m5VNv+CHkogTfJ8vlZVpUNgaMFAmaYiqsACgkQ8vlZVpUN
 gaOWpQf/d6Y9WGyjeC1jOc+vIBxLgL+X0kbzYkkjGTSIZ7mZJS9X4NMMEtqayJ4f
 1zGobcGENc05l4LVxf3uMbDj1aGlHeI9X4GLGaP5s5NcaAl4HKjQ3aFs3MuiJHPj
 Ol2CebXJx+NKt1lkD8PSPGgaTb5zg+SeZifI+OZ1RpkcKmGnkSNa5NkUNAaBh6dl
 5LLXTc2p9NcCwAwDAQSiAJCV35bAZpcp6fwLLaPQ6Eok9HxGcJuYXW2Fict4rbtV
 mXeogXVIo2bkMcfh6tDchDBrFvORYIA7uBVmaG1LgAMrtEnYxnxnEntD0h6j/bzF
 Fl4jjQfd8o2uYto/4eo+iY6Z0haxyQ==
 =rcOo
 -----END PGP SIGNATURE-----

Merge tag 'ext4_for_linus-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "Many cleanups and bug fixes in ext4, especially for the fast commit
  feature.

  Also some performance improvements; in particular, improving IOPS and
  throughput on fast devices running Async Direct I/O by up to 20% by
  optimizing jbd2_transaction_committed()"

* tag 'ext4_for_linus-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (40 commits)
  ext4: make sure the first directory block is not a hole
  ext4: check dot and dotdot of dx_root before making dir indexed
  ext4: sanity check for NULL pointer after ext4_force_shutdown
  jbd2: increase maximum transaction size
  jbd2: drop pointless shrinker batch initialization
  jbd2: avoid infinite transaction commit loop
  jbd2: precompute number of transaction descriptor blocks
  jbd2: make jbd2_journal_get_max_txn_bufs() internal
  jbd2: avoid mount failed when commit block is partial submitted
  ext4: avoid writing unitialized memory to disk in EA inodes
  ext4: don't track ranges in fast_commit if inode has inlined data
  ext4: fix possible tid_t sequence overflows
  ext4: use ext4_update_inode_fsync_trans() helper in inode creation
  ext4: add missing MODULE_DESCRIPTION()
  jbd2: add missing MODULE_DESCRIPTION()
  ext4: use memtostr_pad() for s_volume_name
  jbd2: speed up jbd2_transaction_committed()
  ext4: make ext4_da_map_blocks() buffer_head unaware
  ext4: make ext4_insert_delayed_block() insert multi-blocks
  ext4: factor out a helper to check the cluster allocation state
  ...

fs/buffer.c

@@ -2184,6 +2184,8 @@ static void __block_commit_write(struct folio *folio, size_t from, size_t to)
 	struct buffer_head *bh, *head;
 
 	bh = head = folio_buffers(folio);
+	if (!bh)
+		return;
 	blocksize = bh->b_size;
 
 	block_start = 0;

fs/ext4/block_validity.c

@@ -72,7 +72,7 @@ static int add_system_zone(struct ext4_system_blocks *system_blks,
 {
 	struct ext4_system_zone *new_entry, *entry;
 	struct rb_node **n = &system_blks->root.rb_node, *node;
-	struct rb_node *parent = NULL, *new_node = NULL;
+	struct rb_node *parent = NULL, *new_node;
 
 	while (*n) {
 		parent = *n;

fs/ext4/ext4.h

@@ -1347,7 +1347,7 @@ struct ext4_super_block {
 /*60*/	__le32	s_feature_incompat;	/* incompatible feature set */
 	__le32	s_feature_ro_compat;	/* readonly-compatible feature set */
 /*68*/	__u8	s_uuid[16];		/* 128-bit uuid for volume */
-/*78*/	char	s_volume_name[EXT4_LABEL_MAX];	/* volume name */
+/*78*/	char	s_volume_name[EXT4_LABEL_MAX] __nonstring; /* volume name */
 /*88*/	char	s_last_mounted[64] __nonstring;	/* directory where last mounted */
 /*C8*/	__le32	s_algorithm_usage_bitmap; /* For compression */
 	/*

fs/ext4/extents_status.c

@@ -310,6 +310,8 @@ void ext4_es_find_extent_range(struct inode *inode,
 			       ext4_lblk_t lblk, ext4_lblk_t end,
 			       struct extent_status *es)
 {
+	es->es_lblk = es->es_len = es->es_pblk = 0;
+
 	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
 		return;
 
@@ -2052,34 +2054,49 @@ bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk)
 }
 
 /*
- * ext4_es_insert_delayed_block - adds a delayed block to the extents status
+ * ext4_es_insert_delayed_extent - adds some delayed blocks to the extents
- *                                tree, adding a pending reservation where
+ *                                 status tree, adding a pending reservation
- *                                needed
+ *                                 where needed
  *
  * @inode - file containing the newly added block
- * @lblk - logical block to be added
+ * @lblk - start logical block to be added
- * @allocated - indicates whether a physical cluster has been allocated for
+ * @len - length of blocks to be added
- *              the logical cluster that contains the block
+ * @lclu_allocated/end_allocated - indicates whether a physical cluster has
+ *                                 been allocated for the logical cluster
+ *                                 that contains the start/end block. Note that
+ *                                 end_allocated should always be set to false
+ *                                 if the start and the end block are in the
+ *                                 same cluster
  */
-void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
+void ext4_es_insert_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
-				  bool allocated)
+				   ext4_lblk_t len, bool lclu_allocated,
+				   bool end_allocated)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct extent_status newes;
+	ext4_lblk_t end = lblk + len - 1;
 	int err1 = 0, err2 = 0, err3 = 0;
 	struct extent_status *es1 = NULL;
 	struct extent_status *es2 = NULL;
-	struct pending_reservation *pr = NULL;
+	struct pending_reservation *pr1 = NULL;
+	struct pending_reservation *pr2 = NULL;
 
 	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
 		return;
 
-	es_debug("add [%u/1) delayed to extent status tree of inode %lu\n",
+	es_debug("add [%u/%u) delayed to extent status tree of inode %lu\n",
-		 lblk, inode->i_ino);
+		 lblk, len, inode->i_ino);
+	if (!len)
+		return;
+
+	WARN_ON_ONCE((EXT4_B2C(sbi, lblk) == EXT4_B2C(sbi, end)) &&
+		     end_allocated);
 
 	newes.es_lblk = lblk;
-	newes.es_len = 1;
+	newes.es_len = len;
 	ext4_es_store_pblock_status(&newes, ~0, EXTENT_STATUS_DELAYED);
-	trace_ext4_es_insert_delayed_block(inode, &newes, allocated);
+	trace_ext4_es_insert_delayed_extent(inode, &newes, lclu_allocated,
+					    end_allocated);
 
 	ext4_es_insert_extent_check(inode, &newes);
 
@@ -2088,11 +2105,15 @@ retry:
 		es1 = __es_alloc_extent(true);
 	if ((err1 || err2) && !es2)
 		es2 = __es_alloc_extent(true);
-	if ((err1 || err2 || err3) && allocated && !pr)
+	if (err1 || err2 || err3) {
-		pr = __alloc_pending(true);
+		if (lclu_allocated && !pr1)
+			pr1 = __alloc_pending(true);
+		if (end_allocated && !pr2)
+			pr2 = __alloc_pending(true);
+	}
 	write_lock(&EXT4_I(inode)->i_es_lock);
 
-	err1 = __es_remove_extent(inode, lblk, lblk, NULL, es1);
+	err1 = __es_remove_extent(inode, lblk, end, NULL, es1);
 	if (err1 != 0)
 		goto error;
 	/* Free preallocated extent if it didn't get used. */
@@ -2112,13 +2133,22 @@ retry:
 		es2 = NULL;
 	}
 
-	if (allocated) {
+	if (lclu_allocated) {
-		err3 = __insert_pending(inode, lblk, &pr);
+		err3 = __insert_pending(inode, lblk, &pr1);
 		if (err3 != 0)
 			goto error;
-		if (pr) {
+		if (pr1) {
-			__free_pending(pr);
+			__free_pending(pr1);
-			pr = NULL;
+			pr1 = NULL;
+		}
+	}
+	if (end_allocated) {
+		err3 = __insert_pending(inode, end, &pr2);
+		if (err3 != 0)
+			goto error;
+		if (pr2) {
+			__free_pending(pr2);
+			pr2 = NULL;
 		}
 	}
 error:

fs/ext4/extents_status.h

@@ -249,8 +249,9 @@ extern void ext4_exit_pending(void);
 extern void ext4_init_pending_tree(struct ext4_pending_tree *tree);
 extern void ext4_remove_pending(struct inode *inode, ext4_lblk_t lblk);
 extern bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk);
-extern void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
+extern void ext4_es_insert_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
-					 bool allocated);
+					  ext4_lblk_t len, bool lclu_allocated,
+					  bool end_allocated);
 extern unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk,
 					ext4_lblk_t len);
 extern void ext4_clear_inode_es(struct inode *inode);

fs/ext4/fast_commit.c

@@ -353,7 +353,7 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handl
 		read_unlock(&sbi->s_journal->j_state_lock);
 	}
 	spin_lock(&sbi->s_fc_lock);
-	if (sbi->s_fc_ineligible_tid < tid)
+	if (tid_gt(tid, sbi->s_fc_ineligible_tid))
 		sbi->s_fc_ineligible_tid = tid;
 	spin_unlock(&sbi->s_fc_lock);
 	WARN_ON(reason >= EXT4_FC_REASON_MAX);
@@ -649,6 +649,12 @@ void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t star
 	if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
 		return;
 
+	if (ext4_has_inline_data(inode)) {
+		ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR,
+					handle);
+		return;
+	}
+
 	args.start = start;
 	args.end = end;
 
@@ -1207,7 +1213,7 @@ restart_fc:
 	if (ret == -EALREADY) {
 		/* There was an ongoing commit, check if we need to restart */
 		if (atomic_read(&sbi->s_fc_subtid) <= subtid &&
-			commit_tid > journal->j_commit_sequence)
+		    tid_gt(commit_tid, journal->j_commit_sequence))
 			goto restart_fc;
 		ext4_fc_update_stats(sb, EXT4_FC_STATUS_SKIPPED, 0, 0,
 				commit_tid);
@@ -1282,7 +1288,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid)
 		list_del_init(&iter->i_fc_list);
 		ext4_clear_inode_state(&iter->vfs_inode,
 				       EXT4_STATE_FC_COMMITTING);
-		if (iter->i_sync_tid <= tid)
+		if (tid_geq(tid, iter->i_sync_tid))
 			ext4_fc_reset_inode(&iter->vfs_inode);
 		/* Make sure EXT4_STATE_FC_COMMITTING bit is clear */
 		smp_mb();
@@ -1313,7 +1319,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid)
 	list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
 				&sbi->s_fc_q[FC_Q_MAIN]);
 
-	if (tid >= sbi->s_fc_ineligible_tid) {
+	if (tid_geq(tid, sbi->s_fc_ineligible_tid)) {
 		sbi->s_fc_ineligible_tid = 0;
 		ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
 	}

fs/ext4/ialloc.c

@@ -1336,10 +1336,7 @@ got:
 		}
 	}
 
-	if (ext4_handle_valid(handle)) {
+	ext4_update_inode_fsync_trans(handle, inode, 1);
-		ei->i_sync_tid = handle->h_transaction->t_tid;
-		ei->i_datasync_tid = handle->h_transaction->t_tid;
-	}
 
 	err = ext4_mark_inode_dirty(handle, inode);
 	if (err) {

fs/ext4/inline.c

@@ -1410,7 +1410,11 @@ int ext4_inlinedir_to_tree(struct file *dir_file,
 			hinfo->hash = EXT4_DIRENT_HASH(de);
 			hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de);
 		} else {
-			ext4fs_dirhash(dir, de->name, de->name_len, hinfo);
+			err = ext4fs_dirhash(dir, de->name, de->name_len, hinfo);
+			if (err) {
+				ret = err;
+				goto out;
+			}
 		}
 		if ((hinfo->hash < start_hash) ||
 		    ((hinfo->hash == start_hash) &&

fs/ext4/inode-test.c

@@ -279,4 +279,5 @@ static struct kunit_suite ext4_inode_test_suite = {
 
 kunit_test_suites(&ext4_inode_test_suite);
 
+MODULE_DESCRIPTION("KUnit test of ext4 inode timestamp decoding");
 MODULE_LICENSE("GPL v2");

fs/ext4/inode.c

@@ -453,6 +453,35 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
 }
 #endif /* ES_AGGRESSIVE_TEST */
 
+static int ext4_map_query_blocks(handle_t *handle, struct inode *inode,
+				 struct ext4_map_blocks *map)
+{
+	unsigned int status;
+	int retval;
+
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+		retval = ext4_ext_map_blocks(handle, inode, map, 0);
+	else
+		retval = ext4_ind_map_blocks(handle, inode, map, 0);
+
+	if (retval <= 0)
+		return retval;
+
+	if (unlikely(retval != map->m_len)) {
+		ext4_warning(inode->i_sb,
+			     "ES len assertion failed for inode "
+			     "%lu: retval %d != map->m_len %d",
+			     inode->i_ino, retval, map->m_len);
+		WARN_ON(1);
+	}
+
+	status = map->m_flags & EXT4_MAP_UNWRITTEN ?
+			EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
+	ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+			      map->m_pblk, status);
+	return retval;
+}
+
 /*
  * The ext4_map_blocks() function tries to look up the requested blocks,
  * and returns if the blocks are already mapped.
@@ -1450,9 +1479,9 @@ static int ext4_journalled_write_end(struct file *file,
 }
 
 /*
- * Reserve space for a single cluster
+ * Reserve space for 'nr_resv' clusters
  */
-static int ext4_da_reserve_space(struct inode *inode)
+static int ext4_da_reserve_space(struct inode *inode, int nr_resv)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
@@ -1463,18 +1492,18 @@ static int ext4_da_reserve_space(struct inode *inode)
 	 * us from metadata over-estimation, though we may go over by
 	 * a small amount in the end.  Here we just reserve for data.
 	 */
-	ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1));
+	ret = dquot_reserve_block(inode, EXT4_C2B(sbi, nr_resv));
 	if (ret)
 		return ret;
 
 	spin_lock(&ei->i_block_reservation_lock);
-	if (ext4_claim_free_clusters(sbi, 1, 0)) {
+	if (ext4_claim_free_clusters(sbi, nr_resv, 0)) {
 		spin_unlock(&ei->i_block_reservation_lock);
-		dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
+		dquot_release_reservation_block(inode, EXT4_C2B(sbi, nr_resv));
 		return -ENOSPC;
 	}
-	ei->i_reserved_data_blocks++;
+	ei->i_reserved_data_blocks += nr_resv;
-	trace_ext4_da_reserve_space(inode);
+	trace_ext4_da_reserve_space(inode, nr_resv);
 	spin_unlock(&ei->i_block_reservation_lock);
 
 	return 0;       /* success */
@@ -1621,24 +1650,58 @@ static void ext4_print_free_blocks(struct inode *inode)
 }
 
 /*
- * ext4_insert_delayed_block - adds a delayed block to the extents status
+ * Check whether the cluster containing lblk has been allocated or has
- *                             tree, incrementing the reserved cluster/block
+ * delalloc reservation.
- *                             count or making a pending reservation
- *                             where needed
  *
- * @inode - file containing the newly added block
+ * Returns 0 if the cluster doesn't have either, 1 if it has delalloc
- * @lblk - logical block to be added
+ * reservation, 2 if it's already been allocated, negative error code on
- *
+ * failure.
- * Returns 0 on success, negative error code on failure.
  */
-static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
+static int ext4_clu_alloc_state(struct inode *inode, ext4_lblk_t lblk)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	int ret;
-	bool allocated = false;
+
+	/* Has delalloc reservation? */
+	if (ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk))
+		return 1;
+
+	/* Already been allocated? */
+	if (ext4_es_scan_clu(inode, &ext4_es_is_mapped, lblk))
+		return 2;
+	ret = ext4_clu_mapped(inode, EXT4_B2C(sbi, lblk));
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		return 2;
+
+	return 0;
+}
+
+/*
+ * ext4_insert_delayed_blocks - adds a multiple delayed blocks to the extents
+ *                              status tree, incrementing the reserved
+ *                              cluster/block count or making pending
+ *                              reservations where needed
+ *
+ * @inode - file containing the newly added block
+ * @lblk - start logical block to be added
+ * @len - length of blocks to be added
+ *
+ * Returns 0 on success, negative error code on failure.
+ */
+static int ext4_insert_delayed_blocks(struct inode *inode, ext4_lblk_t lblk,
+				      ext4_lblk_t len)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	int ret;
+	bool lclu_allocated = false;
+	bool end_allocated = false;
+	ext4_lblk_t resv_clu;
+	ext4_lblk_t end = lblk + len - 1;
 
 	/*
-	 * If the cluster containing lblk is shared with a delayed,
+	 * If the cluster containing lblk or end is shared with a delayed,
 	 * written, or unwritten extent in a bigalloc file system, it's
 	 * already been accounted for and does not need to be reserved.
 	 * A pending reservation must be made for the cluster if it's
@@ -1649,81 +1712,84 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
 	 * extents status tree doesn't get a match.
 	 */
 	if (sbi->s_cluster_ratio == 1) {
-		ret = ext4_da_reserve_space(inode);
+		ret = ext4_da_reserve_space(inode, len);
 		if (ret != 0)   /* ENOSPC */
 			return ret;
 	} else {   /* bigalloc */
-		if (!ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk)) {
+		resv_clu = EXT4_B2C(sbi, end) - EXT4_B2C(sbi, lblk) + 1;
-			if (!ext4_es_scan_clu(inode,
+
-					      &ext4_es_is_mapped, lblk)) {
+		ret = ext4_clu_alloc_state(inode, lblk);
-				ret = ext4_clu_mapped(inode,
+		if (ret < 0)
-						      EXT4_B2C(sbi, lblk));
+			return ret;
-				if (ret < 0)
+		if (ret > 0) {
-					return ret;
+			resv_clu--;
-				if (ret == 0) {
+			lclu_allocated = (ret == 2);
-					ret = ext4_da_reserve_space(inode);
+		}
-					if (ret != 0)   /* ENOSPC */
+
-						return ret;
+		if (EXT4_B2C(sbi, lblk) != EXT4_B2C(sbi, end)) {
-				} else {
+			ret = ext4_clu_alloc_state(inode, end);
-					allocated = true;
+			if (ret < 0)
-				}
+				return ret;
-			} else {
+			if (ret > 0) {
-				allocated = true;
+				resv_clu--;
+				end_allocated = (ret == 2);
 			}
 		}
+
+		if (resv_clu) {
+			ret = ext4_da_reserve_space(inode, resv_clu);
+			if (ret != 0)   /* ENOSPC */
+				return ret;
+		}
 	}
 
-	ext4_es_insert_delayed_block(inode, lblk, allocated);
+	ext4_es_insert_delayed_extent(inode, lblk, len, lclu_allocated,
+				      end_allocated);
 	return 0;
 }
 
 /*
- * This function is grabs code from the very beginning of
+ * Looks up the requested blocks and sets the delalloc extent map.
- * ext4_map_blocks, but assumes that the caller is from delayed write
+ * First try to look up for the extent entry that contains the requested
- * time. This function looks up the requested blocks and sets the
+ * blocks in the extent status tree without i_data_sem, then try to look
- * buffer delay bit under the protection of i_data_sem.
+ * up for the ondisk extent mapping with i_data_sem in read mode,
+ * finally hold i_data_sem in write mode, looks up again and add a
+ * delalloc extent entry if it still couldn't find any extent. Pass out
+ * the mapped extent through @map and return 0 on success.
  */
-static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
+static int ext4_da_map_blocks(struct inode *inode, struct ext4_map_blocks *map)
-			      struct ext4_map_blocks *map,
-			      struct buffer_head *bh)
 {
 	struct extent_status es;
 	int retval;
-	sector_t invalid_block = ~((sector_t) 0xffff);
 #ifdef ES_AGGRESSIVE_TEST
 	struct ext4_map_blocks orig_map;
 
 	memcpy(&orig_map, map, sizeof(*map));
 #endif
 
-	if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
-		invalid_block = ~0;
-
 	map->m_flags = 0;
 	ext_debug(inode, "max_blocks %u, logical block %lu\n", map->m_len,
 		  (unsigned long) map->m_lblk);
 
 	/* Lookup extent status tree firstly */
-	if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) {
+	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
+		map->m_len = min_t(unsigned int, map->m_len,
+				   es.es_len - (map->m_lblk - es.es_lblk));
+
 		if (ext4_es_is_hole(&es))
 			goto add_delayed;
 
+found:
 		/*
 		 * Delayed extent could be allocated by fallocate.
 		 * So we need to check it.
 		 */
-		if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) {
+		if (ext4_es_is_delonly(&es)) {
-			map_bh(bh, inode->i_sb, invalid_block);
+			map->m_flags |= EXT4_MAP_DELAYED;
-			set_buffer_new(bh);
-			set_buffer_delay(bh);
 			return 0;
 		}
 
-		map->m_pblk = ext4_es_pblock(&es) + iblock - es.es_lblk;
+		map->m_pblk = ext4_es_pblock(&es) + map->m_lblk - es.es_lblk;
-		retval = es.es_len - (iblock - es.es_lblk);
-		if (retval > map->m_len)
-			retval = map->m_len;
-		map->m_len = retval;
 		if (ext4_es_is_written(&es))
 			map->m_flags |= EXT4_MAP_MAPPED;
 		else if (ext4_es_is_unwritten(&es))
@@ -1734,7 +1800,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 #ifdef ES_AGGRESSIVE_TEST
 		ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0);
 #endif
-		return retval;
+		return 0;
 	}
 
 	/*
@@ -1744,44 +1810,41 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 	down_read(&EXT4_I(inode)->i_data_sem);
 	if (ext4_has_inline_data(inode))
 		retval = 0;
-	else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
-		retval = ext4_ext_map_blocks(NULL, inode, map, 0);
 	else
-		retval = ext4_ind_map_blocks(NULL, inode, map, 0);
+		retval = ext4_map_query_blocks(NULL, inode, map);
-	if (retval < 0) {
-		up_read(&EXT4_I(inode)->i_data_sem);
-		return retval;
-	}
-	if (retval > 0) {
-		unsigned int status;
-
-		if (unlikely(retval != map->m_len)) {
-			ext4_warning(inode->i_sb,
-				     "ES len assertion failed for inode "
-				     "%lu: retval %d != map->m_len %d",
-				     inode->i_ino, retval, map->m_len);
-			WARN_ON(1);
-		}
-
-		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
-				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
-		ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
-				      map->m_pblk, status);
-		up_read(&EXT4_I(inode)->i_data_sem);
-		return retval;
-	}
 	up_read(&EXT4_I(inode)->i_data_sem);
+	if (retval)
+		return retval < 0 ? retval : 0;
 
 add_delayed:
 	down_write(&EXT4_I(inode)->i_data_sem);
-	retval = ext4_insert_delayed_block(inode, map->m_lblk);
+	/*
-	up_write(&EXT4_I(inode)->i_data_sem);
+	 * Page fault path (ext4_page_mkwrite does not take i_rwsem)
-	if (retval)
+	 * and fallocate path (no folio lock) can race. Make sure we
-		return retval;
+	 * lookup the extent status tree here again while i_data_sem
+	 * is held in write mode, before inserting a new da entry in
+	 * the extent status tree.
+	 */
+	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
+		map->m_len = min_t(unsigned int, map->m_len,
+				   es.es_len - (map->m_lblk - es.es_lblk));
+
+		if (!ext4_es_is_hole(&es)) {
+			up_write(&EXT4_I(inode)->i_data_sem);
+			goto found;
+		}
+	} else if (!ext4_has_inline_data(inode)) {
+		retval = ext4_map_query_blocks(NULL, inode, map);
+		if (retval) {
+			up_write(&EXT4_I(inode)->i_data_sem);
+			return retval < 0 ? retval : 0;
+		}
+	}
+
+	map->m_flags |= EXT4_MAP_DELAYED;
+	retval = ext4_insert_delayed_blocks(inode, map->m_lblk, map->m_len);
+	up_write(&EXT4_I(inode)->i_data_sem);
 
-	map_bh(bh, inode->i_sb, invalid_block);
-	set_buffer_new(bh);
-	set_buffer_delay(bh);
 	return retval;
 }
 
@@ -1801,11 +1864,15 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 			   struct buffer_head *bh, int create)
 {
 	struct ext4_map_blocks map;
+	sector_t invalid_block = ~((sector_t) 0xffff);
 	int ret = 0;
 
 	BUG_ON(create == 0);
 	BUG_ON(bh->b_size != inode->i_sb->s_blocksize);
 
+	if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
+		invalid_block = ~0;
+
 	map.m_lblk = iblock;
 	map.m_len = 1;
 
@@ -1814,10 +1881,17 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 	 * preallocated blocks are unmapped but should treated
 	 * the same as allocated blocks.
 	 */
-	ret = ext4_da_map_blocks(inode, iblock, &map, bh);
+	ret = ext4_da_map_blocks(inode, &map);
-	if (ret <= 0)
+	if (ret < 0)
 		return ret;
 
+	if (map.m_flags & EXT4_MAP_DELAYED) {
+		map_bh(bh, inode->i_sb, invalid_block);
+		set_buffer_new(bh);
+		set_buffer_delay(bh);
+		return 0;
+	}
+
 	map_bh(bh, inode->i_sb, map.m_pblk);
 	ext4_update_bh_state(bh, map.m_flags);
 
@@ -2945,6 +3019,11 @@ static int ext4_da_do_write_end(struct address_space *mapping,
 	bool disksize_changed = false;
 	loff_t new_i_size;
 
+	if (unlikely(!folio_buffers(folio))) {
+		folio_unlock(folio);
+		folio_put(folio);
+		return -EIO;
+	}
 	/*
 	 * block_write_end() will mark the inode as dirty with I_DIRTY_PAGES
 	 * flag, which all that's needed to trigger page writeback.

fs/ext4/ioctl.c

@@ -1151,7 +1151,7 @@ static int ext4_ioctl_getlabel(struct ext4_sb_info *sbi, char __user *user_label
 	BUILD_BUG_ON(EXT4_LABEL_MAX >= FSLABEL_MAX);
 
 	lock_buffer(sbi->s_sbh);
-	strscpy_pad(label, sbi->s_es->s_volume_name);
+	memtostr_pad(label, sbi->s_es->s_volume_name);
 	unlock_buffer(sbi->s_sbh);
 
 	if (copy_to_user(user_label, label, sizeof(label)))

fs/ext4/namei.c

@@ -151,10 +151,11 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
 
 		return bh;
 	}
-	if (!bh && (type == INDEX || type == DIRENT_HTREE)) {
+	/* The first directory block must not be a hole. */
+	if (!bh && (type == INDEX || type == DIRENT_HTREE || block == 0)) {
 		ext4_error_inode(inode, func, line, block,
-				 "Directory hole found for htree %s block",
+				 "Directory hole found for htree %s block %u",
-				 (type == INDEX) ? "index" : "leaf");
+				 (type == INDEX) ? "index" : "leaf", block);
 		return ERR_PTR(-EFSCORRUPTED);
 	}
 	if (!bh)
@@ -2172,6 +2173,52 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
 	return err ? err : err2;
 }
 
+static bool ext4_check_dx_root(struct inode *dir, struct dx_root *root)
+{
+	struct fake_dirent *fde;
+	const char *error_msg;
+	unsigned int rlen;
+	unsigned int blocksize = dir->i_sb->s_blocksize;
+	char *blockend = (char *)root + dir->i_sb->s_blocksize;
+
+	fde = &root->dot;
+	if (unlikely(fde->name_len != 1)) {
+		error_msg = "invalid name_len for '.'";
+		goto corrupted;
+	}
+	if (unlikely(strncmp(root->dot_name, ".", fde->name_len))) {
+		error_msg = "invalid name for '.'";
+		goto corrupted;
+	}
+	rlen = ext4_rec_len_from_disk(fde->rec_len, blocksize);
+	if (unlikely((char *)fde + rlen >= blockend)) {
+		error_msg = "invalid rec_len for '.'";
+		goto corrupted;
+	}
+
+	fde = &root->dotdot;
+	if (unlikely(fde->name_len != 2)) {
+		error_msg = "invalid name_len for '..'";
+		goto corrupted;
+	}
+	if (unlikely(strncmp(root->dotdot_name, "..", fde->name_len))) {
+		error_msg = "invalid name for '..'";
+		goto corrupted;
+	}
+	rlen = ext4_rec_len_from_disk(fde->rec_len, blocksize);
+	if (unlikely((char *)fde + rlen >= blockend)) {
+		error_msg = "invalid rec_len for '..'";
+		goto corrupted;
+	}
+
+	return true;
+
+corrupted:
+	EXT4_ERROR_INODE(dir, "Corrupt dir, %s, running e2fsck is recommended",
+			 error_msg);
+	return false;
+}
+
 /*
  * This converts a one block unindexed directory to a 3 block indexed
  * directory, and adds the dentry to the indexed directory.
@@ -2206,17 +2253,17 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
 		brelse(bh);
 		return retval;
 	}
+
 	root = (struct dx_root *) bh->b_data;
+	if (!ext4_check_dx_root(dir, root)) {
+		brelse(bh);
+		return -EFSCORRUPTED;
+	}
 
 	/* The 0th block becomes the root, move the dirents out */
 	fde = &root->dotdot;
 	de = (struct ext4_dir_entry_2 *)((char *)fde +
 		ext4_rec_len_from_disk(fde->rec_len, blocksize));
-	if ((char *) de >= (((char *) root) + blocksize)) {
-		EXT4_ERROR_INODE(dir, "invalid rec_len for '..'");
-		brelse(bh);
-		return -EFSCORRUPTED;
-	}
 	len = ((char *) root) + (blocksize - csum_size) - (char *) de;
 
 	/* Allocate new block for the 0th block's dirents */
@@ -3038,10 +3085,7 @@ bool ext4_empty_dir(struct inode *inode)
 		EXT4_ERROR_INODE(inode, "invalid size");
 		return false;
 	}
-	/* The first directory block must not be a hole,
+	bh = ext4_read_dirblock(inode, 0, EITHER);
-	 * so treat it as DIRENT_HTREE
-	 */
-	bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE);
 	if (IS_ERR(bh))
 		return false;
 
@@ -3483,10 +3527,7 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle,
 		struct ext4_dir_entry_2 *de;
 		unsigned int offset;
 
-		/* The first directory block must not be a hole, so
+		bh = ext4_read_dirblock(inode, 0, EITHER);
-		 * treat it as DIRENT_HTREE
-		 */
-		bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE);
 		if (IS_ERR(bh)) {
 			*retval = PTR_ERR(bh);
 			return NULL;

fs/ext4/super.c

@@ -1327,6 +1327,9 @@ static void ext4_put_super(struct super_block *sb)
 
 	ext4_group_desc_free(sbi);
 	ext4_flex_groups_free(sbi);
+
+	WARN_ON_ONCE(!(sbi->s_mount_state & EXT4_ERROR_FS) &&
+		     percpu_counter_sum(&sbi->s_dirtyclusters_counter));
 	ext4_percpu_param_destroy(sbi);
 #ifdef CONFIG_QUOTA
 	for (int i = 0; i < EXT4_MAXQUOTAS; i++)
@@ -1457,7 +1460,8 @@ static void ext4_destroy_inode(struct inode *inode)
 		dump_stack();
 	}
 
-	if (EXT4_I(inode)->i_reserved_data_blocks)
+	if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ERROR_FS) &&
+	    WARN_ON_ONCE(EXT4_I(inode)->i_reserved_data_blocks))
 		ext4_msg(inode->i_sb, KERN_ERR,
 			 "Inode %lu (%p): i_reserved_data_blocks (%u) not cleared!",
 			 inode->i_ino, EXT4_I(inode),

fs/ext4/xattr.c

@@ -1433,6 +1433,12 @@ retry:
 			goto out;
 
 		memcpy(bh->b_data, buf, csize);
+		/*
+		 * Zero out block tail to avoid writing uninitialized memory
+		 * to disk.
+		 */
+		if (csize < blocksize)
+			memset(bh->b_data + csize, 0, blocksize - csize);
 		set_buffer_uptodate(bh);
 		ext4_handle_dirty_metadata(handle, ea_inode, bh);
 

fs/jbd2/commit.c

@@ -353,7 +353,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	struct buffer_head *descriptor;
 	struct buffer_head **wbuf = journal->j_wbuf;
 	int bufs;
-	int flags;
+	int escape;
 	int err;
 	unsigned long long blocknr;
 	ktime_t start_time;
@@ -660,10 +660,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		 */
 		set_bit(BH_JWrite, &jh2bh(jh)->b_state);
 		JBUFFER_TRACE(jh, "ph3: write metadata");
-		flags = jbd2_journal_write_metadata_buffer(commit_transaction,
+		escape = jbd2_journal_write_metadata_buffer(commit_transaction,
 						jh, &wbuf[bufs], blocknr);
-		if (flags < 0) {
+		if (escape < 0) {
-			jbd2_journal_abort(journal, flags);
+			jbd2_journal_abort(journal, escape);
 			continue;
 		}
 		jbd2_file_log_bh(&io_bufs, wbuf[bufs]);
@@ -672,7 +672,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
                    buffer */
 
 		tag_flag = 0;
-		if (flags & 1)
+		if (escape)
 			tag_flag |= JBD2_FLAG_ESCAPE;
 		if (!first_tag)
 			tag_flag |= JBD2_FLAG_SAME_UUID;
@@ -766,7 +766,7 @@ start_journal_io:
 		if (first_block < journal->j_tail)
 			freed += journal->j_last - journal->j_first;
 		/* Update tail only if we free significant amount of space */
-		if (freed < jbd2_journal_get_max_txn_bufs(journal))
+		if (freed < journal->j_max_transaction_buffers)
 			update_tail = 0;
 	}
 	J_ASSERT(commit_transaction->t_state == T_COMMIT);
@@ -1107,7 +1107,7 @@ restart_loop:
 
 	commit_transaction->t_state = T_COMMIT_CALLBACK;
 	J_ASSERT(commit_transaction == journal->j_committing_transaction);
-	journal->j_commit_sequence = commit_transaction->t_tid;
+	WRITE_ONCE(journal->j_commit_sequence, commit_transaction->t_tid);
 	journal->j_committing_transaction = NULL;
 	commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
 

fs/jbd2/journal.c

@@ -220,19 +220,12 @@ loop:
 		 * so we don't sleep
 		 */
 		DEFINE_WAIT(wait);
-		int should_sleep = 1;
 
 		prepare_to_wait(&journal->j_wait_commit, &wait,
 				TASK_INTERRUPTIBLE);
-		if (journal->j_commit_sequence != journal->j_commit_request)
-			should_sleep = 0;
 		transaction = journal->j_running_transaction;
-		if (transaction && time_after_eq(jiffies,
+		if (transaction == NULL ||
-						transaction->t_expires))
+		    time_before(jiffies, transaction->t_expires)) {
-			should_sleep = 0;
-		if (journal->j_flags & JBD2_UNMOUNT)
-			should_sleep = 0;
-		if (should_sleep) {
 			write_unlock(&journal->j_state_lock);
 			schedule();
 			write_lock(&journal->j_state_lock);
@@ -316,11 +309,8 @@ static void journal_kill_thread(journal_t *journal)
  *
  * Return value:
  *  <0: Error
- * >=0: Finished OK
+ *  =0: Finished OK without escape
- *
+ *  =1: Finished OK with escape
- * On success:
- * Bit 0 set == escape performed on the data
- * Bit 1 set == buffer copy-out performed (kfree the data after IO)
  */
 
 int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
@@ -328,7 +318,6 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 				  struct buffer_head **bh_out,
 				  sector_t blocknr)
 {
-	int need_copy_out = 0;
 	int done_copy_out = 0;
 	int do_escape = 0;
 	char *mapped_data;
@@ -355,7 +344,6 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 	atomic_set(&new_bh->b_count, 1);
 
 	spin_lock(&jh_in->b_state_lock);
-repeat:
 	/*
 	 * If a new transaction has already done a buffer copy-out, then
 	 * we use that version of the data for the commit.
@@ -365,8 +353,8 @@ repeat:
 		new_folio = virt_to_folio(jh_in->b_frozen_data);
 		new_offset = offset_in_folio(new_folio, jh_in->b_frozen_data);
 	} else {
-		new_folio = jh2bh(jh_in)->b_folio;
+		new_folio = bh_in->b_folio;
-		new_offset = offset_in_folio(new_folio, jh2bh(jh_in)->b_data);
+		new_offset = offset_in_folio(new_folio, bh_in->b_data);
 	}
 
 	mapped_data = kmap_local_folio(new_folio, new_offset);
@@ -383,54 +371,52 @@ repeat:
 	/*
 	 * Check for escaping
 	 */
-	if (*((__be32 *)mapped_data) == cpu_to_be32(JBD2_MAGIC_NUMBER)) {
+	if (*((__be32 *)mapped_data) == cpu_to_be32(JBD2_MAGIC_NUMBER))
-		need_copy_out = 1;
 		do_escape = 1;
-	}
 	kunmap_local(mapped_data);
 
 	/*
 	 * Do we need to do a data copy?
 	 */
-	if (need_copy_out && !done_copy_out) {
+	if (do_escape && !done_copy_out) {
 		char *tmp;
 
 		spin_unlock(&jh_in->b_state_lock);
 		tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
 		if (!tmp) {
 			brelse(new_bh);
+			free_buffer_head(new_bh);
 			return -ENOMEM;
 		}
 		spin_lock(&jh_in->b_state_lock);
 		if (jh_in->b_frozen_data) {
 			jbd2_free(tmp, bh_in->b_size);
-			goto repeat;
+			goto copy_done;
 		}
 
 		jh_in->b_frozen_data = tmp;
 		memcpy_from_folio(tmp, new_folio, new_offset, bh_in->b_size);
-
-		new_folio = virt_to_folio(tmp);
-		new_offset = offset_in_folio(new_folio, tmp);
-		done_copy_out = 1;
-
 		/*
 		 * This isn't strictly necessary, as we're using frozen
 		 * data for the escaping, but it keeps consistency with
 		 * b_frozen_data usage.
 		 */
 		jh_in->b_frozen_triggers = jh_in->b_triggers;
+
+copy_done:
+		new_folio = virt_to_folio(jh_in->b_frozen_data);
+		new_offset = offset_in_folio(new_folio, jh_in->b_frozen_data);
+		done_copy_out = 1;
 	}
 
 	/*
 	 * Did we need to do an escaping?  Now we've done all the
 	 * copying, we can finally do so.
+	 * b_frozen_data is from jbd2_alloc() which always provides an
+	 * address from the direct kernels mapping.
 	 */
-	if (do_escape) {
+	if (do_escape)
-		mapped_data = kmap_local_folio(new_folio, new_offset);
+		*((unsigned int *)jh_in->b_frozen_data) = 0;
-		*((unsigned int *)mapped_data) = 0;
-		kunmap_local(mapped_data);
-	}
 
 	folio_set_bh(new_bh, new_folio, new_offset);
 	new_bh->b_size = bh_in->b_size;
@@ -454,7 +440,7 @@ repeat:
 	set_buffer_shadow(bh_in);
 	spin_unlock(&jh_in->b_state_lock);
 
-	return do_escape | (done_copy_out << 1);
+	return do_escape;
 }
 
 /*
@@ -789,17 +775,7 @@ EXPORT_SYMBOL(jbd2_fc_end_commit_fallback);
 /* Return 1 when transaction with given tid has already committed. */
 int jbd2_transaction_committed(journal_t *journal, tid_t tid)
 {
-	int ret = 1;
+	return tid_geq(READ_ONCE(journal->j_commit_sequence), tid);
-
-	read_lock(&journal->j_state_lock);
-	if (journal->j_running_transaction &&
-	    journal->j_running_transaction->t_tid == tid)
-		ret = 0;
-	if (journal->j_committing_transaction &&
-	    journal->j_committing_transaction->t_tid == tid)
-		ret = 0;
-	read_unlock(&journal->j_state_lock);
-	return ret;
 }
 EXPORT_SYMBOL(jbd2_transaction_committed);
 
@@ -1451,6 +1427,48 @@ static int journal_revoke_records_per_block(journal_t *journal)
 	return space / record_size;
 }
 
+static int jbd2_journal_get_max_txn_bufs(journal_t *journal)
+{
+	return (journal->j_total_len - journal->j_fc_wbufsize) / 3;
+}
+
+/*
+ * Base amount of descriptor blocks we reserve for each transaction.
+ */
+static int jbd2_descriptor_blocks_per_trans(journal_t *journal)
+{
+	int tag_space = journal->j_blocksize - sizeof(journal_header_t);
+	int tags_per_block;
+
+	/* Subtract UUID */
+	tag_space -= 16;
+	if (jbd2_journal_has_csum_v2or3(journal))
+		tag_space -= sizeof(struct jbd2_journal_block_tail);
+	/* Commit code leaves a slack space of 16 bytes at the end of block */
+	tags_per_block = (tag_space - 16) / journal_tag_bytes(journal);
+	/*
+	 * Revoke descriptors are accounted separately so we need to reserve
+	 * space for commit block and normal transaction descriptor blocks.
+	 */
+	return 1 + DIV_ROUND_UP(jbd2_journal_get_max_txn_bufs(journal),
+				tags_per_block);
+}
+
+/*
+ * Initialize number of blocks each transaction reserves for its bookkeeping
+ * and maximum number of blocks a transaction can use. This needs to be called
+ * after the journal size and the fastcommit area size are initialized.
+ */
+static void jbd2_journal_init_transaction_limits(journal_t *journal)
+{
+	journal->j_revoke_records_per_block =
+				journal_revoke_records_per_block(journal);
+	journal->j_transaction_overhead_buffers =
+				jbd2_descriptor_blocks_per_trans(journal);
+	journal->j_max_transaction_buffers =
+				jbd2_journal_get_max_txn_bufs(journal);
+}
+
 /*
  * Load the on-disk journal superblock and read the key fields into the
  * journal_t.
@@ -1492,8 +1510,8 @@ static int journal_load_superblock(journal_t *journal)
 	if (jbd2_journal_has_csum_v2or3(journal))
 		journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid,
 						   sizeof(sb->s_uuid));
-	journal->j_revoke_records_per_block =
+	/* After journal features are set, we can compute transaction limits */
-				journal_revoke_records_per_block(journal);
+	jbd2_journal_init_transaction_limits(journal);
 
 	if (jbd2_has_feature_fast_commit(journal)) {
 		journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
@@ -1599,7 +1617,6 @@ static journal_t *journal_init_common(struct block_device *bdev,
 
 	journal->j_shrinker->scan_objects = jbd2_journal_shrink_scan;
 	journal->j_shrinker->count_objects = jbd2_journal_shrink_count;
-	journal->j_shrinker->batch = journal->j_max_transaction_buffers;
 	journal->j_shrinker->private_data = journal;
 
 	shrinker_register(journal->j_shrinker);
@@ -1743,8 +1760,6 @@ static int journal_reset(journal_t *journal)
 	journal->j_commit_sequence = journal->j_transaction_sequence - 1;
 	journal->j_commit_request = journal->j_commit_sequence;
 
-	journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal);
-
 	/*
 	 * Now that journal recovery is done, turn fast commits off here. This
 	 * way, if fast commit was enabled before the crash but if now FS has
@@ -2285,8 +2300,6 @@ jbd2_journal_initialize_fast_commit(journal_t *journal)
 	journal->j_fc_first = journal->j_last + 1;
 	journal->j_fc_off = 0;
 	journal->j_free = journal->j_last - journal->j_first;
-	journal->j_max_transaction_buffers =
-		jbd2_journal_get_max_txn_bufs(journal);
 
 	return 0;
 }
@@ -2374,8 +2387,7 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat,
 	sb->s_feature_ro_compat |= cpu_to_be32(ro);
 	sb->s_feature_incompat  |= cpu_to_be32(incompat);
 	unlock_buffer(journal->j_sb_buffer);
-	journal->j_revoke_records_per_block =
+	jbd2_journal_init_transaction_limits(journal);
-				journal_revoke_records_per_block(journal);
 
 	return 1;
 #undef COMPAT_FEATURE_ON
@@ -2406,8 +2418,7 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat,
 	sb->s_feature_compat    &= ~cpu_to_be32(compat);
 	sb->s_feature_ro_compat &= ~cpu_to_be32(ro);
 	sb->s_feature_incompat  &= ~cpu_to_be32(incompat);
-	journal->j_revoke_records_per_block =
+	jbd2_journal_init_transaction_limits(journal);
-				journal_revoke_records_per_block(journal);
 }
 EXPORT_SYMBOL(jbd2_journal_clear_features);
 

fs/jbd2/recovery.c

@@ -19,6 +19,7 @@
 #include <linux/errno.h>
 #include <linux/crc32.h>
 #include <linux/blkdev.h>
+#include <linux/string_choices.h>
 #endif
 
 /*
@@ -374,7 +375,7 @@ int jbd2_journal_skip_recovery(journal_t *journal)
 			be32_to_cpu(journal->j_superblock->s_sequence);
 		jbd2_debug(1,
 			  "JBD2: ignoring %d transaction%s from the journal.\n",
-			  dropped, (dropped == 1) ? "" : "s");
+			  dropped, str_plural(dropped));
 #endif
 		journal->j_transaction_sequence = ++info.end_transaction;
 		journal->j_head = info.head_block;
@@ -443,6 +444,27 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
 	return provided == cpu_to_be32(calculated);
 }
 
+static bool jbd2_commit_block_csum_verify_partial(journal_t *j, void *buf)
+{
+	struct commit_header *h;
+	__be32 provided;
+	__u32 calculated;
+	void *tmpbuf;
+
+	tmpbuf = kzalloc(j->j_blocksize, GFP_KERNEL);
+	if (!tmpbuf)
+		return false;
+
+	memcpy(tmpbuf, buf, sizeof(struct commit_header));
+	h = tmpbuf;
+	provided = h->h_chksum[0];
+	h->h_chksum[0] = 0;
+	calculated = jbd2_chksum(j, j->j_csum_seed, tmpbuf, j->j_blocksize);
+	kfree(tmpbuf);
+
+	return provided == cpu_to_be32(calculated);
+}
+
 static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag,
 				      journal_block_tag3_t *tag3,
 				      void *buf, __u32 sequence)
@@ -810,6 +832,13 @@ static int do_one_pass(journal_t *journal,
 			if (pass == PASS_SCAN &&
 			    !jbd2_commit_block_csum_verify(journal,
 							   bh->b_data)) {
+				if (jbd2_commit_block_csum_verify_partial(
+								  journal,
+								  bh->b_data)) {
+					pr_notice("JBD2: Find incomplete commit block in transaction %u block %lu\n",
+						  next_commit_ID, next_log_block);
+					goto chksum_ok;
+				}
 			chksum_error:
 				if (commit_time < last_trans_commit_time)
 					goto ignore_crc_mismatch;
@@ -824,6 +853,7 @@ static int do_one_pass(journal_t *journal,
 				}
 			}
 			if (pass == PASS_SCAN) {
+			chksum_ok:
 				last_trans_commit_time = commit_time;
 				head_block = next_log_block;
 			}
@@ -843,6 +873,7 @@ static int do_one_pass(journal_t *journal,
 					  next_log_block);
 				need_check_commit_time = true;
 			}
+
 			/* If we aren't in the REVOKE pass, then we can
 			 * just skip over this block. */
 			if (pass != PASS_REVOKE) {

fs/jbd2/transaction.c

@@ -62,28 +62,6 @@ void jbd2_journal_free_transaction(transaction_t *transaction)
 	kmem_cache_free(transaction_cache, transaction);
 }
 
-/*
- * Base amount of descriptor blocks we reserve for each transaction.
- */
-static int jbd2_descriptor_blocks_per_trans(journal_t *journal)
-{
-	int tag_space = journal->j_blocksize - sizeof(journal_header_t);
-	int tags_per_block;
-
-	/* Subtract UUID */
-	tag_space -= 16;
-	if (jbd2_journal_has_csum_v2or3(journal))
-		tag_space -= sizeof(struct jbd2_journal_block_tail);
-	/* Commit code leaves a slack space of 16 bytes at the end of block */
-	tags_per_block = (tag_space - 16) / journal_tag_bytes(journal);
-	/*
-	 * Revoke descriptors are accounted separately so we need to reserve
-	 * space for commit block and normal transaction descriptor blocks.
-	 */
-	return 1 + DIV_ROUND_UP(journal->j_max_transaction_buffers,
-				tags_per_block);
-}
-
 /*
  * jbd2_get_transaction: obtain a new transaction_t object.
  *
@@ -109,7 +87,7 @@ static void jbd2_get_transaction(journal_t *journal,
 	transaction->t_expires = jiffies + journal->j_commit_interval;
 	atomic_set(&transaction->t_updates, 0);
 	atomic_set(&transaction->t_outstanding_credits,
-		   jbd2_descriptor_blocks_per_trans(journal) +
+		   journal->j_transaction_overhead_buffers +
 		   atomic_read(&journal->j_reserved_credits));
 	atomic_set(&transaction->t_outstanding_revokes, 0);
 	atomic_set(&transaction->t_handle_count, 0);
@@ -213,6 +191,13 @@ static void sub_reserved_credits(journal_t *journal, int blocks)
 	wake_up(&journal->j_wait_reserved);
 }
 
+/* Maximum number of blocks for user transaction payload */
+static int jbd2_max_user_trans_buffers(journal_t *journal)
+{
+	return journal->j_max_transaction_buffers -
+				journal->j_transaction_overhead_buffers;
+}
+
 /*
  * Wait until we can add credits for handle to the running transaction.  Called
  * with j_state_lock held for reading. Returns 0 if handle joined the running
@@ -262,12 +247,12 @@ __must_hold(&journal->j_state_lock)
 		 * big to fit this handle? Wait until reserved credits are freed.
 		 */
 		if (atomic_read(&journal->j_reserved_credits) + total >
-		    journal->j_max_transaction_buffers) {
+		    jbd2_max_user_trans_buffers(journal)) {
 			read_unlock(&journal->j_state_lock);
 			jbd2_might_wait_for_commit(journal);
 			wait_event(journal->j_wait_reserved,
 				   atomic_read(&journal->j_reserved_credits) + total <=
-				   journal->j_max_transaction_buffers);
+				   jbd2_max_user_trans_buffers(journal));
 			__acquire(&journal->j_state_lock); /* fake out sparse */
 			return 1;
 		}
@@ -307,14 +292,14 @@ __must_hold(&journal->j_state_lock)
 
 	needed = atomic_add_return(rsv_blocks, &journal->j_reserved_credits);
 	/* We allow at most half of a transaction to be reserved */
-	if (needed > journal->j_max_transaction_buffers / 2) {
+	if (needed > jbd2_max_user_trans_buffers(journal) / 2) {
 		sub_reserved_credits(journal, rsv_blocks);
 		atomic_sub(total, &t->t_outstanding_credits);
 		read_unlock(&journal->j_state_lock);
 		jbd2_might_wait_for_commit(journal);
 		wait_event(journal->j_wait_reserved,
 			 atomic_read(&journal->j_reserved_credits) + rsv_blocks
-			 <= journal->j_max_transaction_buffers / 2);
+			 <= jbd2_max_user_trans_buffers(journal) / 2);
 		__acquire(&journal->j_state_lock); /* fake out sparse */
 		return 1;
 	}
@@ -344,12 +329,12 @@ static int start_this_handle(journal_t *journal, handle_t *handle,
 	 * size and limit the number of total credits to not exceed maximum
 	 * transaction size per operation.
 	 */
-	if ((rsv_blocks > journal->j_max_transaction_buffers / 2) ||
+	if (rsv_blocks > jbd2_max_user_trans_buffers(journal) / 2 ||
-	    (rsv_blocks + blocks > journal->j_max_transaction_buffers)) {
+	    rsv_blocks + blocks > jbd2_max_user_trans_buffers(journal)) {
 		printk(KERN_ERR "JBD2: %s wants too many credits "
 		       "credits:%d rsv_credits:%d max:%d\n",
 		       current->comm, blocks, rsv_blocks,
-		       journal->j_max_transaction_buffers);
+		       jbd2_max_user_trans_buffers(journal));
 		WARN_ON(1);
 		return -ENOSPC;
 	}

include/linux/jbd2.h

@@ -1085,6 +1085,13 @@ struct journal_s
 	 */
 	int			j_revoke_records_per_block;
 
+	/**
+	 * @j_transaction_overhead:
+	 *
+	 * Number of blocks each transaction needs for its own bookkeeping
+	 */
+	int			j_transaction_overhead_buffers;
+
 	/**
 	 * @j_commit_interval:
 	 *
@@ -1660,11 +1667,6 @@ int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
 int jbd2_fc_wait_bufs(journal_t *journal, int num_blks);
 int jbd2_fc_release_bufs(journal_t *journal);
 
-static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal)
-{
-	return (journal->j_total_len - journal->j_fc_wbufsize) / 4;
-}
-
 /*
  * is_journal_abort
  *

include/trace/events/ext4.h

@@ -1246,14 +1246,15 @@ TRACE_EVENT(ext4_da_update_reserve_space,
 );
 
 TRACE_EVENT(ext4_da_reserve_space,
-	TP_PROTO(struct inode *inode),
+	TP_PROTO(struct inode *inode, int nr_resv),
 
-	TP_ARGS(inode),
+	TP_ARGS(inode, nr_resv),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
 		__field(	__u64,	i_blocks		)
+		__field(	int,	reserve_blocks		)
 		__field(	int,	reserved_data_blocks	)
 		__field(	__u16,  mode			)
 	),
@@ -1262,16 +1263,17 @@ TRACE_EVENT(ext4_da_reserve_space,
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
 		__entry->i_blocks = inode->i_blocks;
+		__entry->reserve_blocks = nr_resv;
 		__entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
 		__entry->mode	= inode->i_mode;
 	),
 
-	TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu "
+	TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu reserve_blocks %d"
 		  "reserved_data_blocks %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
 		  __entry->mode, __entry->i_blocks,
-		  __entry->reserved_data_blocks)
+		  __entry->reserve_blocks, __entry->reserved_data_blocks)
 );
 
 TRACE_EVENT(ext4_da_release_space,
@@ -2478,11 +2480,11 @@ TRACE_EVENT(ext4_es_shrink,
 		  __entry->scan_time, __entry->nr_skipped, __entry->retried)
 );
 
-TRACE_EVENT(ext4_es_insert_delayed_block,
+TRACE_EVENT(ext4_es_insert_delayed_extent,
 	TP_PROTO(struct inode *inode, struct extent_status *es,
-		 bool allocated),
+		 bool lclu_allocated, bool end_allocated),
 
-	TP_ARGS(inode, es, allocated),
+	TP_ARGS(inode, es, lclu_allocated, end_allocated),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,		dev		)
@@ -2491,7 +2493,8 @@ TRACE_EVENT(ext4_es_insert_delayed_block,
 		__field(	ext4_lblk_t,	len		)
 		__field(	ext4_fsblk_t,	pblk		)
 		__field(	char,		status		)
-		__field(	bool,		allocated	)
+		__field(	bool,		lclu_allocated	)
+		__field(	bool,		end_allocated	)
 	),
 
 	TP_fast_assign(
@@ -2501,16 +2504,17 @@ TRACE_EVENT(ext4_es_insert_delayed_block,
 		__entry->len		= es->es_len;
 		__entry->pblk		= ext4_es_show_pblock(es);
 		__entry->status		= ext4_es_status(es);
-		__entry->allocated	= allocated;
+		__entry->lclu_allocated	= lclu_allocated;
+		__entry->end_allocated	= end_allocated;
 	),
 
 	TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s "
-		  "allocated %d",
+		  "allocated %d %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
 		  __entry->lblk, __entry->len,
 		  __entry->pblk, show_extent_status(__entry->status),
-		  __entry->allocated)
+		  __entry->lclu_allocated, __entry->end_allocated)
 );
 
 /* fsmap traces */