Merge tag 'ext4_for_linus-6.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "New features and improvements for the ext4 file system:
   - Optimize online defragmentation by using folios instead of
     individual buffer heads
   - Improve error codes stored in the superblock when the journal
     aborts
   - Minor cleanups and clarifications in ext4_map_blocks()
   - Add documentation of the casefold and encrypt flags
   - Add support for file systems with a blocksize greater than the
     pagesize
   - Improve performance by enabling the caching the fact that an inode
     does not have a Posix ACL

  Various Bug Fixes:
   - Fix false positive complaints from smatch
   - Fix error code which is returned by ext4fs_dirhash() when Siphash
     is used without the encryption key
   - Fix races when writing to inline data files which could trigger a
     BUG
   - Fix potential NULL dereference when there is an corrupt file system
     with an extended attribute value stored in a inode
   - Fix false positive lockdep report when syzbot uses ext4 and ocfs2
     together
   - Fix false positive reported by DEPT by adjusting lock annotation
   - Avoid a potential BUG_ON in jbd2 when a file system is massively
     corrupted
   - Fix a WARN_ON when superblock is corrupted with a non-NULL
     terminated mount options field
   - Add check if the userspace passes in a non-NULL terminated mount
     options field to EXT4_IOC_SET_TUNE_SB_PARAM
   - Fix a potential journal checksum failure whena file system is
     copied while it is mounted read-only
   - Fix a potential potential orphan file tracking error which only
     showed on 32-bit systems
   - Fix assertion checks in mballoc (which have to be explicitly enbled
     by manually enabling AGGRESSIVE_CHECKS and recompiling)
   - Avoid complaining about overly large orphan files created by mke2fs
     with with file systems with a 64k block size"

* tag 'ext4_for_linus-6.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (58 commits)
  ext4: mark inodes without acls in __ext4_iget()
  ext4: enable block size larger than page size
  ext4: add checks for large folio incompatibilities when BS > PS
  ext4: support verifying data from large folios with fs-verity
  ext4: make data=journal support large block size
  ext4: support large block size in __ext4_block_zero_page_range()
  ext4: support large block size in mpage_prepare_extent_to_map()
  ext4: support large block size in mpage_map_and_submit_buffers()
  ext4: support large block size in ext4_block_write_begin()
  ext4: support large block size in ext4_mpage_readpages()
  ext4: rename 'page' references to 'folio' in multi-block allocator
  ext4: prepare buddy cache inode for BS > PS with large folios
  ext4: support large block size in ext4_mb_init_cache()
  ext4: support large block size in ext4_mb_get_buddy_page_lock()
  ext4: support large block size in ext4_mb_load_buddy_gfp()
  ext4: add EXT4_LBLK_TO_PG and EXT4_PG_TO_LBLK for block/page conversion
  ext4: add EXT4_LBLK_TO_B macro for logical block to bytes conversion
  ext4: support large block size in ext4_readdir()
  ext4: support large block size in ext4_calculate_overhead()
  ext4: introduce s_min_folio_order for future BS > PS support
  ...

1 files changed, 25 insertions, 6 deletions

diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 31dc0496f8d0..e04fbf10fe4f 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -235,6 +235,13 @@ static inline ext4_lblk_t ext4_es_end(struct extent_status *es)
 	return es->es_lblk + es->es_len - 1;
 }
 
+static inline void ext4_es_inc_seq(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	WRITE_ONCE(ei->i_es_seq, ei->i_es_seq + 1);
+}
+
 /*
  * search through the tree for an delayed extent with a given offset.  If
  * it can't be found, try to find next extent.
@@ -906,7 +913,6 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 	newes.es_lblk = lblk;
 	newes.es_len = len;
 	ext4_es_store_pblock_status(&newes, pblk, status);
-	trace_ext4_es_insert_extent(inode, &newes);
 
 	ext4_es_insert_extent_check(inode, &newes);
 
@@ -955,6 +961,11 @@ retry:
 		}
 		pending = err3;
 	}
+	/*
+	 * TODO: For cache on-disk extents, there is no need to increment
+	 * the sequence counter, this requires future optimization.
+	 */
+	ext4_es_inc_seq(inode);
 error:
 	write_unlock(&EXT4_I(inode)->i_es_lock);
 	/*
@@ -981,6 +992,7 @@ error:
 	if (err1 || err2 || err3 < 0)
 		goto retry;
 
+	trace_ext4_es_insert_extent(inode, &newes);
 	ext4_es_print_tree(inode);
 	return;
 }
@@ -1027,8 +1039,8 @@ void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
  * Return: 1 on found, 0 on not
  */
 int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
-			  ext4_lblk_t *next_lblk,
-			  struct extent_status *es)
+			  ext4_lblk_t *next_lblk, struct extent_status *es,
+			  u64 *pseq)
 {
 	struct ext4_es_tree *tree;
 	struct ext4_es_stats *stats;
@@ -1087,6 +1099,8 @@ out:
 			} else
 				*next_lblk = 0;
 		}
+		if (pseq)
+			*pseq = EXT4_I(inode)->i_es_seq;
 	} else {
 		percpu_counter_inc(&stats->es_stats_cache_misses);
 	}
@@ -1550,7 +1564,6 @@ void ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
 	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
 		return;
 
-	trace_ext4_es_remove_extent(inode, lblk, len);
 	es_debug("remove [%u/%u) from extent status tree of inode %lu\n",
 		 lblk, len, inode->i_ino);
 
@@ -1570,16 +1583,21 @@ retry:
 	 */
 	write_lock(&EXT4_I(inode)->i_es_lock);
 	err = __es_remove_extent(inode, lblk, end, &reserved, es);
+	if (err)
+		goto error;
 	/* Free preallocated extent if it didn't get used. */
 	if (es) {
 		if (!es->es_len)
 			__es_free_extent(es);
 		es = NULL;
 	}
+	ext4_es_inc_seq(inode);
+error:
 	write_unlock(&EXT4_I(inode)->i_es_lock);
 	if (err)
 		goto retry;
 
+	trace_ext4_es_remove_extent(inode, lblk, len);
 	ext4_es_print_tree(inode);
 	ext4_da_release_space(inode, reserved);
 }
@@ -2140,8 +2158,6 @@ void ext4_es_insert_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
 	newes.es_lblk = lblk;
 	newes.es_len = len;
 	ext4_es_store_pblock_status(&newes, ~0, EXTENT_STATUS_DELAYED);
-	trace_ext4_es_insert_delayed_extent(inode, &newes, lclu_allocated,
-					    end_allocated);
 
 	ext4_es_insert_extent_check(inode, &newes);
 
@@ -2196,11 +2212,14 @@ retry:
 			pr2 = NULL;
 		}
 	}
+	ext4_es_inc_seq(inode);
 error:
 	write_unlock(&EXT4_I(inode)->i_es_lock);
 	if (err1 || err2 || err3 < 0)
 		goto retry;
 
+	trace_ext4_es_insert_delayed_extent(inode, &newes, lclu_allocated,
+					    end_allocated);
 	ext4_es_print_tree(inode);
 	ext4_print_pending_tree(inode);
 	return;