Merge tag 'ext4_for_linus-6.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "New ext4 features:

   - Add support so tune2fs can modify/update the superblock using an
     ioctl, without needing write access to the block device

   - Add support for 32-bit reserved uid's and gid's

  Bug fixes:

   - Fix potential warnings and other failures caused by corrupted /
     fuzzed file systems

   - Fail unaligned direct I/O write with EINVAL instead of silently
     falling back to buffered I/O

   - Correectly handle fsmap queries for metadata mappings

   - Avoid journal stalls caused by writeback throttling

   - Add some missing GFP_NOFAIL flags to avoid potential deadlocks
     under extremem memory pressure

  Cleanups:

   - Remove obsolete EXT3 Kconfigs"

* tag 'ext4_for_linus-6.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: fix checks for orphan inodes
  ext4: validate ea_ino and size in check_xattrs
  ext4: guard against EA inode refcount underflow in xattr update
  ext4: implemet new ioctls to set and get superblock parameters
  ext4: add support for 32-bit default reserved uid and gid values
  ext4: avoid potential buffer over-read in parse_apply_sb_mount_options()
  ext4: fix an off-by-one issue during moving extents
  ext4: increase i_disksize to offset + len in ext4_update_disksize_before_punch()
  ext4: verify orphan file size is not too big
  ext4: fail unaligned direct IO write with EINVAL
  ext4: correctly handle queries for metadata mappings
  ext4: increase IO priority of fastcommit
  ext4: remove obsolete EXT3 config options
  jbd2: increase IO priority of checkpoint
  ext4: fix potential null deref in ext4_mb_init()
  ext4: add ext4_sb_bread_nofail() helper function for ext4_free_branches()
  ext4: replace min/max nesting with clamp()
  fs: ext4: change GFP_KERNEL to GFP_NOFS to avoid deadlock

Author: torvalds

fs/ext4/Kconfig

@@ -1,31 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-# Ext3 configs are here for backward compatibility with old configs which may
-# have EXT3_FS set but not EXT4_FS set and thus would result in non-bootable
-# kernels after the removal of ext3 driver.
-config EXT3_FS
-	tristate "The Extended 3 (ext3) filesystem"
-	select EXT4_FS
-	help
-	  This config option is here only for backward compatibility. ext3
-	  filesystem is now handled by the ext4 driver.
-
-config EXT3_FS_POSIX_ACL
-	bool "Ext3 POSIX Access Control Lists"
-	depends on EXT3_FS
-	select EXT4_FS_POSIX_ACL
-	select FS_POSIX_ACL
-	help
-	  This config option is here only for backward compatibility. ext3
-	  filesystem is now handled by the ext4 driver.
-
-config EXT3_FS_SECURITY
-	bool "Ext3 Security Labels"
-	depends on EXT3_FS
-	select EXT4_FS_SECURITY
-	help
-	  This config option is here only for backward compatibility. ext3
-	  filesystem is now handled by the ext4 driver.
-
 config EXT4_FS
 	tristate "The Extended 4 (ext4) filesystem"
 	select BUFFER_HEAD

fs/ext4/ext4.h

@@ -1450,7 +1450,9 @@ struct ext4_super_block {
 	__le16  s_encoding;		/* Filename charset encoding */
 	__le16  s_encoding_flags;	/* Filename charset encoding flags */
 	__le32  s_orphan_file_inum;	/* Inode for tracking orphan inodes */
-	__le32	s_reserved[94];		/* Padding to the end of the block */
+	__le16	s_def_resuid_hi;
+	__le16	s_def_resgid_hi;
+	__le32	s_reserved[93];		/* Padding to the end of the block */
 	__le32	s_checksum;		/* crc32c(superblock) */
 };
 
@@ -1820,6 +1822,18 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 		 ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
 }
 
+static inline int ext4_get_resuid(struct ext4_super_block *es)
+{
+	return le16_to_cpu(es->s_def_resuid) |
+		le16_to_cpu(es->s_def_resuid_hi) << 16;
+}
+
+static inline int ext4_get_resgid(struct ext4_super_block *es)
+{
+	return le16_to_cpu(es->s_def_resgid) |
+		le16_to_cpu(es->s_def_resgid_hi) << 16;
+}
+
 /*
  * Returns: sbi->field[index]
  * Used to access an array element from the following sbi fields which require
@@ -1989,6 +2003,16 @@ static inline bool ext4_verity_in_progress(struct inode *inode)
 
 #define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
 
+/*
+ * Check whether the inode is tracked as orphan (either in orphan file or
+ * orphan list).
+ */
+static inline bool ext4_inode_orphan_tracked(struct inode *inode)
+{
+	return ext4_test_inode_state(inode, EXT4_STATE_ORPHAN_FILE) ||
+		!list_empty(&EXT4_I(inode)->i_orphan);
+}
+
 /*
  * Codes for operating systems
  */
@@ -3142,6 +3166,8 @@ extern struct buffer_head *ext4_sb_bread(struct super_block *sb,
 					 sector_t block, blk_opf_t op_flags);
 extern struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb,
 						   sector_t block);
+extern struct buffer_head *ext4_sb_bread_nofail(struct super_block *sb,
+						sector_t block);
 extern void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
 				bh_end_io_t *end_io, bool simu_fail);
 extern int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,

fs/ext4/fast_commit.c

@@ -663,7 +663,7 @@ void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t star
 
 static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail)
 {
-	blk_opf_t write_flags = REQ_SYNC;
+	blk_opf_t write_flags = JBD2_JOURNAL_REQ_FLAGS;
 	struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh;
 
 	/* Add REQ_FUA | REQ_PREFLUSH only its tail */

fs/ext4/file.c

@@ -354,7 +354,7 @@ static void ext4_inode_extension_cleanup(struct inode *inode, bool need_trunc)
 	 * to cleanup the orphan list in ext4_handle_inode_extension(). Do it
 	 * now.
 	 */
-	if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) {
+	if (ext4_inode_orphan_tracked(inode) && inode->i_nlink) {
 		handle_t *handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
 
 		if (IS_ERR(handle)) {

fs/ext4/fsmap.c

@@ -74,7 +74,8 @@ static int ext4_getfsmap_dev_compare(const void *p1, const void *p2)
 static bool ext4_getfsmap_rec_before_low_key(struct ext4_getfsmap_info *info,
 					     struct ext4_fsmap *rec)
 {
-	return rec->fmr_physical < info->gfi_low.fmr_physical;
+	return rec->fmr_physical + rec->fmr_length <=
+	       info->gfi_low.fmr_physical;
 }
 
 /*
@@ -200,15 +201,18 @@ static int ext4_getfsmap_meta_helper(struct super_block *sb,
 			  ext4_group_first_block_no(sb, agno));
 	fs_end = fs_start + EXT4_C2B(sbi, len);
 
-	/* Return relevant extents from the meta_list */
+	/*
+	 * Return relevant extents from the meta_list. We emit all extents that
+	 * partially/fully overlap with the query range
+	 */
 	list_for_each_entry_safe(p, tmp, &info->gfi_meta_list, fmr_list) {
-		if (p->fmr_physical < info->gfi_next_fsblk) {
+		if (p->fmr_physical + p->fmr_length <= info->gfi_next_fsblk) {
 			list_del(&p->fmr_list);
 			kfree(p);
 			continue;
 		}
-		if (p->fmr_physical <= fs_start ||
-		    p->fmr_physical + p->fmr_length <= fs_end) {
+		if (p->fmr_physical <= fs_end &&
+		    p->fmr_physical + p->fmr_length > fs_start) {
 			/* Emit the retained free extent record if present */
 			if (info->gfi_lastfree.fmr_owner) {
 				error = ext4_getfsmap_helper(sb, info,

fs/ext4/indirect.c

@@ -1025,7 +1025,7 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
 			}
 
 			/* Go read the buffer for the next level down */
-			bh = ext4_sb_bread(inode->i_sb, nr, 0);
+			bh = ext4_sb_bread_nofail(inode->i_sb, nr);
 
 			/*
 			 * A read failure? Report error and clear slot

fs/ext4/inode.c

@@ -3872,47 +3872,12 @@ static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset,
 	return ret;
 }
 
-static inline bool ext4_want_directio_fallback(unsigned flags, ssize_t written)
-{
-	/* must be a directio to fall back to buffered */
-	if ((flags & (IOMAP_WRITE | IOMAP_DIRECT)) !=
-		    (IOMAP_WRITE | IOMAP_DIRECT))
-		return false;
-
-	/* atomic writes are all-or-nothing */
-	if (flags & IOMAP_ATOMIC)
-		return false;
-
-	/* can only try again if we wrote nothing */
-	return written == 0;
-}
-
-static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
-			  ssize_t written, unsigned flags, struct iomap *iomap)
-{
-	/*
-	 * Check to see whether an error occurred while writing out the data to
-	 * the allocated blocks. If so, return the magic error code for
-	 * non-atomic write so that we fallback to buffered I/O and attempt to
-	 * complete the remainder of the I/O.
-	 * For non-atomic writes, any blocks that may have been
-	 * allocated in preparation for the direct I/O will be reused during
-	 * buffered I/O. For atomic write, we never fallback to buffered-io.
-	 */
-	if (ext4_want_directio_fallback(flags, written))
-		return -ENOTBLK;
-
-	return 0;
-}
-
 const struct iomap_ops ext4_iomap_ops = {
 	.iomap_begin		= ext4_iomap_begin,
-	.iomap_end		= ext4_iomap_end,
 };
 
 const struct iomap_ops ext4_iomap_overwrite_ops = {
 	.iomap_begin		= ext4_iomap_overwrite_begin,
-	.iomap_end		= ext4_iomap_end,
 };
 
 static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
@@ -4287,7 +4252,11 @@ int ext4_can_truncate(struct inode *inode)
  * We have to make sure i_disksize gets properly updated before we truncate
  * page cache due to hole punching or zero range. Otherwise i_disksize update
  * can get lost as it may have been postponed to submission of writeback but
- * that will never happen after we truncate page cache.
+ * that will never happen if we remove the folio containing i_size from the
+ * page cache. Also if we punch hole within i_size but above i_disksize,
+ * following ext4_page_mkwrite() may mistakenly allocate written blocks over
+ * the hole and thus introduce allocated blocks beyond i_disksize which is
+ * not allowed (e2fsck would complain in case of crash).
  */
 int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
 				      loff_t len)
@@ -4298,9 +4267,11 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
 	loff_t size = i_size_read(inode);
 
 	WARN_ON(!inode_is_locked(inode));
-	if (offset > size || offset + len < size)
+	if (offset > size)
 		return 0;
 
+	if (offset + len < size)
+		size = offset + len;
 	if (EXT4_I(inode)->i_disksize >= size)
 		return 0;
 
@@ -4748,7 +4719,7 @@ static int ext4_fill_raw_inode(struct inode *inode, struct ext4_inode *raw_inode
 		 * old inodes get re-used with the upper 16 bits of the
 		 * uid/gid intact.
 		 */
-		if (ei->i_dtime && list_empty(&ei->i_orphan)) {
+		if (ei->i_dtime && !ext4_inode_orphan_tracked(inode)) {
 			raw_inode->i_uid_high = 0;
 			raw_inode->i_gid_high = 0;
 		} else {