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, 57 insertions, 15 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 33e7c08c9529..87205660c5d0 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -698,7 +698,7 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error,
 		WARN_ON_ONCE(1);
 
 	if (!continue_fs && !ext4_emergency_ro(sb) && journal)
-		jbd2_journal_abort(journal, -EIO);
+		jbd2_journal_abort(journal, -error);
 
 	if (!bdev_read_only(sb->s_bdev)) {
 		save_error_info(sb, error, ino, block, func, line);
@@ -1396,6 +1396,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 
 	inode_set_iversion(&ei->vfs_inode, 1);
 	ei->i_flags = 0;
+	ext4_clear_state_flags(ei);	/* Only relevant on 32-bit archs */
 	spin_lock_init(&ei->i_raw_lock);
 	ei->i_prealloc_node = RB_ROOT;
 	atomic_set(&ei->i_prealloc_active, 0);
@@ -1406,6 +1407,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_es_all_nr = 0;
 	ei->i_es_shk_nr = 0;
 	ei->i_es_shrink_lblk = 0;
+	ei->i_es_seq = 0;
 	ei->i_reserved_data_blocks = 0;
 	spin_lock_init(&(ei->i_block_reservation_lock));
 	ext4_init_pending_tree(&ei->i_pending_tree);
@@ -2475,7 +2477,7 @@ static int parse_apply_sb_mount_options(struct super_block *sb,
 					struct ext4_fs_context *m_ctx)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	char s_mount_opts[65];
+	char s_mount_opts[64];
 	struct ext4_fs_context *s_ctx = NULL;
 	struct fs_context *fc = NULL;
 	int ret = -ENOMEM;
@@ -2483,7 +2485,8 @@ static int parse_apply_sb_mount_options(struct super_block *sb,
 	if (!sbi->s_es->s_mount_opts[0])
 		return 0;
 
-	strscpy_pad(s_mount_opts, sbi->s_es->s_mount_opts);
+	if (strscpy_pad(s_mount_opts, sbi->s_es->s_mount_opts) < 0)
+		return -E2BIG;
 
 	fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL);
 	if (!fc)
@@ -4188,7 +4191,7 @@ int ext4_calculate_overhead(struct super_block *sb)
 	unsigned int j_blocks, j_inum = le32_to_cpu(es->s_journal_inum);
 	ext4_group_t i, ngroups = ext4_get_groups_count(sb);
 	ext4_fsblk_t overhead = 0;
-	char *buf = (char *) get_zeroed_page(GFP_NOFS);
+	char *buf = kvmalloc(sb->s_blocksize, GFP_NOFS | __GFP_ZERO);
 
 	if (!buf)
 		return -ENOMEM;
@@ -4213,7 +4216,7 @@ int ext4_calculate_overhead(struct super_block *sb)
 		blks = count_overhead(sb, i, buf);
 		overhead += blks;
 		if (blks)
-			memset(buf, 0, PAGE_SIZE);
+			memset(buf, 0, sb->s_blocksize);
 		cond_resched();
 	}
 
@@ -4236,7 +4239,7 @@ int ext4_calculate_overhead(struct super_block *sb)
 	}
 	sbi->s_overhead = overhead;
 	smp_wmb();
-	free_page((unsigned long) buf);
+	kvfree(buf);
 	return 0;
 }
 
@@ -4389,8 +4392,7 @@ static void ext4_set_def_opts(struct super_block *sb,
 	    ((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0))
 		set_opt(sb, DELALLOC);
 
-	if (sb->s_blocksize <= PAGE_SIZE)
-		set_opt(sb, DIOREAD_NOLOCK);
+	set_opt(sb, DIOREAD_NOLOCK);
 }
 
 static int ext4_handle_clustersize(struct super_block *sb)
@@ -5040,6 +5042,41 @@ static const char *ext4_has_journal_option(struct super_block *sb)
 	return NULL;
 }
 
+/*
+ * Limit the maximum folio order to 2048 blocks to prevent overestimation
+ * of reserve handle credits during the folio writeback in environments
+ * where the PAGE_SIZE exceeds 4KB.
+ */
+#define EXT4_MAX_PAGECACHE_ORDER(sb)		\
+		umin(MAX_PAGECACHE_ORDER, (11 + (sb)->s_blocksize_bits - PAGE_SHIFT))
+static void ext4_set_max_mapping_order(struct super_block *sb)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+		sbi->s_max_folio_order = sbi->s_min_folio_order;
+	else
+		sbi->s_max_folio_order = EXT4_MAX_PAGECACHE_ORDER(sb);
+}
+
+static int ext4_check_large_folio(struct super_block *sb)
+{
+	const char *err_str = NULL;
+
+	if (ext4_has_feature_encrypt(sb))
+		err_str = "encrypt";
+
+	if (!err_str) {
+		ext4_set_max_mapping_order(sb);
+	} else if (sb->s_blocksize > PAGE_SIZE) {
+		ext4_msg(sb, KERN_ERR, "bs(%lu) > ps(%lu) unsupported for %s",
+			 sb->s_blocksize, PAGE_SIZE, err_str);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int ext4_load_super(struct super_block *sb, ext4_fsblk_t *lsb,
 			   int silent)
 {
@@ -5107,11 +5144,8 @@ static int ext4_load_super(struct super_block *sb, ext4_fsblk_t *lsb,
 	 * If the default block size is not the same as the real block size,
 	 * we need to reload it.
 	 */
-	if (sb->s_blocksize == blocksize) {
-		*lsb = logical_sb_block;
-		sbi->s_sbh = bh;
-		return 0;
-	}
+	if (sb->s_blocksize == blocksize)
+		goto success;
 
 	/*
 	 * bh must be released before kill_bdev(), otherwise
@@ -5142,6 +5176,9 @@ static int ext4_load_super(struct super_block *sb, ext4_fsblk_t *lsb,
 		ext4_msg(sb, KERN_ERR, "Magic mismatch, very weird!");
 		goto out;
 	}
+
+success:
+	sbi->s_min_folio_order = get_order(blocksize);
 	*lsb = logical_sb_block;
 	sbi->s_sbh = bh;
 	return 0;
@@ -5316,6 +5353,10 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 
 	ext4_apply_options(fc, sb);
 
+	err = ext4_check_large_folio(sb);
+	if (err < 0)
+		goto failed_mount;
+
 	err = ext4_encoding_init(sb, es);
 	if (err)
 		goto failed_mount;
@@ -5842,7 +5883,7 @@ static int ext4_journal_bmap(journal_t *journal, sector_t *block)
 		ext4_msg(journal->j_inode->i_sb, KERN_CRIT,
 			 "journal bmap failed: block %llu ret %d\n",
 			 *block, ret);
-		jbd2_journal_abort(journal, ret ? ret : -EIO);
+		jbd2_journal_abort(journal, ret ? ret : -EFSCORRUPTED);
 		return ret;
 	}
 	*block = map.m_pblk;
@@ -7412,7 +7453,8 @@ static struct file_system_type ext4_fs_type = {
 	.init_fs_context	= ext4_init_fs_context,
 	.parameters		= ext4_param_specs,
 	.kill_sb		= ext4_kill_sb,
-	.fs_flags		= FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME,
+	.fs_flags		= FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME |
+				  FS_LBS,
 };
 MODULE_ALIAS_FS("ext4");