Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 fixes from Ted Ts'o:
 "A large number of ext4 bug fixes and cleanups for v4.13"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: fix copy paste error in ext4_swap_extents()
  ext4: fix overflow caused by missing cast in ext4_resize_fs()
  ext4, project: expand inode extra size if possible
  ext4: cleanup ext4_expand_extra_isize_ea()
  ext4: restructure ext4_expand_extra_isize
  ext4: fix forgetten xattr lock protection in ext4_expand_extra_isize
  ext4: make xattr inode reads faster
  ext4: inplace xattr block update fails to deduplicate blocks
  ext4: remove unused mode parameter
  ext4: fix warning about stack corruption
  ext4: fix dir_nlink behaviour
  ext4: silence array overflow warning
  ext4: fix SEEK_HOLE/SEEK_DATA for blocksize < pagesize
  ext4: release discard bio after sending discard commands
  ext4: convert swap_inode_data() over to use swap() on most of the fields
  ext4: error should be cleared if ea_inode isn't added to the cache
  ext4: Don't clear SGID when inheriting ACLs
  ext4: preserve i_mode if __ext4_set_acl() fails
  ext4: remove unused metadata accounting variables
  ext4: correct comment references to ext4_ext_direct_IO()

fs/ext4/acl.c

@@ -193,13 +193,6 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type,
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
-		if (acl) {
-			error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
-			if (error)
-				return error;
-			inode->i_ctime = current_time(inode);
-			ext4_mark_inode_dirty(handle, inode);
-		}
 		break;
 
 	case ACL_TYPE_DEFAULT:
@@ -221,8 +214,9 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type,
 				      value, size, xattr_flags);
 
 	kfree(value);
-	if (!error)
+	if (!error) {
 		set_cached_acl(inode, type, acl);
+	}
 
 	return error;
 }
@@ -233,6 +227,8 @@ ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	handle_t *handle;
 	int error, credits, retries = 0;
 	size_t acl_size = acl ? ext4_acl_size(acl->a_count) : 0;
+	umode_t mode = inode->i_mode;
+	int update_mode = 0;
 
 	error = dquot_initialize(inode);
 	if (error)
@@ -247,7 +243,20 @@ retry:
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
+	if ((type == ACL_TYPE_ACCESS) && acl) {
+		error = posix_acl_update_mode(inode, &mode, &acl);
+		if (error)
+			goto out_stop;
+		update_mode = 1;
+	}
+
 	error = __ext4_set_acl(handle, inode, type, acl, 0 /* xattr_flags */);
+	if (!error && update_mode) {
+		inode->i_mode = mode;
+		inode->i_ctime = current_time(inode);
+		ext4_mark_inode_dirty(handle, inode);
+	}
+out_stop:
 	ext4_journal_stop(handle);
 	if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;

fs/ext4/ext4.h

@@ -961,7 +961,7 @@ struct ext4_inode_info {
 	/*
 	 * i_block_group is the number of the block group which contains
 	 * this file's inode.  Constant across the lifetime of the inode,
-	 * it is ued for making block allocation decisions - we try to
+	 * it is used for making block allocation decisions - we try to
 	 * place a file's data blocks near its inode block, and new inodes
 	 * near to their parent directory's inode.
 	 */
@@ -1049,10 +1049,8 @@ struct ext4_inode_info {
 	ext4_group_t	i_last_alloc_group;
 
 	/* allocation reservation info for delalloc */
-	/* In case of bigalloc, these refer to clusters rather than blocks */
+	/* In case of bigalloc, this refer to clusters rather than blocks */
 	unsigned int i_reserved_data_blocks;
-	unsigned int i_reserved_meta_blocks;
-	unsigned int i_allocated_meta_blocks;
 	ext4_lblk_t i_da_metadata_calc_last_lblock;
 	int i_da_metadata_calc_len;
 
@@ -2022,7 +2020,8 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
 
 #define is_dx(dir) (ext4_has_feature_dir_index((dir)->i_sb) && \
 		    ext4_test_inode_flag((dir), EXT4_INODE_INDEX))
-#define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX)
+#define EXT4_DIR_LINK_MAX(dir) unlikely((dir)->i_nlink >= EXT4_LINK_MAX && \
+		    !(ext4_has_feature_dir_nlink((dir)->i_sb) && is_dx(dir)))
 #define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)
 
 /* Legal values for the dx_root hash_version field: */
@@ -2462,6 +2461,8 @@ extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid);
 int ext4_inode_is_fast_symlink(struct inode *inode);
 struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
 struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
+int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count,
+		     bool wait, struct buffer_head **bhs);
 int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
 			     struct buffer_head *bh_result, int create);
 int ext4_get_block(struct inode *inode, sector_t iblock,
@@ -3074,7 +3075,7 @@ extern int ext4_handle_dirty_dirent_node(handle_t *handle,
 					 struct inode *inode,
 					 struct buffer_head *bh);
 #define S_SHIFT 12
-static const unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = {
+static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {
 	[S_IFREG >> S_SHIFT]	= EXT4_FT_REG_FILE,
 	[S_IFDIR >> S_SHIFT]	= EXT4_FT_DIR,
 	[S_IFCHR >> S_SHIFT]	= EXT4_FT_CHRDEV,

fs/ext4/ext4_jbd2.h

@@ -227,6 +227,9 @@ int ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
 
 int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode);
 
+int ext4_expand_extra_isize(struct inode *inode,
+			    unsigned int new_extra_isize,
+			    struct ext4_iloc *iloc);
 /*
  * Wrapper functions with which ext4 calls into JBD.
  */

fs/ext4/extents.c

@@ -4652,7 +4652,7 @@ retry:
 
 static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 				  ext4_lblk_t len, loff_t new_size,
-				  int flags, int mode)
+				  int flags)
 {
 	struct inode *inode = file_inode(file);
 	handle_t *handle;
@@ -4815,7 +4815,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 				round_down(offset, 1 << blkbits) >> blkbits,
 				(round_up((offset + len), 1 << blkbits) -
 				 round_down(offset, 1 << blkbits)) >> blkbits,
-				new_size, flags, mode);
+				new_size, flags);
 		if (ret)
 			goto out_dio;
 
@@ -4841,7 +4841,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		inode->i_mtime = inode->i_ctime = current_time(inode);
 
 		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
-					     flags, mode);
+					     flags);
 		up_write(&EXT4_I(inode)->i_mmap_sem);
 		if (ret)
 			goto out_dio;
@@ -4976,8 +4976,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	ext4_inode_block_unlocked_dio(inode);
 	inode_dio_wait(inode);
 
-	ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
-				     flags, mode);
+	ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags);
 	ext4_inode_resume_unlocked_dio(inode);
 	if (ret)
 		goto out;
@@ -5837,7 +5836,7 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1,
 			if (e1_blk > lblk1)
 				next1 = e1_blk;
 			if (e2_blk > lblk2)
-				next2 = e1_blk;
+				next2 = e2_blk;
 			/* Do we have something to swap */
 			if (next1 == EXT_MAX_BLOCKS || next2 == EXT_MAX_BLOCKS)
 				goto finish;

fs/ext4/file.c

@@ -537,6 +537,8 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 				lastoff = page_offset(page);
 				bh = head = page_buffers(page);
 				do {
+					if (lastoff + bh->b_size <= startoff)
+						goto next;
 					if (buffer_uptodate(bh) ||
 					    buffer_unwritten(bh)) {
 						if (whence == SEEK_DATA)
@@ -551,6 +553,7 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 						unlock_page(page);
 						goto out;
 					}
+next:
 					lastoff += bh->b_size;
 					bh = bh->b_this_page;
 				} while (bh != head);

fs/ext4/inode.c

@@ -892,7 +892,7 @@ static int ext4_dio_get_block_unwritten_async(struct inode *inode,
 /*
  * Get block function for non-AIO DIO writes when we create unwritten extent if
  * blocks are not allocated yet. The extent will be converted to written
- * after IO is complete from ext4_ext_direct_IO() function.
+ * after IO is complete by ext4_direct_IO_write().
  */
 static int ext4_dio_get_block_unwritten_sync(struct inode *inode,
 		sector_t iblock, struct buffer_head *bh_result,	int create)
@@ -907,7 +907,7 @@ static int ext4_dio_get_block_unwritten_sync(struct inode *inode,
 
 	/*
 	 * Mark inode as having pending DIO writes to unwritten extents.
-	 * ext4_ext_direct_IO() checks this flag and converts extents to
+	 * ext4_direct_IO_write() checks this flag and converts extents to
 	 * written.
 	 */
 	if (!ret && buffer_unwritten(bh_result))
@@ -1015,6 +1015,50 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
 	return ERR_PTR(-EIO);
 }
 
+/* Read a contiguous batch of blocks. */
+int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count,
+		     bool wait, struct buffer_head **bhs)
+{
+	int i, err;
+
+	for (i = 0; i < bh_count; i++) {
+		bhs[i] = ext4_getblk(NULL, inode, block + i, 0 /* map_flags */);
+		if (IS_ERR(bhs[i])) {
+			err = PTR_ERR(bhs[i]);
+			bh_count = i;
+			goto out_brelse;
+		}
+	}
+
+	for (i = 0; i < bh_count; i++)
+		/* Note that NULL bhs[i] is valid because of holes. */
+		if (bhs[i] && !buffer_uptodate(bhs[i]))
+			ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1,
+				    &bhs[i]);
+
+	if (!wait)
+		return 0;
+
+	for (i = 0; i < bh_count; i++)
+		if (bhs[i])
+			wait_on_buffer(bhs[i]);
+
+	for (i = 0; i < bh_count; i++) {
+		if (bhs[i] && !buffer_uptodate(bhs[i])) {
+			err = -EIO;
+			goto out_brelse;
+		}
+	}
+	return 0;
+
+out_brelse:
+	for (i = 0; i < bh_count; i++) {
+		brelse(bhs[i]);
+		bhs[i] = NULL;
+	}
+	return err;
+}
+
 int ext4_walk_page_buffers(handle_t *handle,
 			   struct buffer_head *head,
 			   unsigned from,
@@ -5658,22 +5702,16 @@ ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
 	return err;
 }
 
-/*
- * Expand an inode by new_extra_isize bytes.
- * Returns 0 on success or negative error number on failure.
- */
-static int ext4_expand_extra_isize(struct inode *inode,
-				   unsigned int new_extra_isize,
-				   struct ext4_iloc iloc,
-				   handle_t *handle)
+static int __ext4_expand_extra_isize(struct inode *inode,
+				     unsigned int new_extra_isize,
+				     struct ext4_iloc *iloc,
+				     handle_t *handle, int *no_expand)
 {
 	struct ext4_inode *raw_inode;
 	struct ext4_xattr_ibody_header *header;
+	int error;
 
-	if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
-		return 0;
-
-	raw_inode = ext4_raw_inode(&iloc);
+	raw_inode = ext4_raw_inode(iloc);
 
 	header = IHDR(inode, raw_inode);
 
@@ -5688,8 +5726,98 @@ static int ext4_expand_extra_isize(struct inode *inode,
 	}
 
 	/* try to expand with EAs present */
-	return ext4_expand_extra_isize_ea(inode, new_extra_isize,
-					  raw_inode, handle);
+	error = ext4_expand_extra_isize_ea(inode, new_extra_isize,
+					   raw_inode, handle);
+	if (error) {
+		/*
+		 * Inode size expansion failed; don't try again
+		 */
+		*no_expand = 1;
+	}
+
+	return error;
+}
+
+/*
+ * Expand an inode by new_extra_isize bytes.
+ * Returns 0 on success or negative error number on failure.
+ */
+static int ext4_try_to_expand_extra_isize(struct inode *inode,
+					  unsigned int new_extra_isize,
+					  struct ext4_iloc iloc,
+					  handle_t *handle)
+{
+	int no_expand;
+	int error;
+
+	if (ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND))
+		return -EOVERFLOW;
+
+	/*
+	 * In nojournal mode, we can immediately attempt to expand
+	 * the inode.  When journaled, we first need to obtain extra
+	 * buffer credits since we may write into the EA block
+	 * with this same handle. If journal_extend fails, then it will
+	 * only result in a minor loss of functionality for that inode.
+	 * If this is felt to be critical, then e2fsck should be run to
+	 * force a large enough s_min_extra_isize.
+	 */
+	if (ext4_handle_valid(handle) &&
+	    jbd2_journal_extend(handle,
+				EXT4_DATA_TRANS_BLOCKS(inode->i_sb)) != 0)
+		return -ENOSPC;
+
+	if (ext4_write_trylock_xattr(inode, &no_expand) == 0)
+		return -EBUSY;
+
+	error = __ext4_expand_extra_isize(inode, new_extra_isize, &iloc,
+					  handle, &no_expand);
+	ext4_write_unlock_xattr(inode, &no_expand);
+
+	return error;
+}
+
+int ext4_expand_extra_isize(struct inode *inode,
+			    unsigned int new_extra_isize,
+			    struct ext4_iloc *iloc)
+{
+	handle_t *handle;
+	int no_expand;
+	int error, rc;
+
+	if (ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
+		brelse(iloc->bh);
+		return -EOVERFLOW;
+	}
+
+	handle = ext4_journal_start(inode, EXT4_HT_INODE,
+				    EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
+	if (IS_ERR(handle)) {
+		error = PTR_ERR(handle);
+		brelse(iloc->bh);
+		return error;
+	}
+
+	ext4_write_lock_xattr(inode, &no_expand);
+
+	BUFFER_TRACE(iloc.bh, "get_write_access");
+	error = ext4_journal_get_write_access(handle, iloc->bh);
+	if (error) {
+		brelse(iloc->bh);
+		goto out_stop;
+	}
+
+	error = __ext4_expand_extra_isize(inode, new_extra_isize, iloc,
+					  handle, &no_expand);
+
+	rc = ext4_mark_iloc_dirty(handle, inode, iloc);
+	if (!error)
+		error = rc;
+
+	ext4_write_unlock_xattr(inode, &no_expand);
+out_stop:
+	ext4_journal_stop(handle);
+	return error;
 }
 
 /*
@@ -5709,44 +5837,18 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 {
 	struct ext4_iloc iloc;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	static unsigned int mnt_count;
-	int err, ret;
+	int err;
 
 	might_sleep();
 	trace_ext4_mark_inode_dirty(inode, _RET_IP_);
 	err = ext4_reserve_inode_write(handle, inode, &iloc);
 	if (err)
 		return err;
-	if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
-	    !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
-		/*
-		 * In nojournal mode, we can immediately attempt to expand
-		 * the inode.  When journaled, we first need to obtain extra
-		 * buffer credits since we may write into the EA block
-		 * with this same handle. If journal_extend fails, then it will
-		 * only result in a minor loss of functionality for that inode.
-		 * If this is felt to be critical, then e2fsck should be run to
-		 * force a large enough s_min_extra_isize.
-		 */
-		if (!ext4_handle_valid(handle) ||
-		    jbd2_journal_extend(handle,
-			     EXT4_DATA_TRANS_BLOCKS(inode->i_sb)) == 0) {
-			ret = ext4_expand_extra_isize(inode,
-						      sbi->s_want_extra_isize,
-						      iloc, handle);
-			if (ret) {
-				if (mnt_count !=
-					le16_to_cpu(sbi->s_es->s_mnt_count)) {
-					ext4_warning(inode->i_sb,
-					"Unable to expand inode %lu. Delete"
-					" some EAs or run e2fsck.",
-					inode->i_ino);
-					mnt_count =
-					  le16_to_cpu(sbi->s_es->s_mnt_count);
-				}
-			}
-		}
-	}
+
+	if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize)
+		ext4_try_to_expand_extra_isize(inode, sbi->s_want_extra_isize,
+					       iloc, handle);
+
 	return ext4_mark_iloc_dirty(handle, inode, &iloc);
 }
 

fs/ext4/ioctl.c

@@ -64,18 +64,16 @@ static void swap_inode_data(struct inode *inode1, struct inode *inode2)
 	ei1 = EXT4_I(inode1);
 	ei2 = EXT4_I(inode2);
 
-	memswap(&inode1->i_flags, &inode2->i_flags, sizeof(inode1->i_flags));
-	memswap(&inode1->i_version, &inode2->i_version,
-		  sizeof(inode1->i_version));
-	memswap(&inode1->i_blocks, &inode2->i_blocks,
-		  sizeof(inode1->i_blocks));
-	memswap(&inode1->i_bytes, &inode2->i_bytes, sizeof(inode1->i_bytes));
-	memswap(&inode1->i_atime, &inode2->i_atime, sizeof(inode1->i_atime));
-	memswap(&inode1->i_mtime, &inode2->i_mtime, sizeof(inode1->i_mtime));
+	swap(inode1->i_flags, inode2->i_flags);
+	swap(inode1->i_version, inode2->i_version);
+	swap(inode1->i_blocks, inode2->i_blocks);
+	swap(inode1->i_bytes, inode2->i_bytes);
+	swap(inode1->i_atime, inode2->i_atime);
+	swap(inode1->i_mtime, inode2->i_mtime);
 
 	memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data));
-	memswap(&ei1->i_flags, &ei2->i_flags, sizeof(ei1->i_flags));
-	memswap(&ei1->i_disksize, &ei2->i_disksize, sizeof(ei1->i_disksize));
+	swap(ei1->i_flags, ei2->i_flags);
+	swap(ei1->i_disksize, ei2->i_disksize);
 	ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS);
 	ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS);
 
@@ -351,11 +349,14 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
 
 	raw_inode = ext4_raw_inode(&iloc);
 	if (!EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) {
-		err = -EOVERFLOW;
+		err = ext4_expand_extra_isize(inode,
+					      EXT4_SB(sb)->s_want_extra_isize,
+					      &iloc);
+		if (err)
+			goto out_unlock;
+	} else {
 		brelse(iloc.bh);
-		goto out_unlock;
 	}
-	brelse(iloc.bh);
 
 	dquot_initialize(inode);
 

fs/ext4/mballoc.c

@@ -2295,9 +2295,12 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	int err, buddy_loaded = 0;
 	struct ext4_buddy e4b;
 	struct ext4_group_info *grinfo;
+	unsigned char blocksize_bits = min_t(unsigned char,
+					     sb->s_blocksize_bits,
+					     EXT4_MAX_BLOCK_LOG_SIZE);
 	struct sg {
 		struct ext4_group_info info;
-		ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2];
+		ext4_grpblk_t counters[blocksize_bits + 2];
 	} sg;
 
 	group--;
@@ -2306,8 +2309,6 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 			      " 2^0   2^1   2^2   2^3   2^4   2^5   2^6  "
 			      " 2^7   2^8   2^9   2^10  2^11  2^12  2^13  ]\n");
 
-	i = (sb->s_blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) +
-		sizeof(struct ext4_group_info);
 	grinfo = ext4_get_group_info(sb, group);
 	/* Load the group info in memory only if not already loaded. */
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) {
@@ -2319,7 +2320,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 		buddy_loaded = 1;
 	}
 
-	memcpy(&sg, ext4_get_group_info(sb, group), i);
+	memcpy(&sg, ext4_get_group_info(sb, group), sizeof(sg));
 
 	if (buddy_loaded)
 		ext4_mb_unload_buddy(&e4b);
@@ -2327,7 +2328,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free,
 			sg.info.bb_fragments, sg.info.bb_first_free);
 	for (i = 0; i <= 13; i++)
-		seq_printf(seq, " %-5u", i <= sb->s_blocksize_bits + 1 ?
+		seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ?
 				sg.info.bb_counters[i] : 0);
 	seq_printf(seq, " ]\n");
 
@@ -2892,8 +2893,10 @@ void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid)
 				break;
 		}
 
-		if (discard_bio)
+		if (discard_bio) {
 			submit_bio_wait(discard_bio);
+			bio_put(discard_bio);
+		}
 	}
 
 	list_for_each_entry_safe(entry, tmp, &freed_data_list, efd_list)

fs/ext4/namei.c

@@ -1342,13 +1342,12 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
 	struct super_block *sb;
 	struct buffer_head *bh_use[NAMEI_RA_SIZE];
 	struct buffer_head *bh, *ret = NULL;
-	ext4_lblk_t start, block, b;
+	ext4_lblk_t start, block;
 	const u8 *name = d_name->name;
-	int ra_max = 0;		/* Number of bh's in the readahead
+	size_t ra_max = 0;	/* Number of bh's in the readahead
 				   buffer, bh_use[] */
-	int ra_ptr = 0;		/* Current index into readahead
+	size_t ra_ptr = 0;	/* Current index into readahead
 				   buffer */
-	int num = 0;
 	ext4_lblk_t  nblocks;
 	int i, namelen, retval;
 	struct ext4_filename fname;
@@ -1411,31 +1410,17 @@ restart:
 		if (ra_ptr >= ra_max) {
 			/* Refill the readahead buffer */
 			ra_ptr = 0;
-			b = block;
-			for (ra_max = 0; ra_max < NAMEI_RA_SIZE; ra_max++) {
-				/*
-				 * Terminate if we reach the end of the
-				 * directory and must wrap, or if our
-				 * search has finished at this block.
-				 */
-				if (b >= nblocks || (num && block == start)) {
-					bh_use[ra_max] = NULL;
-					break;
-				}
-				num++;
-				bh = ext4_getblk(NULL, dir, b++, 0);
-				if (IS_ERR(bh)) {
-					if (ra_max == 0) {
-						ret = bh;
-						goto cleanup_and_exit;
-					}
-					break;
-				}
-				bh_use[ra_max] = bh;
-				if (bh)
-					ll_rw_block(REQ_OP_READ,
-						    REQ_META | REQ_PRIO,
-						    1, &bh);
+			if (block < start)
+				ra_max = start - block;
+			else
+				ra_max = nblocks - block;
+			ra_max = min(ra_max, ARRAY_SIZE(bh_use));
+			retval = ext4_bread_batch(dir, block, ra_max,
+						  false /* wait */, bh_use);
+			if (retval) {
+				ret = ERR_PTR(retval);
+				ra_max = 0;
+				goto cleanup_and_exit;
 			}
 		}
 		if ((bh = bh_use[ra_ptr++]) == NULL)
@@ -2395,19 +2380,22 @@ out:
 }
 
 /*
- * DIR_NLINK feature is set if 1) nlinks > EXT4_LINK_MAX or 2) nlinks == 2,
- * since this indicates that nlinks count was previously 1.
+ * Set directory link count to 1 if nlinks > EXT4_LINK_MAX, or if nlinks == 2
+ * since this indicates that nlinks count was previously 1 to avoid overflowing
+ * the 16-bit i_links_count field on disk.  Directories with i_nlink == 1 mean
+ * that subdirectory link counts are not being maintained accurately.
+ *
+ * The caller has already checked for i_nlink overflow in case the DIR_LINK
+ * feature is not enabled and returned -EMLINK.  The is_dx() check is a proxy
+ * for checking S_ISDIR(inode) (since the INODE_INDEX feature will not be set
+ * on regular files) and to avoid creating huge/slow non-HTREE directories.
  */
 static void ext4_inc_count(handle_t *handle, struct inode *inode)
 {
 	inc_nlink(inode);
-	if (is_dx(inode) && inode->i_nlink > 1) {
-		/* limit is 16-bit i_links_count */
-		if (inode->i_nlink >= EXT4_LINK_MAX || inode->i_nlink == 2) {
-			set_nlink(inode, 1);
-			ext4_set_feature_dir_nlink(inode->i_sb);
-		}
-	}
+	if (is_dx(inode) &&
+	    (inode->i_nlink > EXT4_LINK_MAX || inode->i_nlink == 2))
+		set_nlink(inode, 1);
 }
 
 /*

fs/ext4/resize.c

@@ -1927,7 +1927,8 @@ retry:
 			n_desc_blocks = o_desc_blocks +
 				le16_to_cpu(es->s_reserved_gdt_blocks);
 			n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb);
-			n_blocks_count = n_group * EXT4_BLOCKS_PER_GROUP(sb);
+			n_blocks_count = (ext4_fsblk_t)n_group *
+				EXT4_BLOCKS_PER_GROUP(sb);
 			n_group--; /* set to last group number */
 		}
 

fs/ext4/super.c

@@ -978,8 +978,6 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_es_shk_nr = 0;
 	ei->i_es_shrink_lblk = 0;
 	ei->i_reserved_data_blocks = 0;
-	ei->i_reserved_meta_blocks = 0;
-	ei->i_allocated_meta_blocks = 0;
 	ei->i_da_metadata_calc_len = 0;
 	ei->i_da_metadata_calc_last_lblock = 0;
 	spin_lock_init(&(ei->i_block_reservation_lock));

fs/ext4/xattr.c

@@ -317,28 +317,41 @@ static void ext4_xattr_inode_set_hash(struct inode *ea_inode, u32 hash)
  */
 static int ext4_xattr_inode_read(struct inode *ea_inode, void *buf, size_t size)
 {
-	unsigned long block = 0;
-	struct buffer_head *bh;
-	int blocksize = ea_inode->i_sb->s_blocksize;
-	size_t csize, copied = 0;
-	void *copy_pos = buf;
-
-	while (copied < size) {
-		csize = (size - copied) > blocksize ? blocksize : size - copied;
-		bh = ext4_bread(NULL, ea_inode, block, 0);
-		if (IS_ERR(bh))
-			return PTR_ERR(bh);
-		if (!bh)
-			return -EFSCORRUPTED;
+	int blocksize = 1 << ea_inode->i_blkbits;
+	int bh_count = (size + blocksize - 1) >> ea_inode->i_blkbits;
+	int tail_size = (size % blocksize) ?: blocksize;
+	struct buffer_head *bhs_inline[8];
+	struct buffer_head **bhs = bhs_inline;
+	int i, ret;
+
+	if (bh_count > ARRAY_SIZE(bhs_inline)) {
+		bhs = kmalloc_array(bh_count, sizeof(*bhs), GFP_NOFS);
+		if (!bhs)
+			return -ENOMEM;
+	}
 
-		memcpy(copy_pos, bh->b_data, csize);
-		brelse(bh);
+	ret = ext4_bread_batch(ea_inode, 0 /* block */, bh_count,
+			       true /* wait */, bhs);
+	if (ret)
+		goto free_bhs;
 
-		copy_pos += csize;
-		block += 1;
-		copied += csize;
+	for (i = 0; i < bh_count; i++) {
+		/* There shouldn't be any holes in ea_inode. */
+		if (!bhs[i]) {
+			ret = -EFSCORRUPTED;
+			goto put_bhs;
+		}
+		memcpy((char *)buf + blocksize * i, bhs[i]->b_data,
+		       i < bh_count - 1 ? blocksize : tail_size);
 	}
-	return 0;
+	ret = 0;
+put_bhs:
+	for (i = 0; i < bh_count; i++)
+		brelse(bhs[i]);
+free_bhs:
+	if (bhs != bhs_inline)
+		kfree(bhs);
+	return ret;
 }
 
 static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino,
@@ -451,6 +464,7 @@ ext4_xattr_inode_get(struct inode *inode, struct ext4_xattr_entry *entry,
 		}
 		/* Do not add ea_inode to the cache. */
 		ea_inode_cache = NULL;
+		err = 0;
 	} else if (err)
 		goto out;
 
@@ -1815,9 +1829,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			ea_bdebug(bs->bh, "modifying in-place");
 			error = ext4_xattr_set_entry(i, s, handle, inode,
 						     true /* is_block */);
-			if (!error)
-				ext4_xattr_block_cache_insert(ea_block_cache,
-							      bs->bh);
 			ext4_xattr_block_csum_set(inode, bs->bh);
 			unlock_buffer(bs->bh);
 			if (error == -EFSCORRUPTED)
@@ -1973,6 +1984,7 @@ inserted:
 		} else if (bs->bh && s->base == bs->bh->b_data) {
 			/* We were modifying this block in-place. */
 			ea_bdebug(bs->bh, "keeping this block");
+			ext4_xattr_block_cache_insert(ea_block_cache, bs->bh);
 			new_bh = bs->bh;
 			get_bh(new_bh);
 		} else {
@@ -2625,23 +2637,21 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 			       struct ext4_inode *raw_inode, handle_t *handle)
 {
 	struct ext4_xattr_ibody_header *header;
-	struct buffer_head *bh = NULL;
+	struct buffer_head *bh;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	static unsigned int mnt_count;
 	size_t min_offs;
 	size_t ifree, bfree;
 	int total_ino;
 	void *base, *end;
 	int error = 0, tried_min_extra_isize = 0;
-	int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
+	int s_min_extra_isize = le16_to_cpu(sbi->s_es->s_min_extra_isize);
 	int isize_diff;	/* How much do we need to grow i_extra_isize */
-	int no_expand;
-
-	if (ext4_write_trylock_xattr(inode, &no_expand) == 0)
-		return 0;
 
 retry:
 	isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize;
 	if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
-		goto out;
+		return 0;
 
 	header = IHDR(inode, raw_inode);
 
@@ -2676,6 +2686,7 @@ retry:
 			EXT4_ERROR_INODE(inode, "bad block %llu",
 					 EXT4_I(inode)->i_file_acl);
 			error = -EFSCORRUPTED;
+			brelse(bh);
 			goto cleanup;
 		}
 		base = BHDR(bh);
@@ -2683,11 +2694,11 @@ retry:
 		min_offs = end - base;
 		bfree = ext4_xattr_free_space(BFIRST(bh), &min_offs, base,
 					      NULL);
+		brelse(bh);
 		if (bfree + ifree < isize_diff) {
 			if (!tried_min_extra_isize && s_min_extra_isize) {
 				tried_min_extra_isize++;
 				new_extra_isize = s_min_extra_isize;
-				brelse(bh);
 				goto retry;
 			}
 			error = -ENOSPC;
@@ -2705,7 +2716,6 @@ retry:
 		    s_min_extra_isize) {
 			tried_min_extra_isize++;
 			new_extra_isize = s_min_extra_isize;
-			brelse(bh);
 			goto retry;
 		}
 		goto cleanup;
@@ -2717,18 +2727,13 @@ shift:
 			EXT4_GOOD_OLD_INODE_SIZE + new_extra_isize,
 			(void *)header, total_ino);
 	EXT4_I(inode)->i_extra_isize = new_extra_isize;
-	brelse(bh);
-out:
-	ext4_write_unlock_xattr(inode, &no_expand);
-	return 0;
 
 cleanup:
-	brelse(bh);
-	/*
-	 * Inode size expansion failed; don't try again
-	 */
-	no_expand = 1;
-	ext4_write_unlock_xattr(inode, &no_expand);
+	if (error && (mnt_count != le16_to_cpu(sbi->s_es->s_mnt_count))) {
+		ext4_warning(inode->i_sb, "Unable to expand inode %lu. Delete some EAs or run e2fsck.",
+			     inode->i_ino);
+		mnt_count = le16_to_cpu(sbi->s_es->s_mnt_count);
+	}
 	return error;
 }
 

include/trace/events/ext4.h

@@ -937,21 +937,19 @@ TRACE_EVENT(ext4_alloc_da_blocks,
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
-		__field( unsigned int,	data_blocks	)
-		__field( unsigned int,	meta_blocks	)
+		__field( unsigned int,	data_blocks		)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
 		__entry->data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
-		__entry->meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks;
 	),
 
-	TP_printk("dev %d,%d ino %lu data_blocks %u meta_blocks %u",
+	TP_printk("dev %d,%d ino %lu reserved_data_blocks %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
-		  __entry->data_blocks, __entry->meta_blocks)
+		  __entry->data_blocks)
 );
 
 TRACE_EVENT(ext4_mballoc_alloc,
@@ -1153,8 +1151,6 @@ TRACE_EVENT(ext4_da_update_reserve_space,
 		__field(	__u64,	i_blocks		)
 		__field(	int,	used_blocks		)
 		__field(	int,	reserved_data_blocks	)
-		__field(	int,	reserved_meta_blocks	)
-		__field(	int,	allocated_meta_blocks	)
 		__field(	int,	quota_claim		)
 		__field(	__u16,	mode			)
 	),
@@ -1166,22 +1162,16 @@ TRACE_EVENT(ext4_da_update_reserve_space,
 		__entry->used_blocks = used_blocks;
 		__entry->reserved_data_blocks =
 				EXT4_I(inode)->i_reserved_data_blocks;
-		__entry->reserved_meta_blocks =
-				EXT4_I(inode)->i_reserved_meta_blocks;
-		__entry->allocated_meta_blocks =
-				EXT4_I(inode)->i_allocated_meta_blocks;
 		__entry->quota_claim = quota_claim;
 		__entry->mode	= inode->i_mode;
 	),
 
 	TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu used_blocks %d "
-		  "reserved_data_blocks %d reserved_meta_blocks %d "
-		  "allocated_meta_blocks %d quota_claim %d",
+		  "reserved_data_blocks %d quota_claim %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
 		  __entry->mode, __entry->i_blocks,
 		  __entry->used_blocks, __entry->reserved_data_blocks,
-		  __entry->reserved_meta_blocks, __entry->allocated_meta_blocks,
 		  __entry->quota_claim)
 );
 
@@ -1195,7 +1185,6 @@ TRACE_EVENT(ext4_da_reserve_space,
 		__field(	ino_t,	ino			)
 		__field(	__u64,	i_blocks		)
 		__field(	int,	reserved_data_blocks	)
-		__field(	int,	reserved_meta_blocks	)
 		__field(	__u16,  mode			)
 	),
 
@@ -1204,17 +1193,15 @@ TRACE_EVENT(ext4_da_reserve_space,
 		__entry->ino	= inode->i_ino;
 		__entry->i_blocks = inode->i_blocks;
 		__entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
-		__entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks;
 		__entry->mode	= inode->i_mode;
 	),
 
 	TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu "
-		  "reserved_data_blocks %d reserved_meta_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->reserved_meta_blocks)
+		  __entry->reserved_data_blocks)
 );
 
 TRACE_EVENT(ext4_da_release_space,
@@ -1228,8 +1215,6 @@ TRACE_EVENT(ext4_da_release_space,
 		__field(	__u64,	i_blocks		)
 		__field(	int,	freed_blocks		)
 		__field(	int,	reserved_data_blocks	)
-		__field(	int,	reserved_meta_blocks	)
-		__field(	int,	allocated_meta_blocks	)
 		__field(	__u16,  mode			)
 	),
 
@@ -1239,19 +1224,15 @@ TRACE_EVENT(ext4_da_release_space,
 		__entry->i_blocks = inode->i_blocks;
 		__entry->freed_blocks = freed_blocks;
 		__entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
-		__entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks;
-		__entry->allocated_meta_blocks = EXT4_I(inode)->i_allocated_meta_blocks;
 		__entry->mode	= inode->i_mode;
 	),
 
 	TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu freed_blocks %d "
-		  "reserved_data_blocks %d reserved_meta_blocks %d "
-		  "allocated_meta_blocks %d",
+		  "reserved_data_blocks %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
 		  __entry->mode, __entry->i_blocks,
-		  __entry->freed_blocks, __entry->reserved_data_blocks,
-		  __entry->reserved_meta_blocks, __entry->allocated_meta_blocks)
+		  __entry->freed_blocks, __entry->reserved_data_blocks)
 );
 
 DECLARE_EVENT_CLASS(ext4__bitmap_load,