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

Pull ext4 updates from Ted Ts'o:
 "Many bug fixes and cleanups, and an optimization for case-insensitive
  lookups"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: fix coverity warning on error path of filename setup
  ext4: replace ktype default_attrs with default_groups
  ext4: rename htree_inline_dir_to_tree() to ext4_inlinedir_to_tree()
  ext4: refactor initialize_dirent_tail()
  ext4: rename "dirent_csum" functions to use "dirblock"
  ext4: allow directory holes
  jbd2: drop declaration of journal_sync_buffer()
  ext4: use jbd2_inode dirty range scoping
  jbd2: introduce jbd2_inode dirty range scoping
  mm: add filemap_fdatawait_range_keep_errors()
  ext4: remove redundant assignment to node
  ext4: optimize case-insensitive lookups
  ext4: make __ext4_get_inode_loc plug
  ext4: clean up kerneldoc warnigns when building with W=1
  ext4: only set project inherit bit for directory
  ext4: enforce the immutable flag on open files
  ext4: don't allow any modifications to an immutable file
  jbd2: fix typo in comment of journal_submit_inode_data_buffers
  jbd2: fix some print format mistakes
  ext4: gracefully handle ext4_break_layouts() failure during truncate

fs/ext4/balloc.c

@@ -603,9 +603,9 @@ int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
 }
 
 /**
- * ext4_should_retry_alloc()
+ * ext4_should_retry_alloc() - check if a block allocation should be retried
  * @sb:			super block
- * @retries		number of attemps has been made
+ * @retries:		number of attemps has been made
  *
  * ext4_should_retry_alloc() is called when ENOSPC is returned, and if
  * it is profitable to retry the operation, this function will wait

fs/ext4/dir.c

@@ -33,6 +33,9 @@
 static int ext4_dx_readdir(struct file *, struct dir_context *);
 
 /**
+ * is_dx_dir() - check if a directory is using htree indexing
+ * @inode: directory inode
+ *
  * Check if the given dir-inode refers to an htree-indexed directory
  * (or a directory which could potentially get converted to use htree
  * indexing).
@@ -109,7 +112,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 	struct inode *inode = file_inode(file);
 	struct super_block *sb = inode->i_sb;
 	struct buffer_head *bh = NULL;
-	int dir_has_error = 0;
 	struct fscrypt_str fstr = FSTR_INIT(NULL, 0);
 
 	if (IS_ENCRYPTED(inode)) {
@@ -145,8 +147,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 			return err;
 	}
 
-	offset = ctx->pos & (sb->s_blocksize - 1);
-
 	while (ctx->pos < inode->i_size) {
 		struct ext4_map_blocks map;
 
@@ -155,9 +155,18 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 			goto errout;
 		}
 		cond_resched();
+		offset = ctx->pos & (sb->s_blocksize - 1);
 		map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb);
 		map.m_len = 1;
 		err = ext4_map_blocks(NULL, inode, &map, 0);
+		if (err == 0) {
+			/* m_len should never be zero but let's avoid
+			 * an infinite loop if it somehow is */
+			if (map.m_len == 0)
+				map.m_len = 1;
+			ctx->pos += map.m_len * sb->s_blocksize;
+			continue;
+		}
 		if (err > 0) {
 			pgoff_t index = map.m_pblk >>
 					(PAGE_SHIFT - inode->i_blkbits);
@@ -176,13 +185,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 		}
 
 		if (!bh) {
-			if (!dir_has_error) {
-				EXT4_ERROR_FILE(file, 0,
-						"directory contains a "
-						"hole at offset %llu",
-					   (unsigned long long) ctx->pos);
-				dir_has_error = 1;
-			}
 			/* corrupt size?  Maybe no more blocks to read */
 			if (ctx->pos > inode->i_blocks << 9)
 				break;
@@ -192,8 +194,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 
 		/* Check the checksum */
 		if (!buffer_verified(bh) &&
-		    !ext4_dirent_csum_verify(inode,
-				(struct ext4_dir_entry *)bh->b_data)) {
+		    !ext4_dirblock_csum_verify(inode, bh)) {
 			EXT4_ERROR_FILE(file, 0, "directory fails checksum "
 					"at offset %llu",
 					(unsigned long long)ctx->pos);
@@ -674,7 +675,7 @@ static int ext4_d_compare(const struct dentry *dentry, unsigned int len,
 		return memcmp(str, name->name, len);
 	}
 
-	return ext4_ci_compare(dentry->d_parent->d_inode, name, &qstr);
+	return ext4_ci_compare(dentry->d_parent->d_inode, name, &qstr, false);
 }
 
 static int ext4_d_hash(const struct dentry *dentry, struct qstr *str)

fs/ext4/ext4.h

@@ -421,7 +421,8 @@ struct flex_groups {
 			   EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL)
 
 /* Flags that are appropriate for regular files (all but dir-specific ones). */
-#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL))
+#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL |\
+			   EXT4_PROJINHERIT_FL))
 
 /* Flags that are appropriate for non-directories/regular files. */
 #define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL)
@@ -2077,6 +2078,9 @@ struct ext4_filename {
 #ifdef CONFIG_FS_ENCRYPTION
 	struct fscrypt_str crypto_buf;
 #endif
+#ifdef CONFIG_UNICODE
+	struct fscrypt_str cf_name;
+#endif
 };
 
 #define fname_name(p) ((p)->disk_name.name)
@@ -2302,6 +2306,12 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
 					      struct ext4_group_desc *gdp);
 ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
 
+#ifdef CONFIG_UNICODE
+extern void ext4_fname_setup_ci_filename(struct inode *dir,
+					 const struct qstr *iname,
+					 struct fscrypt_str *fname);
+#endif
+
 #ifdef CONFIG_FS_ENCRYPTION
 static inline void ext4_fname_from_fscrypt_name(struct ext4_filename *dst,
 						const struct fscrypt_name *src)
@@ -2328,6 +2338,10 @@ static inline int ext4_fname_setup_filename(struct inode *dir,
 		return err;
 
 	ext4_fname_from_fscrypt_name(fname, &name);
+
+#ifdef CONFIG_UNICODE
+	ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name);
+#endif
 	return 0;
 }
 
@@ -2343,6 +2357,10 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir,
 		return err;
 
 	ext4_fname_from_fscrypt_name(fname, &name);
+
+#ifdef CONFIG_UNICODE
+	ext4_fname_setup_ci_filename(dir, &dentry->d_name, &fname->cf_name);
+#endif
 	return 0;
 }
 
@@ -2356,6 +2374,11 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname)
 	fname->crypto_buf.name = NULL;
 	fname->usr_fname = NULL;
 	fname->disk_name.name = NULL;
+
+#ifdef CONFIG_UNICODE
+	kfree(fname->cf_name.name);
+	fname->cf_name.name = NULL;
+#endif
 }
 #else /* !CONFIG_FS_ENCRYPTION */
 static inline int ext4_fname_setup_filename(struct inode *dir,
@@ -2366,6 +2389,11 @@ static inline int ext4_fname_setup_filename(struct inode *dir,
 	fname->usr_fname = iname;
 	fname->disk_name.name = (unsigned char *) iname->name;
 	fname->disk_name.len = iname->len;
+
+#ifdef CONFIG_UNICODE
+	ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name);
+#endif
+
 	return 0;
 }
 
@@ -2376,7 +2404,13 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir,
 	return ext4_fname_setup_filename(dir, &dentry->d_name, 1, fname);
 }
 
-static inline void ext4_fname_free_filename(struct ext4_filename *fname) { }
+static inline void ext4_fname_free_filename(struct ext4_filename *fname)
+{
+#ifdef CONFIG_UNICODE
+	kfree(fname->cf_name.name);
+	fname->cf_name.name = NULL;
+#endif
+}
 #endif /* !CONFIG_FS_ENCRYPTION */
 
 /* dir.c */
@@ -2568,8 +2602,8 @@ extern int ext4_ext_migrate(struct inode *);
 extern int ext4_ind_migrate(struct inode *inode);
 
 /* namei.c */
-extern int ext4_dirent_csum_verify(struct inode *inode,
-				   struct ext4_dir_entry *dirent);
+extern int ext4_dirblock_csum_verify(struct inode *inode,
+				     struct buffer_head *bh);
 extern int ext4_orphan_add(handle_t *, struct inode *);
 extern int ext4_orphan_del(handle_t *, struct inode *);
 extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
@@ -3070,7 +3104,7 @@ extern int ext4_try_create_inline_dir(handle_t *handle,
 extern int ext4_read_inline_dir(struct file *filp,
 				struct dir_context *ctx,
 				int *has_inline_data);
-extern int htree_inlinedir_to_tree(struct file *dir_file,
+extern int ext4_inlinedir_to_tree(struct file *dir_file,
 				  struct inode *dir, ext4_lblk_t block,
 				  struct dx_hash_info *hinfo,
 				  __u32 start_hash, __u32 start_minor_hash,
@@ -3113,14 +3147,13 @@ extern struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode,
 				 struct ext4_dir_entry_2 *de,
 				 int blocksize, int csum_size,
 				 unsigned int parent_ino, int dotdot_real_len);
-extern void initialize_dirent_tail(struct ext4_dir_entry_tail *t,
+extern void ext4_initialize_dirent_tail(struct buffer_head *bh,
 					unsigned int blocksize);
-extern int ext4_handle_dirty_dirent_node(handle_t *handle,
-					 struct inode *inode,
+extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode,
 				      struct buffer_head *bh);
 extern int ext4_ci_compare(const struct inode *parent,
-			   const struct qstr *name,
-			   const struct qstr *entry);
+			   const struct qstr *fname,
+			   const struct qstr *entry, bool quick);
 
 #define S_SHIFT 12
 static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {

fs/ext4/ext4_jbd2.h

@@ -361,20 +361,20 @@ static inline int ext4_journal_force_commit(journal_t *journal)
 }
 
 static inline int ext4_jbd2_inode_add_write(handle_t *handle,
-					    struct inode *inode)
+		struct inode *inode, loff_t start_byte, loff_t length)
 {
 	if (ext4_handle_valid(handle))
-		return jbd2_journal_inode_add_write(handle,
-						    EXT4_I(inode)->jinode);
+		return jbd2_journal_inode_ranged_write(handle,
+				EXT4_I(inode)->jinode, start_byte, length);
 	return 0;
 }
 
 static inline int ext4_jbd2_inode_add_wait(handle_t *handle,
-					   struct inode *inode)
+		struct inode *inode, loff_t start_byte, loff_t length)
 {
 	if (ext4_handle_valid(handle))
-		return jbd2_journal_inode_add_wait(handle,
-						   EXT4_I(inode)->jinode);
+		return jbd2_journal_inode_ranged_wait(handle,
+				EXT4_I(inode)->jinode, start_byte, length);
 	return 0;
 }
 

fs/ext4/extents.c

@@ -5676,8 +5676,8 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 }
 
 /**
- * ext4_swap_extents - Swap extents between two inodes
- *
+ * ext4_swap_extents() - Swap extents between two inodes
+ * @handle: handle for this transaction
  * @inode1:	First inode
  * @inode2:	Second inode
  * @lblk1:	Start block for first inode

fs/ext4/extents_status.c

@@ -1317,7 +1317,6 @@ static int es_do_reclaim_extents(struct ext4_inode_info *ei, ext4_lblk_t end,
 	es = __es_tree_search(&tree->root, ei->i_es_shrink_lblk);
 	if (!es)
 		goto out_wrap;
-	node = &es->rb_node;
 	while (*nr_to_scan > 0) {
 		if (es->es_lblk > end) {
 			ei->i_es_shrink_lblk = end + 1;

fs/ext4/file.c

@@ -165,6 +165,10 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
 	ret = generic_write_checks(iocb, from);
 	if (ret <= 0)
 		return ret;
+
+	if (unlikely(IS_IMMUTABLE(inode)))
+		return -EPERM;
+
 	/*
 	 * If we have encountered a bitmap-format file, the size limit
 	 * is smaller than s_maxbytes, which is for extent-mapped files.

fs/ext4/indirect.c

@@ -294,12 +294,10 @@ static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
 }
 
 /**
- *	ext4_alloc_branch - allocate and set up a chain of blocks.
+ * ext4_alloc_branch() - allocate and set up a chain of blocks
  * @handle: handle for this transaction
- *	@inode: owner
+ * @ar: structure describing the allocation request
  * @indirect_blks: number of allocated indirect blocks
- *	@blks: number of allocated direct blocks
- *	@goal: preferred place for allocation
  * @offsets: offsets (in the blocks) to store the pointers to next.
  * @branch: place to store the chain in.
  *
@@ -396,15 +394,11 @@ static int ext4_alloc_branch(handle_t *handle,
 }
 
 /**
- * ext4_splice_branch - splice the allocated branch onto inode.
+ * ext4_splice_branch() - splice the allocated branch onto inode.
  * @handle: handle for this transaction
- * @inode: owner
- * @block: (logical) number of block we are adding
- * @chain: chain of indirect blocks (with a missing link - see
- *	ext4_alloc_branch)
+ * @ar: structure describing the allocation request
  * @where: location of missing link
  * @num:   number of indirect blocks we are adding
- * @blks:  number of direct blocks we are adding
  *
  * This function fills the missing link and does all housekeeping needed in
  * inode (->i_blocks, etc.). In case of success we end up with the full

fs/ext4/inline.c

@@ -1132,7 +1132,6 @@ static int ext4_finish_convert_inline_dir(handle_t *handle,
 {
 	int err, csum_size = 0, header_size = 0;
 	struct ext4_dir_entry_2 *de;
-	struct ext4_dir_entry_tail *t;
 	void *target = dir_block->b_data;
 
 	/*
@@ -1158,13 +1157,11 @@ static int ext4_finish_convert_inline_dir(handle_t *handle,
 			inline_size - EXT4_INLINE_DOTDOT_SIZE + header_size,
 			inode->i_sb->s_blocksize - csum_size);
 
-	if (csum_size) {
-		t = EXT4_DIRENT_TAIL(dir_block->b_data,
+	if (csum_size)
+		ext4_initialize_dirent_tail(dir_block,
 					    inode->i_sb->s_blocksize);
-		initialize_dirent_tail(t, inode->i_sb->s_blocksize);
-	}
 	set_buffer_uptodate(dir_block);
-	err = ext4_handle_dirty_dirent_node(handle, inode, dir_block);
+	err = ext4_handle_dirty_dirblock(handle, inode, dir_block);
 	if (err)
 		return err;
 	set_buffer_verified(dir_block);
@@ -1327,7 +1324,7 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
  * inlined dir.  It returns the number directory entries loaded
  * into the tree.  If there is an error it is returned in err.
  */
-int htree_inlinedir_to_tree(struct file *dir_file,
+int ext4_inlinedir_to_tree(struct file *dir_file,
 			   struct inode *dir, ext4_lblk_t block,
 			   struct dx_hash_info *hinfo,
 			   __u32 start_hash, __u32 start_minor_hash,

fs/ext4/inode.c

@@ -731,10 +731,16 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		    !(flags & EXT4_GET_BLOCKS_ZERO) &&
 		    !ext4_is_quota_file(inode) &&
 		    ext4_should_order_data(inode)) {
+			loff_t start_byte =
+				(loff_t)map->m_lblk << inode->i_blkbits;
+			loff_t length = (loff_t)map->m_len << inode->i_blkbits;
+
 			if (flags & EXT4_GET_BLOCKS_IO_SUBMIT)
-				ret = ext4_jbd2_inode_add_wait(handle, inode);
+				ret = ext4_jbd2_inode_add_wait(handle, inode,
+						start_byte, length);
 			else
-				ret = ext4_jbd2_inode_add_write(handle, inode);
+				ret = ext4_jbd2_inode_add_write(handle, inode,
+						start_byte, length);
 			if (ret)
 				return ret;
 		}
@@ -4094,7 +4100,8 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 		err = 0;
 		mark_buffer_dirty(bh);
 		if (ext4_should_order_data(inode))
-			err = ext4_jbd2_inode_add_write(handle, inode);
+			err = ext4_jbd2_inode_add_write(handle, inode, from,
+					length);
 	}
 
 unlock:
@@ -4579,6 +4586,7 @@ static int __ext4_get_inode_loc(struct inode *inode,
 	struct buffer_head	*bh;
 	struct super_block	*sb = inode->i_sb;
 	ext4_fsblk_t		block;
+	struct blk_plug		plug;
 	int			inodes_per_block, inode_offset;
 
 	iloc->bh = NULL;
@@ -4667,6 +4675,7 @@ static int __ext4_get_inode_loc(struct inode *inode,
 		 * If we need to do any I/O, try to pre-readahead extra
 		 * blocks from the inode table.
 		 */
+		blk_start_plug(&plug);
 		if (EXT4_SB(sb)->s_inode_readahead_blks) {
 			ext4_fsblk_t b, end, table;
 			unsigned num;
@@ -4697,6 +4706,7 @@ static int __ext4_get_inode_loc(struct inode *inode,
 		get_bh(bh);
 		bh->b_end_io = end_buffer_read_sync;
 		submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh);
+		blk_finish_plug(&plug);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
 			EXT4_ERROR_INODE_BLOCK(inode, block,
@@ -5529,6 +5539,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
+	if (unlikely(IS_IMMUTABLE(inode)))
+		return -EPERM;
+
+	if (unlikely(IS_APPEND(inode) &&
+		     (ia_valid & (ATTR_MODE | ATTR_UID |
+				  ATTR_GID | ATTR_TIMES_SET))))
+		return -EPERM;
+
 	error = setattr_prepare(dentry, attr);
 	if (error)
 		return error;
@@ -5580,7 +5598,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 	if (attr->ia_valid & ATTR_SIZE) {
 		handle_t *handle;
 		loff_t oldsize = inode->i_size;
-		int shrink = (attr->ia_size <= inode->i_size);
+		int shrink = (attr->ia_size < inode->i_size);
 
 		if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
 			struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -5594,18 +5612,33 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size)
 			inode_inc_iversion(inode);
 
-		if (ext4_should_order_data(inode) &&
-		    (attr->ia_size < inode->i_size)) {
+		if (shrink) {
+			if (ext4_should_order_data(inode)) {
 				error = ext4_begin_ordered_truncate(inode,
 							    attr->ia_size);
 				if (error)
 					goto err_out;
 			}
+			/*
+			 * Blocks are going to be removed from the inode. Wait
+			 * for dio in flight.
+			 */
+			inode_dio_wait(inode);
+		}
+
+		down_write(&EXT4_I(inode)->i_mmap_sem);
+
+		rc = ext4_break_layouts(inode);
+		if (rc) {
+			up_write(&EXT4_I(inode)->i_mmap_sem);
+			return rc;
+		}
+
 		if (attr->ia_size != inode->i_size) {
 			handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
 			if (IS_ERR(handle)) {
 				error = PTR_ERR(handle);
-				goto err_out;
+				goto out_mmap_sem;
 			}
 			if (ext4_handle_valid(handle) && shrink) {
 				error = ext4_orphan_add(handle, inode);
@@ -5633,30 +5666,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 				i_size_write(inode, attr->ia_size);
 			up_write(&EXT4_I(inode)->i_data_sem);
 			ext4_journal_stop(handle);
-			if (error) {
-				if (orphan && inode->i_nlink)
-					ext4_orphan_del(NULL, inode);
-				goto err_out;
-			}
-		}
+			if (error)
+				goto out_mmap_sem;
 			if (!shrink) {
-			pagecache_isize_extended(inode, oldsize, inode->i_size);
-		} else {
-			/*
-			 * Blocks are going to be removed from the inode. Wait
-			 * for dio in flight.
-			 */
-			inode_dio_wait(inode);
-		}
-		if (orphan && ext4_should_journal_data(inode))
+				pagecache_isize_extended(inode, oldsize,
+							 inode->i_size);
+			} else if (ext4_should_journal_data(inode)) {
 				ext4_wait_for_tail_page_commit(inode);
-		down_write(&EXT4_I(inode)->i_mmap_sem);
-
-		rc = ext4_break_layouts(inode);
-		if (rc) {
-			up_write(&EXT4_I(inode)->i_mmap_sem);
-			error = rc;
-			goto err_out;
+			}
 		}
 
 		/*
@@ -5664,11 +5681,16 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		 * in data=journal mode to make pages freeable.
 		 */
 		truncate_pagecache(inode, inode->i_size);
-		if (shrink) {
+		/*
+		 * Call ext4_truncate() even if i_size didn't change to
+		 * truncate possible preallocated blocks.
+		 */
+		if (attr->ia_size <= oldsize) {
 			rc = ext4_truncate(inode);
 			if (rc)
 				error = rc;
 		}
+out_mmap_sem:
 		up_write(&EXT4_I(inode)->i_mmap_sem);
 	}
 
@@ -6199,6 +6221,9 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 	get_block_t *get_block;
 	int retries = 0;
 
+	if (unlikely(IS_IMMUTABLE(inode)))
+		return VM_FAULT_SIGBUS;
+
 	sb_start_pagefault(inode->i_sb);
 	file_update_time(vma->vm_file);
 

fs/ext4/ioctl.c

@@ -269,6 +269,29 @@ static int uuid_is_zero(__u8 u[16])
 }
 #endif
 
+/*
+ * If immutable is set and we are not clearing it, we're not allowed to change
+ * anything else in the inode.  Don't error out if we're only trying to set
+ * immutable on an immutable file.
+ */
+static int ext4_ioctl_check_immutable(struct inode *inode, __u32 new_projid,
+				      unsigned int flags)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	unsigned int oldflags = ei->i_flags;
+
+	if (!(oldflags & EXT4_IMMUTABLE_FL) || !(flags & EXT4_IMMUTABLE_FL))
+		return 0;
+
+	if ((oldflags & ~EXT4_IMMUTABLE_FL) != (flags & ~EXT4_IMMUTABLE_FL))
+		return -EPERM;
+	if (ext4_has_feature_project(inode->i_sb) &&
+	    __kprojid_val(ei->i_projid) != new_projid)
+		return -EPERM;
+
+	return 0;
+}
+
 static int ext4_ioctl_setflags(struct inode *inode,
 			       unsigned int flags)
 {
@@ -340,6 +363,20 @@ static int ext4_ioctl_setflags(struct inode *inode,
 		}
 	}
 
+	/*
+	 * Wait for all pending directio and then flush all the dirty pages
+	 * for this file.  The flush marks all the pages readonly, so any
+	 * subsequent attempt to write to the file (particularly mmap pages)
+	 * will come through the filesystem and fail.
+	 */
+	if (S_ISREG(inode->i_mode) && !IS_IMMUTABLE(inode) &&
+	    (flags & EXT4_IMMUTABLE_FL)) {
+		inode_dio_wait(inode);
+		err = filemap_write_and_wait(inode->i_mapping);
+		if (err)
+			goto flags_out;
+	}
+
 	handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
 	if (IS_ERR(handle)) {
 		err = PTR_ERR(handle);
@@ -742,6 +779,8 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return ext4_ioc_getfsmap(sb, (void __user *)arg);
 	case EXT4_IOC_GETFLAGS:
 		flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
+		if (S_ISREG(inode->i_mode))
+			flags &= ~EXT4_PROJINHERIT_FL;
 		return put_user(flags, (int __user *) arg);
 	case EXT4_IOC_SETFLAGS: {
 		int err;
@@ -769,6 +808,10 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			return err;
 
 		inode_lock(inode);
+		err = ext4_ioctl_check_immutable(inode,
+				from_kprojid(&init_user_ns, ei->i_projid),
+				flags);
+		if (!err)
 			err = ext4_ioctl_setflags(inode, flags);
 		inode_unlock(inode);
 		mnt_drop_write_file(filp);
@@ -1139,6 +1182,9 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			goto out;
 		flags = (ei->i_flags & ~EXT4_FL_XFLAG_VISIBLE) |
 			 (flags & EXT4_FL_XFLAG_VISIBLE);
+		err = ext4_ioctl_check_immutable(inode, fa.fsx_projid, flags);
+		if (err)
+			goto out;
 		err = ext4_ioctl_setflags(inode, flags);
 		if (err)
 			goto out;

fs/ext4/mballoc.c

@@ -4696,8 +4696,9 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
  * ext4_free_blocks() -- Free given blocks and update quota
  * @handle:		handle for this transaction
  * @inode:		inode
- * @block:		start physical block to free
- * @count:		number of blocks to count
+ * @bh:			optional buffer of the block to be freed
+ * @block:		starting physical block to be freed
+ * @count:		number of blocks to be freed
  * @flags:		flags used by ext4_free_blocks
  */
 void ext4_free_blocks(handle_t *handle, struct inode *inode,

fs/ext4/move_extent.c

@@ -13,11 +13,10 @@
 #include "ext4_extents.h"
 
 /**
- * get_ext_path - Find an extent path for designated logical block number.
- *
- * @inode:	an inode which is searched
+ * get_ext_path() - Find an extent path for designated logical block number.
+ * @inode:	inode to be searched
  * @lblock:	logical block number to find an extent path
- * @path:	pointer to an extent path pointer (for output)
+ * @ppath:	pointer to an extent path pointer (for output)
  *
  * ext4_find_extent wrapper. Return 0 on success, or a negative error value
  * on failure.
@@ -42,8 +41,9 @@ get_ext_path(struct inode *inode, ext4_lblk_t lblock,
 }
 
 /**
- * ext4_double_down_write_data_sem - Acquire two inodes' write lock
- *                                   of i_data_sem
+ * ext4_double_down_write_data_sem() - write lock two inodes's i_data_sem
+ * @first: inode to be locked
+ * @second: inode to be locked
  *
  * Acquire write lock of i_data_sem of the two inodes
  */
@@ -390,7 +390,8 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
 
 	/* Even in case of data=writeback it is reasonable to pin
 	 * inode to transaction, to prevent unexpected data loss */
-	*err = ext4_jbd2_inode_add_write(handle, orig_inode);
+	*err = ext4_jbd2_inode_add_write(handle, orig_inode,
+			(loff_t)orig_page_offset << PAGE_SHIFT, replaced_size);
 
 unlock_pages:
 	unlock_page(pagep[0]);

fs/ext4/sysfs.c

@@ -230,6 +230,7 @@ static struct attribute *ext4_attrs[] = {
 	ATTR_LIST(journal_task),
 	NULL,
 };
+ATTRIBUTE_GROUPS(ext4);
 
 /* Features this copy of ext4 supports */
 EXT4_ATTR_FEATURE(lazy_itable_init);
@@ -256,6 +257,7 @@ static struct attribute *ext4_feat_attrs[] = {
 	ATTR_LIST(metadata_csum_seed),
 	NULL,
 };
+ATTRIBUTE_GROUPS(ext4_feat);
 
 static void *calc_ptr(struct ext4_attr *a, struct ext4_sb_info *sbi)
 {
@@ -374,13 +376,13 @@ static const struct sysfs_ops ext4_attr_ops = {
 };
 
 static struct kobj_type ext4_sb_ktype = {
-	.default_attrs	= ext4_attrs,
+	.default_groups = ext4_groups,
 	.sysfs_ops	= &ext4_attr_ops,
 	.release	= ext4_sb_release,
 };
 
 static struct kobj_type ext4_feat_ktype = {
-	.default_attrs	= ext4_feat_attrs,
+	.default_groups = ext4_feat_groups,
 	.sysfs_ops	= &ext4_attr_ops,
 	.release	= (void (*)(struct kobject *))kfree,
 };

fs/jbd2/commit.c

@@ -184,17 +184,18 @@ static int journal_wait_on_commit_record(journal_t *journal,
 /*
  * write the filemap data using writepage() address_space_operations.
  * We don't do block allocation here even for delalloc. We don't
- * use writepages() because with dealyed allocation we may be doing
+ * use writepages() because with delayed allocation we may be doing
  * block allocation in writepages().
  */
-static int journal_submit_inode_data_buffers(struct address_space *mapping)
+static int journal_submit_inode_data_buffers(struct address_space *mapping,
+		loff_t dirty_start, loff_t dirty_end)
 {
 	int ret;
 	struct writeback_control wbc = {
 		.sync_mode =  WB_SYNC_ALL,
 		.nr_to_write = mapping->nrpages * 2,
-		.range_start = 0,
-		.range_end = i_size_read(mapping->host),
+		.range_start = dirty_start,
+		.range_end = dirty_end,
 	};
 
 	ret = generic_writepages(mapping, &wbc);
@@ -218,6 +219,9 @@ static int journal_submit_data_buffers(journal_t *journal,
 
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
+		loff_t dirty_start = jinode->i_dirty_start;
+		loff_t dirty_end = jinode->i_dirty_end;
+
 		if (!(jinode->i_flags & JI_WRITE_DATA))
 			continue;
 		mapping = jinode->i_vfs_inode->i_mapping;
@@ -230,7 +234,8 @@ static int journal_submit_data_buffers(journal_t *journal,
 		 * only allocated blocks here.
 		 */
 		trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
-		err = journal_submit_inode_data_buffers(mapping);
+		err = journal_submit_inode_data_buffers(mapping, dirty_start,
+				dirty_end);
 		if (!ret)
 			ret = err;
 		spin_lock(&journal->j_list_lock);
@@ -257,12 +262,16 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 	/* For locking, see the comment in journal_submit_data_buffers() */
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
+		loff_t dirty_start = jinode->i_dirty_start;
+		loff_t dirty_end = jinode->i_dirty_end;
+
 		if (!(jinode->i_flags & JI_WAIT_DATA))
 			continue;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
-		err = filemap_fdatawait_keep_errors(
-				jinode->i_vfs_inode->i_mapping);
+		err = filemap_fdatawait_range_keep_errors(
+				jinode->i_vfs_inode->i_mapping, dirty_start,
+				dirty_end);
 		if (!ret)
 			ret = err;
 		spin_lock(&journal->j_list_lock);
@@ -282,6 +291,8 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 				&jinode->i_transaction->t_inode_list);
 		} else {
 			jinode->i_transaction = NULL;
+			jinode->i_dirty_start = 0;
+			jinode->i_dirty_end = 0;
 		}
 	}
 	spin_unlock(&journal->j_list_lock);

fs/jbd2/journal.c

@@ -66,9 +66,6 @@ EXPORT_SYMBOL(jbd2_journal_get_undo_access);
 EXPORT_SYMBOL(jbd2_journal_set_triggers);
 EXPORT_SYMBOL(jbd2_journal_dirty_metadata);
 EXPORT_SYMBOL(jbd2_journal_forget);
-#if 0
-EXPORT_SYMBOL(journal_sync_buffer);
-#endif
 EXPORT_SYMBOL(jbd2_journal_flush);
 EXPORT_SYMBOL(jbd2_journal_revoke);
 
@@ -94,6 +91,8 @@ EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
 EXPORT_SYMBOL(jbd2_journal_force_commit);
 EXPORT_SYMBOL(jbd2_journal_inode_add_write);
 EXPORT_SYMBOL(jbd2_journal_inode_add_wait);
+EXPORT_SYMBOL(jbd2_journal_inode_ranged_write);
+EXPORT_SYMBOL(jbd2_journal_inode_ranged_wait);
 EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);
 EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
 EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
@@ -203,7 +202,7 @@ static int kjournald2(void *arg)
 	if (journal->j_flags & JBD2_UNMOUNT)
 		goto end_loop;
 
-	jbd_debug(1, "commit_sequence=%d, commit_request=%d\n",
+	jbd_debug(1, "commit_sequence=%u, commit_request=%u\n",
 		journal->j_commit_sequence, journal->j_commit_request);
 
 	if (journal->j_commit_sequence != journal->j_commit_request) {
@@ -500,7 +499,7 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t target)
 		 */
 
 		journal->j_commit_request = target;
-		jbd_debug(1, "JBD2: requesting commit %d/%d\n",
+		jbd_debug(1, "JBD2: requesting commit %u/%u\n",
 			  journal->j_commit_request,
 			  journal->j_commit_sequence);
 		journal->j_running_transaction->t_requested = jiffies;
@@ -698,12 +697,12 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 #ifdef CONFIG_JBD2_DEBUG
 	if (!tid_geq(journal->j_commit_request, tid)) {
 		printk(KERN_ERR
-		       "%s: error: j_commit_request=%d, tid=%d\n",
+		       "%s: error: j_commit_request=%u, tid=%u\n",
 		       __func__, journal->j_commit_request, tid);
 	}
 #endif
 	while (tid_gt(tid, journal->j_commit_sequence)) {
-		jbd_debug(1, "JBD2: want %d, j_commit_sequence=%d\n",
+		jbd_debug(1, "JBD2: want %u, j_commit_sequence=%u\n",
 				  tid, journal->j_commit_sequence);
 		read_unlock(&journal->j_state_lock);
 		wake_up(&journal->j_wait_commit);
@@ -944,7 +943,7 @@ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
 
 	trace_jbd2_update_log_tail(journal, tid, block, freed);
 	jbd_debug(1,
-		  "Cleaning journal tail from %d to %d (offset %lu), "
+		  "Cleaning journal tail from %u to %u (offset %lu), "
 		  "freeing %lu\n",
 		  journal->j_tail_sequence, tid, block, freed);
 
@@ -1318,7 +1317,7 @@ static int journal_reset(journal_t *journal)
 	 */
 	if (sb->s_start == 0) {
 		jbd_debug(1, "JBD2: Skipping superblock update on recovered sb "
-			"(start %ld, seq %d, errno %d)\n",
+			"(start %ld, seq %u, errno %d)\n",
 			journal->j_tail, journal->j_tail_sequence,
 			journal->j_errno);
 		journal->j_flags |= JBD2_FLUSHED;
@@ -1453,7 +1452,7 @@ static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
 		return;
 	}
 
-	jbd_debug(1, "JBD2: Marking journal as empty (seq %d)\n",
+	jbd_debug(1, "JBD2: Marking journal as empty (seq %u)\n",
 		  journal->j_tail_sequence);
 
 	sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
@@ -2574,6 +2573,8 @@ void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode)
 	jinode->i_next_transaction = NULL;
 	jinode->i_vfs_inode = inode;
 	jinode->i_flags = 0;
+	jinode->i_dirty_start = 0;
+	jinode->i_dirty_end = 0;
 	INIT_LIST_HEAD(&jinode->i_list);
 }
 

fs/jbd2/transaction.c

@@ -2565,7 +2565,7 @@ void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh)
  * File inode in the inode list of the handle's transaction
  */
 static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode,
-				   unsigned long flags)
+		unsigned long flags, loff_t start_byte, loff_t end_byte)
 {
 	transaction_t *transaction = handle->h_transaction;
 	journal_t *journal;
@@ -2577,26 +2577,17 @@ static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode,
 	jbd_debug(4, "Adding inode %lu, tid:%d\n", jinode->i_vfs_inode->i_ino,
 			transaction->t_tid);
 
-	/*
-	 * First check whether inode isn't already on the transaction's
-	 * lists without taking the lock. Note that this check is safe
-	 * without the lock as we cannot race with somebody removing inode
-	 * from the transaction. The reason is that we remove inode from the
-	 * transaction only in journal_release_jbd_inode() and when we commit
-	 * the transaction. We are guarded from the first case by holding
-	 * a reference to the inode. We are safe against the second case
-	 * because if jinode->i_transaction == transaction, commit code
-	 * cannot touch the transaction because we hold reference to it,
-	 * and if jinode->i_next_transaction == transaction, commit code
-	 * will only file the inode where we want it.
-	 */
-	if ((jinode->i_transaction == transaction ||
-	    jinode->i_next_transaction == transaction) &&
-	    (jinode->i_flags & flags) == flags)
-		return 0;
-
 	spin_lock(&journal->j_list_lock);
 	jinode->i_flags |= flags;
+
+	if (jinode->i_dirty_end) {
+		jinode->i_dirty_start = min(jinode->i_dirty_start, start_byte);
+		jinode->i_dirty_end = max(jinode->i_dirty_end, end_byte);
+	} else {
+		jinode->i_dirty_start = start_byte;
+		jinode->i_dirty_end = end_byte;
+	}
+
 	/* Is inode already attached where we need it? */
 	if (jinode->i_transaction == transaction ||
 	    jinode->i_next_transaction == transaction)
@@ -2631,12 +2622,28 @@ static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode,
 int jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *jinode)
 {
 	return jbd2_journal_file_inode(handle, jinode,
-				       JI_WRITE_DATA | JI_WAIT_DATA);
+			JI_WRITE_DATA | JI_WAIT_DATA, 0, LLONG_MAX);
 }
 
 int jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *jinode)
 {
-	return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA);
+	return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA, 0,
+			LLONG_MAX);
+}
+
+int jbd2_journal_inode_ranged_write(handle_t *handle,
+		struct jbd2_inode *jinode, loff_t start_byte, loff_t length)
+{
+	return jbd2_journal_file_inode(handle, jinode,
+			JI_WRITE_DATA | JI_WAIT_DATA, start_byte,
+			start_byte + length - 1);
+}
+
+int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *jinode,
+		loff_t start_byte, loff_t length)
+{
+	return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA,
+			start_byte, start_byte + length - 1);
 }
 
 /*

fs/unicode/utf8-core.c

@@ -73,6 +73,34 @@ int utf8_strncasecmp(const struct unicode_map *um,
 }
 EXPORT_SYMBOL(utf8_strncasecmp);
 
+/* String cf is expected to be a valid UTF-8 casefolded
+ * string.
+ */
+int utf8_strncasecmp_folded(const struct unicode_map *um,
+			    const struct qstr *cf,
+			    const struct qstr *s1)
+{
+	const struct utf8data *data = utf8nfdicf(um->version);
+	struct utf8cursor cur1;
+	int c1, c2;
+	int i = 0;
+
+	if (utf8ncursor(&cur1, data, s1->name, s1->len) < 0)
+		return -EINVAL;
+
+	do {
+		c1 = utf8byte(&cur1);
+		c2 = cf->name[i++];
+		if (c1 < 0)
+			return -EINVAL;
+		if (c1 != c2)
+			return 1;
+	} while (c1);
+
+	return 0;
+}
+EXPORT_SYMBOL(utf8_strncasecmp_folded);
+
 int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 		  unsigned char *dest, size_t dlen)
 {

include/linux/fs.h

@@ -2718,6 +2718,8 @@ extern int filemap_flush(struct address_space *);
 extern int filemap_fdatawait_keep_errors(struct address_space *mapping);
 extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
 				   loff_t lend);
+extern int filemap_fdatawait_range_keep_errors(struct address_space *mapping,
+		loff_t start_byte, loff_t end_byte);
 
 static inline int filemap_fdatawait(struct address_space *mapping)
 {

include/linux/jbd2.h

@@ -451,6 +451,22 @@ struct jbd2_inode {
 	 * @i_flags: Flags of inode [j_list_lock]
 	 */
 	unsigned long i_flags;
+
+	/**
+	 * @i_dirty_start:
+	 *
+	 * Offset in bytes where the dirty range for this inode starts.
+	 * [j_list_lock]
+	 */
+	loff_t i_dirty_start;
+
+	/**
+	 * @i_dirty_end:
+	 *
+	 * Inclusive offset in bytes where the dirty range for this inode
+	 * ends. [j_list_lock]
+	 */
+	loff_t i_dirty_end;
 };
 
 struct jbd2_revoke_table_s;
@@ -1357,7 +1373,6 @@ void		 jbd2_journal_set_triggers(struct buffer_head *,
 					   struct jbd2_buffer_trigger_type *type);
 extern int	 jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_forget (handle_t *, struct buffer_head *);
-extern void	 journal_sync_buffer (struct buffer_head *);
 extern int	 jbd2_journal_invalidatepage(journal_t *,
 				struct page *, unsigned int, unsigned int);
 extern int	 jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t);
@@ -1397,6 +1412,12 @@ extern int	   jbd2_journal_force_commit(journal_t *);
 extern int	   jbd2_journal_force_commit_nested(journal_t *);
 extern int	   jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *inode);
 extern int	   jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *inode);
+extern int	   jbd2_journal_inode_ranged_write(handle_t *handle,
+			struct jbd2_inode *inode, loff_t start_byte,
+			loff_t length);
+extern int	   jbd2_journal_inode_ranged_wait(handle_t *handle,
+			struct jbd2_inode *inode, loff_t start_byte,
+			loff_t length);
 extern int	   jbd2_journal_begin_ordered_truncate(journal_t *journal,
 				struct jbd2_inode *inode, loff_t new_size);
 extern void	   jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode);

include/linux/unicode.h

@@ -17,6 +17,9 @@ int utf8_strncmp(const struct unicode_map *um,
 
 int utf8_strncasecmp(const struct unicode_map *um,
 		 const struct qstr *s1, const struct qstr *s2);
+int utf8_strncasecmp_folded(const struct unicode_map *um,
+			    const struct qstr *cf,
+			    const struct qstr *s1);
 
 int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 		   unsigned char *dest, size_t dlen);

mm/filemap.c

@@ -549,6 +549,28 @@ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
 }
 EXPORT_SYMBOL(filemap_fdatawait_range);
 
+/**
+ * filemap_fdatawait_range_keep_errors - wait for writeback to complete
+ * @mapping:		address space structure to wait for
+ * @start_byte:		offset in bytes where the range starts
+ * @end_byte:		offset in bytes where the range ends (inclusive)
+ *
+ * Walk the list of under-writeback pages of the given address space in the
+ * given range and wait for all of them.  Unlike filemap_fdatawait_range(),
+ * this function does not clear error status of the address space.
+ *
+ * Use this function if callers don't handle errors themselves.  Expected
+ * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
+ * fsfreeze(8)
+ */
+int filemap_fdatawait_range_keep_errors(struct address_space *mapping,
+		loff_t start_byte, loff_t end_byte)
+{
+	__filemap_fdatawait_range(mapping, start_byte, end_byte);
+	return filemap_check_and_keep_errors(mapping);
+}
+EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors);
+
 /**
  * file_fdatawait_range - wait for writeback to complete
  * @file:		file pointing to address space structure to wait for