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

Pull ext4 update from Ted Ts'o:
 "There are two major features for this merge window.  The first is
  inline data, which allows small files or directories to be stored in
  the in-inode extended attribute area.  (This requires that the file
  system use inodes which are at least 256 bytes or larger; 128 byte
  inodes do not have any room for in-inode xattrs.)

  The second new feature is SEEK_HOLE/SEEK_DATA support.  This is
  enabled by the extent status tree patches, and this infrastructure
  will be used to further optimize ext4 in the future.

  Beyond that, we have the usual collection of code cleanups and bug
  fixes."

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (63 commits)
  ext4: zero out inline data using memset() instead of empty_zero_page
  ext4: ensure Inode flags consistency are checked at build time
  ext4: Remove CONFIG_EXT4_FS_XATTR
  ext4: remove unused variable from ext4_ext_in_cache()
  ext4: remove redundant initialization in ext4_fill_super()
  ext4: remove redundant code in ext4_alloc_inode()
  ext4: use sync_inode_metadata() when syncing inode metadata
  ext4: enable ext4 inline support
  ext4: let fallocate handle inline data correctly
  ext4: let ext4_truncate handle inline data correctly
  ext4: evict inline data out if we need to strore xattr in inode
  ext4: let fiemap work with inline data
  ext4: let ext4_rename handle inline dir
  ext4: let empty_dir handle inline dir
  ext4: let ext4_delete_entry() handle inline data
  ext4: make ext4_delete_entry generic
  ext4: let ext4_find_entry handle inline data
  ext4: create a new function search_dir
  ext4: let ext4_readdir handle inline data
  ext4: let add_dir_entry handle inline data properly
  ...

Documentation/filesystems/ext4.txt

@@ -200,12 +200,9 @@ inode_readahead_blks=n	This tuning parameter controls the maximum
 			table readahead algorithm will pre-read into
 			the buffer cache.  The default value is 32 blocks.
 
-nouser_xattr		Disables Extended User Attributes. If you have extended
-			attribute support enabled in the kernel configuration
-			(CONFIG_EXT4_FS_XATTR), extended attribute support
-			is enabled by default on mount. See the attr(5) manual
-			page and http://acl.bestbits.at/ for more information
-			about extended attributes.
+nouser_xattr		Disables Extended User Attributes.  See the
+			attr(5) manual page and http://acl.bestbits.at/
+			for more information about extended attributes.
 
 noacl			This option disables POSIX Access Control List
 			support. If ACL support is enabled in the kernel

fs/Kconfig

@@ -28,8 +28,8 @@ config FS_MBCACHE
 	tristate
 	default y if EXT2_FS=y && EXT2_FS_XATTR
 	default y if EXT3_FS=y && EXT3_FS_XATTR
-	default y if EXT4_FS=y && EXT4_FS_XATTR
-	default m if EXT2_FS_XATTR || EXT3_FS_XATTR || EXT4_FS_XATTR
+	default y if EXT4_FS=y
+	default m if EXT2_FS_XATTR || EXT3_FS_XATTR || EXT4_FS
 
 source "fs/reiserfs/Kconfig"
 source "fs/jfs/Kconfig"

fs/ext4/Kconfig

@@ -39,22 +39,8 @@ config EXT4_USE_FOR_EXT23
 	  compiled kernel size by using one file system driver for
 	  ext2, ext3, and ext4 file systems.
 
-config EXT4_FS_XATTR
-	bool "Ext4 extended attributes"
-	depends on EXT4_FS
-	default y
-	help
-	  Extended attributes are name:value pairs associated with inodes by
-	  the kernel or by users (see the attr(5) manual page, or visit
-	  <http://acl.bestbits.at/> for details).
-
-	  If unsure, say N.
-
-	  You need this for POSIX ACL support on ext4.
-
 config EXT4_FS_POSIX_ACL
 	bool "Ext4 POSIX Access Control Lists"
-	depends on EXT4_FS_XATTR
 	select FS_POSIX_ACL
 	help
 	  POSIX Access Control Lists (ACLs) support permissions for users and
@@ -67,7 +53,6 @@ config EXT4_FS_POSIX_ACL
 
 config EXT4_FS_SECURITY
 	bool "Ext4 Security Labels"
-	depends on EXT4_FS_XATTR
 	help
 	  Security labels support alternative access control models
 	  implemented by security modules like SELinux.  This option

fs/ext4/Makefile

@@ -7,8 +7,8 @@ obj-$(CONFIG_EXT4_FS) += ext4.o
 ext4-y	:= balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \
 		ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
 		ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \
-		mmp.o indirect.o
+		mmp.o indirect.o extents_status.o xattr.o xattr_user.o \
+		xattr_trusted.o inline.o
 
-ext4-$(CONFIG_EXT4_FS_XATTR)		+= xattr.o xattr_user.o xattr_trusted.o
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
 ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o

fs/ext4/acl.c

@@ -423,8 +423,10 @@ ext4_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
 
 retry:
 	handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
-	if (IS_ERR(handle))
-		return PTR_ERR(handle);
+	if (IS_ERR(handle)) {
+		error = PTR_ERR(handle);
+		goto release_and_out;
+	}
 	error = ext4_set_acl(handle, inode, type, acl);
 	ext4_journal_stop(handle);
 	if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))

fs/ext4/dir.c

@@ -27,23 +27,11 @@
 #include <linux/slab.h>
 #include <linux/rbtree.h>
 #include "ext4.h"
-
-static unsigned char ext4_filetype_table[] = {
-	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
-};
+#include "xattr.h"
 
 static int ext4_dx_readdir(struct file *filp,
 			   void *dirent, filldir_t filldir);
 
-static unsigned char get_dtype(struct super_block *sb, int filetype)
-{
-	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE) ||
-	    (filetype >= EXT4_FT_MAX))
-		return DT_UNKNOWN;
-
-	return (ext4_filetype_table[filetype]);
-}
-
 /**
  * Check if the given dir-inode refers to an htree-indexed directory
  * (or a directory which chould potentially get coverted to use htree
@@ -68,11 +56,14 @@ static int is_dx_dir(struct inode *inode)
  * Return 0 if the directory entry is OK, and 1 if there is a problem
  *
  * Note: this is the opposite of what ext2 and ext3 historically returned...
+ *
+ * bh passed here can be an inode block or a dir data block, depending
+ * on the inode inline data flag.
  */
 int __ext4_check_dir_entry(const char *function, unsigned int line,
 			   struct inode *dir, struct file *filp,
 			   struct ext4_dir_entry_2 *de,
-			   struct buffer_head *bh,
+			   struct buffer_head *bh, char *buf, int size,
 			   unsigned int offset)
 {
 	const char *error_msg = NULL;
@@ -85,9 +76,8 @@ int __ext4_check_dir_entry(const char *function, unsigned int line,
 		error_msg = "rec_len % 4 != 0";
 	else if (unlikely(rlen < EXT4_DIR_REC_LEN(de->name_len)))
 		error_msg = "rec_len is too small for name_len";
-	else if (unlikely(((char *) de - bh->b_data) + rlen >
-			  dir->i_sb->s_blocksize))
-		error_msg = "directory entry across blocks";
+	else if (unlikely(((char *) de - buf) + rlen > size))
+		error_msg = "directory entry across range";
 	else if (unlikely(le32_to_cpu(de->inode) >
 			le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count)))
 		error_msg = "inode out of bounds";
@@ -98,14 +88,14 @@ int __ext4_check_dir_entry(const char *function, unsigned int line,
 		ext4_error_file(filp, function, line, bh->b_blocknr,
 				"bad entry in directory: %s - offset=%u(%u), "
 				"inode=%u, rec_len=%d, name_len=%d",
-				error_msg, (unsigned) (offset % bh->b_size),
+				error_msg, (unsigned) (offset % size),
 				offset, le32_to_cpu(de->inode),
 				rlen, de->name_len);
 	else
 		ext4_error_inode(dir, function, line, bh->b_blocknr,
 				"bad entry in directory: %s - offset=%u(%u), "
 				"inode=%u, rec_len=%d, name_len=%d",
-				error_msg, (unsigned) (offset % bh->b_size),
+				error_msg, (unsigned) (offset % size),
 				offset, le32_to_cpu(de->inode),
 				rlen, de->name_len);
 
@@ -125,6 +115,14 @@ static int ext4_readdir(struct file *filp,
 	int ret = 0;
 	int dir_has_error = 0;
 
+	if (ext4_has_inline_data(inode)) {
+		int has_inline_data = 1;
+		ret = ext4_read_inline_dir(filp, dirent, filldir,
+					   &has_inline_data);
+		if (has_inline_data)
+			return ret;
+	}
+
 	if (is_dx_dir(inode)) {
 		err = ext4_dx_readdir(filp, dirent, filldir);
 		if (err != ERR_BAD_DX_DIR) {
@@ -221,8 +219,9 @@ static int ext4_readdir(struct file *filp,
 		while (!error && filp->f_pos < inode->i_size
 		       && offset < sb->s_blocksize) {
 			de = (struct ext4_dir_entry_2 *) (bh->b_data + offset);
-			if (ext4_check_dir_entry(inode, filp, de,
-						 bh, offset)) {
+			if (ext4_check_dir_entry(inode, filp, de, bh,
+						 bh->b_data, bh->b_size,
+						 offset)) {
 				/*
 				 * On error, skip the f_pos to the next block
 				 */

fs/ext4/ext4_extents.h

@@ -42,16 +42,6 @@
  */
 #define CHECK_BINSEARCH__
 
-/*
- * Turn on EXT_DEBUG to get lots of info about extents operations.
- */
-#define EXT_DEBUG__
-#ifdef EXT_DEBUG
-#define ext_debug(fmt, ...)	printk(fmt, ##__VA_ARGS__)
-#else
-#define ext_debug(fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
-#endif
-
 /*
  * If EXT_STATS is defined then stats numbers are collected.
  * These number will be displayed at umount time.
@@ -143,20 +133,6 @@ struct ext4_ext_path {
  * structure for external API
  */
 
-/*
- * to be called by ext4_ext_walk_space()
- * negative retcode - error
- * positive retcode - signal for ext4_ext_walk_space(), see below
- * callback must return valid extent (passed or newly created)
- */
-typedef int (*ext_prepare_callback)(struct inode *, ext4_lblk_t,
-					struct ext4_ext_cache *,
-					struct ext4_extent *, void *);
-
-#define EXT_CONTINUE   0
-#define EXT_BREAK      1
-#define EXT_REPEAT     2
-
 /*
  * Maximum number of logical blocks in a file; ext4_extent's ee_block is
  * __le32.
@@ -300,21 +276,5 @@ static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix,
 				     0xffff);
 }
 
-extern int ext4_ext_calc_metadata_amount(struct inode *inode,
-					 ext4_lblk_t lblocks);
-extern int ext4_extent_tree_init(handle_t *, struct inode *);
-extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
-						   int num,
-						   struct ext4_ext_path *path);
-extern int ext4_can_extents_be_merged(struct inode *inode,
-				      struct ext4_extent *ex1,
-				      struct ext4_extent *ex2);
-extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *, int);
-extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
-							struct ext4_ext_path *);
-extern void ext4_ext_drop_refs(struct ext4_ext_path *);
-extern int ext4_ext_check_inode(struct inode *inode);
-extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk,
-				      int search_hint_reverse);
 #endif /* _EXT4_EXTENTS */
 

fs/ext4/ext4_jbd2.h

@@ -254,13 +254,6 @@ static inline void ext4_handle_sync(handle_t *handle)
 		handle->h_sync = 1;
 }
 
-static inline void ext4_handle_release_buffer(handle_t *handle,
-						struct buffer_head *bh)
-{
-	if (ext4_handle_valid(handle))
-		jbd2_journal_release_buffer(handle, bh);
-}
-
 static inline int ext4_handle_is_aborted(handle_t *handle)
 {
 	if (ext4_handle_valid(handle))

fs/ext4/extents_status.h

+/*
+ *  fs/ext4/extents_status.h
+ *
+ * Written by Yongqiang Yang <xiaoqiangnk@gmail.com>
+ * Modified by
+ *	Allison Henderson <achender@linux.vnet.ibm.com>
+ *	Zheng Liu <wenqing.lz@taobao.com>
+ *
+ */
+
+#ifndef _EXT4_EXTENTS_STATUS_H
+#define _EXT4_EXTENTS_STATUS_H
+
+/*
+ * Turn on ES_DEBUG__ to get lots of info about extent status operations.
+ */
+#ifdef ES_DEBUG__
+#define es_debug(fmt, ...)	printk(fmt, ##__VA_ARGS__)
+#else
+#define es_debug(fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
+#endif
+
+struct extent_status {
+	struct rb_node rb_node;
+	ext4_lblk_t start;	/* first block extent covers */
+	ext4_lblk_t len;	/* length of extent in block */
+};
+
+struct ext4_es_tree {
+	struct rb_root root;
+	struct extent_status *cache_es;	/* recently accessed extent */
+};
+
+extern int __init ext4_init_es(void);
+extern void ext4_exit_es(void);
+extern void ext4_es_init_tree(struct ext4_es_tree *tree);
+
+extern int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t start,
+				 ext4_lblk_t len);
+extern int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t start,
+				 ext4_lblk_t len);
+extern ext4_lblk_t ext4_es_find_extent(struct inode *inode,
+				struct extent_status *es);
+
+#endif /* _EXT4_EXTENTS_STATUS_H */

fs/ext4/file.c

@@ -24,6 +24,7 @@
 #include <linux/mount.h>
 #include <linux/path.h>
 #include <linux/quotaops.h>
+#include <linux/pagevec.h>
 #include "ext4.h"
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -285,6 +286,324 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	return dquot_file_open(inode, filp);
 }
 
+/*
+ * Here we use ext4_map_blocks() to get a block mapping for a extent-based
+ * file rather than ext4_ext_walk_space() because we can introduce
+ * SEEK_DATA/SEEK_HOLE for block-mapped and extent-mapped file at the same
+ * function.  When extent status tree has been fully implemented, it will
+ * track all extent status for a file and we can directly use it to
+ * retrieve the offset for SEEK_DATA/SEEK_HOLE.
+ */
+
+/*
+ * When we retrieve the offset for SEEK_DATA/SEEK_HOLE, we would need to
+ * lookup page cache to check whether or not there has some data between
+ * [startoff, endoff] because, if this range contains an unwritten extent,
+ * we determine this extent as a data or a hole according to whether the
+ * page cache has data or not.
+ */
+static int ext4_find_unwritten_pgoff(struct inode *inode,
+				     int origin,
+				     struct ext4_map_blocks *map,
+				     loff_t *offset)
+{
+	struct pagevec pvec;
+	unsigned int blkbits;
+	pgoff_t index;
+	pgoff_t end;
+	loff_t endoff;
+	loff_t startoff;
+	loff_t lastoff;
+	int found = 0;
+
+	blkbits = inode->i_sb->s_blocksize_bits;
+	startoff = *offset;
+	lastoff = startoff;
+	endoff = (map->m_lblk + map->m_len) << blkbits;
+
+	index = startoff >> PAGE_CACHE_SHIFT;
+	end = endoff >> PAGE_CACHE_SHIFT;
+
+	pagevec_init(&pvec, 0);
+	do {
+		int i, num;
+		unsigned long nr_pages;
+
+		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
+		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
+					  (pgoff_t)num);
+		if (nr_pages == 0) {
+			if (origin == SEEK_DATA)
+				break;
+
+			BUG_ON(origin != SEEK_HOLE);
+			/*
+			 * If this is the first time to go into the loop and
+			 * offset is not beyond the end offset, it will be a
+			 * hole at this offset
+			 */
+			if (lastoff == startoff || lastoff < endoff)
+				found = 1;
+			break;
+		}
+
+		/*
+		 * If this is the first time to go into the loop and
+		 * offset is smaller than the first page offset, it will be a
+		 * hole at this offset.
+		 */
+		if (lastoff == startoff && origin == SEEK_HOLE &&
+		    lastoff < page_offset(pvec.pages[0])) {
+			found = 1;
+			break;
+		}
+
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+			struct buffer_head *bh, *head;
+
+			/*
+			 * If the current offset is not beyond the end of given
+			 * range, it will be a hole.
+			 */
+			if (lastoff < endoff && origin == SEEK_HOLE &&
+			    page->index > end) {
+				found = 1;
+				*offset = lastoff;
+				goto out;
+			}
+
+			lock_page(page);
+
+			if (unlikely(page->mapping != inode->i_mapping)) {
+				unlock_page(page);
+				continue;
+			}
+
+			if (!page_has_buffers(page)) {
+				unlock_page(page);
+				continue;
+			}
+
+			if (page_has_buffers(page)) {
+				lastoff = page_offset(page);
+				bh = head = page_buffers(page);
+				do {
+					if (buffer_uptodate(bh) ||
+					    buffer_unwritten(bh)) {
+						if (origin == SEEK_DATA)
+							found = 1;
+					} else {
+						if (origin == SEEK_HOLE)
+							found = 1;
+					}
+					if (found) {
+						*offset = max_t(loff_t,
+							startoff, lastoff);
+						unlock_page(page);
+						goto out;
+					}
+					lastoff += bh->b_size;
+					bh = bh->b_this_page;
+				} while (bh != head);
+			}
+
+			lastoff = page_offset(page) + PAGE_SIZE;
+			unlock_page(page);
+		}
+
+		/*
+		 * The no. of pages is less than our desired, that would be a
+		 * hole in there.
+		 */
+		if (nr_pages < num && origin == SEEK_HOLE) {
+			found = 1;
+			*offset = lastoff;
+			break;
+		}
+
+		index = pvec.pages[i - 1]->index + 1;
+		pagevec_release(&pvec);
+	} while (index <= end);
+
+out:
+	pagevec_release(&pvec);
+	return found;
+}
+
+/*
+ * ext4_seek_data() retrieves the offset for SEEK_DATA.
+ */
+static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
+{
+	struct inode *inode = file->f_mapping->host;
+	struct ext4_map_blocks map;
+	struct extent_status es;
+	ext4_lblk_t start, last, end;
+	loff_t dataoff, isize;
+	int blkbits;
+	int ret = 0;
+
+	mutex_lock(&inode->i_mutex);
+
+	isize = i_size_read(inode);
+	if (offset >= isize) {
+		mutex_unlock(&inode->i_mutex);
+		return -ENXIO;
+	}
+
+	blkbits = inode->i_sb->s_blocksize_bits;
+	start = offset >> blkbits;
+	last = start;
+	end = isize >> blkbits;
+	dataoff = offset;
+
+	do {
+		map.m_lblk = last;
+		map.m_len = end - last + 1;
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
+			if (last != start)
+				dataoff = last << blkbits;
+			break;
+		}
+
+		/*
+		 * If there is a delay extent at this offset,
+		 * it will be as a data.
+		 */
+		es.start = last;
+		(void)ext4_es_find_extent(inode, &es);
+		if (last >= es.start &&
+		    last < es.start + es.len) {
+			if (last != start)
+				dataoff = last << blkbits;
+			break;
+		}
+
+		/*
+		 * If there is a unwritten extent at this offset,
+		 * it will be as a data or a hole according to page
+		 * cache that has data or not.
+		 */
+		if (map.m_flags & EXT4_MAP_UNWRITTEN) {
+			int unwritten;
+			unwritten = ext4_find_unwritten_pgoff(inode, SEEK_DATA,
+							      &map, &dataoff);
+			if (unwritten)
+				break;
+		}
+
+		last++;
+		dataoff = last << blkbits;
+	} while (last <= end);
+
+	mutex_unlock(&inode->i_mutex);
+
+	if (dataoff > isize)
+		return -ENXIO;
+
+	if (dataoff < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
+		return -EINVAL;
+	if (dataoff > maxsize)
+		return -EINVAL;
+
+	if (dataoff != file->f_pos) {
+		file->f_pos = dataoff;
+		file->f_version = 0;
+	}
+
+	return dataoff;
+}
+
+/*
+ * ext4_seek_hole() retrieves the offset for SEEK_HOLE.
+ */
+static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
+{
+	struct inode *inode = file->f_mapping->host;
+	struct ext4_map_blocks map;
+	struct extent_status es;
+	ext4_lblk_t start, last, end;
+	loff_t holeoff, isize;
+	int blkbits;
+	int ret = 0;
+
+	mutex_lock(&inode->i_mutex);
+
+	isize = i_size_read(inode);
+	if (offset >= isize) {
+		mutex_unlock(&inode->i_mutex);
+		return -ENXIO;
+	}
+
+	blkbits = inode->i_sb->s_blocksize_bits;
+	start = offset >> blkbits;
+	last = start;
+	end = isize >> blkbits;
+	holeoff = offset;
+
+	do {
+		map.m_lblk = last;
+		map.m_len = end - last + 1;
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
+			last += ret;
+			holeoff = last << blkbits;
+			continue;
+		}
+
+		/*
+		 * If there is a delay extent at this offset,
+		 * we will skip this extent.
+		 */
+		es.start = last;
+		(void)ext4_es_find_extent(inode, &es);
+		if (last >= es.start &&
+		    last < es.start + es.len) {
+			last = es.start + es.len;
+			holeoff = last << blkbits;
+			continue;
+		}
+
+		/*
+		 * If there is a unwritten extent at this offset,
+		 * it will be as a data or a hole according to page
+		 * cache that has data or not.
+		 */
+		if (map.m_flags & EXT4_MAP_UNWRITTEN) {
+			int unwritten;
+			unwritten = ext4_find_unwritten_pgoff(inode, SEEK_HOLE,
+							      &map, &holeoff);
+			if (!unwritten) {
+				last += ret;
+				holeoff = last << blkbits;
+				continue;
+			}
+		}
+
+		/* find a hole */
+		break;
+	} while (last <= end);
+
+	mutex_unlock(&inode->i_mutex);
+
+	if (holeoff > isize)
+		holeoff = isize;
+
+	if (holeoff < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
+		return -EINVAL;
+	if (holeoff > maxsize)
+		return -EINVAL;
+
+	if (holeoff != file->f_pos) {
+		file->f_pos = holeoff;
+		file->f_version = 0;
+	}
+
+	return holeoff;
+}
+
 /*
  * ext4_llseek() handles both block-mapped and extent-mapped maxbytes values
  * by calling generic_file_llseek_size() with the appropriate maxbytes
@@ -300,8 +619,19 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
 	else
 		maxbytes = inode->i_sb->s_maxbytes;
 
-	return generic_file_llseek_size(file, offset, origin,
-					maxbytes, i_size_read(inode));
+	switch (origin) {
+	case SEEK_SET:
+	case SEEK_CUR:
+	case SEEK_END:
+		return generic_file_llseek_size(file, offset, origin,
+						maxbytes, i_size_read(inode));
+	case SEEK_DATA:
+		return ext4_seek_data(file, offset, maxbytes);
+	case SEEK_HOLE:
+		return ext4_seek_hole(file, offset, maxbytes);
+	}
+
+	return -EINVAL;
 }
 
 const struct file_operations ext4_file_operations = {
@@ -326,12 +656,10 @@ const struct file_operations ext4_file_operations = {
 const struct inode_operations ext4_file_inode_operations = {
 	.setattr	= ext4_setattr,
 	.getattr	= ext4_getattr,
-#ifdef CONFIG_EXT4_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr	= ext4_listxattr,
 	.removexattr	= generic_removexattr,
-#endif
 	.get_acl	= ext4_get_acl,
 	.fiemap		= ext4_fiemap,
 };

fs/ext4/fsync.c

@@ -44,7 +44,6 @@
  */
 static int ext4_sync_parent(struct inode *inode)
 {
-	struct writeback_control wbc;
 	struct dentry *dentry = NULL;
 	struct inode *next;
 	int ret = 0;
@@ -66,10 +65,7 @@ static int ext4_sync_parent(struct inode *inode)
 		ret = sync_mapping_buffers(inode->i_mapping);
 		if (ret)
 			break;
-		memset(&wbc, 0, sizeof(wbc));
-		wbc.sync_mode = WB_SYNC_ALL;
-		wbc.nr_to_write = 0;         /* only write out the inode */
-		ret = sync_inode(inode, &wbc);
+		ret = sync_inode_metadata(inode, 1);
 		if (ret)
 			break;
 	}

fs/ext4/ialloc.c

@@ -762,7 +762,6 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, umode_t mode,
 
 		BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
 		err = ext4_handle_dirty_metadata(handle, NULL, block_bitmap_bh);
-		brelse(block_bitmap_bh);
 
 		/* recheck and clear flag under lock if we still need to */
 		ext4_lock_group(sb, group);
@@ -775,6 +774,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, umode_t mode,
 			ext4_group_desc_csum_set(sb, group, gdp);
 		}
 		ext4_unlock_group(sb, group);
+		brelse(block_bitmap_bh);
 
 		if (err)
 			goto fail;
@@ -902,6 +902,10 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, umode_t mode,
 
 	ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
 
+	ei->i_inline_off = 0;
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_INLINE_DATA))
+		ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
+
 	ret = inode;
 	dquot_initialize(inode);
 	err = dquot_alloc_inode(inode);

fs/ext4/indirect.c

@@ -22,6 +22,7 @@
 
 #include "ext4_jbd2.h"
 #include "truncate.h"
+#include "ext4_extents.h"	/* Needed for EXT_MAX_BLOCKS */
 
 #include <trace/events/ext4.h>
 
@@ -755,8 +756,7 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 		partial--;
 	}
 out:
-	trace_ext4_ind_map_blocks_exit(inode, map->m_lblk,
-				map->m_pblk, map->m_len, err);
+	trace_ext4_ind_map_blocks_exit(inode, map, err);
 	return err;
 }
 
@@ -1412,6 +1412,7 @@ void ext4_ind_truncate(struct inode *inode)
 	down_write(&ei->i_data_sem);
 
 	ext4_discard_preallocations(inode);
+	ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block);
 
 	/*
 	 * The orphan list entry will now protect us from any crash which

fs/ext4/mballoc.c

@@ -1373,7 +1373,7 @@ static int mb_find_extent(struct ext4_buddy *e4b, int block,
 	ex->fe_start += next;
 
 	while (needed > ex->fe_len &&
-	       (buddy = mb_find_buddy(e4b, order, &max))) {
+	       mb_find_buddy(e4b, order, &max)) {
 
 		if (block + 1 >= max)
 			break;
@@ -2607,9 +2607,17 @@ static void ext4_free_data_callback(struct super_block *sb,
 	mb_debug(1, "gonna free %u blocks in group %u (0x%p):",
 		 entry->efd_count, entry->efd_group, entry);
 
-	if (test_opt(sb, DISCARD))
-		ext4_issue_discard(sb, entry->efd_group,
-				   entry->efd_start_cluster, entry->efd_count);
+	if (test_opt(sb, DISCARD)) {
+		err = ext4_issue_discard(sb, entry->efd_group,
+					 entry->efd_start_cluster,
+					 entry->efd_count);
+		if (err && err != -EOPNOTSUPP)
+			ext4_msg(sb, KERN_WARNING, "discard request in"
+				 " group:%d block:%d count:%d failed"
+				 " with %d", entry->efd_group,
+				 entry->efd_start_cluster,
+				 entry->efd_count, err);
+	}
 
 	err = ext4_mb_load_buddy(sb, entry->efd_group, &e4b);
 	/* we expect to find existing buddy because it's pinned */
@@ -4310,8 +4318,10 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 repeat:
 		/* allocate space in core */
 		*errp = ext4_mb_regular_allocator(ac);
-		if (*errp)
+		if (*errp) {
+			ext4_discard_allocated_blocks(ac);
 			goto errout;
+		}
 
 		/* as we've just preallocated more space than
 		 * user requested orinally, we store allocated
@@ -4333,10 +4343,10 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 			ac->ac_b_ex.fe_len = 0;
 			ac->ac_status = AC_STATUS_CONTINUE;
 			goto repeat;
-		} else if (*errp)
-		errout:
+		} else if (*errp) {
 			ext4_discard_allocated_blocks(ac);
-		else {
+			goto errout;
+		} else {
 			block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
 			ar->len = ac->ac_b_ex.fe_len;
 		}
@@ -4347,6 +4357,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 		*errp = -ENOSPC;
 	}
 
+errout:
 	if (*errp) {
 		ac->ac_b_ex.fe_len = 0;
 		ar->len = 0;
@@ -4656,8 +4667,16 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 		 * with group lock held. generate_buddy look at
 		 * them with group lock_held
 		 */
-		if (test_opt(sb, DISCARD))
-			ext4_issue_discard(sb, block_group, bit, count);
+		if (test_opt(sb, DISCARD)) {
+			err = ext4_issue_discard(sb, block_group, bit, count);
+			if (err && err != -EOPNOTSUPP)
+				ext4_msg(sb, KERN_WARNING, "discard request in"
+					 " group:%d block:%d count:%lu failed"
+					 " with %d", block_group, bit, count,
+					 err);
+		}
+
+
 		ext4_lock_group(sb, block_group);
 		mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
 		mb_free_blocks(inode, &e4b, bit, count_clusters);
@@ -4851,10 +4870,11 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
  * one will allocate those blocks, mark it as used in buddy bitmap. This must
  * be called with under the group lock.
  */
-static void ext4_trim_extent(struct super_block *sb, int start, int count,
+static int ext4_trim_extent(struct super_block *sb, int start, int count,
 			     ext4_group_t group, struct ext4_buddy *e4b)
 {
 	struct ext4_free_extent ex;
+	int ret = 0;
 
 	trace_ext4_trim_extent(sb, group, start, count);
 
@@ -4870,9 +4890,10 @@ static void ext4_trim_extent(struct super_block *sb, int start, int count,
 	 */
 	mb_mark_used(e4b, &ex);
 	ext4_unlock_group(sb, group);
-	ext4_issue_discard(sb, group, start, count);
+	ret = ext4_issue_discard(sb, group, start, count);
 	ext4_lock_group(sb, group);
 	mb_free_blocks(NULL, e4b, start, ex.fe_len);
+	return ret;
 }
 
 /**
@@ -4901,7 +4922,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 	void *bitmap;
 	ext4_grpblk_t next, count = 0, free_count = 0;
 	struct ext4_buddy e4b;
-	int ret;
+	int ret = 0;
 
 	trace_ext4_trim_all_free(sb, group, start, max);
 
@@ -4928,8 +4949,11 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 		next = mb_find_next_bit(bitmap, max + 1, start);
 
 		if ((next - start) >= minblocks) {
-			ext4_trim_extent(sb, start,
-					 next - start, group, &e4b);
+			ret = ext4_trim_extent(sb, start,
+					       next - start, group, &e4b);
+			if (ret && ret != -EOPNOTSUPP)
+				break;
+			ret = 0;
 			count += next - start;
 		}
 		free_count += next - start;
@@ -4950,8 +4974,10 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 			break;
 	}
 
-	if (!ret)
+	if (!ret) {
+		ret = count;
 		EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info);
+	}
 out:
 	ext4_unlock_group(sb, group);
 	ext4_mb_unload_buddy(&e4b);
@@ -4959,7 +4985,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 	ext4_debug("trimmed %d blocks in the group %d\n",
 		count, group);
 
-	return count;
+	return ret;
 }
 
 /**

fs/ext4/migrate.c

@@ -14,6 +14,7 @@
 
 #include <linux/slab.h>
 #include "ext4_jbd2.h"
+#include "ext4_extents.h"
 
 /*
  * The contiguous blocks details which can be

fs/ext4/move_extent.c

@@ -18,6 +18,7 @@
 #include <linux/slab.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
+#include "ext4_extents.h"
 
 /**
  * get_ext_path - Find an extent path for designated logical block number.

fs/ext4/page-io.c

@@ -27,7 +27,6 @@
 #include "ext4_jbd2.h"
 #include "xattr.h"
 #include "acl.h"
-#include "ext4_extents.h"
 
 static struct kmem_cache *io_page_cachep, *io_end_cachep;
 
@@ -111,7 +110,7 @@ static int ext4_end_io(ext4_io_end_t *io)
 		inode_dio_done(inode);
 	/* Wake up anyone waiting on unwritten extent conversion */
 	if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
-		wake_up_all(ext4_ioend_wq(io->inode));
+		wake_up_all(ext4_ioend_wq(inode));
 	return ret;
 }
 

fs/ext4/resize.c

@@ -783,7 +783,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 
 	err = ext4_journal_get_write_access(handle, gdb_bh);
 	if (unlikely(err))
-		goto exit_sbh;
+		goto exit_dind;
 
 	err = ext4_journal_get_write_access(handle, dind);
 	if (unlikely(err))
@@ -792,7 +792,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	/* ext4_reserve_inode_write() gets a reference on the iloc */
 	err = ext4_reserve_inode_write(handle, inode, &iloc);
 	if (unlikely(err))
-		goto exit_dindj;
+		goto exit_dind;
 
 	n_group_desc = ext4_kvmalloc((gdb_num + 1) *
 				     sizeof(struct buffer_head *),
@@ -846,12 +846,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 
 exit_inode:
 	ext4_kvfree(n_group_desc);
-	/* ext4_handle_release_buffer(handle, iloc.bh); */
 	brelse(iloc.bh);
-exit_dindj:
-	/* ext4_handle_release_buffer(handle, dind); */
-exit_sbh:
-	/* ext4_handle_release_buffer(handle, EXT4_SB(sb)->s_sbh); */
 exit_dind:
 	brelse(dind);
 exit_bh:
@@ -969,14 +964,8 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
 	}
 
 	for (i = 0; i < reserved_gdb; i++) {
-		if ((err = ext4_journal_get_write_access(handle, primary[i]))) {
-			/*
-			int j;
-			for (j = 0; j < i; j++)
-				ext4_handle_release_buffer(handle, primary[j]);
-			 */
+		if ((err = ext4_journal_get_write_access(handle, primary[i])))
 			goto exit_bh;
-		}
 	}
 
 	if ((err = ext4_reserve_inode_write(handle, inode, &iloc)))

fs/ext4/super.c

@@ -45,7 +45,7 @@
 #include <linux/freezer.h>
 
 #include "ext4.h"
-#include "ext4_extents.h"
+#include "ext4_extents.h"	/* Needed for trace points definition */
 #include "ext4_jbd2.h"
 #include "xattr.h"
 #include "acl.h"
@@ -939,10 +939,11 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 		return NULL;
 
 	ei->vfs_inode.i_version = 1;
-	ei->vfs_inode.i_data.writeback_index = 0;
 	memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
 	INIT_LIST_HEAD(&ei->i_prealloc_list);
 	spin_lock_init(&ei->i_prealloc_lock);
+	ext4_es_init_tree(&ei->i_es_tree);
+	rwlock_init(&ei->i_es_lock);
 	ei->i_reserved_data_blocks = 0;
 	ei->i_reserved_meta_blocks = 0;
 	ei->i_allocated_meta_blocks = 0;
@@ -996,9 +997,7 @@ static void init_once(void *foo)
 	struct ext4_inode_info *ei = (struct ext4_inode_info *) foo;
 
 	INIT_LIST_HEAD(&ei->i_orphan);
-#ifdef CONFIG_EXT4_FS_XATTR
 	init_rwsem(&ei->xattr_sem);
-#endif
 	init_rwsem(&ei->i_data_sem);
 	inode_init_once(&ei->vfs_inode);
 }
@@ -1031,6 +1030,7 @@ void ext4_clear_inode(struct inode *inode)
 	clear_inode(inode);
 	dquot_drop(inode);
 	ext4_discard_preallocations(inode);
+	ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
 	if (EXT4_I(inode)->jinode) {
 		jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode),
 					       EXT4_I(inode)->jinode);
@@ -1447,13 +1447,8 @@ static const struct mount_opts {
 	{Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_DATAJ},
 	{Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_DATAJ},
 	{Opt_data_writeback, EXT4_MOUNT_WRITEBACK_DATA, MOPT_DATAJ},
-#ifdef CONFIG_EXT4_FS_XATTR
 	{Opt_user_xattr, EXT4_MOUNT_XATTR_USER, MOPT_SET},
 	{Opt_nouser_xattr, EXT4_MOUNT_XATTR_USER, MOPT_CLEAR},
-#else
-	{Opt_user_xattr, 0, MOPT_NOSUPPORT},
-	{Opt_nouser_xattr, 0, MOPT_NOSUPPORT},
-#endif
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 	{Opt_acl, EXT4_MOUNT_POSIX_ACL, MOPT_SET},
 	{Opt_noacl, EXT4_MOUNT_POSIX_ACL, MOPT_CLEAR},
@@ -3202,7 +3197,6 @@ int ext4_calculate_overhead(struct super_block *sb)
 	ext4_fsblk_t overhead = 0;
 	char *buf = (char *) get_zeroed_page(GFP_KERNEL);
 
-	memset(buf, 0, PAGE_SIZE);
 	if (!buf)
 		return -ENOMEM;
 
@@ -3256,7 +3250,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	unsigned int i;
 	int needs_recovery, has_huge_files, has_bigalloc;
 	__u64 blocks_count;
-	int err;
+	int err = 0;
 	unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
 	ext4_group_t first_not_zeroed;
 
@@ -3272,9 +3266,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 	sb->s_fs_info = sbi;
 	sbi->s_sb = sb;
-	sbi->s_mount_opt = 0;
-	sbi->s_resuid = make_kuid(&init_user_ns, EXT4_DEF_RESUID);
-	sbi->s_resgid = make_kgid(&init_user_ns, EXT4_DEF_RESGID);
 	sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
 	sbi->s_sb_block = sb_block;
 	if (sb->s_bdev->bd_part)
@@ -3285,6 +3276,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	for (cp = sb->s_id; (cp = strchr(cp, '/'));)
 		*cp = '!';
 
+	/* -EINVAL is default */
 	ret = -EINVAL;
 	blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE);
 	if (!blocksize) {
@@ -3369,9 +3361,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (def_mount_opts & EXT4_DEFM_UID16)
 		set_opt(sb, NO_UID32);
 	/* xattr user namespace & acls are now defaulted on */
-#ifdef CONFIG_EXT4_FS_XATTR
 	set_opt(sb, XATTR_USER);
-#endif
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 	set_opt(sb, POSIX_ACL);
 #endif
@@ -3662,7 +3652,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			 " too large to mount safely on this system");
 		if (sizeof(sector_t) < 8)
 			ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled");
-		ret = err;
 		goto failed_mount;
 	}
 
@@ -3770,7 +3759,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "insufficient memory");
-		ret = err;
 		goto failed_mount3;
 	}
 
@@ -3801,7 +3789,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
-	sbi->s_resize_flags = 0;
 
 	sb->s_root = NULL;
 
@@ -3897,8 +3884,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (es->s_overhead_clusters)
 		sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters);
 	else {
-		ret = ext4_calculate_overhead(sb);
-		if (ret)
+		err = ext4_calculate_overhead(sb);
+		if (err)
 			goto failed_mount_wq;
 	}
 
@@ -3910,6 +3897,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		alloc_workqueue("ext4-dio-unwritten", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
 	if (!EXT4_SB(sb)->dio_unwritten_wq) {
 		printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n");
+		ret = -ENOMEM;
 		goto failed_mount_wq;
 	}
 
@@ -4012,12 +4000,20 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	/* Enable quota usage during mount. */
 	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) &&
 	    !(sb->s_flags & MS_RDONLY)) {
-		ret = ext4_enable_quotas(sb);
-		if (ret)
+		err = ext4_enable_quotas(sb);
+		if (err)
 			goto failed_mount7;
 	}
 #endif  /* CONFIG_QUOTA */
 
+	if (test_opt(sb, DISCARD)) {
+		struct request_queue *q = bdev_get_queue(sb->s_bdev);
+		if (!blk_queue_discard(q))
+			ext4_msg(sb, KERN_WARNING,
+				 "mounting with \"discard\" option, but "
+				 "the device does not support discard");
+	}
+
 	ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
 		 "Opts: %s%s%s", descr, sbi->s_es->s_mount_opts,
 		 *sbi->s_es->s_mount_opts ? "; " : "", orig_data);
@@ -4084,7 +4080,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	kfree(sbi);
 out_free_orig:
 	kfree(orig_data);
-	return ret;
+	return err ? err : ret;
 }
 
 /*
@@ -4790,7 +4786,7 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	buf->f_type = EXT4_SUPER_MAGIC;
 	buf->f_bsize = sb->s_blocksize;
-	buf->f_blocks = ext4_blocks_count(es) - EXT4_C2B(sbi, sbi->s_overhead);
+	buf->f_blocks = ext4_blocks_count(es) - EXT4_C2B(sbi, overhead);
 	bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) -
 		percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter);
 	/* prevent underflow in case that few free space is available */
@@ -5282,6 +5278,7 @@ static int __init ext4_init_fs(void)
 	ext4_li_info = NULL;
 	mutex_init(&ext4_li_mtx);
 
+	/* Build-time check for flags consistency */
 	ext4_check_flag_values();
 
 	for (i = 0; i < EXT4_WQ_HASH_SZ; i++) {
@@ -5289,9 +5286,14 @@ static int __init ext4_init_fs(void)
 		init_waitqueue_head(&ext4__ioend_wq[i]);
 	}
 
-	err = ext4_init_pageio();
+	err = ext4_init_es();
 	if (err)
 		return err;
+
+	err = ext4_init_pageio();
+	if (err)
+		goto out7;
+
 	err = ext4_init_system_zone();
 	if (err)
 		goto out6;
@@ -5341,6 +5343,9 @@ static int __init ext4_init_fs(void)
 	ext4_exit_system_zone();
 out6:
 	ext4_exit_pageio();
+out7:
+	ext4_exit_es();
+
 	return err;
 }
 

fs/ext4/symlink.c

@@ -35,22 +35,18 @@ const struct inode_operations ext4_symlink_inode_operations = {
 	.follow_link	= page_follow_link_light,
 	.put_link	= page_put_link,
 	.setattr	= ext4_setattr,
-#ifdef CONFIG_EXT4_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr	= ext4_listxattr,
 	.removexattr	= generic_removexattr,
-#endif
 };
 
 const struct inode_operations ext4_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.follow_link	= ext4_follow_link,
 	.setattr	= ext4_setattr,
-#ifdef CONFIG_EXT4_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr	= ext4_listxattr,
 	.removexattr	= generic_removexattr,
-#endif
 };

fs/ext4/xattr.c

@@ -61,11 +61,6 @@
 #include "xattr.h"
 #include "acl.h"
 
-#define BHDR(bh) ((struct ext4_xattr_header *)((bh)->b_data))
-#define ENTRY(ptr) ((struct ext4_xattr_entry *)(ptr))
-#define BFIRST(bh) ENTRY(BHDR(bh)+1)
-#define IS_LAST_ENTRY(entry) (*(__u32 *)(entry) == 0)
-
 #ifdef EXT4_XATTR_DEBUG
 # define ea_idebug(inode, f...) do { \
 		printk(KERN_DEBUG "inode %s:%lu: ", \
@@ -312,7 +307,7 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
 	return error;
 }
 
-static int
+int
 ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
 		     void *buffer, size_t buffer_size)
 {
@@ -581,21 +576,6 @@ static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last,
 	return (*min_offs - ((void *)last - base) - sizeof(__u32));
 }
 
-struct ext4_xattr_info {
-	int name_index;
-	const char *name;
-	const void *value;
-	size_t value_len;
-};
-
-struct ext4_xattr_search {
-	struct ext4_xattr_entry *first;
-	void *base;
-	void *end;
-	struct ext4_xattr_entry *here;
-	int not_found;
-};
-
 static int
 ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s)
 {
@@ -648,9 +628,14 @@ ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s)
 				   size. Just replace. */
 				s->here->e_value_size =
 					cpu_to_le32(i->value_len);
-				memset(val + size - EXT4_XATTR_PAD, 0,
-				       EXT4_XATTR_PAD); /* Clear pad bytes. */
-				memcpy(val, i->value, i->value_len);
+				if (i->value == EXT4_ZERO_XATTR_VALUE) {
+					memset(val, 0, size);
+				} else {
+					/* Clear pad bytes first. */
+					memset(val + size - EXT4_XATTR_PAD, 0,
+					       EXT4_XATTR_PAD);
+					memcpy(val, i->value, i->value_len);
+				}
 				return 0;
 			}
 
@@ -689,9 +674,14 @@ ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s)
 			size_t size = EXT4_XATTR_SIZE(i->value_len);
 			void *val = s->base + min_offs - size;
 			s->here->e_value_offs = cpu_to_le16(min_offs - size);
-			memset(val + size - EXT4_XATTR_PAD, 0,
-			       EXT4_XATTR_PAD); /* Clear the pad bytes. */
-			memcpy(val, i->value, i->value_len);
+			if (i->value == EXT4_ZERO_XATTR_VALUE) {
+				memset(val, 0, size);
+			} else {
+				/* Clear the pad bytes first. */
+				memset(val + size - EXT4_XATTR_PAD, 0,
+				       EXT4_XATTR_PAD);
+				memcpy(val, i->value, i->value_len);
+			}
 		}
 	}
 	return 0;
@@ -794,7 +784,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			int offset = (char *)s->here - bs->bh->b_data;
 
 			unlock_buffer(bs->bh);
-			ext4_handle_release_buffer(handle, bs->bh);
 			if (ce) {
 				mb_cache_entry_release(ce);
 				ce = NULL;
@@ -950,14 +939,8 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 #undef header
 }
 
-struct ext4_xattr_ibody_find {
-	struct ext4_xattr_search s;
-	struct ext4_iloc iloc;
-};
-
-static int
-ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
-		      struct ext4_xattr_ibody_find *is)
+int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
+			  struct ext4_xattr_ibody_find *is)
 {
 	struct ext4_xattr_ibody_header *header;
 	struct ext4_inode *raw_inode;
@@ -985,10 +968,47 @@ ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
 	return 0;
 }
 
-static int
-ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
-		     struct ext4_xattr_info *i,
-		     struct ext4_xattr_ibody_find *is)
+int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
+				struct ext4_xattr_info *i,
+				struct ext4_xattr_ibody_find *is)
+{
+	struct ext4_xattr_ibody_header *header;
+	struct ext4_xattr_search *s = &is->s;
+	int error;
+
+	if (EXT4_I(inode)->i_extra_isize == 0)
+		return -ENOSPC;
+	error = ext4_xattr_set_entry(i, s);
+	if (error) {
+		if (error == -ENOSPC &&
+		    ext4_has_inline_data(inode)) {
+			error = ext4_try_to_evict_inline_data(handle, inode,
+					EXT4_XATTR_LEN(strlen(i->name) +
+					EXT4_XATTR_SIZE(i->value_len)));
+			if (error)
+				return error;
+			error = ext4_xattr_ibody_find(inode, i, is);
+			if (error)
+				return error;
+			error = ext4_xattr_set_entry(i, s);
+		}
+		if (error)
+			return error;
+	}
+	header = IHDR(inode, ext4_raw_inode(&is->iloc));
+	if (!IS_LAST_ENTRY(s->first)) {
+		header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
+		ext4_set_inode_state(inode, EXT4_STATE_XATTR);
+	} else {
+		header->h_magic = cpu_to_le32(0);
+		ext4_clear_inode_state(inode, EXT4_STATE_XATTR);
+	}
+	return 0;
+}
+
+static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
+				struct ext4_xattr_info *i,
+				struct ext4_xattr_ibody_find *is)
 {
 	struct ext4_xattr_ibody_header *header;
 	struct ext4_xattr_search *s = &is->s;
@@ -1144,9 +1164,17 @@ ext4_xattr_set(struct inode *inode, int name_index, const char *name,
 {
 	handle_t *handle;
 	int error, retries = 0;
+	int credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb);
 
 retry:
-	handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
+	/*
+	 * In case of inline data, we may push out the data to a block,
+	 * So reserve the journal space first.
+	 */
+	if (ext4_has_inline_data(inode))
+		credits += ext4_writepage_trans_blocks(inode) + 1;
+
+	handle = ext4_journal_start(inode, credits);
 	if (IS_ERR(handle)) {
 		error = PTR_ERR(handle);
 	} else {

fs/ext4/xattr.h

@@ -21,6 +21,7 @@
 #define EXT4_XATTR_INDEX_TRUSTED		4
 #define	EXT4_XATTR_INDEX_LUSTRE			5
 #define EXT4_XATTR_INDEX_SECURITY	        6
+#define EXT4_XATTR_INDEX_SYSTEM			7
 
 struct ext4_xattr_header {
 	__le32	h_magic;	/* magic number for identification */
@@ -65,7 +66,32 @@ struct ext4_xattr_entry {
 		EXT4_I(inode)->i_extra_isize))
 #define IFIRST(hdr) ((struct ext4_xattr_entry *)((hdr)+1))
 
-# ifdef CONFIG_EXT4_FS_XATTR
+#define BHDR(bh) ((struct ext4_xattr_header *)((bh)->b_data))
+#define ENTRY(ptr) ((struct ext4_xattr_entry *)(ptr))
+#define BFIRST(bh) ENTRY(BHDR(bh)+1)
+#define IS_LAST_ENTRY(entry) (*(__u32 *)(entry) == 0)
+
+#define EXT4_ZERO_XATTR_VALUE ((void *)-1)
+
+struct ext4_xattr_info {
+	int name_index;
+	const char *name;
+	const void *value;
+	size_t value_len;
+};
+
+struct ext4_xattr_search {
+	struct ext4_xattr_entry *first;
+	void *base;
+	void *end;
+	struct ext4_xattr_entry *here;
+	int not_found;
+};
+
+struct ext4_xattr_ibody_find {
+	struct ext4_xattr_search s;
+	struct ext4_iloc iloc;
+};
 
 extern const struct xattr_handler ext4_xattr_user_handler;
 extern const struct xattr_handler ext4_xattr_trusted_handler;
@@ -90,60 +116,82 @@ extern void ext4_exit_xattr(void);
 
 extern const struct xattr_handler *ext4_xattr_handlers[];
 
-# else  /* CONFIG_EXT4_FS_XATTR */
-
-static inline int
-ext4_xattr_get(struct inode *inode, int name_index, const char *name,
-	       void *buffer, size_t size, int flags)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int
-ext4_xattr_set(struct inode *inode, int name_index, const char *name,
-	       const void *value, size_t size, int flags)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int
-ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
-	       const char *name, const void *value, size_t size, int flags)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline void
-ext4_xattr_delete_inode(handle_t *handle, struct inode *inode)
-{
-}
-
-static inline void
-ext4_xattr_put_super(struct super_block *sb)
-{
-}
-
-static __init inline int
-ext4_init_xattr(void)
-{
-	return 0;
-}
-
-static inline void
-ext4_exit_xattr(void)
-{
-}
-
-static inline int
-ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
-			    struct ext4_inode *raw_inode, handle_t *handle)
-{
-	return -EOPNOTSUPP;
-}
-
-#define ext4_xattr_handlers	NULL
-
-# endif  /* CONFIG_EXT4_FS_XATTR */
+extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
+				 struct ext4_xattr_ibody_find *is);
+extern int ext4_xattr_ibody_get(struct inode *inode, int name_index,
+				const char *name,
+				void *buffer, size_t buffer_size);
+extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
+				       struct ext4_xattr_info *i,
+				       struct ext4_xattr_ibody_find *is);
+
+extern int ext4_has_inline_data(struct inode *inode);
+extern int ext4_get_inline_size(struct inode *inode);
+extern int ext4_get_max_inline_size(struct inode *inode);
+extern int ext4_find_inline_data_nolock(struct inode *inode);
+extern void ext4_write_inline_data(struct inode *inode,
+				   struct ext4_iloc *iloc,
+				   void *buffer, loff_t pos,
+				   unsigned int len);
+extern int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
+				    unsigned int len);
+extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
+				 unsigned int len);
+extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);
+
+extern int ext4_readpage_inline(struct inode *inode, struct page *page);
+extern int ext4_try_to_write_inline_data(struct address_space *mapping,
+					 struct inode *inode,
+					 loff_t pos, unsigned len,
+					 unsigned flags,
+					 struct page **pagep);
+extern int ext4_write_inline_data_end(struct inode *inode,
+				      loff_t pos, unsigned len,
+				      unsigned copied,
+				      struct page *page);
+extern struct buffer_head *
+ext4_journalled_write_inline_data(struct inode *inode,
+				  unsigned len,
+				  struct page *page);
+extern int ext4_da_write_inline_data_begin(struct address_space *mapping,
+					   struct inode *inode,
+					   loff_t pos, unsigned len,
+					   unsigned flags,
+					   struct page **pagep,
+					   void **fsdata);
+extern int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
+					 unsigned len, unsigned copied,
+					 struct page *page);
+extern int ext4_try_add_inline_entry(handle_t *handle, struct dentry *dentry,
+				     struct inode *inode);
+extern int ext4_try_create_inline_dir(handle_t *handle,
+				      struct inode *parent,
+				      struct inode *inode);
+extern int ext4_read_inline_dir(struct file *filp,
+				void *dirent, filldir_t filldir,
+				int *has_inline_data);
+extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
+					const struct qstr *d_name,
+					struct ext4_dir_entry_2 **res_dir,
+					int *has_inline_data);
+extern int ext4_delete_inline_entry(handle_t *handle,
+				    struct inode *dir,
+				    struct ext4_dir_entry_2 *de_del,
+				    struct buffer_head *bh,
+				    int *has_inline_data);
+extern int empty_inline_dir(struct inode *dir, int *has_inline_data);
+extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode,
+					struct ext4_dir_entry_2 **parent_de,
+					int *retval);
+extern int ext4_inline_data_fiemap(struct inode *inode,
+				   struct fiemap_extent_info *fieinfo,
+				   int *has_inline);
+extern int ext4_try_to_evict_inline_data(handle_t *handle,
+					 struct inode *inode,
+					 int needed);
+extern void ext4_inline_data_truncate(struct inode *inode, int *has_inline);
+
+extern int ext4_convert_inline_data(struct inode *inode);
 
 #ifdef CONFIG_EXT4_FS_SECURITY
 extern int ext4_init_security(handle_t *handle, struct inode *inode,

fs/jbd2/journal.c

@@ -60,7 +60,6 @@ EXPORT_SYMBOL(jbd2_journal_get_create_access);
 EXPORT_SYMBOL(jbd2_journal_get_undo_access);
 EXPORT_SYMBOL(jbd2_journal_set_triggers);
 EXPORT_SYMBOL(jbd2_journal_dirty_metadata);
-EXPORT_SYMBOL(jbd2_journal_release_buffer);
 EXPORT_SYMBOL(jbd2_journal_forget);
 #if 0
 EXPORT_SYMBOL(journal_sync_buffer);

fs/jbd2/transaction.c

@@ -1207,17 +1207,6 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 	return ret;
 }
 
-/*
- * jbd2_journal_release_buffer: undo a get_write_access without any buffer
- * updates, if the update decided in the end that it didn't need access.
- *
- */
-void
-jbd2_journal_release_buffer(handle_t *handle, struct buffer_head *bh)
-{
-	BUFFER_TRACE(bh, "entry");
-}
-
 /**
  * void jbd2_journal_forget() - bforget() for potentially-journaled buffers.
  * @handle: transaction handle

include/linux/jbd2.h

@@ -1096,7 +1096,6 @@ extern int	 jbd2_journal_get_undo_access(handle_t *, struct buffer_head *);
 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 void	 jbd2_journal_release_buffer (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_forget (handle_t *, struct buffer_head *);
 extern void	 journal_sync_buffer (struct buffer_head *);
 extern void	 jbd2_journal_invalidatepage(journal_t *,
@@ -1303,15 +1302,21 @@ static inline int jbd_space_needed(journal_t *journal)
 
 extern int jbd_blocks_per_page(struct inode *inode);
 
+/* JBD uses a CRC32 checksum */
+#define JBD_MAX_CHECKSUM_SIZE 4
+
 static inline u32 jbd2_chksum(journal_t *journal, u32 crc,
 			      const void *address, unsigned int length)
 {
 	struct {
 		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(journal->j_chksum_driver)];
+		char ctx[JBD_MAX_CHECKSUM_SIZE];
 	} desc;
 	int err;
 
+	BUG_ON(crypto_shash_descsize(journal->j_chksum_driver) >
+		JBD_MAX_CHECKSUM_SIZE);
+
 	desc.shash.tfm = journal->j_chksum_driver;
 	desc.shash.flags = 0;
 	*(u32 *)desc.ctx = crc;