Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (57 commits)
  jbd2: Fix oops in jbd2_journal_init_inode() on corrupted fs
  ext4: Remove "extents" mount option
  block: Add Kconfig help which notes that ext4 needs CONFIG_LBD
  ext4: Make printk's consistently prefixed with "EXT4-fs: "
  ext4: Add sanity checks for the superblock before mounting the filesystem
  ext4: Add mount option to set kjournald's I/O priority
  jbd2: Submit writes to the journal using WRITE_SYNC
  jbd2: Add pid and journal device name to the "kjournald2 starting" message
  ext4: Add markers for better debuggability
  ext4: Remove code to create the journal inode
  ext4: provide function to release metadata pages under memory pressure
  ext3: provide function to release metadata pages under memory pressure
  add releasepage hooks to block devices which can be used by file systems
  ext4: Fix s_dirty_blocks_counter if block allocation failed with nodelalloc
  ext4: Init the complete page while building buddy cache
  ext4: Don't allow new groups to be added during block allocation
  ext4: mark the blocks/inode bitmap beyond end of group as used
  ext4: Use new buffer_head flag to check uninit group bitmaps initialization
  ext4: Fix the race between read_inode_bitmap() and ext4_new_inode()
  ext4: code cleanup
  ...

Documentation/filesystems/ext4.txt

@@ -58,13 +58,22 @@ Note: More extensive information for getting started with ext4 can be
 
 	# mount -t ext4 /dev/hda1 /wherever
 
-  - When comparing performance with other filesystems, remember that
-    ext3/4 by default offers higher data integrity guarantees than most.
-    So when comparing with a metadata-only journalling filesystem, such
-    as ext3, use `mount -o data=writeback'.  And you might as well use
-    `mount -o nobh' too along with it.  Making the journal larger than
-    the mke2fs default often helps performance with metadata-intensive
-    workloads.
+  - When comparing performance with other filesystems, it's always
+    important to try multiple workloads; very often a subtle change in a
+    workload parameter can completely change the ranking of which
+    filesystems do well compared to others.  When comparing versus ext3,
+    note that ext4 enables write barriers by default, while ext3 does
+    not enable write barriers by default.  So it is useful to use
+    explicitly specify whether barriers are enabled or not when via the
+    '-o barriers=[0|1]' mount option for both ext3 and ext4 filesystems
+    for a fair comparison.  When tuning ext3 for best benchmark numbers,
+    it is often worthwhile to try changing the data journaling mode; '-o
+    data=writeback,nobh' can be faster for some workloads.  (Note
+    however that running mounted with data=writeback can potentially
+    leave stale data exposed in recently written files in case of an
+    unclean shutdown, which could be a security exposure in some
+    situations.)  Configuring the filesystem with a large journal can
+    also be helpful for metadata-intensive workloads.
 
 2. Features
 ===========
@@ -74,7 +83,7 @@ Note: More extensive information for getting started with ext4 can be
 * ability to use filesystems > 16TB (e2fsprogs support not available yet)
 * extent format reduces metadata overhead (RAM, IO for access, transactions)
 * extent format more robust in face of on-disk corruption due to magics,
-* internal redunancy in tree
+* internal redundancy in tree
 * improved file allocation (multi-block alloc)
 * fix 32000 subdirectory limit
 * nsec timestamps for mtime, atime, ctime, create time
@@ -116,10 +125,11 @@ grouping of bitmaps and inode tables.  Some test results available here:
 When mounting an ext4 filesystem, the following option are accepted:
 (*) == default
 
-extents		(*)	ext4 will use extents to address file data.  The
-			file system will no longer be mountable by ext3.
-
-noextents		ext4 will not use extents for newly created files
+ro                   	Mount filesystem read only. Note that ext4 will
+                     	replay the journal (and thus write to the
+                     	partition) even when mounted "read only". The
+                     	mount options "ro,noload" can be used to prevent
+		     	writes to the filesystem.
 
 journal_checksum	Enable checksumming of the journal transactions.
 			This will allow the recovery code in e2fsck and the
@@ -134,17 +144,17 @@ journal_async_commit	Commit block can be written to disk without waiting
 journal=update		Update the ext4 file system's journal to the current
 			format.
 
-journal=inum		When a journal already exists, this option is ignored.
-			Otherwise, it specifies the number of the inode which
-			will represent the ext4 file system's journal file.
-
 journal_dev=devnum	When the external journal device's major/minor numbers
 			have changed, this option allows the user to specify
 			the new journal location.  The journal device is
 			identified through its new major/minor numbers encoded
 			in devnum.
 
-noload			Don't load the journal on mounting.
+noload			Don't load the journal on mounting.  Note that
+                     	if the filesystem was not unmounted cleanly,
+                     	skipping the journal replay will lead to the
+                     	filesystem containing inconsistencies that can
+                     	lead to any number of problems.
 
 data=journal		All data are committed into the journal prior to being
 			written into the main file system.
@@ -219,9 +229,12 @@ minixdf			Make 'df' act like Minix.
 
 debug			Extra debugging information is sent to syslog.
 
-errors=remount-ro(*)	Remount the filesystem read-only on an error.
+errors=remount-ro	Remount the filesystem read-only on an error.
 errors=continue		Keep going on a filesystem error.
 errors=panic		Panic and halt the machine if an error occurs.
+                        (These mount options override the errors behavior
+                        specified in the superblock, which can be configured
+                        using tune2fs)
 
 data_err=ignore(*)	Just print an error message if an error occurs
 			in a file data buffer in ordered mode.
@@ -261,6 +274,42 @@ delalloc	(*)	Deferring block allocation until write-out time.
 nodelalloc		Disable delayed allocation. Blocks are allocation
 			when data is copied from user to page cache.
 
+max_batch_time=usec	Maximum amount of time ext4 should wait for
+			additional filesystem operations to be batch
+			together with a synchronous write operation.
+			Since a synchronous write operation is going to
+			force a commit and then a wait for the I/O
+			complete, it doesn't cost much, and can be a
+			huge throughput win, we wait for a small amount
+			of time to see if any other transactions can
+			piggyback on the synchronous write.   The
+			algorithm used is designed to automatically tune
+			for the speed of the disk, by measuring the
+			amount of time (on average) that it takes to
+			finish committing a transaction.  Call this time
+			the "commit time".  If the time that the
+			transactoin has been running is less than the
+			commit time, ext4 will try sleeping for the
+			commit time to see if other operations will join
+			the transaction.   The commit time is capped by
+			the max_batch_time, which defaults to 15000us
+			(15ms).   This optimization can be turned off
+			entirely by setting max_batch_time to 0.
+
+min_batch_time=usec	This parameter sets the commit time (as
+			described above) to be at least min_batch_time.
+			It defaults to zero microseconds.  Increasing
+			this parameter may improve the throughput of
+			multi-threaded, synchronous workloads on very
+			fast disks, at the cost of increasing latency.
+
+journal_ioprio=prio	The I/O priority (from 0 to 7, where 0 is the
+			highest priorty) which should be used for I/O
+			operations submitted by kjournald2 during a
+			commit operation.  This defaults to 3, which is
+			a slightly higher priority than the default I/O
+			priority.
+
 Data Mode
 =========
 There are 3 different data modes:

block/Kconfig

@@ -36,6 +36,12 @@ config LBD
 	  This option also enables support for single files larger than
 	  2TB.
 
+	  The ext4 filesystem requires that this feature be enabled in
+	  order to support filesystems that have the huge_file feature
+	  enabled.    Otherwise, it will refuse to mount any filesystems
+	  that use the huge_file feature, which is enabled by default
+	  by mke2fs.ext4.   The GFS2 filesystem also requires this feature.
+
 	  If unsure, say N.
 
 config BLK_DEV_IO_TRACE

fs/block_dev.c

@@ -1234,6 +1234,20 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	return blkdev_ioctl(bdev, mode, cmd, arg);
 }
 
+/*
+ * Try to release a page associated with block device when the system
+ * is under memory pressure.
+ */
+static int blkdev_releasepage(struct page *page, gfp_t wait)
+{
+	struct super_block *super = BDEV_I(page->mapping->host)->bdev.bd_super;
+
+	if (super && super->s_op->bdev_try_to_free_page)
+		return super->s_op->bdev_try_to_free_page(super, page, wait);
+
+	return try_to_free_buffers(page);
+}
+
 static const struct address_space_operations def_blk_aops = {
 	.readpage	= blkdev_readpage,
 	.writepage	= blkdev_writepage,
@@ -1241,6 +1255,7 @@ static const struct address_space_operations def_blk_aops = {
 	.write_begin	= blkdev_write_begin,
 	.write_end	= blkdev_write_end,
 	.writepages	= generic_writepages,
+	.releasepage	= blkdev_releasepage,
 	.direct_IO	= blkdev_direct_IO,
 };
 

fs/ext3/hash.c

@@ -35,23 +35,71 @@ static void TEA_transform(__u32 buf[4], __u32 const in[])
 
 
 /* The old legacy hash */
-static __u32 dx_hack_hash (const char *name, int len)
+static __u32 dx_hack_hash_unsigned(const char *name, int len)
 {
-	__u32 hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	const unsigned char *ucp = (const unsigned char *) name;
+
+	while (len--) {
+		hash = hash1 + (hash0 ^ (((int) *ucp++) * 7152373));
+
+		if (hash & 0x80000000)
+			hash -= 0x7fffffff;
+		hash1 = hash0;
+		hash0 = hash;
+	}
+	return hash0 << 1;
+}
+
+static __u32 dx_hack_hash_signed(const char *name, int len)
+{
+	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	const signed char *scp = (const signed char *) name;
+
 	while (len--) {
-		__u32 hash = hash1 + (hash0 ^ (*name++ * 7152373));
+		hash = hash1 + (hash0 ^ (((int) *scp++) * 7152373));
 
-		if (hash & 0x80000000) hash -= 0x7fffffff;
+		if (hash & 0x80000000)
+			hash -= 0x7fffffff;
 		hash1 = hash0;
 		hash0 = hash;
 	}
-	return (hash0 << 1);
+	return hash0 << 1;
 }
 
-static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
+static void str2hashbuf_signed(const char *msg, int len, __u32 *buf, int num)
 {
 	__u32	pad, val;
 	int	i;
+	const signed char *scp = (const signed char *) msg;
+
+	pad = (__u32)len | ((__u32)len << 8);
+	pad |= pad << 16;
+
+	val = pad;
+	if (len > num*4)
+		len = num * 4;
+	for (i = 0; i < len; i++) {
+		if ((i % 4) == 0)
+			val = pad;
+		val = ((int) scp[i]) + (val << 8);
+		if ((i % 4) == 3) {
+			*buf++ = val;
+			val = pad;
+			num--;
+		}
+	}
+	if (--num >= 0)
+		*buf++ = val;
+	while (--num >= 0)
+		*buf++ = pad;
+}
+
+static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num)
+{
+	__u32	pad, val;
+	int	i;
+	const unsigned char *ucp = (const unsigned char *) msg;
 
 	pad = (__u32)len | ((__u32)len << 8);
 	pad |= pad << 16;
@@ -62,7 +110,7 @@ static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
 	for (i=0; i < len; i++) {
 		if ((i % 4) == 0)
 			val = pad;
-		val = msg[i] + (val << 8);
+		val = ((int) ucp[i]) + (val << 8);
 		if ((i % 4) == 3) {
 			*buf++ = val;
 			val = pad;
@@ -95,6 +143,8 @@ int ext3fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 	const char	*p;
 	int		i;
 	__u32		in[8], buf[4];
+	void		(*str2hashbuf)(const char *, int, __u32 *, int) =
+				str2hashbuf_signed;
 
 	/* Initialize the default seed for the hash checksum functions */
 	buf[0] = 0x67452301;
@@ -113,13 +163,18 @@ int ext3fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 	}
 
 	switch (hinfo->hash_version) {
+	case DX_HASH_LEGACY_UNSIGNED:
+		hash = dx_hack_hash_unsigned(name, len);
+		break;
 	case DX_HASH_LEGACY:
-		hash = dx_hack_hash(name, len);
+		hash = dx_hack_hash_signed(name, len);
 		break;
+	case DX_HASH_HALF_MD4_UNSIGNED:
+		str2hashbuf = str2hashbuf_unsigned;
 	case DX_HASH_HALF_MD4:
 		p = name;
 		while (len > 0) {
-			str2hashbuf(p, len, in, 8);
+			(*str2hashbuf)(p, len, in, 8);
 			half_md4_transform(buf, in);
 			len -= 32;
 			p += 32;
@@ -127,10 +182,12 @@ int ext3fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 		minor_hash = buf[2];
 		hash = buf[1];
 		break;
+	case DX_HASH_TEA_UNSIGNED:
+		str2hashbuf = str2hashbuf_unsigned;
 	case DX_HASH_TEA:
 		p = name;
 		while (len > 0) {
-			str2hashbuf(p, len, in, 4);
+			(*str2hashbuf)(p, len, in, 4);
 			TEA_transform(buf, in);
 			len -= 16;
 			p += 16;

fs/ext3/namei.c

@@ -364,6 +364,8 @@ dx_probe(struct qstr *entry, struct inode *dir,
 		goto fail;
 	}
 	hinfo->hash_version = root->info.hash_version;
+	if (hinfo->hash_version <= DX_HASH_TEA)
+		hinfo->hash_version += EXT3_SB(dir->i_sb)->s_hash_unsigned;
 	hinfo->seed = EXT3_SB(dir->i_sb)->s_hash_seed;
 	if (entry)
 		ext3fs_dirhash(entry->name, entry->len, hinfo);
@@ -632,6 +634,9 @@ int ext3_htree_fill_tree(struct file *dir_file, __u32 start_hash,
 	dir = dir_file->f_path.dentry->d_inode;
 	if (!(EXT3_I(dir)->i_flags & EXT3_INDEX_FL)) {
 		hinfo.hash_version = EXT3_SB(dir->i_sb)->s_def_hash_version;
+		if (hinfo.hash_version <= DX_HASH_TEA)
+			hinfo.hash_version +=
+				EXT3_SB(dir->i_sb)->s_hash_unsigned;
 		hinfo.seed = EXT3_SB(dir->i_sb)->s_hash_seed;
 		count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo,
 					       start_hash, start_minor_hash);
@@ -1152,9 +1157,9 @@ static struct ext3_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 	u32 hash2;
 	struct dx_map_entry *map;
 	char *data1 = (*bh)->b_data, *data2;
-	unsigned split, move, size, i;
+	unsigned split, move, size;
 	struct ext3_dir_entry_2 *de = NULL, *de2;
-	int	err = 0;
+	int	err = 0, i;
 
 	bh2 = ext3_append (handle, dir, &newblock, &err);
 	if (!(bh2)) {
@@ -1394,6 +1399,8 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 
 	/* Initialize as for dx_probe */
 	hinfo.hash_version = root->info.hash_version;
+	if (hinfo.hash_version <= DX_HASH_TEA)
+		hinfo.hash_version += EXT3_SB(dir->i_sb)->s_hash_unsigned;
 	hinfo.seed = EXT3_SB(dir->i_sb)->s_hash_seed;
 	ext3fs_dirhash(name, namelen, &hinfo);
 	frame = frames;

fs/ext3/super.c

@@ -683,6 +683,26 @@ static struct dentry *ext3_fh_to_parent(struct super_block *sb, struct fid *fid,
 				    ext3_nfs_get_inode);
 }
 
+/*
+ * Try to release metadata pages (indirect blocks, directories) which are
+ * mapped via the block device.  Since these pages could have journal heads
+ * which would prevent try_to_free_buffers() from freeing them, we must use
+ * jbd layer's try_to_free_buffers() function to release them.
+ */
+static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
+				 gfp_t wait)
+{
+	journal_t *journal = EXT3_SB(sb)->s_journal;
+
+	WARN_ON(PageChecked(page));
+	if (!page_has_buffers(page))
+		return 0;
+	if (journal)
+		return journal_try_to_free_buffers(journal, page, 
+						   wait & ~__GFP_WAIT);
+	return try_to_free_buffers(page);
+}
+
 #ifdef CONFIG_QUOTA
 #define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group")
 #define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
@@ -749,6 +769,7 @@ static const struct super_operations ext3_sops = {
 	.quota_read	= ext3_quota_read,
 	.quota_write	= ext3_quota_write,
 #endif
+	.bdev_try_to_free_page = bdev_try_to_free_page,
 };
 
 static const struct export_operations ext3_export_ops = {
@@ -1750,6 +1771,18 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 	for (i=0; i < 4; i++)
 		sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
 	sbi->s_def_hash_version = es->s_def_hash_version;
+	i = le32_to_cpu(es->s_flags);
+	if (i & EXT2_FLAGS_UNSIGNED_HASH)
+		sbi->s_hash_unsigned = 3;
+	else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+#ifdef __CHAR_UNSIGNED__
+		es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+		sbi->s_hash_unsigned = 3;
+#else
+		es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+#endif
+		sb->s_dirt = 1;
+	}
 
 	if (sbi->s_blocks_per_group > blocksize * 8) {
 		printk (KERN_ERR

fs/ext4/bitmap.c

@@ -15,10 +15,9 @@
 
 static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
 
-unsigned long ext4_count_free(struct buffer_head *map, unsigned int numchars)
+unsigned int ext4_count_free(struct buffer_head *map, unsigned int numchars)
 {
-	unsigned int i;
-	unsigned long sum = 0;
+	unsigned int i, sum = 0;
 
 	if (!map)
 		return 0;

fs/ext4/dir.c

@@ -64,7 +64,7 @@ static unsigned char get_dtype(struct super_block *sb, int filetype)
 int ext4_check_dir_entry(const char *function, struct inode *dir,
 			 struct ext4_dir_entry_2 *de,
 			 struct buffer_head *bh,
-			 unsigned long offset)
+			 unsigned int offset)
 {
 	const char *error_msg = NULL;
 	const int rlen = ext4_rec_len_from_disk(de->rec_len);
@@ -84,9 +84,9 @@ int ext4_check_dir_entry(const char *function, struct inode *dir,
 	if (error_msg != NULL)
 		ext4_error(dir->i_sb, function,
 			"bad entry in directory #%lu: %s - "
-			"offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
+			"offset=%u, inode=%u, rec_len=%d, name_len=%d",
 			dir->i_ino, error_msg, offset,
-			(unsigned long) le32_to_cpu(de->inode),
+			le32_to_cpu(de->inode),
 			rlen, de->name_len);
 	return error_msg == NULL ? 1 : 0;
 }
@@ -95,7 +95,7 @@ static int ext4_readdir(struct file *filp,
 			 void *dirent, filldir_t filldir)
 {
 	int error = 0;
-	unsigned long offset;
+	unsigned int offset;
 	int i, stored;
 	struct ext4_dir_entry_2 *de;
 	struct super_block *sb;
@@ -405,7 +405,7 @@ static int call_filldir(struct file *filp, void *dirent,
 	sb = inode->i_sb;
 
 	if (!fname) {
-		printk(KERN_ERR "ext4: call_filldir: called with "
+		printk(KERN_ERR "EXT4-fs: call_filldir: called with "
 		       "null fname?!?\n");
 		return 0;
 	}

fs/ext4/ext4_extents.h

@@ -194,11 +194,6 @@ static inline unsigned short ext_depth(struct inode *inode)
 	return le16_to_cpu(ext_inode_hdr(inode)->eh_depth);
 }
 
-static inline void ext4_ext_tree_changed(struct inode *inode)
-{
-	EXT4_I(inode)->i_ext_generation++;
-}
-
 static inline void
 ext4_ext_invalidate_cache(struct inode *inode)
 {

fs/ext4/ext4_i.h

@@ -31,7 +31,7 @@ typedef unsigned long long ext4_fsblk_t;
 typedef __u32 ext4_lblk_t;
 
 /* data type for block group number */
-typedef unsigned long ext4_group_t;
+typedef unsigned int ext4_group_t;
 
 #define rsv_start rsv_window._rsv_start
 #define rsv_end rsv_window._rsv_end
@@ -100,9 +100,6 @@ struct ext4_inode_info {
 	 */
 	loff_t	i_disksize;
 
-	/* on-disk additional length */
-	__u16 i_extra_isize;
-
 	/*
 	 * i_data_sem is for serialising ext4_truncate() against
 	 * ext4_getblock().  In the 2.4 ext2 design, great chunks of inode's
@@ -117,7 +114,6 @@ struct ext4_inode_info {
 	struct inode vfs_inode;
 	struct jbd2_inode jinode;
 
-	unsigned long i_ext_generation;
 	struct ext4_ext_cache i_cached_extent;
 	/*
 	 * File creation time. Its function is same as that of
@@ -130,10 +126,14 @@ struct ext4_inode_info {
 	spinlock_t i_prealloc_lock;
 
 	/* allocation reservation info for delalloc */
-	unsigned long i_reserved_data_blocks;
-	unsigned long i_reserved_meta_blocks;
-	unsigned long i_allocated_meta_blocks;
+	unsigned int i_reserved_data_blocks;
+	unsigned int i_reserved_meta_blocks;
+	unsigned int i_allocated_meta_blocks;
 	unsigned short i_delalloc_reserved_flag;
+
+	/* on-disk additional length */
+	__u16 i_extra_isize;
+
 	spinlock_t i_block_reservation_lock;
 };
 

fs/ext4/ext4_jbd2.c

@@ -7,53 +7,96 @@
 int __ext4_journal_get_undo_access(const char *where, handle_t *handle,
 				struct buffer_head *bh)
 {
-	int err = jbd2_journal_get_undo_access(handle, bh);
-	if (err)
-		ext4_journal_abort_handle(where, __func__, bh, handle, err);
+	int err = 0;
+
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_get_undo_access(handle, bh);
+		if (err)
+			ext4_journal_abort_handle(where, __func__, bh,
+						  handle, err);
+	}
 	return err;
 }
 
 int __ext4_journal_get_write_access(const char *where, handle_t *handle,
 				struct buffer_head *bh)
 {
-	int err = jbd2_journal_get_write_access(handle, bh);
-	if (err)
-		ext4_journal_abort_handle(where, __func__, bh, handle, err);
+	int err = 0;
+
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_get_write_access(handle, bh);
+		if (err)
+			ext4_journal_abort_handle(where, __func__, bh,
+						  handle, err);
+	}
 	return err;
 }
 
 int __ext4_journal_forget(const char *where, handle_t *handle,
 				struct buffer_head *bh)
 {
-	int err = jbd2_journal_forget(handle, bh);
-	if (err)
-		ext4_journal_abort_handle(where, __func__, bh, handle, err);
+	int err = 0;
+
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_forget(handle, bh);
+		if (err)
+			ext4_journal_abort_handle(where, __func__, bh,
+						  handle, err);
+	}
 	return err;
 }
 
 int __ext4_journal_revoke(const char *where, handle_t *handle,
 				ext4_fsblk_t blocknr, struct buffer_head *bh)
 {
-	int err = jbd2_journal_revoke(handle, blocknr, bh);
-	if (err)
-		ext4_journal_abort_handle(where, __func__, bh, handle, err);
+	int err = 0;
+
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_revoke(handle, blocknr, bh);
+		if (err)
+			ext4_journal_abort_handle(where, __func__, bh,
+						  handle, err);
+	}
 	return err;
 }
 
 int __ext4_journal_get_create_access(const char *where,
 				handle_t *handle, struct buffer_head *bh)
 {
-	int err = jbd2_journal_get_create_access(handle, bh);
-	if (err)
-		ext4_journal_abort_handle(where, __func__, bh, handle, err);
+	int err = 0;
+
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_get_create_access(handle, bh);
+		if (err)
+			ext4_journal_abort_handle(where, __func__, bh,
+						  handle, err);
+	}
 	return err;
 }
 
-int __ext4_journal_dirty_metadata(const char *where,
-				handle_t *handle, struct buffer_head *bh)
+int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
+				 struct inode *inode, struct buffer_head *bh)
 {
-	int err = jbd2_journal_dirty_metadata(handle, bh);
-	if (err)
-		ext4_journal_abort_handle(where, __func__, bh, handle, err);
+	int err = 0;
+
+	if (ext4_handle_valid(handle)) {
+		err = jbd2_journal_dirty_metadata(handle, bh);
+		if (err)
+			ext4_journal_abort_handle(where, __func__, bh,
+						  handle, err);
+	} else {
+		mark_buffer_dirty(bh);
+		if (inode && inode_needs_sync(inode)) {
+			sync_dirty_buffer(bh);
+			if (buffer_req(bh) && !buffer_uptodate(bh)) {
+				ext4_error(inode->i_sb, __func__,
+					   "IO error syncing inode, "
+					   "inode=%lu, block=%llu",
+					   inode->i_ino,
+					   (unsigned long long) bh->b_blocknr);
+				err = -EIO;
+			}
+		}
+	}
 	return err;
 }

fs/ext4/ext4_jbd2.h

@@ -32,8 +32,8 @@
  * 5 levels of tree + root which are stored in the inode. */
 
 #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb)				\
-	(EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)	\
-		|| test_opt(sb, EXTENTS) ? 27U : 8U)
+	(EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)   \
+	 ? 27U : 8U)
 
 /* Extended attribute operations touch at most two data buffers,
  * two bitmap buffers, and two group summaries, in addition to the inode
@@ -122,12 +122,6 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode);
  * been done yet.
  */
 
-static inline void ext4_journal_release_buffer(handle_t *handle,
-						struct buffer_head *bh)
-{
-	jbd2_journal_release_buffer(handle, bh);
-}
-
 void ext4_journal_abort_handle(const char *caller, const char *err_fn,
 		struct buffer_head *bh, handle_t *handle, int err);
 
@@ -146,8 +140,8 @@ int __ext4_journal_revoke(const char *where, handle_t *handle,
 int __ext4_journal_get_create_access(const char *where,
 				handle_t *handle, struct buffer_head *bh);
 
-int __ext4_journal_dirty_metadata(const char *where,
-				handle_t *handle, struct buffer_head *bh);
+int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
+				 struct inode *inode, struct buffer_head *bh);
 
 #define ext4_journal_get_undo_access(handle, bh) \
 	__ext4_journal_get_undo_access(__func__, (handle), (bh))
@@ -157,14 +151,57 @@ int __ext4_journal_dirty_metadata(const char *where,
 	__ext4_journal_revoke(__func__, (handle), (blocknr), (bh))
 #define ext4_journal_get_create_access(handle, bh) \
 	__ext4_journal_get_create_access(__func__, (handle), (bh))
-#define ext4_journal_dirty_metadata(handle, bh) \
-	__ext4_journal_dirty_metadata(__func__, (handle), (bh))
 #define ext4_journal_forget(handle, bh) \
 	__ext4_journal_forget(__func__, (handle), (bh))
+#define ext4_handle_dirty_metadata(handle, inode, bh) \
+	__ext4_handle_dirty_metadata(__func__, (handle), (inode), (bh))
 
 handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks);
 int __ext4_journal_stop(const char *where, handle_t *handle);
 
+#define EXT4_NOJOURNAL_HANDLE	((handle_t *) 0x1)
+
+static inline int ext4_handle_valid(handle_t *handle)
+{
+	if (handle == EXT4_NOJOURNAL_HANDLE)
+		return 0;
+	return 1;
+}
+
+static inline void ext4_handle_sync(handle_t *handle)
+{
+	if (ext4_handle_valid(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))
+		return is_handle_aborted(handle);
+	return 0;
+}
+
+static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed)
+{
+	if (ext4_handle_valid(handle) && handle->h_buffer_credits < needed)
+		return 0;
+	return 1;
+}
+
+static inline void ext4_journal_release_buffer(handle_t *handle,
+						struct buffer_head *bh)
+{
+	if (ext4_handle_valid(handle))
+		jbd2_journal_release_buffer(handle, bh);
+}
+
 static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks)
 {
 	return ext4_journal_start_sb(inode->i_sb, nblocks);
@@ -180,27 +217,37 @@ static inline handle_t *ext4_journal_current_handle(void)
 
 static inline int ext4_journal_extend(handle_t *handle, int nblocks)
 {
-	return jbd2_journal_extend(handle, nblocks);
+	if (ext4_handle_valid(handle))
+		return jbd2_journal_extend(handle, nblocks);
+	return 0;
 }
 
 static inline int ext4_journal_restart(handle_t *handle, int nblocks)
 {
-	return jbd2_journal_restart(handle, nblocks);
+	if (ext4_handle_valid(handle))
+		return jbd2_journal_restart(handle, nblocks);
+	return 0;
 }
 
 static inline int ext4_journal_blocks_per_page(struct inode *inode)
 {
-	return jbd2_journal_blocks_per_page(inode);
+	if (EXT4_JOURNAL(inode) != NULL)
+		return jbd2_journal_blocks_per_page(inode);
+	return 0;
 }
 
 static inline int ext4_journal_force_commit(journal_t *journal)
 {
-	return jbd2_journal_force_commit(journal);
+	if (journal)
+		return jbd2_journal_force_commit(journal);
+	return 0;
 }
 
 static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
 {
-	return jbd2_journal_file_inode(handle, &EXT4_I(inode)->jinode);
+	if (ext4_handle_valid(handle))
+		return jbd2_journal_file_inode(handle, &EXT4_I(inode)->jinode);
+	return 0;
 }
 
 /* super.c */
@@ -208,6 +255,8 @@ int ext4_force_commit(struct super_block *sb);
 
 static inline int ext4_should_journal_data(struct inode *inode)
 {
+	if (EXT4_JOURNAL(inode) == NULL)
+		return 0;
 	if (!S_ISREG(inode->i_mode))
 		return 1;
 	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
@@ -219,6 +268,8 @@ static inline int ext4_should_journal_data(struct inode *inode)
 
 static inline int ext4_should_order_data(struct inode *inode)
 {
+	if (EXT4_JOURNAL(inode) == NULL)
+		return 0;
 	if (!S_ISREG(inode->i_mode))
 		return 0;
 	if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
@@ -230,6 +281,8 @@ static inline int ext4_should_order_data(struct inode *inode)
 
 static inline int ext4_should_writeback_data(struct inode *inode)
 {
+	if (EXT4_JOURNAL(inode) == NULL)
+		return 0;
 	if (!S_ISREG(inode->i_mode))
 		return 0;
 	if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)

fs/ext4/ext4_sb.h

@@ -57,6 +57,7 @@ struct ext4_sb_info {
 	u32 s_next_generation;
 	u32 s_hash_seed[4];
 	int s_def_hash_version;
+	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
 	struct percpu_counter s_freeblocks_counter;
 	struct percpu_counter s_freeinodes_counter;
 	struct percpu_counter s_dirs_counter;
@@ -73,6 +74,8 @@ struct ext4_sb_info {
 	struct journal_s *s_journal;
 	struct list_head s_orphan;
 	unsigned long s_commit_interval;
+	u32 s_max_batch_time;
+	u32 s_min_batch_time;
 	struct block_device *journal_bdev;
 #ifdef CONFIG_JBD2_DEBUG
 	struct timer_list turn_ro_timer;	/* For turning read-only (crash simulation) */
@@ -101,7 +104,8 @@ struct ext4_sb_info {
 	spinlock_t s_reserve_lock;
 	spinlock_t s_md_lock;
 	tid_t s_last_transaction;
-	unsigned short *s_mb_offsets, *s_mb_maxs;
+	unsigned short *s_mb_offsets;
+	unsigned int *s_mb_maxs;
 
 	/* tunables */
 	unsigned long s_stripe;

fs/ext4/extents.c

@@ -97,6 +97,8 @@ static int ext4_ext_journal_restart(handle_t *handle, int needed)
 {
 	int err;
 
+	if (!ext4_handle_valid(handle))
+		return 0;
 	if (handle->h_buffer_credits > needed)
 		return 0;
 	err = ext4_journal_extend(handle, needed);
@@ -134,7 +136,7 @@ static int ext4_ext_dirty(handle_t *handle, struct inode *inode,
 	int err;
 	if (path->p_bh) {
 		/* path points to block */
-		err = ext4_journal_dirty_metadata(handle, path->p_bh);
+		err = ext4_handle_dirty_metadata(handle, inode, path->p_bh);
 	} else {
 		/* path points to leaf/index in inode body */
 		err = ext4_mark_inode_dirty(handle, inode);
@@ -191,7 +193,7 @@ ext4_ext_new_meta_block(handle_t *handle, struct inode *inode,
 	ext4_fsblk_t goal, newblock;
 
 	goal = ext4_ext_find_goal(inode, path, le32_to_cpu(ex->ee_block));
-	newblock = ext4_new_meta_block(handle, inode, goal, err);
+	newblock = ext4_new_meta_blocks(handle, inode, goal, NULL, err);
 	return newblock;
 }
 
@@ -780,7 +782,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
 	set_buffer_uptodate(bh);
 	unlock_buffer(bh);
 
-	err = ext4_journal_dirty_metadata(handle, bh);
+	err = ext4_handle_dirty_metadata(handle, inode, bh);
 	if (err)
 		goto cleanup;
 	brelse(bh);
@@ -859,7 +861,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
 		set_buffer_uptodate(bh);
 		unlock_buffer(bh);
 
-		err = ext4_journal_dirty_metadata(handle, bh);
+		err = ext4_handle_dirty_metadata(handle, inode, bh);
 		if (err)
 			goto cleanup;
 		brelse(bh);
@@ -955,7 +957,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
 	set_buffer_uptodate(bh);
 	unlock_buffer(bh);
 
-	err = ext4_journal_dirty_metadata(handle, bh);
+	err = ext4_handle_dirty_metadata(handle, inode, bh);
 	if (err)
 		goto out;
 
@@ -1160,15 +1162,13 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
 	while (--depth >= 0) {
 		ix = path[depth].p_idx;
 		if (ix != EXT_LAST_INDEX(path[depth].p_hdr))
-			break;
+			goto got_index;
 	}
 
-	if (depth < 0) {
-		/* we've gone up to the root and
-		 * found no index to the right */
-		return 0;
-	}
+	/* we've gone up to the root and found no index to the right */
+	return 0;
 
+got_index:
 	/* we've found index to the right, let's
 	 * follow it and find the closest allocated
 	 * block to the right */
@@ -1201,7 +1201,6 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
 	*phys = ext_pblock(ex);
 	put_bh(bh);
 	return 0;
-
 }
 
 /*
@@ -1622,7 +1621,6 @@ cleanup:
 		ext4_ext_drop_refs(npath);
 		kfree(npath);
 	}
-	ext4_ext_tree_changed(inode);
 	ext4_ext_invalidate_cache(inode);
 	return err;
 }
@@ -2233,7 +2231,6 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
 		}
 	}
 out:
-	ext4_ext_tree_changed(inode);
 	ext4_ext_drop_refs(path);
 	kfree(path);
 	ext4_journal_stop(handle);
@@ -2250,7 +2247,7 @@ void ext4_ext_init(struct super_block *sb)
 	 * possible initialization would be here
 	 */
 
-	if (test_opt(sb, EXTENTS)) {
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
 		printk(KERN_INFO "EXT4-fs: file extents enabled");
 #ifdef AGGRESSIVE_TEST
 		printk(", aggressive tests");
@@ -2275,7 +2272,7 @@ void ext4_ext_init(struct super_block *sb)
  */
 void ext4_ext_release(struct super_block *sb)
 {
-	if (!test_opt(sb, EXTENTS))
+	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS))
 		return;
 
 #ifdef EXTENTS_STATS
@@ -2380,7 +2377,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 						struct inode *inode,
 						struct ext4_ext_path *path,
 						ext4_lblk_t iblock,
-						unsigned long max_blocks)
+						unsigned int max_blocks)
 {
 	struct ext4_extent *ex, newex, orig_ex;
 	struct ext4_extent *ex1 = NULL;
@@ -2678,26 +2675,26 @@ fix_extent_len:
  */
 int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 			ext4_lblk_t iblock,
-			unsigned long max_blocks, struct buffer_head *bh_result,
+			unsigned int max_blocks, struct buffer_head *bh_result,
 			int create, int extend_disksize)
 {
 	struct ext4_ext_path *path = NULL;
 	struct ext4_extent_header *eh;
 	struct ext4_extent newex, *ex;
-	ext4_fsblk_t goal, newblock;
-	int err = 0, depth, ret;
-	unsigned long allocated = 0;
+	ext4_fsblk_t newblock;
+	int err = 0, depth, ret, cache_type;
+	unsigned int allocated = 0;
 	struct ext4_allocation_request ar;
 	loff_t disksize;
 
 	__clear_bit(BH_New, &bh_result->b_state);
-	ext_debug("blocks %u/%lu requested for inode %u\n",
+	ext_debug("blocks %u/%u requested for inode %u\n",
 			iblock, max_blocks, inode->i_ino);
 
 	/* check in cache */
-	goal = ext4_ext_in_cache(inode, iblock, &newex);
-	if (goal) {
-		if (goal == EXT4_EXT_CACHE_GAP) {
+	cache_type = ext4_ext_in_cache(inode, iblock, &newex);
+	if (cache_type) {
+		if (cache_type == EXT4_EXT_CACHE_GAP) {
 			if (!create) {
 				/*
 				 * block isn't allocated yet and
@@ -2706,7 +2703,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 				goto out2;
 			}
 			/* we should allocate requested block */
-		} else if (goal == EXT4_EXT_CACHE_EXTENT) {
+		} else if (cache_type == EXT4_EXT_CACHE_EXTENT) {
 			/* block is already allocated */
 			newblock = iblock
 				   - le32_to_cpu(newex.ee_block)
@@ -2854,7 +2851,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	if (!newblock)
 		goto out2;
 	ext_debug("allocate new block: goal %llu, found %llu/%lu\n",
-			goal, newblock, allocated);
+		  ar.goal, newblock, allocated);
 
 	/* try to insert new extent into found leaf and return */
 	ext4_ext_store_pblock(&newex, newblock);
@@ -2950,7 +2947,7 @@ void ext4_ext_truncate(struct inode *inode)
 	 * transaction synchronous.
 	 */
 	if (IS_SYNC(inode))
-		handle->h_sync = 1;
+		ext4_handle_sync(handle);
 
 out_stop:
 	up_write(&EXT4_I(inode)->i_data_sem);
@@ -3004,7 +3001,7 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
 	handle_t *handle;
 	ext4_lblk_t block;
 	loff_t new_size;
-	unsigned long max_blocks;
+	unsigned int max_blocks;
 	int ret = 0;
 	int ret2 = 0;
 	int retries = 0;
@@ -3083,7 +3080,7 @@ retry:
 /*
  * Callback function called for each extent to gather FIEMAP information.
  */
-int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
+static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
 		       struct ext4_ext_cache *newex, struct ext4_extent *ex,
 		       void *data)
 {
@@ -3152,7 +3149,8 @@ int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
 /* fiemap flags we can handle specified here */
 #define EXT4_FIEMAP_FLAGS	(FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
 
-int ext4_xattr_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo)
+static int ext4_xattr_fiemap(struct inode *inode,
+				struct fiemap_extent_info *fieinfo)
 {
 	__u64 physical = 0;
 	__u64 length;

fs/ext4/file.c

@@ -140,9 +140,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
-extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
-		__u64 start, __u64 len);
-
 const struct file_operations ext4_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= do_sync_read,

fs/ext4/hash.c

@@ -35,23 +35,71 @@ static void TEA_transform(__u32 buf[4], __u32 const in[])
 
 
 /* The old legacy hash */
-static __u32 dx_hack_hash(const char *name, int len)
+static __u32 dx_hack_hash_unsigned(const char *name, int len)
 {
-	__u32 hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	const unsigned char *ucp = (const unsigned char *) name;
+
+	while (len--) {
+		hash = hash1 + (hash0 ^ (((int) *ucp++) * 7152373));
+
+		if (hash & 0x80000000)
+			hash -= 0x7fffffff;
+		hash1 = hash0;
+		hash0 = hash;
+	}
+	return hash0 << 1;
+}
+
+static __u32 dx_hack_hash_signed(const char *name, int len)
+{
+	__u32 hash, hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	const signed char *scp = (const signed char *) name;
+
 	while (len--) {
-		__u32 hash = hash1 + (hash0 ^ (*name++ * 7152373));
+		hash = hash1 + (hash0 ^ (((int) *scp++) * 7152373));
 
-		if (hash & 0x80000000) hash -= 0x7fffffff;
+		if (hash & 0x80000000)
+			hash -= 0x7fffffff;
 		hash1 = hash0;
 		hash0 = hash;
 	}
-	return (hash0 << 1);
+	return hash0 << 1;
+}
+
+static void str2hashbuf_signed(const char *msg, int len, __u32 *buf, int num)
+{
+	__u32	pad, val;
+	int	i;
+	const signed char *scp = (const signed char *) msg;
+
+	pad = (__u32)len | ((__u32)len << 8);
+	pad |= pad << 16;
+
+	val = pad;
+	if (len > num*4)
+		len = num * 4;
+	for (i = 0; i < len; i++) {
+		if ((i % 4) == 0)
+			val = pad;
+		val = ((int) scp[i]) + (val << 8);
+		if ((i % 4) == 3) {
+			*buf++ = val;
+			val = pad;
+			num--;
+		}
+	}
+	if (--num >= 0)
+		*buf++ = val;
+	while (--num >= 0)
+		*buf++ = pad;
 }
 
-static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
+static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num)
 {
 	__u32	pad, val;
 	int	i;
+	const unsigned char *ucp = (const unsigned char *) msg;
 
 	pad = (__u32)len | ((__u32)len << 8);
 	pad |= pad << 16;
@@ -62,7 +110,7 @@ static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
 	for (i = 0; i < len; i++) {
 		if ((i % 4) == 0)
 			val = pad;
-		val = msg[i] + (val << 8);
+		val = ((int) ucp[i]) + (val << 8);
 		if ((i % 4) == 3) {
 			*buf++ = val;
 			val = pad;
@@ -95,6 +143,8 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 	const char	*p;
 	int		i;
 	__u32		in[8], buf[4];
+	void		(*str2hashbuf)(const char *, int, __u32 *, int) =
+				str2hashbuf_signed;
 
 	/* Initialize the default seed for the hash checksum functions */
 	buf[0] = 0x67452301;
@@ -113,13 +163,18 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 	}
 
 	switch (hinfo->hash_version) {
+	case DX_HASH_LEGACY_UNSIGNED:
+		hash = dx_hack_hash_unsigned(name, len);
+		break;
 	case DX_HASH_LEGACY:
-		hash = dx_hack_hash(name, len);
+		hash = dx_hack_hash_signed(name, len);
 		break;
+	case DX_HASH_HALF_MD4_UNSIGNED:
+		str2hashbuf = str2hashbuf_unsigned;
 	case DX_HASH_HALF_MD4:
 		p = name;
 		while (len > 0) {
-			str2hashbuf(p, len, in, 8);
+			(*str2hashbuf)(p, len, in, 8);
 			half_md4_transform(buf, in);
 			len -= 32;
 			p += 32;
@@ -127,10 +182,12 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 		minor_hash = buf[2];
 		hash = buf[1];
 		break;
+	case DX_HASH_TEA_UNSIGNED:
+		str2hashbuf = str2hashbuf_unsigned;
 	case DX_HASH_TEA:
 		p = name;
 		while (len > 0) {
-			str2hashbuf(p, len, in, 4);
+			(*str2hashbuf)(p, len, in, 4);
 			TEA_transform(buf, in);
 			len -= 16;
 			p += 16;

fs/ext4/ioctl.c

@@ -99,7 +99,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			goto flags_out;
 		}
 		if (IS_SYNC(inode))
-			handle->h_sync = 1;
+			ext4_handle_sync(handle);
 		err = ext4_reserve_inode_write(handle, inode, &iloc);
 		if (err)
 			goto flags_err;

fs/ext4/mballoc.h

@@ -20,6 +20,7 @@
 #include <linux/version.h>
 #include <linux/blkdev.h>
 #include <linux/marker.h>
+#include <linux/mutex.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
 #include "group.h"
@@ -98,9 +99,6 @@
  */
 #define MB_DEFAULT_GROUP_PREALLOC	512
 
-static struct kmem_cache *ext4_pspace_cachep;
-static struct kmem_cache *ext4_ac_cachep;
-static struct kmem_cache *ext4_free_ext_cachep;
 
 struct ext4_free_data {
 	/* this links the free block information from group_info */
@@ -120,26 +118,6 @@ struct ext4_free_data {
 	tid_t	t_tid;
 };
 
-struct ext4_group_info {
-	unsigned long	bb_state;
-	struct rb_root  bb_free_root;
-	unsigned short	bb_first_free;
-	unsigned short	bb_free;
-	unsigned short	bb_fragments;
-	struct		list_head bb_prealloc_list;
-#ifdef DOUBLE_CHECK
-	void		*bb_bitmap;
-#endif
-	unsigned short	bb_counters[];
-};
-
-#define EXT4_GROUP_INFO_NEED_INIT_BIT	0
-#define EXT4_GROUP_INFO_LOCKED_BIT	1
-
-#define EXT4_MB_GRP_NEED_INIT(grp)	\
-	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
-
-
 struct ext4_prealloc_space {
 	struct list_head	pa_inode_list;
 	struct list_head	pa_group_list;
@@ -217,6 +195,11 @@ struct ext4_allocation_context {
 	__u8 ac_op;		/* operation, for history only */
 	struct page *ac_bitmap_page;
 	struct page *ac_buddy_page;
+	/*
+	 * pointer to the held semaphore upon successful
+	 * block allocation
+	 */
+	struct rw_semaphore *alloc_semp;
 	struct ext4_prealloc_space *ac_pa;
 	struct ext4_locality_group *ac_lg;
 };
@@ -250,6 +233,7 @@ struct ext4_buddy {
 	struct super_block *bd_sb;
 	__u16 bd_blkbits;
 	ext4_group_t bd_group;
+	struct rw_semaphore *alloc_semp;
 };
 #define EXT4_MB_BITMAP(e4b)	((e4b)->bd_bitmap)
 #define EXT4_MB_BUDDY(e4b)	((e4b)->bd_buddy)
@@ -259,51 +243,12 @@ static inline void ext4_mb_store_history(struct ext4_allocation_context *ac)
 {
 	return;
 }
-#else
-static void ext4_mb_store_history(struct ext4_allocation_context *ac);
 #endif
 
 #define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)
 
 struct buffer_head *read_block_bitmap(struct super_block *, ext4_group_t);
-
-static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
-					ext4_group_t group);
-static void ext4_mb_return_to_preallocation(struct inode *inode,
-					struct ext4_buddy *e4b, sector_t block,
-					int count);
-static void ext4_mb_put_pa(struct ext4_allocation_context *,
-			struct super_block *, struct ext4_prealloc_space *pa);
-static int ext4_mb_init_per_dev_proc(struct super_block *sb);
-static int ext4_mb_destroy_per_dev_proc(struct super_block *sb);
-static void release_blocks_on_commit(journal_t *journal, transaction_t *txn);
-
-
-static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
-{
-	struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
-
-	bit_spin_lock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
-}
-
-static inline void ext4_unlock_group(struct super_block *sb,
-					ext4_group_t group)
-{
-	struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
-
-	bit_spin_unlock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
-}
-
-static inline int ext4_is_group_locked(struct super_block *sb,
-					ext4_group_t group)
-{
-	struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
-
-	return bit_spin_is_locked(EXT4_GROUP_INFO_LOCKED_BIT,
-						&(grinfo->bb_state));
-}
-
-static ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
+static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
 					struct ext4_free_extent *fex)
 {
 	ext4_fsblk_t block;

fs/ext4/migrate.c

@@ -59,7 +59,8 @@ static int finish_range(handle_t *handle, struct inode *inode,
 	/*
 	 * Make sure the credit we accumalated is not really high
 	 */
-	if (needed && handle->h_buffer_credits >= EXT4_RESERVE_TRANS_BLOCKS) {
+	if (needed && ext4_handle_has_enough_credits(handle,
+						EXT4_RESERVE_TRANS_BLOCKS)) {
 		retval = ext4_journal_restart(handle, needed);
 		if (retval)
 			goto err_out;
@@ -229,7 +230,7 @@ static int extend_credit_for_blkdel(handle_t *handle, struct inode *inode)
 {
 	int retval = 0, needed;
 
-	if (handle->h_buffer_credits > EXT4_RESERVE_TRANS_BLOCKS)
+	if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
 		return 0;
 	/*
 	 * We are freeing a blocks. During this we touch
@@ -458,13 +459,13 @@ int ext4_ext_migrate(struct inode *inode)
 	struct list_blocks_struct lb;
 	unsigned long max_entries;
 
-	if (!test_opt(inode->i_sb, EXTENTS))
-		/*
-		 * if mounted with noextents we don't allow the migrate
-		 */
-		return -EINVAL;
-
-	if ((EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+	/*
+	 * If the filesystem does not support extents, or the inode
+	 * already is extent-based, error out.
+	 */
+	if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
+				       EXT4_FEATURE_INCOMPAT_EXTENTS) ||
+	    (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
 		return -EINVAL;
 
 	if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0)

fs/ext4/xattr.c

@@ -457,7 +457,7 @@ static void ext4_xattr_update_super_block(handle_t *handle,
 	if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
 		EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR);
 		sb->s_dirt = 1;
-		ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+		ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
 	}
 }
 
@@ -487,9 +487,9 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 		ext4_forget(handle, 1, inode, bh, bh->b_blocknr);
 	} else {
 		le32_add_cpu(&BHDR(bh)->h_refcount, -1);
-		error = ext4_journal_dirty_metadata(handle, bh);
+		error = ext4_handle_dirty_metadata(handle, inode, bh);
 		if (IS_SYNC(inode))
-			handle->h_sync = 1;
+			ext4_handle_sync(handle);
 		DQUOT_FREE_BLOCK(inode, 1);
 		ea_bdebug(bh, "refcount now=%d; releasing",
 			  le32_to_cpu(BHDR(bh)->h_refcount));
@@ -724,8 +724,9 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			if (error == -EIO)
 				goto bad_block;
 			if (!error)
-				error = ext4_journal_dirty_metadata(handle,
-								    bs->bh);
+				error = ext4_handle_dirty_metadata(handle,
+								   inode,
+								   bs->bh);
 			if (error)
 				goto cleanup;
 			goto inserted;
@@ -794,8 +795,9 @@ inserted:
 				ea_bdebug(new_bh, "reusing; refcount now=%d",
 					le32_to_cpu(BHDR(new_bh)->h_refcount));
 				unlock_buffer(new_bh);
-				error = ext4_journal_dirty_metadata(handle,
-								    new_bh);
+				error = ext4_handle_dirty_metadata(handle,
+								   inode,
+								   new_bh);
 				if (error)
 					goto cleanup_dquot;
 			}
@@ -810,8 +812,8 @@ inserted:
 			/* We need to allocate a new block */
 			ext4_fsblk_t goal = ext4_group_first_block_no(sb,
 						EXT4_I(inode)->i_block_group);
-			ext4_fsblk_t block = ext4_new_meta_block(handle, inode,
-							goal, &error);
+			ext4_fsblk_t block = ext4_new_meta_blocks(handle, inode,
+						  goal, NULL, &error);
 			if (error)
 				goto cleanup;
 			ea_idebug(inode, "creating block %d", block);
@@ -833,7 +835,8 @@ getblk_failed:
 			set_buffer_uptodate(new_bh);
 			unlock_buffer(new_bh);
 			ext4_xattr_cache_insert(new_bh);
-			error = ext4_journal_dirty_metadata(handle, new_bh);
+			error = ext4_handle_dirty_metadata(handle,
+							   inode, new_bh);
 			if (error)
 				goto cleanup;
 		}
@@ -1040,7 +1043,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 		 */
 		is.iloc.bh = NULL;
 		if (IS_SYNC(inode))
-			handle->h_sync = 1;
+			ext4_handle_sync(handle);
 	}
 
 cleanup:

fs/ioprio.c

@@ -27,7 +27,7 @@
 #include <linux/security.h>
 #include <linux/pid_namespace.h>
 
-static int set_task_ioprio(struct task_struct *task, int ioprio)
+int set_task_ioprio(struct task_struct *task, int ioprio)
 {
 	int err;
 	struct io_context *ioc;
@@ -70,6 +70,7 @@ static int set_task_ioprio(struct task_struct *task, int ioprio)
 	task_unlock(task);
 	return err;
 }
+EXPORT_SYMBOL_GPL(set_task_ioprio);
 
 asmlinkage long sys_ioprio_set(int which, int who, int ioprio)
 {

fs/jbd2/checkpoint.c

@@ -249,16 +249,14 @@ restart:
 	return ret;
 }
 
-#define NR_BATCH	64
-
 static void
-__flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
+__flush_batch(journal_t *journal, int *batch_count)
 {
 	int i;
 
-	ll_rw_block(SWRITE, *batch_count, bhs);
+	ll_rw_block(SWRITE, *batch_count, journal->j_chkpt_bhs);
 	for (i = 0; i < *batch_count; i++) {
-		struct buffer_head *bh = bhs[i];
+		struct buffer_head *bh = journal->j_chkpt_bhs[i];
 		clear_buffer_jwrite(bh);
 		BUFFER_TRACE(bh, "brelse");
 		__brelse(bh);
@@ -277,8 +275,7 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
  * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
  */
 static int __process_buffer(journal_t *journal, struct journal_head *jh,
-			struct buffer_head **bhs, int *batch_count,
-			transaction_t *transaction)
+			    int *batch_count, transaction_t *transaction)
 {
 	struct buffer_head *bh = jh2bh(jh);
 	int ret = 0;
@@ -325,14 +322,14 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 		get_bh(bh);
 		J_ASSERT_BH(bh, !buffer_jwrite(bh));
 		set_buffer_jwrite(bh);
-		bhs[*batch_count] = bh;
+		journal->j_chkpt_bhs[*batch_count] = bh;
 		__buffer_relink_io(jh);
 		jbd_unlock_bh_state(bh);
 		transaction->t_chp_stats.cs_written++;
 		(*batch_count)++;
-		if (*batch_count == NR_BATCH) {
+		if (*batch_count == JBD2_NR_BATCH) {
 			spin_unlock(&journal->j_list_lock);
-			__flush_batch(journal, bhs, batch_count);
+			__flush_batch(journal, batch_count);
 			ret = 1;
 		}
 	}
@@ -388,7 +385,6 @@ restart:
 	if (journal->j_checkpoint_transactions == transaction &&
 			transaction->t_tid == this_tid) {
 		int batch_count = 0;
-		struct buffer_head *bhs[NR_BATCH];
 		struct journal_head *jh;
 		int retry = 0, err;
 
@@ -402,7 +398,7 @@ restart:
 				retry = 1;
 				break;
 			}
-			retry = __process_buffer(journal, jh, bhs, &batch_count,
+			retry = __process_buffer(journal, jh, &batch_count,
 						 transaction);
 			if (retry < 0 && !result)
 				result = retry;
@@ -419,7 +415,7 @@ restart:
 				spin_unlock(&journal->j_list_lock);
 				retry = 1;
 			}
-			__flush_batch(journal, bhs, &batch_count);
+			__flush_batch(journal, &batch_count);
 		}
 
 		if (retry) {
@@ -686,6 +682,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 	   safely remove this transaction from the log */
 
 	__jbd2_journal_drop_transaction(journal, transaction);
+	kfree(transaction);
 
 	/* Just in case anybody was waiting for more transactions to be
            checkpointed... */
@@ -760,5 +757,4 @@ void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transact
 	J_ASSERT(journal->j_running_transaction != transaction);
 
 	jbd_debug(1, "Dropping transaction %d, all done\n", transaction->t_tid);
-	kfree(transaction);
 }

fs/super.c

@@ -810,6 +810,7 @@ int get_sb_bdev(struct file_system_type *fs_type,
 		}
 
 		s->s_flags |= MS_ACTIVE;
+		bdev->bd_super = s;
 	}
 
 	return simple_set_mnt(mnt, s);
@@ -829,6 +830,7 @@ void kill_block_super(struct super_block *sb)
 	struct block_device *bdev = sb->s_bdev;
 	fmode_t mode = sb->s_mode;
 
+	bdev->bd_super = 0;
 	generic_shutdown_super(sb);
 	sync_blockdev(bdev);
 	close_bdev_exclusive(bdev, mode);

include/linux/ext3_fs_sb.h

@@ -57,6 +57,7 @@ struct ext3_sb_info {
 	u32 s_next_generation;
 	u32 s_hash_seed[4];
 	int s_def_hash_version;
+	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
 	struct percpu_counter s_freeblocks_counter;
 	struct percpu_counter s_freeinodes_counter;
 	struct percpu_counter s_dirs_counter;

include/linux/ioprio.h

@@ -86,4 +86,6 @@ static inline int task_nice_ioclass(struct task_struct *task)
  */
 extern int ioprio_best(unsigned short aprio, unsigned short bprio);
 
+extern int set_task_ioprio(struct task_struct *task, int ioprio);
+
 #endif