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

@@ -1234,13 +1234,28 @@ 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,
 	.sync_page	= block_sync_page,
 	.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;
@@ -113,24 +163,31 @@ 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;
 		}
 		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;