From: Jan Kara <jack@suse.cz>

We should really call journal_abort() and not __journal_abort_hard() in
case of errors.  The latter call does not record the error in the journal
superblock and thus filesystem won't be marked as with errors later (and
user could happily mount it without any warning).

Signed-off-by: Jan Kara <jack@suse.cz>
Cc: <linux-ext4@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/jbd2/commit.c |    8 ++++----
 1 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index b898ee4..6986f33 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -475,7 +475,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	spin_unlock(&journal->j_list_lock);
 
 	if (err)
-		__jbd2_journal_abort_hard(journal);
+		jbd2_journal_abort(journal, err);
 
 	jbd2_journal_write_revoke_records(journal, commit_transaction);
 
@@ -533,7 +533,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 
 			descriptor = jbd2_journal_get_descriptor_buffer(journal);
 			if (!descriptor) {
-				__jbd2_journal_abort_hard(journal);
+				jbd2_journal_abort(journal, -EIO);
 				continue;
 			}
 
@@ -566,7 +566,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		   and repeat this loop: we'll fall into the
 		   refile-on-abort condition above. */
 		if (err) {
-			__jbd2_journal_abort_hard(journal);
+			jbd2_journal_abort(journal, err);
 			continue;
 		}
 
@@ -757,7 +757,7 @@ wait_for_iobuf:
 		err = -EIO;
 
 	if (err)
-		__jbd2_journal_abort_hard(journal);
+		jbd2_journal_abort(journal, err);
 
 	/* End of a transaction!  Finally, we can do checkpoint
            processing: any buffers committed as a result of this
-- 
1.5.3.2.81.g17ed

-

[ message continues ]

From: Jose R. Santos <jrs@us.ibm.com>

Mostly stolen from akpm's JBD cleanup patch.

- use `#ifdef foo' instead of `#if defined(foo)'

- Make journal_enable_debug __read_mostly just for the heck of it

- Make jbd_debugfs_dir and jbd_debug static

- debugfs_remove(NULL) is legal: remove unneeded tests

- remove unnecessary empty loops

Signed-off-by: Jose R. Santos <jrs@us.ibm.com>
Cc: <linux-ext4@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/jbd2/journal.c |   20 ++++++--------------
 1 files changed, 6 insertions(+), 14 deletions(-)

diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index ff07bff..6ddc553 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1864,16 +1864,14 @@ void jbd2_journal_put_journal_head(struct journal_head *jh)
 /*
  * debugfs tunables
  */
-#if defined(CONFIG_JBD2_DEBUG)
-u8 jbd2_journal_enable_debug;
+#ifdef CONFIG_JBD2_DEBUG
+u8 jbd2_journal_enable_debug __read_mostly;
 EXPORT_SYMBOL(jbd2_journal_enable_debug);
-#endif
-
-#if defined(CONFIG_JBD2_DEBUG) && defined(CONFIG_DEBUG_FS)
 
 #define JBD2_DEBUG_NAME "jbd2-debug"
 
-struct dentry *jbd2_debugfs_dir, *jbd2_debug;
+static struct dentry *jbd2_debugfs_dir;
+static struct dentry *jbd2_debug;
 
 static void __init jbd2_create_debugfs_entry(void)
 {
@@ -1886,24 +1884,18 @@ static void __init jbd2_create_debugfs_entry(void)
 
 static void __exit jbd2_remove_debugfs_entry(void)
 {
-	if (jbd2_debug)
-		debugfs_remove(jbd2_debug);
-	if (jbd2_debugfs_dir)
-		debugfs_remove(jbd2_debugfs_dir);
+	debugfs_remove(jbd2_debug);
+	debugfs_remove(jbd2_debugfs_dir);
 }
 
 #else
 
 static void __init jbd2_create_debugfs_entry(void)
 {
-	do {
-	} while (0);
 }
 
 static void __exit jbd2_remove_debugfs_entry(void)
 {
-	do {
-	} while (0);
 }
 
 #endif
-- 
1.5.3.2.81.g17ed

-

[ message continues ]

From: Coly Li <coyli@suse.de>

implement in future.  Therefore fragment related source code in ext4 should
be obsoleted -- no one will use it.

This patch obsolete fragment from ext4.  Another patch posted on linux-ext4
removing fragment supporting from e2fsprogs.

Signed-off-by: Coly Li <coyli@suse.de>
Acked-by: Andreas Dilger <adilger@clusterfs.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/ext4/ialloc.c           |    5 -----
 fs/ext4/inode.c            |   10 ----------
 fs/ext4/super.c            |   15 ---------------
 include/linux/ext4_fs.h    |   35 ++++++-----------------------------
 include/linux/ext4_fs_i.h  |    5 -----
 include/linux/ext4_fs_sb.h |    3 ---
 6 files changed, 6 insertions(+), 67 deletions(-)

diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 427f830..b8b538d 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -576,11 +576,6 @@ got:
 	/* dirsync only applies to directories */
 	if (!S_ISDIR(mode))
 		ei->i_flags &= ~EXT4_DIRSYNC_FL;
-#ifdef EXT4_FRAGMENTS
-	ei->i_faddr = 0;
-	ei->i_frag_no = 0;
-	ei->i_frag_size = 0;
-#endif
 	ei->i_file_acl = 0;
 	ei->i_dir_acl = 0;
 	ei->i_dtime = 0;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index a4848e0..f283522 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2645,11 +2645,6 @@ void ext4_read_inode(struct inode * inode)
 	}
 	inode->i_blocks = le32_to_cpu(raw_inode->i_blocks);
 	ei->i_flags = le32_to_cpu(raw_inode->i_flags);
-#ifdef EXT4_FRAGMENTS
-	ei->i_faddr = le32_to_cpu(raw_inode->i_faddr);
-	ei->i_frag_no = raw_inode->i_frag;
-	ei->i_frag_size = raw_inode->i_fsize;
-#endif
 	ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl);
 	if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
 	    cpu_to_le32(EXT4_OS_HURD))
@@ -2794,11 +2789,6 @@ static int ext4_do_update_inode(handle_t *handle,
 	raw_inode->i_blocks = cpu_to_le32(inode->i_blocks);
 	raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
 	raw_inode->i_flags = cpu_to_le32(ei->i_flags);
-#ifdef ...
[ message continues ]

From: Eric Sandeen <sandeen@redhat.com>

CONFIG_EXT4_INDEX is not an exposed config option in the kernel, and it is
unconditionally defined in ext4_fs.h.  tune2fs is already able to turn off
dir indexing, so at this point it's just cluttering up the code.  Remove
it.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Mingming Cao <cmm@us.ibm.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/ext4/dir.c           |    7 -------
 fs/ext4/namei.c         |   20 --------------------
 include/linux/ext4_fs.h |   14 ++------------
 3 files changed, 2 insertions(+), 39 deletions(-)

diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 3ab01c0..2ba49ff 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -47,9 +47,7 @@ const struct file_operations ext4_dir_operations = {
 	.compat_ioctl	= ext4_compat_ioctl,
 #endif
 	.fsync		= ext4_sync_file,	/* BKL held */
-#ifdef CONFIG_EXT4_INDEX
 	.release	= ext4_release_dir,
-#endif
 };
 
 
@@ -107,7 +105,6 @@ static int ext4_readdir(struct file * filp,
 
 	sb = inode->i_sb;
 
-#ifdef CONFIG_EXT4_INDEX
 	if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
 				    EXT4_FEATURE_COMPAT_DIR_INDEX) &&
 	    ((EXT4_I(inode)->i_flags & EXT4_INDEX_FL) ||
@@ -123,7 +120,6 @@ static int ext4_readdir(struct file * filp,
 		 */
 		EXT4_I(filp->f_path.dentry->d_inode)->i_flags &= ~EXT4_INDEX_FL;
 	}
-#endif
 	stored = 0;
 	offset = filp->f_pos & (sb->s_blocksize - 1);
 
@@ -232,7 +228,6 @@ out:
 	return ret;
 }
 
-#ifdef CONFIG_EXT4_INDEX
 /*
  * These functions convert from the major/minor hash to an f_pos
  * value.
@@ -518,5 +513,3 @@ static int ext4_release_dir (struct inode * inode, struct file * filp)
 
 	return 0;
 }
-
-#endif
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 5fdb862..94ee6f3 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -144,7 +144,6 @@ struct dx_map_entry
 	u16 size;
 };
 
-#ifdef CONFIG_EXT4_INDEX
 static inline unsigned ...
[ message continues ]

From: Andreas Dilger <adilger@clusterfs.com>

In pass1 of e2fsck, every inode table in the fileystem is scanned and checked,
regardless of whether it is in use.  This is this the most time consuming part
of the filesystem check.  The unintialized block group feature can greatly
reduce e2fsck time by eliminating checking of uninitialized inodes.

With this feature, there is a a high water mark of used inodes for each block
group.  Block and inode bitmaps can be uninitialized on disk via a flag in the
group descriptor to avoid reading or scanning them at e2fsck time.  A checksum
of each group descriptor is used to ensure that corruption in the group
descriptor's bit flags does not cause incorrect operation.

The feature is enabled through a mkfs option

	mke2fs /dev/ -O uninit_groups

A patch adding support for uninitialized block groups to e2fsprogs tools has
been posted to the linux-ext4 mailing list.

The patches have been stress tested with fsstress and fsx.  In performance
tests testing e2fsck time, we have seen that e2fsck time on ext3 grows
linearly with the total number of inodes in the filesytem.  In ext4 with the
uninitialized block groups feature, the e2fsck time is constant, based
solely on the number of used inodes rather than the total inode count.
Since typical ext4 filesystems only use 1-10% of their inodes, this feature can
greatly reduce e2fsck time for users.  With performance improvement of 2-20
times, depending on how full the filesystem is.

The attached graph shows the major improvements in e2fsck times in filesystems
with a large total inode count, but few inodes in use.

In each group descriptor if we have

EXT4_BG_INODE_UNINIT set in bg_flags:
        Inode table is not initialized/used in this group. So we can skip
        the consistency check during fsck.
EXT4_BG_BLOCK_UNINIT set in bg_flags:
        No block in the group is used. So we can skip the block bitmap
        verification for this group.

We also add two new fields to group ...
[ message continues ]

From: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/ext4/inode.c         |    6 ++++--
 include/linux/ext4_fs.h |   14 +++++++-------
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f283522..a2e1ea4 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3167,12 +3167,14 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 						      iloc, handle);
 			if (ret) {
 				EXT4_I(inode)->i_state |= EXT4_STATE_NO_EXPAND;
-				if (mnt_count != sbi->s_es->s_mnt_count) {
+				if (mnt_count !=
+					le16_to_cpu(sbi->s_es->s_mnt_count)) {
 					ext4_warning(inode->i_sb, __FUNCTION__,
 					"Unable to expand inode %lu. Delete"
 					" some EAs or run e2fsck.",
 					inode->i_ino);
-					mnt_count = sbi->s_es->s_mnt_count;
+					mnt_count =
+					  le16_to_cpu(sbi->s_es->s_mnt_count);
 				}
 			}
 		}
diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h
index b77b59f..722d4ef 100644
--- a/include/linux/ext4_fs.h
+++ b/include/linux/ext4_fs.h
@@ -574,13 +574,13 @@ struct ext4_super_block {
 /*150*/	__le32	s_blocks_count_hi;	/* Blocks count */
 	__le32	s_r_blocks_count_hi;	/* Reserved blocks count */
 	__le32	s_free_blocks_count_hi;	/* Free blocks count */
-	__u16	s_min_extra_isize;	/* All inodes have at least # bytes */
-	__u16	s_want_extra_isize; 	/* New inodes should reserve # bytes */
-	__u32	s_flags;		/* Miscellaneous flags */
-	__u16   s_raid_stride;		/* RAID stride */
-	__u16   s_mmp_interval;         /* # seconds to wait in MMP checking */
-	__u64   s_mmp_block;            /* Block for multi-mount protection */
-	__u32   s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
+	__le16	s_min_extra_isize;	/* All inodes have at least # bytes */
+	__le16	s_want_extra_isize; 	/* New inodes should reserve # bytes */
+	__le32	s_flags;		/* ...
[ message continues ]

From: Jose R. Santos <jrs@us.ibm.com>

data is located within the storage media.  This allows for the allocation
of bitmaps or inode tables outside the block group boundaries in cases
where bad blocks forces us to look for new blocks which the owning block
group can not satisfy.  This will also allow for new meta-data allocation
schemes to improve performance and scalability.

Signed-off-by: Jose R. Santos <jrs@us.ibm.com>
Cc: <linux-ext4@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/ext4/super.c         |    9 +++++++--
 include/linux/ext4_fs.h |    4 +++-
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b59610d..619db84 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1287,13 +1287,17 @@ static int ext4_check_descriptors (struct super_block * sb)
 	ext4_fsblk_t inode_table;
 	struct ext4_group_desc * gdp = NULL;
 	int desc_block = 0;
+	int flexbg_flag = 0;
 	int i;
 
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
+		flexbg_flag = 1;
+
 	ext4_debug ("Checking group descriptors");
 
 	for (i = 0; i < sbi->s_groups_count; i++)
 	{
-		if (i == sbi->s_groups_count - 1)
+		if (i == sbi->s_groups_count - 1 || flexbg_flag)
 			last_block = ext4_blocks_count(sbi->s_es) - 1;
 		else
 			last_block = first_block +
@@ -1338,7 +1342,8 @@ static int ext4_check_descriptors (struct super_block * sb)
 				   le16_to_cpu(gdp->bg_checksum));
 			return 0;
 		}
-		first_block += EXT4_BLOCKS_PER_GROUP(sb);
+		if (!flexbg_flag)
+			first_block += EXT4_BLOCKS_PER_GROUP(sb);
 		gdp = (struct ext4_group_desc *)
 			((__u8 *)gdp + EXT4_DESC_SIZE(sb));
 	}
diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h
index 722d4ef..46b304d 100644
--- a/include/linux/ext4_fs.h
+++ b/include/linux/ext4_fs.h
@@ -682,13 +682,15 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 #define EXT4_FEATURE_INCOMPAT_META_BG		0x0010
 #define ...
[ message continues ]

From: Takashi Sato <sho@tnes.nec.co.jp>

This patch set supports large block size(>4k, <=64k) in ext4,
just enlarging the block size limit. But it is NOT possible to have 64kB
blocksize on ext4 without some changes to the directory handling
code.  The reason is that an empty 64kB directory block would have a
rec_len == (__u16)2^16 == 0, and this would cause an error to be hit in
the filesystem.  The proposed solution is treat 64k rec_len
with a an impossible value like rec_len = 0xffff to handle this.

The Patch-set consists of the following 2 patches.
  [1/2]  ext4: enlarge blocksize
         - Allow blocksize up to pagesize

  [2/2]  ext4: fix rec_len overflow
         - prevent rec_len from overflow with 64KB blocksize

Now on 64k page ppc64 box runs with this patch set we could create a 64k
block size ext4dev, and able to handle empty directory block.

Signed-off-by: Takashi Sato <sho@tnes.nec.co.jp>
Signed-off-by: Mingming Cao <cmm@us.ibm.com>
---
 fs/ext4/super.c         |    5 +++++
 include/linux/ext4_fs.h |    4 ++--
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 619db84..d8bb279 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1548,6 +1548,11 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
 		goto out_fail;
 	}
 
+	if (!sb_set_blocksize(sb, blocksize)) {
+		printk(KERN_ERR "EXT4-fs: bad blocksize %d.\n", blocksize);
+		goto out_fail;
+	}
+
 	/*
 	 * The ext4 superblock will not be buffer aligned for other than 1kB
 	 * block sizes.  We need to calculate the offset from buffer start.
diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h
index 46b304d..5d90616 100644
--- a/include/linux/ext4_fs.h
+++ b/include/linux/ext4_fs.h
@@ -73,8 +73,8 @@
  * Macro-instructions used to manage several block sizes
  */
 #define EXT4_MIN_BLOCK_SIZE		1024
-#define	EXT4_MAX_BLOCK_SIZE		4096
-#define EXT4_MIN_BLOCK_LOG_SIZE		  ...
[ message continues ]

From: Jan Kara <jack@suse.cz>

With 64KB blocksize, a directory entry can have size 64KB which does not fit
into 16 bits we have for entry lenght. So we store 0xffff instead and convert
value when read from / written to disk. The patch also converts some places
to use ext4_next_entry() when we are changing them anyway.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mingming Cao <cmm@us.ibm.com>
---
 fs/ext4/dir.c           |   12 ++++----
 fs/ext4/namei.c         |   76 ++++++++++++++++++++++------------------------
 include/linux/ext4_fs.h |   20 ++++++++++++
 3 files changed, 62 insertions(+), 46 deletions(-)

diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 2ba49ff..8236352 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -67,7 +67,7 @@ int ext4_check_dir_entry (const char * function, struct inode * dir,
 			  unsigned long offset)
 {
 	const char * error_msg = NULL;
-	const int rlen = le16_to_cpu(de->rec_len);
+	const int rlen = ext4_rec_len_from_disk(de->rec_len);
 
 	if (rlen < EXT4_DIR_REC_LEN(1))
 		error_msg = "rec_len is smaller than minimal";
@@ -172,10 +172,10 @@ revalidate:
 				 * least that it is non-zero.  A
 				 * failure will be detected in the
 				 * dirent test below. */
-				if (le16_to_cpu(de->rec_len) <
-						EXT4_DIR_REC_LEN(1))
+				if (ext4_rec_len_from_disk(de->rec_len)
+						< EXT4_DIR_REC_LEN(1))
 					break;
-				i += le16_to_cpu(de->rec_len);
+				i += ext4_rec_len_from_disk(de->rec_len);
 			}
 			offset = i;
 			filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1))
@@ -197,7 +197,7 @@ revalidate:
 				ret = stored;
 				goto out;
 			}
-			offset += le16_to_cpu(de->rec_len);
+			offset += ext4_rec_len_from_disk(de->rec_len);
 			if (le32_to_cpu(de->inode)) {
 				/* We might block in the next section
 				 * if the data destination is
@@ -219,7 +219,7 @@ revalidate:
 					goto revalidate;
 				stored ++;
 			}
-			filp->f_pos += le16_to_cpu(de->rec_len);
+			filp->f_pos += ...
[ message continues ]

From: Takashi Sato <sho@tnes.nec.co.jp>

This patch set supports large block size(>4k, <=64k) in ext2,
just enlarging the block size limit. But it is NOT possible to have 64kB
blocksize on ext2 without some changes to the directory handling
code.  The reason is that an empty 64kB directory block would have a
rec_len == (__u16)2^16 == 0, and this would cause an error to be hit in
the filesystem.  The proposed solution is treat 64k rec_len
with a an impossible value like rec_len = 0xffff to handle this.

The Patch-set consists of the following 2 patches.
  [1/2]  ext2: enlarge blocksize
         - Allow blocksize up to pagesize

  [2/2]  ext2: fix rec_len overflow
         - prevent rec_len from overflow with 64KB blocksize

Now on 64k page ppc64 box runs with this patch set we could create a 64k
block size ext2, and able to handle empty directory block.

Signed-off-by: Takashi Sato <sho@tnes.nec.co.jp>
Signed-off-by: Mingming Cao <cmm@us.ibm.com>
---
 fs/ext2/super.c         |    3 ++-
 include/linux/ext2_fs.h |    4 ++--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 639a32c..765c805 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -775,7 +775,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 		brelse(bh);
 
 		if (!sb_set_blocksize(sb, blocksize)) {
-			printk(KERN_ERR "EXT2-fs: blocksize too small for device.\n");
+			printk(KERN_ERR "EXT2-fs: bad blocksize %d.\n",
+				blocksize);
 			goto failed_sbi;
 		}
 
diff --git a/include/linux/ext2_fs.h b/include/linux/ext2_fs.h
index 153d755..910a705 100644
--- a/include/linux/ext2_fs.h
+++ b/include/linux/ext2_fs.h
@@ -86,8 +86,8 @@ static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb)
  * Macro-instructions used to manage several block sizes
  */
 #define EXT2_MIN_BLOCK_SIZE		1024
-#define	EXT2_MAX_BLOCK_SIZE		4096
-#define EXT2_MIN_BLOCK_LOG_SIZE		  10
+#define EXT2_MAX_BLOCK_SIZE		65536
+#define ...
[ message continues ]

From: Takashi Sato <sho@tnes.nec.co.jp>

This patch set supports large block size(>4k, <=64k) in ext3
just enlarging the block size limit. But it is NOT possible to have 64kB
blocksize on ext3 without some changes to the directory handling
code.  The reason is that an empty 64kB directory block would have a
rec_len == (__u16)2^16 == 0, and this would cause an error to be hit in
the filesystem.  The proposed solution is treat 64k rec_len
with a an impossible value like rec_len = 0xffff to handle this.

The Patch-set consists of the following 2 patches.
  [1/2]  ext3: enlarge blocksize
         - Allow blocksize up to pagesize

  [2/2]  ext3: fix rec_len overflow
         - prevent rec_len from overflow with 64KB blocksize

Now on 64k page ppc64 box runs with this patch set we could create a 64k
block size ext3, and able to handle empty directory block.

Signed-off-by: Takashi Sato <sho@tnes.nec.co.jp>
Signed-off-by: Mingming Cao <cmm@us.ibm.com>
---
 fs/ext3/super.c         |    6 +++++-
 include/linux/ext3_fs.h |    4 ++--
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 9537316..b4bfd36 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -1549,7 +1549,11 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 		}
 
 		brelse (bh);
-		sb_set_blocksize(sb, blocksize);
+		if (!sb_set_blocksize(sb, blocksize)) {
+			printk(KERN_ERR "EXT3-fs: bad blocksize %d.\n",
+				blocksize);
+			goto out_fail;
+		}
 		logic_sb_block = (sb_block * EXT3_MIN_BLOCK_SIZE) / blocksize;
 		offset = (sb_block * EXT3_MIN_BLOCK_SIZE) % blocksize;
 		bh = sb_bread(sb, logic_sb_block);
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index ece49a8..7aa5556 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -76,8 +76,8 @@
  * Macro-instructions used to manage several block sizes
  */
 #define EXT3_MIN_BLOCK_SIZE		1024
-#define	EXT3_MAX_BLOCK_SIZE		4096
-#define ...
[ message continues ]

From: Jan Kara <jack@suse.cz>

With 64KB blocksize, a directory entry can have size 64KB which does not fit
into 16 bits we have for entry lenght. So we store 0xffff instead and convert
value when read from / written to disk.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mingming Cao <cmm@us.ibm.com>
---
 fs/ext2/dir.c           |   43 +++++++++++++++++++++++++++++++------------
 include/linux/ext2_fs.h |    1 +
 2 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 2bf49d7..1329bdb 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -26,6 +26,24 @@
 
 typedef struct ext2_dir_entry_2 ext2_dirent;
 
+static inline unsigned ext2_rec_len_from_disk(__le16 dlen)
+{
+	unsigned len = le16_to_cpu(dlen);
+
+	if (len == EXT2_MAX_REC_LEN)
+		return 1 << 16;
+	return len;
+}
+
+static inline __le16 ext2_rec_len_to_disk(unsigned len)
+{
+	if (len == (1 << 16))
+		return cpu_to_le16(EXT2_MAX_REC_LEN);
+	else if (len > (1 << 16))
+		BUG();
+	return cpu_to_le16(len);
+}
+
 /*
  * ext2 uses block-sized chunks. Arguably, sector-sized ones would be
  * more robust, but we have what we have
@@ -95,7 +113,7 @@ static void ext2_check_page(struct page *page)
 	}
 	for (offs = 0; offs <= limit - EXT2_DIR_REC_LEN(1); offs += rec_len) {
 		p = (ext2_dirent *)(kaddr + offs);
-		rec_len = le16_to_cpu(p->rec_len);
+		rec_len = ext2_rec_len_from_disk(p->rec_len);
 
 		if (rec_len < EXT2_DIR_REC_LEN(1))
 			goto Eshort;
@@ -193,7 +211,8 @@ static inline int ext2_match (int len, const char * const name,
  */
 static inline ext2_dirent *ext2_next_entry(ext2_dirent *p)
 {
-	return (ext2_dirent *)((char*)p + le16_to_cpu(p->rec_len));
+	return (ext2_dirent *)((char*)p +
+			ext2_rec_len_from_disk(p->rec_len));
 }
 
 static inline unsigned 
@@ -305,7 +324,7 @@ ext2_readdir (struct file * filp, void * dirent, filldir_t filldir)
 					return 0;
 				}
 			}
-			filp->f_pos += le16_to_cpu(de->rec_len);
+			filp->f_pos += ...
[ message continues ]

From: Jan Kara <jack@suse.cz>

With 64KB blocksize, a directory entry can have size 64KB which does not fit
into 16 bits we have for entry lenght. So we store 0xffff instead and convert
value when read from / written to disk. The patch also converts some places
to use ext3_next_entry() when we are changing them anyway.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mingming Cao <cmm@us.ibm.com>
---
 fs/ext3/dir.c           |   10 +++---
 fs/ext3/namei.c         |   90 ++++++++++++++++++++++------------------------
 include/linux/ext3_fs.h |   20 ++++++++++
 3 files changed, 68 insertions(+), 52 deletions(-)

diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index c00723a..3c4c43a 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -69,7 +69,7 @@ int ext3_check_dir_entry (const char * function, struct inode * dir,
 			  unsigned long offset)
 {
 	const char * error_msg = NULL;
-	const int rlen = le16_to_cpu(de->rec_len);
+	const int rlen = ext3_rec_len_from_disk(de->rec_len);
 
 	if (rlen < EXT3_DIR_REC_LEN(1))
 		error_msg = "rec_len is smaller than minimal";
@@ -177,10 +177,10 @@ revalidate:
 				 * least that it is non-zero.  A
 				 * failure will be detected in the
 				 * dirent test below. */
-				if (le16_to_cpu(de->rec_len) <
+				if (ext3_rec_len_from_disk(de->rec_len) <
 						EXT3_DIR_REC_LEN(1))
 					break;
-				i += le16_to_cpu(de->rec_len);
+				i += ext3_rec_len_from_disk(de->rec_len);
 			}
 			offset = i;
 			filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1))
@@ -201,7 +201,7 @@ revalidate:
 				ret = stored;
 				goto out;
 			}
-			offset += le16_to_cpu(de->rec_len);
+			offset += ext3_rec_len_from_disk(de->rec_len);
 			if (le32_to_cpu(de->inode)) {
 				/* We might block in the next section
 				 * if the data destination is
@@ -223,7 +223,7 @@ revalidate:
 					goto revalidate;
 				stored ++;
 			}
-			filp->f_pos += le16_to_cpu(de->rec_len);
+			filp->f_pos += ext3_rec_len_from_disk(de->rec_len);
 		}
 		offset = 0;
 		brelse ...
[ message continues ]