[PATCH] ext4: remove #ifdef CONFIG_EXT4_INDEX

[PATCH] ext4: remove #ifdef CONFIG_EXT4_INDEX

[Eric Sandeen]

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>

 Index: ext4.git/fs/ext4/dir.c
===================================================================
--- ext4.git.orig/fs/ext4/dir.c
+++ ext4.git/fs/ext4/dir.c
@@ -47,9 +47,7 @@ const struct file_operations ext4_dir_op
 	.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 * fi
 
 	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 * fi
 		 */
 		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 inod
 
 	return 0;
 }
-
-#endif
Index: ext4.git/fs/ext4/namei.c
===================================================================
--- ext4.git.orig/fs/ext4/namei.c
+++ ext4.git/fs/ext4/namei.c
@@ -144,7 +144,6 @@ struct dx_map_entry
 	u16 size;
 };
 
-#ifdef CONFIG_EXT4_INDEX
 static inline unsigned dx_get_block (struct dx_entry *entry);
 static void dx_set_block (struct dx_entry *entry, unsigned value);
 static inline unsigned dx_get_hash (struct dx_entry *entry);
@@ -766,8 +765,6 @@ static void dx_insert_block(struct dx_fr
 	dx_set_block(new, block);
 	dx_set_count(entries, count + 1);
 }
-#endif
-
 
 static void ext4_update_dx_flag(struct inode *inode)
 {
@@ -869,7 +866,6 @@ static struct buffer_head * ext4_find_en
 	name = dentry->d_name.name;
 	if (namelen > EXT4_NAME_LEN)
 		return NULL;
-#ifdef CONFIG_EXT4_INDEX
 	if (is_dx(dir)) {
 		bh = ext4_dx_find_entry(dentry, res_dir, &err);
 		/*
@@ -881,7 +877,6 @@ static struct buffer_head * ext4_find_en
 			return bh;
 		dxtrace(printk("ext4_find_entry: dx failed, falling back\n"));
 	}
-#endif
 	nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
 	start = EXT4_I(dir)->i_dir_start_lookup;
 	if (start >= nblocks)
@@ -957,7 +952,6 @@ cleanup_and_exit:
 	return ret;
 }
 
-#ifdef CONFIG_EXT4_INDEX
 static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
 		       struct ext4_dir_entry_2 **res_dir, int *err)
 {
@@ -1025,7 +1019,6 @@ errout:
 	dx_release (frames);
 	return NULL;
 }
-#endif
 
 static struct dentry *ext4_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
 {
@@ -1121,7 +1114,6 @@ static inline void ext4_set_de_type(stru
 		de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
 }
 
-#ifdef CONFIG_EXT4_INDEX
 /*
  * Move count entries from end of map between two memory locations.
  * Returns pointer to last entry moved.
@@ -1266,8 +1258,6 @@ errout:
 	*error = err;
 	return NULL;
 }
-#endif
-
 
 /*
  * Add a new entry into a directory (leaf) block.  If de is non-NULL,
@@ -1364,7 +1354,6 @@ static int add_dirent_to_buf(handle_t *h
 	return 0;
 }
 
-#ifdef CONFIG_EXT4_INDEX
 /*
  * This converts a one block unindexed directory to a 3 block indexed
  * directory, and adds the dentry to the indexed directory.
@@ -1443,7 +1432,6 @@ static int make_indexed_dir(handle_t *ha
 
 	return add_dirent_to_buf(handle, dentry, inode, de, bh);
 }
-#endif
 
 /*
  *	ext4_add_entry()
@@ -1464,9 +1452,7 @@ static int ext4_add_entry (handle_t *han
 	struct ext4_dir_entry_2 *de;
 	struct super_block * sb;
 	int	retval;
-#ifdef CONFIG_EXT4_INDEX
 	int	dx_fallback=0;
-#endif
 	unsigned blocksize;
 	u32 block, blocks;
 
@@ -1474,7 +1460,6 @@ static int ext4_add_entry (handle_t *han
 	blocksize = sb->s_blocksize;
 	if (!dentry->d_name.len)
 		return -EINVAL;
-#ifdef CONFIG_EXT4_INDEX
 	if (is_dx(dir)) {
 		retval = ext4_dx_add_entry(handle, dentry, inode);
 		if (!retval || (retval != ERR_BAD_DX_DIR))
@@ -1483,7 +1468,6 @@ static int ext4_add_entry (handle_t *han
 		dx_fallback++;
 		ext4_mark_inode_dirty(handle, dir);
 	}
-#endif
 	blocks = dir->i_size >> sb->s_blocksize_bits;
 	for (block = 0, offset = 0; block < blocks; block++) {
 		bh = ext4_bread(handle, dir, block, 0, &retval);
@@ -1493,11 +1477,9 @@ static int ext4_add_entry (handle_t *han
 		if (retval != -ENOSPC)
 			return retval;
 
-#ifdef CONFIG_EXT4_INDEX
 		if (blocks == 1 && !dx_fallback &&
 		    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX))
 			return make_indexed_dir(handle, dentry, inode, bh);
-#endif
 		brelse(bh);
 	}
 	bh = ext4_append(handle, dir, &block, &retval);
@@ -1509,7 +1491,6 @@ static int ext4_add_entry (handle_t *han
 	return add_dirent_to_buf(handle, dentry, inode, de, bh);
 }
 
-#ifdef CONFIG_EXT4_INDEX
 /*
  * Returns 0 for success, or a negative error value
  */
@@ -1644,7 +1625,6 @@ cleanup:
 	dx_release(frames);
 	return err;
 }
-#endif
 
 /*
  * ext4_delete_entry deletes a directory entry by merging it with the
Index: ext4.git/include/linux/ext4_fs.h
===================================================================
--- ext4.git.orig/include/linux/ext4_fs.h
+++ ext4.git/include/linux/ext4_fs.h
@@ -36,10 +36,6 @@
 /*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */
 #define EXT4_MAX_RESERVE_BLOCKS		1027
 #define EXT4_RESERVE_WINDOW_NOT_ALLOCATED 0
-/*
- * Always enable hashed directories
- */
-#define CONFIG_EXT4_INDEX
 
 /*
  * Debug code
@@ -789,17 +785,11 @@ struct ext4_dir_entry_2 {
  * (c) Daniel Phillips, 2001
  */
 
-#ifdef CONFIG_EXT4_INDEX
-  #define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \
-					      EXT4_FEATURE_COMPAT_DIR_INDEX) && \
+#define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \
+				      EXT4_FEATURE_COMPAT_DIR_INDEX) && \
 		      (EXT4_I(dir)->i_flags & EXT4_INDEX_FL))
 #define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX)
 #define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)
-#else
-  #define is_dx(dir) 0
-#define EXT4_DIR_LINK_MAX(dir) ((dir)->i_nlink >= EXT4_LINK_MAX)
-#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2)
-#endif
 
 /* Legal values for the dx_root hash_version field: */
 

[PATCH, RFC] Ext4 patches planned for submission upstream

[Theodore Ts'o]

The following ext4 patches are planned for submission to Linus once
the merge window for 2.6.24-rc1 is opened.

						- Ted

[PATCH] jbd/jbd2: JBD memory allocation cleanups

[Theodore Ts'o]

From: Mingming Cao <cmm@us.ibm.com>

JBD: Replace slab allocations with page cache allocations

JBD allocate memory for committed_data and frozen_data from slab. However
JBD should not pass slab pages down to the block layer. Use page allocator pages instead. This will also prepare JBD for the large blocksize patchset.


Also this patch cleans up jbd_kmalloc and replace it with kmalloc directly

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Mingming Cao <cmm@us.ibm.com>
---
 fs/jbd/commit.c       |    6 +-
 fs/jbd/journal.c      |   99 ++----------------------------------------------
 fs/jbd/transaction.c  |   12 +++---
 fs/jbd2/commit.c      |    6 +-
 fs/jbd2/journal.c     |   99 ++----------------------------------------------
 fs/jbd2/transaction.c |   18 ++++----
 include/linux/jbd.h   |   18 +++++----
 include/linux/jbd2.h  |   19 +++++----
 8 files changed, 51 insertions(+), 226 deletions(-)

diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index a003d50..a263d82 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -375,7 +375,7 @@ void journal_commit_transaction(journal_t *journal)
 			struct buffer_head *bh = jh2bh(jh);
 
 			jbd_lock_bh_state(bh);
-			jbd_slab_free(jh->b_committed_data, bh->b_size);
+			jbd_free(jh->b_committed_data, bh->b_size);
 			jh->b_committed_data = NULL;
 			jbd_unlock_bh_state(bh);
 		}
@@ -792,14 +792,14 @@ restart_loop:
 		 * Otherwise, we can just throw away the frozen data now.
 		 */
 		if (jh->b_committed_data) {
-			jbd_slab_free(jh->b_committed_data, bh->b_size);
+			jbd_free(jh->b_committed_data, bh->b_size);
 			jh->b_committed_data = NULL;
 			if (jh->b_frozen_data) {
 				jh->b_committed_data = jh->b_frozen_data;
 				jh->b_frozen_data = NULL;
 			}
 		} else if (jh->b_frozen_data) {
-			jbd_slab_free(jh->b_frozen_data, bh->b_size);
+			jbd_free(jh->b_frozen_data, bh->b_size);
 			jh->b_frozen_data = NULL;
 		}
 
diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index 06ab3c1..ae2c25d 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -83,7 +83,6 @@ EXPORT_SYMBOL(journal_force_commit);
 
 static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
 static void __journal_abort_soft (journal_t *journal, int errno);
-static int journal_create_jbd_slab(size_t slab_size);
 
 /*
  * Helper function used to manage commit timeouts
@@ -334,10 +333,10 @@ repeat:
 		char *tmp;
 
 		jbd_unlock_bh_state(bh_in);
-		tmp = jbd_slab_alloc(bh_in->b_size, GFP_NOFS);
+		tmp = jbd_alloc(bh_in->b_size, GFP_NOFS);
 		jbd_lock_bh_state(bh_in);
 		if (jh_in->b_frozen_data) {
-			jbd_slab_free(tmp, bh_in->b_size);
+			jbd_free(tmp, bh_in->b_size);
 			goto repeat;
 		}
 
@@ -654,7 +653,7 @@ static journal_t * journal_init_common (void)
 	journal_t *journal;
 	int err;
 
-	journal = jbd_kmalloc(sizeof(*journal), GFP_KERNEL);
+	journal = kmalloc(sizeof(*journal), GFP_KERNEL|__GFP_NOFAIL);
 	if (!journal)
 		goto fail;
 	memset(journal, 0, sizeof(*journal));
@@ -1095,13 +1094,6 @@ int journal_load(journal_t *journal)
 		}
 	}
 
-	/*
-	 * Create a slab for this blocksize
-	 */
-	err = journal_create_jbd_slab(be32_to_cpu(sb->s_blocksize));
-	if (err)
-		return err;
-
 	/* Let the recovery code check whether it needs to recover any
 	 * data from the journal. */
 	if (journal_recover(journal))
@@ -1615,86 +1607,6 @@ int journal_blocks_per_page(struct inode *inode)
 }
 
 /*
- * Simple support for retrying memory allocations.  Introduced to help to
- * debug different VM deadlock avoidance strategies.
- */
-void * __jbd_kmalloc (const char *where, size_t size, gfp_t flags, int retry)
-{
-	return kmalloc(size, flags | (retry ? __GFP_NOFAIL : 0));
-}
-
-/*
- * jbd slab management: create 1k, 2k, 4k, 8k slabs as needed
- * and allocate frozen and commit buffers from these slabs.
- *
- * Reason for doing this is to avoid, SLAB_DEBUG - since it could
- * cause bh to cross page boundary.
- */
-
-#define JBD_MAX_SLABS 5
-#define JBD_SLAB_INDEX(size)  (size >> 11)
-
-static struct kmem_cache *jbd_slab[JBD_MAX_SLABS];
-static const char *jbd_slab_names[JBD_MAX_SLABS] = {
-	"jbd_1k", "jbd_2k", "jbd_4k", NULL, "jbd_8k"
-};
-
-static void journal_destroy_jbd_slabs(void)
-{
-	int i;
-
-	for (i = 0; i < JBD_MAX_SLABS; i++) {
-		if (jbd_slab[i])
-			kmem_cache_destroy(jbd_slab[i]);
-		jbd_slab[i] = NULL;
-	}
-}
-
-static int journal_create_jbd_slab(size_t slab_size)
-{
-	int i = JBD_SLAB_INDEX(slab_size);
-
-	BUG_ON(i >= JBD_MAX_SLABS);
-
-	/*
-	 * Check if we already have a slab created for this size
-	 */
-	if (jbd_slab[i])
-		return 0;
-
-	/*
-	 * Create a slab and force alignment to be same as slabsize -
-	 * this will make sure that allocations won't cross the page
-	 * boundary.
-	 */
-	jbd_slab[i] = kmem_cache_create(jbd_slab_names[i],
-				slab_size, slab_size, 0, NULL);
-	if (!jbd_slab[i]) {
-		printk(KERN_EMERG "JBD: no memory for jbd_slab cache\n");
-		return -ENOMEM;
-	}
-	return 0;
-}
-
-void * jbd_slab_alloc(size_t size, gfp_t flags)
-{
-	int idx;
-
-	idx = JBD_SLAB_INDEX(size);
-	BUG_ON(jbd_slab[idx] == NULL);
-	return kmem_cache_alloc(jbd_slab[idx], flags | __GFP_NOFAIL);
-}
-
-void jbd_slab_free(void *ptr,  size_t size)
-{
-	int idx;
-
-	idx = JBD_SLAB_INDEX(size);
-	BUG_ON(jbd_slab[idx] == NULL);
-	kmem_cache_free(jbd_slab[idx], ptr);
-}
-
-/*
  * Journal_head storage management
  */
 static struct kmem_cache *journal_head_cache;
@@ -1881,13 +1793,13 @@ static void __journal_remove_journal_head(struct buffer_head *bh)
 				printk(KERN_WARNING "%s: freeing "
 						"b_frozen_data\n",
 						__FUNCTION__);
-				jbd_slab_free(jh->b_frozen_data, bh->b_size);
+				jbd_free(jh->b_frozen_data, bh->b_size);
 			}
 			if (jh->b_committed_data) {
 				printk(KERN_WARNING "%s: freeing "
 						"b_committed_data\n",
 						__FUNCTION__);
-				jbd_slab_free(jh->b_committed_data, bh->b_size);
+				jbd_free(jh->b_committed_data, bh->b_size);
 			}
 			bh->b_private = NULL;
 			jh->b_bh = NULL;	/* debug, really */
@@ -2042,7 +1954,6 @@ static void journal_destroy_caches(void)
 	journal_destroy_revoke_caches();
 	journal_destroy_journal_head_cache();
 	journal_destroy_handle_cache();
-	journal_destroy_jbd_slabs();
 }
 
 static int __init journal_init(void)
diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index 772b653..11d846c 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -96,8 +96,8 @@ static int start_this_handle(journal_t *journal, handle_t *handle)
 
 alloc_transaction:
 	if (!journal->j_running_transaction) {
-		new_transaction = jbd_kmalloc(sizeof(*new_transaction),
-						GFP_NOFS);
+		new_transaction = kmalloc(sizeof(*new_transaction),
+						GFP_NOFS|__GFP_NOFAIL);
 		if (!new_transaction) {
 			ret = -ENOMEM;
 			goto out;
@@ -668,7 +668,7 @@ repeat:
 				JBUFFER_TRACE(jh, "allocate memory for buffer");
 				jbd_unlock_bh_state(bh);
 				frozen_buffer =
-					jbd_slab_alloc(jh2bh(jh)->b_size,
+					jbd_alloc(jh2bh(jh)->b_size,
 							 GFP_NOFS);
 				if (!frozen_buffer) {
 					printk(KERN_EMERG
@@ -728,7 +728,7 @@ done:
 
 out:
 	if (unlikely(frozen_buffer))	/* It's usually NULL */
-		jbd_slab_free(frozen_buffer, bh->b_size);
+		jbd_free(frozen_buffer, bh->b_size);
 
 	JBUFFER_TRACE(jh, "exit");
 	return error;
@@ -881,7 +881,7 @@ int journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
 
 repeat:
 	if (!jh->b_committed_data) {
-		committed_data = jbd_slab_alloc(jh2bh(jh)->b_size, GFP_NOFS);
+		committed_data = jbd_alloc(jh2bh(jh)->b_size, GFP_NOFS);
 		if (!committed_data) {
 			printk(KERN_EMERG "%s: No memory for committed data\n",
 				__FUNCTION__);
@@ -908,7 +908,7 @@ repeat:
 out:
 	journal_put_journal_head(jh);
 	if (unlikely(committed_data))
-		jbd_slab_free(committed_data, bh->b_size);
+		jbd_free(committed_data, bh->b_size);
 	return err;
 }
 
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index c0f59d1..2cac34a 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -384,7 +384,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 			struct buffer_head *bh = jh2bh(jh);
 
 			jbd_lock_bh_state(bh);
-			jbd2_slab_free(jh->b_committed_data, bh->b_size);
+			jbd2_free(jh->b_committed_data, bh->b_size);
 			jh->b_committed_data = NULL;
 			jbd_unlock_bh_state(bh);
 		}
@@ -801,14 +801,14 @@ restart_loop:
 		 * Otherwise, we can just throw away the frozen data now.
 		 */
 		if (jh->b_committed_data) {
-			jbd2_slab_free(jh->b_committed_data, bh->b_size);
+			jbd2_free(jh->b_committed_data, bh->b_size);
 			jh->b_committed_data = NULL;
 			if (jh->b_frozen_data) {
 				jh->b_committed_data = jh->b_frozen_data;
 				jh->b_frozen_data = NULL;
 			}
 		} else if (jh->b_frozen_data) {
-			jbd2_slab_free(jh->b_frozen_data, bh->b_size);
+			jbd2_free(jh->b_frozen_data, bh->b_size);
 			jh->b_frozen_data = NULL;
 		}
 
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index f37324a..4281244 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -84,7 +84,6 @@ EXPORT_SYMBOL(jbd2_journal_force_commit);
 
 static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
 static void __journal_abort_soft (journal_t *journal, int errno);
-static int jbd2_journal_create_jbd_slab(size_t slab_size);
 
 /*
  * Helper function used to manage commit timeouts
@@ -335,10 +334,10 @@ repeat:
 		char *tmp;
 
 		jbd_unlock_bh_state(bh_in);
-		tmp = jbd2_slab_alloc(bh_in->b_size, GFP_NOFS);
+		tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
 		jbd_lock_bh_state(bh_in);
 		if (jh_in->b_frozen_data) {
-			jbd2_slab_free(tmp, bh_in->b_size);
+			jbd2_free(tmp, bh_in->b_size);
 			goto repeat;
 		}
 
@@ -655,7 +654,7 @@ static journal_t * journal_init_common (void)
 	journal_t *journal;
 	int err;
 
-	journal = jbd_kmalloc(sizeof(*journal), GFP_KERNEL);
+	journal = kmalloc(sizeof(*journal), GFP_KERNEL|__GFP_NOFAIL);
 	if (!journal)
 		goto fail;
 	memset(journal, 0, sizeof(*journal));
@@ -1096,13 +1095,6 @@ int jbd2_journal_load(journal_t *journal)
 		}
 	}
 
-	/*
-	 * Create a slab for this blocksize
-	 */
-	err = jbd2_journal_create_jbd_slab(be32_to_cpu(sb->s_blocksize));
-	if (err)
-		return err;
-
 	/* Let the recovery code check whether it needs to recover any
 	 * data from the journal. */
 	if (jbd2_journal_recover(journal))
@@ -1627,86 +1619,6 @@ size_t journal_tag_bytes(journal_t *journal)
 }
 
 /*
- * Simple support for retrying memory allocations.  Introduced to help to
- * debug different VM deadlock avoidance strategies.
- */
-void * __jbd2_kmalloc (const char *where, size_t size, gfp_t flags, int retry)
-{
-	return kmalloc(size, flags | (retry ? __GFP_NOFAIL : 0));
-}
-
-/*
- * jbd slab management: create 1k, 2k, 4k, 8k slabs as needed
- * and allocate frozen and commit buffers from these slabs.
- *
- * Reason for doing this is to avoid, SLAB_DEBUG - since it could
- * cause bh to cross page boundary.
- */
-
-#define JBD_MAX_SLABS 5
-#define JBD_SLAB_INDEX(size)  (size >> 11)
-
-static struct kmem_cache *jbd_slab[JBD_MAX_SLABS];
-static const char *jbd_slab_names[JBD_MAX_SLABS] = {
-	"jbd2_1k", "jbd2_2k", "jbd2_4k", NULL, "jbd2_8k"
-};
-
-static void jbd2_journal_destroy_jbd_slabs(void)
-{
-	int i;
-
-	for (i = 0; i < JBD_MAX_SLABS; i++) {
-		if (jbd_slab[i])
-			kmem_cache_destroy(jbd_slab[i]);
-		jbd_slab[i] = NULL;
-	}
-}
-
-static int jbd2_journal_create_jbd_slab(size_t slab_size)
-{
-	int i = JBD_SLAB_INDEX(slab_size);
-
-	BUG_ON(i >= JBD_MAX_SLABS);
-
-	/*
-	 * Check if we already have a slab created for this size
-	 */
-	if (jbd_slab[i])
-		return 0;
-
-	/*
-	 * Create a slab and force alignment to be same as slabsize -
-	 * this will make sure that allocations won't cross the page
-	 * boundary.
-	 */
-	jbd_slab[i] = kmem_cache_create(jbd_slab_names[i],
-				slab_size, slab_size, 0, NULL);
-	if (!jbd_slab[i]) {
-		printk(KERN_EMERG "JBD: no memory for jbd_slab cache\n");
-		return -ENOMEM;
-	}
-	return 0;
-}
-
-void * jbd2_slab_alloc(size_t size, gfp_t flags)
-{
-	int idx;
-
-	idx = JBD_SLAB_INDEX(size);
-	BUG_ON(jbd_slab[idx] == NULL);
-	return kmem_cache_alloc(jbd_slab[idx], flags | __GFP_NOFAIL);
-}
-
-void jbd2_slab_free(void *ptr,  size_t size)
-{
-	int idx;
-
-	idx = JBD_SLAB_INDEX(size);
-	BUG_ON(jbd_slab[idx] == NULL);
-	kmem_cache_free(jbd_slab[idx], ptr);
-}
-
-/*
  * Journal_head storage management
  */
 static struct kmem_cache *jbd2_journal_head_cache;
@@ -1893,13 +1805,13 @@ static void __journal_remove_journal_head(struct buffer_head *bh)
 				printk(KERN_WARNING "%s: freeing "
 						"b_frozen_data\n",
 						__FUNCTION__);
-				jbd2_slab_free(jh->b_frozen_data, bh->b_size);
+				jbd2_free(jh->b_frozen_data, bh->b_size);
 			}
 			if (jh->b_committed_data) {
 				printk(KERN_WARNING "%s: freeing "
 						"b_committed_data\n",
 						__FUNCTION__);
-				jbd2_slab_free(jh->b_committed_data, bh->b_size);
+				jbd2_free(jh->b_committed_data, bh->b_size);
 			}
 			bh->b_private = NULL;
 			jh->b_bh = NULL;	/* debug, really */
@@ -2040,7 +1952,6 @@ static void jbd2_journal_destroy_caches(void)
 	jbd2_journal_destroy_revoke_caches();
 	jbd2_journal_destroy_jbd2_journal_head_cache();
 	jbd2_journal_destroy_handle_cache();
-	jbd2_journal_destroy_jbd_slabs();
 }
 
 static int __init journal_init(void)
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 7946ff4..a5fb70f 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -96,8 +96,8 @@ static int start_this_handle(journal_t *journal, handle_t *handle)
 
 alloc_transaction:
 	if (!journal->j_running_transaction) {
-		new_transaction = jbd_kmalloc(sizeof(*new_transaction),
-						GFP_NOFS);
+		new_transaction = kmalloc(sizeof(*new_transaction),
+						GFP_NOFS|__GFP_NOFAIL);
 		if (!new_transaction) {
 			ret = -ENOMEM;
 			goto out;
@@ -236,7 +236,7 @@ out:
 /* Allocate a new handle.  This should probably be in a slab... */
 static handle_t *new_handle(int nblocks)
 {
-	handle_t *handle = jbd_alloc_handle(GFP_NOFS);
+	handle_t *handle = jbd2_alloc_handle(GFP_NOFS);
 	if (!handle)
 		return NULL;
 	memset(handle, 0, sizeof(*handle));
@@ -282,7 +282,7 @@ handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
 
 	err = start_this_handle(journal, handle);
 	if (err < 0) {
-		jbd_free_handle(handle);
+		jbd2_free_handle(handle);
 		current->journal_info = NULL;
 		handle = ERR_PTR(err);
 	}
@@ -668,7 +668,7 @@ repeat:
 				JBUFFER_TRACE(jh, "allocate memory for buffer");
 				jbd_unlock_bh_state(bh);
 				frozen_buffer =
-					jbd2_slab_alloc(jh2bh(jh)->b_size,
+					jbd2_alloc(jh2bh(jh)->b_size,
 							 GFP_NOFS);
 				if (!frozen_buffer) {
 					printk(KERN_EMERG
@@ -728,7 +728,7 @@ done:
 
 out:
 	if (unlikely(frozen_buffer))	/* It's usually NULL */
-		jbd2_slab_free(frozen_buffer, bh->b_size);
+		jbd2_free(frozen_buffer, bh->b_size);
 
 	JBUFFER_TRACE(jh, "exit");
 	return error;
@@ -881,7 +881,7 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
 
 repeat:
 	if (!jh->b_committed_data) {
-		committed_data = jbd2_slab_alloc(jh2bh(jh)->b_size, GFP_NOFS);
+		committed_data = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS);
 		if (!committed_data) {
 			printk(KERN_EMERG "%s: No memory for committed data\n",
 				__FUNCTION__);
@@ -908,7 +908,7 @@ repeat:
 out:
 	jbd2_journal_put_journal_head(jh);
 	if (unlikely(committed_data))
-		jbd2_slab_free(committed_data, bh->b_size);
+		jbd2_free(committed_data, bh->b_size);
 	return err;
 }
 
@@ -1411,7 +1411,7 @@ int jbd2_journal_stop(handle_t *handle)
 		spin_unlock(&journal->j_state_lock);
 	}
 
-	jbd_free_handle(handle);
+	jbd2_free_handle(handle);
 	return err;
 }
 
diff --git a/include/linux/jbd.h b/include/linux/jbd.h
index 4527375..26216c1 100644
--- a/include/linux/jbd.h
+++ b/include/linux/jbd.h
@@ -71,14 +71,16 @@ extern int journal_enable_debug;
 #define jbd_debug(f, a...)	/**/
 #endif
 
-extern void * __jbd_kmalloc (const char *where, size_t size, gfp_t flags, int retry);
-extern void * jbd_slab_alloc(size_t size, gfp_t flags);
-extern void jbd_slab_free(void *ptr, size_t size);
-
-#define jbd_kmalloc(size, flags) \
-	__jbd_kmalloc(__FUNCTION__, (size), (flags), journal_oom_retry)
-#define jbd_rep_kmalloc(size, flags) \
-	__jbd_kmalloc(__FUNCTION__, (size), (flags), 1)
+
+static inline void *jbd_alloc(size_t size, gfp_t flags)
+{
+	return (void *)__get_free_pages(flags, get_order(size));
+}
+
+static inline void jbd_free(void *ptr, size_t size)
+{
+	free_pages((unsigned long)ptr, get_order(size));
+};
 
 #define JFS_MIN_JOURNAL_BLOCKS 1024
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 260d6d7..5f8b876 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -71,14 +71,15 @@ extern u8 jbd2_journal_enable_debug;
 #define jbd_debug(f, a...)	/**/
 #endif
 
-extern void * __jbd2_kmalloc (const char *where, size_t size, gfp_t flags, int retry);
-extern void * jbd2_slab_alloc(size_t size, gfp_t flags);
-extern void jbd2_slab_free(void *ptr, size_t size);
+static inline void *jbd2_alloc(size_t size, gfp_t flags)
+{
+	return (void *)__get_free_pages(flags, get_order(size));
+}
 
-#define jbd_kmalloc(size, flags) \
-	__jbd2_kmalloc(__FUNCTION__, (size), (flags), journal_oom_retry)
-#define jbd_rep_kmalloc(size, flags) \
-	__jbd2_kmalloc(__FUNCTION__, (size), (flags), 1)
+static inline void jbd2_free(void *ptr, size_t size)
+{
+	free_pages((unsigned long)ptr, get_order(size));
+};
 
 #define JBD2_MIN_JOURNAL_BLOCKS 1024
 
@@ -959,12 +960,12 @@ void jbd2_journal_put_journal_head(struct journal_head *jh);
  */
 extern struct kmem_cache *jbd2_handle_cache;
 
-static inline handle_t *jbd_alloc_handle(gfp_t gfp_flags)
+static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags)
 {
 	return kmem_cache_alloc(jbd2_handle_cache, gfp_flags);
 }
 
-static inline void jbd_free_handle(handle_t *handle)
+static inline void jbd2_free_handle(handle_t *handle)
 {
 	kmem_cache_free(jbd2_handle_cache, handle);
 }
-- 
1.5.3.2.81.g17ed

[PATCH] jbd/jbd2: Journal initialization doesn't need __GFP_NOFAIL

[Theodore Ts'o]

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

Signed-off-by: Mingming Cao <cmm@us.ibm.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/jbd/journal.c  |    2 +-
 fs/jbd2/journal.c |    2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index ae2c25d..8d6d475 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -653,7 +653,7 @@ static journal_t * journal_init_common (void)
 	journal_t *journal;
 	int err;
 
-	journal = kmalloc(sizeof(*journal), GFP_KERNEL|__GFP_NOFAIL);
+	journal = kmalloc(sizeof(*journal), GFP_KERNEL);
 	if (!journal)
 		goto fail;
 	memset(journal, 0, sizeof(*journal));
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 4281244..0e329a3 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -654,7 +654,7 @@ static journal_t * journal_init_common (void)
 	journal_t *journal;
 	int err;
 
-	journal = kmalloc(sizeof(*journal), GFP_KERNEL|__GFP_NOFAIL);
+	journal = kmalloc(sizeof(*journal), GFP_KERNEL);
 	if (!journal)
 		goto fail;
 	memset(journal, 0, sizeof(*journal));
-- 
1.5.3.2.81.g17ed

[PATCH] JBD2/Ext4: Convert kmalloc to kzalloc in jbd2/ext4

[Theodore Ts'o]

From: Mingming Cao <cmm@us.ibm.com>

Convert kmalloc to kzalloc() and get rid of the memset().

Signed-off-by: Mingming Cao <cmm@us.ibm.com>
---
 fs/ext4/xattr.c       |    3 +--
 fs/jbd2/journal.c     |    3 +--
 fs/jbd2/transaction.c |    3 +--
 3 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index b10d68f..12c7d65 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -750,12 +750,11 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 		}
 	} else {
 		/* Allocate a buffer where we construct the new block. */
-		s->base = kmalloc(sb->s_blocksize, GFP_KERNEL);
+		s->base = kzalloc(sb->s_blocksize, GFP_KERNEL);
 		/* assert(header == s->base) */
 		error = -ENOMEM;
 		if (s->base == NULL)
 			goto cleanup;
-		memset(s->base, 0, sb->s_blocksize);
 		header(s->base)->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
 		header(s->base)->h_blocks = cpu_to_le32(1);
 		header(s->base)->h_refcount = cpu_to_le32(1);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 0e329a3..f12c65b 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -654,10 +654,9 @@ static journal_t * journal_init_common (void)
 	journal_t *journal;
 	int err;
 
-	journal = kmalloc(sizeof(*journal), GFP_KERNEL);
+	journal = kzalloc(sizeof(*journal), GFP_KERNEL|__GFP_NOFAIL);
 	if (!journal)
 		goto fail;
-	memset(journal, 0, sizeof(*journal));
 
 	init_waitqueue_head(&journal->j_wait_transaction_locked);
 	init_waitqueue_head(&journal->j_wait_logspace);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index a5fb70f..b1fcf2b 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -96,13 +96,12 @@ static int start_this_handle(journal_t *journal, handle_t *handle)
 
 alloc_transaction:
 	if (!journal->j_running_transaction) {
-		new_transaction = kmalloc(sizeof(*new_transaction),
+		new_transaction = kzalloc(sizeof(*new_transaction),
 						GFP_NOFS|__GFP_NOFAIL);
 		if (!new_transaction) {
 			ret = -ENOMEM;
 			goto out;
 		}
-		memset(new_transaction, 0, sizeof(*new_transaction));
 	}
 
 	jbd_debug(3, "New handle %p going live.\n", handle);
-- 
1.5.3.2.81.g17ed

[PATCH] jbd2: fix commit code to properly abort journal

[Theodore Ts'o]

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

[PATCH] JBD2: debug code cleanup.

[Theodore Ts'o]

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

[PATCH] Once ext4 will not implement fragment, it is believed it will never be

[Theodore Ts'o]

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 EXT4_FRAGMENTS
-	raw_inode->i_faddr = cpu_to_le32(ei->i_faddr);
-	raw_inode->i_frag = ei->i_frag_no;
-	raw_inode->i_fsize = ei->i_frag_size;
-#endif
 	if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
 	    cpu_to_le32(EXT4_OS_HURD))
 		raw_inode->i_file_acl_high =
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 42cbdb5..420d39d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1655,14 +1655,6 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
 		if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE)
 			sb->s_time_gran = 1 << (EXT4_EPOCH_BITS - 2);
 	}
-	sbi->s_frag_size = EXT4_MIN_FRAG_SIZE <<
-				   le32_to_cpu(es->s_log_frag_size);
-	if (blocksize != sbi->s_frag_size) {
-		printk(KERN_ERR
-		       "EXT4-fs: fragsize %lu != blocksize %u (unsupported)\n",
-		       sbi->s_frag_size, blocksize);
-		goto failed_mount;
-	}
 	sbi->s_desc_size = le16_to_cpu(es->s_desc_size);
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) {
 		if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT ||
@@ -1676,7 +1668,6 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
 	} else
 		sbi->s_desc_size = EXT4_MIN_DESC_SIZE;
 	sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
-	sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group);
 	sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
 	if (EXT4_INODE_SIZE(sb) == 0)
 		goto cantfind_ext4;
@@ -1700,12 +1691,6 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
 			sbi->s_blocks_per_group);
 		goto failed_mount;
 	}
-	if (sbi->s_frags_per_group > blocksize * 8) {
-		printk (KERN_ERR
-			"EXT4-fs: #fragments per group too big: %lu\n",
-			sbi->s_frags_per_group);
-		goto failed_mount;
-	}
 	if (sbi->s_inodes_per_group > blocksize * 8) {
 		printk (KERN_ERR
 			"EXT4-fs: #inodes per group too big: %lu\n",
diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h
index cdee7aa..3baeb99 100644
--- a/include/linux/ext4_fs.h
+++ b/include/linux/ext4_fs.h
@@ -105,20 +105,6 @@
 #define EXT4_BLOCK_ALIGN(size, blkbits)		ALIGN((size), (1 << (blkbits)))
 
 /*
- * Macro-instructions used to manage fragments
- */
-#define EXT4_MIN_FRAG_SIZE		1024
-#define	EXT4_MAX_FRAG_SIZE		4096
-#define EXT4_MIN_FRAG_LOG_SIZE		  10
-#ifdef __KERNEL__
-# define EXT4_FRAG_SIZE(s)		(EXT4_SB(s)->s_frag_size)
-# define EXT4_FRAGS_PER_BLOCK(s)	(EXT4_SB(s)->s_frags_per_block)
-#else
-# define EXT4_FRAG_SIZE(s)		(EXT4_MIN_FRAG_SIZE << (s)->s_log_frag_size)
-# define EXT4_FRAGS_PER_BLOCK(s)	(EXT4_BLOCK_SIZE(s) / EXT4_FRAG_SIZE(s))
-#endif
-
-/*
  * Structure of a blocks group descriptor
  */
 struct ext4_group_desc
@@ -311,27 +297,24 @@ struct ext4_inode {
 	__le32	i_generation;	/* File version (for NFS) */
 	__le32	i_file_acl;	/* File ACL */
 	__le32	i_dir_acl;	/* Directory ACL */
-	__le32	i_faddr;	/* Fragment address */
+	__le32	i_obso_faddr;	/* Obsoleted fragment address */
 	union {
 		struct {
-			__u8	l_i_frag;	/* Fragment number */
-			__u8	l_i_fsize;	/* Fragment size */
+			__le16	l_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
 			__le16	l_i_file_acl_high;
 			__le16	l_i_uid_high;	/* these 2 fields */
 			__le16	l_i_gid_high;	/* were reserved2[0] */
 			__u32	l_i_reserved2;
 		} linux2;
 		struct {
-			__u8	h_i_frag;	/* Fragment number */
-			__u8	h_i_fsize;	/* Fragment size */
+			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
 			__u16	h_i_mode_high;
 			__u16	h_i_uid_high;
 			__u16	h_i_gid_high;
 			__u32	h_i_author;
 		} hurd2;
 		struct {
-			__u8	m_i_frag;	/* Fragment number */
-			__u8	m_i_fsize;	/* Fragment size */
+			__le16	h_i_reserved1;	/* Obsoleted fragment number/size which are removed in ext4 */
 			__le16	m_i_file_acl_high;
 			__u32	m_i_reserved2[2];
 		} masix2;
@@ -419,8 +402,6 @@ do {									       \
 
 #if defined(__KERNEL__) || defined(__linux__)
 #define i_reserved1	osd1.linux1.l_i_reserved1
-#define i_frag		osd2.linux2.l_i_frag
-#define i_fsize		osd2.linux2.l_i_fsize
 #define i_file_acl_high	osd2.linux2.l_i_file_acl_high
 #define i_uid_low	i_uid
 #define i_gid_low	i_gid
@@ -431,8 +412,6 @@ do {									       \
 #elif defined(__GNU__)
 
 #define i_translator	osd1.hurd1.h_i_translator
-#define i_frag		osd2.hurd2.h_i_frag;
-#define i_fsize		osd2.hurd2.h_i_fsize;
 #define i_uid_high	osd2.hurd2.h_i_uid_high
 #define i_gid_high	osd2.hurd2.h_i_gid_high
 #define i_author	osd2.hurd2.h_i_author
@@ -440,8 +419,6 @@ do {									       \
 #elif defined(__masix__)
 
 #define i_reserved1	osd1.masix1.m_i_reserved1
-#define i_frag		osd2.masix2.m_i_frag
-#define i_fsize		osd2.masix2.m_i_fsize
 #define i_file_acl_high	osd2.masix2.m_i_file_acl_high
 #define i_reserved2	osd2.masix2.m_i_reserved2
 
@@ -528,9 +505,9 @@ struct ext4_super_block {
 /*10*/	__le32	s_free_inodes_count;	/* Free inodes count */
 	__le32	s_first_data_block;	/* First Data Block */
 	__le32	s_log_block_size;	/* Block size */
-	__le32	s_log_frag_size;	/* Fragment size */
+	__le32	s_obso_log_frag_size;	/* Obsoleted fragment size */
 /*20*/	__le32	s_blocks_per_group;	/* # Blocks per group */
-	__le32	s_frags_per_group;	/* # Fragments per group */
+	__le32	s_obso_frags_per_group;	/* Obsoleted fragments per group */
 	__le32	s_inodes_per_group;	/* # Inodes per group */
 	__le32	s_mtime;		/* Mount time */
 /*30*/	__le32	s_wtime;		/* Write time */
diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h
index 1a511e9..86ddfe2 100644
--- a/include/linux/ext4_fs_i.h
+++ b/include/linux/ext4_fs_i.h
@@ -78,11 +78,6 @@ struct ext4_ext_cache {
 struct ext4_inode_info {
 	__le32	i_data[15];	/* unconverted */
 	__u32	i_flags;
-#ifdef EXT4_FRAGMENTS
-	__u32	i_faddr;
-	__u8	i_frag_no;
-	__u8	i_frag_size;
-#endif
 	ext4_fsblk_t	i_file_acl;
 	__u32	i_dir_acl;
 	__u32	i_dtime;
diff --git a/include/linux/ext4_fs_sb.h b/include/linux/ext4_fs_sb.h
index 1b2ffee..a978fba 100644
--- a/include/linux/ext4_fs_sb.h
+++ b/include/linux/ext4_fs_sb.h
@@ -28,11 +28,8 @@
  * third extended-fs super-block data in memory
  */
 struct ext4_sb_info {
-	unsigned long s_frag_size;	/* Size of a fragment in bytes */
 	unsigned long s_desc_size;	/* Size of a group descriptor in bytes */
-	unsigned long s_frags_per_block;/* Number of fragments per block */
 	unsigned long s_inodes_per_block;/* Number of inodes per block */
-	unsigned long s_frags_per_group;/* Number of fragments in a group */
 	unsigned long s_blocks_per_group;/* Number of blocks in a group */
 	unsigned long s_inodes_per_group;/* Number of inodes in a group */
 	unsigned long s_itb_per_group;	/* Number of inode table blocks per group */
-- 
1.5.3.2.81.g17ed

[PATCH] ext4: remove #ifdef CONFIG_EXT4_INDEX

[Theodore Ts'o]

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 dx_get_block (struct dx_entry *entry);
 static void dx_set_block (struct dx_entry *entry, unsigned value);
 static inline unsigned dx_get_hash (struct dx_entry *entry);
@@ -766,8 +765,6 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, u32 block)
 	dx_set_block(new, block);
 	dx_set_count(entries, count + 1);
 }
-#endif
-
 
 static void ext4_update_dx_flag(struct inode *inode)
 {
@@ -869,7 +866,6 @@ static struct buffer_head * ext4_find_entry (struct dentry *dentry,
 	name = dentry->d_name.name;
 	if (namelen > EXT4_NAME_LEN)
 		return NULL;
-#ifdef CONFIG_EXT4_INDEX
 	if (is_dx(dir)) {
 		bh = ext4_dx_find_entry(dentry, res_dir, &err);
 		/*
@@ -881,7 +877,6 @@ static struct buffer_head * ext4_find_entry (struct dentry *dentry,
 			return bh;
 		dxtrace(printk("ext4_find_entry: dx failed, falling back\n"));
 	}
-#endif
 	nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
 	start = EXT4_I(dir)->i_dir_start_lookup;
 	if (start >= nblocks)
@@ -957,7 +952,6 @@ cleanup_and_exit:
 	return ret;
 }
 
-#ifdef CONFIG_EXT4_INDEX
 static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
 		       struct ext4_dir_entry_2 **res_dir, int *err)
 {
@@ -1025,7 +1019,6 @@ errout:
 	dx_release (frames);
 	return NULL;
 }
-#endif
 
 static struct dentry *ext4_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
 {
@@ -1121,7 +1114,6 @@ static inline void ext4_set_de_type(struct super_block *sb,
 		de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
 }
 
-#ifdef CONFIG_EXT4_INDEX
 /*
  * Move count entries from end of map between two memory locations.
  * Returns pointer to last entry moved.
@@ -1266,8 +1258,6 @@ errout:
 	*error = err;
 	return NULL;
 }
-#endif
-
 
 /*
  * Add a new entry into a directory (leaf) block.  If de is non-NULL,
@@ -1364,7 +1354,6 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
 	return 0;
 }
 
-#ifdef CONFIG_EXT4_INDEX
 /*
  * This converts a one block unindexed directory to a 3 block indexed
  * directory, and adds the dentry to the indexed directory.
@@ -1443,7 +1432,6 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 
 	return add_dirent_to_buf(handle, dentry, inode, de, bh);
 }
-#endif
 
 /*
  *	ext4_add_entry()
@@ -1464,9 +1452,7 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry,
 	struct ext4_dir_entry_2 *de;
 	struct super_block * sb;
 	int	retval;
-#ifdef CONFIG_EXT4_INDEX
 	int	dx_fallback=0;
-#endif
 	unsigned blocksize;
 	u32 block, blocks;
 
@@ -1474,7 +1460,6 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry,
 	blocksize = sb->s_blocksize;
 	if (!dentry->d_name.len)
 		return -EINVAL;
-#ifdef CONFIG_EXT4_INDEX
 	if (is_dx(dir)) {
 		retval = ext4_dx_add_entry(handle, dentry, inode);
 		if (!retval || (retval != ERR_BAD_DX_DIR))
@@ -1483,7 +1468,6 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry,
 		dx_fallback++;
 		ext4_mark_inode_dirty(handle, dir);
 	}
-#endif
 	blocks = dir->i_size >> sb->s_blocksize_bits;
 	for (block = 0, offset = 0; block < blocks; block++) {
 		bh = ext4_bread(handle, dir, block, 0, &retval);
@@ -1493,11 +1477,9 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry,
 		if (retval != -ENOSPC)
 			return retval;
 
-#ifdef CONFIG_EXT4_INDEX
 		if (blocks == 1 && !dx_fallback &&
 		    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX))
 			return make_indexed_dir(handle, dentry, inode, bh);
-#endif
 		brelse(bh);
 	}
 	bh = ext4_append(handle, dir, &block, &retval);
@@ -1509,7 +1491,6 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry,
 	return add_dirent_to_buf(handle, dentry, inode, de, bh);
 }
 
-#ifdef CONFIG_EXT4_INDEX
 /*
  * Returns 0 for success, or a negative error value
  */
@@ -1644,7 +1625,6 @@ cleanup:
 	dx_release(frames);
 	return err;
 }
-#endif
 
 /*
  * ext4_delete_entry deletes a directory entry by merging it with the
diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h
index 3baeb99..151738a 100644
--- a/include/linux/ext4_fs.h
+++ b/include/linux/ext4_fs.h
@@ -36,10 +36,6 @@
 /*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */
 #define EXT4_MAX_RESERVE_BLOCKS		1027
 #define EXT4_RESERVE_WINDOW_NOT_ALLOCATED 0
-/*
- * Always enable hashed directories
- */
-#define CONFIG_EXT4_INDEX
 
 /*
  * Debug code
@@ -766,17 +762,11 @@ struct ext4_dir_entry_2 {
  * (c) Daniel Phillips, 2001
  */
 
-#ifdef CONFIG_EXT4_INDEX
-  #define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \
-					      EXT4_FEATURE_COMPAT_DIR_INDEX) && \
+#define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \
+				      EXT4_FEATURE_COMPAT_DIR_INDEX) && \
 		      (EXT4_I(dir)->i_flags & EXT4_INDEX_FL))
 #define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX)
 #define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)
-#else
-  #define is_dx(dir) 0
-#define EXT4_DIR_LINK_MAX(dir) ((dir)->i_nlink >= EXT4_LINK_MAX)
-#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2)
-#endif
 
 /* Legal values for the dx_root hash_version field: */
 
-- 
1.5.3.2.81.g17ed