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: (49 commits)
  ext4: Avoid corrupting the uninitialized bit in the extent during truncate
  ext4: Don't treat a truncation of a zero-length file as replace-via-truncate
  ext4: fix dx_map_entry to support 256k directory blocks
  ext4: truncate the file properly if we fail to copy data from userspace
  ext4: Avoid leaking blocks after a block allocation failure
  ext4: Change all super.c messages to print the device
  ext4: Get rid of EXTEND_DISKSIZE flag of ext4_get_blocks_handle()
  ext4: super.c whitespace cleanup
  jbd2: Fix minor typos in comments in fs/jbd2/journal.c
  ext4: Clean up calls to ext4_get_group_desc()
  ext4: remove unused function __ext4_write_dirty_metadata
  ext2: Fix memory leak in ext2_fill_super() in case of a failed mount
  ext3: Fix memory leak in ext3_fill_super() in case of a failed mount
  ext4: Fix memory leak in ext4_fill_super() in case of a failed mount
  ext4: down i_data_sem only for read when walking tree for fiemap
  ext4: Add a comprehensive block validity check to ext4_get_blocks()
  ext4: Clean up ext4_get_blocks() so it does not depend on bh_result->b_state
  ext4: Merge ext4_da_get_block_write() into mpage_da_map_blocks()
  ext4: Add BUG_ON debugging checks to noalloc_get_block_write()
  ext4: Add documentation to the ext4_*get_block* functions
  ...

fs/buffer.c

@@ -2935,6 +2935,8 @@ int submit_bh(int rw, struct buffer_head * bh)
 	BUG_ON(!buffer_locked(bh));
 	BUG_ON(!buffer_mapped(bh));
 	BUG_ON(!bh->b_end_io);
+	BUG_ON(buffer_delay(bh));
+	BUG_ON(buffer_unwritten(bh));
 
 	/*
 	 * Mask in barrier bit for a write (could be either a WRITE or a

fs/ext2/super.c

@@ -1093,6 +1093,7 @@ failed_mount:
 	brelse(bh);
 failed_sbi:
 	sb->s_fs_info = NULL;
+	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
 	return ret;
 }

fs/ext3/super.c

@@ -2021,6 +2021,7 @@ failed_mount:
 	brelse(bh);
 out_fail:
 	sb->s_fs_info = NULL;
+	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
 	lock_kernel();
 	return ret;

fs/ext4/Makefile

@@ -5,8 +5,8 @@
 obj-$(CONFIG_EXT4_FS) += ext4.o
 
 ext4-y	:= balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \
-		   ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
-		   ext4_jbd2.o migrate.o mballoc.o
+		ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
+		ext4_jbd2.o migrate.o mballoc.o block_validity.o
 
 ext4-$(CONFIG_EXT4_FS_XATTR)		+= xattr.o xattr_user.o xattr_trusted.o
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o

fs/ext4/balloc.c

@@ -19,7 +19,6 @@
 #include <linux/buffer_head.h>
 #include "ext4.h"
 #include "ext4_jbd2.h"
-#include "group.h"
 #include "mballoc.h"
 
 /*
@@ -88,6 +87,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 		 ext4_group_t block_group, struct ext4_group_desc *gdp)
 {
 	int bit, bit_max;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	unsigned free_blocks, group_blocks;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
@@ -123,7 +123,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 		bit_max += ext4_bg_num_gdb(sb, block_group);
 	}
 
-	if (block_group == sbi->s_groups_count - 1) {
+	if (block_group == ngroups - 1) {
 		/*
 		 * Even though mke2fs always initialize first and last group
 		 * if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need
@@ -131,7 +131,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 		 */
 		group_blocks = ext4_blocks_count(sbi->s_es) -
 			le32_to_cpu(sbi->s_es->s_first_data_block) -
-			(EXT4_BLOCKS_PER_GROUP(sb) * (sbi->s_groups_count - 1));
+			(EXT4_BLOCKS_PER_GROUP(sb) * (ngroups - 1));
 	} else {
 		group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
 	}
@@ -205,18 +205,18 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
 {
 	unsigned int group_desc;
 	unsigned int offset;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	struct ext4_group_desc *desc;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-	if (block_group >= sbi->s_groups_count) {
+	if (block_group >= ngroups) {
 		ext4_error(sb, "ext4_get_group_desc",
 			   "block_group >= groups_count - "
 			   "block_group = %u, groups_count = %u",
-			   block_group, sbi->s_groups_count);
+			   block_group, ngroups);
 
 		return NULL;
 	}
-	smp_rmb();
 
 	group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
 	offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
@@ -326,16 +326,16 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 		unlock_buffer(bh);
 		return bh;
 	}
-	spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
+	ext4_lock_group(sb, block_group);
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 		ext4_init_block_bitmap(sb, bh, block_group, desc);
 		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
-		spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
 		return bh;
 	}
-	spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+	ext4_unlock_group(sb, block_group);
 	if (buffer_uptodate(bh)) {
 		/*
 		 * if not uninit if bh is uptodate,
@@ -451,7 +451,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
 	down_write(&grp->alloc_sem);
 	for (i = 0, blocks_freed = 0; i < count; i++) {
 		BUFFER_TRACE(bitmap_bh, "clear bit");
-		if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
+		if (!ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
 						bit + i, bitmap_bh->b_data)) {
 			ext4_error(sb, __func__,
 				   "bit already cleared for block %llu",
@@ -461,11 +461,11 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
 			blocks_freed++;
 		}
 	}
-	spin_lock(sb_bgl_lock(sbi, block_group));
+	ext4_lock_group(sb, block_group);
 	blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
 	ext4_free_blks_set(sb, desc, blk_free_count);
 	desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
-	spin_unlock(sb_bgl_lock(sbi, block_group));
+	ext4_unlock_group(sb, block_group);
 	percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed);
 
 	if (sbi->s_log_groups_per_flex) {
@@ -665,7 +665,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 	ext4_fsblk_t desc_count;
 	struct ext4_group_desc *gdp;
 	ext4_group_t i;
-	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 #ifdef EXT4FS_DEBUG
 	struct ext4_super_block *es;
 	ext4_fsblk_t bitmap_count;
@@ -677,7 +677,6 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 	bitmap_count = 0;
 	gdp = NULL;
 
-	smp_rmb();
 	for (i = 0; i < ngroups; i++) {
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
@@ -700,7 +699,6 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 	return bitmap_count;
 #else
 	desc_count = 0;
-	smp_rmb();
 	for (i = 0; i < ngroups; i++) {
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)

fs/ext4/block_validity.c

@@ -0,0 +1,244 @@
+/*
+ *  linux/fs/ext4/block_validity.c
+ *
+ * Copyright (C) 2009
+ * Theodore Ts'o (tytso@mit.edu)
+ *
+ * Track which blocks in the filesystem are metadata blocks that
+ * should never be used as data blocks by files or directories.
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/pagemap.h>
+#include <linux/version.h>
+#include <linux/blkdev.h>
+#include <linux/mutex.h>
+#include "ext4.h"
+
+struct ext4_system_zone {
+	struct rb_node	node;
+	ext4_fsblk_t	start_blk;
+	unsigned int	count;
+};
+
+static struct kmem_cache *ext4_system_zone_cachep;
+
+int __init init_ext4_system_zone(void)
+{
+	ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone,
+					     SLAB_RECLAIM_ACCOUNT);
+	if (ext4_system_zone_cachep == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+void exit_ext4_system_zone(void)
+{
+	kmem_cache_destroy(ext4_system_zone_cachep);
+}
+
+static inline int can_merge(struct ext4_system_zone *entry1,
+		     struct ext4_system_zone *entry2)
+{
+	if ((entry1->start_blk + entry1->count) == entry2->start_blk)
+		return 1;
+	return 0;
+}
+
+/*
+ * Mark a range of blocks as belonging to the "system zone" --- that
+ * is, filesystem metadata blocks which should never be used by
+ * inodes.
+ */
+static int add_system_zone(struct ext4_sb_info *sbi,
+			   ext4_fsblk_t start_blk,
+			   unsigned int count)
+{
+	struct ext4_system_zone *new_entry = NULL, *entry;
+	struct rb_node **n = &sbi->system_blks.rb_node, *node;
+	struct rb_node *parent = NULL, *new_node = NULL;
+
+	while (*n) {
+		parent = *n;
+		entry = rb_entry(parent, struct ext4_system_zone, node);
+		if (start_blk < entry->start_blk)
+			n = &(*n)->rb_left;
+		else if (start_blk >= (entry->start_blk + entry->count))
+			n = &(*n)->rb_right;
+		else {
+			if (start_blk + count > (entry->start_blk + 
+						 entry->count))
+				entry->count = (start_blk + count - 
+						entry->start_blk);
+			new_node = *n;
+			new_entry = rb_entry(new_node, struct ext4_system_zone,
+					     node);
+			break;
+		}
+	}
+
+	if (!new_entry) {
+		new_entry = kmem_cache_alloc(ext4_system_zone_cachep,
+					     GFP_KERNEL);
+		if (!new_entry)
+			return -ENOMEM;
+		new_entry->start_blk = start_blk;
+		new_entry->count = count;
+		new_node = &new_entry->node;
+
+		rb_link_node(new_node, parent, n);
+		rb_insert_color(new_node, &sbi->system_blks);
+	}
+
+	/* Can we merge to the left? */
+	node = rb_prev(new_node);
+	if (node) {
+		entry = rb_entry(node, struct ext4_system_zone, node);
+		if (can_merge(entry, new_entry)) {
+			new_entry->start_blk = entry->start_blk;
+			new_entry->count += entry->count;
+			rb_erase(node, &sbi->system_blks);
+			kmem_cache_free(ext4_system_zone_cachep, entry);
+		}
+	}
+
+	/* Can we merge to the right? */
+	node = rb_next(new_node);
+	if (node) {
+		entry = rb_entry(node, struct ext4_system_zone, node);
+		if (can_merge(new_entry, entry)) {
+			new_entry->count += entry->count;
+			rb_erase(node, &sbi->system_blks);
+			kmem_cache_free(ext4_system_zone_cachep, entry);
+		}
+	}
+	return 0;
+}
+
+static void debug_print_tree(struct ext4_sb_info *sbi)
+{
+	struct rb_node *node;
+	struct ext4_system_zone *entry;
+	int first = 1;
+
+	printk(KERN_INFO "System zones: ");
+	node = rb_first(&sbi->system_blks);
+	while (node) {
+		entry = rb_entry(node, struct ext4_system_zone, node);
+		printk("%s%llu-%llu", first ? "" : ", ",
+		       entry->start_blk, entry->start_blk + entry->count - 1);
+		first = 0;
+		node = rb_next(node);
+	}
+	printk("\n");
+}
+
+int ext4_setup_system_zone(struct super_block *sb)
+{
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_desc *gdp;
+	ext4_group_t i;
+	int flex_size = ext4_flex_bg_size(sbi);
+	int ret;
+
+	if (!test_opt(sb, BLOCK_VALIDITY)) {
+		if (EXT4_SB(sb)->system_blks.rb_node)
+			ext4_release_system_zone(sb);
+		return 0;
+	}
+	if (EXT4_SB(sb)->system_blks.rb_node)
+		return 0;
+
+	for (i=0; i < ngroups; i++) {
+		if (ext4_bg_has_super(sb, i) &&
+		    ((i < 5) || ((i % flex_size) == 0)))
+			add_system_zone(sbi, ext4_group_first_block_no(sb, i),
+					sbi->s_gdb_count + 1);
+		gdp = ext4_get_group_desc(sb, i, NULL);
+		ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1);
+		if (ret)
+			return ret;
+		ret = add_system_zone(sbi, ext4_inode_bitmap(sb, gdp), 1);
+		if (ret)
+			return ret;
+		ret = add_system_zone(sbi, ext4_inode_table(sb, gdp),
+				sbi->s_itb_per_group);
+		if (ret)
+			return ret;
+	}
+
+	if (test_opt(sb, DEBUG))
+		debug_print_tree(EXT4_SB(sb));
+	return 0;
+}
+
+/* Called when the filesystem is unmounted */
+void ext4_release_system_zone(struct super_block *sb)
+{
+	struct rb_node	*n = EXT4_SB(sb)->system_blks.rb_node;
+	struct rb_node	*parent;
+	struct ext4_system_zone	*entry;
+
+	while (n) {
+		/* Do the node's children first */
+		if (n->rb_left) {
+			n = n->rb_left;
+			continue;
+		}
+		if (n->rb_right) {
+			n = n->rb_right;
+			continue;
+		}
+		/*
+		 * The node has no children; free it, and then zero
+		 * out parent's link to it.  Finally go to the
+		 * beginning of the loop and try to free the parent
+		 * node.
+		 */
+		parent = rb_parent(n);
+		entry = rb_entry(n, struct ext4_system_zone, node);
+		kmem_cache_free(ext4_system_zone_cachep, entry);
+		if (!parent)
+			EXT4_SB(sb)->system_blks.rb_node = NULL;
+		else if (parent->rb_left == n)
+			parent->rb_left = NULL;
+		else if (parent->rb_right == n)
+			parent->rb_right = NULL;
+		n = parent;
+	}
+	EXT4_SB(sb)->system_blks.rb_node = NULL;
+}
+
+/*
+ * Returns 1 if the passed-in block region (start_blk,
+ * start_blk+count) is valid; 0 if some part of the block region
+ * overlaps with filesystem metadata blocks.
+ */
+int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
+			  unsigned int count)
+{
+	struct ext4_system_zone *entry;
+	struct rb_node *n = sbi->system_blks.rb_node;
+
+	if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
+	    (start_blk + count > ext4_blocks_count(sbi->s_es)))
+		return 0;
+	while (n) {
+		entry = rb_entry(n, struct ext4_system_zone, node);
+		if (start_blk + count - 1 < entry->start_blk)
+			n = n->rb_left;
+		else if (start_blk >= (entry->start_blk + entry->count))
+			n = n->rb_right;
+		else
+			return 0;
+	}
+	return 1;
+}
+

fs/ext4/dir.c

@@ -131,8 +131,7 @@ static int ext4_readdir(struct file *filp,
 		struct buffer_head *bh = NULL;
 
 		map_bh.b_state = 0;
-		err = ext4_get_blocks_wrap(NULL, inode, blk, 1, &map_bh,
-						0, 0, 0);
+		err = ext4_get_blocks(NULL, inode, blk, 1, &map_bh, 0);
 		if (err > 0) {
 			pgoff_t index = map_bh.b_blocknr >>
 					(PAGE_CACHE_SHIFT - inode->i_blkbits);

fs/ext4/ext4.h

@@ -21,7 +21,14 @@
 #include <linux/magic.h>
 #include <linux/jbd2.h>
 #include <linux/quota.h>
-#include "ext4_i.h"
+#include <linux/rwsem.h>
+#include <linux/rbtree.h>
+#include <linux/seqlock.h>
+#include <linux/mutex.h>
+#include <linux/timer.h>
+#include <linux/wait.h>
+#include <linux/blockgroup_lock.h>
+#include <linux/percpu_counter.h>
 
 /*
  * The fourth extended filesystem constants/structures
@@ -46,6 +53,19 @@
 #define ext4_debug(f, a...)	do {} while (0)
 #endif
 
+/* data type for block offset of block group */
+typedef int ext4_grpblk_t;
+
+/* data type for filesystem-wide blocks number */
+typedef unsigned long long ext4_fsblk_t;
+
+/* data type for file logical block number */
+typedef __u32 ext4_lblk_t;
+
+/* data type for block group number */
+typedef unsigned int ext4_group_t;
+
+
 /* prefer goal again. length */
 #define EXT4_MB_HINT_MERGE		1
 /* blocks already reserved */
@@ -179,9 +199,6 @@ struct flex_groups {
 #define EXT4_BG_BLOCK_UNINIT	0x0002 /* Block bitmap not in use */
 #define EXT4_BG_INODE_ZEROED	0x0004 /* On-disk itable initialized to zero */
 
-#ifdef __KERNEL__
-#include "ext4_sb.h"
-#endif
 /*
  * Macro-instructions used to manage group descriptors
  */
@@ -297,10 +314,23 @@ struct ext4_new_group_data {
 };
 
 /*
- * Following is used by preallocation code to tell get_blocks() that we
- * want uninitialzed extents.
+ * Flags used by ext4_get_blocks()
  */
-#define EXT4_CREATE_UNINITIALIZED_EXT		2
+	/* Allocate any needed blocks and/or convert an unitialized
+	   extent to be an initialized ext4 */
+#define EXT4_GET_BLOCKS_CREATE			0x0001
+	/* Request the creation of an unitialized extent */
+#define EXT4_GET_BLOCKS_UNINIT_EXT		0x0002
+#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT	(EXT4_GET_BLOCKS_UNINIT_EXT|\
+						 EXT4_GET_BLOCKS_CREATE)
+	/* Caller is from the delayed allocation writeout path,
+	   so set the magic i_delalloc_reserve_flag after taking the 
+	   inode allocation semaphore for */
+#define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
+	/* Call ext4_da_update_reserve_space() after successfully 
+	   allocating the blocks */
+#define EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE	0x0008
+
 
 /*
  * ioctl commands
@@ -515,6 +545,110 @@ do {									       \
 
 #endif /* defined(__KERNEL__) || defined(__linux__) */
 
+/*
+ * storage for cached extent
+ */
+struct ext4_ext_cache {
+	ext4_fsblk_t	ec_start;
+	ext4_lblk_t	ec_block;
+	__u32		ec_len; /* must be 32bit to return holes */
+	__u32		ec_type;
+};
+
+/*
+ * fourth extended file system inode data in memory
+ */
+struct ext4_inode_info {
+	__le32	i_data[15];	/* unconverted */
+	__u32	i_flags;
+	ext4_fsblk_t	i_file_acl;
+	__u32	i_dtime;
+
+	/*
+	 * i_block_group is the number of the block group which contains
+	 * this file's inode.  Constant across the lifetime of the inode,
+	 * it is ued for making block allocation decisions - we try to
+	 * place a file's data blocks near its inode block, and new inodes
+	 * near to their parent directory's inode.
+	 */
+	ext4_group_t	i_block_group;
+	__u32	i_state;		/* Dynamic state flags for ext4 */
+
+	ext4_lblk_t		i_dir_start_lookup;
+#ifdef CONFIG_EXT4_FS_XATTR
+	/*
+	 * Extended attributes can be read independently of the main file
+	 * data. Taking i_mutex even when reading would cause contention
+	 * between readers of EAs and writers of regular file data, so
+	 * instead we synchronize on xattr_sem when reading or changing
+	 * EAs.
+	 */
+	struct rw_semaphore xattr_sem;
+#endif
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
+	struct posix_acl	*i_acl;
+	struct posix_acl	*i_default_acl;
+#endif
+
+	struct list_head i_orphan;	/* unlinked but open inodes */
+
+	/*
+	 * i_disksize keeps track of what the inode size is ON DISK, not
+	 * in memory.  During truncate, i_size is set to the new size by
+	 * the VFS prior to calling ext4_truncate(), but the filesystem won't
+	 * set i_disksize to 0 until the truncate is actually under way.
+	 *
+	 * The intent is that i_disksize always represents the blocks which
+	 * are used by this file.  This allows recovery to restart truncate
+	 * on orphans if we crash during truncate.  We actually write i_disksize
+	 * into the on-disk inode when writing inodes out, instead of i_size.
+	 *
+	 * The only time when i_disksize and i_size may be different is when
+	 * a truncate is in progress.  The only things which change i_disksize
+	 * are ext4_get_block (growth) and ext4_truncate (shrinkth).
+	 */
+	loff_t	i_disksize;
+
+	/*
+	 * i_data_sem is for serialising ext4_truncate() against
+	 * ext4_getblock().  In the 2.4 ext2 design, great chunks of inode's
+	 * data tree are chopped off during truncate. We can't do that in
+	 * ext4 because whenever we perform intermediate commits during
+	 * truncate, the inode and all the metadata blocks *must* be in a
+	 * consistent state which allows truncation of the orphans to restart
+	 * during recovery.  Hence we must fix the get_block-vs-truncate race
+	 * by other means, so we have i_data_sem.
+	 */
+	struct rw_semaphore i_data_sem;
+	struct inode vfs_inode;
+	struct jbd2_inode jinode;
+
+	struct ext4_ext_cache i_cached_extent;
+	/*
+	 * File creation time. Its function is same as that of
+	 * struct timespec i_{a,c,m}time in the generic inode.
+	 */
+	struct timespec i_crtime;
+
+	/* mballoc */
+	struct list_head i_prealloc_list;
+	spinlock_t i_prealloc_lock;
+
+	/* ialloc */
+	ext4_group_t	i_last_alloc_group;
+
+	/* allocation reservation info for delalloc */
+	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;
+};
+
 /*
  * File system states
  */
@@ -560,6 +694,7 @@ do {									       \
 #define EXT4_MOUNT_I_VERSION            0x2000000 /* i_version support */
 #define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
 #define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
+#define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
 
 /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */
 #ifndef _LINUX_EXT2_FS_H
@@ -689,6 +824,137 @@ struct ext4_super_block {
 };
 
 #ifdef __KERNEL__
+/*
+ * fourth extended-fs super-block data in memory
+ */
+struct ext4_sb_info {
+	unsigned long s_desc_size;	/* Size of a group descriptor in bytes */
+	unsigned long s_inodes_per_block;/* Number of inodes per block */
+	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 */
+	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
+	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
+	ext4_group_t s_groups_count;	/* Number of groups in the fs */
+	unsigned long s_overhead_last;  /* Last calculated overhead */
+	unsigned long s_blocks_last;    /* Last seen block count */
+	loff_t s_bitmap_maxbytes;	/* max bytes for bitmap files */
+	struct buffer_head * s_sbh;	/* Buffer containing the super block */
+	struct ext4_super_block *s_es;	/* Pointer to the super block in the buffer */
+	struct buffer_head **s_group_desc;
+	unsigned long  s_mount_opt;
+	ext4_fsblk_t s_sb_block;
+	uid_t s_resuid;
+	gid_t s_resgid;
+	unsigned short s_mount_state;
+	unsigned short s_pad;
+	int s_addr_per_block_bits;
+	int s_desc_per_block_bits;
+	int s_inode_size;
+	int s_first_ino;
+	unsigned int s_inode_readahead_blks;
+	spinlock_t s_next_gen_lock;
+	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;
+	struct percpu_counter s_dirtyblocks_counter;
+	struct blockgroup_lock *s_blockgroup_lock;
+	struct proc_dir_entry *s_proc;
+	struct kobject s_kobj;
+	struct completion s_kobj_unregister;
+
+	/* Journaling */
+	struct inode *s_journal_inode;
+	struct journal_s *s_journal;
+	struct list_head s_orphan;
+	struct mutex s_orphan_lock;
+	struct mutex s_resize_lock;
+	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) */
+	wait_queue_head_t ro_wait_queue;	/* For people waiting for the fs to go read-only */
+#endif
+#ifdef CONFIG_QUOTA
+	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
+	int s_jquota_fmt;			/* Format of quota to use */
+#endif
+	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
+	struct rb_root system_blks;
+
+#ifdef EXTENTS_STATS
+	/* ext4 extents stats */
+	unsigned long s_ext_min;
+	unsigned long s_ext_max;
+	unsigned long s_depth_max;
+	spinlock_t s_ext_stats_lock;
+	unsigned long s_ext_blocks;
+	unsigned long s_ext_extents;
+#endif
+
+	/* for buddy allocator */
+	struct ext4_group_info ***s_group_info;
+	struct inode *s_buddy_cache;
+	long s_blocks_reserved;
+	spinlock_t s_reserve_lock;
+	spinlock_t s_md_lock;
+	tid_t s_last_transaction;
+	unsigned short *s_mb_offsets;
+	unsigned int *s_mb_maxs;
+
+	/* tunables */
+	unsigned long s_stripe;
+	unsigned int s_mb_stream_request;
+	unsigned int s_mb_max_to_scan;
+	unsigned int s_mb_min_to_scan;
+	unsigned int s_mb_stats;
+	unsigned int s_mb_order2_reqs;
+	unsigned int s_mb_group_prealloc;
+	/* where last allocation was done - for stream allocation */
+	unsigned long s_mb_last_group;
+	unsigned long s_mb_last_start;
+
+	/* history to debug policy */
+	struct ext4_mb_history *s_mb_history;
+	int s_mb_history_cur;
+	int s_mb_history_max;
+	int s_mb_history_num;
+	spinlock_t s_mb_history_lock;
+	int s_mb_history_filter;
+
+	/* stats for buddy allocator */
+	spinlock_t s_mb_pa_lock;
+	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
+	atomic_t s_bal_success;	/* we found long enough chunks */
+	atomic_t s_bal_allocated;	/* in blocks */
+	atomic_t s_bal_ex_scanned;	/* total extents scanned */
+	atomic_t s_bal_goals;	/* goal hits */
+	atomic_t s_bal_breaks;	/* too long searches */
+	atomic_t s_bal_2orders;	/* 2^order hits */
+	spinlock_t s_bal_lock;
+	unsigned long s_mb_buddies_generated;
+	unsigned long long s_mb_generation_time;
+	atomic_t s_mb_lost_chunks;
+	atomic_t s_mb_preallocated;
+	atomic_t s_mb_discarded;
+
+	/* locality groups */
+	struct ext4_locality_group *s_locality_groups;
+
+	/* for write statistics */
+	unsigned long s_sectors_written_start;
+	u64 s_kbytes_written;
+
+	unsigned int s_log_groups_per_flex;
+	struct flex_groups *s_flex_groups;
+};
+
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
 {
 	return sb->s_fs_info;
@@ -704,7 +970,6 @@ static inline struct timespec ext4_current_time(struct inode *inode)
 		current_fs_time(inode->i_sb) : CURRENT_TIME_SEC;
 }
 
-
 static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 {
 	return ino == EXT4_ROOT_INO ||
@@ -1014,6 +1279,14 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
 						    ext4_group_t block_group,
 						    struct buffer_head ** bh);
 extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
+struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
+				      ext4_group_t block_group);
+extern unsigned ext4_init_block_bitmap(struct super_block *sb,
+				       struct buffer_head *bh,
+				       ext4_group_t group,
+				       struct ext4_group_desc *desc);
+#define ext4_free_blocks_after_init(sb, group, desc)			\
+		ext4_init_block_bitmap(sb, NULL, group, desc)
 
 /* dir.c */
 extern int ext4_check_dir_entry(const char *, struct inode *,
@@ -1038,6 +1311,11 @@ extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
 extern unsigned long ext4_count_free_inodes(struct super_block *);
 extern unsigned long ext4_count_dirs(struct super_block *);
 extern void ext4_check_inodes_bitmap(struct super_block *);
+extern unsigned ext4_init_inode_bitmap(struct super_block *sb,
+				       struct buffer_head *bh,
+				       ext4_group_t group,
+				       struct ext4_group_desc *desc);
+extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
 
 /* mballoc.c */
 extern long ext4_mb_stats;
@@ -1123,6 +1401,8 @@ extern void ext4_abort(struct super_block *, const char *, const char *, ...)
 	__attribute__ ((format (printf, 3, 4)));
 extern void ext4_warning(struct super_block *, const char *, const char *, ...)
 	__attribute__ ((format (printf, 3, 4)));
+extern void ext4_msg(struct super_block *, const char *, const char *, ...)
+	__attribute__ ((format (printf, 3, 4)));
 extern void ext4_grp_locked_error(struct super_block *, ext4_group_t,
 				const char *, const char *, ...)
 	__attribute__ ((format (printf, 4, 5)));
@@ -1161,6 +1441,10 @@ extern void ext4_used_dirs_set(struct super_block *sb,
 				struct ext4_group_desc *bg, __u32 count);
 extern void ext4_itable_unused_set(struct super_block *sb,
 				   struct ext4_group_desc *bg, __u32 count);
+extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group,
+				   struct ext4_group_desc *gdp);
+extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group,
+				       struct ext4_group_desc *gdp);
 
 static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
 {
@@ -1228,6 +1512,18 @@ struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
 	 return grp_info[indexv][indexh];
 }
 
+/*
+ * Reading s_groups_count requires using smp_rmb() afterwards.  See
+ * the locking protocol documented in the comments of ext4_group_add()
+ * in resize.c
+ */
+static inline ext4_group_t ext4_get_groups_count(struct super_block *sb)
+{
+	ext4_group_t	ngroups = EXT4_SB(sb)->s_groups_count;
+
+	smp_rmb();
+	return ngroups;
+}
 
 static inline ext4_group_t ext4_flex_group(struct ext4_sb_info *sbi,
 					     ext4_group_t block_group)
@@ -1283,33 +1579,25 @@ struct ext4_group_info {
 };
 
 #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)))
 
-static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
+static inline spinlock_t *ext4_group_lock_ptr(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));
+	return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group);
 }
 
-static inline void ext4_unlock_group(struct super_block *sb,
-					ext4_group_t group)
+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_unlock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
+	spin_lock(ext4_group_lock_ptr(sb, group));
 }
 
-static inline int ext4_is_group_locked(struct super_block *sb,
+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);
-
-	return bit_spin_is_locked(EXT4_GROUP_INFO_LOCKED_BIT,
-						&(grinfo->bb_state));
+	spin_unlock(ext4_group_lock_ptr(sb, group));
 }
 
 /*
@@ -1326,11 +1614,21 @@ extern const struct file_operations ext4_file_operations;
 /* namei.c */
 extern const struct inode_operations ext4_dir_inode_operations;
 extern const struct inode_operations ext4_special_inode_operations;
+extern struct dentry *ext4_get_parent(struct dentry *child);
 
 /* symlink.c */
 extern const struct inode_operations ext4_symlink_inode_operations;
 extern const struct inode_operations ext4_fast_symlink_inode_operations;
 
+/* block_validity */
+extern void ext4_release_system_zone(struct super_block *sb);
+extern int ext4_setup_system_zone(struct super_block *sb);
+extern int __init init_ext4_system_zone(void);
+extern void exit_ext4_system_zone(void);
+extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
+				 ext4_fsblk_t start_blk,
+				 unsigned int count);
+
 /* extents.c */
 extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
 extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
@@ -1338,17 +1636,15 @@ extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
 				       int chunk);
 extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 			       ext4_lblk_t iblock, unsigned int max_blocks,
-			       struct buffer_head *bh_result,
-			       int create, int extend_disksize);
+			       struct buffer_head *bh_result, int flags);
 extern void ext4_ext_truncate(struct inode *);
 extern void ext4_ext_init(struct super_block *);
 extern void ext4_ext_release(struct super_block *);
 extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
 			  loff_t len);
-extern int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode,
-			sector_t block, unsigned int max_blocks,
-			struct buffer_head *bh, int create,
-			int extend_disksize, int flag);
+extern int ext4_get_blocks(handle_t *handle, struct inode *inode,
+			   sector_t block, unsigned int max_blocks,
+			   struct buffer_head *bh, int flags);
 extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			__u64 start, __u64 len);
 

fs/ext4/ext4_i.h

@@ -1,140 +0,0 @@
-/*
- *  ext4_i.h
- *
- * Copyright (C) 1992, 1993, 1994, 1995
- * Remy Card (card@masi.ibp.fr)
- * Laboratoire MASI - Institut Blaise Pascal
- * Universite Pierre et Marie Curie (Paris VI)
- *
- *  from
- *
- *  linux/include/linux/minix_fs_i.h
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds
- */
-
-#ifndef _EXT4_I
-#define _EXT4_I
-
-#include <linux/rwsem.h>
-#include <linux/rbtree.h>
-#include <linux/seqlock.h>
-#include <linux/mutex.h>
-
-/* data type for block offset of block group */
-typedef int ext4_grpblk_t;
-
-/* data type for filesystem-wide blocks number */
-typedef unsigned long long ext4_fsblk_t;
-
-/* data type for file logical block number */
-typedef __u32 ext4_lblk_t;
-
-/* data type for block group number */
-typedef unsigned int ext4_group_t;
-
-/*
- * storage for cached extent
- */
-struct ext4_ext_cache {
-	ext4_fsblk_t	ec_start;
-	ext4_lblk_t	ec_block;
-	__u32		ec_len; /* must be 32bit to return holes */
-	__u32		ec_type;
-};
-
-/*
- * fourth extended file system inode data in memory
- */
-struct ext4_inode_info {
-	__le32	i_data[15];	/* unconverted */
-	__u32	i_flags;
-	ext4_fsblk_t	i_file_acl;
-	__u32	i_dtime;
-
-	/*
-	 * i_block_group is the number of the block group which contains
-	 * this file's inode.  Constant across the lifetime of the inode,
-	 * it is ued for making block allocation decisions - we try to
-	 * place a file's data blocks near its inode block, and new inodes
-	 * near to their parent directory's inode.
-	 */
-	ext4_group_t	i_block_group;
-	__u32	i_state;		/* Dynamic state flags for ext4 */
-
-	ext4_lblk_t		i_dir_start_lookup;
-#ifdef CONFIG_EXT4_FS_XATTR
-	/*
-	 * Extended attributes can be read independently of the main file
-	 * data. Taking i_mutex even when reading would cause contention
-	 * between readers of EAs and writers of regular file data, so
-	 * instead we synchronize on xattr_sem when reading or changing
-	 * EAs.
-	 */
-	struct rw_semaphore xattr_sem;
-#endif
-#ifdef CONFIG_EXT4_FS_POSIX_ACL
-	struct posix_acl	*i_acl;
-	struct posix_acl	*i_default_acl;
-#endif
-
-	struct list_head i_orphan;	/* unlinked but open inodes */
-
-	/*
-	 * i_disksize keeps track of what the inode size is ON DISK, not
-	 * in memory.  During truncate, i_size is set to the new size by
-	 * the VFS prior to calling ext4_truncate(), but the filesystem won't
-	 * set i_disksize to 0 until the truncate is actually under way.
-	 *
-	 * The intent is that i_disksize always represents the blocks which
-	 * are used by this file.  This allows recovery to restart truncate
-	 * on orphans if we crash during truncate.  We actually write i_disksize
-	 * into the on-disk inode when writing inodes out, instead of i_size.
-	 *
-	 * The only time when i_disksize and i_size may be different is when
-	 * a truncate is in progress.  The only things which change i_disksize
-	 * are ext4_get_block (growth) and ext4_truncate (shrinkth).
-	 */
-	loff_t	i_disksize;
-
-	/*
-	 * i_data_sem is for serialising ext4_truncate() against
-	 * ext4_getblock().  In the 2.4 ext2 design, great chunks of inode's
-	 * data tree are chopped off during truncate. We can't do that in
-	 * ext4 because whenever we perform intermediate commits during
-	 * truncate, the inode and all the metadata blocks *must* be in a
-	 * consistent state which allows truncation of the orphans to restart
-	 * during recovery.  Hence we must fix the get_block-vs-truncate race
-	 * by other means, so we have i_data_sem.
-	 */
-	struct rw_semaphore i_data_sem;
-	struct inode vfs_inode;
-	struct jbd2_inode jinode;
-
-	struct ext4_ext_cache i_cached_extent;
-	/*
-	 * File creation time. Its function is same as that of
-	 * struct timespec i_{a,c,m}time in the generic inode.
-	 */
-	struct timespec i_crtime;
-
-	/* mballoc */
-	struct list_head i_prealloc_list;
-	spinlock_t i_prealloc_lock;
-
-	/* ialloc */
-	ext4_group_t	i_last_alloc_group;
-
-	/* allocation reservation info for delalloc */
-	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;
-};
-
-#endif	/* _EXT4_I */

fs/ext4/ext4_sb.h

@@ -1,161 +0,0 @@
-/*
- *  ext4_sb.h
- *
- * Copyright (C) 1992, 1993, 1994, 1995
- * Remy Card (card@masi.ibp.fr)
- * Laboratoire MASI - Institut Blaise Pascal
- * Universite Pierre et Marie Curie (Paris VI)
- *
- *  from
- *
- *  linux/include/linux/minix_fs_sb.h
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds
- */
-
-#ifndef _EXT4_SB
-#define _EXT4_SB
-
-#ifdef __KERNEL__
-#include <linux/timer.h>
-#include <linux/wait.h>
-#include <linux/blockgroup_lock.h>
-#include <linux/percpu_counter.h>
-#endif
-#include <linux/rbtree.h>
-
-/*
- * fourth extended-fs super-block data in memory
- */
-struct ext4_sb_info {
-	unsigned long s_desc_size;	/* Size of a group descriptor in bytes */
-	unsigned long s_inodes_per_block;/* Number of inodes per block */
-	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 */
-	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
-	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
-	ext4_group_t s_groups_count;	/* Number of groups in the fs */
-	unsigned long s_overhead_last;  /* Last calculated overhead */
-	unsigned long s_blocks_last;    /* Last seen block count */
-	loff_t s_bitmap_maxbytes;	/* max bytes for bitmap files */
-	struct buffer_head * s_sbh;	/* Buffer containing the super block */
-	struct ext4_super_block *s_es;	/* Pointer to the super block in the buffer */
-	struct buffer_head **s_group_desc;
-	unsigned long  s_mount_opt;
-	ext4_fsblk_t s_sb_block;
-	uid_t s_resuid;
-	gid_t s_resgid;
-	unsigned short s_mount_state;
-	unsigned short s_pad;
-	int s_addr_per_block_bits;
-	int s_desc_per_block_bits;
-	int s_inode_size;
-	int s_first_ino;
-	unsigned int s_inode_readahead_blks;
-	spinlock_t s_next_gen_lock;
-	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;
-	struct percpu_counter s_dirtyblocks_counter;
-	struct blockgroup_lock *s_blockgroup_lock;
-	struct proc_dir_entry *s_proc;
-	struct kobject s_kobj;
-	struct completion s_kobj_unregister;
-
-	/* Journaling */
-	struct inode *s_journal_inode;
-	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) */
-	wait_queue_head_t ro_wait_queue;	/* For people waiting for the fs to go read-only */
-#endif
-#ifdef CONFIG_QUOTA
-	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
-	int s_jquota_fmt;			/* Format of quota to use */
-#endif
-	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
-
-#ifdef EXTENTS_STATS
-	/* ext4 extents stats */
-	unsigned long s_ext_min;
-	unsigned long s_ext_max;
-	unsigned long s_depth_max;
-	spinlock_t s_ext_stats_lock;
-	unsigned long s_ext_blocks;
-	unsigned long s_ext_extents;
-#endif
-
-	/* for buddy allocator */
-	struct ext4_group_info ***s_group_info;
-	struct inode *s_buddy_cache;
-	long s_blocks_reserved;
-	spinlock_t s_reserve_lock;
-	spinlock_t s_md_lock;
-	tid_t s_last_transaction;
-	unsigned short *s_mb_offsets;
-	unsigned int *s_mb_maxs;
-
-	/* tunables */
-	unsigned long s_stripe;
-	unsigned int s_mb_stream_request;
-	unsigned int s_mb_max_to_scan;
-	unsigned int s_mb_min_to_scan;
-	unsigned int s_mb_stats;
-	unsigned int s_mb_order2_reqs;
-	unsigned int s_mb_group_prealloc;
-	/* where last allocation was done - for stream allocation */
-	unsigned long s_mb_last_group;
-	unsigned long s_mb_last_start;
-
-	/* history to debug policy */
-	struct ext4_mb_history *s_mb_history;
-	int s_mb_history_cur;
-	int s_mb_history_max;
-	int s_mb_history_num;
-	spinlock_t s_mb_history_lock;
-	int s_mb_history_filter;
-
-	/* stats for buddy allocator */
-	spinlock_t s_mb_pa_lock;
-	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
-	atomic_t s_bal_success;	/* we found long enough chunks */
-	atomic_t s_bal_allocated;	/* in blocks */
-	atomic_t s_bal_ex_scanned;	/* total extents scanned */
-	atomic_t s_bal_goals;	/* goal hits */
-	atomic_t s_bal_breaks;	/* too long searches */
-	atomic_t s_bal_2orders;	/* 2^order hits */
-	spinlock_t s_bal_lock;
-	unsigned long s_mb_buddies_generated;
-	unsigned long long s_mb_generation_time;
-	atomic_t s_mb_lost_chunks;
-	atomic_t s_mb_preallocated;
-	atomic_t s_mb_discarded;
-
-	/* locality groups */
-	struct ext4_locality_group *s_locality_groups;
-
-	/* for write statistics */
-	unsigned long s_sectors_written_start;
-	u64 s_kbytes_written;
-
-	unsigned int s_log_groups_per_flex;
-	struct flex_groups *s_flex_groups;
-};
-
-static inline spinlock_t *
-sb_bgl_lock(struct ext4_sb_info *sbi, unsigned int block_group)
-{
-	return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group);
-}
-
-#endif	/* _EXT4_SB */

fs/ext4/extents.c

@@ -326,32 +326,18 @@ ext4_ext_max_entries(struct inode *inode, int depth)
 
 static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
 {
-	ext4_fsblk_t block = ext_pblock(ext), valid_block;
+	ext4_fsblk_t block = ext_pblock(ext);
 	int len = ext4_ext_get_actual_len(ext);
-	struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
 
-	valid_block = le32_to_cpu(es->s_first_data_block) +
-		EXT4_SB(inode->i_sb)->s_gdb_count;
-	if (unlikely(block <= valid_block ||
-		     ((block + len) > ext4_blocks_count(es))))
-		return 0;
-	else
-		return 1;
+	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
 }
 
 static int ext4_valid_extent_idx(struct inode *inode,
 				struct ext4_extent_idx *ext_idx)
 {
-	ext4_fsblk_t block = idx_pblock(ext_idx), valid_block;
-	struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+	ext4_fsblk_t block = idx_pblock(ext_idx);
 
-	valid_block = le32_to_cpu(es->s_first_data_block) +
-		EXT4_SB(inode->i_sb)->s_gdb_count;
-	if (unlikely(block <= valid_block ||
-		     (block >= ext4_blocks_count(es))))
-		return 0;
-	else
-		return 1;
+	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1);
 }
 
 static int ext4_valid_extent_entries(struct inode *inode,
@@ -2097,12 +2083,16 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 	ex = EXT_LAST_EXTENT(eh);
 
 	ex_ee_block = le32_to_cpu(ex->ee_block);
-	if (ext4_ext_is_uninitialized(ex))
-		uninitialized = 1;
 	ex_ee_len = ext4_ext_get_actual_len(ex);
 
 	while (ex >= EXT_FIRST_EXTENT(eh) &&
 			ex_ee_block + ex_ee_len > start) {
+
+		if (ext4_ext_is_uninitialized(ex))
+			uninitialized = 1;
+		else
+			uninitialized = 0;
+
 		ext_debug("remove ext %lu:%u\n", ex_ee_block, ex_ee_len);
 		path[depth].p_ext = ex;
 
@@ -2784,7 +2774,7 @@ fix_extent_len:
 int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 			ext4_lblk_t iblock,
 			unsigned int max_blocks, struct buffer_head *bh_result,
-			int create, int extend_disksize)
+			int flags)
 {
 	struct ext4_ext_path *path = NULL;
 	struct ext4_extent_header *eh;
@@ -2793,7 +2783,6 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	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/%u requested for inode %u\n",
@@ -2803,7 +2792,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	cache_type = ext4_ext_in_cache(inode, iblock, &newex);
 	if (cache_type) {
 		if (cache_type == EXT4_EXT_CACHE_GAP) {
-			if (!create) {
+			if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
 				/*
 				 * block isn't allocated yet and
 				 * user doesn't want to allocate it
@@ -2869,9 +2858,11 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 							EXT4_EXT_CACHE_EXTENT);
 				goto out;
 			}
-			if (create == EXT4_CREATE_UNINITIALIZED_EXT)
+			if (flags & EXT4_GET_BLOCKS_UNINIT_EXT)
 				goto out;
-			if (!create) {
+			if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
+				if (allocated > max_blocks)
+					allocated = max_blocks;
 				/*
 				 * We have blocks reserved already.  We
 				 * return allocated blocks so that delalloc
@@ -2879,8 +2870,6 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 				 * the buffer head will be unmapped so that
 				 * a read from the block returns 0s.
 				 */
-				if (allocated > max_blocks)
-					allocated = max_blocks;
 				set_buffer_unwritten(bh_result);
 				bh_result->b_bdev = inode->i_sb->s_bdev;
 				bh_result->b_blocknr = newblock;
@@ -2903,7 +2892,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	 * requested block isn't allocated yet;
 	 * we couldn't try to create block if create flag is zero
 	 */
-	if (!create) {
+	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
 		/*
 		 * put just found gap into cache to speed up
 		 * subsequent requests
@@ -2932,10 +2921,10 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	 * EXT_UNINIT_MAX_LEN.
 	 */
 	if (max_blocks > EXT_INIT_MAX_LEN &&
-	    create != EXT4_CREATE_UNINITIALIZED_EXT)
+	    !(flags & EXT4_GET_BLOCKS_UNINIT_EXT))
 		max_blocks = EXT_INIT_MAX_LEN;
 	else if (max_blocks > EXT_UNINIT_MAX_LEN &&
-		 create == EXT4_CREATE_UNINITIALIZED_EXT)
+		 (flags & EXT4_GET_BLOCKS_UNINIT_EXT))
 		max_blocks = EXT_UNINIT_MAX_LEN;
 
 	/* Check if we can really insert (iblock)::(iblock+max_blocks) extent */
@@ -2966,7 +2955,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	/* try to insert new extent into found leaf and return */
 	ext4_ext_store_pblock(&newex, newblock);
 	newex.ee_len = cpu_to_le16(ar.len);
-	if (create == EXT4_CREATE_UNINITIALIZED_EXT)  /* Mark uninitialized */
+	if (flags & EXT4_GET_BLOCKS_UNINIT_EXT)  /* Mark uninitialized */
 		ext4_ext_mark_uninitialized(&newex);
 	err = ext4_ext_insert_extent(handle, inode, path, &newex);
 	if (err) {
@@ -2983,18 +2972,10 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	newblock = ext_pblock(&newex);
 	allocated = ext4_ext_get_actual_len(&newex);
 outnew:
-	if (extend_disksize) {
-		disksize = ((loff_t) iblock + ar.len) << inode->i_blkbits;
-		if (disksize > i_size_read(inode))
-			disksize = i_size_read(inode);
-		if (disksize > EXT4_I(inode)->i_disksize)
-			EXT4_I(inode)->i_disksize = disksize;
-	}
-
 	set_buffer_new(bh_result);
 
 	/* Cache only when it is _not_ an uninitialized extent */
-	if (create != EXT4_CREATE_UNINITIALIZED_EXT)
+	if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0)
 		ext4_ext_put_in_cache(inode, iblock, allocated, newblock,
 						EXT4_EXT_CACHE_EXTENT);
 out:
@@ -3150,9 +3131,10 @@ retry:
 			ret = PTR_ERR(handle);
 			break;
 		}
-		ret = ext4_get_blocks_wrap(handle, inode, block,
-					  max_blocks, &map_bh,
-					  EXT4_CREATE_UNINITIALIZED_EXT, 0, 0);
+		map_bh.b_state = 0;
+		ret = ext4_get_blocks(handle, inode, block,
+				      max_blocks, &map_bh,
+				      EXT4_GET_BLOCKS_CREATE_UNINIT_EXT);
 		if (ret <= 0) {
 #ifdef EXT4FS_DEBUG
 			WARN_ON(ret <= 0);
@@ -3195,7 +3177,7 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
 		       void *data)
 {
 	struct fiemap_extent_info *fieinfo = data;
-	unsigned long blksize_bits = inode->i_sb->s_blocksize_bits;
+	unsigned char blksize_bits = inode->i_sb->s_blocksize_bits;
 	__u64	logical;
 	__u64	physical;
 	__u64	length;
@@ -3242,9 +3224,16 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
 	 *
 	 * XXX this might miss a single-block extent at EXT_MAX_BLOCK
 	 */
-	if (logical + length - 1 == EXT_MAX_BLOCK ||
-	    ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK)
+	if (ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK ||
+	    newex->ec_block + newex->ec_len - 1 == EXT_MAX_BLOCK) {
+		loff_t size = i_size_read(inode);
+		loff_t bs = EXT4_BLOCK_SIZE(inode->i_sb);
+
 		flags |= FIEMAP_EXTENT_LAST;
+		if ((flags & FIEMAP_EXTENT_DELALLOC) &&
+		    logical+length > size)
+			length = (size - logical + bs - 1) & ~(bs-1);
+	}
 
 	error = fiemap_fill_next_extent(fieinfo, logical, physical,
 					length, flags);
@@ -3318,10 +3307,10 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		 * Walk the extent tree gathering extent information.
 		 * ext4_ext_fiemap_cb will push extents back to user.
 		 */
-		down_write(&EXT4_I(inode)->i_data_sem);
+		down_read(&EXT4_I(inode)->i_data_sem);
 		error = ext4_ext_walk_space(inode, start_blk, len_blks,
 					  ext4_ext_fiemap_cb, fieinfo);
-		up_write(&EXT4_I(inode)->i_data_sem);
+		up_read(&EXT4_I(inode)->i_data_sem);
 	}
 
 	return error;

fs/ext4/group.h

@@ -1,29 +0,0 @@
-/*
- *  linux/fs/ext4/group.h
- *
- * Copyright (C) 2007 Cluster File Systems, Inc
- *
- * Author: Andreas Dilger <adilger@clusterfs.com>
- */
-
-#ifndef _LINUX_EXT4_GROUP_H
-#define _LINUX_EXT4_GROUP_H
-
-extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group,
-				   struct ext4_group_desc *gdp);
-extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group,
-				       struct ext4_group_desc *gdp);
-struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
-				      ext4_group_t block_group);
-extern unsigned ext4_init_block_bitmap(struct super_block *sb,
-				       struct buffer_head *bh,
-				       ext4_group_t group,
-				       struct ext4_group_desc *desc);
-#define ext4_free_blocks_after_init(sb, group, desc)			\
-		ext4_init_block_bitmap(sb, NULL, group, desc)
-extern unsigned ext4_init_inode_bitmap(struct super_block *sb,
-				       struct buffer_head *bh,
-				       ext4_group_t group,
-				       struct ext4_group_desc *desc);
-extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
-#endif /* _LINUX_EXT4_GROUP_H */

fs/ext4/ialloc.c

@@ -27,7 +27,6 @@
 #include "ext4_jbd2.h"
 #include "xattr.h"
 #include "acl.h"
-#include "group.h"
 
 /*
  * ialloc.c contains the inodes allocation and deallocation routines
@@ -123,16 +122,16 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 		unlock_buffer(bh);
 		return bh;
 	}
-	spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
+	ext4_lock_group(sb, block_group);
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
 		ext4_init_inode_bitmap(sb, bh, block_group, desc);
 		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
-		spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
 		return bh;
 	}
-	spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+	ext4_unlock_group(sb, block_group);
 	if (buffer_uptodate(bh)) {
 		/*
 		 * if not uninit if bh is uptodate,
@@ -247,9 +246,8 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 		goto error_return;
 
 	/* Ok, now we can actually update the inode bitmaps.. */
-	spin_lock(sb_bgl_lock(sbi, block_group));
-	cleared = ext4_clear_bit(bit, bitmap_bh->b_data);
-	spin_unlock(sb_bgl_lock(sbi, block_group));
+	cleared = ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
+					bit, bitmap_bh->b_data);
 	if (!cleared)
 		ext4_error(sb, "ext4_free_inode",
 			   "bit already cleared for inode %lu", ino);
@@ -261,7 +259,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 		if (fatal) goto error_return;
 
 		if (gdp) {
-			spin_lock(sb_bgl_lock(sbi, block_group));
+			ext4_lock_group(sb, block_group);
 			count = ext4_free_inodes_count(sb, gdp) + 1;
 			ext4_free_inodes_set(sb, gdp, count);
 			if (is_directory) {
@@ -277,7 +275,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 			}
 			gdp->bg_checksum = ext4_group_desc_csum(sbi,
 							block_group, gdp);
-			spin_unlock(sb_bgl_lock(sbi, block_group));
+			ext4_unlock_group(sb, block_group);
 			percpu_counter_inc(&sbi->s_freeinodes_counter);
 			if (is_directory)
 				percpu_counter_dec(&sbi->s_dirs_counter);
@@ -316,7 +314,7 @@ error_return:
 static int find_group_dir(struct super_block *sb, struct inode *parent,
 				ext4_group_t *best_group)
 {
-	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	unsigned int freei, avefreei;
 	struct ext4_group_desc *desc, *best_desc = NULL;
 	ext4_group_t group;
@@ -349,11 +347,10 @@ static int find_group_flex(struct super_block *sb, struct inode *parent,
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_group_desc *desc;
-	struct buffer_head *bh;
 	struct flex_groups *flex_group = sbi->s_flex_groups;
 	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
 	ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group);
-	ext4_group_t ngroups = sbi->s_groups_count;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	int flex_size = ext4_flex_bg_size(sbi);
 	ext4_group_t best_flex = parent_fbg_group;
 	int blocks_per_flex = sbi->s_blocks_per_group * flex_size;
@@ -362,7 +359,7 @@ static int find_group_flex(struct super_block *sb, struct inode *parent,
 	ext4_group_t n_fbg_groups;
 	ext4_group_t i;
 
-	n_fbg_groups = (sbi->s_groups_count + flex_size - 1) >>
+	n_fbg_groups = (ngroups + flex_size - 1) >>
 		sbi->s_log_groups_per_flex;
 
 find_close_to_parent:
@@ -404,7 +401,7 @@ find_close_to_parent:
 found_flexbg:
 	for (i = best_flex * flex_size; i < ngroups &&
 		     i < (best_flex + 1) * flex_size; i++) {
-		desc = ext4_get_group_desc(sb, i, &bh);
+		desc = ext4_get_group_desc(sb, i, NULL);
 		if (ext4_free_inodes_count(sb, desc)) {
 			*best_group = i;
 			goto out;
@@ -478,20 +475,21 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 {
 	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	ext4_group_t ngroups = sbi->s_groups_count;
+	ext4_group_t real_ngroups = ext4_get_groups_count(sb);
 	int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
 	unsigned int freei, avefreei;
 	ext4_fsblk_t freeb, avefreeb;
 	unsigned int ndirs;
 	int max_dirs, min_inodes;
 	ext4_grpblk_t min_blocks;
-	ext4_group_t i, grp, g;
+	ext4_group_t i, grp, g, ngroups;
 	struct ext4_group_desc *desc;
 	struct orlov_stats stats;
 	int flex_size = ext4_flex_bg_size(sbi);
 
+	ngroups = real_ngroups;
 	if (flex_size > 1) {
-		ngroups = (ngroups + flex_size - 1) >>
+		ngroups = (real_ngroups + flex_size - 1) >>
 			sbi->s_log_groups_per_flex;
 		parent_group >>= sbi->s_log_groups_per_flex;
 	}
@@ -543,7 +541,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 		 */
 		grp *= flex_size;
 		for (i = 0; i < flex_size; i++) {
-			if (grp+i >= sbi->s_groups_count)
+			if (grp+i >= real_ngroups)
 				break;
 			desc = ext4_get_group_desc(sb, grp+i, NULL);
 			if (desc && ext4_free_inodes_count(sb, desc)) {
@@ -583,7 +581,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 	}
 
 fallback:
-	ngroups = sbi->s_groups_count;
+	ngroups = real_ngroups;
 	avefreei = freei / ngroups;
 fallback_retry:
 	parent_group = EXT4_I(parent)->i_block_group;
@@ -613,9 +611,8 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
 			    ext4_group_t *group, int mode)
 {
 	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
-	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+	ext4_group_t i, last, ngroups = ext4_get_groups_count(sb);
 	struct ext4_group_desc *desc;
-	ext4_group_t i, last;
 	int flex_size = ext4_flex_bg_size(EXT4_SB(sb));
 
 	/*
@@ -708,10 +705,10 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
 
 /*
  * claim the inode from the inode bitmap. If the group
- * is uninit we need to take the groups's sb_bgl_lock
+ * is uninit we need to take the groups's ext4_group_lock
  * and clear the uninit flag. The inode bitmap update
  * and group desc uninit flag clear should be done
- * after holding sb_bgl_lock so that ext4_read_inode_bitmap
+ * after holding ext4_group_lock so that ext4_read_inode_bitmap
  * doesn't race with the ext4_claim_inode
  */
 static int ext4_claim_inode(struct super_block *sb,
@@ -722,7 +719,7 @@ static int ext4_claim_inode(struct super_block *sb,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
 
-	spin_lock(sb_bgl_lock(sbi, group));
+	ext4_lock_group(sb, group);
 	if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) {
 		/* not a free inode */
 		retval = 1;
@@ -731,7 +728,7 @@ static int ext4_claim_inode(struct super_block *sb,
 	ino++;
 	if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
 			ino > EXT4_INODES_PER_GROUP(sb)) {
-		spin_unlock(sb_bgl_lock(sbi, group));
+		ext4_unlock_group(sb, group);
 		ext4_error(sb, __func__,
 			   "reserved inode or inode > inodes count - "
 			   "block_group = %u, inode=%lu", group,
@@ -780,7 +777,7 @@ static int ext4_claim_inode(struct super_block *sb,
 	}
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
 err_ret:
-	spin_unlock(sb_bgl_lock(sbi, group));
+	ext4_unlock_group(sb, group);
 	return retval;
 }
 
@@ -799,11 +796,10 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
 	struct super_block *sb;
 	struct buffer_head *inode_bitmap_bh = NULL;
 	struct buffer_head *group_desc_bh;
-	ext4_group_t group = 0;
+	ext4_group_t ngroups, group = 0;
 	unsigned long ino = 0;
 	struct inode *inode;
 	struct ext4_group_desc *gdp = NULL;
-	struct ext4_super_block *es;
 	struct ext4_inode_info *ei;
 	struct ext4_sb_info *sbi;
 	int ret2, err = 0;
@@ -818,15 +814,14 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
 		return ERR_PTR(-EPERM);
 
 	sb = dir->i_sb;
+	ngroups = ext4_get_groups_count(sb);
 	trace_mark(ext4_request_inode, "dev %s dir %lu mode %d", sb->s_id,
 		   dir->i_ino, mode);
 	inode = new_inode(sb);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 	ei = EXT4_I(inode);
-
 	sbi = EXT4_SB(sb);
-	es = sbi->s_es;
 
 	if (sbi->s_log_groups_per_flex && test_opt(sb, OLDALLOC)) {
 		ret2 = find_group_flex(sb, dir, &group);
@@ -856,7 +851,7 @@ got_group:
 	if (ret2 == -1)
 		goto out;
 
-	for (i = 0; i < sbi->s_groups_count; i++) {
+	for (i = 0; i < ngroups; i++) {
 		err = -EIO;
 
 		gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
@@ -917,7 +912,7 @@ repeat_in_this_group:
 		 * group descriptor metadata has not yet been updated.
 		 * So we just go onto the next blockgroup.
 		 */
-		if (++group == sbi->s_groups_count)
+		if (++group == ngroups)
 			group = 0;
 	}
 	err = -ENOSPC;
@@ -938,7 +933,7 @@ got:
 		}
 
 		free = 0;
-		spin_lock(sb_bgl_lock(sbi, group));
+		ext4_lock_group(sb, group);
 		/* recheck and clear flag under lock if we still need to */
 		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 			free = ext4_free_blocks_after_init(sb, group, gdp);
@@ -947,7 +942,7 @@ got:
 			gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
 								gdp);
 		}
-		spin_unlock(sb_bgl_lock(sbi, group));
+		ext4_unlock_group(sb, group);
 
 		/* Don't need to dirty bitmap block if we didn't change it */
 		if (free) {
@@ -1158,7 +1153,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
 {
 	unsigned long desc_count;
 	struct ext4_group_desc *gdp;
-	ext4_group_t i;
+	ext4_group_t i, ngroups = ext4_get_groups_count(sb);
 #ifdef EXT4FS_DEBUG
 	struct ext4_super_block *es;
 	unsigned long bitmap_count, x;
@@ -1168,7 +1163,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
 	desc_count = 0;
 	bitmap_count = 0;
 	gdp = NULL;
-	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+	for (i = 0; i < ngroups; i++) {
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
@@ -1190,7 +1185,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
 	return desc_count;
 #else
 	desc_count = 0;
-	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+	for (i = 0; i < ngroups; i++) {
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
@@ -1205,9 +1200,9 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
 unsigned long ext4_count_dirs(struct super_block * sb)
 {
 	unsigned long count = 0;
-	ext4_group_t i;
+	ext4_group_t i, ngroups = ext4_get_groups_count(sb);
 
-	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+	for (i = 0; i < ngroups; i++) {
 		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;

fs/ext4/mballoc.c

@@ -372,24 +372,12 @@ static inline void mb_set_bit(int bit, void *addr)
 	ext4_set_bit(bit, addr);
 }
 
-static inline void mb_set_bit_atomic(spinlock_t *lock, int bit, void *addr)
-{
-	addr = mb_correct_addr_and_bit(&bit, addr);
-	ext4_set_bit_atomic(lock, bit, addr);
-}
-
 static inline void mb_clear_bit(int bit, void *addr)
 {
 	addr = mb_correct_addr_and_bit(&bit, addr);
 	ext4_clear_bit(bit, addr);
 }
 
-static inline void mb_clear_bit_atomic(spinlock_t *lock, int bit, void *addr)
-{
-	addr = mb_correct_addr_and_bit(&bit, addr);
-	ext4_clear_bit_atomic(lock, bit, addr);
-}
-
 static inline int mb_find_next_zero_bit(void *addr, int max, int start)
 {
 	int fix = 0, ret, tmpmax;
@@ -448,7 +436,7 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b,
 
 	if (unlikely(e4b->bd_info->bb_bitmap == NULL))
 		return;
-	BUG_ON(!ext4_is_group_locked(sb, e4b->bd_group));
+	assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
 	for (i = 0; i < count; i++) {
 		if (!mb_test_bit(first + i, e4b->bd_info->bb_bitmap)) {
 			ext4_fsblk_t blocknr;
@@ -472,7 +460,7 @@ static void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count)
 
 	if (unlikely(e4b->bd_info->bb_bitmap == NULL))
 		return;
-	BUG_ON(!ext4_is_group_locked(e4b->bd_sb, e4b->bd_group));
+	assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
 	for (i = 0; i < count; i++) {
 		BUG_ON(mb_test_bit(first + i, e4b->bd_info->bb_bitmap));
 		mb_set_bit(first + i, e4b->bd_info->bb_bitmap);
@@ -739,6 +727,7 @@ static void ext4_mb_generate_buddy(struct super_block *sb,
 
 static int ext4_mb_init_cache(struct page *page, char *incore)
 {
+	ext4_group_t ngroups;
 	int blocksize;
 	int blocks_per_page;
 	int groups_per_page;
@@ -757,6 +746,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 
 	inode = page->mapping->host;
 	sb = inode->i_sb;
+	ngroups = ext4_get_groups_count(sb);
 	blocksize = 1 << inode->i_blkbits;
 	blocks_per_page = PAGE_CACHE_SIZE / blocksize;
 
@@ -780,7 +770,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 	for (i = 0; i < groups_per_page; i++) {
 		struct ext4_group_desc *desc;
 
-		if (first_group + i >= EXT4_SB(sb)->s_groups_count)
+		if (first_group + i >= ngroups)
 			break;
 
 		err = -EIO;
@@ -801,17 +791,17 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 			unlock_buffer(bh[i]);
 			continue;
 		}
-		spin_lock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
+		ext4_lock_group(sb, first_group + i);
 		if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 			ext4_init_block_bitmap(sb, bh[i],
 						first_group + i, desc);
 			set_bitmap_uptodate(bh[i]);
 			set_buffer_uptodate(bh[i]);
-			spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
+			ext4_unlock_group(sb, first_group + i);
 			unlock_buffer(bh[i]);
 			continue;
 		}
-		spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
+		ext4_unlock_group(sb, first_group + i);
 		if (buffer_uptodate(bh[i])) {
 			/*
 			 * if not uninit if bh is uptodate,
@@ -852,7 +842,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 		struct ext4_group_info *grinfo;
 
 		group = (first_block + i) >> 1;
-		if (group >= EXT4_SB(sb)->s_groups_count)
+		if (group >= ngroups)
 			break;
 
 		/*
@@ -1078,7 +1068,7 @@ static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
 	return 0;
 }
 
-static void mb_clear_bits(spinlock_t *lock, void *bm, int cur, int len)
+static void mb_clear_bits(void *bm, int cur, int len)
 {
 	__u32 *addr;
 
@@ -1091,15 +1081,12 @@ static void mb_clear_bits(spinlock_t *lock, void *bm, int cur, int len)
 			cur += 32;
 			continue;
 		}
-		if (lock)
-			mb_clear_bit_atomic(lock, cur, bm);
-		else
-			mb_clear_bit(cur, bm);
+		mb_clear_bit(cur, bm);
 		cur++;
 	}
 }
 
-static void mb_set_bits(spinlock_t *lock, void *bm, int cur, int len)
+static void mb_set_bits(void *bm, int cur, int len)
 {
 	__u32 *addr;
 
@@ -1112,10 +1099,7 @@ static void mb_set_bits(spinlock_t *lock, void *bm, int cur, int len)
 			cur += 32;
 			continue;
 		}
-		if (lock)
-			mb_set_bit_atomic(lock, cur, bm);
-		else
-			mb_set_bit(cur, bm);
+		mb_set_bit(cur, bm);
 		cur++;
 	}
 }
@@ -1131,7 +1115,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 	struct super_block *sb = e4b->bd_sb;
 
 	BUG_ON(first + count > (sb->s_blocksize << 3));
-	BUG_ON(!ext4_is_group_locked(sb, e4b->bd_group));
+	assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
 	mb_check_buddy(e4b);
 	mb_free_blocks_double(inode, e4b, first, count);
 
@@ -1212,7 +1196,7 @@ static int mb_find_extent(struct ext4_buddy *e4b, int order, int block,
 	int ord;
 	void *buddy;
 
-	BUG_ON(!ext4_is_group_locked(e4b->bd_sb, e4b->bd_group));
+	assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
 	BUG_ON(ex == NULL);
 
 	buddy = mb_find_buddy(e4b, order, &max);
@@ -1276,7 +1260,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
 
 	BUG_ON(start + len > (e4b->bd_sb->s_blocksize << 3));
 	BUG_ON(e4b->bd_group != ex->fe_group);
-	BUG_ON(!ext4_is_group_locked(e4b->bd_sb, e4b->bd_group));
+	assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
 	mb_check_buddy(e4b);
 	mb_mark_used_double(e4b, start, len);
 
@@ -1330,8 +1314,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
 		e4b->bd_info->bb_counters[ord]++;
 	}
 
-	mb_set_bits(sb_bgl_lock(EXT4_SB(e4b->bd_sb), ex->fe_group),
-			EXT4_MB_BITMAP(e4b), ex->fe_start, len0);
+	mb_set_bits(EXT4_MB_BITMAP(e4b), ex->fe_start, len0);
 	mb_check_buddy(e4b);
 
 	return ret;
@@ -1726,7 +1709,6 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac,
 	unsigned free, fragments;
 	unsigned i, bits;
 	int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb));
-	struct ext4_group_desc *desc;
 	struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group);
 
 	BUG_ON(cr < 0 || cr >= 4);
@@ -1742,10 +1724,6 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac,
 	switch (cr) {
 	case 0:
 		BUG_ON(ac->ac_2order == 0);
-		/* If this group is uninitialized, skip it initially */
-		desc = ext4_get_group_desc(ac->ac_sb, group, NULL);
-		if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))
-			return 0;
 
 		/* Avoid using the first bg of a flexgroup for data files */
 		if ((ac->ac_flags & EXT4_MB_HINT_DATA) &&
@@ -1788,6 +1766,7 @@ int ext4_mb_get_buddy_cache_lock(struct super_block *sb, ext4_group_t group)
 	int block, pnum;
 	int blocks_per_page;
 	int groups_per_page;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	ext4_group_t first_group;
 	struct ext4_group_info *grp;
 
@@ -1807,7 +1786,7 @@ int ext4_mb_get_buddy_cache_lock(struct super_block *sb, ext4_group_t group)
 	/* read all groups the page covers into the cache */
 	for (i = 0; i < groups_per_page; i++) {
 
-		if ((first_group + i) >= EXT4_SB(sb)->s_groups_count)
+		if ((first_group + i) >= ngroups)
 			break;
 		grp = ext4_get_group_info(sb, first_group + i);
 		/* take all groups write allocation
@@ -1945,8 +1924,7 @@ err:
 static noinline_for_stack int
 ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 {
-	ext4_group_t group;
-	ext4_group_t i;
+	ext4_group_t ngroups, group, i;
 	int cr;
 	int err = 0;
 	int bsbits;
@@ -1957,6 +1935,7 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 
 	sb = ac->ac_sb;
 	sbi = EXT4_SB(sb);
+	ngroups = ext4_get_groups_count(sb);
 	BUG_ON(ac->ac_status == AC_STATUS_FOUND);
 
 	/* first, try the goal */
@@ -2017,11 +1996,11 @@ repeat:
 		 */
 		group = ac->ac_g_ex.fe_group;
 
-		for (i = 0; i < EXT4_SB(sb)->s_groups_count; group++, i++) {
+		for (i = 0; i < ngroups; group++, i++) {
 			struct ext4_group_info *grp;
 			struct ext4_group_desc *desc;
 
-			if (group == EXT4_SB(sb)->s_groups_count)
+			if (group == ngroups)
 				group = 0;
 
 			/* quick check to skip empty groups */
@@ -2064,9 +2043,7 @@ repeat:
 
 			ac->ac_groups_scanned++;
 			desc = ext4_get_group_desc(sb, group, NULL);
-			if (cr == 0 || (desc->bg_flags &
-					cpu_to_le16(EXT4_BG_BLOCK_UNINIT) &&
-					ac->ac_2order != 0))
+			if (cr == 0)
 				ext4_mb_simple_scan_group(ac, &e4b);
 			else if (cr == 1 &&
 					ac->ac_g_ex.fe_len == sbi->s_stripe)
@@ -2315,12 +2292,10 @@ static struct file_operations ext4_mb_seq_history_fops = {
 static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos)
 {
 	struct super_block *sb = seq->private;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_group_t group;
 
-	if (*pos < 0 || *pos >= sbi->s_groups_count)
+	if (*pos < 0 || *pos >= ext4_get_groups_count(sb))
 		return NULL;
-
 	group = *pos + 1;
 	return (void *) ((unsigned long) group);
 }
@@ -2328,11 +2303,10 @@ static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos)
 static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct super_block *sb = seq->private;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_group_t group;
 
 	++*pos;
-	if (*pos < 0 || *pos >= sbi->s_groups_count)
+	if (*pos < 0 || *pos >= ext4_get_groups_count(sb))
 		return NULL;
 	group = *pos + 1;
 	return (void *) ((unsigned long) group);
@@ -2420,7 +2394,8 @@ static void ext4_mb_history_release(struct super_block *sb)
 
 	if (sbi->s_proc != NULL) {
 		remove_proc_entry("mb_groups", sbi->s_proc);
-		remove_proc_entry("mb_history", sbi->s_proc);
+		if (sbi->s_mb_history_max)
+			remove_proc_entry("mb_history", sbi->s_proc);
 	}
 	kfree(sbi->s_mb_history);
 }
@@ -2431,17 +2406,17 @@ static void ext4_mb_history_init(struct super_block *sb)
 	int i;
 
 	if (sbi->s_proc != NULL) {
-		proc_create_data("mb_history", S_IRUGO, sbi->s_proc,
-				 &ext4_mb_seq_history_fops, sb);
+		if (sbi->s_mb_history_max)
+			proc_create_data("mb_history", S_IRUGO, sbi->s_proc,
+					 &ext4_mb_seq_history_fops, sb);
 		proc_create_data("mb_groups", S_IRUGO, sbi->s_proc,
 				 &ext4_mb_seq_groups_fops, sb);
 	}
 
-	sbi->s_mb_history_max = 1000;
 	sbi->s_mb_history_cur = 0;
 	spin_lock_init(&sbi->s_mb_history_lock);
 	i = sbi->s_mb_history_max * sizeof(struct ext4_mb_history);
-	sbi->s_mb_history = kzalloc(i, GFP_KERNEL);
+	sbi->s_mb_history = i ? kzalloc(i, GFP_KERNEL) : NULL;
 	/* if we can't allocate history, then we simple won't use it */
 }
 
@@ -2451,7 +2426,7 @@ ext4_mb_store_history(struct ext4_allocation_context *ac)
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_mb_history h;
 
-	if (unlikely(sbi->s_mb_history == NULL))
+	if (sbi->s_mb_history == NULL)
 		return;
 
 	if (!(ac->ac_op & sbi->s_mb_history_filter))
@@ -2587,6 +2562,7 @@ void ext4_mb_update_group_info(struct ext4_group_info *grp, ext4_grpblk_t add)
 
 static int ext4_mb_init_backend(struct super_block *sb)
 {
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	ext4_group_t i;
 	int metalen;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -2598,7 +2574,7 @@ static int ext4_mb_init_backend(struct super_block *sb)
 	struct ext4_group_desc *desc;
 
 	/* This is the number of blocks used by GDT */
-	num_meta_group_infos = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) -
+	num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) -
 				1) >> EXT4_DESC_PER_BLOCK_BITS(sb);
 
 	/*
@@ -2644,7 +2620,7 @@ static int ext4_mb_init_backend(struct super_block *sb)
 	for (i = 0; i < num_meta_group_infos; i++) {
 		if ((i + 1) == num_meta_group_infos)
 			metalen = sizeof(*meta_group_info) *
-				(sbi->s_groups_count -
+				(ngroups -
 					(i << EXT4_DESC_PER_BLOCK_BITS(sb)));
 		meta_group_info = kmalloc(metalen, GFP_KERNEL);
 		if (meta_group_info == NULL) {
@@ -2655,7 +2631,7 @@ static int ext4_mb_init_backend(struct super_block *sb)
 		sbi->s_group_info[i] = meta_group_info;
 	}
 
-	for (i = 0; i < sbi->s_groups_count; i++) {
+	for (i = 0; i < ngroups; i++) {
 		desc = ext4_get_group_desc(sb, i, NULL);
 		if (desc == NULL) {
 			printk(KERN_ERR
@@ -2761,7 +2737,7 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 	return 0;
 }
 
-/* need to called with ext4 group lock (ext4_lock_group) */
+/* need to called with the ext4 group lock held */
 static void ext4_mb_cleanup_pa(struct ext4_group_info *grp)
 {
 	struct ext4_prealloc_space *pa;
@@ -2781,13 +2757,14 @@ static void ext4_mb_cleanup_pa(struct ext4_group_info *grp)
 
 int ext4_mb_release(struct super_block *sb)
 {
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	ext4_group_t i;
 	int num_meta_group_infos;
 	struct ext4_group_info *grinfo;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (sbi->s_group_info) {
-		for (i = 0; i < sbi->s_groups_count; i++) {
+		for (i = 0; i < ngroups; i++) {
 			grinfo = ext4_get_group_info(sb, i);
 #ifdef DOUBLE_CHECK
 			kfree(grinfo->bb_bitmap);
@@ -2797,7 +2774,7 @@ int ext4_mb_release(struct super_block *sb)
 			ext4_unlock_group(sb, i);
 			kfree(grinfo);
 		}
-		num_meta_group_infos = (sbi->s_groups_count +
+		num_meta_group_infos = (ngroups +
 				EXT4_DESC_PER_BLOCK(sb) - 1) >>
 			EXT4_DESC_PER_BLOCK_BITS(sb);
 		for (i = 0; i < num_meta_group_infos; i++)
@@ -2984,27 +2961,25 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 		+ le32_to_cpu(es->s_first_data_block);
 
 	len = ac->ac_b_ex.fe_len;
-	if (in_range(ext4_block_bitmap(sb, gdp), block, len) ||
-	    in_range(ext4_inode_bitmap(sb, gdp), block, len) ||
-	    in_range(block, ext4_inode_table(sb, gdp),
-		     EXT4_SB(sb)->s_itb_per_group) ||
-	    in_range(block + len - 1, ext4_inode_table(sb, gdp),
-		     EXT4_SB(sb)->s_itb_per_group)) {
+	if (!ext4_data_block_valid(sbi, block, len)) {
 		ext4_error(sb, __func__,
-			   "Allocating block %llu in system zone of %d group\n",
-			   block, ac->ac_b_ex.fe_group);
+			   "Allocating blocks %llu-%llu which overlap "
+			   "fs metadata\n", block, block+len);
 		/* File system mounted not to panic on error
 		 * Fix the bitmap and repeat the block allocation
 		 * We leak some of the blocks here.
 		 */
-		mb_set_bits(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group),
-				bitmap_bh->b_data, ac->ac_b_ex.fe_start,
-				ac->ac_b_ex.fe_len);
+		ext4_lock_group(sb, ac->ac_b_ex.fe_group);
+		mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
+			    ac->ac_b_ex.fe_len);
+		ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
 		err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
 		if (!err)
 			err = -EAGAIN;
 		goto out_err;
 	}
+
+	ext4_lock_group(sb, ac->ac_b_ex.fe_group);
 #ifdef AGGRESSIVE_CHECK
 	{
 		int i;
@@ -3014,9 +2989,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 		}
 	}
 #endif
-	spin_lock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group));
-	mb_set_bits(NULL, bitmap_bh->b_data,
-				ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len);
+	mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,ac->ac_b_ex.fe_len);
 	if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 		gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
 		ext4_free_blks_set(sb, gdp,
@@ -3026,7 +2999,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	len = ext4_free_blks_count(sb, gdp) - ac->ac_b_ex.fe_len;
 	ext4_free_blks_set(sb, gdp, len);
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp);
-	spin_unlock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group));
+
+	ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
 	percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len);
 	/*
 	 * Now reduce the dirty block count also. Should not go negative
@@ -3459,7 +3433,7 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
  * the function goes through all block freed in the group
  * but not yet committed and marks them used in in-core bitmap.
  * buddy must be generated from this bitmap
- * Need to be called with ext4 group lock (ext4_lock_group)
+ * Need to be called with the ext4 group lock held
  */
 static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
 						ext4_group_t group)
@@ -3473,9 +3447,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
 
 	while (n) {
 		entry = rb_entry(n, struct ext4_free_data, node);
-		mb_set_bits(sb_bgl_lock(EXT4_SB(sb), group),
-				bitmap, entry->start_blk,
-				entry->count);
+		mb_set_bits(bitmap, entry->start_blk, entry->count);
 		n = rb_next(n);
 	}
 	return;
@@ -3484,7 +3456,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
 /*
  * the function goes through all preallocation in this group and marks them
  * used in in-core bitmap. buddy must be generated from this bitmap
- * Need to be called with ext4 group lock (ext4_lock_group)
+ * Need to be called with ext4 group lock held
  */
 static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 					ext4_group_t group)
@@ -3516,8 +3488,7 @@ static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 		if (unlikely(len == 0))
 			continue;
 		BUG_ON(groupnr != group);
-		mb_set_bits(sb_bgl_lock(EXT4_SB(sb), group),
-						bitmap, start, len);
+		mb_set_bits(bitmap, start, len);
 		preallocated += len;
 		count++;
 	}
@@ -4121,7 +4092,7 @@ static void ext4_mb_return_to_preallocation(struct inode *inode,
 static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
 {
 	struct super_block *sb = ac->ac_sb;
-	ext4_group_t i;
+	ext4_group_t ngroups, i;
 
 	printk(KERN_ERR "EXT4-fs: Can't allocate:"
 			" Allocation context details:\n");
@@ -4145,7 +4116,8 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
 	printk(KERN_ERR "EXT4-fs: %lu scanned, %d found\n", ac->ac_ex_scanned,
 		ac->ac_found);
 	printk(KERN_ERR "EXT4-fs: groups: \n");
-	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+	ngroups = ext4_get_groups_count(sb);
+	for (i = 0; i < ngroups; i++) {
 		struct ext4_group_info *grp = ext4_get_group_info(sb, i);
 		struct ext4_prealloc_space *pa;
 		ext4_grpblk_t start;
@@ -4469,13 +4441,13 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 
 static int ext4_mb_discard_preallocations(struct super_block *sb, int needed)
 {
-	ext4_group_t i;
+	ext4_group_t i, ngroups = ext4_get_groups_count(sb);
 	int ret;
 	int freed = 0;
 
 	trace_mark(ext4_mb_discard_preallocations, "dev %s needed %d",
 		   sb->s_id, needed);
-	for (i = 0; i < EXT4_SB(sb)->s_groups_count && needed > 0; i++) {
+	for (i = 0; i < ngroups && needed > 0; i++) {
 		ret = ext4_mb_discard_group_preallocations(sb, i, needed);
 		freed += ret;
 		needed -= ret;
@@ -4859,29 +4831,25 @@ do_more:
 		new_entry->group  = block_group;
 		new_entry->count = count;
 		new_entry->t_tid = handle->h_transaction->t_tid;
+
 		ext4_lock_group(sb, block_group);
-		mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data,
-				bit, count);
+		mb_clear_bits(bitmap_bh->b_data, bit, count);
 		ext4_mb_free_metadata(handle, &e4b, new_entry);
-		ext4_unlock_group(sb, block_group);
 	} else {
-		ext4_lock_group(sb, block_group);
 		/* need to update group_info->bb_free and bitmap
 		 * with group lock held. generate_buddy look at
 		 * them with group lock_held
 		 */
-		mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data,
-				bit, count);
+		ext4_lock_group(sb, block_group);
+		mb_clear_bits(bitmap_bh->b_data, bit, count);
 		mb_free_blocks(inode, &e4b, bit, count);
 		ext4_mb_return_to_preallocation(inode, &e4b, block, count);
-		ext4_unlock_group(sb, block_group);
 	}
 
-	spin_lock(sb_bgl_lock(sbi, block_group));
 	ret = ext4_free_blks_count(sb, gdp) + count;
 	ext4_free_blks_set(sb, gdp, ret);
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp);
-	spin_unlock(sb_bgl_lock(sbi, block_group));
+	ext4_unlock_group(sb, block_group);
 	percpu_counter_add(&sbi->s_freeblocks_counter, count);
 
 	if (sbi->s_log_groups_per_flex) {

fs/ext4/mballoc.h

@@ -23,7 +23,6 @@
 #include <linux/mutex.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
-#include "group.h"
 
 /*
  * with AGGRESSIVE_CHECK allocator runs consistency checks over

fs/ext4/namei.c

@@ -37,7 +37,6 @@
 #include "ext4.h"
 #include "ext4_jbd2.h"
 
-#include "namei.h"
 #include "xattr.h"
 #include "acl.h"
 
@@ -750,7 +749,7 @@ static int dx_make_map(struct ext4_dir_entry_2 *de, unsigned blocksize,
 			ext4fs_dirhash(de->name, de->name_len, &h);
 			map_tail--;
 			map_tail->hash = h.hash;
-			map_tail->offs = (u16) ((char *) de - base);
+			map_tail->offs = ((char *) de - base)>>2;
 			map_tail->size = le16_to_cpu(de->rec_len);
 			count++;
 			cond_resched();
@@ -1148,7 +1147,8 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count,
 	unsigned rec_len = 0;
 
 	while (count--) {
-		struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) (from + map->offs);
+		struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) 
+						(from + (map->offs<<2));
 		rec_len = EXT4_DIR_REC_LEN(de->name_len);
 		memcpy (to, de, rec_len);
 		((struct ext4_dir_entry_2 *) to)->rec_len =
@@ -1997,7 +1997,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 	if (!ext4_handle_valid(handle))
 		return 0;
 
-	lock_super(sb);
+	mutex_lock(&EXT4_SB(sb)->s_orphan_lock);
 	if (!list_empty(&EXT4_I(inode)->i_orphan))
 		goto out_unlock;
 
@@ -2006,9 +2006,13 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 
 	/* @@@ FIXME: Observation from aviro:
 	 * I think I can trigger J_ASSERT in ext4_orphan_add().  We block
-	 * here (on lock_super()), so race with ext4_link() which might bump
+	 * here (on s_orphan_lock), so race with ext4_link() which might bump
 	 * ->i_nlink. For, say it, character device. Not a regular file,
 	 * not a directory, not a symlink and ->i_nlink > 0.
+	 *
+	 * tytso, 4/25/2009: I'm not sure how that could happen;
+	 * shouldn't the fs core protect us from these sort of
+	 * unlink()/link() races?
 	 */
 	J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 		  S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
@@ -2045,7 +2049,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 	jbd_debug(4, "orphan inode %lu will point to %d\n",
 			inode->i_ino, NEXT_ORPHAN(inode));
 out_unlock:
-	unlock_super(sb);
+	mutex_unlock(&EXT4_SB(sb)->s_orphan_lock);
 	ext4_std_error(inode->i_sb, err);
 	return err;
 }
@@ -2066,11 +2070,9 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
 	if (!ext4_handle_valid(handle))
 		return 0;
 
-	lock_super(inode->i_sb);
-	if (list_empty(&ei->i_orphan)) {
-		unlock_super(inode->i_sb);
-		return 0;
-	}
+	mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
+	if (list_empty(&ei->i_orphan))
+		goto out;
 
 	ino_next = NEXT_ORPHAN(inode);
 	prev = ei->i_orphan.prev;
@@ -2120,7 +2122,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
 out_err:
 	ext4_std_error(inode->i_sb, err);
 out:
-	unlock_super(inode->i_sb);
+	mutex_unlock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
 	return err;
 
 out_brelse:
@@ -2533,6 +2535,7 @@ const struct inode_operations ext4_dir_inode_operations = {
 	.removexattr	= generic_removexattr,
 #endif
 	.permission	= ext4_permission,
+	.fiemap         = ext4_fiemap,
 };
 
 const struct inode_operations ext4_special_inode_operations = {

fs/ext4/namei.h

@@ -1,8 +0,0 @@
-/*  linux/fs/ext4/namei.h
- *
- * Copyright (C) 2005 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
-*/
-
-extern struct dentry *ext4_get_parent(struct dentry *child);

fs/ext4/resize.c

@@ -15,7 +15,6 @@
 #include <linux/slab.h>
 
 #include "ext4_jbd2.h"
-#include "group.h"
 
 #define outside(b, first, last)	((b) < (first) || (b) >= (last))
 #define inside(b, first, last)	((b) >= (first) && (b) < (last))
@@ -193,7 +192,7 @@ static int setup_new_group_blocks(struct super_block *sb,
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
-	lock_super(sb);
+	mutex_lock(&sbi->s_resize_lock);
 	if (input->group != sbi->s_groups_count) {
 		err = -EBUSY;
 		goto exit_journal;
@@ -302,7 +301,7 @@ exit_bh:
 	brelse(bh);
 
 exit_journal:
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_resize_lock);
 	if ((err2 = ext4_journal_stop(handle)) && !err)
 		err = err2;
 
@@ -643,11 +642,12 @@ exit_free:
  * important part is that the new block and inode counts are in the backup
  * superblocks, and the location of the new group metadata in the GDT backups.
  *
- * We do not need lock_super() for this, because these blocks are not
- * otherwise touched by the filesystem code when it is mounted.  We don't
- * need to worry about last changing from sbi->s_groups_count, because the
- * worst that can happen is that we do not copy the full number of backups
- * at this time.  The resize which changed s_groups_count will backup again.
+ * We do not need take the s_resize_lock for this, because these
+ * blocks are not otherwise touched by the filesystem code when it is
+ * mounted.  We don't need to worry about last changing from
+ * sbi->s_groups_count, because the worst that can happen is that we
+ * do not copy the full number of backups at this time.  The resize
+ * which changed s_groups_count will backup again.
  */
 static void update_backups(struct super_block *sb,
 			   int blk_off, char *data, int size)
@@ -809,7 +809,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 		goto exit_put;
 	}
 
-	lock_super(sb);
+	mutex_lock(&sbi->s_resize_lock);
 	if (input->group != sbi->s_groups_count) {
 		ext4_warning(sb, __func__,
 			     "multiple resizers run on filesystem!");
@@ -840,7 +840,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
         /*
          * OK, now we've set up the new group.  Time to make it active.
          *
-         * Current kernels don't lock all allocations via lock_super(),
+         * We do not lock all allocations via s_resize_lock
          * so we have to be safe wrt. concurrent accesses the group
          * data.  So we need to be careful to set all of the relevant
          * group descriptor data etc. *before* we enable the group.
@@ -900,12 +900,12 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 	 *
 	 * The precise rules we use are:
 	 *
-	 * * Writers of s_groups_count *must* hold lock_super
+	 * * Writers of s_groups_count *must* hold s_resize_lock
 	 * AND
 	 * * Writers must perform a smp_wmb() after updating all dependent
 	 *   data and before modifying the groups count
 	 *
-	 * * Readers must hold lock_super() over the access
+	 * * Readers must hold s_resize_lock over the access
 	 * OR
 	 * * Readers must perform an smp_rmb() after reading the groups count
 	 *   and before reading any dependent data.
@@ -948,7 +948,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 	sb->s_dirt = 1;
 
 exit_journal:
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_resize_lock);
 	if ((err2 = ext4_journal_stop(handle)) && !err)
 		err = err2;
 	if (!err) {
@@ -986,7 +986,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 
 	/* We don't need to worry about locking wrt other resizers just
 	 * yet: we're going to revalidate es->s_blocks_count after
-	 * taking lock_super() below. */
+	 * taking the s_resize_lock below. */
 	o_blocks_count = ext4_blocks_count(es);
 	o_groups_count = EXT4_SB(sb)->s_groups_count;
 
@@ -1056,11 +1056,11 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 		goto exit_put;
 	}
 
-	lock_super(sb);
+	mutex_lock(&EXT4_SB(sb)->s_resize_lock);
 	if (o_blocks_count != ext4_blocks_count(es)) {
 		ext4_warning(sb, __func__,
 			     "multiple resizers run on filesystem!");
-		unlock_super(sb);
+		mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
 		ext4_journal_stop(handle);
 		err = -EBUSY;
 		goto exit_put;
@@ -1070,14 +1070,14 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 						 EXT4_SB(sb)->s_sbh))) {
 		ext4_warning(sb, __func__,
 			     "error %d on journal write access", err);
-		unlock_super(sb);
+		mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
 		ext4_journal_stop(handle);
 		goto exit_put;
 	}
 	ext4_blocks_count_set(es, o_blocks_count + add);
 	ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
 	sb->s_dirt = 1;
-	unlock_super(sb);
+	mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
 	ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
 		   o_blocks_count + add);
 	/* We add the blocks to the bitmap and set the group need init bit */

fs/ioctl.c

@@ -414,10 +414,6 @@ static int file_ioctl(struct file *filp, unsigned int cmd,
 	switch (cmd) {
 	case FIBMAP:
 		return ioctl_fibmap(filp, p);
-	case FS_IOC_FIEMAP:
-		return ioctl_fiemap(filp, arg);
-	case FIGETBSZ:
-		return put_user(inode->i_sb->s_blocksize, p);
 	case FIONREAD:
 		return put_user(i_size_read(inode) - filp->f_pos, p);
 	}
@@ -557,6 +553,16 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 		error = ioctl_fsthaw(filp);
 		break;
 
+	case FS_IOC_FIEMAP:
+		return ioctl_fiemap(filp, arg);
+
+	case FIGETBSZ:
+	{
+		struct inode *inode = filp->f_path.dentry->d_inode;
+		int __user *p = (int __user *)arg;
+		return put_user(inode->i_sb->s_blocksize, p);
+	}
+
 	default:
 		if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
 			error = file_ioctl(filp, cmd, arg);

fs/jbd2/journal.c

@@ -1781,7 +1781,7 @@ int jbd2_journal_wipe(journal_t *journal, int write)
  * Journal abort has very specific semantics, which we describe
  * for journal abort.
  *
- * Two internal function, which provide abort to te jbd layer
+ * Two internal functions, which provide abort to the jbd layer
  * itself are here.
  */
 
@@ -1879,7 +1879,7 @@ void jbd2_journal_abort(journal_t *journal, int errno)
  * int jbd2_journal_errno () - returns the journal's error state.
  * @journal: journal to examine.
  *
- * This is the errno numbet set with jbd2_journal_abort(), the last
+ * This is the errno number set with jbd2_journal_abort(), the last
  * time the journal was mounted - if the journal was stopped
  * without calling abort this will be 0.
  *
@@ -1903,7 +1903,7 @@ int jbd2_journal_errno(journal_t *journal)
  * int jbd2_journal_clear_err () - clears the journal's error state
  * @journal: journal to act on.
  *
- * An error must be cleared or Acked to take a FS out of readonly
+ * An error must be cleared or acked to take a FS out of readonly
  * mode.
  */
 int jbd2_journal_clear_err(journal_t *journal)
@@ -1923,7 +1923,7 @@ int jbd2_journal_clear_err(journal_t *journal)
  * void jbd2_journal_ack_err() - Ack journal err.
  * @journal: journal to act on.
  *
- * An error must be cleared or Acked to take a FS out of readonly
+ * An error must be cleared or acked to take a FS out of readonly
  * mode.
  */
 void jbd2_journal_ack_err(journal_t *journal)

fs/mpage.c

@@ -379,7 +379,8 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
 
-	clear_buffer_mapped(&map_bh);
+	map_bh.b_state = 0;
+	map_bh.b_size = 0;
 	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
 		struct page *page = list_entry(pages->prev, struct page, lru);
 
@@ -412,7 +413,8 @@ int mpage_readpage(struct page *page, get_block_t get_block)
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
 
-	clear_buffer_mapped(&map_bh);
+	map_bh.b_state = 0;
+	map_bh.b_size = 0;
 	bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio,
 			&map_bh, &first_logical_block, get_block);
 	if (bio)