Linux-2.6.12-rc2

Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!

fs/ext3/Makefile

@@ -0,0 +1,12 @@
+#
+# Makefile for the linux ext3-filesystem routines.
+#
+
+obj-$(CONFIG_EXT3_FS) += ext3.o
+
+ext3-y	:= balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \
+	   ioctl.o namei.o super.o symlink.o hash.o resize.o
+
+ext3-$(CONFIG_EXT3_FS_XATTR)	 += xattr.o xattr_user.o xattr_trusted.o
+ext3-$(CONFIG_EXT3_FS_POSIX_ACL) += acl.o
+ext3-$(CONFIG_EXT3_FS_SECURITY)	 += xattr_security.o

fs/ext3/acl.c

@@ -0,0 +1,547 @@
+/*
+ * linux/fs/ext3/acl.c
+ *
+ * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
+ */
+
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/ext3_jbd.h>
+#include <linux/ext3_fs.h>
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * Convert from filesystem to in-memory representation.
+ */
+static struct posix_acl *
+ext3_acl_from_disk(const void *value, size_t size)
+{
+	const char *end = (char *)value + size;
+	int n, count;
+	struct posix_acl *acl;
+
+	if (!value)
+		return NULL;
+	if (size < sizeof(ext3_acl_header))
+		 return ERR_PTR(-EINVAL);
+	if (((ext3_acl_header *)value)->a_version !=
+	    cpu_to_le32(EXT3_ACL_VERSION))
+		return ERR_PTR(-EINVAL);
+	value = (char *)value + sizeof(ext3_acl_header);
+	count = ext3_acl_count(size);
+	if (count < 0)
+		return ERR_PTR(-EINVAL);
+	if (count == 0)
+		return NULL;
+	acl = posix_acl_alloc(count, GFP_KERNEL);
+	if (!acl)
+		return ERR_PTR(-ENOMEM);
+	for (n=0; n < count; n++) {
+		ext3_acl_entry *entry =
+			(ext3_acl_entry *)value;
+		if ((char *)value + sizeof(ext3_acl_entry_short) > end)
+			goto fail;
+		acl->a_entries[n].e_tag  = le16_to_cpu(entry->e_tag);
+		acl->a_entries[n].e_perm = le16_to_cpu(entry->e_perm);
+		switch(acl->a_entries[n].e_tag) {
+			case ACL_USER_OBJ:
+			case ACL_GROUP_OBJ:
+			case ACL_MASK:
+			case ACL_OTHER:
+				value = (char *)value +
+					sizeof(ext3_acl_entry_short);
+				acl->a_entries[n].e_id = ACL_UNDEFINED_ID;
+				break;
+
+			case ACL_USER:
+			case ACL_GROUP:
+				value = (char *)value + sizeof(ext3_acl_entry);
+				if ((char *)value > end)
+					goto fail;
+				acl->a_entries[n].e_id =
+					le32_to_cpu(entry->e_id);
+				break;
+
+			default:
+				goto fail;
+		}
+	}
+	if (value != end)
+		goto fail;
+	return acl;
+
+fail:
+	posix_acl_release(acl);
+	return ERR_PTR(-EINVAL);
+}
+
+/*
+ * Convert from in-memory to filesystem representation.
+ */
+static void *
+ext3_acl_to_disk(const struct posix_acl *acl, size_t *size)
+{
+	ext3_acl_header *ext_acl;
+	char *e;
+	size_t n;
+
+	*size = ext3_acl_size(acl->a_count);
+	ext_acl = (ext3_acl_header *)kmalloc(sizeof(ext3_acl_header) +
+		acl->a_count * sizeof(ext3_acl_entry), GFP_KERNEL);
+	if (!ext_acl)
+		return ERR_PTR(-ENOMEM);
+	ext_acl->a_version = cpu_to_le32(EXT3_ACL_VERSION);
+	e = (char *)ext_acl + sizeof(ext3_acl_header);
+	for (n=0; n < acl->a_count; n++) {
+		ext3_acl_entry *entry = (ext3_acl_entry *)e;
+		entry->e_tag  = cpu_to_le16(acl->a_entries[n].e_tag);
+		entry->e_perm = cpu_to_le16(acl->a_entries[n].e_perm);
+		switch(acl->a_entries[n].e_tag) {
+			case ACL_USER:
+			case ACL_GROUP:
+				entry->e_id =
+					cpu_to_le32(acl->a_entries[n].e_id);
+				e += sizeof(ext3_acl_entry);
+				break;
+
+			case ACL_USER_OBJ:
+			case ACL_GROUP_OBJ:
+			case ACL_MASK:
+			case ACL_OTHER:
+				e += sizeof(ext3_acl_entry_short);
+				break;
+
+			default:
+				goto fail;
+		}
+	}
+	return (char *)ext_acl;
+
+fail:
+	kfree(ext_acl);
+	return ERR_PTR(-EINVAL);
+}
+
+static inline struct posix_acl *
+ext3_iget_acl(struct inode *inode, struct posix_acl **i_acl)
+{
+	struct posix_acl *acl = EXT3_ACL_NOT_CACHED;
+
+	spin_lock(&inode->i_lock);
+	if (*i_acl != EXT3_ACL_NOT_CACHED)
+		acl = posix_acl_dup(*i_acl);
+	spin_unlock(&inode->i_lock);
+
+	return acl;
+}
+
+static inline void
+ext3_iset_acl(struct inode *inode, struct posix_acl **i_acl,
+                  struct posix_acl *acl)
+{
+	spin_lock(&inode->i_lock);
+	if (*i_acl != EXT3_ACL_NOT_CACHED)
+		posix_acl_release(*i_acl);
+	*i_acl = posix_acl_dup(acl);
+	spin_unlock(&inode->i_lock);
+}
+
+/*
+ * Inode operation get_posix_acl().
+ *
+ * inode->i_sem: don't care
+ */
+static struct posix_acl *
+ext3_get_acl(struct inode *inode, int type)
+{
+	struct ext3_inode_info *ei = EXT3_I(inode);
+	int name_index;
+	char *value = NULL;
+	struct posix_acl *acl;
+	int retval;
+
+	if (!test_opt(inode->i_sb, POSIX_ACL))
+		return NULL;
+
+	switch(type) {
+		case ACL_TYPE_ACCESS:
+			acl = ext3_iget_acl(inode, &ei->i_acl);
+			if (acl != EXT3_ACL_NOT_CACHED)
+				return acl;
+			name_index = EXT3_XATTR_INDEX_POSIX_ACL_ACCESS;
+			break;
+
+		case ACL_TYPE_DEFAULT:
+			acl = ext3_iget_acl(inode, &ei->i_default_acl);
+			if (acl != EXT3_ACL_NOT_CACHED)
+				return acl;
+			name_index = EXT3_XATTR_INDEX_POSIX_ACL_DEFAULT;
+			break;
+
+		default:
+			return ERR_PTR(-EINVAL);
+	}
+	retval = ext3_xattr_get(inode, name_index, "", NULL, 0);
+	if (retval > 0) {
+		value = kmalloc(retval, GFP_KERNEL);
+		if (!value)
+			return ERR_PTR(-ENOMEM);
+		retval = ext3_xattr_get(inode, name_index, "", value, retval);
+	}
+	if (retval > 0)
+		acl = ext3_acl_from_disk(value, retval);
+	else if (retval == -ENODATA || retval == -ENOSYS)
+		acl = NULL;
+	else
+		acl = ERR_PTR(retval);
+	kfree(value);
+
+	if (!IS_ERR(acl)) {
+		switch(type) {
+			case ACL_TYPE_ACCESS:
+				ext3_iset_acl(inode, &ei->i_acl, acl);
+				break;
+
+			case ACL_TYPE_DEFAULT:
+				ext3_iset_acl(inode, &ei->i_default_acl, acl);
+				break;
+		}
+	}
+	return acl;
+}
+
+/*
+ * Set the access or default ACL of an inode.
+ *
+ * inode->i_sem: down unless called from ext3_new_inode
+ */
+static int
+ext3_set_acl(handle_t *handle, struct inode *inode, int type,
+	     struct posix_acl *acl)
+{
+	struct ext3_inode_info *ei = EXT3_I(inode);
+	int name_index;
+	void *value = NULL;
+	size_t size;
+	int error;
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	switch(type) {
+		case ACL_TYPE_ACCESS:
+			name_index = EXT3_XATTR_INDEX_POSIX_ACL_ACCESS;
+			if (acl) {
+				mode_t mode = inode->i_mode;
+				error = posix_acl_equiv_mode(acl, &mode);
+				if (error < 0)
+					return error;
+				else {
+					inode->i_mode = mode;
+					ext3_mark_inode_dirty(handle, inode);
+					if (error == 0)
+						acl = NULL;
+				}
+			}
+			break;
+
+		case ACL_TYPE_DEFAULT:
+			name_index = EXT3_XATTR_INDEX_POSIX_ACL_DEFAULT;
+			if (!S_ISDIR(inode->i_mode))
+				return acl ? -EACCES : 0;
+			break;
+
+		default:
+			return -EINVAL;
+	}
+ 	if (acl) {
+		value = ext3_acl_to_disk(acl, &size);
+		if (IS_ERR(value))
+			return (int)PTR_ERR(value);
+	}
+
+	error = ext3_xattr_set_handle(handle, inode, name_index, "",
+				      value, size, 0);
+
+	kfree(value);
+	if (!error) {
+		switch(type) {
+			case ACL_TYPE_ACCESS:
+				ext3_iset_acl(inode, &ei->i_acl, acl);
+				break;
+
+			case ACL_TYPE_DEFAULT:
+				ext3_iset_acl(inode, &ei->i_default_acl, acl);
+				break;
+		}
+	}
+	return error;
+}
+
+static int
+ext3_check_acl(struct inode *inode, int mask)
+{
+	struct posix_acl *acl = ext3_get_acl(inode, ACL_TYPE_ACCESS);
+
+	if (acl) {
+		int error = posix_acl_permission(inode, acl, mask);
+		posix_acl_release(acl);
+		return error;
+	}
+
+	return -EAGAIN;
+}
+
+int
+ext3_permission(struct inode *inode, int mask, struct nameidata *nd)
+{
+	return generic_permission(inode, mask, ext3_check_acl);
+}
+
+/*
+ * Initialize the ACLs of a new inode. Called from ext3_new_inode.
+ *
+ * dir->i_sem: down
+ * inode->i_sem: up (access to inode is still exclusive)
+ */
+int
+ext3_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
+{
+	struct posix_acl *acl = NULL;
+	int error = 0;
+
+	if (!S_ISLNK(inode->i_mode)) {
+		if (test_opt(dir->i_sb, POSIX_ACL)) {
+			acl = ext3_get_acl(dir, ACL_TYPE_DEFAULT);
+			if (IS_ERR(acl))
+				return PTR_ERR(acl);
+		}
+		if (!acl)
+			inode->i_mode &= ~current->fs->umask;
+	}
+	if (test_opt(inode->i_sb, POSIX_ACL) && acl) {
+		struct posix_acl *clone;
+		mode_t mode;
+
+		if (S_ISDIR(inode->i_mode)) {
+			error = ext3_set_acl(handle, inode,
+					     ACL_TYPE_DEFAULT, acl);
+			if (error)
+				goto cleanup;
+		}
+		clone = posix_acl_clone(acl, GFP_KERNEL);
+		error = -ENOMEM;
+		if (!clone)
+			goto cleanup;
+
+		mode = inode->i_mode;
+		error = posix_acl_create_masq(clone, &mode);
+		if (error >= 0) {
+			inode->i_mode = mode;
+			if (error > 0) {
+				/* This is an extended ACL */
+				error = ext3_set_acl(handle, inode,
+						     ACL_TYPE_ACCESS, clone);
+			}
+		}
+		posix_acl_release(clone);
+	}
+cleanup:
+	posix_acl_release(acl);
+	return error;
+}
+
+/*
+ * Does chmod for an inode that may have an Access Control List. The
+ * inode->i_mode field must be updated to the desired value by the caller
+ * before calling this function.
+ * Returns 0 on success, or a negative error number.
+ *
+ * We change the ACL rather than storing some ACL entries in the file
+ * mode permission bits (which would be more efficient), because that
+ * would break once additional permissions (like  ACL_APPEND, ACL_DELETE
+ * for directories) are added. There are no more bits available in the
+ * file mode.
+ *
+ * inode->i_sem: down
+ */
+int
+ext3_acl_chmod(struct inode *inode)
+{
+	struct posix_acl *acl, *clone;
+        int error;
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+	if (!test_opt(inode->i_sb, POSIX_ACL))
+		return 0;
+	acl = ext3_get_acl(inode, ACL_TYPE_ACCESS);
+	if (IS_ERR(acl) || !acl)
+		return PTR_ERR(acl);
+	clone = posix_acl_clone(acl, GFP_KERNEL);
+	posix_acl_release(acl);
+	if (!clone)
+		return -ENOMEM;
+	error = posix_acl_chmod_masq(clone, inode->i_mode);
+	if (!error) {
+		handle_t *handle;
+		int retries = 0;
+
+	retry:
+		handle = ext3_journal_start(inode, EXT3_DATA_TRANS_BLOCKS);
+		if (IS_ERR(handle)) {
+			error = PTR_ERR(handle);
+			ext3_std_error(inode->i_sb, error);
+			goto out;
+		}
+		error = ext3_set_acl(handle, inode, ACL_TYPE_ACCESS, clone);
+		ext3_journal_stop(handle);
+		if (error == -ENOSPC &&
+		    ext3_should_retry_alloc(inode->i_sb, &retries))
+			goto retry;
+	}
+out:
+	posix_acl_release(clone);
+	return error;
+}
+
+/*
+ * Extended attribute handlers
+ */
+static size_t
+ext3_xattr_list_acl_access(struct inode *inode, char *list, size_t list_len,
+			   const char *name, size_t name_len)
+{
+	const size_t size = sizeof(XATTR_NAME_ACL_ACCESS);
+
+	if (!test_opt(inode->i_sb, POSIX_ACL))
+		return 0;
+	if (list && size <= list_len)
+		memcpy(list, XATTR_NAME_ACL_ACCESS, size);
+	return size;
+}
+
+static size_t
+ext3_xattr_list_acl_default(struct inode *inode, char *list, size_t list_len,
+			    const char *name, size_t name_len)
+{
+	const size_t size = sizeof(XATTR_NAME_ACL_DEFAULT);
+
+	if (!test_opt(inode->i_sb, POSIX_ACL))
+		return 0;
+	if (list && size <= list_len)
+		memcpy(list, XATTR_NAME_ACL_DEFAULT, size);
+	return size;
+}
+
+static int
+ext3_xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size)
+{
+	struct posix_acl *acl;
+	int error;
+
+	if (!test_opt(inode->i_sb, POSIX_ACL))
+		return -EOPNOTSUPP;
+
+	acl = ext3_get_acl(inode, type);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (acl == NULL)
+		return -ENODATA;
+	error = posix_acl_to_xattr(acl, buffer, size);
+	posix_acl_release(acl);
+
+	return error;
+}
+
+static int
+ext3_xattr_get_acl_access(struct inode *inode, const char *name,
+			  void *buffer, size_t size)
+{
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+	return ext3_xattr_get_acl(inode, ACL_TYPE_ACCESS, buffer, size);
+}
+
+static int
+ext3_xattr_get_acl_default(struct inode *inode, const char *name,
+			   void *buffer, size_t size)
+{
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+	return ext3_xattr_get_acl(inode, ACL_TYPE_DEFAULT, buffer, size);
+}
+
+static int
+ext3_xattr_set_acl(struct inode *inode, int type, const void *value,
+		   size_t size)
+{
+	handle_t *handle;
+	struct posix_acl *acl;
+	int error, retries = 0;
+
+	if (!test_opt(inode->i_sb, POSIX_ACL))
+		return -EOPNOTSUPP;
+	if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+		return -EPERM;
+
+	if (value) {
+		acl = posix_acl_from_xattr(value, size);
+		if (IS_ERR(acl))
+			return PTR_ERR(acl);
+		else if (acl) {
+			error = posix_acl_valid(acl);
+			if (error)
+				goto release_and_out;
+		}
+	} else
+		acl = NULL;
+
+retry:
+	handle = ext3_journal_start(inode, EXT3_DATA_TRANS_BLOCKS);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+	error = ext3_set_acl(handle, inode, type, acl);
+	ext3_journal_stop(handle);
+	if (error == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
+		goto retry;
+
+release_and_out:
+	posix_acl_release(acl);
+	return error;
+}
+
+static int
+ext3_xattr_set_acl_access(struct inode *inode, const char *name,
+			  const void *value, size_t size, int flags)
+{
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+	return ext3_xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size);
+}
+
+static int
+ext3_xattr_set_acl_default(struct inode *inode, const char *name,
+			   const void *value, size_t size, int flags)
+{
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+	return ext3_xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size);
+}
+
+struct xattr_handler ext3_xattr_acl_access_handler = {
+	.prefix	= XATTR_NAME_ACL_ACCESS,
+	.list	= ext3_xattr_list_acl_access,
+	.get	= ext3_xattr_get_acl_access,
+	.set	= ext3_xattr_set_acl_access,
+};
+
+struct xattr_handler ext3_xattr_acl_default_handler = {
+	.prefix	= XATTR_NAME_ACL_DEFAULT,
+	.list	= ext3_xattr_list_acl_default,
+	.get	= ext3_xattr_get_acl_default,
+	.set	= ext3_xattr_set_acl_default,
+};

fs/ext3/acl.h

@@ -0,0 +1,84 @@
+/*
+  File: fs/ext3/acl.h
+
+  (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org>
+*/
+
+#include <linux/xattr_acl.h>
+
+#define EXT3_ACL_VERSION	0x0001
+
+typedef struct {
+	__le16		e_tag;
+	__le16		e_perm;
+	__le32		e_id;
+} ext3_acl_entry;
+
+typedef struct {
+	__le16		e_tag;
+	__le16		e_perm;
+} ext3_acl_entry_short;
+
+typedef struct {
+	__le32		a_version;
+} ext3_acl_header;
+
+static inline size_t ext3_acl_size(int count)
+{
+	if (count <= 4) {
+		return sizeof(ext3_acl_header) +
+		       count * sizeof(ext3_acl_entry_short);
+	} else {
+		return sizeof(ext3_acl_header) +
+		       4 * sizeof(ext3_acl_entry_short) +
+		       (count - 4) * sizeof(ext3_acl_entry);
+	}
+}
+
+static inline int ext3_acl_count(size_t size)
+{
+	ssize_t s;
+	size -= sizeof(ext3_acl_header);
+	s = size - 4 * sizeof(ext3_acl_entry_short);
+	if (s < 0) {
+		if (size % sizeof(ext3_acl_entry_short))
+			return -1;
+		return size / sizeof(ext3_acl_entry_short);
+	} else {
+		if (s % sizeof(ext3_acl_entry))
+			return -1;
+		return s / sizeof(ext3_acl_entry) + 4;
+	}
+}
+
+#ifdef CONFIG_EXT3_FS_POSIX_ACL
+
+/* Value for inode->u.ext3_i.i_acl and inode->u.ext3_i.i_default_acl
+   if the ACL has not been cached */
+#define EXT3_ACL_NOT_CACHED ((void *)-1)
+
+/* acl.c */
+extern int ext3_permission (struct inode *, int, struct nameidata *);
+extern int ext3_acl_chmod (struct inode *);
+extern int ext3_init_acl (handle_t *, struct inode *, struct inode *);
+
+extern int init_ext3_acl(void);
+extern void exit_ext3_acl(void);
+
+#else  /* CONFIG_EXT3_FS_POSIX_ACL */
+#include <linux/sched.h>
+#define ext3_permission NULL
+
+static inline int
+ext3_acl_chmod(struct inode *inode)
+{
+	return 0;
+}
+
+static inline int
+ext3_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
+{
+	return 0;
+}
+#endif  /* CONFIG_EXT3_FS_POSIX_ACL */
+

fs/ext3/bitmap.c

@@ -0,0 +1,26 @@
+/*
+ *  linux/fs/ext3/bitmap.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ */
+
+#include <linux/buffer_head.h>
+
+
+static int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
+
+unsigned long ext3_count_free (struct buffer_head * map, unsigned int numchars)
+{
+	unsigned int i;
+	unsigned long sum = 0;
+
+	if (!map) 
+		return (0);
+	for (i = 0; i < numchars; i++)
+		sum += nibblemap[map->b_data[i] & 0xf] +
+			nibblemap[(map->b_data[i] >> 4) & 0xf];
+	return (sum);
+}

fs/ext3/dir.c

@@ -0,0 +1,519 @@
+/*
+ *  linux/fs/ext3/dir.c
+ *
+ * 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/fs/minix/dir.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  ext3 directory handling functions
+ *
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ *
+ * Hash Tree Directory indexing (c) 2001  Daniel Phillips
+ *
+ */
+
+#include <linux/fs.h>
+#include <linux/jbd.h>
+#include <linux/ext3_fs.h>
+#include <linux/buffer_head.h>
+#include <linux/smp_lock.h>
+#include <linux/slab.h>
+#include <linux/rbtree.h>
+
+static unsigned char ext3_filetype_table[] = {
+	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
+};
+
+static int ext3_readdir(struct file *, void *, filldir_t);
+static int ext3_dx_readdir(struct file * filp,
+			   void * dirent, filldir_t filldir);
+static int ext3_release_dir (struct inode * inode,
+				struct file * filp);
+
+struct file_operations ext3_dir_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= generic_read_dir,
+	.readdir	= ext3_readdir,		/* we take BKL. needed?*/
+	.ioctl		= ext3_ioctl,		/* BKL held */
+	.fsync		= ext3_sync_file,	/* BKL held */
+#ifdef CONFIG_EXT3_INDEX
+	.release	= ext3_release_dir,
+#endif
+};
+
+
+static unsigned char get_dtype(struct super_block *sb, int filetype)
+{
+	if (!EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_FILETYPE) ||
+	    (filetype >= EXT3_FT_MAX))
+		return DT_UNKNOWN;
+
+	return (ext3_filetype_table[filetype]);
+}
+			       
+
+int ext3_check_dir_entry (const char * function, struct inode * dir,
+			  struct ext3_dir_entry_2 * de,
+			  struct buffer_head * bh,
+			  unsigned long offset)
+{
+	const char * error_msg = NULL;
+ 	const int rlen = le16_to_cpu(de->rec_len);
+
+	if (rlen < EXT3_DIR_REC_LEN(1))
+		error_msg = "rec_len is smaller than minimal";
+	else if (rlen % 4 != 0)
+		error_msg = "rec_len % 4 != 0";
+	else if (rlen < EXT3_DIR_REC_LEN(de->name_len))
+		error_msg = "rec_len is too small for name_len";
+	else if (((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize)
+		error_msg = "directory entry across blocks";
+	else if (le32_to_cpu(de->inode) >
+			le32_to_cpu(EXT3_SB(dir->i_sb)->s_es->s_inodes_count))
+		error_msg = "inode out of bounds";
+
+	if (error_msg != NULL)
+		ext3_error (dir->i_sb, function,
+			"bad entry in directory #%lu: %s - "
+			"offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
+			dir->i_ino, error_msg, offset,
+			(unsigned long) le32_to_cpu(de->inode),
+			rlen, de->name_len);
+	return error_msg == NULL ? 1 : 0;
+}
+
+static int ext3_readdir(struct file * filp,
+			 void * dirent, filldir_t filldir)
+{
+	int error = 0;
+	unsigned long offset, blk;
+	int i, num, stored;
+	struct buffer_head * bh, * tmp, * bha[16];
+	struct ext3_dir_entry_2 * de;
+	struct super_block * sb;
+	int err;
+	struct inode *inode = filp->f_dentry->d_inode;
+	int ret = 0;
+
+	sb = inode->i_sb;
+
+#ifdef CONFIG_EXT3_INDEX
+	if (EXT3_HAS_COMPAT_FEATURE(inode->i_sb,
+				    EXT3_FEATURE_COMPAT_DIR_INDEX) &&
+	    ((EXT3_I(inode)->i_flags & EXT3_INDEX_FL) ||
+	     ((inode->i_size >> sb->s_blocksize_bits) == 1))) {
+		err = ext3_dx_readdir(filp, dirent, filldir);
+		if (err != ERR_BAD_DX_DIR) {
+			ret = err;
+			goto out;
+		}
+		/*
+		 * We don't set the inode dirty flag since it's not
+		 * critical that it get flushed back to the disk.
+		 */
+		EXT3_I(filp->f_dentry->d_inode)->i_flags &= ~EXT3_INDEX_FL;
+	}
+#endif
+	stored = 0;
+	bh = NULL;
+	offset = filp->f_pos & (sb->s_blocksize - 1);
+
+	while (!error && !stored && filp->f_pos < inode->i_size) {
+		blk = (filp->f_pos) >> EXT3_BLOCK_SIZE_BITS(sb);
+		bh = ext3_bread(NULL, inode, blk, 0, &err);
+		if (!bh) {
+			ext3_error (sb, "ext3_readdir",
+				"directory #%lu contains a hole at offset %lu",
+				inode->i_ino, (unsigned long)filp->f_pos);
+			filp->f_pos += sb->s_blocksize - offset;
+			continue;
+		}
+
+		/*
+		 * Do the readahead
+		 */
+		if (!offset) {
+			for (i = 16 >> (EXT3_BLOCK_SIZE_BITS(sb) - 9), num = 0;
+			     i > 0; i--) {
+				tmp = ext3_getblk (NULL, inode, ++blk, 0, &err);
+				if (tmp && !buffer_uptodate(tmp) &&
+						!buffer_locked(tmp))
+					bha[num++] = tmp;
+				else
+					brelse (tmp);
+			}
+			if (num) {
+				ll_rw_block (READA, num, bha);
+				for (i = 0; i < num; i++)
+					brelse (bha[i]);
+			}
+		}
+
+revalidate:
+		/* If the dir block has changed since the last call to
+		 * readdir(2), then we might be pointing to an invalid
+		 * dirent right now.  Scan from the start of the block
+		 * to make sure. */
+		if (filp->f_version != inode->i_version) {
+			for (i = 0; i < sb->s_blocksize && i < offset; ) {
+				de = (struct ext3_dir_entry_2 *) 
+					(bh->b_data + i);
+				/* It's too expensive to do a full
+				 * dirent test each time round this
+				 * loop, but we do have to test at
+				 * least that it is non-zero.  A
+				 * failure will be detected in the
+				 * dirent test below. */
+				if (le16_to_cpu(de->rec_len) <
+						EXT3_DIR_REC_LEN(1))
+					break;
+				i += le16_to_cpu(de->rec_len);
+			}
+			offset = i;
+			filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1))
+				| offset;
+			filp->f_version = inode->i_version;
+		}
+
+		while (!error && filp->f_pos < inode->i_size 
+		       && offset < sb->s_blocksize) {
+			de = (struct ext3_dir_entry_2 *) (bh->b_data + offset);
+			if (!ext3_check_dir_entry ("ext3_readdir", inode, de,
+						   bh, offset)) {
+				/* On error, skip the f_pos to the
+                                   next block. */
+				filp->f_pos = (filp->f_pos |
+						(sb->s_blocksize - 1)) + 1;
+				brelse (bh);
+				ret = stored;
+				goto out;
+			}
+			offset += le16_to_cpu(de->rec_len);
+			if (le32_to_cpu(de->inode)) {
+				/* We might block in the next section
+				 * if the data destination is
+				 * currently swapped out.  So, use a
+				 * version stamp to detect whether or
+				 * not the directory has been modified
+				 * during the copy operation.
+				 */
+				unsigned long version = filp->f_version;
+
+				error = filldir(dirent, de->name,
+						de->name_len,
+						filp->f_pos,
+						le32_to_cpu(de->inode),
+						get_dtype(sb, de->file_type));
+				if (error)
+					break;
+				if (version != filp->f_version)
+					goto revalidate;
+				stored ++;
+			}
+			filp->f_pos += le16_to_cpu(de->rec_len);
+		}
+		offset = 0;
+		brelse (bh);
+	}
+out:
+	return ret;
+}
+
+#ifdef CONFIG_EXT3_INDEX
+/*
+ * These functions convert from the major/minor hash to an f_pos
+ * value.
+ * 
+ * Currently we only use major hash numer.  This is unfortunate, but
+ * on 32-bit machines, the same VFS interface is used for lseek and
+ * llseek, so if we use the 64 bit offset, then the 32-bit versions of
+ * lseek/telldir/seekdir will blow out spectacularly, and from within
+ * the ext2 low-level routine, we don't know if we're being called by
+ * a 64-bit version of the system call or the 32-bit version of the
+ * system call.  Worse yet, NFSv2 only allows for a 32-bit readdir
+ * cookie.  Sigh.
+ */
+#define hash2pos(major, minor)	(major >> 1)
+#define pos2maj_hash(pos)	((pos << 1) & 0xffffffff)
+#define pos2min_hash(pos)	(0)
+
+/*
+ * This structure holds the nodes of the red-black tree used to store
+ * the directory entry in hash order.
+ */
+struct fname {
+	__u32		hash;
+	__u32		minor_hash;
+	struct rb_node	rb_hash; 
+	struct fname	*next;
+	__u32		inode;
+	__u8		name_len;
+	__u8		file_type;
+	char		name[0];
+};
+
+/*
+ * This functoin implements a non-recursive way of freeing all of the
+ * nodes in the red-black tree.
+ */
+static void free_rb_tree_fname(struct rb_root *root)
+{
+	struct rb_node	*n = root->rb_node;
+	struct rb_node	*parent;
+	struct fname	*fname;
+
+	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 = n->rb_parent;
+		fname = rb_entry(n, struct fname, rb_hash);
+		while (fname) {
+			struct fname * old = fname;
+			fname = fname->next;
+			kfree (old);
+		}
+		if (!parent)
+			root->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;
+	}
+	root->rb_node = NULL;
+}
+
+
+static struct dir_private_info *create_dir_info(loff_t pos)
+{
+	struct dir_private_info *p;
+
+	p = kmalloc(sizeof(struct dir_private_info), GFP_KERNEL);
+	if (!p)
+		return NULL;
+	p->root.rb_node = NULL;
+	p->curr_node = NULL;
+	p->extra_fname = NULL;
+	p->last_pos = 0;
+	p->curr_hash = pos2maj_hash(pos);
+	p->curr_minor_hash = pos2min_hash(pos);
+	p->next_hash = 0;
+	return p;
+}
+
+void ext3_htree_free_dir_info(struct dir_private_info *p)
+{
+	free_rb_tree_fname(&p->root);
+	kfree(p);
+}
+
+/*
+ * Given a directory entry, enter it into the fname rb tree.
+ */
+int ext3_htree_store_dirent(struct file *dir_file, __u32 hash,
+			     __u32 minor_hash,
+			     struct ext3_dir_entry_2 *dirent)
+{
+	struct rb_node **p, *parent = NULL;
+	struct fname * fname, *new_fn;
+	struct dir_private_info *info;
+	int len;
+
+	info = (struct dir_private_info *) dir_file->private_data;
+	p = &info->root.rb_node;
+
+	/* Create and allocate the fname structure */
+	len = sizeof(struct fname) + dirent->name_len + 1;
+	new_fn = kmalloc(len, GFP_KERNEL);
+	if (!new_fn)
+		return -ENOMEM;
+	memset(new_fn, 0, len);
+	new_fn->hash = hash;
+	new_fn->minor_hash = minor_hash;
+	new_fn->inode = le32_to_cpu(dirent->inode);
+	new_fn->name_len = dirent->name_len;
+	new_fn->file_type = dirent->file_type;
+	memcpy(new_fn->name, dirent->name, dirent->name_len);
+	new_fn->name[dirent->name_len] = 0;
+
+	while (*p) {
+		parent = *p;
+		fname = rb_entry(parent, struct fname, rb_hash);
+
+		/*
+		 * If the hash and minor hash match up, then we put
+		 * them on a linked list.  This rarely happens...
+		 */
+		if ((new_fn->hash == fname->hash) &&
+		    (new_fn->minor_hash == fname->minor_hash)) {
+			new_fn->next = fname->next;
+			fname->next = new_fn;
+			return 0;
+		}
+
+		if (new_fn->hash < fname->hash)
+			p = &(*p)->rb_left;
+		else if (new_fn->hash > fname->hash)
+			p = &(*p)->rb_right;
+		else if (new_fn->minor_hash < fname->minor_hash)
+			p = &(*p)->rb_left;
+		else /* if (new_fn->minor_hash > fname->minor_hash) */
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&new_fn->rb_hash, parent, p);
+	rb_insert_color(&new_fn->rb_hash, &info->root);
+	return 0;
+}
+
+
+
+/*
+ * This is a helper function for ext3_dx_readdir.  It calls filldir
+ * for all entres on the fname linked list.  (Normally there is only
+ * one entry on the linked list, unless there are 62 bit hash collisions.)
+ */
+static int call_filldir(struct file * filp, void * dirent,
+			filldir_t filldir, struct fname *fname)
+{
+	struct dir_private_info *info = filp->private_data;
+	loff_t	curr_pos;
+	struct inode *inode = filp->f_dentry->d_inode;
+	struct super_block * sb;
+	int error;
+
+	sb = inode->i_sb;
+
+	if (!fname) {
+		printk("call_filldir: called with null fname?!?\n");
+		return 0;
+	}
+	curr_pos = hash2pos(fname->hash, fname->minor_hash);
+	while (fname) {
+		error = filldir(dirent, fname->name,
+				fname->name_len, curr_pos, 
+				fname->inode,
+				get_dtype(sb, fname->file_type));
+		if (error) {
+			filp->f_pos = curr_pos;
+			info->extra_fname = fname->next;
+			return error;
+		}
+		fname = fname->next;
+	}
+	return 0;
+}
+
+static int ext3_dx_readdir(struct file * filp,
+			 void * dirent, filldir_t filldir)
+{
+	struct dir_private_info *info = filp->private_data;
+	struct inode *inode = filp->f_dentry->d_inode;
+	struct fname *fname;
+	int	ret;
+
+	if (!info) {
+		info = create_dir_info(filp->f_pos);
+		if (!info)
+			return -ENOMEM;
+		filp->private_data = info;
+	}
+
+	if (filp->f_pos == EXT3_HTREE_EOF)
+		return 0;	/* EOF */
+
+	/* Some one has messed with f_pos; reset the world */
+	if (info->last_pos != filp->f_pos) {
+		free_rb_tree_fname(&info->root);
+		info->curr_node = NULL;
+		info->extra_fname = NULL;
+		info->curr_hash = pos2maj_hash(filp->f_pos);
+		info->curr_minor_hash = pos2min_hash(filp->f_pos);
+	}
+
+	/*
+	 * If there are any leftover names on the hash collision
+	 * chain, return them first.
+	 */
+	if (info->extra_fname &&
+	    call_filldir(filp, dirent, filldir, info->extra_fname))
+		goto finished;
+
+	if (!info->curr_node)
+		info->curr_node = rb_first(&info->root);
+
+	while (1) {
+		/*
+		 * Fill the rbtree if we have no more entries,
+		 * or the inode has changed since we last read in the
+		 * cached entries. 
+		 */
+		if ((!info->curr_node) ||
+		    (filp->f_version != inode->i_version)) {
+			info->curr_node = NULL;
+			free_rb_tree_fname(&info->root);
+			filp->f_version = inode->i_version;
+			ret = ext3_htree_fill_tree(filp, info->curr_hash,
+						   info->curr_minor_hash,
+						   &info->next_hash);
+			if (ret < 0)
+				return ret;
+			if (ret == 0) {
+				filp->f_pos = EXT3_HTREE_EOF;
+				break;
+			}
+			info->curr_node = rb_first(&info->root);
+		}
+
+		fname = rb_entry(info->curr_node, struct fname, rb_hash);
+		info->curr_hash = fname->hash;
+		info->curr_minor_hash = fname->minor_hash;
+		if (call_filldir(filp, dirent, filldir, fname))
+			break;
+
+		info->curr_node = rb_next(info->curr_node);
+		if (!info->curr_node) {
+			if (info->next_hash == ~0) {
+				filp->f_pos = EXT3_HTREE_EOF;
+				break;
+			}
+			info->curr_hash = info->next_hash;
+			info->curr_minor_hash = 0;
+		}
+	}
+finished:
+	info->last_pos = filp->f_pos;
+	return 0;
+}
+
+static int ext3_release_dir (struct inode * inode, struct file * filp)
+{
+       if (filp->private_data)
+		ext3_htree_free_dir_info(filp->private_data);
+
+	return 0;
+}
+
+#endif

fs/ext3/file.c

@@ -0,0 +1,131 @@
+/*
+ *  linux/fs/ext3/file.c
+ *
+ * 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/fs/minix/file.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  ext3 fs regular file handling primitives
+ *
+ *  64-bit file support on 64-bit platforms by Jakub Jelinek
+ *	(jj@sunsite.ms.mff.cuni.cz)
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/jbd.h>
+#include <linux/ext3_fs.h>
+#include <linux/ext3_jbd.h>
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * Called when an inode is released. Note that this is different
+ * from ext3_file_open: open gets called at every open, but release
+ * gets called only when /all/ the files are closed.
+ */
+static int ext3_release_file (struct inode * inode, struct file * filp)
+{
+	/* if we are the last writer on the inode, drop the block reservation */
+	if ((filp->f_mode & FMODE_WRITE) &&
+			(atomic_read(&inode->i_writecount) == 1))
+		ext3_discard_reservation(inode);
+	if (is_dx(inode) && filp->private_data)
+		ext3_htree_free_dir_info(filp->private_data);
+
+	return 0;
+}
+
+static ssize_t
+ext3_file_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t pos)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_dentry->d_inode;
+	ssize_t ret;
+	int err;
+
+	ret = generic_file_aio_write(iocb, buf, count, pos);
+
+	/*
+	 * Skip flushing if there was an error, or if nothing was written.
+	 */
+	if (ret <= 0)
+		return ret;
+
+	/*
+	 * If the inode is IS_SYNC, or is O_SYNC and we are doing data
+	 * journalling then we need to make sure that we force the transaction
+	 * to disk to keep all metadata uptodate synchronously.
+	 */
+	if (file->f_flags & O_SYNC) {
+		/*
+		 * If we are non-data-journaled, then the dirty data has
+		 * already been flushed to backing store by generic_osync_inode,
+		 * and the inode has been flushed too if there have been any
+		 * modifications other than mere timestamp updates.
+		 *
+		 * Open question --- do we care about flushing timestamps too
+		 * if the inode is IS_SYNC?
+		 */
+		if (!ext3_should_journal_data(inode))
+			return ret;
+
+		goto force_commit;
+	}
+
+	/*
+	 * So we know that there has been no forced data flush.  If the inode
+	 * is marked IS_SYNC, we need to force one ourselves.
+	 */
+	if (!IS_SYNC(inode))
+		return ret;
+
+	/*
+	 * Open question #2 --- should we force data to disk here too?  If we
+	 * don't, the only impact is that data=writeback filesystems won't
+	 * flush data to disk automatically on IS_SYNC, only metadata (but
+	 * historically, that is what ext2 has done.)
+	 */
+
+force_commit:
+	err = ext3_force_commit(inode->i_sb);
+	if (err) 
+		return err;
+	return ret;
+}
+
+struct file_operations ext3_file_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read	= generic_file_aio_read,
+	.aio_write	= ext3_file_write,
+	.readv		= generic_file_readv,
+	.writev		= generic_file_writev,
+	.ioctl		= ext3_ioctl,
+	.mmap		= generic_file_mmap,
+	.open		= generic_file_open,
+	.release	= ext3_release_file,
+	.fsync		= ext3_sync_file,
+	.sendfile	= generic_file_sendfile,
+};
+
+struct inode_operations ext3_file_inode_operations = {
+	.truncate	= ext3_truncate,
+	.setattr	= ext3_setattr,
+#ifdef CONFIG_EXT3_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext3_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+	.permission	= ext3_permission,
+};
+

fs/ext3/fsync.c

@@ -0,0 +1,88 @@
+/*
+ *  linux/fs/ext3/fsync.c
+ *
+ *  Copyright (C) 1993  Stephen Tweedie (sct@redhat.com)
+ *  from
+ *  Copyright (C) 1992  Remy Card (card@masi.ibp.fr)
+ *                      Laboratoire MASI - Institut Blaise Pascal
+ *                      Universite Pierre et Marie Curie (Paris VI)
+ *  from
+ *  linux/fs/minix/truncate.c   Copyright (C) 1991, 1992  Linus Torvalds
+ * 
+ *  ext3fs fsync primitive
+ *
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ * 
+ *  Removed unnecessary code duplication for little endian machines
+ *  and excessive __inline__s. 
+ *        Andi Kleen, 1997
+ *
+ * Major simplications and cleanup - we only need to do the metadata, because
+ * we can depend on generic_block_fdatasync() to sync the data blocks.
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/writeback.h>
+#include <linux/jbd.h>
+#include <linux/ext3_fs.h>
+#include <linux/ext3_jbd.h>
+
+/*
+ * akpm: A new design for ext3_sync_file().
+ *
+ * This is only called from sys_fsync(), sys_fdatasync() and sys_msync().
+ * There cannot be a transaction open by this task.
+ * Another task could have dirtied this inode.  Its data can be in any
+ * state in the journalling system.
+ *
+ * What we do is just kick off a commit and wait on it.  This will snapshot the
+ * inode to disk.
+ */
+
+int ext3_sync_file(struct file * file, struct dentry *dentry, int datasync)
+{
+	struct inode *inode = dentry->d_inode;
+	int ret = 0;
+
+	J_ASSERT(ext3_journal_current_handle() == 0);
+
+	/*
+	 * data=writeback:
+	 *  The caller's filemap_fdatawrite()/wait will sync the data.
+	 *  sync_inode() will sync the metadata
+	 *
+	 * data=ordered:
+	 *  The caller's filemap_fdatawrite() will write the data and
+	 *  sync_inode() will write the inode if it is dirty.  Then the caller's
+	 *  filemap_fdatawait() will wait on the pages.
+	 *
+	 * data=journal:
+	 *  filemap_fdatawrite won't do anything (the buffers are clean).
+	 *  ext3_force_commit will write the file data into the journal and
+	 *  will wait on that.
+	 *  filemap_fdatawait() will encounter a ton of newly-dirtied pages
+	 *  (they were dirtied by commit).  But that's OK - the blocks are
+	 *  safe in-journal, which is all fsync() needs to ensure.
+	 */
+	if (ext3_should_journal_data(inode)) {
+		ret = ext3_force_commit(inode->i_sb);
+		goto out;
+	}
+
+	/*
+	 * The VFS has written the file data.  If the inode is unaltered
+	 * then we need not start a commit.
+	 */
+	if (inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC)) {
+		struct writeback_control wbc = {
+			.sync_mode = WB_SYNC_ALL,
+			.nr_to_write = 0, /* sys_fsync did this */
+		};
+		ret = sync_inode(inode, &wbc);
+	}
+out:
+	return ret;
+}

fs/ext3/hash.c

@@ -0,0 +1,152 @@
+/*
+ *  linux/fs/ext3/hash.c
+ *
+ * Copyright (C) 2002 by Theodore Ts'o
+ *
+ * This file is released under the GPL v2.
+ * 
+ * This file may be redistributed under the terms of the GNU Public
+ * License.
+ */
+
+#include <linux/fs.h>
+#include <linux/jbd.h>
+#include <linux/sched.h>
+#include <linux/ext3_fs.h>
+#include <linux/cryptohash.h>
+
+#define DELTA 0x9E3779B9
+
+static void TEA_transform(__u32 buf[4], __u32 const in[])
+{
+	__u32	sum = 0;
+	__u32	b0 = buf[0], b1 = buf[1];
+	__u32	a = in[0], b = in[1], c = in[2], d = in[3];
+	int	n = 16;
+
+	do {
+		sum += DELTA;
+		b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);
+		b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);
+	} while(--n);
+
+	buf[0] += b0;
+	buf[1] += b1;
+}
+
+
+/* The old legacy hash */
+static __u32 dx_hack_hash (const char *name, int len)
+{
+	__u32 hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+	while (len--) {
+		__u32 hash = hash1 + (hash0 ^ (*name++ * 7152373));
+
+		if (hash & 0x80000000) hash -= 0x7fffffff;
+		hash1 = hash0;
+		hash0 = hash;
+	}
+	return (hash0 << 1);
+}
+
+static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
+{
+	__u32	pad, val;
+	int	i;
+
+	pad = (__u32)len | ((__u32)len << 8);
+	pad |= pad << 16;
+
+	val = pad;
+	if (len > num*4)
+		len = num * 4;
+	for (i=0; i < len; i++) {
+		if ((i % 4) == 0)
+			val = pad;
+		val = msg[i] + (val << 8);
+		if ((i % 4) == 3) {
+			*buf++ = val;
+			val = pad;
+			num--;
+		}
+	}
+	if (--num >= 0)
+		*buf++ = val;
+	while (--num >= 0)
+		*buf++ = pad;
+}
+
+/*
+ * Returns the hash of a filename.  If len is 0 and name is NULL, then
+ * this function can be used to test whether or not a hash version is
+ * supported.
+ * 
+ * The seed is an 4 longword (32 bits) "secret" which can be used to
+ * uniquify a hash.  If the seed is all zero's, then some default seed
+ * may be used.
+ * 
+ * A particular hash version specifies whether or not the seed is
+ * represented, and whether or not the returned hash is 32 bits or 64
+ * bits.  32 bit hashes will return 0 for the minor hash.
+ */
+int ext3fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
+{
+	__u32	hash;
+	__u32	minor_hash = 0;
+	const char	*p;
+	int		i;
+	__u32 		in[8], buf[4];
+
+	/* Initialize the default seed for the hash checksum functions */
+	buf[0] = 0x67452301;
+	buf[1] = 0xefcdab89;
+	buf[2] = 0x98badcfe;
+	buf[3] = 0x10325476;
+
+	/* Check to see if the seed is all zero's */
+	if (hinfo->seed) {
+		for (i=0; i < 4; i++) {
+			if (hinfo->seed[i])
+				break;
+		}
+		if (i < 4)
+			memcpy(buf, hinfo->seed, sizeof(buf));
+	}
+
+	switch (hinfo->hash_version) {
+	case DX_HASH_LEGACY:
+		hash = dx_hack_hash(name, len);
+		break;
+	case DX_HASH_HALF_MD4:
+		p = name;
+		while (len > 0) {
+			str2hashbuf(p, len, in, 8);
+			half_md4_transform(buf, in);
+			len -= 32;
+			p += 32;
+		}
+		minor_hash = buf[2];
+		hash = buf[1];
+		break;
+	case DX_HASH_TEA:
+		p = name;
+		while (len > 0) {
+			str2hashbuf(p, len, in, 4);
+			TEA_transform(buf, in);
+			len -= 16;
+			p += 16;
+		}
+		hash = buf[0];
+		minor_hash = buf[1];
+		break;
+	default:
+		hinfo->hash = 0;
+		return -1;
+	}
+	hash = hash & ~1;
+	if (hash == (EXT3_HTREE_EOF << 1))
+		hash = (EXT3_HTREE_EOF-1) << 1;
+	hinfo->hash = hash;
+	hinfo->minor_hash = minor_hash;
+	return 0;
+}

fs/ext3/ialloc.c

@@ -0,0 +1,794 @@
+/*
+ *  linux/fs/ext3/ialloc.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  BSD ufs-inspired inode and directory allocation by
+ *  Stephen Tweedie (sct@redhat.com), 1993
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/jbd.h>
+#include <linux/ext3_fs.h>
+#include <linux/ext3_jbd.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+#include <linux/random.h>
+#include <linux/bitops.h>
+
+#include <asm/byteorder.h>
+
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * ialloc.c contains the inodes allocation and deallocation routines
+ */
+
+/*
+ * The free inodes are managed by bitmaps.  A file system contains several
+ * blocks groups.  Each group contains 1 bitmap block for blocks, 1 bitmap
+ * block for inodes, N blocks for the inode table and data blocks.
+ *
+ * The file system contains group descriptors which are located after the
+ * super block.  Each descriptor contains the number of the bitmap block and
+ * the free blocks count in the block.
+ */
+
+
+/*
+ * Read the inode allocation bitmap for a given block_group, reading
+ * into the specified slot in the superblock's bitmap cache.
+ *
+ * Return buffer_head of bitmap on success or NULL.
+ */
+static struct buffer_head *
+read_inode_bitmap(struct super_block * sb, unsigned long block_group)
+{
+	struct ext3_group_desc *desc;
+	struct buffer_head *bh = NULL;
+
+	desc = ext3_get_group_desc(sb, block_group, NULL);
+	if (!desc)
+		goto error_out;
+
+	bh = sb_bread(sb, le32_to_cpu(desc->bg_inode_bitmap));
+	if (!bh)
+		ext3_error(sb, "read_inode_bitmap",
+			    "Cannot read inode bitmap - "
+			    "block_group = %lu, inode_bitmap = %u",
+			    block_group, le32_to_cpu(desc->bg_inode_bitmap));
+error_out:
+	return bh;
+}
+
+/*
+ * NOTE! When we get the inode, we're the only people
+ * that have access to it, and as such there are no
+ * race conditions we have to worry about. The inode
+ * is not on the hash-lists, and it cannot be reached
+ * through the filesystem because the directory entry
+ * has been deleted earlier.
+ *
+ * HOWEVER: we must make sure that we get no aliases,
+ * which means that we have to call "clear_inode()"
+ * _before_ we mark the inode not in use in the inode
+ * bitmaps. Otherwise a newly created file might use
+ * the same inode number (not actually the same pointer
+ * though), and then we'd have two inodes sharing the
+ * same inode number and space on the harddisk.
+ */
+void ext3_free_inode (handle_t *handle, struct inode * inode)
+{
+	struct super_block * sb = inode->i_sb;
+	int is_directory;
+	unsigned long ino;
+	struct buffer_head *bitmap_bh = NULL;
+	struct buffer_head *bh2;
+	unsigned long block_group;
+	unsigned long bit;
+	struct ext3_group_desc * gdp;
+	struct ext3_super_block * es;
+	struct ext3_sb_info *sbi;
+	int fatal = 0, err;
+
+	if (atomic_read(&inode->i_count) > 1) {
+		printk ("ext3_free_inode: inode has count=%d\n",
+					atomic_read(&inode->i_count));
+		return;
+	}
+	if (inode->i_nlink) {
+		printk ("ext3_free_inode: inode has nlink=%d\n",
+			inode->i_nlink);
+		return;
+	}
+	if (!sb) {
+		printk("ext3_free_inode: inode on nonexistent device\n");
+		return;
+	}
+	sbi = EXT3_SB(sb);
+
+	ino = inode->i_ino;
+	ext3_debug ("freeing inode %lu\n", ino);
+
+	/*
+	 * Note: we must free any quota before locking the superblock,
+	 * as writing the quota to disk may need the lock as well.
+	 */
+	DQUOT_INIT(inode);
+	ext3_xattr_delete_inode(handle, inode);
+	DQUOT_FREE_INODE(inode);
+	DQUOT_DROP(inode);
+
+	is_directory = S_ISDIR(inode->i_mode);
+
+	/* Do this BEFORE marking the inode not in use or returning an error */
+	clear_inode (inode);
+
+	es = EXT3_SB(sb)->s_es;
+	if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
+		ext3_error (sb, "ext3_free_inode",
+			    "reserved or nonexistent inode %lu", ino);
+		goto error_return;
+	}
+	block_group = (ino - 1) / EXT3_INODES_PER_GROUP(sb);
+	bit = (ino - 1) % EXT3_INODES_PER_GROUP(sb);
+	bitmap_bh = read_inode_bitmap(sb, block_group);
+	if (!bitmap_bh)
+		goto error_return;
+
+	BUFFER_TRACE(bitmap_bh, "get_write_access");
+	fatal = ext3_journal_get_write_access(handle, bitmap_bh);
+	if (fatal)
+		goto error_return;
+
+	/* Ok, now we can actually update the inode bitmaps.. */
+	if (!ext3_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
+					bit, bitmap_bh->b_data))
+		ext3_error (sb, "ext3_free_inode",
+			      "bit already cleared for inode %lu", ino);
+	else {
+		gdp = ext3_get_group_desc (sb, block_group, &bh2);
+
+		BUFFER_TRACE(bh2, "get_write_access");
+		fatal = ext3_journal_get_write_access(handle, bh2);
+		if (fatal) goto error_return;
+
+		if (gdp) {
+			spin_lock(sb_bgl_lock(sbi, block_group));
+			gdp->bg_free_inodes_count = cpu_to_le16(
+				le16_to_cpu(gdp->bg_free_inodes_count) + 1);
+			if (is_directory)
+				gdp->bg_used_dirs_count = cpu_to_le16(
+				  le16_to_cpu(gdp->bg_used_dirs_count) - 1);
+			spin_unlock(sb_bgl_lock(sbi, block_group));
+			percpu_counter_inc(&sbi->s_freeinodes_counter);
+			if (is_directory)
+				percpu_counter_dec(&sbi->s_dirs_counter);
+
+		}
+		BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
+		err = ext3_journal_dirty_metadata(handle, bh2);
+		if (!fatal) fatal = err;
+	}
+	BUFFER_TRACE(bitmap_bh, "call ext3_journal_dirty_metadata");
+	err = ext3_journal_dirty_metadata(handle, bitmap_bh);
+	if (!fatal)
+		fatal = err;
+	sb->s_dirt = 1;
+error_return:
+	brelse(bitmap_bh);
+	ext3_std_error(sb, fatal);
+}
+
+/*
+ * There are two policies for allocating an inode.  If the new inode is
+ * a directory, then a forward search is made for a block group with both
+ * free space and a low directory-to-inode ratio; if that fails, then of
+ * the groups with above-average free space, that group with the fewest
+ * directories already is chosen.
+ *
+ * For other inodes, search forward from the parent directory\'s block
+ * group to find a free inode.
+ */
+static int find_group_dir(struct super_block *sb, struct inode *parent)
+{
+	int ngroups = EXT3_SB(sb)->s_groups_count;
+	int freei, avefreei;
+	struct ext3_group_desc *desc, *best_desc = NULL;
+	struct buffer_head *bh;
+	int group, best_group = -1;
+
+	freei = percpu_counter_read_positive(&EXT3_SB(sb)->s_freeinodes_counter);
+	avefreei = freei / ngroups;
+
+	for (group = 0; group < ngroups; group++) {
+		desc = ext3_get_group_desc (sb, group, &bh);
+		if (!desc || !desc->bg_free_inodes_count)
+			continue;
+		if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
+			continue;
+		if (!best_desc || 
+		    (le16_to_cpu(desc->bg_free_blocks_count) >
+		     le16_to_cpu(best_desc->bg_free_blocks_count))) {
+			best_group = group;
+			best_desc = desc;
+		}
+	}
+	return best_group;
+}
+
+/* 
+ * Orlov's allocator for directories. 
+ * 
+ * We always try to spread first-level directories.
+ *
+ * If there are blockgroups with both free inodes and free blocks counts 
+ * not worse than average we return one with smallest directory count. 
+ * Otherwise we simply return a random group. 
+ * 
+ * For the rest rules look so: 
+ * 
+ * It's OK to put directory into a group unless 
+ * it has too many directories already (max_dirs) or 
+ * it has too few free inodes left (min_inodes) or 
+ * it has too few free blocks left (min_blocks) or 
+ * it's already running too large debt (max_debt). 
+ * Parent's group is prefered, if it doesn't satisfy these 
+ * conditions we search cyclically through the rest. If none 
+ * of the groups look good we just look for a group with more 
+ * free inodes than average (starting at parent's group). 
+ * 
+ * Debt is incremented each time we allocate a directory and decremented 
+ * when we allocate an inode, within 0--255. 
+ */ 
+
+#define INODE_COST 64
+#define BLOCK_COST 256
+
+static int find_group_orlov(struct super_block *sb, struct inode *parent)
+{
+	int parent_group = EXT3_I(parent)->i_block_group;
+	struct ext3_sb_info *sbi = EXT3_SB(sb);
+	struct ext3_super_block *es = sbi->s_es;
+	int ngroups = sbi->s_groups_count;
+	int inodes_per_group = EXT3_INODES_PER_GROUP(sb);
+	int freei, avefreei;
+	int freeb, avefreeb;
+	int blocks_per_dir, ndirs;
+	int max_debt, max_dirs, min_blocks, min_inodes;
+	int group = -1, i;
+	struct ext3_group_desc *desc;
+	struct buffer_head *bh;
+
+	freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
+	avefreei = freei / ngroups;
+	freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+	avefreeb = freeb / ngroups;
+	ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
+
+	if ((parent == sb->s_root->d_inode) ||
+	    (EXT3_I(parent)->i_flags & EXT3_TOPDIR_FL)) {
+		int best_ndir = inodes_per_group;
+		int best_group = -1;
+
+		get_random_bytes(&group, sizeof(group));
+		parent_group = (unsigned)group % ngroups;
+		for (i = 0; i < ngroups; i++) {
+			group = (parent_group + i) % ngroups;
+			desc = ext3_get_group_desc (sb, group, &bh);
+			if (!desc || !desc->bg_free_inodes_count)
+				continue;
+			if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir)
+				continue;
+			if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
+				continue;
+			if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb)
+				continue;
+			best_group = group;
+			best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
+		}
+		if (best_group >= 0)
+			return best_group;
+		goto fallback;
+	}
+
+	blocks_per_dir = (le32_to_cpu(es->s_blocks_count) - freeb) / ndirs;
+
+	max_dirs = ndirs / ngroups + inodes_per_group / 16;
+	min_inodes = avefreei - inodes_per_group / 4;
+	min_blocks = avefreeb - EXT3_BLOCKS_PER_GROUP(sb) / 4;
+
+	max_debt = EXT3_BLOCKS_PER_GROUP(sb) / max(blocks_per_dir, BLOCK_COST);
+	if (max_debt * INODE_COST > inodes_per_group)
+		max_debt = inodes_per_group / INODE_COST;
+	if (max_debt > 255)
+		max_debt = 255;
+	if (max_debt == 0)
+		max_debt = 1;
+
+	for (i = 0; i < ngroups; i++) {
+		group = (parent_group + i) % ngroups;
+		desc = ext3_get_group_desc (sb, group, &bh);
+		if (!desc || !desc->bg_free_inodes_count)
+			continue;
+		if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs)
+			continue;
+		if (le16_to_cpu(desc->bg_free_inodes_count) < min_inodes)
+			continue;
+		if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks)
+			continue;
+		return group;
+	}
+
+fallback:
+	for (i = 0; i < ngroups; i++) {
+		group = (parent_group + i) % ngroups;
+		desc = ext3_get_group_desc (sb, group, &bh);
+		if (!desc || !desc->bg_free_inodes_count)
+			continue;
+		if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
+			return group;
+	}
+
+	if (avefreei) {
+		/*
+		 * The free-inodes counter is approximate, and for really small
+		 * filesystems the above test can fail to find any blockgroups
+		 */
+		avefreei = 0;
+		goto fallback;
+	}
+
+	return -1;
+}
+
+static int find_group_other(struct super_block *sb, struct inode *parent)
+{
+	int parent_group = EXT3_I(parent)->i_block_group;
+	int ngroups = EXT3_SB(sb)->s_groups_count;
+	struct ext3_group_desc *desc;
+	struct buffer_head *bh;
+	int group, i;
+
+	/*
+	 * Try to place the inode in its parent directory
+	 */
+	group = parent_group;
+	desc = ext3_get_group_desc (sb, group, &bh);
+	if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
+			le16_to_cpu(desc->bg_free_blocks_count))
+		return group;
+
+	/*
+	 * We're going to place this inode in a different blockgroup from its
+	 * parent.  We want to cause files in a common directory to all land in
+	 * the same blockgroup.  But we want files which are in a different
+	 * directory which shares a blockgroup with our parent to land in a
+	 * different blockgroup.
+	 *
+	 * So add our directory's i_ino into the starting point for the hash.
+	 */
+	group = (group + parent->i_ino) % ngroups;
+
+	/*
+	 * Use a quadratic hash to find a group with a free inode and some free
+	 * blocks.
+	 */
+	for (i = 1; i < ngroups; i <<= 1) {
+		group += i;
+		if (group >= ngroups)
+			group -= ngroups;
+		desc = ext3_get_group_desc (sb, group, &bh);
+		if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
+				le16_to_cpu(desc->bg_free_blocks_count))
+			return group;
+	}
+
+	/*
+	 * That failed: try linear search for a free inode, even if that group
+	 * has no free blocks.
+	 */
+	group = parent_group;
+	for (i = 0; i < ngroups; i++) {
+		if (++group >= ngroups)
+			group = 0;
+		desc = ext3_get_group_desc (sb, group, &bh);
+		if (desc && le16_to_cpu(desc->bg_free_inodes_count))
+			return group;
+	}
+
+	return -1;
+}
+
+/*
+ * There are two policies for allocating an inode.  If the new inode is
+ * a directory, then a forward search is made for a block group with both
+ * free space and a low directory-to-inode ratio; if that fails, then of
+ * the groups with above-average free space, that group with the fewest
+ * directories already is chosen.
+ *
+ * For other inodes, search forward from the parent directory's block
+ * group to find a free inode.
+ */
+struct inode *ext3_new_inode(handle_t *handle, struct inode * dir, int mode)
+{
+	struct super_block *sb;
+	struct buffer_head *bitmap_bh = NULL;
+	struct buffer_head *bh2;
+	int group;
+	unsigned long ino = 0;
+	struct inode * inode;
+	struct ext3_group_desc * gdp = NULL;
+	struct ext3_super_block * es;
+	struct ext3_inode_info *ei;
+	struct ext3_sb_info *sbi;
+	int err = 0;
+	struct inode *ret;
+	int i;
+
+	/* Cannot create files in a deleted directory */
+	if (!dir || !dir->i_nlink)
+		return ERR_PTR(-EPERM);
+
+	sb = dir->i_sb;
+	inode = new_inode(sb);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+	ei = EXT3_I(inode);
+
+	sbi = EXT3_SB(sb);
+	es = sbi->s_es;
+	if (S_ISDIR(mode)) {
+		if (test_opt (sb, OLDALLOC))
+			group = find_group_dir(sb, dir);
+		else
+			group = find_group_orlov(sb, dir);
+	} else 
+		group = find_group_other(sb, dir);
+
+	err = -ENOSPC;
+	if (group == -1)
+		goto out;
+
+	for (i = 0; i < sbi->s_groups_count; i++) {
+		err = -EIO;
+
+		gdp = ext3_get_group_desc(sb, group, &bh2);
+		if (!gdp)
+			goto fail;
+
+		brelse(bitmap_bh);
+		bitmap_bh = read_inode_bitmap(sb, group);
+		if (!bitmap_bh)
+			goto fail;
+
+		ino = 0;
+
+repeat_in_this_group:
+		ino = ext3_find_next_zero_bit((unsigned long *)
+				bitmap_bh->b_data, EXT3_INODES_PER_GROUP(sb), ino);
+		if (ino < EXT3_INODES_PER_GROUP(sb)) {
+
+			BUFFER_TRACE(bitmap_bh, "get_write_access");
+			err = ext3_journal_get_write_access(handle, bitmap_bh);
+			if (err)
+				goto fail;
+
+			if (!ext3_set_bit_atomic(sb_bgl_lock(sbi, group),
+						ino, bitmap_bh->b_data)) {
+				/* we won it */
+				BUFFER_TRACE(bitmap_bh,
+					"call ext3_journal_dirty_metadata");
+				err = ext3_journal_dirty_metadata(handle,
+								bitmap_bh);
+				if (err)
+					goto fail;
+				goto got;
+			}
+			/* we lost it */
+			journal_release_buffer(handle, bitmap_bh);
+
+			if (++ino < EXT3_INODES_PER_GROUP(sb))
+				goto repeat_in_this_group;
+		}
+
+		/*
+		 * This case is possible in concurrent environment.  It is very
+		 * rare.  We cannot repeat the find_group_xxx() call because
+		 * that will simply return the same blockgroup, because the
+		 * group descriptor metadata has not yet been updated.
+		 * So we just go onto the next blockgroup.
+		 */
+		if (++group == sbi->s_groups_count)
+			group = 0;
+	}
+	err = -ENOSPC;
+	goto out;
+
+got:
+	ino += group * EXT3_INODES_PER_GROUP(sb) + 1;
+	if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
+		ext3_error (sb, "ext3_new_inode",
+			    "reserved inode or inode > inodes count - "
+			    "block_group = %d, inode=%lu", group, ino);
+		err = -EIO;
+		goto fail;
+	}
+
+	BUFFER_TRACE(bh2, "get_write_access");
+	err = ext3_journal_get_write_access(handle, bh2);
+	if (err) goto fail;
+	spin_lock(sb_bgl_lock(sbi, group));
+	gdp->bg_free_inodes_count =
+		cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1);
+	if (S_ISDIR(mode)) {
+		gdp->bg_used_dirs_count =
+			cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1);
+	}
+	spin_unlock(sb_bgl_lock(sbi, group));
+	BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
+	err = ext3_journal_dirty_metadata(handle, bh2);
+	if (err) goto fail;
+
+	percpu_counter_dec(&sbi->s_freeinodes_counter);
+	if (S_ISDIR(mode))
+		percpu_counter_inc(&sbi->s_dirs_counter);
+	sb->s_dirt = 1;
+
+	inode->i_uid = current->fsuid;
+	if (test_opt (sb, GRPID))
+		inode->i_gid = dir->i_gid;
+	else if (dir->i_mode & S_ISGID) {
+		inode->i_gid = dir->i_gid;
+		if (S_ISDIR(mode))
+			mode |= S_ISGID;
+	} else
+		inode->i_gid = current->fsgid;
+	inode->i_mode = mode;
+
+	inode->i_ino = ino;
+	/* This is the optimal IO size (for stat), not the fs block size */
+	inode->i_blksize = PAGE_SIZE;
+	inode->i_blocks = 0;
+	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
+
+	memset(ei->i_data, 0, sizeof(ei->i_data));
+	ei->i_dir_start_lookup = 0;
+	ei->i_disksize = 0;
+
+	ei->i_flags = EXT3_I(dir)->i_flags & ~EXT3_INDEX_FL;
+	if (S_ISLNK(mode))
+		ei->i_flags &= ~(EXT3_IMMUTABLE_FL|EXT3_APPEND_FL);
+	/* dirsync only applies to directories */
+	if (!S_ISDIR(mode))
+		ei->i_flags &= ~EXT3_DIRSYNC_FL;
+#ifdef EXT3_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;
+	ei->i_block_alloc_info = NULL;
+	ei->i_block_group = group;
+
+	ext3_set_inode_flags(inode);
+	if (IS_DIRSYNC(inode))
+		handle->h_sync = 1;
+	insert_inode_hash(inode);
+	spin_lock(&sbi->s_next_gen_lock);
+	inode->i_generation = sbi->s_next_generation++;
+	spin_unlock(&sbi->s_next_gen_lock);
+
+	ei->i_state = EXT3_STATE_NEW;
+	ei->i_extra_isize =
+		(EXT3_INODE_SIZE(inode->i_sb) > EXT3_GOOD_OLD_INODE_SIZE) ?
+		sizeof(struct ext3_inode) - EXT3_GOOD_OLD_INODE_SIZE : 0;
+
+	ret = inode;
+	if(DQUOT_ALLOC_INODE(inode)) {
+		DQUOT_DROP(inode);
+		err = -EDQUOT;
+		goto fail2;
+	}
+	err = ext3_init_acl(handle, inode, dir);
+	if (err) {
+		DQUOT_FREE_INODE(inode);
+		goto fail2;
+  	}
+	err = ext3_mark_inode_dirty(handle, inode);
+	if (err) {
+		ext3_std_error(sb, err);
+		DQUOT_FREE_INODE(inode);
+		goto fail2;
+	}
+
+	ext3_debug("allocating inode %lu\n", inode->i_ino);
+	goto really_out;
+fail:
+	ext3_std_error(sb, err);
+out:
+	iput(inode);
+	ret = ERR_PTR(err);
+really_out:
+	brelse(bitmap_bh);
+	return ret;
+
+fail2:
+	inode->i_flags |= S_NOQUOTA;
+	inode->i_nlink = 0;
+	iput(inode);
+	brelse(bitmap_bh);
+	return ERR_PTR(err);
+}
+
+/* Verify that we are loading a valid orphan from disk */
+struct inode *ext3_orphan_get(struct super_block *sb, unsigned long ino)
+{
+	unsigned long max_ino = le32_to_cpu(EXT3_SB(sb)->s_es->s_inodes_count);
+	unsigned long block_group;
+	int bit;
+	struct buffer_head *bitmap_bh = NULL;
+	struct inode *inode = NULL;
+
+	/* Error cases - e2fsck has already cleaned up for us */
+	if (ino > max_ino) {
+		ext3_warning(sb, __FUNCTION__,
+			     "bad orphan ino %lu!  e2fsck was run?\n", ino);
+		goto out;
+	}
+
+	block_group = (ino - 1) / EXT3_INODES_PER_GROUP(sb);
+	bit = (ino - 1) % EXT3_INODES_PER_GROUP(sb);
+	bitmap_bh = read_inode_bitmap(sb, block_group);
+	if (!bitmap_bh) {
+		ext3_warning(sb, __FUNCTION__,
+			     "inode bitmap error for orphan %lu\n", ino);
+		goto out;
+	}
+
+	/* Having the inode bit set should be a 100% indicator that this
+	 * is a valid orphan (no e2fsck run on fs).  Orphans also include
+	 * inodes that were being truncated, so we can't check i_nlink==0.
+	 */
+	if (!ext3_test_bit(bit, bitmap_bh->b_data) ||
+			!(inode = iget(sb, ino)) || is_bad_inode(inode) ||
+			NEXT_ORPHAN(inode) > max_ino) {
+		ext3_warning(sb, __FUNCTION__,
+			     "bad orphan inode %lu!  e2fsck was run?\n", ino);
+		printk(KERN_NOTICE "ext3_test_bit(bit=%d, block=%llu) = %d\n",
+		       bit, (unsigned long long)bitmap_bh->b_blocknr,
+		       ext3_test_bit(bit, bitmap_bh->b_data));
+		printk(KERN_NOTICE "inode=%p\n", inode);
+		if (inode) {
+			printk(KERN_NOTICE "is_bad_inode(inode)=%d\n",
+			       is_bad_inode(inode));
+			printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n",
+			       NEXT_ORPHAN(inode));
+			printk(KERN_NOTICE "max_ino=%lu\n", max_ino);
+		}
+		/* Avoid freeing blocks if we got a bad deleted inode */
+		if (inode && inode->i_nlink == 0)
+			inode->i_blocks = 0;
+		iput(inode);
+		inode = NULL;
+	}
+out:
+	brelse(bitmap_bh);
+	return inode;
+}
+
+unsigned long ext3_count_free_inodes (struct super_block * sb)
+{
+	unsigned long desc_count;
+	struct ext3_group_desc *gdp;
+	int i;
+#ifdef EXT3FS_DEBUG
+	struct ext3_super_block *es;
+	unsigned long bitmap_count, x;
+	struct buffer_head *bitmap_bh = NULL;
+
+	lock_super (sb);
+	es = EXT3_SB(sb)->s_es;
+	desc_count = 0;
+	bitmap_count = 0;
+	gdp = NULL;
+	for (i = 0; i < EXT3_SB(sb)->s_groups_count; i++) {
+		gdp = ext3_get_group_desc (sb, i, NULL);
+		if (!gdp)
+			continue;
+		desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
+		brelse(bitmap_bh);
+		bitmap_bh = read_inode_bitmap(sb, i);
+		if (!bitmap_bh)
+			continue;
+
+		x = ext3_count_free(bitmap_bh, EXT3_INODES_PER_GROUP(sb) / 8);
+		printk("group %d: stored = %d, counted = %lu\n",
+			i, le16_to_cpu(gdp->bg_free_inodes_count), x);
+		bitmap_count += x;
+	}
+	brelse(bitmap_bh);
+	printk("ext3_count_free_inodes: stored = %u, computed = %lu, %lu\n",
+		le32_to_cpu(es->s_free_inodes_count), desc_count, bitmap_count);
+	unlock_super(sb);
+	return desc_count;
+#else
+	desc_count = 0;
+	for (i = 0; i < EXT3_SB(sb)->s_groups_count; i++) {
+		gdp = ext3_get_group_desc (sb, i, NULL);
+		if (!gdp)
+			continue;
+		desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
+		cond_resched();
+	}
+	return desc_count;
+#endif
+}
+
+/* Called at mount-time, super-block is locked */
+unsigned long ext3_count_dirs (struct super_block * sb)
+{
+	unsigned long count = 0;
+	int i;
+
+	for (i = 0; i < EXT3_SB(sb)->s_groups_count; i++) {
+		struct ext3_group_desc *gdp = ext3_get_group_desc (sb, i, NULL);
+		if (!gdp)
+			continue;
+		count += le16_to_cpu(gdp->bg_used_dirs_count);
+	}
+	return count;
+}
+
+#ifdef CONFIG_EXT3_CHECK
+/* Called at mount-time, super-block is locked */
+void ext3_check_inodes_bitmap (struct super_block * sb)
+{
+	struct ext3_super_block * es;
+	unsigned long desc_count, bitmap_count, x;
+	struct buffer_head *bitmap_bh = NULL;
+	struct ext3_group_desc * gdp;
+	int i;
+
+	es = EXT3_SB(sb)->s_es;
+	desc_count = 0;
+	bitmap_count = 0;
+	gdp = NULL;
+	for (i = 0; i < EXT3_SB(sb)->s_groups_count; i++) {
+		gdp = ext3_get_group_desc (sb, i, NULL);
+		if (!gdp)
+			continue;
+		desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
+		brelse(bitmap_bh);
+		bitmap_bh = read_inode_bitmap(sb, i);
+		if (!bitmap_bh)
+			continue;
+
+		x = ext3_count_free(bitmap_bh, EXT3_INODES_PER_GROUP(sb) / 8);
+		if (le16_to_cpu(gdp->bg_free_inodes_count) != x)
+			ext3_error (sb, "ext3_check_inodes_bitmap",
+				    "Wrong free inodes count in group %d, "
+				    "stored = %d, counted = %lu", i,
+				    le16_to_cpu(gdp->bg_free_inodes_count), x);
+		bitmap_count += x;
+	}
+	brelse(bitmap_bh);
+	if (le32_to_cpu(es->s_free_inodes_count) != bitmap_count)
+		ext3_error (sb, "ext3_check_inodes_bitmap",
+			    "Wrong free inodes count in super block, "
+			    "stored = %lu, counted = %lu",
+			    (unsigned long)le32_to_cpu(es->s_free_inodes_count),
+			    bitmap_count);
+}
+#endif

fs/ext3/ioctl.c

@@ -0,0 +1,243 @@
+/*
+ * linux/fs/ext3/ioctl.c
+ *
+ * Copyright (C) 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ */
+
+#include <linux/fs.h>
+#include <linux/jbd.h>
+#include <linux/ext3_fs.h>
+#include <linux/ext3_jbd.h>
+#include <linux/time.h>
+#include <asm/uaccess.h>
+
+
+int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
+		unsigned long arg)
+{
+	struct ext3_inode_info *ei = EXT3_I(inode);
+	unsigned int flags;
+	unsigned short rsv_window_size;
+
+	ext3_debug ("cmd = %u, arg = %lu\n", cmd, arg);
+
+	switch (cmd) {
+	case EXT3_IOC_GETFLAGS:
+		flags = ei->i_flags & EXT3_FL_USER_VISIBLE;
+		return put_user(flags, (int __user *) arg);
+	case EXT3_IOC_SETFLAGS: {
+		handle_t *handle = NULL;
+		int err;
+		struct ext3_iloc iloc;
+		unsigned int oldflags;
+		unsigned int jflag;
+
+		if (IS_RDONLY(inode))
+			return -EROFS;
+
+		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+			return -EACCES;
+
+		if (get_user(flags, (int __user *) arg))
+			return -EFAULT;
+
+		if (!S_ISDIR(inode->i_mode))
+			flags &= ~EXT3_DIRSYNC_FL;
+
+		oldflags = ei->i_flags;
+
+		/* The JOURNAL_DATA flag is modifiable only by root */
+		jflag = flags & EXT3_JOURNAL_DATA_FL;
+
+		/*
+		 * The IMMUTABLE and APPEND_ONLY flags can only be changed by
+		 * the relevant capability.
+		 *
+		 * This test looks nicer. Thanks to Pauline Middelink
+		 */
+		if ((flags ^ oldflags) & (EXT3_APPEND_FL | EXT3_IMMUTABLE_FL)) {
+			if (!capable(CAP_LINUX_IMMUTABLE))
+				return -EPERM;
+		}
+
+		/*
+		 * The JOURNAL_DATA flag can only be changed by
+		 * the relevant capability.
+		 */
+		if ((jflag ^ oldflags) & (EXT3_JOURNAL_DATA_FL)) {
+			if (!capable(CAP_SYS_RESOURCE))
+				return -EPERM;
+		}
+
+
+		handle = ext3_journal_start(inode, 1);
+		if (IS_ERR(handle))
+			return PTR_ERR(handle);
+		if (IS_SYNC(inode))
+			handle->h_sync = 1;
+		err = ext3_reserve_inode_write(handle, inode, &iloc);
+		if (err)
+			goto flags_err;
+
+		flags = flags & EXT3_FL_USER_MODIFIABLE;
+		flags |= oldflags & ~EXT3_FL_USER_MODIFIABLE;
+		ei->i_flags = flags;
+
+		ext3_set_inode_flags(inode);
+		inode->i_ctime = CURRENT_TIME_SEC;
+
+		err = ext3_mark_iloc_dirty(handle, inode, &iloc);
+flags_err:
+		ext3_journal_stop(handle);
+		if (err)
+			return err;
+
+		if ((jflag ^ oldflags) & (EXT3_JOURNAL_DATA_FL))
+			err = ext3_change_inode_journal_flag(inode, jflag);
+		return err;
+	}
+	case EXT3_IOC_GETVERSION:
+	case EXT3_IOC_GETVERSION_OLD:
+		return put_user(inode->i_generation, (int __user *) arg);
+	case EXT3_IOC_SETVERSION:
+	case EXT3_IOC_SETVERSION_OLD: {
+		handle_t *handle;
+		struct ext3_iloc iloc;
+		__u32 generation;
+		int err;
+
+		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+			return -EPERM;
+		if (IS_RDONLY(inode))
+			return -EROFS;
+		if (get_user(generation, (int __user *) arg))
+			return -EFAULT;
+
+		handle = ext3_journal_start(inode, 1);
+		if (IS_ERR(handle))
+			return PTR_ERR(handle);
+		err = ext3_reserve_inode_write(handle, inode, &iloc);
+		if (err == 0) {
+			inode->i_ctime = CURRENT_TIME_SEC;
+			inode->i_generation = generation;
+			err = ext3_mark_iloc_dirty(handle, inode, &iloc);
+		}
+		ext3_journal_stop(handle);
+		return err;
+	}
+#ifdef CONFIG_JBD_DEBUG
+	case EXT3_IOC_WAIT_FOR_READONLY:
+		/*
+		 * This is racy - by the time we're woken up and running,
+		 * the superblock could be released.  And the module could
+		 * have been unloaded.  So sue me.
+		 *
+		 * Returns 1 if it slept, else zero.
+		 */
+		{
+			struct super_block *sb = inode->i_sb;
+			DECLARE_WAITQUEUE(wait, current);
+			int ret = 0;
+
+			set_current_state(TASK_INTERRUPTIBLE);
+			add_wait_queue(&EXT3_SB(sb)->ro_wait_queue, &wait);
+			if (timer_pending(&EXT3_SB(sb)->turn_ro_timer)) {
+				schedule();
+				ret = 1;
+			}
+			remove_wait_queue(&EXT3_SB(sb)->ro_wait_queue, &wait);
+			return ret;
+		}
+#endif
+	case EXT3_IOC_GETRSVSZ:
+		if (test_opt(inode->i_sb, RESERVATION)
+			&& S_ISREG(inode->i_mode)
+			&& ei->i_block_alloc_info) {
+			rsv_window_size = ei->i_block_alloc_info->rsv_window_node.rsv_goal_size;
+			return put_user(rsv_window_size, (int __user *)arg);
+		}
+		return -ENOTTY;
+	case EXT3_IOC_SETRSVSZ: {
+
+		if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode))
+			return -ENOTTY;
+
+		if (IS_RDONLY(inode))
+			return -EROFS;
+
+		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+			return -EACCES;
+
+		if (get_user(rsv_window_size, (int __user *)arg))
+			return -EFAULT;
+
+		if (rsv_window_size > EXT3_MAX_RESERVE_BLOCKS)
+			rsv_window_size = EXT3_MAX_RESERVE_BLOCKS;
+
+		/*
+		 * need to allocate reservation structure for this inode
+		 * before set the window size
+		 */
+		down(&ei->truncate_sem);
+		if (!ei->i_block_alloc_info)
+			ext3_init_block_alloc_info(inode);
+
+		if (ei->i_block_alloc_info){
+			struct ext3_reserve_window_node *rsv = &ei->i_block_alloc_info->rsv_window_node;
+			rsv->rsv_goal_size = rsv_window_size;
+		}
+		up(&ei->truncate_sem);
+		return 0;
+	}
+	case EXT3_IOC_GROUP_EXTEND: {
+		unsigned long n_blocks_count;
+		struct super_block *sb = inode->i_sb;
+		int err;
+
+		if (!capable(CAP_SYS_RESOURCE))
+			return -EPERM;
+
+		if (IS_RDONLY(inode))
+			return -EROFS;
+
+		if (get_user(n_blocks_count, (__u32 __user *)arg))
+			return -EFAULT;
+
+		err = ext3_group_extend(sb, EXT3_SB(sb)->s_es, n_blocks_count);
+		journal_lock_updates(EXT3_SB(sb)->s_journal);
+		journal_flush(EXT3_SB(sb)->s_journal);
+		journal_unlock_updates(EXT3_SB(sb)->s_journal);
+
+		return err;
+	}
+	case EXT3_IOC_GROUP_ADD: {
+		struct ext3_new_group_data input;
+		struct super_block *sb = inode->i_sb;
+		int err;
+
+		if (!capable(CAP_SYS_RESOURCE))
+			return -EPERM;
+
+		if (IS_RDONLY(inode))
+			return -EROFS;
+
+		if (copy_from_user(&input, (struct ext3_new_group_input __user *)arg,
+				sizeof(input)))
+			return -EFAULT;
+
+		err = ext3_group_add(sb, &input);
+		journal_lock_updates(EXT3_SB(sb)->s_journal);
+		journal_flush(EXT3_SB(sb)->s_journal);
+		journal_unlock_updates(EXT3_SB(sb)->s_journal);
+
+		return err;
+	}
+
+
+	default:
+		return -ENOTTY;
+	}
+}

fs/ext3/resize.c

@@ -0,0 +1,996 @@
+/*
+ *  linux/fs/ext3/resize.c
+ *
+ * Support for resizing an ext3 filesystem while it is mounted.
+ *
+ * Copyright (C) 2001, 2002 Andreas Dilger <adilger@clusterfs.com>
+ *
+ * This could probably be made into a module, because it is not often in use.
+ */
+
+#include <linux/config.h>
+
+#define EXT3FS_DEBUG
+
+#include <linux/sched.h>
+#include <linux/smp_lock.h>
+#include <linux/ext3_jbd.h>
+
+#include <linux/errno.h>
+#include <linux/slab.h>
+
+
+#define outside(b, first, last)	((b) < (first) || (b) >= (last))
+#define inside(b, first, last)	((b) >= (first) && (b) < (last))
+
+static int verify_group_input(struct super_block *sb,
+			      struct ext3_new_group_data *input)
+{
+	struct ext3_sb_info *sbi = EXT3_SB(sb);
+	struct ext3_super_block *es = sbi->s_es;
+	unsigned start = le32_to_cpu(es->s_blocks_count);
+	unsigned end = start + input->blocks_count;
+	unsigned group = input->group;
+	unsigned itend = input->inode_table + EXT3_SB(sb)->s_itb_per_group;
+	unsigned overhead = ext3_bg_has_super(sb, group) ?
+		(1 + ext3_bg_num_gdb(sb, group) +
+		 le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
+	unsigned metaend = start + overhead;
+	struct buffer_head *bh = NULL;
+	int free_blocks_count;
+	int err = -EINVAL;
+
+	input->free_blocks_count = free_blocks_count =
+		input->blocks_count - 2 - overhead - sbi->s_itb_per_group;
+
+	if (test_opt(sb, DEBUG))
+		printk(KERN_DEBUG "EXT3-fs: adding %s group %u: %u blocks "
+		       "(%d free, %u reserved)\n",
+		       ext3_bg_has_super(sb, input->group) ? "normal" :
+		       "no-super", input->group, input->blocks_count,
+		       free_blocks_count, input->reserved_blocks);
+
+	if (group != sbi->s_groups_count)
+		ext3_warning(sb, __FUNCTION__,
+			     "Cannot add at group %u (only %lu groups)",
+			     input->group, sbi->s_groups_count);
+	else if ((start - le32_to_cpu(es->s_first_data_block)) %
+		 EXT3_BLOCKS_PER_GROUP(sb))
+		ext3_warning(sb, __FUNCTION__, "Last group not full");
+	else if (input->reserved_blocks > input->blocks_count / 5)
+		ext3_warning(sb, __FUNCTION__, "Reserved blocks too high (%u)",
+			     input->reserved_blocks);
+	else if (free_blocks_count < 0)
+		ext3_warning(sb, __FUNCTION__, "Bad blocks count %u",
+			     input->blocks_count);
+	else if (!(bh = sb_bread(sb, end - 1)))
+		ext3_warning(sb, __FUNCTION__, "Cannot read last block (%u)",
+			     end - 1);
+	else if (outside(input->block_bitmap, start, end))
+		ext3_warning(sb, __FUNCTION__,
+			     "Block bitmap not in group (block %u)",
+			     input->block_bitmap);
+	else if (outside(input->inode_bitmap, start, end))
+		ext3_warning(sb, __FUNCTION__,
+			     "Inode bitmap not in group (block %u)",
+			     input->inode_bitmap);
+	else if (outside(input->inode_table, start, end) ||
+	         outside(itend - 1, start, end))
+		ext3_warning(sb, __FUNCTION__,
+			     "Inode table not in group (blocks %u-%u)",
+			     input->inode_table, itend - 1);
+	else if (input->inode_bitmap == input->block_bitmap)
+		ext3_warning(sb, __FUNCTION__,
+			     "Block bitmap same as inode bitmap (%u)",
+			     input->block_bitmap);
+	else if (inside(input->block_bitmap, input->inode_table, itend))
+		ext3_warning(sb, __FUNCTION__,
+			     "Block bitmap (%u) in inode table (%u-%u)",
+			     input->block_bitmap, input->inode_table, itend-1);
+	else if (inside(input->inode_bitmap, input->inode_table, itend))
+		ext3_warning(sb, __FUNCTION__,
+			     "Inode bitmap (%u) in inode table (%u-%u)",
+			     input->inode_bitmap, input->inode_table, itend-1);
+	else if (inside(input->block_bitmap, start, metaend))
+		ext3_warning(sb, __FUNCTION__,
+			     "Block bitmap (%u) in GDT table (%u-%u)",
+			     input->block_bitmap, start, metaend - 1);
+	else if (inside(input->inode_bitmap, start, metaend))
+		ext3_warning(sb, __FUNCTION__,
+			     "Inode bitmap (%u) in GDT table (%u-%u)",
+			     input->inode_bitmap, start, metaend - 1);
+	else if (inside(input->inode_table, start, metaend) ||
+	         inside(itend - 1, start, metaend))
+		ext3_warning(sb, __FUNCTION__,
+			     "Inode table (%u-%u) overlaps GDT table (%u-%u)",
+			     input->inode_table, itend - 1, start, metaend - 1);
+	else
+		err = 0;
+	brelse(bh);
+
+	return err;
+}
+
+static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
+				  unsigned long blk)
+{
+	struct buffer_head *bh;
+	int err;
+
+	bh = sb_getblk(sb, blk);
+	if ((err = ext3_journal_get_write_access(handle, bh))) {
+		brelse(bh);
+		bh = ERR_PTR(err);
+	} else {
+		lock_buffer(bh);
+		memset(bh->b_data, 0, sb->s_blocksize);
+		set_buffer_uptodate(bh);
+		unlock_buffer(bh);
+	}
+
+	return bh;
+}
+
+/*
+ * To avoid calling the atomic setbit hundreds or thousands of times, we only
+ * need to use it within a single byte (to ensure we get endianness right).
+ * We can use memset for the rest of the bitmap as there are no other users.
+ */
+static void mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
+{
+	int i;
+
+	if (start_bit >= end_bit)
+		return;
+
+	ext3_debug("mark end bits +%d through +%d used\n", start_bit, end_bit);
+	for (i = start_bit; i < ((start_bit + 7) & ~7UL); i++)
+		ext3_set_bit(i, bitmap);
+	if (i < end_bit)
+		memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3);
+}
+
+/*
+ * Set up the block and inode bitmaps, and the inode table for the new group.
+ * This doesn't need to be part of the main transaction, since we are only
+ * changing blocks outside the actual filesystem.  We still do journaling to
+ * ensure the recovery is correct in case of a failure just after resize.
+ * If any part of this fails, we simply abort the resize.
+ */
+static int setup_new_group_blocks(struct super_block *sb,
+				  struct ext3_new_group_data *input)
+{
+	struct ext3_sb_info *sbi = EXT3_SB(sb);
+	unsigned long start = input->group * sbi->s_blocks_per_group +
+		le32_to_cpu(sbi->s_es->s_first_data_block);
+	int reserved_gdb = ext3_bg_has_super(sb, input->group) ?
+		le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0;
+	unsigned long gdblocks = ext3_bg_num_gdb(sb, input->group);
+	struct buffer_head *bh;
+	handle_t *handle;
+	unsigned long block;
+	int bit;
+	int i;
+	int err = 0, err2;
+
+	handle = ext3_journal_start_sb(sb, reserved_gdb + gdblocks +
+				       2 + sbi->s_itb_per_group);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	lock_super(sb);
+	if (input->group != sbi->s_groups_count) {
+		err = -EBUSY;
+		goto exit_journal;
+	}
+
+	if (IS_ERR(bh = bclean(handle, sb, input->block_bitmap))) {
+		err = PTR_ERR(bh);
+		goto exit_journal;
+	}
+
+	if (ext3_bg_has_super(sb, input->group)) {
+		ext3_debug("mark backup superblock %#04lx (+0)\n", start);
+		ext3_set_bit(0, bh->b_data);
+	}
+
+	/* Copy all of the GDT blocks into the backup in this group */
+	for (i = 0, bit = 1, block = start + 1;
+	     i < gdblocks; i++, block++, bit++) {
+		struct buffer_head *gdb;
+
+		ext3_debug("update backup group %#04lx (+%d)\n", block, bit);
+
+		gdb = sb_getblk(sb, block);
+		if ((err = ext3_journal_get_write_access(handle, gdb))) {
+			brelse(gdb);
+			goto exit_bh;
+		}
+		lock_buffer(bh);
+		memcpy(gdb->b_data, sbi->s_group_desc[i], bh->b_size);
+		set_buffer_uptodate(gdb);
+		unlock_buffer(bh);
+		ext3_journal_dirty_metadata(handle, gdb);
+		ext3_set_bit(bit, bh->b_data);
+		brelse(gdb);
+	}
+
+	/* Zero out all of the reserved backup group descriptor table blocks */
+	for (i = 0, bit = gdblocks + 1, block = start + bit;
+	     i < reserved_gdb; i++, block++, bit++) {
+		struct buffer_head *gdb;
+
+		ext3_debug("clear reserved block %#04lx (+%d)\n", block, bit);
+
+		if (IS_ERR(gdb = bclean(handle, sb, block))) {
+			err = PTR_ERR(bh);
+			goto exit_bh;
+		}
+		ext3_journal_dirty_metadata(handle, gdb);
+		ext3_set_bit(bit, bh->b_data);
+		brelse(gdb);
+	}
+	ext3_debug("mark block bitmap %#04x (+%ld)\n", input->block_bitmap,
+		   input->block_bitmap - start);
+	ext3_set_bit(input->block_bitmap - start, bh->b_data);
+	ext3_debug("mark inode bitmap %#04x (+%ld)\n", input->inode_bitmap,
+		   input->inode_bitmap - start);
+	ext3_set_bit(input->inode_bitmap - start, bh->b_data);
+
+	/* Zero out all of the inode table blocks */
+	for (i = 0, block = input->inode_table, bit = block - start;
+	     i < sbi->s_itb_per_group; i++, bit++, block++) {
+		struct buffer_head *it;
+
+		ext3_debug("clear inode block %#04x (+%ld)\n", block, bit);
+		if (IS_ERR(it = bclean(handle, sb, block))) {
+			err = PTR_ERR(it);
+			goto exit_bh;
+		}
+		ext3_journal_dirty_metadata(handle, it);
+		brelse(it);
+		ext3_set_bit(bit, bh->b_data);
+	}
+	mark_bitmap_end(input->blocks_count, EXT3_BLOCKS_PER_GROUP(sb),
+			bh->b_data);
+	ext3_journal_dirty_metadata(handle, bh);
+	brelse(bh);
+
+	/* Mark unused entries in inode bitmap used */
+	ext3_debug("clear inode bitmap %#04x (+%ld)\n",
+		   input->inode_bitmap, input->inode_bitmap - start);
+	if (IS_ERR(bh = bclean(handle, sb, input->inode_bitmap))) {
+		err = PTR_ERR(bh);
+		goto exit_journal;
+	}
+
+	mark_bitmap_end(EXT3_INODES_PER_GROUP(sb), EXT3_BLOCKS_PER_GROUP(sb),
+			bh->b_data);
+	ext3_journal_dirty_metadata(handle, bh);
+exit_bh:
+	brelse(bh);
+
+exit_journal:
+	unlock_super(sb);
+	if ((err2 = ext3_journal_stop(handle)) && !err)
+		err = err2;
+
+	return err;
+}
+
+/*
+ * Iterate through the groups which hold BACKUP superblock/GDT copies in an
+ * ext3 filesystem.  The counters should be initialized to 1, 5, and 7 before
+ * calling this for the first time.  In a sparse filesystem it will be the
+ * sequence of powers of 3, 5, and 7: 1, 3, 5, 7, 9, 25, 27, 49, 81, ...
+ * For a non-sparse filesystem it will be every group: 1, 2, 3, 4, ...
+ */
+static unsigned ext3_list_backups(struct super_block *sb, unsigned *three,
+				  unsigned *five, unsigned *seven)
+{
+	unsigned *min = three;
+	int mult = 3;
+	unsigned ret;
+
+	if (!EXT3_HAS_RO_COMPAT_FEATURE(sb,
+					EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
+		ret = *min;
+		*min += 1;
+		return ret;
+	}
+
+	if (*five < *min) {
+		min = five;
+		mult = 5;
+	}
+	if (*seven < *min) {
+		min = seven;
+		mult = 7;
+	}
+
+	ret = *min;
+	*min *= mult;
+
+	return ret;
+}
+
+/*
+ * Check that all of the backup GDT blocks are held in the primary GDT block.
+ * It is assumed that they are stored in group order.  Returns the number of
+ * groups in current filesystem that have BACKUPS, or -ve error code.
+ */
+static int verify_reserved_gdb(struct super_block *sb,
+			       struct buffer_head *primary)
+{
+	const unsigned long blk = primary->b_blocknr;
+	const unsigned long end = EXT3_SB(sb)->s_groups_count;
+	unsigned three = 1;
+	unsigned five = 5;
+	unsigned seven = 7;
+	unsigned grp;
+	__u32 *p = (__u32 *)primary->b_data;
+	int gdbackups = 0;
+
+	while ((grp = ext3_list_backups(sb, &three, &five, &seven)) < end) {
+		if (le32_to_cpu(*p++) != grp * EXT3_BLOCKS_PER_GROUP(sb) + blk){
+			ext3_warning(sb, __FUNCTION__,
+				     "reserved GDT %ld missing grp %d (%ld)\n",
+				     blk, grp,
+				     grp * EXT3_BLOCKS_PER_GROUP(sb) + blk);
+			return -EINVAL;
+		}
+		if (++gdbackups > EXT3_ADDR_PER_BLOCK(sb))
+			return -EFBIG;
+	}
+
+	return gdbackups;
+}
+
+/*
+ * Called when we need to bring a reserved group descriptor table block into
+ * use from the resize inode.  The primary copy of the new GDT block currently
+ * is an indirect block (under the double indirect block in the resize inode).
+ * The new backup GDT blocks will be stored as leaf blocks in this indirect
+ * block, in group order.  Even though we know all the block numbers we need,
+ * we check to ensure that the resize inode has actually reserved these blocks.
+ *
+ * Don't need to update the block bitmaps because the blocks are still in use.
+ *
+ * We get all of the error cases out of the way, so that we are sure to not
+ * fail once we start modifying the data on disk, because JBD has no rollback.
+ */
+static int add_new_gdb(handle_t *handle, struct inode *inode,
+		       struct ext3_new_group_data *input,
+		       struct buffer_head **primary)
+{
+	struct super_block *sb = inode->i_sb;
+	struct ext3_super_block *es = EXT3_SB(sb)->s_es;
+	unsigned long gdb_num = input->group / EXT3_DESC_PER_BLOCK(sb);
+	unsigned long gdblock = EXT3_SB(sb)->s_sbh->b_blocknr + 1 + gdb_num;
+	struct buffer_head **o_group_desc, **n_group_desc;
+	struct buffer_head *dind;
+	int gdbackups;
+	struct ext3_iloc iloc;
+	__u32 *data;
+	int err;
+
+	if (test_opt(sb, DEBUG))
+		printk(KERN_DEBUG
+		       "EXT3-fs: ext3_add_new_gdb: adding group block %lu\n",
+		       gdb_num);
+
+	/*
+	 * If we are not using the primary superblock/GDT copy don't resize,
+	 * because the user tools have no way of handling this.  Probably a
+	 * bad time to do it anyways.
+	 */
+	if (EXT3_SB(sb)->s_sbh->b_blocknr !=
+	    le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block)) {
+		ext3_warning(sb, __FUNCTION__,
+			"won't resize using backup superblock at %llu\n",
+			(unsigned long long)EXT3_SB(sb)->s_sbh->b_blocknr);
+		return -EPERM;
+	}
+
+	*primary = sb_bread(sb, gdblock);
+	if (!*primary)
+		return -EIO;
+
+	if ((gdbackups = verify_reserved_gdb(sb, *primary)) < 0) {
+		err = gdbackups;
+		goto exit_bh;
+	}
+
+	data = EXT3_I(inode)->i_data + EXT3_DIND_BLOCK;
+	dind = sb_bread(sb, le32_to_cpu(*data));
+	if (!dind) {
+		err = -EIO;
+		goto exit_bh;
+	}
+
+	data = (__u32 *)dind->b_data;
+	if (le32_to_cpu(data[gdb_num % EXT3_ADDR_PER_BLOCK(sb)]) != gdblock) {
+		ext3_warning(sb, __FUNCTION__,
+			     "new group %u GDT block %lu not reserved\n",
+			     input->group, gdblock);
+		err = -EINVAL;
+		goto exit_dind;
+	}
+
+	if ((err = ext3_journal_get_write_access(handle, EXT3_SB(sb)->s_sbh)))
+		goto exit_dind;
+
+	if ((err = ext3_journal_get_write_access(handle, *primary)))
+		goto exit_sbh;
+
+	if ((err = ext3_journal_get_write_access(handle, dind)))
+		goto exit_primary;
+
+	/* ext3_reserve_inode_write() gets a reference on the iloc */
+	if ((err = ext3_reserve_inode_write(handle, inode, &iloc)))
+		goto exit_dindj;
+
+	n_group_desc = (struct buffer_head **)kmalloc((gdb_num + 1) *
+				sizeof(struct buffer_head *), GFP_KERNEL);
+	if (!n_group_desc) {
+		err = -ENOMEM;
+		ext3_warning (sb, __FUNCTION__,
+			      "not enough memory for %lu groups", gdb_num + 1);
+		goto exit_inode;
+	}
+
+	/*
+	 * Finally, we have all of the possible failures behind us...
+	 *
+	 * Remove new GDT block from inode double-indirect block and clear out
+	 * the new GDT block for use (which also "frees" the backup GDT blocks
+	 * from the reserved inode).  We don't need to change the bitmaps for
+	 * these blocks, because they are marked as in-use from being in the
+	 * reserved inode, and will become GDT blocks (primary and backup).
+	 */
+	data[gdb_num % EXT3_ADDR_PER_BLOCK(sb)] = 0;
+	ext3_journal_dirty_metadata(handle, dind);
+	brelse(dind);
+	inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
+	ext3_mark_iloc_dirty(handle, inode, &iloc);
+	memset((*primary)->b_data, 0, sb->s_blocksize);
+	ext3_journal_dirty_metadata(handle, *primary);
+
+	o_group_desc = EXT3_SB(sb)->s_group_desc;
+	memcpy(n_group_desc, o_group_desc,
+	       EXT3_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
+	n_group_desc[gdb_num] = *primary;
+	EXT3_SB(sb)->s_group_desc = n_group_desc;
+	EXT3_SB(sb)->s_gdb_count++;
+	kfree(o_group_desc);
+
+	es->s_reserved_gdt_blocks =
+		cpu_to_le16(le16_to_cpu(es->s_reserved_gdt_blocks) - 1);
+	ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh);
+
+	return 0;
+
+exit_inode:
+	//ext3_journal_release_buffer(handle, iloc.bh);
+	brelse(iloc.bh);
+exit_dindj:
+	//ext3_journal_release_buffer(handle, dind);
+exit_primary:
+	//ext3_journal_release_buffer(handle, *primary);
+exit_sbh:
+	//ext3_journal_release_buffer(handle, *primary);
+exit_dind:
+	brelse(dind);
+exit_bh:
+	brelse(*primary);
+
+	ext3_debug("leaving with error %d\n", err);
+	return err;
+}
+
+/*
+ * Called when we are adding a new group which has a backup copy of each of
+ * the GDT blocks (i.e. sparse group) and there are reserved GDT blocks.
+ * We need to add these reserved backup GDT blocks to the resize inode, so
+ * that they are kept for future resizing and not allocated to files.
+ *
+ * Each reserved backup GDT block will go into a different indirect block.
+ * The indirect blocks are actually the primary reserved GDT blocks,
+ * so we know in advance what their block numbers are.  We only get the
+ * double-indirect block to verify it is pointing to the primary reserved
+ * GDT blocks so we don't overwrite a data block by accident.  The reserved
+ * backup GDT blocks are stored in their reserved primary GDT block.
+ */
+static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
+			      struct ext3_new_group_data *input)
+{
+	struct super_block *sb = inode->i_sb;
+	int reserved_gdb =le16_to_cpu(EXT3_SB(sb)->s_es->s_reserved_gdt_blocks);
+	struct buffer_head **primary;
+	struct buffer_head *dind;
+	struct ext3_iloc iloc;
+	unsigned long blk;
+	__u32 *data, *end;
+	int gdbackups = 0;
+	int res, i;
+	int err;
+
+	primary = kmalloc(reserved_gdb * sizeof(*primary), GFP_KERNEL);
+	if (!primary)
+		return -ENOMEM;
+
+	data = EXT3_I(inode)->i_data + EXT3_DIND_BLOCK;
+	dind = sb_bread(sb, le32_to_cpu(*data));
+	if (!dind) {
+		err = -EIO;
+		goto exit_free;
+	}
+
+	blk = EXT3_SB(sb)->s_sbh->b_blocknr + 1 + EXT3_SB(sb)->s_gdb_count;
+	data = (__u32 *)dind->b_data + EXT3_SB(sb)->s_gdb_count;
+	end = (__u32 *)dind->b_data + EXT3_ADDR_PER_BLOCK(sb);
+
+	/* Get each reserved primary GDT block and verify it holds backups */
+	for (res = 0; res < reserved_gdb; res++, blk++) {
+		if (le32_to_cpu(*data) != blk) {
+			ext3_warning(sb, __FUNCTION__,
+				     "reserved block %lu not at offset %ld\n",
+				     blk, (long)(data - (__u32 *)dind->b_data));
+			err = -EINVAL;
+			goto exit_bh;
+		}
+		primary[res] = sb_bread(sb, blk);
+		if (!primary[res]) {
+			err = -EIO;
+			goto exit_bh;
+		}
+		if ((gdbackups = verify_reserved_gdb(sb, primary[res])) < 0) {
+			brelse(primary[res]);
+			err = gdbackups;
+			goto exit_bh;
+		}
+		if (++data >= end)
+			data = (__u32 *)dind->b_data;
+	}
+
+	for (i = 0; i < reserved_gdb; i++) {
+		if ((err = ext3_journal_get_write_access(handle, primary[i]))) {
+			/*
+			int j;
+			for (j = 0; j < i; j++)
+				ext3_journal_release_buffer(handle, primary[j]);
+			 */
+			goto exit_bh;
+		}
+	}
+
+	if ((err = ext3_reserve_inode_write(handle, inode, &iloc)))
+		goto exit_bh;
+
+	/*
+	 * Finally we can add each of the reserved backup GDT blocks from
+	 * the new group to its reserved primary GDT block.
+	 */
+	blk = input->group * EXT3_BLOCKS_PER_GROUP(sb);
+	for (i = 0; i < reserved_gdb; i++) {
+		int err2;
+		data = (__u32 *)primary[i]->b_data;
+		/* printk("reserving backup %lu[%u] = %lu\n",
+		       primary[i]->b_blocknr, gdbackups,
+		       blk + primary[i]->b_blocknr); */
+		data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr);
+		err2 = ext3_journal_dirty_metadata(handle, primary[i]);
+		if (!err)
+			err = err2;
+	}
+	inode->i_blocks += reserved_gdb * sb->s_blocksize >> 9;
+	ext3_mark_iloc_dirty(handle, inode, &iloc);
+
+exit_bh:
+	while (--res >= 0)
+		brelse(primary[res]);
+	brelse(dind);
+
+exit_free:
+	kfree(primary);
+
+	return err;
+}
+
+/*
+ * Update the backup copies of the ext3 metadata.  These don't need to be part
+ * of the main resize transaction, because e2fsck will re-write them if there
+ * is a problem (basically only OOM will cause a problem).  However, we
+ * _should_ update the backups if possible, in case the primary gets trashed
+ * for some reason and we need to run e2fsck from a backup superblock.  The
+ * 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.
+ */
+static void update_backups(struct super_block *sb,
+			   int blk_off, char *data, int size)
+{
+	struct ext3_sb_info *sbi = EXT3_SB(sb);
+	const unsigned long last = sbi->s_groups_count;
+	const int bpg = EXT3_BLOCKS_PER_GROUP(sb);
+	unsigned three = 1;
+	unsigned five = 5;
+	unsigned seven = 7;
+	unsigned group;
+	int rest = sb->s_blocksize - size;
+	handle_t *handle;
+	int err = 0, err2;
+
+	handle = ext3_journal_start_sb(sb, EXT3_MAX_TRANS_DATA);
+	if (IS_ERR(handle)) {
+		group = 1;
+		err = PTR_ERR(handle);
+		goto exit_err;
+	}
+
+	while ((group = ext3_list_backups(sb, &three, &five, &seven)) < last) {
+		struct buffer_head *bh;
+
+		/* Out of journal space, and can't get more - abort - so sad */
+		if (handle->h_buffer_credits == 0 &&
+		    ext3_journal_extend(handle, EXT3_MAX_TRANS_DATA) &&
+		    (err = ext3_journal_restart(handle, EXT3_MAX_TRANS_DATA)))
+			break;
+
+		bh = sb_getblk(sb, group * bpg + blk_off);
+		ext3_debug(sb, __FUNCTION__, "update metadata backup %#04lx\n",
+			   bh->b_blocknr);
+		if ((err = ext3_journal_get_write_access(handle, bh)))
+			break;
+		lock_buffer(bh);
+		memcpy(bh->b_data, data, size);
+		if (rest)
+			memset(bh->b_data + size, 0, rest);
+		set_buffer_uptodate(bh);
+		unlock_buffer(bh);
+		ext3_journal_dirty_metadata(handle, bh);
+		brelse(bh);
+	}
+	if ((err2 = ext3_journal_stop(handle)) && !err)
+		err = err2;
+
+	/*
+	 * Ugh! Need to have e2fsck write the backup copies.  It is too
+	 * late to revert the resize, we shouldn't fail just because of
+	 * the backup copies (they are only needed in case of corruption).
+	 *
+	 * However, if we got here we have a journal problem too, so we
+	 * can't really start a transaction to mark the superblock.
+	 * Chicken out and just set the flag on the hope it will be written
+	 * to disk, and if not - we will simply wait until next fsck.
+	 */
+exit_err:
+	if (err) {
+		ext3_warning(sb, __FUNCTION__,
+			     "can't update backup for group %d (err %d), "
+			     "forcing fsck on next reboot\n", group, err);
+		sbi->s_mount_state &= ~EXT3_VALID_FS;
+		sbi->s_es->s_state &= ~cpu_to_le16(EXT3_VALID_FS);
+		mark_buffer_dirty(sbi->s_sbh);
+	}
+}
+
+/* Add group descriptor data to an existing or new group descriptor block.
+ * Ensure we handle all possible error conditions _before_ we start modifying
+ * the filesystem, because we cannot abort the transaction and not have it
+ * write the data to disk.
+ *
+ * If we are on a GDT block boundary, we need to get the reserved GDT block.
+ * Otherwise, we may need to add backup GDT blocks for a sparse group.
+ *
+ * We only need to hold the superblock lock while we are actually adding
+ * in the new group's counts to the superblock.  Prior to that we have
+ * not really "added" the group at all.  We re-check that we are still
+ * adding in the last group in case things have changed since verifying.
+ */
+int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
+{
+	struct ext3_sb_info *sbi = EXT3_SB(sb);
+	struct ext3_super_block *es = sbi->s_es;
+	int reserved_gdb = ext3_bg_has_super(sb, input->group) ?
+		le16_to_cpu(es->s_reserved_gdt_blocks) : 0;
+	struct buffer_head *primary = NULL;
+	struct ext3_group_desc *gdp;
+	struct inode *inode = NULL;
+	handle_t *handle;
+	int gdb_off, gdb_num;
+	int err, err2;
+
+	gdb_num = input->group / EXT3_DESC_PER_BLOCK(sb);
+	gdb_off = input->group % EXT3_DESC_PER_BLOCK(sb);
+
+	if (gdb_off == 0 && !EXT3_HAS_RO_COMPAT_FEATURE(sb,
+					EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
+		ext3_warning(sb, __FUNCTION__,
+			     "Can't resize non-sparse filesystem further\n");
+		return -EPERM;
+	}
+
+	if (reserved_gdb || gdb_off == 0) {
+		if (!EXT3_HAS_COMPAT_FEATURE(sb,
+					     EXT3_FEATURE_COMPAT_RESIZE_INODE)){
+			ext3_warning(sb, __FUNCTION__,
+				     "No reserved GDT blocks, can't resize\n");
+			return -EPERM;
+		}
+		inode = iget(sb, EXT3_RESIZE_INO);
+		if (!inode || is_bad_inode(inode)) {
+			ext3_warning(sb, __FUNCTION__,
+				     "Error opening resize inode\n");
+			iput(inode);
+			return -ENOENT;
+		}
+	}
+
+	if ((err = verify_group_input(sb, input)))
+		goto exit_put;
+
+	if ((err = setup_new_group_blocks(sb, input)))
+		goto exit_put;
+
+	/*
+	 * We will always be modifying at least the superblock and a GDT
+	 * block.  If we are adding a group past the last current GDT block,
+	 * we will also modify the inode and the dindirect block.  If we
+	 * are adding a group with superblock/GDT backups  we will also
+	 * modify each of the reserved GDT dindirect blocks.
+	 */
+	handle = ext3_journal_start_sb(sb,
+				       ext3_bg_has_super(sb, input->group) ?
+				       3 + reserved_gdb : 4);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		goto exit_put;
+	}
+
+	lock_super(sb);
+	if (input->group != EXT3_SB(sb)->s_groups_count) {
+		ext3_warning(sb, __FUNCTION__,
+			     "multiple resizers run on filesystem!\n");
+		goto exit_journal;
+	}
+
+	if ((err = ext3_journal_get_write_access(handle, sbi->s_sbh)))
+		goto exit_journal;
+
+	/*
+	 * We will only either add reserved group blocks to a backup group
+	 * or remove reserved blocks for the first group in a new group block.
+	 * Doing both would be mean more complex code, and sane people don't
+	 * use non-sparse filesystems anymore.  This is already checked above.
+	 */
+	if (gdb_off) {
+		primary = sbi->s_group_desc[gdb_num];
+		if ((err = ext3_journal_get_write_access(handle, primary)))
+			goto exit_journal;
+
+		if (reserved_gdb && ext3_bg_num_gdb(sb, input->group) &&
+		    (err = reserve_backup_gdb(handle, inode, input)))
+			goto exit_journal;
+	} else if ((err = add_new_gdb(handle, inode, input, &primary)))
+		goto exit_journal;
+
+	/*
+	 * OK, now we've set up the new group.  Time to make it active.
+	 *
+	 * Current kernels don't lock all allocations via lock_super(),
+	 * 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.
+	 *
+	 * The key field here is EXT3_SB(sb)->s_groups_count: as long as
+	 * that retains its old value, nobody is going to access the new
+	 * group.
+	 *
+	 * So first we update all the descriptor metadata for the new
+	 * group; then we update the total disk blocks count; then we
+	 * update the groups count to enable the group; then finally we
+	 * update the free space counts so that the system can start
+	 * using the new disk blocks.
+	 */
+
+	/* Update group descriptor block for new group */
+	gdp = (struct ext3_group_desc *)primary->b_data + gdb_off;
+
+	gdp->bg_block_bitmap = cpu_to_le32(input->block_bitmap);
+	gdp->bg_inode_bitmap = cpu_to_le32(input->inode_bitmap);
+	gdp->bg_inode_table = cpu_to_le32(input->inode_table);
+	gdp->bg_free_blocks_count = cpu_to_le16(input->free_blocks_count);
+	gdp->bg_free_inodes_count = cpu_to_le16(EXT3_INODES_PER_GROUP(sb));
+
+	/*
+	 * Make the new blocks and inodes valid next.  We do this before
+	 * increasing the group count so that once the group is enabled,
+	 * all of its blocks and inodes are already valid.
+	 *
+	 * We always allocate group-by-group, then block-by-block or
+	 * inode-by-inode within a group, so enabling these
+	 * blocks/inodes before the group is live won't actually let us
+	 * allocate the new space yet.
+	 */
+	es->s_blocks_count = cpu_to_le32(le32_to_cpu(es->s_blocks_count) +
+		input->blocks_count);
+	es->s_inodes_count = cpu_to_le32(le32_to_cpu(es->s_inodes_count) +
+		EXT3_INODES_PER_GROUP(sb));
+
+	/*
+	 * We need to protect s_groups_count against other CPUs seeing
+	 * inconsistent state in the superblock.
+	 *
+	 * The precise rules we use are:
+	 *
+	 * * Writers of s_groups_count *must* hold lock_super
+	 * 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
+	 * OR
+	 * * Readers must perform an smp_rmb() after reading the groups count
+	 *   and before reading any dependent data.
+	 *
+	 * NB. These rules can be relaxed when checking the group count
+	 * while freeing data, as we can only allocate from a block
+	 * group after serialising against the group count, and we can
+	 * only then free after serialising in turn against that
+	 * allocation.
+	 */
+	smp_wmb();
+
+	/* Update the global fs size fields */
+	EXT3_SB(sb)->s_groups_count++;
+
+	ext3_journal_dirty_metadata(handle, primary);
+
+	/* Update the reserved block counts only once the new group is
+	 * active. */
+	es->s_r_blocks_count = cpu_to_le32(le32_to_cpu(es->s_r_blocks_count) +
+		input->reserved_blocks);
+
+	/* Update the free space counts */
+	percpu_counter_mod(&sbi->s_freeblocks_counter,
+			   input->free_blocks_count);
+	percpu_counter_mod(&sbi->s_freeinodes_counter,
+			   EXT3_INODES_PER_GROUP(sb));
+
+	ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh);
+	sb->s_dirt = 1;
+
+exit_journal:
+	unlock_super(sb);
+	if ((err2 = ext3_journal_stop(handle)) && !err)
+		err = err2;
+	if (!err) {
+		update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es,
+			       sizeof(struct ext3_super_block));
+		update_backups(sb, primary->b_blocknr, primary->b_data,
+			       primary->b_size);
+	}
+exit_put:
+	iput(inode);
+	return err;
+} /* ext3_group_add */
+
+/* Extend the filesystem to the new number of blocks specified.  This entry
+ * point is only used to extend the current filesystem to the end of the last
+ * existing group.  It can be accessed via ioctl, or by "remount,resize=<size>"
+ * for emergencies (because it has no dependencies on reserved blocks).
+ *
+ * If we _really_ wanted, we could use default values to call ext3_group_add()
+ * allow the "remount" trick to work for arbitrary resizing, assuming enough
+ * GDT blocks are reserved to grow to the desired size.
+ */
+int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
+		      unsigned long n_blocks_count)
+{
+	unsigned long o_blocks_count;
+	unsigned long o_groups_count;
+	unsigned long last;
+	int add;
+	struct buffer_head * bh;
+	handle_t *handle;
+	int err, freed_blocks;
+
+	/* 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. */
+	o_blocks_count = le32_to_cpu(es->s_blocks_count);
+	o_groups_count = EXT3_SB(sb)->s_groups_count;
+
+	if (test_opt(sb, DEBUG))
+		printk(KERN_DEBUG "EXT3-fs: extending last group from %lu to %lu blocks\n",
+		       o_blocks_count, n_blocks_count);
+
+	if (n_blocks_count == 0 || n_blocks_count == o_blocks_count)
+		return 0;
+
+	if (n_blocks_count < o_blocks_count) {
+		ext3_warning(sb, __FUNCTION__,
+			     "can't shrink FS - resize aborted");
+		return -EBUSY;
+	}
+
+	/* Handle the remaining blocks in the last group only. */
+	last = (o_blocks_count - le32_to_cpu(es->s_first_data_block)) %
+		EXT3_BLOCKS_PER_GROUP(sb);
+
+	if (last == 0) {
+		ext3_warning(sb, __FUNCTION__,
+			     "need to use ext2online to resize further\n");
+		return -EPERM;
+	}
+
+	add = EXT3_BLOCKS_PER_GROUP(sb) - last;
+
+	if (o_blocks_count + add > n_blocks_count)
+		add = n_blocks_count - o_blocks_count;
+
+	if (o_blocks_count + add < n_blocks_count)
+		ext3_warning(sb, __FUNCTION__,
+			     "will only finish group (%lu blocks, %u new)",
+			     o_blocks_count + add, add);
+
+	/* See if the device is actually as big as what was requested */
+	bh = sb_bread(sb, o_blocks_count + add -1);
+	if (!bh) {
+		ext3_warning(sb, __FUNCTION__,
+			     "can't read last block, resize aborted");
+		return -ENOSPC;
+	}
+	brelse(bh);
+
+	/* We will update the superblock, one block bitmap, and
+	 * one group descriptor via ext3_free_blocks().
+	 */
+	handle = ext3_journal_start_sb(sb, 3);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		ext3_warning(sb, __FUNCTION__, "error %d on journal start",err);
+		goto exit_put;
+	}
+
+	lock_super(sb);
+	if (o_blocks_count != le32_to_cpu(es->s_blocks_count)) {
+		ext3_warning(sb, __FUNCTION__,
+			     "multiple resizers run on filesystem!\n");
+		err = -EBUSY;
+		goto exit_put;
+	}
+
+	if ((err = ext3_journal_get_write_access(handle,
+						 EXT3_SB(sb)->s_sbh))) {
+		ext3_warning(sb, __FUNCTION__,
+			     "error %d on journal write access", err);
+		unlock_super(sb);
+		ext3_journal_stop(handle);
+		goto exit_put;
+	}
+	es->s_blocks_count = cpu_to_le32(o_blocks_count + add);
+	ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh);
+	sb->s_dirt = 1;
+	unlock_super(sb);
+	ext3_debug("freeing blocks %ld through %ld\n", o_blocks_count,
+		   o_blocks_count + add);
+	ext3_free_blocks_sb(handle, sb, o_blocks_count, add, &freed_blocks);
+	ext3_debug("freed blocks %ld through %ld\n", o_blocks_count,
+		   o_blocks_count + add);
+	if ((err = ext3_journal_stop(handle)))
+		goto exit_put;
+	if (test_opt(sb, DEBUG))
+		printk(KERN_DEBUG "EXT3-fs: extended group to %u blocks\n",
+		       le32_to_cpu(es->s_blocks_count));
+	update_backups(sb, EXT3_SB(sb)->s_sbh->b_blocknr, (char *)es,
+		       sizeof(struct ext3_super_block));
+exit_put:
+	return err;
+} /* ext3_group_extend */

fs/ext3/symlink.c

@@ -0,0 +1,54 @@
+/*
+ *  linux/fs/ext3/symlink.c
+ *
+ * Only fast symlinks left here - the rest is done by generic code. AV, 1999
+ *
+ * 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/fs/minix/symlink.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  ext3 symlink handling code
+ */
+
+#include <linux/fs.h>
+#include <linux/jbd.h>
+#include <linux/ext3_fs.h>
+#include <linux/namei.h>
+#include "xattr.h"
+
+static int ext3_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	struct ext3_inode_info *ei = EXT3_I(dentry->d_inode);
+	nd_set_link(nd, (char*)ei->i_data);
+	return 0;
+}
+
+struct inode_operations ext3_symlink_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= page_follow_link_light,
+	.put_link	= page_put_link,
+#ifdef CONFIG_EXT3_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext3_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+};
+
+struct inode_operations ext3_fast_symlink_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= ext3_follow_link,
+#ifdef CONFIG_EXT3_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext3_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+};

fs/ext3/xattr.h

@@ -0,0 +1,135 @@
+/*
+  File: fs/ext3/xattr.h
+
+  On-disk format of extended attributes for the ext3 filesystem.
+
+  (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org>
+*/
+
+#include <linux/config.h>
+#include <linux/xattr.h>
+
+/* Magic value in attribute blocks */
+#define EXT3_XATTR_MAGIC		0xEA020000
+
+/* Maximum number of references to one attribute block */
+#define EXT3_XATTR_REFCOUNT_MAX		1024
+
+/* Name indexes */
+#define EXT3_XATTR_INDEX_USER			1
+#define EXT3_XATTR_INDEX_POSIX_ACL_ACCESS	2
+#define EXT3_XATTR_INDEX_POSIX_ACL_DEFAULT	3
+#define EXT3_XATTR_INDEX_TRUSTED		4
+#define	EXT3_XATTR_INDEX_LUSTRE			5
+#define EXT3_XATTR_INDEX_SECURITY	        6
+
+struct ext3_xattr_header {
+	__le32	h_magic;	/* magic number for identification */
+	__le32	h_refcount;	/* reference count */
+	__le32	h_blocks;	/* number of disk blocks used */
+	__le32	h_hash;		/* hash value of all attributes */
+	__u32	h_reserved[4];	/* zero right now */
+};
+
+struct ext3_xattr_ibody_header {
+	__le32	h_magic;	/* magic number for identification */
+};
+
+struct ext3_xattr_entry {
+	__u8	e_name_len;	/* length of name */
+	__u8	e_name_index;	/* attribute name index */
+	__le16	e_value_offs;	/* offset in disk block of value */
+	__le32	e_value_block;	/* disk block attribute is stored on (n/i) */
+	__le32	e_value_size;	/* size of attribute value */
+	__le32	e_hash;		/* hash value of name and value */
+	char	e_name[0];	/* attribute name */
+};
+
+#define EXT3_XATTR_PAD_BITS		2
+#define EXT3_XATTR_PAD		(1<<EXT3_XATTR_PAD_BITS)
+#define EXT3_XATTR_ROUND		(EXT3_XATTR_PAD-1)
+#define EXT3_XATTR_LEN(name_len) \
+	(((name_len) + EXT3_XATTR_ROUND + \
+	sizeof(struct ext3_xattr_entry)) & ~EXT3_XATTR_ROUND)
+#define EXT3_XATTR_NEXT(entry) \
+	( (struct ext3_xattr_entry *)( \
+	  (char *)(entry) + EXT3_XATTR_LEN((entry)->e_name_len)) )
+#define EXT3_XATTR_SIZE(size) \
+	(((size) + EXT3_XATTR_ROUND) & ~EXT3_XATTR_ROUND)
+
+# ifdef CONFIG_EXT3_FS_XATTR
+
+extern struct xattr_handler ext3_xattr_user_handler;
+extern struct xattr_handler ext3_xattr_trusted_handler;
+extern struct xattr_handler ext3_xattr_acl_access_handler;
+extern struct xattr_handler ext3_xattr_acl_default_handler;
+extern struct xattr_handler ext3_xattr_security_handler;
+
+extern ssize_t ext3_listxattr(struct dentry *, char *, size_t);
+
+extern int ext3_xattr_get(struct inode *, int, const char *, void *, size_t);
+extern int ext3_xattr_list(struct inode *, char *, size_t);
+extern int ext3_xattr_set(struct inode *, int, const char *, const void *, size_t, int);
+extern int ext3_xattr_set_handle(handle_t *, struct inode *, int, const char *, const void *, size_t, int);
+
+extern void ext3_xattr_delete_inode(handle_t *, struct inode *);
+extern void ext3_xattr_put_super(struct super_block *);
+
+extern int init_ext3_xattr(void);
+extern void exit_ext3_xattr(void);
+
+extern struct xattr_handler *ext3_xattr_handlers[];
+
+# else  /* CONFIG_EXT3_FS_XATTR */
+
+static inline int
+ext3_xattr_get(struct inode *inode, int name_index, const char *name,
+	       void *buffer, size_t size, int flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+ext3_xattr_list(struct inode *inode, void *buffer, size_t size)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+ext3_xattr_set(struct inode *inode, int name_index, const char *name,
+	       const void *value, size_t size, int flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+ext3_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
+	       const char *name, const void *value, size_t size, int flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void
+ext3_xattr_delete_inode(handle_t *handle, struct inode *inode)
+{
+}
+
+static inline void
+ext3_xattr_put_super(struct super_block *sb)
+{
+}
+
+static inline int
+init_ext3_xattr(void)
+{
+	return 0;
+}
+
+static inline void
+exit_ext3_xattr(void)
+{
+}
+
+#define ext3_xattr_handlers	NULL
+
+# endif  /* CONFIG_EXT3_FS_XATTR */

fs/ext3/xattr_security.c

@@ -0,0 +1,55 @@
+/*
+ * linux/fs/ext3/xattr_security.c
+ * Handler for storing security labels as extended attributes.
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/smp_lock.h>
+#include <linux/ext3_jbd.h>
+#include <linux/ext3_fs.h>
+#include "xattr.h"
+
+static size_t
+ext3_xattr_security_list(struct inode *inode, char *list, size_t list_size,
+			 const char *name, size_t name_len)
+{
+	const size_t prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1;
+	const size_t total_len = prefix_len + name_len + 1;
+
+
+	if (list && total_len <= list_size) {
+		memcpy(list, XATTR_SECURITY_PREFIX, prefix_len);
+		memcpy(list+prefix_len, name, name_len);
+		list[prefix_len + name_len] = '\0';
+	}
+	return total_len;
+}
+
+static int
+ext3_xattr_security_get(struct inode *inode, const char *name,
+		       void *buffer, size_t size)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	return ext3_xattr_get(inode, EXT3_XATTR_INDEX_SECURITY, name,
+			      buffer, size);
+}
+
+static int
+ext3_xattr_security_set(struct inode *inode, const char *name,
+		       const void *value, size_t size, int flags)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	return ext3_xattr_set(inode, EXT3_XATTR_INDEX_SECURITY, name,
+			      value, size, flags);
+}
+
+struct xattr_handler ext3_xattr_security_handler = {
+	.prefix	= XATTR_SECURITY_PREFIX,
+	.list	= ext3_xattr_security_list,
+	.get	= ext3_xattr_security_get,
+	.set	= ext3_xattr_security_set,
+};

fs/ext3/xattr_trusted.c

@@ -0,0 +1,65 @@
+/*
+ * linux/fs/ext3/xattr_trusted.c
+ * Handler for trusted extended attributes.
+ *
+ * Copyright (C) 2003 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/smp_lock.h>
+#include <linux/ext3_jbd.h>
+#include <linux/ext3_fs.h>
+#include "xattr.h"
+
+#define XATTR_TRUSTED_PREFIX "trusted."
+
+static size_t
+ext3_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
+			const char *name, size_t name_len)
+{
+	const size_t prefix_len = sizeof(XATTR_TRUSTED_PREFIX)-1;
+	const size_t total_len = prefix_len + name_len + 1;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return 0;
+
+	if (list && total_len <= list_size) {
+		memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len);
+		memcpy(list+prefix_len, name, name_len);
+		list[prefix_len + name_len] = '\0';
+	}
+	return total_len;
+}
+
+static int
+ext3_xattr_trusted_get(struct inode *inode, const char *name,
+		       void *buffer, size_t size)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	return ext3_xattr_get(inode, EXT3_XATTR_INDEX_TRUSTED, name,
+			      buffer, size);
+}
+
+static int
+ext3_xattr_trusted_set(struct inode *inode, const char *name,
+		       const void *value, size_t size, int flags)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	return ext3_xattr_set(inode, EXT3_XATTR_INDEX_TRUSTED, name,
+			      value, size, flags);
+}
+
+struct xattr_handler ext3_xattr_trusted_handler = {
+	.prefix	= XATTR_TRUSTED_PREFIX,
+	.list	= ext3_xattr_trusted_list,
+	.get	= ext3_xattr_trusted_get,
+	.set	= ext3_xattr_trusted_set,
+};

fs/ext3/xattr_user.c

@@ -0,0 +1,79 @@
+/*
+ * linux/fs/ext3/xattr_user.c
+ * Handler for extended user attributes.
+ *
+ * Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/smp_lock.h>
+#include <linux/ext3_jbd.h>
+#include <linux/ext3_fs.h>
+#include "xattr.h"
+
+#define XATTR_USER_PREFIX "user."
+
+static size_t
+ext3_xattr_user_list(struct inode *inode, char *list, size_t list_size,
+		     const char *name, size_t name_len)
+{
+	const size_t prefix_len = sizeof(XATTR_USER_PREFIX)-1;
+	const size_t total_len = prefix_len + name_len + 1;
+
+	if (!test_opt(inode->i_sb, XATTR_USER))
+		return 0;
+
+	if (list && total_len <= list_size) {
+		memcpy(list, XATTR_USER_PREFIX, prefix_len);
+		memcpy(list+prefix_len, name, name_len);
+		list[prefix_len + name_len] = '\0';
+	}
+	return total_len;
+}
+
+static int
+ext3_xattr_user_get(struct inode *inode, const char *name,
+		    void *buffer, size_t size)
+{
+	int error;
+
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	if (!test_opt(inode->i_sb, XATTR_USER))
+		return -EOPNOTSUPP;
+	error = permission(inode, MAY_READ, NULL);
+	if (error)
+		return error;
+
+	return ext3_xattr_get(inode, EXT3_XATTR_INDEX_USER, name, buffer, size);
+}
+
+static int
+ext3_xattr_user_set(struct inode *inode, const char *name,
+		    const void *value, size_t size, int flags)
+{
+	int error;
+
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	if (!test_opt(inode->i_sb, XATTR_USER))
+		return -EOPNOTSUPP;
+	if ( !S_ISREG(inode->i_mode) &&
+	    (!S_ISDIR(inode->i_mode) || inode->i_mode & S_ISVTX))
+		return -EPERM;
+	error = permission(inode, MAY_WRITE, NULL);
+	if (error)
+		return error;
+
+	return ext3_xattr_set(inode, EXT3_XATTR_INDEX_USER, name,
+			      value, size, flags);
+}
+
+struct xattr_handler ext3_xattr_user_handler = {
+	.prefix	= XATTR_USER_PREFIX,
+	.list	= ext3_xattr_user_list,
+	.get	= ext3_xattr_user_get,
+	.set	= ext3_xattr_user_set,
+};