21 files changed, 7523 insertions, 0 deletions

diff --git a/fs/ext2/CHANGES b/fs/ext2/CHANGES
new file mode 100644
index 000000000000..aa5aaf0e5911
--- /dev/null
+++ b/fs/ext2/CHANGES
@@ -0,0 +1,157 @@
+Changes from version 0.5a to version 0.5b
+=========================================
+	- Now that we have sysctl(), the immutable flag cannot be changed when
+	  the system is running at security level > 0.
+	- Some cleanups in the code.
+	- More consistency checks on directories.
+	- The ext2.diff patch from Tom May <ftom@netcom.com> has been
+	  integrated.  This patch replaces expensive "/" and "%" with
+	  cheap ">>" and "&" where possible.
+
+Changes from version 0.5 to version 0.5a
+========================================
+	- Zero the partial block following the end of the file when a file
+	  is truncated.
+	- Dates updated in the copyright.
+	- More checks when the filesystem is mounted: the count of blocks,
+	  fragments, and inodes per group is checked against the block size.
+	- The buffers used by the error routines are now static variables, to
+	  avoid using space on the kernel stack, as requested by Linus.
+	- Some cleanups in the error messages (some versions of syslog contain
+	  a bug which truncates an error message if it contains '\n').
+	- Check that no data can be written to a file past the 2GB limit.
+	- The famous readdir() bug has been fixed by Stephen Tweedie.
+	- Added a revision level in the superblock.
+	- Full support for O_SYNC flag of the open system call.
+	- New mount options: `resuid=#uid' and `resgid=#gid'.  `resuid' causes
+	  ext2fs to consider user #uid like root for the reserved blocks.
+	  `resgid' acts the same way with group #gid.  New fields in the
+	  superblock contain default values for resuid and resgid and can
+	  be modified by tune2fs.
+	  Idea comes from Rene Cougnenc <cougnenc@renux.frmug.fr.net>.
+	- New mount options: `bsddf' and `minixdf'.  `bsddf' causes ext2fs
+	  to remove the blocks used for FS structures from the total block
+	  count in statfs.  With `minixdf', ext2fs mimics Minix behavior
+	  in statfs (i.e. it returns the total number of blocks on the
+	  partition).  This is intended to make bde happy :-)
+	- New file attributes:
+	  - Immutable files cannot be modified.  Data cannot be written to
+	    these files.  They cannot be removed, renamed and new links cannot
+	    be created.  Even root cannot modify the files.  He has to remove
+	    the immutable attribute first.
+	  - Append-only files: can only be written in append-mode when writing.
+	    They cannot be removed, renamed and new links cannot be created.
+	    Note: files may only be added to an append-only directory.
+	  - No-dump files: the attribute is not used by the kernel.  My port
+	    of dump uses it to avoid backing up files which are not important.
+	- New check in ext2_check_dir_entry: the inode number is checked.
+	- Support for big file systems: the copy of the FS descriptor is now
+	  dynamically allocated (previous versions used a fixed size array).
+	  This allows to mount 2GB+ FS.
+	- Reorganization of the ext2_inode structure to allow other operating
+	  systems to create specific fields if they use ext2fs as their native
+	  file system.  Currently, ext2fs is only implemented in Linux but
+	  will soon be part of Gnu Hurd and of Masix.
+
+Changes from version 0.4b to version 0.5
+========================================
+	- New superblock fields: s_lastcheck and s_checkinterval added
+	  by Uwe Ohse <uwe@tirka.gun.de> to implement timedependent checks
+	  of the file system
+	- Real random numbers for secure rm added by Pierre del Perugia
+	  <delperug@gla.ecoledoc.ibp.fr>
+	- The mount warnings related to the state of a fs are not printed
+	  if the fs is mounted read-only, idea by Nick Holloway
+	  <alfie@dcs.warwick.ac.uk>
+
+Changes from version 0.4a to version 0.4b
+=========================================
+	- Copyrights changed to include the name of my laboratory.
+	- Clean up of balloc.c and ialloc.c.
+	- More consistency checks.
+	- Block preallocation added by Stephen Tweedie.
+	- Direct reads of directories disallowed.
+	- Readahead implemented in readdir by Stephen Tweedie.
+	- Bugs in block and inodes allocation fixed.
+	- Readahead implemented in ext2_find_entry by Chip Salzenberg.
+	- New mount options:
+	  `check=none|normal|strict'
+	  `debug'
+	  `errors=continue|remount-ro|panic'
+	  `grpid', `bsdgroups'
+	  `nocheck'
+	  `nogrpid', `sysvgroups'
+	- truncate() now tries to deallocate contiguous blocks in a single call
+	  to ext2_free_blocks().
+	- lots of cosmetic changes.
+
+Changes from version 0.4 to version 0.4a
+========================================
+        - the `sync' option support is now complete.  Version 0.4 was not
+          supporting it when truncating a file.  I have tested the synchronous
+          writes and they work but they make the system very slow :-(  I have
+          to work again on this to make it faster.
+        - when detecting an error on a mounted filesystem, version 0.4 used
+          to try to write a flag in the super block even if the filesystem had
+          been mounted read-only.  This is fixed.
+        - the `sb=#' option now causes the kernel code to use the filesystem
+          descriptors located at block #+1.  Version 0.4 used the superblock
+          backup located at block # but used the main copy of the descriptors.
+        - a new file attribute `S' is supported.  This attribute causes
+          synchronous writes but is applied to a file not to the entire file
+          system (thanks to Michael Kraehe <kraehe@bakunin.north.de> for
+          suggesting it).
+        - the directory cache is inhibited by default.  The cache management
+          code seems to be buggy and I have to look at it carefully before
+          using it again.
+        - deleting a file with the `s' attribute (secure deletion) causes its
+          blocks to be overwritten with random values not with zeros (thanks to
+          Michael A. Griffith <grif@cs.ucr.edu> for suggesting it).
+        - lots of cosmetic changes have been made.
+
+Changes from version 0.3 to version 0.4
+=======================================
+        - Three new mount options are supported: `check', `sync' and `sb=#'.
+          `check' tells the kernel code to make more consistency checks
+          when the file system is mounted.  Currently, the kernel code checks
+          that the blocks and inodes bitmaps are consistent with the free
+          blocks and inodes counts.  More checks will be added in future
+          releases.
+          `sync' tells the kernel code to use synchronous writes when updating
+          an inode, a bitmap, a directory entry or an indirect block.  This
+          can make the file system much slower but can be a big win for files
+          recovery in case of a crash (and we can now say to the BSD folks
+          that Linux also supports synchronous updates :-).
+          `sb=#' tells the kernel code to use an alternate super block instead
+          of its master copy.  `#' is the number of the block (counted in
+          1024 bytes blocks) which contains the alternate super block.
+          An ext2 file system typically contains backups of the super block
+          at blocks 8193, 16385, and so on.
+        - I have change the meaning of the valid flag used by e2fsck.  it
+          now contains the state of the file system.  If the kernel code
+          detects an inconsistency while the file system is mounted, it flags
+          it as erroneous and e2fsck will detect that on next run.
+        - The super block now contains a mount counter.  This counter is
+          incremented each time the file system is mounted read/write.   When
+          this counter becomes bigger than a maximal mount counts (also stored
+          in the super block), e2fsck checks the file system, even if it had
+          been unmounted cleanly, and resets this counter to 0.
+        - File attributes are now supported.  One can associate a set of
+          attributes to a file.  Three attributes are defined:
+          `c': the file is marked for automatic compression,
+          `s': the file is marked for secure deletion: when the file is
+          deleted, its blocks are zeroed and written back to the disk,
+          `u': the file is marked for undeletion: when the file is deleted,
+          its contents are saved to allow a future undeletion.
+          Currently, only the `s' attribute is implemented in the kernel
+          code.  Support for the other attributes will be added in a future
+          release.
+        - a few bugs related to times updates have been fixed by Bruce
+          Evans and me.
+        - a bug related to the links count of deleted inodes has been fixed.
+          Previous versions used to keep the links count set to 1 when a file
+          was deleted.  The new version now sets links_count to 0 when deleting
+          the last link.
+        - a race condition when deallocating an inode has been fixed by
+          Stephen Tweedie.
+
diff --git a/fs/ext2/Makefile b/fs/ext2/Makefile
new file mode 100644
index 000000000000..ee240a14e70f
--- /dev/null
+++ b/fs/ext2/Makefile
@@ -0,0 +1,12 @@
+#
+# Makefile for the linux ext2-filesystem routines.
+#
+
+obj-$(CONFIG_EXT2_FS) += ext2.o
+
+ext2-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \
+	  ioctl.o namei.o super.o symlink.o
+
+ext2-$(CONFIG_EXT2_FS_XATTR)	 += xattr.o xattr_user.o xattr_trusted.o
+ext2-$(CONFIG_EXT2_FS_POSIX_ACL) += acl.o
+ext2-$(CONFIG_EXT2_FS_SECURITY)	 += xattr_security.o
diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c
new file mode 100644
index 000000000000..8369ee8d28c4
--- /dev/null
+++ b/fs/ext2/acl.c
@@ -0,0 +1,518 @@
+/*
+ * linux/fs/ext2/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 "ext2.h"
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * Convert from filesystem to in-memory representation.
+ */
+static struct posix_acl *
+ext2_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(ext2_acl_header))
+		 return ERR_PTR(-EINVAL);
+	if (((ext2_acl_header *)value)->a_version !=
+	    cpu_to_le32(EXT2_ACL_VERSION))
+		return ERR_PTR(-EINVAL);
+	value = (char *)value + sizeof(ext2_acl_header);
+	count = ext2_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++) {
+		ext2_acl_entry *entry =
+			(ext2_acl_entry *)value;
+		if ((char *)value + sizeof(ext2_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(ext2_acl_entry_short);
+				acl->a_entries[n].e_id = ACL_UNDEFINED_ID;
+				break;
+
+			case ACL_USER:
+			case ACL_GROUP:
+				value = (char *)value + sizeof(ext2_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 *
+ext2_acl_to_disk(const struct posix_acl *acl, size_t *size)
+{
+	ext2_acl_header *ext_acl;
+	char *e;
+	size_t n;
+
+	*size = ext2_acl_size(acl->a_count);
+	ext_acl = (ext2_acl_header *)kmalloc(sizeof(ext2_acl_header) +
+		acl->a_count * sizeof(ext2_acl_entry), GFP_KERNEL);
+	if (!ext_acl)
+		return ERR_PTR(-ENOMEM);
+	ext_acl->a_version = cpu_to_le32(EXT2_ACL_VERSION);
+	e = (char *)ext_acl + sizeof(ext2_acl_header);
+	for (n=0; n < acl->a_count; n++) {
+		ext2_acl_entry *entry = (ext2_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(ext2_acl_entry);
+				break;
+
+			case ACL_USER_OBJ:
+			case ACL_GROUP_OBJ:
+			case ACL_MASK:
+			case ACL_OTHER:
+				e += sizeof(ext2_acl_entry_short);
+				break;
+
+			default:
+				goto fail;
+		}
+	}
+	return (char *)ext_acl;
+
+fail:
+	kfree(ext_acl);
+	return ERR_PTR(-EINVAL);
+}
+
+static inline struct posix_acl *
+ext2_iget_acl(struct inode *inode, struct posix_acl **i_acl)
+{
+	struct posix_acl *acl = EXT2_ACL_NOT_CACHED;
+
+	spin_lock(&inode->i_lock);
+	if (*i_acl != EXT2_ACL_NOT_CACHED)
+		acl = posix_acl_dup(*i_acl);
+	spin_unlock(&inode->i_lock);
+
+	return acl;
+}
+
+static inline void
+ext2_iset_acl(struct inode *inode, struct posix_acl **i_acl,
+		   struct posix_acl *acl)
+{
+	spin_lock(&inode->i_lock);
+	if (*i_acl != EXT2_ACL_NOT_CACHED)
+		posix_acl_release(*i_acl);
+	*i_acl = posix_acl_dup(acl);
+	spin_unlock(&inode->i_lock);
+}
+
+/*
+ * inode->i_sem: don't care
+ */
+static struct posix_acl *
+ext2_get_acl(struct inode *inode, int type)
+{
+	struct ext2_inode_info *ei = EXT2_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 = ext2_iget_acl(inode, &ei->i_acl);
+			if (acl != EXT2_ACL_NOT_CACHED)
+				return acl;
+			name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS;
+			break;
+
+		case ACL_TYPE_DEFAULT:
+			acl = ext2_iget_acl(inode, &ei->i_default_acl);
+			if (acl != EXT2_ACL_NOT_CACHED)
+				return acl;
+			name_index = EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT;
+			break;
+
+		default:
+			return ERR_PTR(-EINVAL);
+	}
+	retval = ext2_xattr_get(inode, name_index, "", NULL, 0);
+	if (retval > 0) {
+		value = kmalloc(retval, GFP_KERNEL);
+		if (!value)
+			return ERR_PTR(-ENOMEM);
+		retval = ext2_xattr_get(inode, name_index, "", value, retval);
+	}
+	if (retval > 0)
+		acl = ext2_acl_from_disk(value, retval);
+	else if (retval == -ENODATA || retval == -ENOSYS)
+		acl = NULL;
+	else
+		acl = ERR_PTR(retval);
+	if (value)
+		kfree(value);
+
+	if (!IS_ERR(acl)) {
+		switch(type) {
+			case ACL_TYPE_ACCESS:
+				ext2_iset_acl(inode, &ei->i_acl, acl);
+				break;
+
+			case ACL_TYPE_DEFAULT:
+				ext2_iset_acl(inode, &ei->i_default_acl, acl);
+				break;
+		}
+	}
+	return acl;
+}
+
+/*
+ * inode->i_sem: down
+ */
+static int
+ext2_set_acl(struct inode *inode, int type, struct posix_acl *acl)
+{
+	struct ext2_inode_info *ei = EXT2_I(inode);
+	int name_index;
+	void *value = NULL;
+	size_t size;
+	int error;
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+	if (!test_opt(inode->i_sb, POSIX_ACL))
+		return 0;
+
+	switch(type) {
+		case ACL_TYPE_ACCESS:
+			name_index = EXT2_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;
+					mark_inode_dirty(inode);
+					if (error == 0)
+						acl = NULL;
+				}
+			}
+			break;
+
+		case ACL_TYPE_DEFAULT:
+			name_index = EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT;
+			if (!S_ISDIR(inode->i_mode))
+				return acl ? -EACCES : 0;
+			break;
+
+		default:
+			return -EINVAL;
+	}
+ 	if (acl) {
+		value = ext2_acl_to_disk(acl, &size);
+		if (IS_ERR(value))
+			return (int)PTR_ERR(value);
+	}
+
+	error = ext2_xattr_set(inode, name_index, "", value, size, 0);
+
+	if (value)
+		kfree(value);
+	if (!error) {
+		switch(type) {
+			case ACL_TYPE_ACCESS:
+				ext2_iset_acl(inode, &ei->i_acl, acl);
+				break;
+
+			case ACL_TYPE_DEFAULT:
+				ext2_iset_acl(inode, &ei->i_default_acl, acl);
+				break;
+		}
+	}
+	return error;
+}
+
+static int
+ext2_check_acl(struct inode *inode, int mask)
+{
+	struct posix_acl *acl = ext2_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
+ext2_permission(struct inode *inode, int mask, struct nameidata *nd)
+{
+	return generic_permission(inode, mask, ext2_check_acl);
+}
+
+/*
+ * Initialize the ACLs of a new inode. Called from ext2_new_inode.
+ *
+ * dir->i_sem: down
+ * inode->i_sem: up (access to inode is still exclusive)
+ */
+int
+ext2_init_acl(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 = ext2_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 = ext2_set_acl(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 = ext2_set_acl(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
+ext2_acl_chmod(struct inode *inode)
+{
+	struct posix_acl *acl, *clone;
+        int error;
+
+	if (!test_opt(inode->i_sb, POSIX_ACL))
+		return 0;
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+	acl = ext2_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)
+		error = ext2_set_acl(inode, ACL_TYPE_ACCESS, clone);
+	posix_acl_release(clone);
+	return error;
+}
+
+/*
+ * Extended attribut handlers
+ */
+static size_t
+ext2_xattr_list_acl_access(struct inode *inode, char *list, size_t list_size,
+			   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_size)
+		memcpy(list, XATTR_NAME_ACL_ACCESS, size);
+	return size;
+}
+
+static size_t
+ext2_xattr_list_acl_default(struct inode *inode, char *list, size_t list_size,
+			    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_size)
+		memcpy(list, XATTR_NAME_ACL_DEFAULT, size);
+	return size;
+}
+
+static int
+ext2_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 = ext2_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
+ext2_xattr_get_acl_access(struct inode *inode, const char *name,
+			  void *buffer, size_t size)
+{
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+	return ext2_xattr_get_acl(inode, ACL_TYPE_ACCESS, buffer, size);
+}
+
+static int
+ext2_xattr_get_acl_default(struct inode *inode, const char *name,
+			   void *buffer, size_t size)
+{
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+	return ext2_xattr_get_acl(inode, ACL_TYPE_DEFAULT, buffer, size);
+}
+
+static int
+ext2_xattr_set_acl(struct inode *inode, int type, const void *value,
+		   size_t size)
+{
+	struct posix_acl *acl;
+	int error;
+
+	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;
+
+	error = ext2_set_acl(inode, type, acl);
+
+release_and_out:
+	posix_acl_release(acl);
+	return error;
+}
+
+static int
+ext2_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 ext2_xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size);
+}
+
+static int
+ext2_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 ext2_xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size);
+}
+
+struct xattr_handler ext2_xattr_acl_access_handler = {
+	.prefix	= XATTR_NAME_ACL_ACCESS,
+	.list	= ext2_xattr_list_acl_access,
+	.get	= ext2_xattr_get_acl_access,
+	.set	= ext2_xattr_set_acl_access,
+};
+
+struct xattr_handler ext2_xattr_acl_default_handler = {
+	.prefix	= XATTR_NAME_ACL_DEFAULT,
+	.list	= ext2_xattr_list_acl_default,
+	.get	= ext2_xattr_get_acl_default,
+	.set	= ext2_xattr_set_acl_default,
+};
diff --git a/fs/ext2/acl.h b/fs/ext2/acl.h
new file mode 100644
index 000000000000..fed96ae81a7d
--- /dev/null
+++ b/fs/ext2/acl.h
@@ -0,0 +1,82 @@
+/*
+  File: fs/ext2/acl.h
+
+  (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org>
+*/
+
+#include <linux/xattr_acl.h>
+
+#define EXT2_ACL_VERSION	0x0001
+
+typedef struct {
+	__le16		e_tag;
+	__le16		e_perm;
+	__le32		e_id;
+} ext2_acl_entry;
+
+typedef struct {
+	__le16		e_tag;
+	__le16		e_perm;
+} ext2_acl_entry_short;
+
+typedef struct {
+	__le32		a_version;
+} ext2_acl_header;
+
+static inline size_t ext2_acl_size(int count)
+{
+	if (count <= 4) {
+		return sizeof(ext2_acl_header) +
+		       count * sizeof(ext2_acl_entry_short);
+	} else {
+		return sizeof(ext2_acl_header) +
+		       4 * sizeof(ext2_acl_entry_short) +
+		       (count - 4) * sizeof(ext2_acl_entry);
+	}
+}
+
+static inline int ext2_acl_count(size_t size)
+{
+	ssize_t s;
+	size -= sizeof(ext2_acl_header);
+	s = size - 4 * sizeof(ext2_acl_entry_short);
+	if (s < 0) {
+		if (size % sizeof(ext2_acl_entry_short))
+			return -1;
+		return size / sizeof(ext2_acl_entry_short);
+	} else {
+		if (s % sizeof(ext2_acl_entry))
+			return -1;
+		return s / sizeof(ext2_acl_entry) + 4;
+	}
+}
+
+#ifdef CONFIG_EXT2_FS_POSIX_ACL
+
+/* Value for inode->u.ext2_i.i_acl and inode->u.ext2_i.i_default_acl
+   if the ACL has not been cached */
+#define EXT2_ACL_NOT_CACHED ((void *)-1)
+
+/* acl.c */
+extern int ext2_permission (struct inode *, int, struct nameidata *);
+extern int ext2_acl_chmod (struct inode *);
+extern int ext2_init_acl (struct inode *, struct inode *);
+
+#else
+#include <linux/sched.h>
+#define ext2_permission NULL
+#define ext2_get_acl	NULL
+#define ext2_set_acl	NULL
+
+static inline int
+ext2_acl_chmod (struct inode *inode)
+{
+	return 0;
+}
+
+static inline int ext2_init_acl (struct inode *inode, struct inode *dir)
+{
+	return 0;
+}
+#endif
+
diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c
new file mode 100644
index 000000000000..6591abef64d0
--- /dev/null
+++ b/fs/ext2/balloc.c
@@ -0,0 +1,699 @@
+/*
+ *  linux/fs/ext2/balloc.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)
+ *
+ *  Enhanced block 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/config.h>
+#include "ext2.h"
+#include <linux/quotaops.h>
+#include <linux/sched.h>
+#include <linux/buffer_head.h>
+
+/*
+ * balloc.c contains the blocks allocation and deallocation routines
+ */
+
+/*
+ * The free blocks 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.  The descriptors are loaded in memory
+ * when a file system is mounted (see ext2_read_super).
+ */
+
+
+#define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)
+
+struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb,
+					     unsigned int block_group,
+					     struct buffer_head ** bh)
+{
+	unsigned long group_desc;
+	unsigned long offset;
+	struct ext2_group_desc * desc;
+	struct ext2_sb_info *sbi = EXT2_SB(sb);
+
+	if (block_group >= sbi->s_groups_count) {
+		ext2_error (sb, "ext2_get_group_desc",
+			    "block_group >= groups_count - "
+			    "block_group = %d, groups_count = %lu",
+			    block_group, sbi->s_groups_count);
+
+		return NULL;
+	}
+
+	group_desc = block_group >> EXT2_DESC_PER_BLOCK_BITS(sb);
+	offset = block_group & (EXT2_DESC_PER_BLOCK(sb) - 1);
+	if (!sbi->s_group_desc[group_desc]) {
+		ext2_error (sb, "ext2_get_group_desc",
+			    "Group descriptor not loaded - "
+			    "block_group = %d, group_desc = %lu, desc = %lu",
+			     block_group, group_desc, offset);
+		return NULL;
+	}
+
+	desc = (struct ext2_group_desc *) sbi->s_group_desc[group_desc]->b_data;
+	if (bh)
+		*bh = sbi->s_group_desc[group_desc];
+	return desc + offset;
+}
+
+/*
+ * Read the bitmap for a given block_group, reading into the specified 
+ * slot in the superblock's bitmap cache.
+ *
+ * Return buffer_head on success or NULL in case of failure.
+ */
+static struct buffer_head *
+read_block_bitmap(struct super_block *sb, unsigned int block_group)
+{
+	struct ext2_group_desc * desc;
+	struct buffer_head * bh = NULL;
+	
+	desc = ext2_get_group_desc (sb, block_group, NULL);
+	if (!desc)
+		goto error_out;
+	bh = sb_bread(sb, le32_to_cpu(desc->bg_block_bitmap));
+	if (!bh)
+		ext2_error (sb, "read_block_bitmap",
+			    "Cannot read block bitmap - "
+			    "block_group = %d, block_bitmap = %u",
+			    block_group, le32_to_cpu(desc->bg_block_bitmap));
+error_out:
+	return bh;
+}
+
+/*
+ * Set sb->s_dirt here because the superblock was "logically" altered.  We
+ * need to recalculate its free blocks count and flush it out.
+ */
+static int reserve_blocks(struct super_block *sb, int count)
+{
+	struct ext2_sb_info *sbi = EXT2_SB(sb);
+	struct ext2_super_block *es = sbi->s_es;
+	unsigned free_blocks;
+	unsigned root_blocks;
+
+	free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+	root_blocks = le32_to_cpu(es->s_r_blocks_count);
+
+	if (free_blocks < count)
+		count = free_blocks;
+
+	if (free_blocks < root_blocks + count && !capable(CAP_SYS_RESOURCE) &&
+	    sbi->s_resuid != current->fsuid &&
+	    (sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) {
+		/*
+		 * We are too close to reserve and we are not privileged.
+		 * Can we allocate anything at all?
+		 */
+		if (free_blocks > root_blocks)
+			count = free_blocks - root_blocks;
+		else
+			return 0;
+	}
+
+	percpu_counter_mod(&sbi->s_freeblocks_counter, -count);
+	sb->s_dirt = 1;
+	return count;
+}
+
+static void release_blocks(struct super_block *sb, int count)
+{
+	if (count) {
+		struct ext2_sb_info *sbi = EXT2_SB(sb);
+
+		percpu_counter_mod(&sbi->s_freeblocks_counter, count);
+		sb->s_dirt = 1;
+	}
+}
+
+static int group_reserve_blocks(struct ext2_sb_info *sbi, int group_no,
+	struct ext2_group_desc *desc, struct buffer_head *bh, int count)
+{
+	unsigned free_blocks;
+
+	if (!desc->bg_free_blocks_count)
+		return 0;
+
+	spin_lock(sb_bgl_lock(sbi, group_no));
+	free_blocks = le16_to_cpu(desc->bg_free_blocks_count);
+	if (free_blocks < count)
+		count = free_blocks;
+	desc->bg_free_blocks_count = cpu_to_le16(free_blocks - count);
+	spin_unlock(sb_bgl_lock(sbi, group_no));
+	mark_buffer_dirty(bh);
+	return count;
+}
+
+static void group_release_blocks(struct super_block *sb, int group_no,
+	struct ext2_group_desc *desc, struct buffer_head *bh, int count)
+{
+	if (count) {
+		struct ext2_sb_info *sbi = EXT2_SB(sb);
+		unsigned free_blocks;
+
+		spin_lock(sb_bgl_lock(sbi, group_no));
+		free_blocks = le16_to_cpu(desc->bg_free_blocks_count);
+		desc->bg_free_blocks_count = cpu_to_le16(free_blocks + count);
+		spin_unlock(sb_bgl_lock(sbi, group_no));
+		sb->s_dirt = 1;
+		mark_buffer_dirty(bh);
+	}
+}
+
+/* Free given blocks, update quota and i_blocks field */
+void ext2_free_blocks (struct inode * inode, unsigned long block,
+		       unsigned long count)
+{
+	struct buffer_head *bitmap_bh = NULL;
+	struct buffer_head * bh2;
+	unsigned long block_group;
+	unsigned long bit;
+	unsigned long i;
+	unsigned long overflow;
+	struct super_block * sb = inode->i_sb;
+	struct ext2_sb_info * sbi = EXT2_SB(sb);
+	struct ext2_group_desc * desc;
+	struct ext2_super_block * es = sbi->s_es;
+	unsigned freed = 0, group_freed;
+
+	if (block < le32_to_cpu(es->s_first_data_block) ||
+	    block + count < block ||
+	    block + count > le32_to_cpu(es->s_blocks_count)) {
+		ext2_error (sb, "ext2_free_blocks",
+			    "Freeing blocks not in datazone - "
+			    "block = %lu, count = %lu", block, count);