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/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.
+

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

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,
+};

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
+

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);
+		goto error_return;
+	}
+
+	ext2_debug ("freeing block(s) %lu-%lu\n", block, block + count - 1);
+
+do_more:
+	overflow = 0;
+	block_group = (block - le32_to_cpu(es->s_first_data_block)) /
+		      EXT2_BLOCKS_PER_GROUP(sb);
+	bit = (block - le32_to_cpu(es->s_first_data_block)) %
+		      EXT2_BLOCKS_PER_GROUP(sb);
+	/*
+	 * Check to see if we are freeing blocks across a group
+	 * boundary.
+	 */
+	if (bit + count > EXT2_BLOCKS_PER_GROUP(sb)) {
+		overflow = bit + count - EXT2_BLOCKS_PER_GROUP(sb);
+		count -= overflow;
+	}
+	brelse(bitmap_bh);
+	bitmap_bh = read_block_bitmap(sb, block_group);
+	if (!bitmap_bh)
+		goto error_return;
+
+	desc = ext2_get_group_desc (sb, block_group, &bh2);
+	if (!desc)
+		goto error_return;
+
+	if (in_range (le32_to_cpu(desc->bg_block_bitmap), block, count) ||
+	    in_range (le32_to_cpu(desc->bg_inode_bitmap), block, count) ||
+	    in_range (block, le32_to_cpu(desc->bg_inode_table),
+		      sbi->s_itb_per_group) ||
+	    in_range (block + count - 1, le32_to_cpu(desc->bg_inode_table),
+		      sbi->s_itb_per_group))
+		ext2_error (sb, "ext2_free_blocks",
+			    "Freeing blocks in system zones - "
+			    "Block = %lu, count = %lu",
+			    block, count);
+
+	for (i = 0, group_freed = 0; i < count; i++) {
+		if (!ext2_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
+						bit + i, bitmap_bh->b_data)) {
+			ext2_error(sb, __FUNCTION__,
+				"bit already cleared for block %lu", block + i);
+		} else {
+			group_freed++;
+		}
+	}
+
+	mark_buffer_dirty(bitmap_bh);
+	if (sb->s_flags & MS_SYNCHRONOUS)
+		sync_dirty_buffer(bitmap_bh);
+
+	group_release_blocks(sb, block_group, desc, bh2, group_freed);
+	freed += group_freed;
+
+	if (overflow) {
+		block += count;
+		count = overflow;
+		goto do_more;
+	}
+error_return:
+	brelse(bitmap_bh);
+	release_blocks(sb, freed);
+	DQUOT_FREE_BLOCK(inode, freed);
+}
+
+static int grab_block(spinlock_t *lock, char *map, unsigned size, int goal)
+{
+	int k;
+	char *p, *r;
+
+	if (!ext2_test_bit(goal, map))
+		goto got_it;
+
+repeat:
+	if (goal) {
+		/*
+		 * The goal was occupied; search forward for a free 
+		 * block within the next XX blocks.
+		 *
+		 * end_goal is more or less random, but it has to be
+		 * less than EXT2_BLOCKS_PER_GROUP. Aligning up to the
+		 * next 64-bit boundary is simple..
+		 */
+		k = (goal + 63) & ~63;
+		goal = ext2_find_next_zero_bit(map, k, goal);
+		if (goal < k)
+			goto got_it;
+		/*
+		 * Search in the remainder of the current group.
+		 */
+	}
+
+	p = map + (goal >> 3);
+	r = memscan(p, 0, (size - goal + 7) >> 3);
+	k = (r - map) << 3;
+	if (k < size) {
+		/* 
+		 * We have succeeded in finding a free byte in the block
+		 * bitmap.  Now search backwards to find the start of this
+		 * group of free blocks - won't take more than 7 iterations.
+		 */
+		for (goal = k; goal && !ext2_test_bit (goal - 1, map); goal--)
+			;
+		goto got_it;
+	}
+
+	k = ext2_find_next_zero_bit ((u32 *)map, size, goal);
+	if (k < size) {
+		goal = k;
+		goto got_it;
+	}
+	return -1;
+got_it:
+	if (ext2_set_bit_atomic(lock, goal, (void *) map)) 
+		goto repeat;	
+	return goal;
+}
+
+/*
+ * ext2_new_block uses a goal block to assist allocation.  If the goal is
+ * free, or there is a free block within 32 blocks of the goal, that block
+ * is allocated.  Otherwise a forward search is made for a free block; within 
+ * each block group the search first looks for an entire free byte in the block
+ * bitmap, and then for any free bit if that fails.
+ * This function also updates quota and i_blocks field.
+ */
+int ext2_new_block(struct inode *inode, unsigned long goal,
+			u32 *prealloc_count, u32 *prealloc_block, int *err)
+{
+	struct buffer_head *bitmap_bh = NULL;
+	struct buffer_head *gdp_bh;	/* bh2 */
+	struct ext2_group_desc *desc;
+	int group_no;			/* i */
+	int ret_block;			/* j */
+	int group_idx;			/* k */
+	int target_block;		/* tmp */
+	int block = 0;
+	struct super_block *sb = inode->i_sb;
+	struct ext2_sb_info *sbi = EXT2_SB(sb);
+	struct ext2_super_block *es = sbi->s_es;
+	unsigned group_size = EXT2_BLOCKS_PER_GROUP(sb);
+	unsigned prealloc_goal = es->s_prealloc_blocks;
+	unsigned group_alloc = 0, es_alloc, dq_alloc;
+	int nr_scanned_groups;
+
+	if (!prealloc_goal--)
+		prealloc_goal = EXT2_DEFAULT_PREALLOC_BLOCKS - 1;
+	if (!prealloc_count || *prealloc_count)
+		prealloc_goal = 0;
+
+	if (DQUOT_ALLOC_BLOCK(inode, 1)) {
+		*err = -EDQUOT;
+		goto out;
+	}
+
+	while (prealloc_goal && DQUOT_PREALLOC_BLOCK(inode, prealloc_goal))
+		prealloc_goal--;
+
+	dq_alloc = prealloc_goal + 1;
+	es_alloc = reserve_blocks(sb, dq_alloc);
+	if (!es_alloc) {
+		*err = -ENOSPC;
+		goto out_dquot;
+	}
+
+	ext2_debug ("goal=%lu.\n", goal);
+
+	if (goal < le32_to_cpu(es->s_first_data_block) ||
+	    goal >= le32_to_cpu(es->s_blocks_count))
+		goal = le32_to_cpu(es->s_first_data_block);
+	group_no = (goal - le32_to_cpu(es->s_first_data_block)) / group_size;
+	desc = ext2_get_group_desc (sb, group_no, &gdp_bh);
+	if (!desc) {
+		/*
+		 * gdp_bh may still be uninitialised.  But group_release_blocks
+		 * will not touch it because group_alloc is zero.
+		 */
+		goto io_error;
+	}
+
+	group_alloc = group_reserve_blocks(sbi, group_no, desc,
+					gdp_bh, es_alloc);
+	if (group_alloc) {
+		ret_block = ((goal - le32_to_cpu(es->s_first_data_block)) %
+					group_size);
+		brelse(bitmap_bh);
+		bitmap_bh = read_block_bitmap(sb, group_no);
+		if (!bitmap_bh)
+			goto io_error;
+		
+		ext2_debug("goal is at %d:%d.\n", group_no, ret_block);
+
+		ret_block = grab_block(sb_bgl_lock(sbi, group_no),
+				bitmap_bh->b_data, group_size, ret_block);
+		if (ret_block >= 0)
+			goto got_block;
+		group_release_blocks(sb, group_no, desc, gdp_bh, group_alloc);
+		group_alloc = 0;
+	}
+
+	ext2_debug ("Bit not found in block group %d.\n", group_no);
+
+	/*
+	 * Now search the rest of the groups.  We assume that 
+	 * i and desc correctly point to the last group visited.
+	 */
+	nr_scanned_groups = 0;
+retry:
+	for (group_idx = 0; !group_alloc &&
+			group_idx < sbi->s_groups_count; group_idx++) {
+		group_no++;
+		if (group_no >= sbi->s_groups_count)
+			group_no = 0;
+		desc = ext2_get_group_desc(sb, group_no, &gdp_bh);
+		if (!desc)
+			goto io_error;
+		group_alloc = group_reserve_blocks(sbi, group_no, desc,
+						gdp_bh, es_alloc);
+	}
+	if (!group_alloc) {
+		*err = -ENOSPC;
+		goto out_release;
+	}
+	brelse(bitmap_bh);
+	bitmap_bh = read_block_bitmap(sb, group_no);
+	if (!bitmap_bh)
+		goto io_error;
+
+	ret_block = grab_block(sb_bgl_lock(sbi, group_no), bitmap_bh->b_data,
+				group_size, 0);
+	if (ret_block < 0) {
+		/*
+		 * If a free block counter is corrupted we can loop inifintely.
+		 * Detect that here.
+		 */
+		nr_scanned_groups++;
+		if (nr_scanned_groups > 2 * sbi->s_groups_count) {
+			ext2_error(sb, "ext2_new_block",
+				"corrupted free blocks counters");
+			goto io_error;
+		}
+		/*
+		 * Someone else grabbed the last free block in this blockgroup
+		 * before us.  Retry the scan.
+		 */
+		group_release_blocks(sb, group_no, desc, gdp_bh, group_alloc);
+		group_alloc = 0;
+		goto retry;
+	}
+
+got_block:
+	ext2_debug("using block group %d(%d)\n",
+		group_no, desc->bg_free_blocks_count);
+
+	target_block = ret_block + group_no * group_size +
+			le32_to_cpu(es->s_first_data_block);
+
+	if (target_block == le32_to_cpu(desc->bg_block_bitmap) ||
+	    target_block == le32_to_cpu(desc->bg_inode_bitmap) ||
+	    in_range(target_block, le32_to_cpu(desc->bg_inode_table),
+		      sbi->s_itb_per_group))
+		ext2_error (sb, "ext2_new_block",
+			    "Allocating block in system zone - "
+			    "block = %u", target_block);
+
+	if (target_block >= le32_to_cpu(es->s_blocks_count)) {
+		ext2_error (sb, "ext2_new_block",
+			    "block(%d) >= blocks count(%d) - "
+			    "block_group = %d, es == %p ", ret_block,
+			le32_to_cpu(es->s_blocks_count), group_no, es);
+		goto io_error;
+	}
+	block = target_block;
+
+	/* OK, we _had_ allocated something */
+	ext2_debug("found bit %d\n", ret_block);
+
+	dq_alloc--;
+	es_alloc--;
+	group_alloc--;
+
+	/*
+	 * Do block preallocation now if required.
+	 */
+	write_lock(&EXT2_I(inode)->i_meta_lock);
+	if (group_alloc && !*prealloc_count) {
+		unsigned n;
+
+		for (n = 0; n < group_alloc && ++ret_block < group_size; n++) {
+			if (ext2_set_bit_atomic(sb_bgl_lock(sbi, group_no),
+						ret_block,
+						(void*) bitmap_bh->b_data))
+ 				break;
+		}
+		*prealloc_block = block + 1;
+		*prealloc_count = n;
+		es_alloc -= n;
+		dq_alloc -= n;
+		group_alloc -= n;
+	}
+	write_unlock(&EXT2_I(inode)->i_meta_lock);
+
+	mark_buffer_dirty(bitmap_bh);
+	if (sb->s_flags & MS_SYNCHRONOUS)
+		sync_dirty_buffer(bitmap_bh);
+
+	ext2_debug ("allocating block %d. ", block);
+
+	*err = 0;
+out_release:
+	group_release_blocks(sb, group_no, desc, gdp_bh, group_alloc);
+	release_blocks(sb, es_alloc);
+out_dquot:
+	DQUOT_FREE_BLOCK(inode, dq_alloc);
+out:
+	brelse(bitmap_bh);
+	return block;
+
+io_error:
+	*err = -EIO;
+	goto out_release;
+}
+
+unsigned long ext2_count_free_blocks (struct super_block * sb)
+{
+	struct ext2_group_desc * desc;
+	unsigned long desc_count = 0;
+	int i;
+#ifdef EXT2FS_DEBUG
+	unsigned long bitmap_count, x;
+	struct ext2_super_block *es;
+
+	lock_super (sb);
+	es = EXT2_SB(sb)->s_es;
+	desc_count = 0;
+	bitmap_count = 0;
+	desc = NULL;
+	for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) {
+		struct buffer_head *bitmap_bh;
+		desc = ext2_get_group_desc (sb, i, NULL);
+		if (!desc)
+			continue;
+		desc_count += le16_to_cpu(desc->bg_free_blocks_count);
+		bitmap_bh = read_block_bitmap(sb, i);
+		if (!bitmap_bh)
+			continue;
+		
+		x = ext2_count_free(bitmap_bh, sb->s_blocksize);
+		printk ("group %d: stored = %d, counted = %lu\n",
+			i, le16_to_cpu(desc->bg_free_blocks_count), x);
+		bitmap_count += x;
+		brelse(bitmap_bh);
+	}
+	printk("ext2_count_free_blocks: stored = %lu, computed = %lu, %lu\n",
+		(long)le32_to_cpu(es->s_free_blocks_count),
+		desc_count, bitmap_count);
+	unlock_super (sb);
+	return bitmap_count;
+#else
+        for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) {
+                desc = ext2_get_group_desc (sb, i, NULL);
+                if (!desc)
+                        continue;
+                desc_count += le16_to_cpu(desc->bg_free_blocks_count);
+	}
+	return desc_count;
+#endif
+}
+
+static inline int
+block_in_use(unsigned long block, struct super_block *sb, unsigned char *map)
+{
+	return ext2_test_bit ((block -
+		le32_to_cpu(EXT2_SB(sb)->s_es->s_first_data_block)) %
+			 EXT2_BLOCKS_PER_GROUP(sb), map);
+}
+
+static inline int test_root(int a, int b)
+{
+	int num = b;
+
+	while (a > num)
+		num *= b;
+	return num == a;
+}
+
+static int ext2_group_sparse(int group)
+{
+	if (group <= 1)
+		return 1;
+	return (test_root(group, 3) || test_root(group, 5) ||
+		test_root(group, 7));
+}
+
+/**
+ *	ext2_bg_has_super - number of blocks used by the superblock in group
+ *	@sb: superblock for filesystem
+ *	@group: group number to check
+ *
+ *	Return the number of blocks used by the superblock (primary or backup)
+ *	in this group.  Currently this will be only 0 or 1.
+ */
+int ext2_bg_has_super(struct super_block *sb, int group)
+{
+	if (EXT2_HAS_RO_COMPAT_FEATURE(sb,EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER)&&
+	    !ext2_group_sparse(group))
+		return 0;
+	return 1;
+}
+
+/**
+ *	ext2_bg_num_gdb - number of blocks used by the group table in group
+ *	@sb: superblock for filesystem
+ *	@group: group number to check
+ *
+ *	Return the number of blocks used by the group descriptor table
+ *	(primary or backup) in this group.  In the future there may be a
+ *	different number of descriptor blocks in each group.
+ */
+unsigned long ext2_bg_num_gdb(struct super_block *sb, int group)
+{
+	if (EXT2_HAS_RO_COMPAT_FEATURE(sb,EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER)&&
+	    !ext2_group_sparse(group))
+		return 0;
+	return EXT2_SB(sb)->s_gdb_count;
+}
+
+#ifdef CONFIG_EXT2_CHECK
+/* Called at mount-time, super-block is locked */
+void ext2_check_blocks_bitmap (struct super_block * sb)
+{
+	struct buffer_head *bitmap_bh = NULL;
+	struct ext2_super_block * es;
+	unsigned long desc_count, bitmap_count, x, j;
+	unsigned long desc_blocks;
+	struct ext2_group_desc * desc;
+	int i;
+
+	es = EXT2_SB(sb)->s_es;
+	desc_count = 0;
+	bitmap_count = 0;
+	desc = NULL;
+	for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) {
+		desc = ext2_get_group_desc (sb, i, NULL);
+		if (!desc)
+			continue;
+		desc_count += le16_to_cpu(desc->bg_free_blocks_count);
+		brelse(bitmap_bh);
+		bitmap_bh = read_block_bitmap(sb, i);
+		if (!bitmap_bh)
+			continue;
+
+		if (ext2_bg_has_super(sb, i) &&
+				!ext2_test_bit(0, bitmap_bh->b_data))
+			ext2_error(sb, __FUNCTION__,
+				   "Superblock in group %d is marked free", i);
+
+		desc_blocks = ext2_bg_num_gdb(sb, i);
+		for (j = 0; j < desc_blocks; j++)
+			if (!ext2_test_bit(j + 1, bitmap_bh->b_data))
+				ext2_error(sb, __FUNCTION__,
+					   "Descriptor block #%ld in group "
+					   "%d is marked free", j, i);
+
+		if (!block_in_use(le32_to_cpu(desc->bg_block_bitmap),
+					sb, bitmap_bh->b_data))
+			ext2_error(sb, "ext2_check_blocks_bitmap",
+				    "Block bitmap for group %d is marked free",
+				    i);
+
+		if (!block_in_use(le32_to_cpu(desc->bg_inode_bitmap),
+					sb, bitmap_bh->b_data))
+			ext2_error(sb, "ext2_check_blocks_bitmap",
+				    "Inode bitmap for group %d is marked free",
+				    i);
+
+		for (j = 0; j < EXT2_SB(sb)->s_itb_per_group; j++)
+			if (!block_in_use(le32_to_cpu(desc->bg_inode_table) + j,
+						sb, bitmap_bh->b_data))
+				ext2_error (sb, "ext2_check_blocks_bitmap",
+					    "Block #%ld of the inode table in "
+					    "group %d is marked free", j, i);
+
+		x = ext2_count_free(bitmap_bh, sb->s_blocksize);
+		if (le16_to_cpu(desc->bg_free_blocks_count) != x)
+			ext2_error (sb, "ext2_check_blocks_bitmap",
+				    "Wrong free blocks count for group %d, "
+				    "stored = %d, counted = %lu", i,
+				    le16_to_cpu(desc->bg_free_blocks_count), x);
+		bitmap_count += x;
+	}
+	if (le32_to_cpu(es->s_free_blocks_count) != bitmap_count)
+		ext2_error (sb, "ext2_check_blocks_bitmap",
+			"Wrong free blocks count in super block, "
+			"stored = %lu, counted = %lu",
+			(unsigned long)le32_to_cpu(es->s_free_blocks_count),
+			bitmap_count);
+	brelse(bitmap_bh);
+}
+#endif

fs/ext2/bitmap.c

@@ -0,0 +1,25 @@
+/*
+ *  linux/fs/ext2/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 ext2_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/ext2/dir.c

@@ -0,0 +1,673 @@
+/*
+ *  linux/fs/ext2/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
+ *
+ *  ext2 directory handling functions
+ *
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ *
+ * All code that works with directory layout had been switched to pagecache
+ * and moved here. AV
+ */
+
+#include "ext2.h"
+#include <linux/pagemap.h>
+#include <linux/smp_lock.h>
+
+typedef struct ext2_dir_entry_2 ext2_dirent;
+
+/*
+ * ext2 uses block-sized chunks. Arguably, sector-sized ones would be
+ * more robust, but we have what we have
+ */
+static inline unsigned ext2_chunk_size(struct inode *inode)
+{
+	return inode->i_sb->s_blocksize;
+}
+
+static inline void ext2_put_page(struct page *page)
+{
+	kunmap(page);
+	page_cache_release(page);
+}
+
+static inline unsigned long dir_pages(struct inode *inode)
+{
+	return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
+}
+
+/*
+ * Return the offset into page `page_nr' of the last valid
+ * byte in that page, plus one.
+ */
+static unsigned
+ext2_last_byte(struct inode *inode, unsigned long page_nr)
+{
+	unsigned last_byte = inode->i_size;
+
+	last_byte -= page_nr << PAGE_CACHE_SHIFT;
+	if (last_byte > PAGE_CACHE_SIZE)
+		last_byte = PAGE_CACHE_SIZE;
+	return last_byte;
+}
+
+static int ext2_commit_chunk(struct page *page, unsigned from, unsigned to)
+{
+	struct inode *dir = page->mapping->host;
+	int err = 0;
+	dir->i_version++;
+	page->mapping->a_ops->commit_write(NULL, page, from, to);
+	if (IS_DIRSYNC(dir))
+		err = write_one_page(page, 1);
+	else
+		unlock_page(page);
+	return err;
+}
+
+static void ext2_check_page(struct page *page)
+{
+	struct inode *dir = page->mapping->host;
+	struct super_block *sb = dir->i_sb;
+	unsigned chunk_size = ext2_chunk_size(dir);
+	char *kaddr = page_address(page);
+	u32 max_inumber = le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count);
+	unsigned offs, rec_len;
+	unsigned limit = PAGE_CACHE_SIZE;
+	ext2_dirent *p;
+	char *error;
+
+	if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) {
+		limit = dir->i_size & ~PAGE_CACHE_MASK;
+		if (limit & (chunk_size - 1))
+			goto Ebadsize;
+		if (!limit)
+			goto out;
+	}
+	for (offs = 0; offs <= limit - EXT2_DIR_REC_LEN(1); offs += rec_len) {
+		p = (ext2_dirent *)(kaddr + offs);
+		rec_len = le16_to_cpu(p->rec_len);
+
+		if (rec_len < EXT2_DIR_REC_LEN(1))
+			goto Eshort;
+		if (rec_len & 3)
+			goto Ealign;
+		if (rec_len < EXT2_DIR_REC_LEN(p->name_len))
+			goto Enamelen;
+		if (((offs + rec_len - 1) ^ offs) & ~(chunk_size-1))
+			goto Espan;
+		if (le32_to_cpu(p->inode) > max_inumber)
+			goto Einumber;
+	}
+	if (offs != limit)
+		goto Eend;
+out:
+	SetPageChecked(page);
+	return;
+
+	/* Too bad, we had an error */
+
+Ebadsize:
+	ext2_error(sb, "ext2_check_page",
+		"size of directory #%lu is not a multiple of chunk size",
+		dir->i_ino
+	);
+	goto fail;
+Eshort:
+	error = "rec_len is smaller than minimal";
+	goto bad_entry;
+Ealign:
+	error = "unaligned directory entry";
+	goto bad_entry;
+Enamelen:
+	error = "rec_len is too small for name_len";
+	goto bad_entry;
+Espan:
+	error = "directory entry across blocks";
+	goto bad_entry;
+Einumber:
+	error = "inode out of bounds";
+bad_entry:
+	ext2_error (sb, "ext2_check_page", "bad entry in directory #%lu: %s - "
+		"offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
+		dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
+		(unsigned long) le32_to_cpu(p->inode),
+		rec_len, p->name_len);
+	goto fail;
+Eend:
+	p = (ext2_dirent *)(kaddr + offs);
+	ext2_error (sb, "ext2_check_page",
+		"entry in directory #%lu spans the page boundary"
+		"offset=%lu, inode=%lu",
+		dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
+		(unsigned long) le32_to_cpu(p->inode));
+fail:
+	SetPageChecked(page);
+	SetPageError(page);
+}
+
+static struct page * ext2_get_page(struct inode *dir, unsigned long n)
+{
+	struct address_space *mapping = dir->i_mapping;
+	struct page *page = read_cache_page(mapping, n,
+				(filler_t*)mapping->a_ops->readpage, NULL);
+	if (!IS_ERR(page)) {
+		wait_on_page_locked(page);
+		kmap(page);
+		if (!PageUptodate(page))
+			goto fail;
+		if (!PageChecked(page))
+			ext2_check_page(page);
+		if (PageError(page))
+			goto fail;
+	}
+	return page;
+
+fail:
+	ext2_put_page(page);
+	return ERR_PTR(-EIO);
+}
+
+/*
+ * NOTE! unlike strncmp, ext2_match returns 1 for success, 0 for failure.
+ *
+ * len <= EXT2_NAME_LEN and de != NULL are guaranteed by caller.
+ */
+static inline int ext2_match (int len, const char * const name,
+					struct ext2_dir_entry_2 * de)
+{
+	if (len != de->name_len)
+		return 0;
+	if (!de->inode)
+		return 0;
+	return !memcmp(name, de->name, len);
+}
+
+/*
+ * p is at least 6 bytes before the end of page
+ */
+static inline ext2_dirent *ext2_next_entry(ext2_dirent *p)
+{
+	return (ext2_dirent *)((char*)p + le16_to_cpu(p->rec_len));
+}
+
+static inline unsigned 
+ext2_validate_entry(char *base, unsigned offset, unsigned mask)
+{
+	ext2_dirent *de = (ext2_dirent*)(base + offset);
+	ext2_dirent *p = (ext2_dirent*)(base + (offset&mask));
+	while ((char*)p < (char*)de) {
+		if (p->rec_len == 0)
+			break;
+		p = ext2_next_entry(p);
+	}
+	return (char *)p - base;
+}
+
+static unsigned char ext2_filetype_table[EXT2_FT_MAX] = {
+	[EXT2_FT_UNKNOWN]	= DT_UNKNOWN,
+	[EXT2_FT_REG_FILE]	= DT_REG,
+	[EXT2_FT_DIR]		= DT_DIR,
+	[EXT2_FT_CHRDEV]	= DT_CHR,
+	[EXT2_FT_BLKDEV]	= DT_BLK,
+	[EXT2_FT_FIFO]		= DT_FIFO,
+	[EXT2_FT_SOCK]		= DT_SOCK,
+	[EXT2_FT_SYMLINK]	= DT_LNK,
+};
+
+#define S_SHIFT 12
+static unsigned char ext2_type_by_mode[S_IFMT >> S_SHIFT] = {
+	[S_IFREG >> S_SHIFT]	= EXT2_FT_REG_FILE,
+	[S_IFDIR >> S_SHIFT]	= EXT2_FT_DIR,
+	[S_IFCHR >> S_SHIFT]	= EXT2_FT_CHRDEV,
+	[S_IFBLK >> S_SHIFT]	= EXT2_FT_BLKDEV,
+	[S_IFIFO >> S_SHIFT]	= EXT2_FT_FIFO,
+	[S_IFSOCK >> S_SHIFT]	= EXT2_FT_SOCK,
+	[S_IFLNK >> S_SHIFT]	= EXT2_FT_SYMLINK,
+};
+
+static inline void ext2_set_de_type(ext2_dirent *de, struct inode *inode)
+{
+	mode_t mode = inode->i_mode;
+	if (EXT2_HAS_INCOMPAT_FEATURE(inode->i_sb, EXT2_FEATURE_INCOMPAT_FILETYPE))
+		de->file_type = ext2_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
+	else
+		de->file_type = 0;
+}
+
+static int
+ext2_readdir (struct file * filp, void * dirent, filldir_t filldir)
+{
+	loff_t pos = filp->f_pos;
+	struct inode *inode = filp->f_dentry->d_inode;
+	struct super_block *sb = inode->i_sb;
+	unsigned int offset = pos & ~PAGE_CACHE_MASK;
+	unsigned long n = pos >> PAGE_CACHE_SHIFT;
+	unsigned long npages = dir_pages(inode);
+	unsigned chunk_mask = ~(ext2_chunk_size(inode)-1);
+	unsigned char *types = NULL;
+	int need_revalidate = (filp->f_version != inode->i_version);
+	int ret;
+
+	if (pos > inode->i_size - EXT2_DIR_REC_LEN(1))
+		goto success;
+
+	if (EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_FILETYPE))
+		types = ext2_filetype_table;
+
+	for ( ; n < npages; n++, offset = 0) {
+		char *kaddr, *limit;
+		ext2_dirent *de;
+		struct page *page = ext2_get_page(inode, n);
+
+		if (IS_ERR(page)) {
+			ext2_error(sb, __FUNCTION__,
+				   "bad page in #%lu",
+				   inode->i_ino);
+			filp->f_pos += PAGE_CACHE_SIZE - offset;
+			ret = -EIO;
+			goto done;
+		}
+		kaddr = page_address(page);
+		if (need_revalidate) {
+			offset = ext2_validate_entry(kaddr, offset, chunk_mask);
+			need_revalidate = 0;
+		}
+		de = (ext2_dirent *)(kaddr+offset);
+		limit = kaddr + ext2_last_byte(inode, n) - EXT2_DIR_REC_LEN(1);
+		for ( ;(char*)de <= limit; de = ext2_next_entry(de)) {
+			if (de->rec_len == 0) {
+				ext2_error(sb, __FUNCTION__,
+					"zero-length directory entry");
+				ret = -EIO;
+				ext2_put_page(page);
+				goto done;
+			}
+			if (de->inode) {
+				int over;
+				unsigned char d_type = DT_UNKNOWN;
+
+				if (types && de->file_type < EXT2_FT_MAX)
+					d_type = types[de->file_type];
+
+				offset = (char *)de - kaddr;
+				over = filldir(dirent, de->name, de->name_len,
+						(n<<PAGE_CACHE_SHIFT) | offset,
+						le32_to_cpu(de->inode), d_type);
+				if (over) {
+					ext2_put_page(page);
+					goto success;
+				}
+			}
+			filp->f_pos += le16_to_cpu(de->rec_len);
+		}
+		ext2_put_page(page);
+	}
+
+success:
+	ret = 0;
+done:
+	filp->f_version = inode->i_version;
+	return ret;
+}
+
+/*
+ *	ext2_find_entry()
+ *
+ * finds an entry in the specified directory with the wanted name. It
+ * returns the page in which the entry was found, and the entry itself
+ * (as a parameter - res_dir). Page is returned mapped and unlocked.
+ * Entry is guaranteed to be valid.
+ */
+struct ext2_dir_entry_2 * ext2_find_entry (struct inode * dir,
+			struct dentry *dentry, struct page ** res_page)
+{
+	const char *name = dentry->d_name.name;
+	int namelen = dentry->d_name.len;
+	unsigned reclen = EXT2_DIR_REC_LEN(namelen);
+	unsigned long start, n;
+	unsigned long npages = dir_pages(dir);
+	struct page *page = NULL;
+	struct ext2_inode_info *ei = EXT2_I(dir);
+	ext2_dirent * de;
+
+	if (npages == 0)
+		goto out;
+
+	/* OFFSET_CACHE */
+	*res_page = NULL;
+
+	start = ei->i_dir_start_lookup;
+	if (start >= npages)
+		start = 0;
+	n = start;
+	do {
+		char *kaddr;
+		page = ext2_get_page(dir, n);
+		if (!IS_ERR(page)) {
+			kaddr = page_address(page);
+			de = (ext2_dirent *) kaddr;
+			kaddr += ext2_last_byte(dir, n) - reclen;
+			while ((char *) de <= kaddr) {
+				if (de->rec_len == 0) {
+					ext2_error(dir->i_sb, __FUNCTION__,
+						"zero-length directory entry");
+					ext2_put_page(page);
+					goto out;
+				}
+				if (ext2_match (namelen, name, de))
+					goto found;
+				de = ext2_next_entry(de);
+			}
+			ext2_put_page(page);
+		}
+		if (++n >= npages)
+			n = 0;
+	} while (n != start);
+out:
+	return NULL;
+
+found:
+	*res_page = page;
+	ei->i_dir_start_lookup = n;
+	return de;
+}
+
+struct ext2_dir_entry_2 * ext2_dotdot (struct inode *dir, struct page **p)
+{
+	struct page *page = ext2_get_page(dir, 0);
+	ext2_dirent *de = NULL;
+
+	if (!IS_ERR(page)) {
+		de = ext2_next_entry((ext2_dirent *) page_address(page));
+		*p = page;
+	}
+	return de;
+}
+
+ino_t ext2_inode_by_name(struct inode * dir, struct dentry *dentry)
+{
+	ino_t res = 0;
+	struct ext2_dir_entry_2 * de;
+	struct page *page;
+	
+	de = ext2_find_entry (dir, dentry, &page);
+	if (de) {
+		res = le32_to_cpu(de->inode);
+		kunmap(page);
+		page_cache_release(page);
+	}
+	return res;
+}
+
+/* Releases the page */
+void ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de,
+			struct page *page, struct inode *inode)
+{
+	unsigned from = (char *) de - (char *) page_address(page);
+	unsigned to = from + le16_to_cpu(de->rec_len);
+	int err;
+
+	lock_page(page);
+	err = page->mapping->a_ops->prepare_write(NULL, page, from, to);
+	if (err)
+		BUG();
+	de->inode = cpu_to_le32(inode->i_ino);
+	ext2_set_de_type (de, inode);
+	err = ext2_commit_chunk(page, from, to);
+	ext2_put_page(page);
+	dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
+	EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL;
+	mark_inode_dirty(dir);
+}
+
+/*
+ *	Parent is locked.
+ */
+int ext2_add_link (struct dentry *dentry, struct inode *inode)
+{
+	struct inode *dir = dentry->d_parent->d_inode;
+	const char *name = dentry->d_name.name;
+	int namelen = dentry->d_name.len;
+	unsigned chunk_size = ext2_chunk_size(dir);
+	unsigned reclen = EXT2_DIR_REC_LEN(namelen);
+	unsigned short rec_len, name_len;
+	struct page *page = NULL;
+	ext2_dirent * de;
+	unsigned long npages = dir_pages(dir);
+	unsigned long n;
+	char *kaddr;
+	unsigned from, to;
+	int err;
+
+	/*
+	 * We take care of directory expansion in the same loop.
+	 * This code plays outside i_size, so it locks the page
+	 * to protect that region.
+	 */
+	for (n = 0; n <= npages; n++) {
+		char *dir_end;
+
+		page = ext2_get_page(dir, n);
+		err = PTR_ERR(page);
+		if (IS_ERR(page))
+			goto out;
+		lock_page(page);
+		kaddr = page_address(page);
+		dir_end = kaddr + ext2_last_byte(dir, n);
+		de = (ext2_dirent *)kaddr;
+		kaddr += PAGE_CACHE_SIZE - reclen;
+		while ((char *)de <= kaddr) {
+			if ((char *)de == dir_end) {
+				/* We hit i_size */
+				name_len = 0;
+				rec_len = chunk_size;
+				de->rec_len = cpu_to_le16(chunk_size);
+				de->inode = 0;
+				goto got_it;
+			}
+			if (de->rec_len == 0) {
+				ext2_error(dir->i_sb, __FUNCTION__,
+					"zero-length directory entry");
+				err = -EIO;
+				goto out_unlock;
+			}
+			err = -EEXIST;
+			if (ext2_match (namelen, name, de))
+				goto out_unlock;
+			name_len = EXT2_DIR_REC_LEN(de->name_len);
+			rec_len = le16_to_cpu(de->rec_len);
+			if (!de->inode && rec_len >= reclen)
+				goto got_it;
+			if (rec_len >= name_len + reclen)
+				goto got_it;
+			de = (ext2_dirent *) ((char *) de + rec_len);
+		}
+		unlock_page(page);
+		ext2_put_page(page);
+	}
+	BUG();
+	return -EINVAL;
+
+got_it:
+	from = (char*)de - (char*)page_address(page);
+	to = from + rec_len;
+	err = page->mapping->a_ops->prepare_write(NULL, page, from, to);
+	if (err)
+		goto out_unlock;
+	if (de->inode) {
+		ext2_dirent *de1 = (ext2_dirent *) ((char *) de + name_len);
+		de1->rec_len = cpu_to_le16(rec_len - name_len);
+		de->rec_len = cpu_to_le16(name_len);
+		de = de1;
+	}
+	de->name_len = namelen;
+	memcpy (de->name, name, namelen);
+	de->inode = cpu_to_le32(inode->i_ino);
+	ext2_set_de_type (de, inode);
+	err = ext2_commit_chunk(page, from, to);
+	dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
+	EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL;
+	mark_inode_dirty(dir);
+	/* OFFSET_CACHE */
+out_put:
+	ext2_put_page(page);
+out:
+	return err;
+out_unlock:
+	unlock_page(page);
+	goto out_put;
+}
+
+/*
+ * ext2_delete_entry deletes a directory entry by merging it with the
+ * previous entry. Page is up-to-date. Releases the page.
+ */
+int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page )
+{
+	struct address_space *mapping = page->mapping;
+	struct inode *inode = mapping->host;
+	char *kaddr = page_address(page);
+	unsigned from = ((char*)dir - kaddr) & ~(ext2_chunk_size(inode)-1);
+	unsigned to = ((char*)dir - kaddr) + le16_to_cpu(dir->rec_len);
+	ext2_dirent * pde = NULL;
+	ext2_dirent * de = (ext2_dirent *) (kaddr + from);
+	int err;
+
+	while ((char*)de < (char*)dir) {
+		if (de->rec_len == 0) {
+			ext2_error(inode->i_sb, __FUNCTION__,
+				"zero-length directory entry");
+			err = -EIO;
+			goto out;
+		}
+		pde = de;
+		de = ext2_next_entry(de);
+	}
+	if (pde)
+		from = (char*)pde - (char*)page_address(page);
+	lock_page(page);
+	err = mapping->a_ops->prepare_write(NULL, page, from, to);
+	if (err)
+		BUG();
+	if (pde)
+		pde->rec_len = cpu_to_le16(to-from);
+	dir->inode = 0;
+	err = ext2_commit_chunk(page, from, to);
+	inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC;
+	EXT2_I(inode)->i_flags &= ~EXT2_BTREE_FL;
+	mark_inode_dirty(inode);
+out:
+	ext2_put_page(page);
+	return err;
+}
+
+/*
+ * Set the first fragment of directory.
+ */
+int ext2_make_empty(struct inode *inode, struct inode *parent)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct page *page = grab_cache_page(mapping, 0);
+	unsigned chunk_size = ext2_chunk_size(inode);
+	struct ext2_dir_entry_2 * de;
+	int err;
+	void *kaddr;
+
+	if (!page)
+		return -ENOMEM;
+	err = mapping->a_ops->prepare_write(NULL, page, 0, chunk_size);
+	if (err) {
+		unlock_page(page);
+		goto fail;
+	}
+	kaddr = kmap_atomic(page, KM_USER0);
+       memset(kaddr, 0, chunk_size);
+	de = (struct ext2_dir_entry_2 *)kaddr;
+	de->name_len = 1;
+	de->rec_len = cpu_to_le16(EXT2_DIR_REC_LEN(1));
+	memcpy (de->name, ".\0\0", 4);
+	de->inode = cpu_to_le32(inode->i_ino);
+	ext2_set_de_type (de, inode);
+
+	de = (struct ext2_dir_entry_2 *)(kaddr + EXT2_DIR_REC_LEN(1));
+	de->name_len = 2;
+	de->rec_len = cpu_to_le16(chunk_size - EXT2_DIR_REC_LEN(1));
+	de->inode = cpu_to_le32(parent->i_ino);
+	memcpy (de->name, "..\0", 4);
+	ext2_set_de_type (de, inode);
+	kunmap_atomic(kaddr, KM_USER0);
+	err = ext2_commit_chunk(page, 0, chunk_size);
+fail:
+	page_cache_release(page);
+	return err;
+}
+
+/*
+ * routine to check that the specified directory is empty (for rmdir)
+ */
+int ext2_empty_dir (struct inode * inode)
+{
+	struct page *page = NULL;
+	unsigned long i, npages = dir_pages(inode);
+
+	for (i = 0; i < npages; i++) {
+		char *kaddr;
+		ext2_dirent * de;
+		page = ext2_get_page(inode, i);
+
+		if (IS_ERR(page))
+			continue;
+
+		kaddr = page_address(page);
+		de = (ext2_dirent *)kaddr;
+		kaddr += ext2_last_byte(inode, i) - EXT2_DIR_REC_LEN(1);
+
+		while ((char *)de <= kaddr) {
+			if (de->rec_len == 0) {
+				ext2_error(inode->i_sb, __FUNCTION__,
+					"zero-length directory entry");
+				printk("kaddr=%p, de=%p\n", kaddr, de);
+				goto not_empty;
+			}
+			if (de->inode != 0) {
+				/* check for . and .. */
+				if (de->name[0] != '.')
+					goto not_empty;
+				if (de->name_len > 2)
+					goto not_empty;
+				if (de->name_len < 2) {
+					if (de->inode !=
+					    cpu_to_le32(inode->i_ino))
+						goto not_empty;
+				} else if (de->name[1] != '.')
+					goto not_empty;
+			}
+			de = ext2_next_entry(de);
+		}
+		ext2_put_page(page);
+	}
+	return 1;
+
+not_empty:
+	ext2_put_page(page);
+	return 0;
+}
+
+struct file_operations ext2_dir_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= generic_read_dir,
+	.readdir	= ext2_readdir,
+	.ioctl		= ext2_ioctl,
+	.fsync		= ext2_sync_file,
+};

fs/ext2/ext2.h

@@ -0,0 +1,160 @@
+#include <linux/fs.h>
+#include <linux/ext2_fs.h>
+
+/*
+ * second extended file system inode data in memory
+ */
+struct ext2_inode_info {
+	__le32	i_data[15];
+	__u32	i_flags;
+	__u32	i_faddr;
+	__u8	i_frag_no;
+	__u8	i_frag_size;
+	__u16	i_state;
+	__u32	i_file_acl;
+	__u32	i_dir_acl;
+	__u32	i_dtime;
+
+	/*
+	 * i_block_group is the number of the block group which contains
+	 * this file's inode.  Constant across the lifetime of the inode,
+	 * it is ued for making block allocation decisions - we try to
+	 * place a file's data blocks near its inode block, and new inodes
+	 * near to their parent directory's inode.
+	 */
+	__u32	i_block_group;
+
+	/*
+	 * i_next_alloc_block is the logical (file-relative) number of the
+	 * most-recently-allocated block in this file.  Yes, it is misnamed.
+	 * We use this for detecting linearly ascending allocation requests.
+	 */
+	__u32	i_next_alloc_block;
+
+	/*
+	 * i_next_alloc_goal is the *physical* companion to i_next_alloc_block.
+	 * it the the physical block number of the block which was most-recently
+	 * allocated to this file.  This give us the goal (target) for the next
+	 * allocation when we detect linearly ascending requests.
+	 */
+	__u32	i_next_alloc_goal;
+	__u32	i_prealloc_block;
+	__u32	i_prealloc_count;
+	__u32	i_dir_start_lookup;
+#ifdef CONFIG_EXT2_FS_XATTR
+	/*
+	 * Extended attributes can be read independently of the main file
+	 * data. Taking i_sem even when reading would cause contention
+	 * between readers of EAs and writers of regular file data, so
+	 * instead we synchronize on xattr_sem when reading or changing
+	 * EAs.
+	 */
+	struct rw_semaphore xattr_sem;
+#endif
+#ifdef CONFIG_EXT2_FS_POSIX_ACL
+	struct posix_acl	*i_acl;
+	struct posix_acl	*i_default_acl;
+#endif
+	rwlock_t i_meta_lock;
+	struct inode	vfs_inode;
+};
+
+/*
+ * Inode dynamic state flags
+ */
+#define EXT2_STATE_NEW			0x00000001 /* inode is newly created */
+
+
+/*
+ * Function prototypes
+ */
+
+/*
+ * Ok, these declarations are also in <linux/kernel.h> but none of the
+ * ext2 source programs needs to include it so they are duplicated here.
+ */
+
+static inline struct ext2_inode_info *EXT2_I(struct inode *inode)
+{
+	return container_of(inode, struct ext2_inode_info, vfs_inode);
+}
+
+/* balloc.c */
+extern int ext2_bg_has_super(struct super_block *sb, int group);
+extern unsigned long ext2_bg_num_gdb(struct super_block *sb, int group);
+extern int ext2_new_block (struct inode *, unsigned long,
+			   __u32 *, __u32 *, int *);
+extern void ext2_free_blocks (struct inode *, unsigned long,
+			      unsigned long);
+extern unsigned long ext2_count_free_blocks (struct super_block *);
+extern unsigned long ext2_count_dirs (struct super_block *);
+extern void ext2_check_blocks_bitmap (struct super_block *);
+extern struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb,
+						    unsigned int block_group,
+						    struct buffer_head ** bh);
+
+/* dir.c */
+extern int ext2_add_link (struct dentry *, struct inode *);
+extern ino_t ext2_inode_by_name(struct inode *, struct dentry *);
+extern int ext2_make_empty(struct inode *, struct inode *);
+extern struct ext2_dir_entry_2 * ext2_find_entry (struct inode *,struct dentry *, struct page **);
+extern int ext2_delete_entry (struct ext2_dir_entry_2 *, struct page *);
+extern int ext2_empty_dir (struct inode *);
+extern struct ext2_dir_entry_2 * ext2_dotdot (struct inode *, struct page **);
+extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, struct inode *);
+
+/* fsync.c */
+extern int ext2_sync_file (struct file *, struct dentry *, int);
+
+/* ialloc.c */
+extern struct inode * ext2_new_inode (struct inode *, int);
+extern void ext2_free_inode (struct inode *);
+extern unsigned long ext2_count_free_inodes (struct super_block *);
+extern void ext2_check_inodes_bitmap (struct super_block *);
+extern unsigned long ext2_count_free (struct buffer_head *, unsigned);
+
+/* inode.c */
+extern void ext2_read_inode (struct inode *);
+extern int ext2_write_inode (struct inode *, int);
+extern void ext2_delete_inode (struct inode *);
+extern int ext2_sync_inode (struct inode *);
+extern void ext2_discard_prealloc (struct inode *);
+extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int);
+extern void ext2_truncate (struct inode *);
+extern int ext2_setattr (struct dentry *, struct iattr *);
+extern void ext2_set_inode_flags(struct inode *inode);
+
+/* ioctl.c */
+extern int ext2_ioctl (struct inode *, struct file *, unsigned int,
+		       unsigned long);
+
+/* super.c */
+extern void ext2_error (struct super_block *, const char *, const char *, ...)
+	__attribute__ ((format (printf, 3, 4)));
+extern void ext2_warning (struct super_block *, const char *, const char *, ...)
+	__attribute__ ((format (printf, 3, 4)));
+extern void ext2_update_dynamic_rev (struct super_block *sb);
+extern void ext2_write_super (struct super_block *);
+
+/*
+ * Inodes and files operations
+ */
+
+/* dir.c */
+extern struct file_operations ext2_dir_operations;
+
+/* file.c */
+extern struct inode_operations ext2_file_inode_operations;
+extern struct file_operations ext2_file_operations;
+
+/* inode.c */
+extern struct address_space_operations ext2_aops;
+extern struct address_space_operations ext2_nobh_aops;
+
+/* namei.c */
+extern struct inode_operations ext2_dir_inode_operations;
+extern struct inode_operations ext2_special_inode_operations;
+
+/* symlink.c */
+extern struct inode_operations ext2_fast_symlink_inode_operations;
+extern struct inode_operations ext2_symlink_inode_operations;

fs/ext2/file.c

@@ -0,0 +1,68 @@
+/*
+ *  linux/fs/ext2/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
+ *
+ *  ext2 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 "ext2.h"
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * Called when an inode is released. Note that this is different
+ * from ext2_open_file: open gets called at every open, but release
+ * gets called only when /all/ the files are closed.
+ */
+static int ext2_release_file (struct inode * inode, struct file * filp)
+{
+	if (filp->f_mode & FMODE_WRITE)
+		ext2_discard_prealloc (inode);
+	return 0;
+}
+
+/*
+ * We have mostly NULL's here: the current defaults are ok for
+ * the ext2 filesystem.
+ */
+struct file_operations ext2_file_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= generic_file_read,
+	.write		= generic_file_write,
+	.aio_read	= generic_file_aio_read,
+	.aio_write	= generic_file_aio_write,
+	.ioctl		= ext2_ioctl,
+	.mmap		= generic_file_mmap,
+	.open		= generic_file_open,
+	.release	= ext2_release_file,
+	.fsync		= ext2_sync_file,
+	.readv		= generic_file_readv,
+	.writev		= generic_file_writev,
+	.sendfile	= generic_file_sendfile,
+};
+
+struct inode_operations ext2_file_inode_operations = {
+	.truncate	= ext2_truncate,
+#ifdef CONFIG_EXT2_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext2_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+	.setattr	= ext2_setattr,
+	.permission	= ext2_permission,
+};

fs/ext2/fsync.c

@@ -0,0 +1,51 @@
+/*
+ *  linux/fs/ext2/fsync.c
+ *
+ *  Copyright (C) 1993  Stephen Tweedie (sct@dcs.ed.ac.uk)
+ *  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
+ * 
+ *  ext2fs 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 "ext2.h"
+#include <linux/smp_lock.h>
+#include <linux/buffer_head.h>		/* for fsync_inode_buffers() */
+
+
+/*
+ *	File may be NULL when we are called. Perhaps we shouldn't
+ *	even pass file to fsync ?
+ */
+
+int ext2_sync_file(struct file *file, struct dentry *dentry, int datasync)
+{
+	struct inode *inode = dentry->d_inode;
+	int err;
+	int ret;
+
+	ret = sync_mapping_buffers(inode->i_mapping);
+	if (!(inode->i_state & I_DIRTY))
+		return ret;
+	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
+		return ret;
+
+	err = ext2_sync_inode(inode);
+	if (ret == 0)
+		ret = err;
+	return ret;
+}

fs/ext2/ialloc.c

@@ -0,0 +1,735 @@
+/*
+ *  linux/fs/ext2/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@dcs.ed.ac.uk), 1993
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ */
+
+#include <linux/config.h>
+#include <linux/quotaops.h>
+#include <linux/sched.h>
+#include <linux/backing-dev.h>
+#include <linux/buffer_head.h>
+#include <linux/random.h>
+#include "ext2.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 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_inode_bitmap));
+	if (!bh)
+		ext2_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;
+}
+
+static void ext2_release_inode(struct super_block *sb, int group, int dir)
+{
+	struct ext2_group_desc * desc;
+	struct buffer_head *bh;
+
+	desc = ext2_get_group_desc(sb, group, &bh);
+	if (!desc) {
+		ext2_error(sb, "ext2_release_inode",
+			"can't get descriptor for group %d", group);
+		return;
+	}
+
+	spin_lock(sb_bgl_lock(EXT2_SB(sb), group));
+	desc->bg_free_inodes_count =
+		cpu_to_le16(le16_to_cpu(desc->bg_free_inodes_count) + 1);
+	if (dir)
+		desc->bg_used_dirs_count =
+			cpu_to_le16(le16_to_cpu(desc->bg_used_dirs_count) - 1);
+	spin_unlock(sb_bgl_lock(EXT2_SB(sb), group));
+	if (dir)
+		percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter);
+	sb->s_dirt = 1;
+	mark_buffer_dirty(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 ext2_free_inode (struct inode * inode)
+{
+	struct super_block * sb = inode->i_sb;
+	int is_directory;
+	unsigned long ino;
+	struct buffer_head *bitmap_bh = NULL;
+	unsigned long block_group;
+	unsigned long bit;
+	struct ext2_super_block * es;
+
+	ino = inode->i_ino;
+	ext2_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.
+	 */
+	if (!is_bad_inode(inode)) {
+		/* Quota is already initialized in iput() */
+		ext2_xattr_delete_inode(inode);
+	    	DQUOT_FREE_INODE(inode);
+		DQUOT_DROP(inode);
+	}
+
+	es = EXT2_SB(sb)->s_es;
+	is_directory = S_ISDIR(inode->i_mode);
+
+	/* Do this BEFORE marking the inode not in use or returning an error */
+	clear_inode (inode);
+
+	if (ino < EXT2_FIRST_INO(sb) ||
+	    ino > le32_to_cpu(es->s_inodes_count)) {
+		ext2_error (sb, "ext2_free_inode",
+			    "reserved or nonexistent inode %lu", ino);
+		goto error_return;
+	}
+	block_group = (ino - 1) / EXT2_INODES_PER_GROUP(sb);
+	bit = (ino - 1) % EXT2_INODES_PER_GROUP(sb);
+	brelse(bitmap_bh);
+	bitmap_bh = read_inode_bitmap(sb, block_group);
+	if (!bitmap_bh)
+		goto error_return;
+
+	/* Ok, now we can actually update the inode bitmaps.. */
+	if (!ext2_clear_bit_atomic(sb_bgl_lock(EXT2_SB(sb), block_group),
+				bit, (void *) bitmap_bh->b_data))
+		ext2_error (sb, "ext2_free_inode",
+			      "bit already cleared for inode %lu", ino);
+	else
+		ext2_release_inode(sb, block_group, is_directory);
+	mark_buffer_dirty(bitmap_bh);
+	if (sb->s_flags & MS_SYNCHRONOUS)
+		sync_dirty_buffer(bitmap_bh);
+error_return:
+	brelse(bitmap_bh);
+}
+
+/*
+ * We perform asynchronous prereading of the new inode's inode block when
+ * we create the inode, in the expectation that the inode will be written
+ * back soon.  There are two reasons:
+ *
+ * - When creating a large number of files, the async prereads will be
+ *   nicely merged into large reads
+ * - When writing out a large number of inodes, we don't need to keep on
+ *   stalling the writes while we read the inode block.
+ *
+ * FIXME: ext2_get_group_desc() needs to be simplified.
+ */
+static void ext2_preread_inode(struct inode *inode)
+{
+	unsigned long block_group;
+	unsigned long offset;
+	unsigned long block;
+	struct buffer_head *bh;
+	struct ext2_group_desc * gdp;
+	struct backing_dev_info *bdi;
+
+	bdi = inode->i_mapping->backing_dev_info;
+	if (bdi_read_congested(bdi))
+		return;
+	if (bdi_write_congested(bdi))
+		return;
+
+	block_group = (inode->i_ino - 1) / EXT2_INODES_PER_GROUP(inode->i_sb);
+	gdp = ext2_get_group_desc(inode->i_sb, block_group, &bh);
+	if (gdp == NULL)
+		return;
+
+	/*
+	 * Figure out the offset within the block group inode table
+	 */
+	offset = ((inode->i_ino - 1) % EXT2_INODES_PER_GROUP(inode->i_sb)) *
+				EXT2_INODE_SIZE(inode->i_sb);
+	block = le32_to_cpu(gdp->bg_inode_table) +
+				(offset >> EXT2_BLOCK_SIZE_BITS(inode->i_sb));
+	sb_breadahead(inode->i_sb, block);
+}
+
+/*
+ * 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 = EXT2_SB(sb)->s_groups_count;
+	int avefreei = ext2_count_free_inodes(sb) / ngroups;
+	struct ext2_group_desc *desc, *best_desc = NULL;
+	struct buffer_head *bh, *best_bh = NULL;
+	int group, best_group = -1;
+
+	for (group = 0; group < ngroups; group++) {
+		desc = ext2_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;
+			best_bh = bh;
+		}
+	}
+	if (!best_desc)
+		return -1;
+
+	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 = EXT2_I(parent)->i_block_group;
+	struct ext2_sb_info *sbi = EXT2_SB(sb);
+	struct ext2_super_block *es = sbi->s_es;
+	int ngroups = sbi->s_groups_count;
+	int inodes_per_group = EXT2_INODES_PER_GROUP(sb);
+	int freei;
+	int avefreei;
+	int free_blocks;
+	int avefreeb;
+	int blocks_per_dir;
+	int ndirs;
+	int max_debt, max_dirs, min_blocks, min_inodes;
+	int group = -1, i;
+	struct ext2_group_desc *desc;
+	struct buffer_head *bh;
+
+	freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
+	avefreei = freei / ngroups;
+	free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+	avefreeb = free_blocks / ngroups;
+	ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
+
+	if ((parent == sb->s_root->d_inode) ||
+	    (EXT2_I(parent)->i_flags & EXT2_TOPDIR_FL)) {
+		struct ext2_group_desc *best_desc = NULL;
+		struct buffer_head *best_bh = NULL;
+		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 = ext2_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);
+			best_desc = desc;
+			best_bh = bh;
+		}
+		if (best_group >= 0) {
+			desc = best_desc;
+			bh = best_bh;
+			group = best_group;
+			goto found;
+		}
+		goto fallback;
+	}
+
+	if (ndirs == 0)
+		ndirs = 1;	/* percpu_counters are approximate... */
+
+	blocks_per_dir = (le32_to_cpu(es->s_blocks_count)-free_blocks) / ndirs;
+
+	max_dirs = ndirs / ngroups + inodes_per_group / 16;
+	min_inodes = avefreei - inodes_per_group / 4;
+	min_blocks = avefreeb - EXT2_BLOCKS_PER_GROUP(sb) / 4;
+
+	max_debt = EXT2_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 = ext2_get_group_desc (sb, group, &bh);
+		if (!desc || !desc->bg_free_inodes_count)
+			continue;
+		if (sbi->s_debts[group] >= max_debt)
+			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;
+		goto found;
+	}
+
+fallback:
+	for (i = 0; i < ngroups; i++) {
+		group = (parent_group + i) % ngroups;
+		desc = ext2_get_group_desc (sb, group, &bh);
+		if (!desc || !desc->bg_free_inodes_count)
+			continue;
+		if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
+			goto found;
+	}
+
+	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;
+
+found:
+	return group;
+}
+
+static int find_group_other(struct super_block *sb, struct inode *parent)
+{
+	int parent_group = EXT2_I(parent)->i_block_group;
+	int ngroups = EXT2_SB(sb)->s_groups_count;
+	struct ext2_group_desc *desc;
+	struct buffer_head *bh;
+	int group, i;
+
+	/*
+	 * Try to place the inode in its parent directory
+	 */
+	group = parent_group;
+	desc = ext2_get_group_desc (sb, group, &bh);
+	if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
+			le16_to_cpu(desc->bg_free_blocks_count))
+		goto found;
+
+	/*
+	 * 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 = ext2_get_group_desc (sb, group, &bh);
+		if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
+				le16_to_cpu(desc->bg_free_blocks_count))
+			goto found;
+	}
+
+	/*
+	 * 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 = ext2_get_group_desc (sb, group, &bh);
+		if (desc && le16_to_cpu(desc->bg_free_inodes_count))
+			goto found;
+	}
+
+	return -1;
+
+found:
+	return group;
+}
+
+struct inode *ext2_new_inode(struct inode *dir, int mode)
+{
+	struct super_block *sb;
+	struct buffer_head *bitmap_bh = NULL;
+	struct buffer_head *bh2;
+	int group, i;
+	ino_t ino = 0;
+	struct inode * inode;
+	struct ext2_group_desc *gdp;
+	struct ext2_super_block *es;
+	struct ext2_inode_info *ei;
+	struct ext2_sb_info *sbi;
+	int err;
+
+	sb = dir->i_sb;
+	inode = new_inode(sb);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	ei = EXT2_I(inode);
+	sbi = EXT2_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);
+
+	if (group == -1) {
+		err = -ENOSPC;
+		goto fail;
+	}
+
+	for (i = 0; i < sbi->s_groups_count; i++) {
+		gdp = ext2_get_group_desc(sb, group, &bh2);
+		brelse(bitmap_bh);
+		bitmap_bh = read_inode_bitmap(sb, group);
+		if (!bitmap_bh) {
+			err = -EIO;
+			goto fail;
+		}
+		ino = 0;
+
+repeat_in_this_group:
+		ino = ext2_find_next_zero_bit((unsigned long *)bitmap_bh->b_data,
+					      EXT2_INODES_PER_GROUP(sb), ino);
+		if (ino >= EXT2_INODES_PER_GROUP(sb)) {
+			/*
+			 * Rare race: find_group_xx() decided that there were
+			 * free inodes in this group, but by the time we tried
+			 * to allocate one, they're all gone.  This can also
+			 * occur because the counters which find_group_orlov()
+			 * uses are approximate.  So just go and search the
+			 * next block group.
+			 */
+			if (++group == sbi->s_groups_count)
+				group = 0;
+			continue;
+		}
+		if (ext2_set_bit_atomic(sb_bgl_lock(sbi, group),
+						ino, bitmap_bh->b_data)) {
+			/* we lost this inode */
+			if (++ino >= EXT2_INODES_PER_GROUP(sb)) {
+				/* this group is exhausted, try next group */
+				if (++group == sbi->s_groups_count)
+					group = 0;
+				continue;
+			}
+			/* try to find free inode in the same group */
+			goto repeat_in_this_group;
+		}
+		goto got;
+	}
+
+	/*
+	 * Scanned all blockgroups.
+	 */
+	err = -ENOSPC;
+	goto fail;
+got:
+	mark_buffer_dirty(bitmap_bh);
+	if (sb->s_flags & MS_SYNCHRONOUS)
+		sync_dirty_buffer(bitmap_bh);
+	brelse(bitmap_bh);
+
+	ino += group * EXT2_INODES_PER_GROUP(sb) + 1;
+	if (ino < EXT2_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
+		ext2_error (sb, "ext2_new_inode",
+			    "reserved inode or inode > inodes count - "
+			    "block_group = %d,inode=%lu", group,
+			    (unsigned long) ino);
+		err = -EIO;
+		goto fail;
+	}
+
+	percpu_counter_mod(&sbi->s_freeinodes_counter, -1);
+	if (S_ISDIR(mode))
+		percpu_counter_inc(&sbi->s_dirs_counter);
+
+	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)) {
+		if (sbi->s_debts[group] < 255)
+			sbi->s_debts[group]++;
+		gdp->bg_used_dirs_count =
+			cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1);
+	} else {
+		if (sbi->s_debts[group])
+			sbi->s_debts[group]--;
+	}
+	spin_unlock(sb_bgl_lock(sbi, group));
+
+	sb->s_dirt = 1;
+	mark_buffer_dirty(bh2);
+	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;
+	inode->i_blksize = PAGE_SIZE;	/* This is the optimal IO size (for stat), not the fs block 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_flags = EXT2_I(dir)->i_flags & ~EXT2_BTREE_FL;
+	if (S_ISLNK(mode))
+		ei->i_flags &= ~(EXT2_IMMUTABLE_FL|EXT2_APPEND_FL);
+	/* dirsync is only applied to directories */
+	if (!S_ISDIR(mode))
+		ei->i_flags &= ~EXT2_DIRSYNC_FL;
+	ei->i_faddr = 0;
+	ei->i_frag_no = 0;
+	ei->i_frag_size = 0;
+	ei->i_file_acl = 0;
+	ei->i_dir_acl = 0;
+	ei->i_dtime = 0;
+	ei->i_block_group = group;
+	ei->i_next_alloc_block = 0;
+	ei->i_next_alloc_goal = 0;
+	ei->i_prealloc_block = 0;
+	ei->i_prealloc_count = 0;
+	ei->i_dir_start_lookup = 0;
+	ei->i_state = EXT2_STATE_NEW;
+	ext2_set_inode_flags(inode);
+	spin_lock(&sbi->s_next_gen_lock);
+	inode->i_generation = sbi->s_next_generation++;
+	spin_unlock(&sbi->s_next_gen_lock);
+	insert_inode_hash(inode);
+
+	if (DQUOT_ALLOC_INODE(inode)) {
+		DQUOT_DROP(inode);
+		err = -ENOSPC;
+		goto fail2;
+	}
+	err = ext2_init_acl(inode, dir);
+	if (err) {
+		DQUOT_FREE_INODE(inode);
+		goto fail2;
+	}
+	mark_inode_dirty(inode);
+	ext2_debug("allocating inode %lu\n", inode->i_ino);
+	ext2_preread_inode(inode);
+	return inode;
+
+fail2:
+	inode->i_flags |= S_NOQUOTA;
+	inode->i_nlink = 0;
+	iput(inode);
+	return ERR_PTR(err);
+
+fail:
+	make_bad_inode(inode);
+	iput(inode);
+	return ERR_PTR(err);
+}
+
+unsigned long ext2_count_free_inodes (struct super_block * sb)
+{
+	struct ext2_group_desc *desc;
+	unsigned long desc_count = 0;
+	int i;	
+
+#ifdef EXT2FS_DEBUG
+	struct ext2_super_block *es;
+	unsigned long bitmap_count = 0;
+	struct buffer_head *bitmap_bh = NULL;
+
+	lock_super (sb);
+	es = EXT2_SB(sb)->s_es;
+	for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) {
+		unsigned x;
+
+		desc = ext2_get_group_desc (sb, i, NULL);
+		if (!desc)
+			continue;
+		desc_count += le16_to_cpu(desc->bg_free_inodes_count);
+		brelse(bitmap_bh);
+		bitmap_bh = read_inode_bitmap(sb, i);
+		if (!bitmap_bh)
+			continue;
+
+		x = ext2_count_free(bitmap_bh, EXT2_INODES_PER_GROUP(sb) / 8);
+		printk("group %d: stored = %d, counted = %u\n",
+			i, le16_to_cpu(desc->bg_free_inodes_count), x);
+		bitmap_count += x;
+	}
+	brelse(bitmap_bh);
+	printk("ext2_count_free_inodes: stored = %lu, computed = %lu, %lu\n",
+		percpu_counter_read(&EXT2_SB(sb)->s_freeinodes_counter),
+		desc_count, bitmap_count);
+	unlock_super(sb);
+	return desc_count;
+#else
+	for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) {
+		desc = ext2_get_group_desc (sb, i, NULL);
+		if (!desc)
+			continue;
+		desc_count += le16_to_cpu(desc->bg_free_inodes_count);
+	}
+	return desc_count;
+#endif
+}
+
+/* Called at mount-time, super-block is locked */
+unsigned long ext2_count_dirs (struct super_block * sb)
+{
+	unsigned long count = 0;
+	int i;
+
+	for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) {
+		struct ext2_group_desc *gdp = ext2_get_group_desc (sb, i, NULL);
+		if (!gdp)
+			continue;
+		count += le16_to_cpu(gdp->bg_used_dirs_count);
+	}
+	return count;
+}
+
+#ifdef CONFIG_EXT2_CHECK
+/* Called at mount-time, super-block is locked */
+void ext2_check_inodes_bitmap (struct super_block * sb)
+{
+	struct ext2_super_block * es = EXT2_SB(sb)->s_es;
+	unsigned long desc_count = 0, bitmap_count = 0;
+	struct buffer_head *bitmap_bh = NULL;
+	int i;
+
+	for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) {
+		struct ext2_group_desc *desc;
+		unsigned x;
+
+		desc = ext2_get_group_desc(sb, i, NULL);
+		if (!desc)
+			continue;
+		desc_count += le16_to_cpu(desc->bg_free_inodes_count);
+		brelse(bitmap_bh);
+		bitmap_bh = read_inode_bitmap(sb, i);
+		if (!bitmap_bh)
+			continue;
+		
+		x = ext2_count_free(bitmap_bh, EXT2_INODES_PER_GROUP(sb) / 8);
+		if (le16_to_cpu(desc->bg_free_inodes_count) != x)
+			ext2_error (sb, "ext2_check_inodes_bitmap",
+				    "Wrong free inodes count in group %d, "
+				    "stored = %d, counted = %lu", i,
+				    le16_to_cpu(desc->bg_free_inodes_count), x);
+		bitmap_count += x;
+	}
+	brelse(bitmap_bh);
+	if (percpu_counter_read(&EXT2_SB(sb)->s_freeinodes_counter) !=
+				bitmap_count)
+		ext2_error(sb, "ext2_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/ext2/ioctl.c

@@ -0,0 +1,81 @@
+/*
+ * linux/fs/ext2/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 "ext2.h"
+#include <linux/time.h>
+#include <linux/sched.h>
+#include <asm/current.h>
+#include <asm/uaccess.h>
+
+
+int ext2_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
+		unsigned long arg)
+{
+	struct ext2_inode_info *ei = EXT2_I(inode);
+	unsigned int flags;
+
+	ext2_debug ("cmd = %u, arg = %lu\n", cmd, arg);
+
+	switch (cmd) {
+	case EXT2_IOC_GETFLAGS:
+		flags = ei->i_flags & EXT2_FL_USER_VISIBLE;
+		return put_user(flags, (int __user *) arg);
+	case EXT2_IOC_SETFLAGS: {
+		unsigned int oldflags;
+
+		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 &= ~EXT2_DIRSYNC_FL;
+
+		oldflags = ei->i_flags;
+
+		/*
+		 * 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) & (EXT2_APPEND_FL | EXT2_IMMUTABLE_FL)) {
+			if (!capable(CAP_LINUX_IMMUTABLE))
+				return -EPERM;
+		}
+
+		flags = flags & EXT2_FL_USER_MODIFIABLE;
+		flags |= oldflags & ~EXT2_FL_USER_MODIFIABLE;
+		ei->i_flags = flags;
+
+		ext2_set_inode_flags(inode);
+		inode->i_ctime = CURRENT_TIME_SEC;
+		mark_inode_dirty(inode);
+		return 0;
+	}
+	case EXT2_IOC_GETVERSION:
+		return put_user(inode->i_generation, (int __user *) arg);
+	case EXT2_IOC_SETVERSION:
+		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+			return -EPERM;
+		if (IS_RDONLY(inode))
+			return -EROFS;
+		if (get_user(inode->i_generation, (int __user *) arg))
+			return -EFAULT;	
+		inode->i_ctime = CURRENT_TIME_SEC;
+		mark_inode_dirty(inode);
+		return 0;
+	default:
+		return -ENOTTY;
+	}
+}

fs/ext2/namei.c

@@ -0,0 +1,418 @@
+/*
+ * linux/fs/ext2/namei.c
+ *
+ * Rewrite to pagecache. Almost all code had been changed, so blame me
+ * if the things go wrong. Please, send bug reports to
+ * viro@parcelfarce.linux.theplanet.co.uk
+ *
+ * Stuff here is basically a glue between the VFS and generic UNIXish
+ * filesystem that keeps everything in pagecache. All knowledge of the
+ * directory layout is in fs/ext2/dir.c - it turned out to be easily separatable
+ * and it's easier to debug that way. In principle we might want to
+ * generalize that a bit and turn it into a library. Or not.
+ *
+ * The only non-static object here is ext2_dir_inode_operations.
+ *
+ * TODO: get rid of kmap() use, add readahead.
+ *
+ * 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/namei.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  Big-endian to little-endian byte-swapping/bitmaps by
+ *        David S. Miller (davem@caip.rutgers.edu), 1995
+ */
+
+#include <linux/pagemap.h>
+#include "ext2.h"
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * Couple of helper functions - make the code slightly cleaner.
+ */
+
+static inline void ext2_inc_count(struct inode *inode)
+{
+	inode->i_nlink++;
+	mark_inode_dirty(inode);
+}
+
+static inline void ext2_dec_count(struct inode *inode)
+{
+	inode->i_nlink--;
+	mark_inode_dirty(inode);
+}
+
+static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
+{
+	int err = ext2_add_link(dentry, inode);
+	if (!err) {
+		d_instantiate(dentry, inode);
+		return 0;
+	}
+	ext2_dec_count(inode);
+	iput(inode);
+	return err;
+}
+
+/*
+ * Methods themselves.
+ */
+
+static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+{
+	struct inode * inode;
+	ino_t ino;
+	
+	if (dentry->d_name.len > EXT2_NAME_LEN)
+		return ERR_PTR(-ENAMETOOLONG);
+
+	ino = ext2_inode_by_name(dir, dentry);
+	inode = NULL;
+	if (ino) {
+		inode = iget(dir->i_sb, ino);
+		if (!inode)
+			return ERR_PTR(-EACCES);
+	}
+	if (inode)
+		return d_splice_alias(inode, dentry);
+	d_add(dentry, inode);
+	return NULL;
+}
+
+struct dentry *ext2_get_parent(struct dentry *child)
+{
+	unsigned long ino;
+	struct dentry *parent;
+	struct inode *inode;
+	struct dentry dotdot;
+
+	dotdot.d_name.name = "..";
+	dotdot.d_name.len = 2;
+
+	ino = ext2_inode_by_name(child->d_inode, &dotdot);
+	if (!ino)
+		return ERR_PTR(-ENOENT);
+	inode = iget(child->d_inode->i_sb, ino);
+
+	if (!inode)
+		return ERR_PTR(-EACCES);
+	parent = d_alloc_anon(inode);
+	if (!parent) {
+		iput(inode);
+		parent = ERR_PTR(-ENOMEM);
+	}
+	return parent;
+} 
+
+/*
+ * By the time this is called, we already have created
+ * the directory cache entry for the new file, but it
+ * is so far negative - it has no inode.
+ *
+ * If the create succeeds, we fill in the inode information
+ * with d_instantiate(). 
+ */
+static int ext2_create (struct inode * dir, struct dentry * dentry, int mode, struct nameidata *nd)
+{
+	struct inode * inode = ext2_new_inode (dir, mode);
+	int err = PTR_ERR(inode);
+	if (!IS_ERR(inode)) {
+		inode->i_op = &ext2_file_inode_operations;
+		inode->i_fop = &ext2_file_operations;
+		if (test_opt(inode->i_sb, NOBH))
+			inode->i_mapping->a_ops = &ext2_nobh_aops;
+		else
+			inode->i_mapping->a_ops = &ext2_aops;
+		mark_inode_dirty(inode);
+		err = ext2_add_nondir(dentry, inode);
+	}
+	return err;
+}
+
+static int ext2_mknod (struct inode * dir, struct dentry *dentry, int mode, dev_t rdev)
+{
+	struct inode * inode;
+	int err;
+
+	if (!new_valid_dev(rdev))
+		return -EINVAL;
+
+	inode = ext2_new_inode (dir, mode);
+	err = PTR_ERR(inode);
+	if (!IS_ERR(inode)) {
+		init_special_inode(inode, inode->i_mode, rdev);
+#ifdef CONFIG_EXT2_FS_XATTR
+		inode->i_op = &ext2_special_inode_operations;
+#endif
+		mark_inode_dirty(inode);
+		err = ext2_add_nondir(dentry, inode);
+	}
+	return err;
+}
+
+static int ext2_symlink (struct inode * dir, struct dentry * dentry,
+	const char * symname)
+{
+	struct super_block * sb = dir->i_sb;
+	int err = -ENAMETOOLONG;
+	unsigned l = strlen(symname)+1;
+	struct inode * inode;
+
+	if (l > sb->s_blocksize)
+		goto out;
+
+	inode = ext2_new_inode (dir, S_IFLNK | S_IRWXUGO);
+	err = PTR_ERR(inode);
+	if (IS_ERR(inode))
+		goto out;
+
+	if (l > sizeof (EXT2_I(inode)->i_data)) {
+		/* slow symlink */
+		inode->i_op = &ext2_symlink_inode_operations;
+		if (test_opt(inode->i_sb, NOBH))
+			inode->i_mapping->a_ops = &ext2_nobh_aops;
+		else
+			inode->i_mapping->a_ops = &ext2_aops;
+		err = page_symlink(inode, symname, l);
+		if (err)
+			goto out_fail;
+	} else {
+		/* fast symlink */
+		inode->i_op = &ext2_fast_symlink_inode_operations;
+		memcpy((char*)(EXT2_I(inode)->i_data),symname,l);
+		inode->i_size = l-1;
+	}
+	mark_inode_dirty(inode);
+
+	err = ext2_add_nondir(dentry, inode);
+out:
+	return err;
+
+out_fail:
+	ext2_dec_count(inode);
+	iput (inode);
+	goto out;
+}
+
+static int ext2_link (struct dentry * old_dentry, struct inode * dir,
+	struct dentry *dentry)
+{
+	struct inode *inode = old_dentry->d_inode;
+
+	if (inode->i_nlink >= EXT2_LINK_MAX)
+		return -EMLINK;
+
+	inode->i_ctime = CURRENT_TIME_SEC;
+	ext2_inc_count(inode);
+	atomic_inc(&inode->i_count);
+
+	return ext2_add_nondir(dentry, inode);
+}
+
+static int ext2_mkdir(struct inode * dir, struct dentry * dentry, int mode)
+{
+	struct inode * inode;
+	int err = -EMLINK;
+
+	if (dir->i_nlink >= EXT2_LINK_MAX)
+		goto out;
+
+	ext2_inc_count(dir);
+
+	inode = ext2_new_inode (dir, S_IFDIR | mode);
+	err = PTR_ERR(inode);
+	if (IS_ERR(inode))
+		goto out_dir;
+
+	inode->i_op = &ext2_dir_inode_operations;
+	inode->i_fop = &ext2_dir_operations;
+	if (test_opt(inode->i_sb, NOBH))
+		inode->i_mapping->a_ops = &ext2_nobh_aops;
+	else
+		inode->i_mapping->a_ops = &ext2_aops;
+
+	ext2_inc_count(inode);
+
+	err = ext2_make_empty(inode, dir);
+	if (err)
+		goto out_fail;
+
+	err = ext2_add_link(dentry, inode);
+	if (err)
+		goto out_fail;
+
+	d_instantiate(dentry, inode);
+out:
+	return err;
+
+out_fail:
+	ext2_dec_count(inode);
+	ext2_dec_count(inode);
+	iput(inode);
+out_dir:
+	ext2_dec_count(dir);
+	goto out;
+}
+
+static int ext2_unlink(struct inode * dir, struct dentry *dentry)
+{
+	struct inode * inode = dentry->d_inode;
+	struct ext2_dir_entry_2 * de;
+	struct page * page;
+	int err = -ENOENT;
+
+	de = ext2_find_entry (dir, dentry, &page);
+	if (!de)
+		goto out;
+
+	err = ext2_delete_entry (de, page);
+	if (err)
+		goto out;
+
+	inode->i_ctime = dir->i_ctime;
+	ext2_dec_count(inode);
+	err = 0;
+out:
+	return err;
+}
+
+static int ext2_rmdir (struct inode * dir, struct dentry *dentry)
+{
+	struct inode * inode = dentry->d_inode;
+	int err = -ENOTEMPTY;
+
+	if (ext2_empty_dir(inode)) {
+		err = ext2_unlink(dir, dentry);
+		if (!err) {
+			inode->i_size = 0;
+			ext2_dec_count(inode);
+			ext2_dec_count(dir);
+		}
+	}
+	return err;
+}
+
+static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry,
+	struct inode * new_dir,	struct dentry * new_dentry )
+{
+	struct inode * old_inode = old_dentry->d_inode;
+	struct inode * new_inode = new_dentry->d_inode;
+	struct page * dir_page = NULL;
+	struct ext2_dir_entry_2 * dir_de = NULL;
+	struct page * old_page;
+	struct ext2_dir_entry_2 * old_de;
+	int err = -ENOENT;
+
+	old_de = ext2_find_entry (old_dir, old_dentry, &old_page);
+	if (!old_de)
+		goto out;
+
+	if (S_ISDIR(old_inode->i_mode)) {
+		err = -EIO;
+		dir_de = ext2_dotdot(old_inode, &dir_page);
+		if (!dir_de)
+			goto out_old;
+	}
+
+	if (new_inode) {
+		struct page *new_page;
+		struct ext2_dir_entry_2 *new_de;
+
+		err = -ENOTEMPTY;
+		if (dir_de && !ext2_empty_dir (new_inode))
+			goto out_dir;
+
+		err = -ENOENT;
+		new_de = ext2_find_entry (new_dir, new_dentry, &new_page);
+		if (!new_de)
+			goto out_dir;
+		ext2_inc_count(old_inode);
+		ext2_set_link(new_dir, new_de, new_page, old_inode);
+		new_inode->i_ctime = CURRENT_TIME_SEC;
+		if (dir_de)
+			new_inode->i_nlink--;
+		ext2_dec_count(new_inode);
+	} else {
+		if (dir_de) {
+			err = -EMLINK;
+			if (new_dir->i_nlink >= EXT2_LINK_MAX)
+				goto out_dir;
+		}
+		ext2_inc_count(old_inode);
+		err = ext2_add_link(new_dentry, old_inode);
+		if (err) {
+			ext2_dec_count(old_inode);
+			goto out_dir;
+		}
+		if (dir_de)
+			ext2_inc_count(new_dir);
+	}
+
+	/*
+	 * Like most other Unix systems, set the ctime for inodes on a
+ 	 * rename.
+	 * ext2_dec_count() will mark the inode dirty.
+	 */
+	old_inode->i_ctime = CURRENT_TIME_SEC;
+
+	ext2_delete_entry (old_de, old_page);
+	ext2_dec_count(old_inode);
+
+	if (dir_de) {
+		ext2_set_link(old_inode, dir_de, dir_page, new_dir);
+		ext2_dec_count(old_dir);
+	}
+	return 0;
+
+
+out_dir:
+	if (dir_de) {
+		kunmap(dir_page);
+		page_cache_release(dir_page);
+	}
+out_old:
+	kunmap(old_page);
+	page_cache_release(old_page);
+out:
+	return err;
+}
+
+struct inode_operations ext2_dir_inode_operations = {
+	.create		= ext2_create,
+	.lookup		= ext2_lookup,
+	.link		= ext2_link,
+	.unlink		= ext2_unlink,
+	.symlink	= ext2_symlink,
+	.mkdir		= ext2_mkdir,
+	.rmdir		= ext2_rmdir,
+	.mknod		= ext2_mknod,
+	.rename		= ext2_rename,
+#ifdef CONFIG_EXT2_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext2_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+	.setattr	= ext2_setattr,
+	.permission	= ext2_permission,
+};
+
+struct inode_operations ext2_special_inode_operations = {
+#ifdef CONFIG_EXT2_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext2_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+	.setattr	= ext2_setattr,
+	.permission	= ext2_permission,
+};

fs/ext2/symlink.c

@@ -0,0 +1,52 @@
+/*
+ *  linux/fs/ext2/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
+ *
+ *  ext2 symlink handling code
+ */
+
+#include "ext2.h"
+#include "xattr.h"
+#include <linux/namei.h>
+
+static int ext2_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	struct ext2_inode_info *ei = EXT2_I(dentry->d_inode);
+	nd_set_link(nd, (char *)ei->i_data);
+	return 0;
+}
+
+struct inode_operations ext2_symlink_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= page_follow_link_light,
+	.put_link	= page_put_link,
+#ifdef CONFIG_EXT2_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext2_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+};
+ 
+struct inode_operations ext2_fast_symlink_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= ext2_follow_link,
+#ifdef CONFIG_EXT2_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext2_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+};

fs/ext2/xattr.h

@@ -0,0 +1,118 @@
+/*
+  File: linux/ext2_xattr.h
+
+  On-disk format of extended attributes for the ext2 filesystem.
+
+  (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org>
+*/
+
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/xattr.h>
+
+/* Magic value in attribute blocks */
+#define EXT2_XATTR_MAGIC		0xEA020000
+
+/* Maximum number of references to one attribute block */
+#define EXT2_XATTR_REFCOUNT_MAX		1024
+
+/* Name indexes */
+#define EXT2_XATTR_INDEX_USER			1
+#define EXT2_XATTR_INDEX_POSIX_ACL_ACCESS	2
+#define EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT	3
+#define EXT2_XATTR_INDEX_TRUSTED		4
+#define	EXT2_XATTR_INDEX_LUSTRE			5
+#define EXT2_XATTR_INDEX_SECURITY	        6
+
+struct ext2_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 ext2_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 EXT2_XATTR_PAD_BITS		2
+#define EXT2_XATTR_PAD		(1<<EXT2_XATTR_PAD_BITS)
+#define EXT2_XATTR_ROUND		(EXT2_XATTR_PAD-1)
+#define EXT2_XATTR_LEN(name_len) \
+	(((name_len) + EXT2_XATTR_ROUND + \
+	sizeof(struct ext2_xattr_entry)) & ~EXT2_XATTR_ROUND)
+#define EXT2_XATTR_NEXT(entry) \
+	( (struct ext2_xattr_entry *)( \
+	  (char *)(entry) + EXT2_XATTR_LEN((entry)->e_name_len)) )
+#define EXT2_XATTR_SIZE(size) \
+	(((size) + EXT2_XATTR_ROUND) & ~EXT2_XATTR_ROUND)
+
+# ifdef CONFIG_EXT2_FS_XATTR
+
+extern struct xattr_handler ext2_xattr_user_handler;
+extern struct xattr_handler ext2_xattr_trusted_handler;
+extern struct xattr_handler ext2_xattr_acl_access_handler;
+extern struct xattr_handler ext2_xattr_acl_default_handler;
+extern struct xattr_handler ext2_xattr_security_handler;
+
+extern ssize_t ext2_listxattr(struct dentry *, char *, size_t);
+
+extern int ext2_xattr_get(struct inode *, int, const char *, void *, size_t);
+extern int ext2_xattr_set(struct inode *, int, const char *, const void *, size_t, int);
+
+extern void ext2_xattr_delete_inode(struct inode *);
+extern void ext2_xattr_put_super(struct super_block *);
+
+extern int init_ext2_xattr(void);
+extern void exit_ext2_xattr(void);
+
+extern struct xattr_handler *ext2_xattr_handlers[];
+
+# else  /* CONFIG_EXT2_FS_XATTR */
+
+static inline int
+ext2_xattr_get(struct inode *inode, int name_index,
+	       const char *name, void *buffer, size_t size)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+ext2_xattr_set(struct inode *inode, int name_index, const char *name,
+	       const void *value, size_t size, int flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void
+ext2_xattr_delete_inode(struct inode *inode)
+{
+}
+
+static inline void
+ext2_xattr_put_super(struct super_block *sb)
+{
+}
+
+static inline int
+init_ext2_xattr(void)
+{
+	return 0;
+}
+
+static inline void
+exit_ext2_xattr(void)
+{
+}
+
+#define ext2_xattr_handlers NULL
+
+# endif  /* CONFIG_EXT2_FS_XATTR */
+

fs/ext2/xattr_security.c

@@ -0,0 +1,53 @@
+/*
+ * linux/fs/ext2/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/ext2_fs.h>
+#include "xattr.h"
+
+static size_t
+ext2_xattr_security_list(struct inode *inode, char *list, size_t list_size,
+			 const char *name, size_t name_len)
+{
+	const int 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
+ext2_xattr_security_get(struct inode *inode, const char *name,
+		       void *buffer, size_t size)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	return ext2_xattr_get(inode, EXT2_XATTR_INDEX_SECURITY, name,
+			      buffer, size);
+}
+
+static int
+ext2_xattr_security_set(struct inode *inode, const char *name,
+		       const void *value, size_t size, int flags)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	return ext2_xattr_set(inode, EXT2_XATTR_INDEX_SECURITY, name,
+			      value, size, flags);
+}
+
+struct xattr_handler ext2_xattr_security_handler = {
+	.prefix	= XATTR_SECURITY_PREFIX,
+	.list	= ext2_xattr_security_list,
+	.get	= ext2_xattr_security_get,
+	.set	= ext2_xattr_security_set,
+};

fs/ext2/xattr_trusted.c

@@ -0,0 +1,64 @@
+/*
+ * linux/fs/ext2/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/ext2_fs.h>
+#include "xattr.h"
+
+#define XATTR_TRUSTED_PREFIX "trusted."
+
+static size_t
+ext2_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
+			const char *name, size_t name_len)
+{
+	const int 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
+ext2_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 ext2_xattr_get(inode, EXT2_XATTR_INDEX_TRUSTED, name,
+			      buffer, size);
+}
+
+static int
+ext2_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 ext2_xattr_set(inode, EXT2_XATTR_INDEX_TRUSTED, name,
+			      value, size, flags);
+}
+
+struct xattr_handler ext2_xattr_trusted_handler = {
+	.prefix	= XATTR_TRUSTED_PREFIX,
+	.list	= ext2_xattr_trusted_list,
+	.get	= ext2_xattr_trusted_get,
+	.set	= ext2_xattr_trusted_set,
+};

fs/ext2/xattr_user.c

@@ -0,0 +1,77 @@
+/*
+ * linux/fs/ext2/xattr_user.c
+ * Handler for extended user attributes.
+ *
+ * Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include "ext2.h"
+#include "xattr.h"
+
+#define XATTR_USER_PREFIX "user."
+
+static size_t
+ext2_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
+ext2_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 ext2_xattr_get(inode, EXT2_XATTR_INDEX_USER, name, buffer, size);
+}
+
+static int
+ext2_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 ext2_xattr_set(inode, EXT2_XATTR_INDEX_USER, name,
+			      value, size, flags);
+}
+
+struct xattr_handler ext2_xattr_user_handler = {
+	.prefix	= XATTR_USER_PREFIX,
+	.list	= ext2_xattr_user_list,
+	.get	= ext2_xattr_user_get,
+	.set	= ext2_xattr_user_set,
+};