Fixed MTP to work with TWRP

fs/ext2/Kconfig

@@ -0,0 +1,55 @@
+config EXT2_FS
+	tristate "Second extended fs support"
+	help
+	  Ext2 is a standard Linux file system for hard disks.
+
+	  To compile this file system support as a module, choose M here: the
+	  module will be called ext2.
+
+	  If unsure, say Y.
+
+config EXT2_FS_XATTR
+	bool "Ext2 extended attributes"
+	depends on EXT2_FS
+	help
+	  Extended attributes are name:value pairs associated with inodes by
+	  the kernel or by users (see the attr(5) manual page, or visit
+	  <http://acl.bestbits.at/> for details).
+
+	  If unsure, say N.
+
+config EXT2_FS_POSIX_ACL
+	bool "Ext2 POSIX Access Control Lists"
+	depends on EXT2_FS_XATTR
+	select FS_POSIX_ACL
+	help
+	  Posix Access Control Lists (ACLs) support permissions for users and
+	  groups beyond the owner/group/world scheme.
+
+	  To learn more about Access Control Lists, visit the Posix ACLs for
+	  Linux website <http://acl.bestbits.at/>.
+
+	  If you don't know what Access Control Lists are, say N
+
+config EXT2_FS_SECURITY
+	bool "Ext2 Security Labels"
+	depends on EXT2_FS_XATTR
+	help
+	  Security labels support alternative access control models
+	  implemented by security modules like SELinux.  This option
+	  enables an extended attribute handler for file security
+	  labels in the ext2 filesystem.
+
+	  If you are not using a security module that requires using
+	  extended attributes for file security labels, say N.
+
+config EXT2_FS_XIP
+	bool "Ext2 execute in place support"
+	depends on EXT2_FS && MMU
+	help
+	  Execute in place can be used on memory-backed block devices. If you
+	  enable this option, you can select to mount block devices which are
+	  capable of this feature without using the page cache.
+
+	  If you do not use a block device that is capable of using this,
+	  or if unsure, say N.

fs/ext2/Makefile

@@ -0,0 +1,13 @@
+#
+# Makefile for the linux ext2-filesystem routines.
+#
+
+obj-$(CONFIG_EXT2_FS) += ext2.o
+
+ext2-y := balloc.o dir.o file.o ialloc.o inode.o \
+	  ioctl.o namei.o super.o symlink.o
+
+ext2-$(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
+ext2-$(CONFIG_EXT2_FS_XIP)	 += xip.o

fs/ext2/acl.c

@@ -0,0 +1,257 @@
+/*
+ * 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);
+				break;
+
+			case ACL_USER:
+				value = (char *)value + sizeof(ext2_acl_entry);
+				if ((char *)value > end)
+					goto fail;
+				acl->a_entries[n].e_uid =
+					make_kuid(&init_user_ns,
+						  le32_to_cpu(entry->e_id));
+				break;
+			case ACL_GROUP:
+				value = (char *)value + sizeof(ext2_acl_entry);
+				if ((char *)value > end)
+					goto fail;
+				acl->a_entries[n].e_gid =
+					make_kgid(&init_user_ns,
+						  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 = 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++) {
+		const struct posix_acl_entry *acl_e = &acl->a_entries[n];
+		ext2_acl_entry *entry = (ext2_acl_entry *)e;
+		entry->e_tag  = cpu_to_le16(acl_e->e_tag);
+		entry->e_perm = cpu_to_le16(acl_e->e_perm);
+		switch(acl_e->e_tag) {
+			case ACL_USER:
+				entry->e_id = cpu_to_le32(
+					from_kuid(&init_user_ns, acl_e->e_uid));
+				e += sizeof(ext2_acl_entry);
+				break;
+			case ACL_GROUP:
+				entry->e_id = cpu_to_le32(
+					from_kgid(&init_user_ns, acl_e->e_gid));
+				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);
+}
+
+/*
+ * inode->i_mutex: don't care
+ */
+struct posix_acl *
+ext2_get_acl(struct inode *inode, int type)
+{
+	int name_index;
+	char *value = NULL;
+	struct posix_acl *acl;
+	int retval;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		name_index = EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT;
+		break;
+	default:
+		BUG();
+	}
+	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);
+	kfree(value);
+
+	if (!IS_ERR(acl))
+		set_cached_acl(inode, type, acl);
+
+	return acl;
+}
+
+/*
+ * inode->i_mutex: down
+ */
+int
+ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+{
+	int name_index;
+	void *value = NULL;
+	size_t size = 0;
+	int error;
+
+	switch(type) {
+		case ACL_TYPE_ACCESS:
+			name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS;
+			if (acl) {
+				error = posix_acl_equiv_mode(acl, &inode->i_mode);
+				if (error < 0)
+					return error;
+				else {
+					inode->i_ctime = CURRENT_TIME_SEC;
+					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);
+
+	kfree(value);
+	if (!error)
+		set_cached_acl(inode, type, acl);
+	return error;
+}
+
+/*
+ * Initialize the ACLs of a new inode. Called from ext2_new_inode.
+ *
+ * dir->i_mutex: down
+ * inode->i_mutex: up (access to inode is still exclusive)
+ */
+int
+ext2_init_acl(struct inode *inode, struct inode *dir)
+{
+	struct posix_acl *default_acl, *acl;
+	int error;
+
+	error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
+	if (error)
+		return error;
+
+	if (default_acl) {
+		error = ext2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
+		posix_acl_release(default_acl);
+	}
+	if (acl) {
+		if (!error)
+			error = ext2_set_acl(inode, acl, ACL_TYPE_ACCESS);
+		posix_acl_release(acl);
+	}
+	return error;
+}

fs/ext2/acl.h

@@ -0,0 +1,71 @@
+/*
+  File: fs/ext2/acl.h
+
+  (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org>
+*/
+
+#include <linux/posix_acl_xattr.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
+
+/* acl.c */
+extern struct posix_acl *ext2_get_acl(struct inode *inode, int type);
+extern int ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+extern int ext2_init_acl (struct inode *, struct inode *);
+
+#else
+#include <linux/sched.h>
+#define ext2_get_acl	NULL
+#define ext2_set_acl	NULL
+
+static inline int ext2_init_acl (struct inode *inode, struct inode *dir)
+{
+	return 0;
+}
+#endif
+

fs/ext2/dir.c

@@ -0,0 +1,730 @@
+/*
+ *  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/buffer_head.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+
+typedef struct ext2_dir_entry_2 ext2_dirent;
+
+/*
+ * Tests against MAX_REC_LEN etc were put in place for 64k block
+ * sizes; if that is not possible on this arch, we can skip
+ * those tests and speed things up.
+ */
+static inline unsigned ext2_rec_len_from_disk(__le16 dlen)
+{
+	unsigned len = le16_to_cpu(dlen);
+
+#if (PAGE_CACHE_SIZE >= 65536)
+	if (len == EXT2_MAX_REC_LEN)
+		return 1 << 16;
+#endif
+	return len;
+}
+
+static inline __le16 ext2_rec_len_to_disk(unsigned len)
+{
+#if (PAGE_CACHE_SIZE >= 65536)
+	if (len == (1 << 16))
+		return cpu_to_le16(EXT2_MAX_REC_LEN);
+	else
+		BUG_ON(len > (1 << 16));
+#endif
+	return cpu_to_le16(len);
+}
+
+/*
+ * 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, loff_t pos, unsigned len)
+{
+	struct address_space *mapping = page->mapping;
+	struct inode *dir = mapping->host;
+	int err = 0;
+
+	dir->i_version++;
+	block_write_end(NULL, mapping, pos, len, len, page, NULL);
+
+	if (pos+len > dir->i_size) {
+		i_size_write(dir, pos+len);
+		mark_inode_dirty(dir);
+	}
+
+	if (IS_DIRSYNC(dir)) {
+		err = write_one_page(page, 1);
+		if (!err)
+			err = sync_inode_metadata(dir, 1);
+	} else {
+		unlock_page(page);
+	}
+
+	return err;
+}
+
+static void ext2_check_page(struct page *page, int quiet)
+{
+	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 = ext2_rec_len_from_disk(p->rec_len);
+
+		if (unlikely(rec_len < EXT2_DIR_REC_LEN(1)))
+			goto Eshort;
+		if (unlikely(rec_len & 3))
+			goto Ealign;
+		if (unlikely(rec_len < EXT2_DIR_REC_LEN(p->name_len)))
+			goto Enamelen;
+		if (unlikely(((offs + rec_len - 1) ^ offs) & ~(chunk_size-1)))
+			goto Espan;
+		if (unlikely(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:
+	if (!quiet)
+		ext2_error(sb, __func__,
+			"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:
+	if (!quiet)
+		ext2_error(sb, __func__, "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:
+	if (!quiet) {
+		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,
+				   int quiet)
+{
+	struct address_space *mapping = dir->i_mapping;
+	struct page *page = read_mapping_page(mapping, n, NULL);
+	if (!IS_ERR(page)) {
+		kmap(page);
+		if (!PageChecked(page))
+			ext2_check_page(page, quiet);
+		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 +
+			ext2_rec_len_from_disk(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)
+{
+	umode_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 *file, struct dir_context *ctx)
+{
+	loff_t pos = ctx->pos;
+	struct inode *inode = file_inode(file);
+	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 = file->f_version != inode->i_version;
+
+	if (pos > inode->i_size - EXT2_DIR_REC_LEN(1))
+		return 0;
+
+	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, 0);
+
+		if (IS_ERR(page)) {
+			ext2_error(sb, __func__,
+				   "bad page in #%lu",
+				   inode->i_ino);
+			ctx->pos += PAGE_CACHE_SIZE - offset;
+			return PTR_ERR(page);
+		}
+		kaddr = page_address(page);
+		if (unlikely(need_revalidate)) {
+			if (offset) {
+				offset = ext2_validate_entry(kaddr, offset, chunk_mask);
+				ctx->pos = (n<<PAGE_CACHE_SHIFT) + offset;
+			}
+			file->f_version = inode->i_version;
+			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, __func__,
+					"zero-length directory entry");
+				ext2_put_page(page);
+				return -EIO;
+			}
+			if (de->inode) {
+				unsigned char d_type = DT_UNKNOWN;
+
+				if (types && de->file_type < EXT2_FT_MAX)
+					d_type = types[de->file_type];
+
+				if (!dir_emit(ctx, de->name, de->name_len,
+						le32_to_cpu(de->inode),
+						d_type)) {
+					ext2_put_page(page);
+					return 0;
+				}
+			}
+			ctx->pos += ext2_rec_len_from_disk(de->rec_len);
+		}
+		ext2_put_page(page);
+	}
+	return 0;
+}
+
+/*
+ *	ext2_find_entry()
+ *
+ * finds an entry in the specified directory with the wanted name. It
+ * returns the page in which the entry was found (as a parameter - res_page),
+ * and the entry itself. Page is returned mapped and unlocked.
+ * Entry is guaranteed to be valid.
+ */
+struct ext2_dir_entry_2 *ext2_find_entry (struct inode * dir,
+			struct qstr *child, struct page ** res_page)
+{
+	const char *name = child->name;
+	int namelen = child->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;
+	int dir_has_error = 0;
+
+	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, dir_has_error);
+		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, __func__,
+						"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);
+		} else
+			dir_has_error = 1;
+
+		if (++n >= npages)
+			n = 0;
+		/* next page is past the blocks we've got */
+		if (unlikely(n > (dir->i_blocks >> (PAGE_CACHE_SHIFT - 9)))) {
+			ext2_error(dir->i_sb, __func__,
+				"dir %lu size %lld exceeds block count %llu",
+				dir->i_ino, dir->i_size,
+				(unsigned long long)dir->i_blocks);
+			goto out;
+		}
+	} 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, 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 qstr *child)
+{
+	ino_t res = 0;
+	struct ext2_dir_entry_2 *de;
+	struct page *page;
+	
+	de = ext2_find_entry (dir, child, &page);
+	if (de) {
+		res = le32_to_cpu(de->inode);
+		ext2_put_page(page);
+	}
+	return res;
+}
+
+static int ext2_prepare_chunk(struct page *page, loff_t pos, unsigned len)
+{
+	return __block_write_begin(page, pos, len, ext2_get_block);
+}
+
+/* Releases the page */
+void ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de,
+		   struct page *page, struct inode *inode, int update_times)
+{
+	loff_t pos = page_offset(page) +
+			(char *) de - (char *) page_address(page);
+	unsigned len = ext2_rec_len_from_disk(de->rec_len);
+	int err;
+
+	lock_page(page);
+	err = ext2_prepare_chunk(page, pos, len);
+	BUG_ON(err);
+	de->inode = cpu_to_le32(inode->i_ino);
+	ext2_set_de_type(de, inode);
+	err = ext2_commit_chunk(page, pos, len);
+	ext2_put_page(page);
+	if (update_times)
+		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;
+	loff_t pos;
+	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, 0);
+		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 = ext2_rec_len_to_disk(chunk_size);
+				de->inode = 0;
+				goto got_it;
+			}
+			if (de->rec_len == 0) {
+				ext2_error(dir->i_sb, __func__,
+					"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 = ext2_rec_len_from_disk(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:
+	pos = page_offset(page) +
+		(char*)de - (char*)page_address(page);
+	err = ext2_prepare_chunk(page, pos, rec_len);
+	if (err)
+		goto out_unlock;
+	if (de->inode) {
+		ext2_dirent *de1 = (ext2_dirent *) ((char *) de + name_len);
+		de1->rec_len = ext2_rec_len_to_disk(rec_len - name_len);
+		de->rec_len = ext2_rec_len_to_disk(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, pos, rec_len);
+	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 inode *inode = page->mapping->host;
+	char *kaddr = page_address(page);
+	unsigned from = ((char*)dir - kaddr) & ~(ext2_chunk_size(inode)-1);
+	unsigned to = ((char *)dir - kaddr) +
+				ext2_rec_len_from_disk(dir->rec_len);
+	loff_t pos;
+	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, __func__,
+				"zero-length directory entry");
+			err = -EIO;
+			goto out;
+		}
+		pde = de;
+		de = ext2_next_entry(de);
+	}
+	if (pde)
+		from = (char*)pde - (char*)page_address(page);
+	pos = page_offset(page) + from;
+	lock_page(page);
+	err = ext2_prepare_chunk(page, pos, to - from);
+	BUG_ON(err);
+	if (pde)
+		pde->rec_len = ext2_rec_len_to_disk(to - from);
+	dir->inode = 0;
+	err = ext2_commit_chunk(page, pos, to - from);
+	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 page *page = grab_cache_page(inode->i_mapping, 0);
+	unsigned chunk_size = ext2_chunk_size(inode);
+	struct ext2_dir_entry_2 * de;
+	int err;
+	void *kaddr;
+
+	if (!page)
+		return -ENOMEM;
+
+	err = ext2_prepare_chunk(page, 0, chunk_size);
+	if (err) {
+		unlock_page(page);
+		goto fail;
+	}
+	kaddr = kmap_atomic(page);
+	memset(kaddr, 0, chunk_size);
+	de = (struct ext2_dir_entry_2 *)kaddr;
+	de->name_len = 1;
+	de->rec_len = ext2_rec_len_to_disk(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 = ext2_rec_len_to_disk(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);
+	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);
+	int dir_has_error = 0;
+
+	for (i = 0; i < npages; i++) {
+		char *kaddr;
+		ext2_dirent * de;
+		page = ext2_get_page(inode, i, dir_has_error);
+
+		if (IS_ERR(page)) {
+			dir_has_error = 1;
+			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, __func__,
+					"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;
+}
+
+const struct file_operations ext2_dir_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= generic_read_dir,
+	.iterate	= ext2_readdir,
+	.unlocked_ioctl = ext2_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext2_compat_ioctl,
+#endif
+	.fsync		= ext2_fsync,
+};

fs/ext2/ext2.h

@@ -0,0 +1,814 @@
+/*
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  from
+ *
+ *  linux/include/linux/minix_fs.h
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+#include <linux/fs.h>
+#include <linux/ext2_fs.h>
+#include <linux/blockgroup_lock.h>
+#include <linux/percpu_counter.h>
+#include <linux/rbtree.h>
+
+/* XXX Here for now... not interested in restructing headers JUST now */
+
+/* data type for block offset of block group */
+typedef int ext2_grpblk_t;
+
+/* data type for filesystem-wide blocks number */
+typedef unsigned long ext2_fsblk_t;
+
+#define E2FSBLK "%lu"
+
+struct ext2_reserve_window {
+	ext2_fsblk_t		_rsv_start;	/* First byte reserved */
+	ext2_fsblk_t		_rsv_end;	/* Last byte reserved or 0 */
+};
+
+struct ext2_reserve_window_node {
+	struct rb_node	 	rsv_node;
+	__u32			rsv_goal_size;
+	__u32			rsv_alloc_hit;
+	struct ext2_reserve_window	rsv_window;
+};
+
+struct ext2_block_alloc_info {
+	/* information about reservation window */
+	struct ext2_reserve_window_node	rsv_window_node;
+	/*
+	 * was i_next_alloc_block in ext2_inode_info
+	 * is the logical (file-relative) number of the
+	 * most-recently-allocated block in this file.
+	 * We use this for detecting linearly ascending allocation requests.
+	 */
+	__u32			last_alloc_logical_block;
+	/*
+	 * Was i_next_alloc_goal in ext2_inode_info
+	 * is the *physical* companion to i_next_alloc_block.
+	 * it the the physical block number of the block which was most-recentl
+	 * allocated to this file.  This give us the goal (target) for the next
+	 * allocation when we detect linearly ascending requests.
+	 */
+	ext2_fsblk_t		last_alloc_physical_block;
+};
+
+#define rsv_start rsv_window._rsv_start
+#define rsv_end rsv_window._rsv_end
+
+/*
+ * second extended-fs super-block data in memory
+ */
+struct ext2_sb_info {
+	unsigned long s_frag_size;	/* Size of a fragment in bytes */
+	unsigned long s_frags_per_block;/* Number of fragments per block */
+	unsigned long s_inodes_per_block;/* Number of inodes per block */
+	unsigned long s_frags_per_group;/* Number of fragments in a group */
+	unsigned long s_blocks_per_group;/* Number of blocks in a group */
+	unsigned long s_inodes_per_group;/* Number of inodes in a group */
+	unsigned long s_itb_per_group;	/* Number of inode table blocks per group */
+	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
+	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
+	unsigned long s_groups_count;	/* Number of groups in the fs */
+	unsigned long s_overhead_last;  /* Last calculated overhead */
+	unsigned long s_blocks_last;    /* Last seen block count */
+	struct buffer_head * s_sbh;	/* Buffer containing the super block */
+	struct ext2_super_block * s_es;	/* Pointer to the super block in the buffer */
+	struct buffer_head ** s_group_desc;
+	unsigned long  s_mount_opt;
+	unsigned long s_sb_block;
+	kuid_t s_resuid;
+	kgid_t s_resgid;
+	unsigned short s_mount_state;
+	unsigned short s_pad;
+	int s_addr_per_block_bits;
+	int s_desc_per_block_bits;
+	int s_inode_size;
+	int s_first_ino;
+	spinlock_t s_next_gen_lock;
+	u32 s_next_generation;
+	unsigned long s_dir_count;
+	u8 *s_debts;
+	struct percpu_counter s_freeblocks_counter;
+	struct percpu_counter s_freeinodes_counter;
+	struct percpu_counter s_dirs_counter;
+	struct blockgroup_lock *s_blockgroup_lock;
+	/* root of the per fs reservation window tree */
+	spinlock_t s_rsv_window_lock;
+	struct rb_root s_rsv_window_root;
+	struct ext2_reserve_window_node s_rsv_window_head;
+	/*
+	 * s_lock protects against concurrent modifications of s_mount_state,
+	 * s_blocks_last, s_overhead_last and the content of superblock's
+	 * buffer pointed to by sbi->s_es.
+	 *
+	 * Note: It is used in ext2_show_options() to provide a consistent view
+	 * of the mount options.
+	 */
+	spinlock_t s_lock;
+};
+
+static inline spinlock_t *
+sb_bgl_lock(struct ext2_sb_info *sbi, unsigned int block_group)
+{
+	return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group);
+}
+
+/*
+ * Define EXT2FS_DEBUG to produce debug messages
+ */
+#undef EXT2FS_DEBUG
+
+/*
+ * Define EXT2_RESERVATION to reserve data blocks for expanding files
+ */
+#define EXT2_DEFAULT_RESERVE_BLOCKS     8
+/*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */
+#define EXT2_MAX_RESERVE_BLOCKS         1027
+#define EXT2_RESERVE_WINDOW_NOT_ALLOCATED 0
+/*
+ * The second extended file system version
+ */
+#define EXT2FS_DATE		"95/08/09"
+#define EXT2FS_VERSION		"0.5b"
+
+/*
+ * Debug code
+ */
+#ifdef EXT2FS_DEBUG
+#	define ext2_debug(f, a...)	{ \
+					printk ("EXT2-fs DEBUG (%s, %d): %s:", \
+						__FILE__, __LINE__, __func__); \
+				  	printk (f, ## a); \
+					}
+#else
+#	define ext2_debug(f, a...)	/**/
+#endif
+
+/*
+ * Special inode numbers
+ */
+#define	EXT2_BAD_INO		 1	/* Bad blocks inode */
+#define EXT2_ROOT_INO		 2	/* Root inode */
+#define EXT2_BOOT_LOADER_INO	 5	/* Boot loader inode */
+#define EXT2_UNDEL_DIR_INO	 6	/* Undelete directory inode */
+
+/* First non-reserved inode for old ext2 filesystems */
+#define EXT2_GOOD_OLD_FIRST_INO	11
+
+static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+/*
+ * Macro-instructions used to manage several block sizes
+ */
+#define EXT2_MIN_BLOCK_SIZE		1024
+#define	EXT2_MAX_BLOCK_SIZE		4096
+#define EXT2_MIN_BLOCK_LOG_SIZE		  10
+#define EXT2_BLOCK_SIZE(s)		((s)->s_blocksize)
+#define	EXT2_ADDR_PER_BLOCK(s)		(EXT2_BLOCK_SIZE(s) / sizeof (__u32))
+#define EXT2_BLOCK_SIZE_BITS(s)		((s)->s_blocksize_bits)
+#define	EXT2_ADDR_PER_BLOCK_BITS(s)	(EXT2_SB(s)->s_addr_per_block_bits)
+#define EXT2_INODE_SIZE(s)		(EXT2_SB(s)->s_inode_size)
+#define EXT2_FIRST_INO(s)		(EXT2_SB(s)->s_first_ino)
+
+/*
+ * Macro-instructions used to manage fragments
+ */
+#define EXT2_MIN_FRAG_SIZE		1024
+#define	EXT2_MAX_FRAG_SIZE		4096
+#define EXT2_MIN_FRAG_LOG_SIZE		  10
+#define EXT2_FRAG_SIZE(s)		(EXT2_SB(s)->s_frag_size)
+#define EXT2_FRAGS_PER_BLOCK(s)		(EXT2_SB(s)->s_frags_per_block)
+
+/*
+ * Structure of a blocks group descriptor
+ */
+struct ext2_group_desc
+{
+	__le32	bg_block_bitmap;		/* Blocks bitmap block */
+	__le32	bg_inode_bitmap;		/* Inodes bitmap block */
+	__le32	bg_inode_table;		/* Inodes table block */
+	__le16	bg_free_blocks_count;	/* Free blocks count */
+	__le16	bg_free_inodes_count;	/* Free inodes count */
+	__le16	bg_used_dirs_count;	/* Directories count */
+	__le16	bg_pad;
+	__le32	bg_reserved[3];
+};
+
+/*
+ * Macro-instructions used to manage group descriptors
+ */
+#define EXT2_BLOCKS_PER_GROUP(s)	(EXT2_SB(s)->s_blocks_per_group)
+#define EXT2_DESC_PER_BLOCK(s)		(EXT2_SB(s)->s_desc_per_block)
+#define EXT2_INODES_PER_GROUP(s)	(EXT2_SB(s)->s_inodes_per_group)
+#define EXT2_DESC_PER_BLOCK_BITS(s)	(EXT2_SB(s)->s_desc_per_block_bits)
+
+/*
+ * Constants relative to the data blocks
+ */
+#define	EXT2_NDIR_BLOCKS		12
+#define	EXT2_IND_BLOCK			EXT2_NDIR_BLOCKS
+#define	EXT2_DIND_BLOCK			(EXT2_IND_BLOCK + 1)
+#define	EXT2_TIND_BLOCK			(EXT2_DIND_BLOCK + 1)
+#define	EXT2_N_BLOCKS			(EXT2_TIND_BLOCK + 1)
+
+/*
+ * Inode flags (GETFLAGS/SETFLAGS)
+ */
+#define	EXT2_SECRM_FL			FS_SECRM_FL	/* Secure deletion */
+#define	EXT2_UNRM_FL			FS_UNRM_FL	/* Undelete */
+#define	EXT2_COMPR_FL			FS_COMPR_FL	/* Compress file */
+#define EXT2_SYNC_FL			FS_SYNC_FL	/* Synchronous updates */
+#define EXT2_IMMUTABLE_FL		FS_IMMUTABLE_FL	/* Immutable file */
+#define EXT2_APPEND_FL			FS_APPEND_FL	/* writes to file may only append */
+#define EXT2_NODUMP_FL			FS_NODUMP_FL	/* do not dump file */
+#define EXT2_NOATIME_FL			FS_NOATIME_FL	/* do not update atime */
+/* Reserved for compression usage... */
+#define EXT2_DIRTY_FL			FS_DIRTY_FL
+#define EXT2_COMPRBLK_FL		FS_COMPRBLK_FL	/* One or more compressed clusters */
+#define EXT2_NOCOMP_FL			FS_NOCOMP_FL	/* Don't compress */
+#define EXT2_ECOMPR_FL			FS_ECOMPR_FL	/* Compression error */
+/* End compression flags --- maybe not all used */	
+#define EXT2_BTREE_FL			FS_BTREE_FL	/* btree format dir */
+#define EXT2_INDEX_FL			FS_INDEX_FL	/* hash-indexed directory */
+#define EXT2_IMAGIC_FL			FS_IMAGIC_FL	/* AFS directory */
+#define EXT2_JOURNAL_DATA_FL		FS_JOURNAL_DATA_FL /* Reserved for ext3 */
+#define EXT2_NOTAIL_FL			FS_NOTAIL_FL	/* file tail should not be merged */
+#define EXT2_DIRSYNC_FL			FS_DIRSYNC_FL	/* dirsync behaviour (directories only) */
+#define EXT2_TOPDIR_FL			FS_TOPDIR_FL	/* Top of directory hierarchies*/
+#define EXT2_RESERVED_FL		FS_RESERVED_FL	/* reserved for ext2 lib */
+
+#define EXT2_FL_USER_VISIBLE		FS_FL_USER_VISIBLE	/* User visible flags */
+#define EXT2_FL_USER_MODIFIABLE		FS_FL_USER_MODIFIABLE	/* User modifiable flags */
+
+/* Flags that should be inherited by new inodes from their parent. */
+#define EXT2_FL_INHERITED (EXT2_SECRM_FL | EXT2_UNRM_FL | EXT2_COMPR_FL |\
+			   EXT2_SYNC_FL | EXT2_NODUMP_FL |\
+			   EXT2_NOATIME_FL | EXT2_COMPRBLK_FL |\
+			   EXT2_NOCOMP_FL | EXT2_JOURNAL_DATA_FL |\
+			   EXT2_NOTAIL_FL | EXT2_DIRSYNC_FL)
+
+/* Flags that are appropriate for regular files (all but dir-specific ones). */
+#define EXT2_REG_FLMASK (~(EXT2_DIRSYNC_FL | EXT2_TOPDIR_FL))
+
+/* Flags that are appropriate for non-directories/regular files. */
+#define EXT2_OTHER_FLMASK (EXT2_NODUMP_FL | EXT2_NOATIME_FL)
+
+/* Mask out flags that are inappropriate for the given type of inode. */
+static inline __u32 ext2_mask_flags(umode_t mode, __u32 flags)
+{
+	if (S_ISDIR(mode))
+		return flags;
+	else if (S_ISREG(mode))
+		return flags & EXT2_REG_FLMASK;
+	else
+		return flags & EXT2_OTHER_FLMASK;
+}
+
+/*
+ * ioctl commands
+ */
+#define	EXT2_IOC_GETFLAGS		FS_IOC_GETFLAGS
+#define	EXT2_IOC_SETFLAGS		FS_IOC_SETFLAGS
+#define	EXT2_IOC_GETVERSION		FS_IOC_GETVERSION
+#define	EXT2_IOC_SETVERSION		FS_IOC_SETVERSION
+#define	EXT2_IOC_GETRSVSZ		_IOR('f', 5, long)
+#define	EXT2_IOC_SETRSVSZ		_IOW('f', 6, long)
+
+/*
+ * ioctl commands in 32 bit emulation
+ */
+#define EXT2_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
+#define EXT2_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
+#define EXT2_IOC32_GETVERSION		FS_IOC32_GETVERSION
+#define EXT2_IOC32_SETVERSION		FS_IOC32_SETVERSION
+
+/*
+ * Structure of an inode on the disk
+ */
+struct ext2_inode {
+	__le16	i_mode;		/* File mode */
+	__le16	i_uid;		/* Low 16 bits of Owner Uid */
+	__le32	i_size;		/* Size in bytes */
+	__le32	i_atime;	/* Access time */
+	__le32	i_ctime;	/* Creation time */
+	__le32	i_mtime;	/* Modification time */
+	__le32	i_dtime;	/* Deletion Time */
+	__le16	i_gid;		/* Low 16 bits of Group Id */
+	__le16	i_links_count;	/* Links count */
+	__le32	i_blocks;	/* Blocks count */
+	__le32	i_flags;	/* File flags */
+	union {
+		struct {
+			__le32  l_i_reserved1;
+		} linux1;
+		struct {
+			__le32  h_i_translator;
+		} hurd1;
+		struct {
+			__le32  m_i_reserved1;
+		} masix1;
+	} osd1;				/* OS dependent 1 */
+	__le32	i_block[EXT2_N_BLOCKS];/* Pointers to blocks */
+	__le32	i_generation;	/* File version (for NFS) */
+	__le32	i_file_acl;	/* File ACL */
+	__le32	i_dir_acl;	/* Directory ACL */
+	__le32	i_faddr;	/* Fragment address */
+	union {
+		struct {
+			__u8	l_i_frag;	/* Fragment number */
+			__u8	l_i_fsize;	/* Fragment size */
+			__u16	i_pad1;
+			__le16	l_i_uid_high;	/* these 2 fields    */
+			__le16	l_i_gid_high;	/* were reserved2[0] */
+			__u32	l_i_reserved2;
+		} linux2;
+		struct {
+			__u8	h_i_frag;	/* Fragment number */
+			__u8	h_i_fsize;	/* Fragment size */
+			__le16	h_i_mode_high;
+			__le16	h_i_uid_high;
+			__le16	h_i_gid_high;
+			__le32	h_i_author;
+		} hurd2;
+		struct {
+			__u8	m_i_frag;	/* Fragment number */
+			__u8	m_i_fsize;	/* Fragment size */
+			__u16	m_pad1;
+			__u32	m_i_reserved2[2];
+		} masix2;
+	} osd2;				/* OS dependent 2 */
+};
+
+#define i_size_high	i_dir_acl
+
+#define i_reserved1	osd1.linux1.l_i_reserved1
+#define i_frag		osd2.linux2.l_i_frag
+#define i_fsize		osd2.linux2.l_i_fsize
+#define i_uid_low	i_uid
+#define i_gid_low	i_gid
+#define i_uid_high	osd2.linux2.l_i_uid_high
+#define i_gid_high	osd2.linux2.l_i_gid_high
+#define i_reserved2	osd2.linux2.l_i_reserved2
+
+/*
+ * File system states
+ */
+#define	EXT2_VALID_FS			0x0001	/* Unmounted cleanly */
+#define	EXT2_ERROR_FS			0x0002	/* Errors detected */
+
+/*
+ * Mount flags
+ */
+#define EXT2_MOUNT_CHECK		0x000001  /* Do mount-time checks */
+#define EXT2_MOUNT_OLDALLOC		0x000002  /* Don't use the new Orlov allocator */
+#define EXT2_MOUNT_GRPID		0x000004  /* Create files with directory's group */
+#define EXT2_MOUNT_DEBUG		0x000008  /* Some debugging messages */
+#define EXT2_MOUNT_ERRORS_CONT		0x000010  /* Continue on errors */
+#define EXT2_MOUNT_ERRORS_RO		0x000020  /* Remount fs ro on errors */
+#define EXT2_MOUNT_ERRORS_PANIC		0x000040  /* Panic on errors */
+#define EXT2_MOUNT_MINIX_DF		0x000080  /* Mimics the Minix statfs */
+#define EXT2_MOUNT_NOBH			0x000100  /* No buffer_heads */
+#define EXT2_MOUNT_NO_UID32		0x000200  /* Disable 32-bit UIDs */
+#define EXT2_MOUNT_XATTR_USER		0x004000  /* Extended user attributes */
+#define EXT2_MOUNT_POSIX_ACL		0x008000  /* POSIX Access Control Lists */
+#define EXT2_MOUNT_XIP			0x010000  /* Execute in place */
+#define EXT2_MOUNT_USRQUOTA		0x020000  /* user quota */
+#define EXT2_MOUNT_GRPQUOTA		0x040000  /* group quota */
+#define EXT2_MOUNT_RESERVATION		0x080000  /* Preallocation */
+
+
+#define clear_opt(o, opt)		o &= ~EXT2_MOUNT_##opt
+#define set_opt(o, opt)			o |= EXT2_MOUNT_##opt
+#define test_opt(sb, opt)		(EXT2_SB(sb)->s_mount_opt & \
+					 EXT2_MOUNT_##opt)
+/*
+ * Maximal mount counts between two filesystem checks
+ */
+#define EXT2_DFL_MAX_MNT_COUNT		20	/* Allow 20 mounts */
+#define EXT2_DFL_CHECKINTERVAL		0	/* Don't use interval check */
+
+/*
+ * Behaviour when detecting errors
+ */
+#define EXT2_ERRORS_CONTINUE		1	/* Continue execution */
+#define EXT2_ERRORS_RO			2	/* Remount fs read-only */
+#define EXT2_ERRORS_PANIC		3	/* Panic */
+#define EXT2_ERRORS_DEFAULT		EXT2_ERRORS_CONTINUE
+
+/*
+ * Structure of the super block
+ */
+struct ext2_super_block {
+	__le32	s_inodes_count;		/* Inodes count */
+	__le32	s_blocks_count;		/* Blocks count */
+	__le32	s_r_blocks_count;	/* Reserved blocks count */
+	__le32	s_free_blocks_count;	/* Free blocks count */
+	__le32	s_free_inodes_count;	/* Free inodes count */
+	__le32	s_first_data_block;	/* First Data Block */
+	__le32	s_log_block_size;	/* Block size */
+	__le32	s_log_frag_size;	/* Fragment size */
+	__le32	s_blocks_per_group;	/* # Blocks per group */
+	__le32	s_frags_per_group;	/* # Fragments per group */
+	__le32	s_inodes_per_group;	/* # Inodes per group */
+	__le32	s_mtime;		/* Mount time */
+	__le32	s_wtime;		/* Write time */
+	__le16	s_mnt_count;		/* Mount count */
+	__le16	s_max_mnt_count;	/* Maximal mount count */
+	__le16	s_magic;		/* Magic signature */
+	__le16	s_state;		/* File system state */
+	__le16	s_errors;		/* Behaviour when detecting errors */
+	__le16	s_minor_rev_level; 	/* minor revision level */
+	__le32	s_lastcheck;		/* time of last check */
+	__le32	s_checkinterval;	/* max. time between checks */
+	__le32	s_creator_os;		/* OS */
+	__le32	s_rev_level;		/* Revision level */
+	__le16	s_def_resuid;		/* Default uid for reserved blocks */
+	__le16	s_def_resgid;		/* Default gid for reserved blocks */
+	/*
+	 * These fields are for EXT2_DYNAMIC_REV superblocks only.
+	 *
+	 * Note: the difference between the compatible feature set and
+	 * the incompatible feature set is that if there is a bit set
+	 * in the incompatible feature set that the kernel doesn't
+	 * know about, it should refuse to mount the filesystem.
+	 * 
+	 * e2fsck's requirements are more strict; if it doesn't know
+	 * about a feature in either the compatible or incompatible
+	 * feature set, it must abort and not try to meddle with
+	 * things it doesn't understand...
+	 */
+	__le32	s_first_ino; 		/* First non-reserved inode */
+	__le16   s_inode_size; 		/* size of inode structure */
+	__le16	s_block_group_nr; 	/* block group # of this superblock */
+	__le32	s_feature_compat; 	/* compatible feature set */
+	__le32	s_feature_incompat; 	/* incompatible feature set */
+	__le32	s_feature_ro_compat; 	/* readonly-compatible feature set */
+	__u8	s_uuid[16];		/* 128-bit uuid for volume */
+	char	s_volume_name[16]; 	/* volume name */
+	char	s_last_mounted[64]; 	/* directory where last mounted */
+	__le32	s_algorithm_usage_bitmap; /* For compression */
+	/*
+	 * Performance hints.  Directory preallocation should only
+	 * happen if the EXT2_COMPAT_PREALLOC flag is on.
+	 */
+	__u8	s_prealloc_blocks;	/* Nr of blocks to try to preallocate*/
+	__u8	s_prealloc_dir_blocks;	/* Nr to preallocate for dirs */
+	__u16	s_padding1;
+	/*
+	 * Journaling support valid if EXT3_FEATURE_COMPAT_HAS_JOURNAL set.
+	 */
+	__u8	s_journal_uuid[16];	/* uuid of journal superblock */
+	__u32	s_journal_inum;		/* inode number of journal file */
+	__u32	s_journal_dev;		/* device number of journal file */
+	__u32	s_last_orphan;		/* start of list of inodes to delete */
+	__u32	s_hash_seed[4];		/* HTREE hash seed */
+	__u8	s_def_hash_version;	/* Default hash version to use */
+	__u8	s_reserved_char_pad;
+	__u16	s_reserved_word_pad;
+	__le32	s_default_mount_opts;
+ 	__le32	s_first_meta_bg; 	/* First metablock block group */
+	__u32	s_reserved[190];	/* Padding to the end of the block */
+};
+
+/*
+ * Codes for operating systems
+ */
+#define EXT2_OS_LINUX		0
+#define EXT2_OS_HURD		1
+#define EXT2_OS_MASIX		2
+#define EXT2_OS_FREEBSD		3
+#define EXT2_OS_LITES		4
+
+/*
+ * Revision levels
+ */
+#define EXT2_GOOD_OLD_REV	0	/* The good old (original) format */
+#define EXT2_DYNAMIC_REV	1 	/* V2 format w/ dynamic inode sizes */
+
+#define EXT2_CURRENT_REV	EXT2_GOOD_OLD_REV
+#define EXT2_MAX_SUPP_REV	EXT2_DYNAMIC_REV
+
+#define EXT2_GOOD_OLD_INODE_SIZE 128
+
+/*
+ * Feature set definitions
+ */
+
+#define EXT2_HAS_COMPAT_FEATURE(sb,mask)			\
+	( EXT2_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) )
+#define EXT2_HAS_RO_COMPAT_FEATURE(sb,mask)			\
+	( EXT2_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) )
+#define EXT2_HAS_INCOMPAT_FEATURE(sb,mask)			\
+	( EXT2_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) )
+#define EXT2_SET_COMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
+#define EXT2_SET_RO_COMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask)
+#define EXT2_SET_INCOMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask)
+#define EXT2_CLEAR_COMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask)
+#define EXT2_CLEAR_RO_COMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask)
+#define EXT2_CLEAR_INCOMPAT_FEATURE(sb,mask)			\
+	EXT2_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask)
+
+#define EXT2_FEATURE_COMPAT_DIR_PREALLOC	0x0001
+#define EXT2_FEATURE_COMPAT_IMAGIC_INODES	0x0002
+#define EXT3_FEATURE_COMPAT_HAS_JOURNAL		0x0004
+#define EXT2_FEATURE_COMPAT_EXT_ATTR		0x0008
+#define EXT2_FEATURE_COMPAT_RESIZE_INO		0x0010
+#define EXT2_FEATURE_COMPAT_DIR_INDEX		0x0020
+#define EXT2_FEATURE_COMPAT_ANY			0xffffffff
+
+#define EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
+#define EXT2_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
+#define EXT2_FEATURE_RO_COMPAT_BTREE_DIR	0x0004
+#define EXT2_FEATURE_RO_COMPAT_ANY		0xffffffff
+
+#define EXT2_FEATURE_INCOMPAT_COMPRESSION	0x0001
+#define EXT2_FEATURE_INCOMPAT_FILETYPE		0x0002
+#define EXT3_FEATURE_INCOMPAT_RECOVER		0x0004
+#define EXT3_FEATURE_INCOMPAT_JOURNAL_DEV	0x0008
+#define EXT2_FEATURE_INCOMPAT_META_BG		0x0010
+#define EXT2_FEATURE_INCOMPAT_ANY		0xffffffff
+
+#define EXT2_FEATURE_COMPAT_SUPP	EXT2_FEATURE_COMPAT_EXT_ATTR
+#define EXT2_FEATURE_INCOMPAT_SUPP	(EXT2_FEATURE_INCOMPAT_FILETYPE| \
+					 EXT2_FEATURE_INCOMPAT_META_BG)
+#define EXT2_FEATURE_RO_COMPAT_SUPP	(EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER| \
+					 EXT2_FEATURE_RO_COMPAT_LARGE_FILE| \
+					 EXT2_FEATURE_RO_COMPAT_BTREE_DIR)
+#define EXT2_FEATURE_RO_COMPAT_UNSUPPORTED	~EXT2_FEATURE_RO_COMPAT_SUPP
+#define EXT2_FEATURE_INCOMPAT_UNSUPPORTED	~EXT2_FEATURE_INCOMPAT_SUPP
+
+/*
+ * Default values for user and/or group using reserved blocks
+ */
+#define	EXT2_DEF_RESUID		0
+#define	EXT2_DEF_RESGID		0
+
+/*
+ * Default mount options
+ */
+#define EXT2_DEFM_DEBUG		0x0001
+#define EXT2_DEFM_BSDGROUPS	0x0002
+#define EXT2_DEFM_XATTR_USER	0x0004
+#define EXT2_DEFM_ACL		0x0008
+#define EXT2_DEFM_UID16		0x0010
+    /* Not used by ext2, but reserved for use by ext3 */
+#define EXT3_DEFM_JMODE		0x0060 
+#define EXT3_DEFM_JMODE_DATA	0x0020
+#define EXT3_DEFM_JMODE_ORDERED	0x0040
+#define EXT3_DEFM_JMODE_WBACK	0x0060
+
+/*
+ * Structure of a directory entry
+ */
+
+struct ext2_dir_entry {
+	__le32	inode;			/* Inode number */
+	__le16	rec_len;		/* Directory entry length */
+	__le16	name_len;		/* Name length */
+	char	name[];			/* File name, up to EXT2_NAME_LEN */
+};
+
+/*
+ * The new version of the directory entry.  Since EXT2 structures are
+ * stored in intel byte order, and the name_len field could never be
+ * bigger than 255 chars, it's safe to reclaim the extra byte for the
+ * file_type field.
+ */
+struct ext2_dir_entry_2 {
+	__le32	inode;			/* Inode number */
+	__le16	rec_len;		/* Directory entry length */
+	__u8	name_len;		/* Name length */
+	__u8	file_type;
+	char	name[];			/* File name, up to EXT2_NAME_LEN */
+};
+
+/*
+ * Ext2 directory file types.  Only the low 3 bits are used.  The
+ * other bits are reserved for now.
+ */
+enum {
+	EXT2_FT_UNKNOWN		= 0,
+	EXT2_FT_REG_FILE	= 1,
+	EXT2_FT_DIR		= 2,
+	EXT2_FT_CHRDEV		= 3,
+	EXT2_FT_BLKDEV		= 4,
+	EXT2_FT_FIFO		= 5,
+	EXT2_FT_SOCK		= 6,
+	EXT2_FT_SYMLINK		= 7,
+	EXT2_FT_MAX
+};
+
+/*
+ * EXT2_DIR_PAD defines the directory entries boundaries
+ *
+ * NOTE: It must be a multiple of 4
+ */
+#define EXT2_DIR_PAD		 	4
+#define EXT2_DIR_ROUND 			(EXT2_DIR_PAD - 1)
+#define EXT2_DIR_REC_LEN(name_len)	(((name_len) + 8 + EXT2_DIR_ROUND) & \
+					 ~EXT2_DIR_ROUND)
+#define EXT2_MAX_REC_LEN		((1<<16)-1)
+
+static inline void verify_offsets(void)
+{
+#define A(x,y) BUILD_BUG_ON(x != offsetof(struct ext2_super_block, y));
+	A(EXT2_SB_MAGIC_OFFSET, s_magic);
+	A(EXT2_SB_BLOCKS_OFFSET, s_blocks_count);
+	A(EXT2_SB_BSIZE_OFFSET, s_log_block_size);
+#undef A
+}
+
+/*
+ * ext2 mount options
+ */
+struct ext2_mount_options {
+	unsigned long s_mount_opt;
+	kuid_t s_resuid;
+	kgid_t s_resgid;
+};
+
+/*
+ * 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 used 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;
+
+	/* block reservation info */
+	struct ext2_block_alloc_info *i_block_alloc_info;
+
+	__u32	i_dir_start_lookup;
+#ifdef CONFIG_EXT2_FS_XATTR
+	/*
+	 * Extended attributes can be read independently of the main file
+	 * data. Taking i_mutex even when reading would cause contention
+	 * between readers of EAs and writers of regular file data, so
+	 * instead we synchronize on xattr_sem when reading or changing
+	 * EAs.
+	 */
+	struct rw_semaphore xattr_sem;
+#endif
+	rwlock_t i_meta_lock;
+
+	/*
+	 * truncate_mutex is for serialising ext2_truncate() against
+	 * ext2_getblock().  It also protects the internals of the inode's
+	 * reservation data structures: ext2_reserve_window and
+	 * ext2_reserve_window_node.
+	 */
+	struct mutex truncate_mutex;
+	struct inode	vfs_inode;
+	struct list_head i_orphan;	/* unlinked but open inodes */
+};
+
+/*
+ * 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 ext2_fsblk_t ext2_new_block(struct inode *, unsigned long, int *);
+extern ext2_fsblk_t ext2_new_blocks(struct inode *, unsigned long,
+				unsigned long *, 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);
+extern void ext2_discard_reservation (struct inode *);
+extern int ext2_should_retry_alloc(struct super_block *sb, int *retries);
+extern void ext2_init_block_alloc_info(struct inode *);
+extern void ext2_rsv_window_add(struct super_block *sb, struct ext2_reserve_window_node *rsv);
+
+/* dir.c */
+extern int ext2_add_link (struct dentry *, struct inode *);
+extern ino_t ext2_inode_by_name(struct inode *, struct qstr *);
+extern int ext2_make_empty(struct inode *, struct inode *);
+extern struct ext2_dir_entry_2 * ext2_find_entry (struct inode *,struct qstr *, 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 *, int);
+
+/* ialloc.c */
+extern struct inode * ext2_new_inode (struct inode *, umode_t, const struct qstr *);
+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 struct inode *ext2_iget (struct super_block *, unsigned long);
+extern int ext2_write_inode (struct inode *, struct writeback_control *);
+extern void ext2_evict_inode(struct inode *);
+extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int);
+extern int ext2_setattr (struct dentry *, struct iattr *);
+extern void ext2_set_inode_flags(struct inode *inode);
+extern void ext2_get_inode_flags(struct ext2_inode_info *);
+extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		       u64 start, u64 len);
+
+/* ioctl.c */
+extern long ext2_ioctl(struct file *, unsigned int, unsigned long);
+extern long ext2_compat_ioctl(struct file *, unsigned int, unsigned long);
+
+/* namei.c */
+struct dentry *ext2_get_parent(struct dentry *child);
+
+/* super.c */
+extern __printf(3, 4)
+void ext2_error(struct super_block *, const char *, const char *, ...);
+extern __printf(3, 4)
+void ext2_msg(struct super_block *, const char *, const char *, ...);
+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 const struct file_operations ext2_dir_operations;
+
+/* file.c */
+extern int ext2_fsync(struct file *file, loff_t start, loff_t end,
+		      int datasync);
+extern const struct inode_operations ext2_file_inode_operations;
+extern const struct file_operations ext2_file_operations;
+extern const struct file_operations ext2_xip_file_operations;
+
+/* inode.c */
+extern const struct address_space_operations ext2_aops;
+extern const struct address_space_operations ext2_aops_xip;
+extern const struct address_space_operations ext2_nobh_aops;
+
+/* namei.c */
+extern const struct inode_operations ext2_dir_inode_operations;
+extern const struct inode_operations ext2_special_inode_operations;
+
+/* symlink.c */
+extern const struct inode_operations ext2_fast_symlink_inode_operations;
+extern const struct inode_operations ext2_symlink_inode_operations;
+
+static inline ext2_fsblk_t
+ext2_group_first_block_no(struct super_block *sb, unsigned long group_no)
+{
+	return group_no * (ext2_fsblk_t)EXT2_BLOCKS_PER_GROUP(sb) +
+		le32_to_cpu(EXT2_SB(sb)->s_es->s_first_data_block);
+}
+
+#define ext2_set_bit	__test_and_set_bit_le
+#define ext2_clear_bit	__test_and_clear_bit_le
+#define ext2_test_bit	test_bit_le
+#define ext2_find_first_zero_bit	find_first_zero_bit_le
+#define ext2_find_next_zero_bit		find_next_zero_bit_le

fs/ext2/file.c

@@ -0,0 +1,108 @@
+/*
+ *  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 <linux/pagemap.h>
+#include <linux/quotaops.h>
+#include "ext2.h"
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * Called when filp is released. This happens when all file descriptors
+ * for a single struct file are closed. Note that different open() calls
+ * for the same file yield different struct file structures.
+ */
+static int ext2_release_file (struct inode * inode, struct file * filp)
+{
+	if (filp->f_mode & FMODE_WRITE) {
+		mutex_lock(&EXT2_I(inode)->truncate_mutex);
+		ext2_discard_reservation(inode);
+		mutex_unlock(&EXT2_I(inode)->truncate_mutex);
+	}
+	return 0;
+}
+
+int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	int ret;
+	struct super_block *sb = file->f_mapping->host->i_sb;
+	struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
+
+	ret = generic_file_fsync(file, start, end, datasync);
+	if (ret == -EIO || test_and_clear_bit(AS_EIO, &mapping->flags)) {
+		/* We don't really know where the IO error happened... */
+		ext2_error(sb, __func__,
+			   "detected IO error when writing metadata buffers");
+		ret = -EIO;
+	}
+	return ret;
+}
+
+/*
+ * We have mostly NULL's here: the current defaults are ok for
+ * the ext2 filesystem.
+ */
+const struct file_operations ext2_file_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
+	.unlocked_ioctl = ext2_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext2_compat_ioctl,
+#endif
+	.mmap		= generic_file_mmap,
+	.open		= dquot_file_open,
+	.release	= ext2_release_file,
+	.fsync		= ext2_fsync,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= iter_file_splice_write,
+};
+
+#ifdef CONFIG_EXT2_FS_XIP
+const struct file_operations ext2_xip_file_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= xip_file_read,
+	.write		= xip_file_write,
+	.unlocked_ioctl = ext2_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext2_compat_ioctl,
+#endif
+	.mmap		= xip_file_mmap,
+	.open		= dquot_file_open,
+	.release	= ext2_release_file,
+	.fsync		= ext2_fsync,
+};
+#endif
+
+const struct inode_operations ext2_file_inode_operations = {
+#ifdef CONFIG_EXT2_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext2_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+	.setattr	= ext2_setattr,
+	.get_acl	= ext2_get_acl,
+	.set_acl	= ext2_set_acl,
+	.fiemap		= ext2_fiemap,
+};

fs/ext2/ialloc.c

@@ -0,0 +1,675 @@
+/*
+ *  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/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));
+	le16_add_cpu(&desc->bg_free_inodes_count, 1);
+	if (dir)
+		le16_add_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);
+	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;
+	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.
+	 */
+	/* Quota is already initialized in iput() */
+	dquot_free_inode(inode);
+	dquot_drop(inode);
+
+	es = EXT2_SB(sb)->s_es;
+	is_directory = S_ISDIR(inode->i_mode);
+
+	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);
+		return;
+	}
+	block_group = (ino - 1) / EXT2_INODES_PER_GROUP(sb);
+	bit = (ino - 1) % EXT2_INODES_PER_GROUP(sb);
+	bitmap_bh = read_inode_bitmap(sb, block_group);
+	if (!bitmap_bh)
+		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);
+
+	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 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, NULL);
+	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;
+	int group, best_group = -1;
+
+	for (group = 0; group < ngroups; group++) {
+		desc = ext2_get_group_desc (sb, group, NULL);
+		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;
+		}
+	}
+	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 preferred, 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;
+
+	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;
+		int best_ndir = inodes_per_group;
+		int best_group = -1;
+
+		group = prandom_u32();
+		parent_group = (unsigned)group % ngroups;
+		for (i = 0; i < ngroups; i++) {
+			group = (parent_group + i) % ngroups;
+			desc = ext2_get_group_desc (sb, group, NULL);
+			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;
+		}
+		if (best_group >= 0) {
+			desc = best_desc;
+			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, NULL);
+		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, NULL);
+		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;
+	int group, i;
+
+	/*
+	 * Try to place the inode in its parent directory
+	 */
+	group = parent_group;
+	desc = ext2_get_group_desc (sb, group, NULL);
+	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, NULL);
+		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, NULL);
+		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, umode_t mode,
+			     const struct qstr *qstr)
+{
+	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_add(&sbi->s_freeinodes_counter, -1);
+	if (S_ISDIR(mode))
+		percpu_counter_inc(&sbi->s_dirs_counter);
+
+	spin_lock(sb_bgl_lock(sbi, group));
+	le16_add_cpu(&gdp->bg_free_inodes_count, -1);
+	if (S_ISDIR(mode)) {
+		if (sbi->s_debts[group] < 255)
+			sbi->s_debts[group]++;
+		le16_add_cpu(&gdp->bg_used_dirs_count, 1);
+	} else {
+		if (sbi->s_debts[group])
+			sbi->s_debts[group]--;
+	}
+	spin_unlock(sb_bgl_lock(sbi, group));
+
+	mark_buffer_dirty(bh2);
+	if (test_opt(sb, GRPID)) {
+		inode->i_mode = mode;
+		inode->i_uid = current_fsuid();
+		inode->i_gid = dir->i_gid;
+	} else
+		inode_init_owner(inode, dir, mode);
+
+	inode->i_ino = ino;
+	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_mask_flags(mode, EXT2_I(dir)->i_flags & EXT2_FL_INHERITED);
+	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_alloc_info = NULL;
+	ei->i_block_group = group;
+	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);
+	if (insert_inode_locked(inode) < 0) {
+		ext2_error(sb, "ext2_new_inode",
+			   "inode number already in use - inode=%lu",
+			   (unsigned long) ino);
+		err = -EIO;
+		goto fail;
+	}
+
+	dquot_initialize(inode);
+	err = dquot_alloc_inode(inode);
+	if (err)
+		goto fail_drop;
+
+	err = ext2_init_acl(inode, dir);
+	if (err)
+		goto fail_free_drop;
+
+	err = ext2_init_security(inode, dir, qstr);
+	if (err)
+		goto fail_free_drop;
+
+	mark_inode_dirty(inode);
+	ext2_debug("allocating inode %lu\n", inode->i_ino);
+	ext2_preread_inode(inode);
+	return inode;
+
+fail_free_drop:
+	dquot_free_inode(inode);
+
+fail_drop:
+	dquot_drop(inode);
+	inode->i_flags |= S_NOQUOTA;
+	clear_nlink(inode);
+	unlock_new_inode(inode);
+	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;
+
+	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",
+		(unsigned long)
+		percpu_counter_read(&EXT2_SB(sb)->s_freeinodes_counter),
+		desc_count, bitmap_count);
+	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;
+}
+

fs/ext2/ioctl.c

@@ -0,0 +1,188 @@
+/*
+ * 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/capability.h>
+#include <linux/time.h>
+#include <linux/sched.h>
+#include <linux/compat.h>
+#include <linux/mount.h>
+#include <asm/current.h>
+#include <asm/uaccess.h>
+
+
+long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+	struct ext2_inode_info *ei = EXT2_I(inode);
+	unsigned int flags;
+	unsigned short rsv_window_size;
+	int ret;
+
+	ext2_debug ("cmd = %u, arg = %lu\n", cmd, arg);
+
+	switch (cmd) {
+	case EXT2_IOC_GETFLAGS:
+		ext2_get_inode_flags(ei);
+		flags = ei->i_flags & EXT2_FL_USER_VISIBLE;
+		return put_user(flags, (int __user *) arg);
+	case EXT2_IOC_SETFLAGS: {
+		unsigned int oldflags;
+
+		ret = mnt_want_write_file(filp);
+		if (ret)
+			return ret;
+
+		if (!inode_owner_or_capable(inode)) {
+			ret = -EACCES;
+			goto setflags_out;
+		}
+
+		if (get_user(flags, (int __user *) arg)) {
+			ret = -EFAULT;
+			goto setflags_out;
+		}
+
+		flags = ext2_mask_flags(inode->i_mode, flags);
+
+		mutex_lock(&inode->i_mutex);
+		/* Is it quota file? Do not allow user to mess with it */
+		if (IS_NOQUOTA(inode)) {
+			mutex_unlock(&inode->i_mutex);
+			ret = -EPERM;
+			goto setflags_out;
+		}
+		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)) {
+				mutex_unlock(&inode->i_mutex);
+				ret = -EPERM;
+				goto setflags_out;
+			}
+		}
+
+		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;
+		mutex_unlock(&inode->i_mutex);
+
+		mark_inode_dirty(inode);
+setflags_out:
+		mnt_drop_write_file(filp);
+		return ret;
+	}
+	case EXT2_IOC_GETVERSION:
+		return put_user(inode->i_generation, (int __user *) arg);
+	case EXT2_IOC_SETVERSION: {
+		__u32 generation;
+
+		if (!inode_owner_or_capable(inode))
+			return -EPERM;
+		ret = mnt_want_write_file(filp);
+		if (ret)
+			return ret;
+		if (get_user(generation, (int __user *) arg)) {
+			ret = -EFAULT;
+			goto setversion_out;
+		}
+
+		mutex_lock(&inode->i_mutex);
+		inode->i_ctime = CURRENT_TIME_SEC;
+		inode->i_generation = generation;
+		mutex_unlock(&inode->i_mutex);
+
+		mark_inode_dirty(inode);
+setversion_out:
+		mnt_drop_write_file(filp);
+		return ret;
+	}
+	case EXT2_IOC_GETRSVSZ:
+		if (test_opt(inode->i_sb, RESERVATION)
+			&& S_ISREG(inode->i_mode)
+			&& ei->i_block_alloc_info) {
+			rsv_window_size = ei->i_block_alloc_info->rsv_window_node.rsv_goal_size;
+			return put_user(rsv_window_size, (int __user *)arg);
+		}
+		return -ENOTTY;
+	case EXT2_IOC_SETRSVSZ: {
+
+		if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode))
+			return -ENOTTY;
+
+		if (!inode_owner_or_capable(inode))
+			return -EACCES;
+
+		if (get_user(rsv_window_size, (int __user *)arg))
+			return -EFAULT;
+
+		ret = mnt_want_write_file(filp);
+		if (ret)
+			return ret;
+
+		if (rsv_window_size > EXT2_MAX_RESERVE_BLOCKS)
+			rsv_window_size = EXT2_MAX_RESERVE_BLOCKS;
+
+		/*
+		 * need to allocate reservation structure for this inode
+		 * before set the window size
+		 */
+		/*
+		 * XXX What lock should protect the rsv_goal_size?
+		 * Accessed in ext2_get_block only.  ext3 uses i_truncate.
+		 */
+		mutex_lock(&ei->truncate_mutex);
+		if (!ei->i_block_alloc_info)
+			ext2_init_block_alloc_info(inode);
+
+		if (ei->i_block_alloc_info){
+			struct ext2_reserve_window_node *rsv = &ei->i_block_alloc_info->rsv_window_node;
+			rsv->rsv_goal_size = rsv_window_size;
+		}
+		mutex_unlock(&ei->truncate_mutex);
+		mnt_drop_write_file(filp);
+		return 0;
+	}
+	default:
+		return -ENOTTY;
+	}
+}
+
+#ifdef CONFIG_COMPAT
+long ext2_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	/* These are just misnamed, they actually get/put from/to user an int */
+	switch (cmd) {
+	case EXT2_IOC32_GETFLAGS:
+		cmd = EXT2_IOC_GETFLAGS;
+		break;
+	case EXT2_IOC32_SETFLAGS:
+		cmd = EXT2_IOC_SETFLAGS;
+		break;
+	case EXT2_IOC32_GETVERSION:
+		cmd = EXT2_IOC_GETVERSION;
+		break;
+	case EXT2_IOC32_SETVERSION:
+		cmd = EXT2_IOC_SETVERSION;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+	return ext2_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
+}
+#endif

fs/ext2/namei.c

@@ -0,0 +1,438 @@
+/*
+ * 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 <linux/quotaops.h>
+#include "ext2.h"
+#include "xattr.h"
+#include "acl.h"
+#include "xip.h"
+
+static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
+{
+	int err = ext2_add_link(dentry, inode);
+	if (!err) {
+		unlock_new_inode(inode);
+		d_instantiate(dentry, inode);
+		return 0;
+	}
+	inode_dec_link_count(inode);
+	unlock_new_inode(inode);
+	iput(inode);
+	return err;
+}
+
+/*
+ * Methods themselves.
+ */
+
+static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags)
+{
+	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->d_name);
+	inode = NULL;
+	if (ino) {
+		inode = ext2_iget(dir->i_sb, ino);
+		if (inode == ERR_PTR(-ESTALE)) {
+			ext2_error(dir->i_sb, __func__,
+					"deleted inode referenced: %lu",
+					(unsigned long) ino);
+			return ERR_PTR(-EIO);
+		}
+	}
+	return d_splice_alias(inode, dentry);
+}
+
+struct dentry *ext2_get_parent(struct dentry *child)
+{
+	struct qstr dotdot = QSTR_INIT("..", 2);
+	unsigned long ino = ext2_inode_by_name(child->d_inode, &dotdot);
+	if (!ino)
+		return ERR_PTR(-ENOENT);
+	return d_obtain_alias(ext2_iget(child->d_inode->i_sb, ino));
+} 
+
+/*
+ * 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, umode_t mode, bool excl)
+{
+	struct inode *inode;
+
+	dquot_initialize(dir);
+
+	inode = ext2_new_inode(dir, mode, &dentry->d_name);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+
+	inode->i_op = &ext2_file_inode_operations;
+	if (ext2_use_xip(inode->i_sb)) {
+		inode->i_mapping->a_ops = &ext2_aops_xip;
+		inode->i_fop = &ext2_xip_file_operations;
+	} else if (test_opt(inode->i_sb, NOBH)) {
+		inode->i_mapping->a_ops = &ext2_nobh_aops;
+		inode->i_fop = &ext2_file_operations;
+	} else {
+		inode->i_mapping->a_ops = &ext2_aops;
+		inode->i_fop = &ext2_file_operations;
+	}
+	mark_inode_dirty(inode);
+	return ext2_add_nondir(dentry, inode);
+}
+
+static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	struct inode *inode = ext2_new_inode(dir, mode, NULL);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+
+	inode->i_op = &ext2_file_inode_operations;
+	if (ext2_use_xip(inode->i_sb)) {
+		inode->i_mapping->a_ops = &ext2_aops_xip;
+		inode->i_fop = &ext2_xip_file_operations;
+	} else if (test_opt(inode->i_sb, NOBH)) {
+		inode->i_mapping->a_ops = &ext2_nobh_aops;
+		inode->i_fop = &ext2_file_operations;
+	} else {
+		inode->i_mapping->a_ops = &ext2_aops;
+		inode->i_fop = &ext2_file_operations;
+	}
+	mark_inode_dirty(inode);
+	d_tmpfile(dentry, inode);
+	unlock_new_inode(inode);
+	return 0;
+}
+
+static int ext2_mknod (struct inode * dir, struct dentry *dentry, umode_t mode, dev_t rdev)
+{
+	struct inode * inode;
+	int err;
+
+	if (!new_valid_dev(rdev))
+		return -EINVAL;
+
+	dquot_initialize(dir);
+
+	inode = ext2_new_inode (dir, mode, &dentry->d_name);
+	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;
+
+	dquot_initialize(dir);
+
+	inode = ext2_new_inode (dir, S_IFLNK | S_IRWXUGO, &dentry->d_name);
+	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:
+	inode_dec_link_count(inode);
+	unlock_new_inode(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;
+	int err;
+
+	dquot_initialize(dir);
+
+	inode->i_ctime = CURRENT_TIME_SEC;
+	inode_inc_link_count(inode);
+	ihold(inode);
+
+	err = ext2_add_link(dentry, inode);
+	if (!err) {
+		d_instantiate(dentry, inode);
+		return 0;
+	}
+	inode_dec_link_count(inode);
+	iput(inode);
+	return err;
+}
+
+static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
+{
+	struct inode * inode;
+	int err;
+
+	dquot_initialize(dir);
+
+	inode_inc_link_count(dir);
+
+	inode = ext2_new_inode(dir, S_IFDIR | mode, &dentry->d_name);
+	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;
+
+	inode_inc_link_count(inode);
+
+	err = ext2_make_empty(inode, dir);
+	if (err)
+		goto out_fail;
+
+	err = ext2_add_link(dentry, inode);
+	if (err)
+		goto out_fail;
+
+	unlock_new_inode(inode);
+	d_instantiate(dentry, inode);
+out:
+	return err;
+
+out_fail:
+	inode_dec_link_count(inode);
+	inode_dec_link_count(inode);
+	unlock_new_inode(inode);
+	iput(inode);
+out_dir:
+	inode_dec_link_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;
+
+	dquot_initialize(dir);
+
+	de = ext2_find_entry (dir, &dentry->d_name, &page);
+	if (!de)
+		goto out;
+
+	err = ext2_delete_entry (de, page);
+	if (err)
+		goto out;
+
+	inode->i_ctime = dir->i_ctime;
+	inode_dec_link_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;
+			inode_dec_link_count(inode);
+			inode_dec_link_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;
+
+	dquot_initialize(old_dir);
+	dquot_initialize(new_dir);
+
+	old_de = ext2_find_entry (old_dir, &old_dentry->d_name, &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->d_name, &new_page);
+		if (!new_de)
+			goto out_dir;
+		ext2_set_link(new_dir, new_de, new_page, old_inode, 1);
+		new_inode->i_ctime = CURRENT_TIME_SEC;
+		if (dir_de)
+			drop_nlink(new_inode);
+		inode_dec_link_count(new_inode);
+	} else {
+		err = ext2_add_link(new_dentry, old_inode);
+		if (err)
+			goto out_dir;
+		if (dir_de)
+			inode_inc_link_count(new_dir);
+	}
+
+	/*
+	 * Like most other Unix systems, set the ctime for inodes on a
+ 	 * rename.
+	 */
+	old_inode->i_ctime = CURRENT_TIME_SEC;
+	mark_inode_dirty(old_inode);
+
+	ext2_delete_entry (old_de, old_page);
+
+	if (dir_de) {
+		if (old_dir != new_dir)
+			ext2_set_link(old_inode, dir_de, dir_page, new_dir, 0);
+		else {
+			kunmap(dir_page);
+			page_cache_release(dir_page);
+		}
+		inode_dec_link_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;
+}
+
+const 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,
+	.get_acl	= ext2_get_acl,
+	.set_acl	= ext2_set_acl,
+	.tmpfile	= ext2_tmpfile,
+};
+
+const 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,
+	.get_acl	= ext2_get_acl,
+	.set_acl	= ext2_set_acl,
+};

fs/ext2/symlink.c

@@ -0,0 +1,54 @@
+/*
+ *  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 void *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 NULL;
+}
+
+const struct inode_operations ext2_symlink_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= page_follow_link_light,
+	.put_link	= page_put_link,
+	.setattr	= ext2_setattr,
+#ifdef CONFIG_EXT2_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext2_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+};
+ 
+const struct inode_operations ext2_fast_symlink_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= ext2_follow_link,
+	.setattr	= ext2_setattr,
+#ifdef CONFIG_EXT2_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= ext2_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+};

fs/ext2/xattr.h

@@ -0,0 +1,125 @@
+/*
+  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/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 const struct xattr_handler ext2_xattr_user_handler;
+extern const struct xattr_handler ext2_xattr_trusted_handler;
+extern const 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 const 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 */
+
+#ifdef CONFIG_EXT2_FS_SECURITY
+extern int ext2_init_security(struct inode *inode, struct inode *dir,
+			      const struct qstr *qstr);
+#else
+static inline int ext2_init_security(struct inode *inode, struct inode *dir,
+				     const struct qstr *qstr)
+{
+	return 0;
+}
+#endif

fs/ext2/xattr_security.c

@@ -0,0 +1,74 @@
+/*
+ * linux/fs/ext2/xattr_security.c
+ * Handler for storing security labels as extended attributes.
+ */
+
+#include "ext2.h"
+#include <linux/security.h>
+#include "xattr.h"
+
+static size_t
+ext2_xattr_security_list(struct dentry *dentry, char *list, size_t list_size,
+			 const char *name, size_t name_len, int type)
+{
+	const int prefix_len = XATTR_SECURITY_PREFIX_LEN;
+	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 dentry *dentry, const char *name,
+		       void *buffer, size_t size, int type)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	return ext2_xattr_get(dentry->d_inode, EXT2_XATTR_INDEX_SECURITY, name,
+			      buffer, size);
+}
+
+static int
+ext2_xattr_security_set(struct dentry *dentry, const char *name,
+		const void *value, size_t size, int flags, int type)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	return ext2_xattr_set(dentry->d_inode, EXT2_XATTR_INDEX_SECURITY, name,
+			      value, size, flags);
+}
+
+static int ext2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
+			   void *fs_info)
+{
+	const struct xattr *xattr;
+	int err = 0;
+
+	for (xattr = xattr_array; xattr->name != NULL; xattr++) {
+		err = ext2_xattr_set(inode, EXT2_XATTR_INDEX_SECURITY,
+				     xattr->name, xattr->value,
+				     xattr->value_len, 0);
+		if (err < 0)
+			break;
+	}
+	return err;
+}
+
+int
+ext2_init_security(struct inode *inode, struct inode *dir,
+		   const struct qstr *qstr)
+{
+	return security_inode_init_security(inode, dir, qstr,
+					    &ext2_initxattrs, NULL);
+}
+
+const 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 +1,54 @@
+/*
+ * linux/fs/ext2/xattr_trusted.c
+ * Handler for trusted extended attributes.
+ *
+ * Copyright (C) 2003 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
+ */
+
+#include "ext2.h"
+#include "xattr.h"
+
+static size_t
+ext2_xattr_trusted_list(struct dentry *dentry, char *list, size_t list_size,
+		const char *name, size_t name_len, int type)
+{
+	const int prefix_len = XATTR_TRUSTED_PREFIX_LEN;
+	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 dentry *dentry, const char *name,
+		void *buffer, size_t size, int type)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	return ext2_xattr_get(dentry->d_inode, EXT2_XATTR_INDEX_TRUSTED, name,
+			      buffer, size);
+}
+
+static int
+ext2_xattr_trusted_set(struct dentry *dentry, const char *name,
+		const void *value, size_t size, int flags, int type)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	return ext2_xattr_set(dentry->d_inode, EXT2_XATTR_INDEX_TRUSTED, name,
+			      value, size, flags);
+}
+
+const 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 +1,61 @@
+/*
+ * 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/string.h>
+#include "ext2.h"
+#include "xattr.h"
+
+static size_t
+ext2_xattr_user_list(struct dentry *dentry, char *list, size_t list_size,
+		const char *name, size_t name_len, int type)
+{
+	const size_t prefix_len = XATTR_USER_PREFIX_LEN;
+	const size_t total_len = prefix_len + name_len + 1;
+
+	if (!test_opt(dentry->d_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 dentry *dentry, const char *name,
+		void *buffer, size_t size, int type)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	if (!test_opt(dentry->d_sb, XATTR_USER))
+		return -EOPNOTSUPP;
+	return ext2_xattr_get(dentry->d_inode, EXT2_XATTR_INDEX_USER,
+			      name, buffer, size);
+}
+
+static int
+ext2_xattr_user_set(struct dentry *dentry, const char *name,
+		const void *value, size_t size, int flags, int type)
+{
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	if (!test_opt(dentry->d_sb, XATTR_USER))
+		return -EOPNOTSUPP;
+
+	return ext2_xattr_set(dentry->d_inode, EXT2_XATTR_INDEX_USER,
+			      name, value, size, flags);
+}
+
+const 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,
+};

fs/ext2/xip.c

@@ -0,0 +1,91 @@
+/*
+ *  linux/fs/ext2/xip.c
+ *
+ * Copyright (C) 2005 IBM Corporation
+ * Author: Carsten Otte (cotte@de.ibm.com)
+ */
+
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/genhd.h>
+#include <linux/buffer_head.h>
+#include <linux/blkdev.h>
+#include "ext2.h"
+#include "xip.h"
+
+static inline int
+__inode_direct_access(struct inode *inode, sector_t block,
+		      void **kaddr, unsigned long *pfn)
+{
+	struct block_device *bdev = inode->i_sb->s_bdev;
+	const struct block_device_operations *ops = bdev->bd_disk->fops;
+	sector_t sector;
+
+	sector = block * (PAGE_SIZE / 512); /* ext2 block to bdev sector */
+
+	BUG_ON(!ops->direct_access);
+	return ops->direct_access(bdev, sector, kaddr, pfn);
+}
+
+static inline int
+__ext2_get_block(struct inode *inode, pgoff_t pgoff, int create,
+		   sector_t *result)
+{
+	struct buffer_head tmp;
+	int rc;
+
+	memset(&tmp, 0, sizeof(struct buffer_head));
+	tmp.b_size = 1 << inode->i_blkbits;
+	rc = ext2_get_block(inode, pgoff, &tmp, create);
+	*result = tmp.b_blocknr;
+
+	/* did we get a sparse block (hole in the file)? */
+	if (!tmp.b_blocknr && !rc) {
+		BUG_ON(create);
+		rc = -ENODATA;
+	}
+
+	return rc;
+}
+
+int
+ext2_clear_xip_target(struct inode *inode, sector_t block)
+{
+	void *kaddr;
+	unsigned long pfn;
+	int rc;
+
+	rc = __inode_direct_access(inode, block, &kaddr, &pfn);
+	if (!rc)
+		clear_page(kaddr);
+	return rc;
+}
+
+void ext2_xip_verify_sb(struct super_block *sb)
+{
+	struct ext2_sb_info *sbi = EXT2_SB(sb);
+
+	if ((sbi->s_mount_opt & EXT2_MOUNT_XIP) &&
+	    !sb->s_bdev->bd_disk->fops->direct_access) {
+		sbi->s_mount_opt &= (~EXT2_MOUNT_XIP);
+		ext2_msg(sb, KERN_WARNING,
+			     "warning: ignoring xip option - "
+			     "not supported by bdev");
+	}
+}
+
+int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
+				void **kmem, unsigned long *pfn)
+{
+	int rc;
+	sector_t block;
+
+	/* first, retrieve the sector number */
+	rc = __ext2_get_block(mapping->host, pgoff, create, &block);
+	if (rc)
+		return rc;
+
+	/* retrieve address of the target data */
+	rc = __inode_direct_access(mapping->host, block, kmem, pfn);
+	return rc;
+}

fs/ext2/xip.h

@@ -0,0 +1,26 @@
+/*
+ *  linux/fs/ext2/xip.h
+ *
+ * Copyright (C) 2005 IBM Corporation
+ * Author: Carsten Otte (cotte@de.ibm.com)
+ */
+
+#ifdef CONFIG_EXT2_FS_XIP
+extern void ext2_xip_verify_sb (struct super_block *);
+extern int ext2_clear_xip_target (struct inode *, sector_t);
+
+static inline int ext2_use_xip (struct super_block *sb)
+{
+	struct ext2_sb_info *sbi = EXT2_SB(sb);
+	return (sbi->s_mount_opt & EXT2_MOUNT_XIP);
+}
+int ext2_get_xip_mem(struct address_space *, pgoff_t, int,
+				void **, unsigned long *);
+#define mapping_is_xip(map) unlikely(map->a_ops->get_xip_mem)
+#else
+#define mapping_is_xip(map)			0
+#define ext2_xip_verify_sb(sb)			do { } while (0)
+#define ext2_use_xip(sb)			0
+#define ext2_clear_xip_target(inode, chain)	0
+#define ext2_get_xip_mem			NULL
+#endif