Linux-2.6.12-rc2v2.6.12-rc2

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

Let it rip!

1 files changed, 2454 insertions, 0 deletions

diff --git a/fs/namei.c b/fs/namei.c
new file mode 100644
index 00000000000..9e4aef2a1a2
--- /dev/null
+++ b/fs/namei.c
@@ -0,0 +1,2454 @@
+/*
+ *  linux/fs/namei.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+/*
+ * Some corrections by tytso.
+ */
+
+/* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname
+ * lookup logic.
+ */
+/* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/quotaops.h>
+#include <linux/pagemap.h>
+#include <linux/dnotify.h>
+#include <linux/smp_lock.h>
+#include <linux/personality.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+#include <linux/mount.h>
+#include <linux/audit.h>
+#include <asm/namei.h>
+#include <asm/uaccess.h>
+
+#define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE])
+
+/* [Feb-1997 T. Schoebel-Theuer]
+ * Fundamental changes in the pathname lookup mechanisms (namei)
+ * were necessary because of omirr.  The reason is that omirr needs
+ * to know the _real_ pathname, not the user-supplied one, in case
+ * of symlinks (and also when transname replacements occur).
+ *
+ * The new code replaces the old recursive symlink resolution with
+ * an iterative one (in case of non-nested symlink chains).  It does
+ * this with calls to <fs>_follow_link().
+ * As a side effect, dir_namei(), _namei() and follow_link() are now 
+ * replaced with a single function lookup_dentry() that can handle all 
+ * the special cases of the former code.
+ *
+ * With the new dcache, the pathname is stored at each inode, at least as
+ * long as the refcount of the inode is positive.  As a side effect, the
+ * size of the dcache depends on the inode cache and thus is dynamic.
+ *
+ * [29-Apr-1998 C. Scott Ananian] Updated above description of symlink
+ * resolution to correspond with current state of the code.
+ *
+ * Note that the symlink resolution is not *completely* iterative.
+ * There is still a significant amount of tail- and mid- recursion in
+ * the algorithm.  Also, note that <fs>_readlink() is not used in
+ * lookup_dentry(): lookup_dentry() on the result of <fs>_readlink()
+ * may return different results than <fs>_follow_link().  Many virtual
+ * filesystems (including /proc) exhibit this behavior.
+ */
+
+/* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation:
+ * New symlink semantics: when open() is called with flags O_CREAT | O_EXCL
+ * and the name already exists in form of a symlink, try to create the new
+ * name indicated by the symlink. The old code always complained that the
+ * name already exists, due to not following the symlink even if its target
+ * is nonexistent.  The new semantics affects also mknod() and link() when
+ * the name is a symlink pointing to a non-existant name.
+ *
+ * I don't know which semantics is the right one, since I have no access
+ * to standards. But I found by trial that HP-UX 9.0 has the full "new"
+ * semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the
+ * "old" one. Personally, I think the new semantics is much more logical.
+ * Note that "ln old new" where "new" is a symlink pointing to a non-existing
+ * file does succeed in both HP-UX and SunOs, but not in Solaris
+ * and in the old Linux semantics.
+ */
+
+/* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink
+ * semantics.  See the comments in "open_namei" and "do_link" below.
+ *
+ * [10-Sep-98 Alan Modra] Another symlink change.
+ */
+
+/* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks:
+ *	inside the path - always follow.
+ *	in the last component in creation/removal/renaming - never follow.
+ *	if LOOKUP_FOLLOW passed - follow.
+ *	if the pathname has trailing slashes - follow.
+ *	otherwise - don't follow.
+ * (applied in that order).
+ *
+ * [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT
+ * restored for 2.4. This is the last surviving part of old 4.2BSD bug.
+ * During the 2.4 we need to fix the userland stuff depending on it -
+ * hopefully we will be able to get rid of that wart in 2.5. So far only
+ * XEmacs seems to be relying on it...
+ */
+/*
+ * [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland)
+ * implemented.  Let's see if raised priority of ->s_vfs_rename_sem gives
+ * any extra contention...
+ */
+
+/* In order to reduce some races, while at the same time doing additional
+ * checking and hopefully speeding things up, we copy filenames to the
+ * kernel data space before using them..
+ *
+ * POSIX.1 2.4: an empty pathname is invalid (ENOENT).
+ * PATH_MAX includes the nul terminator --RR.
+ */
+static inline int do_getname(const char __user *filename, char *page)
+{
+	int retval;
+	unsigned long len = PATH_MAX;
+
+	if (!segment_eq(get_fs(), KERNEL_DS)) {
+		if ((unsigned long) filename >= TASK_SIZE)
+			return -EFAULT;
+		if (TASK_SIZE - (unsigned long) filename < PATH_MAX)
+			len = TASK_SIZE - (unsigned long) filename;
+	}
+
+	retval = strncpy_from_user(page, filename, len);
+	if (retval > 0) {
+		if (retval < len)
+			return 0;
+		return -ENAMETOOLONG;
+	} else if (!retval)
+		retval = -ENOENT;
+	return retval;
+}
+
+char * getname(const char __user * filename)
+{
+	char *tmp, *result;
+
+	result = ERR_PTR(-ENOMEM);
+	tmp = __getname();
+	if (tmp)  {
+		int retval = do_getname(filename, tmp);
+
+		result = tmp;
+		if (retval < 0) {
+			__putname(tmp);
+			result = ERR_PTR(retval);
+		}
+	}
+	audit_getname(result);
+	return result;
+}
+
+#ifdef CONFIG_AUDITSYSCALL
+void putname(const char *name)
+{
+	if (unlikely(current->audit_context))
+		audit_putname(name);
+	else
+		__putname(name);
+}
+EXPORT_SYMBOL(putname);
+#endif
+
+
+/**
+ * generic_permission  -  check for access rights on a Posix-like filesystem
+ * @inode:	inode to check access rights for
+ * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
+ * @check_acl:	optional callback to check for Posix ACLs
+ *
+ * Used to check for read/write/execute permissions on a file.
+ * We use "fsuid" for this, letting us set arbitrary permissions
+ * for filesystem access without changing the "normal" uids which
+ * are used for other things..
+ */
+int generic_permission(struct inode *inode, int mask,
+		int (*check_acl)(struct inode *inode, int mask))
+{
+	umode_t			mode = inode->i_mode;
+
+	if (current->fsuid == inode->i_uid)
+		mode >>= 6;
+	else {
+		if (IS_POSIXACL(inode) && (mode & S_IRWXG) && check_acl) {
+			int error = check_acl(inode, mask);
+			if (error == -EACCES)
+				goto check_capabilities;
+			else if (error != -EAGAIN)
+				return error;
+		}
+
+		if (in_group_p(inode->i_gid))
+			mode >>= 3;
+	}
+
+	/*
+	 * If the DACs are ok we don't need any capability check.
+	 */
+	if (((mode & mask & (MAY_READ|MAY_WRITE|MAY_EXEC)) == mask))
+		return 0;
+
+ check_capabilities:
+	/*
+	 * Read/write DACs are always overridable.
+	 * Executable DACs are overridable if at least one exec bit is set.
+	 */
+	if (!(mask & MAY_EXEC) ||
+	    (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode))
+		if (capable(CAP_DAC_OVERRIDE))
+			return 0;
+
+	/*
+	 * Searching includes executable on directories, else just read.
+	 */
+	if (mask == MAY_READ || (S_ISDIR(inode->i_mode) && !(mask & MAY_WRITE)))
+		if (capable(CAP_DAC_READ_SEARCH))
+			return 0;
+
+	return -EACCES;
+}
+
+int permission(struct inode *inode, int mask, struct nameidata *nd)
+{
+	int retval, submask;
+
+	if (mask & MAY_WRITE) {
+		umode_t mode = inode->i_mode;
+
+		/*
+		 * Nobody gets write access to a read-only fs.
+		 */
+		if (IS_RDONLY(inode) &&
+		    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
+			return -EROFS;
+
+		/*
+		 * Nobody gets write access to an immutable file.
+		 */
+		if (IS_IMMUTABLE(inode))
+			return -EACCES;
+	}
+
+
+	/* Ordinary permission routines do not understand MAY_APPEND. */
+	submask = mask & ~MAY_APPEND;
+	if (inode->i_op && inode->i_op->permission)
+		retval = inode->i_op->permission(inode, submask, nd);
+	else
+		retval = generic_permission(inode, submask, NULL);
+	if (retval)
+		return retval;
+
+	return security_inode_permission(inode, mask, nd);
+}
+
+/*
+ * get_write_access() gets write permission for a file.
+ * put_write_access() releases this write permission.
+ * This is used for regular files.
+ * We cannot support write (and maybe mmap read-write shared) accesses and
+ * MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode
+ * can have the following values:
+ * 0: no writers, no VM_DENYWRITE mappings
+ * < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist
+ * > 0: (i_writecount) users are writing to the file.
+ *
+ * Normally we operate on that counter with atomic_{inc,dec} and it's safe
+ * except for the cases where we don't hold i_writecount yet. Then we need to
+ * use {get,deny}_write_access() - these functions check the sign and refuse
+ * to do the change if sign is wrong. Exclusion between them is provided by
+ * the inode->i_lock spinlock.
+ */
+
+int get_write_access(struct inode * inode)
+{
+	spin_lock(&inode->i_lock);
+	if (atomic_read(&inode->i_writecount) < 0) {
+		spin_unlock(&inode->i_lock);
+		return -ETXTBSY;
+	}
+	atomic_inc(&inode->i_writecount);
+	spin_unlock(&inode->i_lock);
+
+	return 0;
+}
+
+int deny_write_access(struct file * file)
+{
+	struct inode *inode = file->f_dentry->d_inode;
+
+	spin_lock(&inode->i_lock);
+	if (atomic_read(&inode->i_writecount) > 0) {
+		spin_unlock(&inode->i_lock);
+		return -ETXTBSY;
+	}
+	atomic_dec(&inode->i_writecount);
+	spin_unlock(&inode->i_lock);
+
+	return 0;
+}
+
+void path_release(struct nameidata *nd)
+{
+	dput(nd->dentry);
+	mntput(nd->mnt);
+}
+
+/*
+ * umount() mustn't call path_release()/mntput() as that would clear
+ * mnt_expiry_mark
+ */
+void path_release_on_umount(struct nameidata *nd)
+{
+	dput(nd->dentry);
+	_mntput(nd->mnt);
+}
+
+/*
+ * Internal lookup() using the new generic dcache.
+ * SMP-safe
+ */
+static struct dentry * cached_lookup(struct dentry * parent, struct qstr * name, struct nameidata *nd)
+{
+	struct dentry * dentry = __d_lookup(parent, name);
+
+	/* lockess __d_lookup may fail due to concurrent d_move() 
+	 * in some unrelated directory, so try with d_lookup
+	 */
+	if (!dentry)
+		dentry = d_lookup(parent, name);
+
+	if (dentry && dentry->d_op && dentry->d_op->d_revalidate) {
+		if (!dentry->d_op->d_revalidate(dentry, nd) && !d_invalidate(dentry)) {
+			dput(dentry);
+			dentry = NULL;
+		}
+	}
+	return dentry;
+}
+
+/*
+ * Short-cut version of permission(), for calling by
+ * path_walk(), when dcache lock is held.  Combines parts
+ * of permission() and generic_permission(), and tests ONLY for
+ * MAY_EXEC permission.
+ *
+ * If appropriate, check DAC only.  If not appropriate, or
+ * short-cut DAC fails, then call permission() to do more
+ * complete permission check.
+ */
+static inline int exec_permission_lite(struct inode *inode,
+				       struct nameidata *nd)
+{
+	umode_t	mode = inode->i_mode;
+
+	if (inode->i_op && inode->i_op->permission)
+		return -EAGAIN;
+
+	if (current->fsuid == inode->i_uid)
+		mode >>= 6;
+	else if (in_group_p(inode->i_gid))
+		mode >>= 3;
+
+	if (mode & MAY_EXEC)
+		goto ok;
+
+	if ((inode->i_mode & S_IXUGO) && capable(CAP_DAC_OVERRIDE))
+		goto ok;
+
+	if (S_ISDIR(inode->i_mode) && capable(CAP_DAC_OVERRIDE))
+		goto ok;
+
+	if (S_ISDIR(inode->i_mode) && capable(CAP_DAC_READ_SEARCH))
+		goto ok;
+
+	return -EACCES;
+ok:
+	return security_inode_permission(inode, MAY_EXEC, nd);
+}
+
+/*
+ * This is called when everything else fails, and we actually have
+ * to go to the low-level filesystem to find out what we should do..
+ *
+ * We get the directory semaphore, and after getting that we also
+ * make sure that nobody added the entry to the dcache in the meantime..
+ * SMP-safe
+ */
+static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, struct nameidata *nd)
+{
+	struct dentry * result;
+	struct inode *dir = parent->d_inode;
+
+	down(&dir->i_sem);
+	/*
+	 * First re-do the cached lookup just in case it was created
+	 * while we waited for the directory semaphore..
+	 *
+	 * FIXME! This could use version numbering or similar to
+	 * avoid unnecessary cache lookups.
+	 *
+	 * The "dcache_lock" is purely to protect the RCU list walker
+	 * from concurrent renames at this point (we mustn't get false
+	 * negatives from the RCU list walk here, unlike the optimistic
+	 * fast walk).
+	 *
+	 * so doing d_lookup() (with seqlock), instead of lockfree __d_lookup
+	 */
+	result = d_lookup(parent, name);
+	if (!result) {
+		struct dentry * dentry = d_alloc(parent, name);
+		result = ERR_PTR(-ENOMEM);
+		if (dentry) {
+			result = dir->i_op->lookup(dir, dentry, nd);
+			if (result)
+				dput(dentry);
+			else
+				result = dentry;
+		}
+		up(&dir->i_sem);
+		return result;
+	}
+
+	/*
+	 * Uhhuh! Nasty case: the cache was re-populated while
+	 * we waited on the semaphore. Need to revalidate.
+	 */
+	up(&dir->i_sem);
+	if (result->d_op && result->d_op->d_revalidate) {
+		if (!result->d_op->d_revalidate(result, nd) && !d_invalidate(result)) {
+			dput(result);
+			result = ERR_PTR(-ENOENT);
+		}
+	}
+	return result;
+}
+
+static int __emul_lookup_dentry(const char *, struct nameidata *);
+
+/* SMP-safe */
+static inline int
+walk_init_root(const char *name, struct nameidata *nd)
+{
+	read_lock(&current->fs->lock);
+	if (current->fs->altroot && !(nd->flags & LOOKUP_NOALT)) {
+		nd->mnt = mntget(current->fs->altrootmnt);
+		nd->dentry = dget(current->fs->altroot);
+		read_unlock(&current->fs->lock);
+		if (__emul_lookup_dentry(name,nd))
+			return 0;
+		read_lock(&current->fs->lock);
+	}
+	nd->mnt = mntget(current->fs->rootmnt);
+	nd->dentry = dget(current->fs->root);
+	read_unlock(&current->fs->lock);
+	return 1;
+}
+
+static inline int __vfs_follow_link(struct nameidata *nd, const char *link)
+{
+	int res = 0;
+	char *name;
+	if (IS_ERR(link))
+		goto fail;
+
+	if (*link == '/') {
+		path_release(nd);
+		if (!walk_init_root(link, nd))
+			/* weird __emul_prefix() stuff did it */
+			goto out;
+	}
+	res = link_path_walk(link, nd);
+out:
+	if (nd->depth || res || nd->last_type!=LAST_NORM)
+		return res;
+	/*
+	 * If it is an iterative symlinks resolution in open_namei() we
+	 * have to copy the last component. And all that crap because of
+	 * bloody create() on broken symlinks. Furrfu...
+	 */
+	name = __getname();
+	if (unlikely(!name)) {
+		path_release(nd);
+		return -ENOMEM;
+	}
+	strcpy(name, nd->last.name);
+	nd->last.name = name;
+	return 0;
+fail:
+	path_release(nd);
+	return PTR_ERR(link);
+}
+
+static inline int __do_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	int error;
+
+	touch_atime(nd->mnt, dentry);
+	nd_set_link(nd, NULL);
+	error = dentry->d_inode->i_op->follow_link(dentry, nd);
+	if (!error) {
+		char *s = nd_get_link(nd);
+		if (s)
+			error = __vfs_follow_link(nd, s);
+		if (dentry->d_inode->i_op->put_link)
+			dentry->d_inode->i_op->put_link(dentry, nd);
+	}
+
+	return error;
+}
+
+/*
+ * This limits recursive symlink follows to 8, while
+ * limiting consecutive symlinks to 40.
+ *
+ * Without that kind of total limit, nasty chains of consecutive
+ * symlinks can cause almost arbitrarily long lookups. 
+ */
+static inline int do_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	int err = -ELOOP;
+	if (current->link_count >= MAX_NESTED_LINKS)
+		goto loop;
+	if (current->total_link_count >= 40)
+		goto loop;
+	BUG_ON(nd->depth >= MAX_NESTED_LINKS);
+	cond_resched();
+	err = security_inode_follow_link(dentry, nd);
+	if (err)
+		goto loop;
+	current->link_count++;
+	current->total_link_count++;
+	nd->depth++;
+	err = __do_follow_link(dentry, nd);
+	current->link_count--;
+	nd->depth--;
+	return err;
+loop:
+	path_release(nd);
+	return err;
+}
+
+int follow_up(struct vfsmount **mnt, struct dentry **dentry)
+{
+	struct vfsmount *parent;
+	struct dentry *mountpoint;
+	spin_lock(&vfsmount_lock);
+	parent=(*mnt)->mnt_parent;
+	if (parent == *mnt) {
+		spin_unlock(&vfsmount_lock);
+		return 0;
+	}
+	mntget(parent);
+	mountpoint=dget((*mnt)->mnt_mountpoint);
+	spin_unlock(&vfsmount_lock);
+	dput(*dentry);
+	*dentry = mountpoint;
+	mntput(*mnt);
+	*mnt = parent;
+	return 1;
+}
+
+/* no need for dcache_lock, as serialization is taken care in
+ * namespace.c
+ */
+static int follow_mount(struct vfsmount **mnt, struct dentry **dentry)
+{
+	int res = 0;
+	while (d_mountpoint(*dentry)) {
+		struct vfsmount *mounted = lookup_mnt(*mnt, *dentry);
+		if (!mounted)
+			break;
+		mntput(*mnt);
+		*mnt = mounted;
+		dput(*dentry);
+		*dentry = dget(mounted->mnt_root);
+		res = 1;
+	}
+	return res;
+}
+
+/* no need for dcache_lock, as serialization is taken care in
+ * namespace.c
+ */
+static inline int __follow_down(struct vfsmount **mnt, struct dentry **dentry)
+{
+	struct vfsmount *mounted;
+
+	mounted = lookup_mnt(*mnt, *dentry);
+	if (mounted) {
+		mntput(*mnt);
+		*mnt = mounted;
+		dput(*dentry);
+		*dentry = dget(mounted->mnt_root);
+		return 1;
+	}
+	return 0;
+}
+
+int follow_down(struct vfsmount **mnt, struct dentry **dentry)
+{
+	return __follow_down(mnt,dentry);
+}
+ 
+static inline void follow_dotdot(struct vfsmount **mnt, struct dentry **dentry)
+{
+	while(1) {
+		struct vfsmount *parent;
+		struct dentry *old = *dentry;
+
+                read_lock(&current->fs->lock);
+		if (*dentry == current->fs->root &&
+		    *mnt == current->fs->rootmnt) {
+                        read_unlock(&current->fs->lock);
+			break;
+		}
+                read_unlock(&current->fs->lock);
+		spin_lock(&dcache_lock);
+		if (*dentry != (*mnt)->mnt_root) {
+			*dentry = dget((*dentry)->d_parent);
+			spin_unlock(&dcache_lock);
+			dput(old);
+			break;
+		}
+		spin_unlock(&dcache_lock);
+		spin_lock(&vfsmount_lock);
+		parent = (*mnt)->mnt_parent;
+		if (parent == *mnt) {
+			spin_unlock(&vfsmount_lock);
+			break;
+		}
+		mntget(parent);
+		*dentry = dget((*mnt)->mnt_mountpoint);
+		spin_unlock(&vfsmount_lock);
+		dput(old);
+		mntput(*mnt);
+		*mnt = parent;
+	}
+	follow_mount(mnt, dentry);
+}
+
+struct path {
+	struct vfsmount *mnt;
+	struct dentry *dentry;
+};
+
+/*
+ *  It's more convoluted than I'd like it to be, but... it's still fairly
+ *  small and for now I'd prefer to have fast path as straight as possible.
+ *  It _is_ time-critical.
+ */
+static int do_lookup(struct nameidata *nd, struct qstr *name,
+		     struct path *path)
+{
+	struct vfsmount *mnt = nd->mnt;
+	struct dentry *dentry = __d_lookup(nd->dentry, name);
+
+	if (!dentry)
+		goto need_lookup;
+	if (dentry->d_op && dentry->d_op->d_revalidate)
+		goto need_revalidate;
+done:
+	path->mnt = mnt;
+	path->dentry = dentry;
+	return 0;
+
+need_lookup:
+	dentry = real_lookup(nd->dentry, name, nd);
+	if (IS_ERR(dentry))
+		goto fail;
+	goto done;
+
+need_revalidate:
+	if (dentry->d_op->d_revalidate(dentry, nd))
+		goto done;
+	if (d_invalidate(dentry))
+		goto done;
+	dput(dentry);
+	goto need_lookup;
+
+fail:
+	return PTR_ERR(dentry);
+}
+
+/*
+ * Name resolution.
+ *
+ * This is the basic name resolution function, turning a pathname
+ * into the final dentry.
+ *
+ * We expect 'base' to be positive and a directory.
+ */
+static fastcall int __link_path_walk(const char * name, struct nameidata *nd)
+{
+	struct path next;
+	struct inode *inode;
+	int err;
+	unsigned int lookup_flags = nd->flags;
+	
+	while (*name=='/')
+		name++;
+	if (!*name)
+		goto return_reval;
+
+	inode = nd->dentry->d_inode;
+	if (nd->depth)
+		lookup_flags = LOOKUP_FOLLOW;
+
+	/* At this point we know we have a real path component. */
+	for(;;) {
+		unsigned long hash;
+		struct qstr this;
+		unsigned int c;
+
+		err = exec_permission_lite(inode, nd);
+		if (err == -EAGAIN) { 
+			err = permission(inode, MAY_EXEC, nd);
+		}
+ 		if (err)
+			break;
+
+		this.name = name;
+		c = *(const unsigned char *)name;
+
+		hash = init_name_hash();
+		do {
+			name++;
+			hash = partial_name_hash(c, hash);
+			c = *(const unsigned char *)name;
+		} while (c && (c != '/'));
+		this.len = name - (const char *) this.name;
+		this.hash = end_name_hash(hash);
+
+		/* remove trailing slashes? */
+		if (!c)
+			goto last_component;
+		while (*++name == '/');
+		if (!*name)
+			goto last_with_slashes;
+
+		/*
+		 * "." and ".." are special - ".." especially so because it has
+		 * to be able to know about the current root directory and
+		 * parent relationships.
+		 */
+		if (this.name[0] == '.') switch (this.len) {
+			default:
+				break;
+			case 2:	
+				if (this.name[1] != '.')
+					break;
+				follow_dotdot(&nd->mnt, &nd->dentry);
+				inode = nd->dentry->d_inode;
+				/* fallthrough */
+			case 1:
+				continue;
+		}
+		/*
+		 * See if the low-level filesystem might want
+		 * to use its own hash..
+		 */
+		if (nd->dentry->d_op && nd->dentry->d_op->d_hash) {
+			err = nd->dentry->d_op->d_hash(nd->dentry, &this);
+			if (err < 0)
+				break;
+		}
+		nd->flags |= LOOKUP_CONTINUE;
+		/* This does the actual lookups.. */
+		err = do_lookup(nd, &this, &next);
+		if (err)
+			break;
+		/* Check mountpoints.. */
+		follow_mount(&next.mnt, &next.dentry);
+
+		err = -ENOENT;
+		inode = next.dentry->d_inode;
+		if (!inode)
+			goto out_dput;
+		err = -ENOTDIR; 
+		if (!inode->i_op)
+			goto out_dput;
+
+		if (inode->i_op->follow_link) {
+			mntget(next.mnt);
+			err = do_follow_link(next.dentry, nd);
+			dput(next.dentry);
+			mntput(next.mnt);
+			if (err)
+				goto return_err;
+			err = -ENOENT;
+			inode = nd->dentry->d_inode;
+			if (!inode)
+				break;
+			err = -ENOTDIR; 
+			if (!inode->i_op)
+				break;
+		} else {
+			dput(nd->dentry);
+			nd->mnt = next.mnt;
+			nd->dentry = next.dentry;
+		}
+		err = -ENOTDIR; 
+		if (!inode->i_op->lookup)
+			break;
+		continue;
+		/* here ends the main loop */
+
+last_with_slashes:
+		lookup_flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
+last_component:
+		nd->flags &= ~LOOKUP_CONTINUE;
+		if (lookup_flags & LOOKUP_PARENT)
+			goto lookup_parent;
+		if (this.name[0] == '.') switch (this.len) {
+			default:
+				break;
+			case 2:	
+				if (this.name[1] != '.')
+					break;
+				follow_dotdot(&nd->mnt, &nd->dentry);
+				inode = nd->dentry->d_inode;
+				/* fallthrough */
+			case 1:
+				goto return_reval;
+		}
+		if (nd->dentry->d_op && nd->dentry->d_op->d_hash) {
+			err = nd->dentry->d_op->d_hash(nd->dentry, &this);
+			if (err < 0)
+				break;
+		}
+		err = do_lookup(nd, &this, &next);
+		if (err)
+			break;
+		follow_mount(&next.mnt, &next.dentry);
+		inode = next.dentry->d_inode;
+		if ((lookup_flags & LOOKUP_FOLLOW)
+		    && inode && inode->i_op && inode->i_op->follow_link) {
+			mntget(next.mnt);
+			err = do_follow_link(next.dentry, nd);
+			dput(next.dentry);
+			mntput(next.mnt);
+			if (err)
+				goto return_err;
+			inode = nd->dentry->d_inode;
+		} else {
+			dput(nd->dentry);
+			nd->mnt = next.mnt;
+			nd->dentry = next.dentry;
+		}
+		err = -ENOENT;
+		if (!inode)
+			break;
+		if (lookup_flags & LOOKUP_DIRECTORY) {
+			err = -ENOTDIR; 
+			if (!inode->i_op || !inode->i_op->lookup)
+				break;
+		}
+		goto return_base;
+lookup_parent:
+		nd->last = this;
+		nd->last_type = LAST_NORM;
+		if (this.name[0] != '.')
+			goto return_base;
+		if (this.len == 1)
+			nd->last_type = LAST_DOT;
+		else if (this.len == 2 && this.name[1] == '.')
+			nd->last_type = LAST_DOTDOT;
+		else
+			goto return_base;
+return_reval:
+		/*
+		 * We bypassed the ordinary revalidation routines.
+		 * We may need to check the cached dentry for staleness.
+		 */
+		if (nd->dentry && nd->dentry->d_sb &&
+		    (nd->dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)) {
+			err = -ESTALE;
+			/* Note: we do not d_invalidate() */
+			if (!nd->dentry->d_op->d_revalidate(nd->dentry, nd))
+				break;
+		}
+return_base:
+		return 0;
+out_dput:
+		dput(next.dentry);
+		break;
+	}
+	path_release(nd);
+return_err:
+	return err;
+}
+
+/*
+ * Wrapper to retry pathname resolution whenever the underlying
+ * file system returns an ESTALE.
+ *
+ * Retry the whole path once, forcing real lookup requests
+ * instead of relying on the dcache.
+ */
+int fastcall link_path_walk(const char *name, struct nameidata *nd)
+{
+	struct nameidata save = *nd;
+	int result;
+
+	/* make sure the stuff we saved doesn't go away */
+	dget(save.dentry);
+	mntget(save.mnt);
+
+	result = __link_path_walk(name, nd);
+	if (result == -ESTALE) {
+		*nd = save;
+		dget(nd->dentry);
+		mntget(nd->mnt);
+		nd->flags |= LOOKUP_REVAL;
+		result = __link_path_walk(name, nd);
+	}
+
+	dput(save.dentry);
+	mntput(save.mnt);
+
+	return result;
+}
+
+int fastcall path_walk(const char * name, struct nameidata *nd)
+{
+	current->total_link_count = 0;
+	return link_path_walk(name, nd);
+}
+
+/* SMP-safe */
+/* returns 1 if everything is done */
+static int __emul_lookup_dentry(const char *name, struct nameidata *nd)
+{
+	if (path_walk(name, nd))
+		return 0;		/* something went wrong... */
+
+	if (!nd->dentry->d_inode || S_ISDIR(nd->dentry->d_inode->i_mode)) {
+		struct dentry *old_dentry = nd->dentry;
+		struct vfsmount *old_mnt = nd->mnt;
+		struct qstr last = nd->last;
+		int last_type = nd->last_type;
+		/*
+		 * NAME was not found in alternate root or it's a directory.  Try to find
+		 * it in the normal root:
+		 */
+		nd->last_type = LAST_ROOT;
+		read_lock(&current->fs->lock);
+		nd->mnt = mntget(current->fs->rootmnt);
+		nd->dentry = dget(current->fs->root);
+		read_unlock(&current->fs->lock);
+		if (path_walk(name, nd) == 0) {
+			if (nd->dentry->d_inode) {
+				dput(old_dentry);
+				mntput(old_mnt);
+				return 1;
+			}
+			path_release(nd);
+		}
+		nd->dentry = old_dentry;
+		nd->mnt = old_mnt;
+		nd->last = last;
+		nd->last_type = last_type;
+	}
+	return 1;
+}
+
+void set_fs_altroot(void)
+{
+	char *emul = __emul_prefix();
+	struct nameidata nd;
+	struct vfsmount *mnt = NULL, *oldmnt;
+	struct dentry *dentry = NULL, *olddentry;
+	int err;
+
+	if (!emul)
+		goto set_it;
+	err = path_lookup(emul, LOOKUP_FOLLOW|LOOKUP_DIRECTORY|LOOKUP_NOALT, &nd);
+	if (!err) {
+		mnt = nd.mnt;
+		dentry = nd.dentry;
+	}
+set_it:
+	write_lock(&current->fs->lock);
+	oldmnt = current->fs->altrootmnt;
+	olddentry = current->fs->altroot;
+	current->fs->altrootmnt = mnt;
+	current->fs->altroot = dentry;
+	write_unlock(&current->fs->lock);
+	if (olddentry) {
+		dput(olddentry);
+		mntput(oldmnt);
+	}
+}
+
+int fastcall path_lookup(const char *name, unsigned int flags, struct nameidata *nd)
+{
+	int retval;
+
+	nd->last_type = LAST_ROOT; /* if there are only slashes... */
+	nd->flags = flags;
+	nd->depth = 0;
+
+	read_lock(&current->fs->lock);
+	if (*name=='/') {
+		if (current->fs->altroot && !(nd->flags & LOOKUP_NOALT)) {
+			nd->mnt = mntget(current->fs->altrootmnt);
+			nd->dentry = dget(current->fs->altroot);
+			read_unlock(&current->fs->lock);
+			if (__emul_lookup_dentry(name,nd))
+				return 0;
+			read_lock(&current->fs->lock);
+		}
+		nd->mnt = mntget(current->fs->rootmnt);
+		nd->dentry = dget(current->fs->root);
+	} else {
+		nd->mnt = mntget(current->fs->pwdmnt);
+		nd->dentry = dget(current->fs->pwd);
+	}
+	read_unlock(&current->fs->lock);
+	current->total_link_count = 0;
+	retval = link_path_walk(name, nd);
+	if (unlikely(current->audit_context
+		     && nd && nd->dentry && nd->dentry->d_inode))
+		audit_inode(name, nd->dentry->d_inode);
+	return retval;
+}
+
+/*
+ * Restricted form of lookup. Doesn't follow links, single-component only,
+ * needs parent already locked. Doesn't follow mounts.
+ * SMP-safe.
+ */
+static struct dentry * __lookup_hash(struct qstr *name, struct dentry * base, struct nameidata *nd)
+{
+	struct dentry * dentry;
+	struct inode *inode;
+	int err;
+
+	inode = base->d_inode;
+	err = permission(inode, MAY_EXEC, nd);
+	dentry = ERR_PTR(err);
+	if (err)
+		goto out;
+
+	/*
+	 * See if the low-level filesystem might want
+	 * to use its own hash..
+	 */
+	if (base->d_op && base->d_op->d_hash) {
+		err = base->d_op->d_hash(base, name);
+		dentry = ERR_PTR(err);
+		if (err < 0)
+			goto out;
+	}
+
+	dentry = cached_lookup(base, name, nd);
+	if (!dentry) {
+		struct dentry *new = d_alloc(base, name);
+		dentry = ERR_PTR(-ENOMEM);
+		if (!new)
+			goto out;
+		dentry = inode->i_op->lookup(inode, new, nd);
+		if (!dentry)
+			dentry = new;
+		else
+			dput(new);
+	}
+out:
+	return dentry;
+}
+
+struct dentry * lookup_hash(struct qstr *name, struct dentry * base)
+{
+	return __lookup_hash(name, base, NULL);
+}
+
+/* SMP-safe */
+struct dentry * lookup_one_len(const char * name, struct dentry * base, int len)
+{
+	unsigned long hash;
+	struct qstr this;
+	unsigned int c;
+
+	this.name = name;
+	this.len = len;
+	if (!len)
+		goto access;
+
+	hash = init_name_hash();
+	while (len--) {
+		c = *(const unsigned char *)name++;
+		if (c == '/' || c == '\0')
+			goto access;
+		hash = partial_name_hash(c, hash);
+	}
+	this.hash = end_name_hash(hash);
+
+	return lookup_hash(&this, base);
+access:
+	return ERR_PTR(-EACCES);
+}
+
+/*
+ *	namei()
+ *
+ * is used by most simple commands to get the inode of a specified name.
+ * Open, link etc use their own routines, but this is enough for things
+ * like 'chmod' etc.
+ *
+ * namei exists in two versions: namei/lnamei. The only difference is
+ * that namei follows links, while lnamei does not.
+ * SMP-safe
+ */
+int fastcall __user_walk(const char __user *name, unsigned flags, struct nameidata *nd)
+{
+	char *tmp = getname(name);
+	int err = PTR_ERR(tmp);
+
+	if (!IS_ERR(tmp)) {
+		err = path_lookup(tmp, flags, nd);
+		putname(tmp);
+	}
+	return err;
+}
+
+/*
+ * It's inline, so penalty for filesystems that don't use sticky bit is
+ * minimal.
+ */
+static inline int check_sticky(struct inode *dir, struct inode *inode)
+{
+	if (!(dir->i_mode & S_ISVTX))
+		return 0;
+	if (inode->i_uid == current->fsuid)
+		return 0;
+	if (dir->i_uid == current->fsuid)
+		return 0;
+	return !capable(CAP_FOWNER);
+}
+
+/*
+ *	Check whether we can remove a link victim from directory dir, check
+ *  whether the type of victim is right.
+ *  1. We can't do it if dir is read-only (done in permission())
+ *  2. We should have write and exec permissions on dir
+ *  3. We can't remove anything from append-only dir
+ *  4. We can't do anything with immutable dir (done in permission())
+ *  5. If the sticky bit on dir is set we should either
+ *	a. be owner of dir, or
+ *	b. be owner of victim, or
+ *	c. have CAP_FOWNER capability
+ *  6. If the victim is append-only or immutable we can't do antyhing with
+ *     links pointing to it.
+ *  7. If we were asked to remove a directory and victim isn't one - ENOTDIR.
+ *  8. If we were asked to remove a non-directory and victim isn't one - EISDIR.
+ *  9. We can't remove a root or mountpoint.
+ * 10. We don't allow removal of NFS sillyrenamed files; it's handled by
+ *     nfs_async_unlink().
+ */
+static inline int may_delete(struct inode *dir,struct dentry *victim,int isdir)
+{
+	int error;
+
+	if (!victim->d_inode)
+		return -ENOENT;
+
+	BUG_ON(victim->d_parent->d_inode != dir);
+
+	error = permission(dir,MAY_WRITE | MAY_EXEC, NULL);
+	if (error)
+		return error;
+	if (IS_APPEND(dir))
+		return -EPERM;
+	if (check_sticky(dir, victim->d_inode)||IS_APPEND(victim->d_inode)||
+	    IS_IMMUTABLE(victim->d_inode))
+		return -EPERM;
+	if (isdir) {
+		if (!S_ISDIR(