[PATCH 02/24] VFS: replace {, total_}link_count in task_struct with pointer to nameidata

[Al Viro <viro@ZenIV.linux.org.uk>]

From: NeilBrown <neilb@suse.de>

task_struct currently contains two ad-hoc members for use by
the VFS: link_count and total_link_count.
These are only interesting to fs/namei.c, so exposing them
explicitly is poor layering.

This patches replaces those with a single pointer to 'struct
nameidata'.
This structure represents the current filename lookup of which
there can only be one per process, and is a natural place to
store link_count and total_link_count.

This will allow the current "nameidata" argument to all
follow_link operations to be removed as current->nameidata
can be used instead.

As there are occasional circumstances where pathname lookup can
recurse, such as through kern_path_locked, we always save and old
current->nameidata (if there is one) when setting a new value, and
make sure any active link_counts are preserved.

follow_mount and follow_automount now get a 'struct nameidata *'
rather than 'int flags' so that they can directly access
link_count and total_link_count, rather than going through 'current'.

Suggested-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c            | 79 +++++++++++++++++++++++++++++++++++----------------
 include/linux/sched.h |  2 +-
 2 files changed, 55 insertions(+), 26 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index ffab2e0..bdd5067 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -501,10 +501,29 @@ struct nameidata {
 	unsigned	seq, m_seq;
 	int		last_type;
 	unsigned	depth;
+	int		link_count,
+			total_link_count;
 	struct file	*base;
 	char *saved_names[MAX_NESTED_LINKS + 1];
 };
 
+static struct nameidata *set_nameidata(struct nameidata *p)
+{
+	struct nameidata *old = current->nameidata;
+
+	current->nameidata = p;
+	if (p) {
+		if (!old) {
+			p->link_count = 0;
+			p->total_link_count = 0;
+		} else {
+			p->link_count = old->link_count;
+			p->total_link_count = old->total_link_count;
+		}
+	}
+	return old;
+}
+
 /*
  * Path walking has 2 modes, rcu-walk and ref-walk (see
  * Documentation/filesystems/path-lookup.txt).  In situations when we can't
@@ -862,11 +881,11 @@ follow_link(struct path *link, struct nameidata *nd, void **p)
 		mntget(link->mnt);
 
 	error = -ELOOP;
-	if (unlikely(current->total_link_count >= 40))
+	if (unlikely(nd->total_link_count >= 40))
 		goto out_put_nd_path;
 
 	cond_resched();
-	current->total_link_count++;
+	nd->total_link_count++;
 
 	touch_atime(link);
 	nd_set_link(nd, NULL);
@@ -965,7 +984,7 @@ EXPORT_SYMBOL(follow_up);
  * - return -EISDIR to tell follow_managed() to stop and return the path we
  *   were called with.
  */
-static int follow_automount(struct path *path, unsigned flags,
+static int follow_automount(struct path *path, struct nameidata *nd,
 			    bool *need_mntput)
 {
 	struct vfsmount *mnt;
@@ -985,13 +1004,13 @@ static int follow_automount(struct path *path, unsigned flags,
 	 * as being automount points.  These will need the attentions
 	 * of the daemon to instantiate them before they can be used.
 	 */
-	if (!(flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
-		     LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
+	if (!(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
+			   LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
 	    path->dentry->d_inode)
 		return -EISDIR;
 
-	current->total_link_count++;
-	if (current->total_link_count >= 40)
+	nd->total_link_count++;
+	if (nd->total_link_count >= 40)
 		return -ELOOP;
 
 	mnt = path->dentry->d_op->d_automount(path);
@@ -1005,7 +1024,7 @@ static int follow_automount(struct path *path, unsigned flags,
 		 * the path being looked up; if it wasn't then the remainder of
 		 * the path is inaccessible and we should say so.
 		 */
-		if (PTR_ERR(mnt) == -EISDIR && (flags & LOOKUP_PARENT))
+		if (PTR_ERR(mnt) == -EISDIR && (nd->flags & LOOKUP_PARENT))
 			return -EREMOTE;
 		return PTR_ERR(mnt);
 	}
@@ -1045,7 +1064,7 @@ static int follow_automount(struct path *path, unsigned flags,
  *
  * Serialization is taken care of in namespace.c
  */
-static int follow_managed(struct path *path, unsigned flags)
+static int follow_managed(struct path *path, struct nameidata *nd)
 {
 	struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */
 	unsigned managed;
@@ -1089,7 +1108,7 @@ static int follow_managed(struct path *path, unsigned flags)
 
 		/* Handle an automount point */
 		if (managed & DCACHE_NEED_AUTOMOUNT) {
-			ret = follow_automount(path, flags, &need_mntput);
+			ret = follow_automount(path, nd, &need_mntput);
 			if (ret < 0)
 				break;
 			continue;
@@ -1474,7 +1493,7 @@ unlazy:
 
 	path->mnt = mnt;
 	path->dentry = dentry;
-	err = follow_managed(path, nd->flags);
+	err = follow_managed(path, nd);
 	if (unlikely(err < 0)) {
 		path_put_conditional(path, nd);
 		return err;
@@ -1504,7 +1523,7 @@ static int lookup_slow(struct nameidata *nd, struct path *path)
 		return PTR_ERR(dentry);
 	path->mnt = nd->path.mnt;
 	path->dentry = dentry;
-	err = follow_managed(path, nd->flags);
+	err = follow_managed(path, nd);
 	if (unlikely(err < 0)) {
 		path_put_conditional(path, nd);
 		return err;
@@ -1620,7 +1639,7 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd)
 {
 	int res;
 
-	if (unlikely(current->link_count >= MAX_NESTED_LINKS)) {
+	if (unlikely(nd->link_count >= MAX_NESTED_LINKS)) {
 		path_put_conditional(path, nd);
 		path_put(&nd->path);
 		return -ELOOP;
@@ -1628,7 +1647,7 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd)
 	BUG_ON(nd->depth >= MAX_NESTED_LINKS);
 
 	nd->depth++;
-	current->link_count++;
+	nd->link_count++;
 
 	do {
 		struct path link = *path;
@@ -1641,7 +1660,7 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd)
 		put_link(nd, &link, cookie);
 	} while (res > 0);
 
-	current->link_count--;
+	nd->link_count--;
 	nd->depth--;
 	return res;
 }
@@ -1948,7 +1967,7 @@ static int path_init(int dfd, const struct filename *name, unsigned int flags,
 	rcu_read_unlock();
 	return -ECHILD;
 done:
-	current->total_link_count = 0;
+	nd->total_link_count = 0;
 	return link_path_walk(s, nd);
 }
 
@@ -2027,7 +2046,10 @@ static int path_lookupat(int dfd, const struct filename *name,
 static int filename_lookup(int dfd, struct filename *name,
 				unsigned int flags, struct nameidata *nd)
 {
-	int retval = path_lookupat(dfd, name, flags | LOOKUP_RCU, nd);
+	int retval;
+	struct nameidata *saved_nd = set_nameidata(nd);
+
+	retval = path_lookupat(dfd, name, flags | LOOKUP_RCU, nd);
 	if (unlikely(retval == -ECHILD))
 		retval = path_lookupat(dfd, name, flags, nd);
 	if (unlikely(retval == -ESTALE))
@@ -2035,6 +2057,7 @@ static int filename_lookup(int dfd, struct filename *name,
 
 	if (likely(!retval))
 		audit_inode(name, nd->path.dentry, flags & LOOKUP_PARENT);
+	set_nameidata(saved_nd);
 	return retval;
 }
 
@@ -2341,7 +2364,7 @@ static int
 path_mountpoint(int dfd, const struct filename *name, struct path *path,
 		unsigned int flags)
 {
-	struct nameidata nd;
+	struct nameidata nd, *saved = set_nameidata(&nd);
 	int err;
 
 	err = path_init(dfd, name, flags, &nd);
@@ -2364,6 +2387,7 @@ path_mountpoint(int dfd, const struct filename *name, struct path *path,
 	}
 out:
 	path_cleanup(&nd);
+	set_nameidata(saved);
 	return err;
 }
 
@@ -3026,7 +3050,7 @@ retry_lookup:
 	if ((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT))
 		goto exit_dput;
 
-	error = follow_managed(path, nd->flags);
+	error = follow_managed(path, nd);
 	if (error < 0)
 		goto exit_dput;
 
@@ -3215,12 +3239,14 @@ static struct file *path_openat(int dfd, struct filename *pathname,
 	struct path path;
 	int opened = 0;
 	int error;
+	struct nameidata *saved_nd;
 
 	file = get_empty_filp();
 	if (IS_ERR(file))
 		return file;
 
 	file->f_flags = op->open_flag;
+	saved_nd = set_nameidata(nd);
 
 	if (unlikely(file->f_flags & __O_TMPFILE)) {
 		error = do_tmpfile(dfd, pathname, nd, flags, op, file, &opened);
@@ -3267,6 +3293,7 @@ out:
 		}
 		file = ERR_PTR(error);
 	}
+	set_nameidata(saved_nd);
 	return file;
 }
 
@@ -4427,18 +4454,20 @@ EXPORT_SYMBOL(readlink_copy);
  */
 int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
-	struct nameidata nd;
+	struct nameidata nd, *saved = set_nameidata(&nd);
 	void *cookie;
 	int res;
 
 	nd.depth = 0;
 	cookie = dentry->d_inode->i_op->follow_link(dentry, &nd);
 	if (IS_ERR(cookie))
-		return PTR_ERR(cookie);
-
-	res = readlink_copy(buffer, buflen, nd_get_link(&nd));
-	if (dentry->d_inode->i_op->put_link)
-		dentry->d_inode->i_op->put_link(dentry, &nd, cookie);
+		res = PTR_ERR(cookie);
+	else {
+		res = readlink_copy(buffer, buflen, nd_get_link(&nd));
+		if (dentry->d_inode->i_op->put_link)
+			dentry->d_inode->i_op->put_link(dentry, &nd, cookie);
+	}
+	set_nameidata(saved);
 	return res;
 }
 EXPORT_SYMBOL(generic_readlink);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a419b65..4402c91 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1447,7 +1447,7 @@ struct task_struct {
 				       it with task_lock())
 				     - initialized normally by setup_new_exec */
 /* file system info */
-	int link_count, total_link_count;
+	struct nameidata *nameidata;
 #ifdef CONFIG_SYSVIPC
 /* ipc stuff */
 	struct sysv_sem sysvsem;
-- 
2.1.4