1 files changed, 166 insertions, 45 deletions

diff --git a/fs/namei.c b/fs/namei.c
index b7fad009bbf..5008f01787f 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -32,6 +32,7 @@
 #include <linux/fcntl.h>
 #include <linux/device_cgroup.h>
 #include <linux/fs_struct.h>
+#include <linux/posix_acl.h>
 #include <asm/uaccess.h>
 
 #include "internal.h"
@@ -136,7 +137,7 @@ static int do_getname(const char __user *filename, char *page)
 	return retval;
 }
 
-static char *getname_flags(const char __user * filename, int flags)
+static char *getname_flags(const char __user *filename, int flags, int *empty)
 {
 	char *tmp, *result;
 
@@ -147,6 +148,8 @@ static char *getname_flags(const char __user * filename, int flags)
 
 		result = tmp;
 		if (retval < 0) {
+			if (retval == -ENOENT && empty)
+				*empty = 1;
 			if (retval != -ENOENT || !(flags & LOOKUP_EMPTY)) {
 				__putname(tmp);
 				result = ERR_PTR(retval);
@@ -159,7 +162,7 @@ static char *getname_flags(const char __user * filename, int flags)
 
 char *getname(const char __user * filename)
 {
-	return getname_flags(filename, 0);
+	return getname_flags(filename, 0, 0);
 }
 
 #ifdef CONFIG_AUDITSYSCALL
@@ -173,24 +176,66 @@ void putname(const char *name)
 EXPORT_SYMBOL(putname);
 #endif
 
+static int check_acl(struct inode *inode, int mask)
+{
+#ifdef CONFIG_FS_POSIX_ACL
+	struct posix_acl *acl;
+
+	if (mask & MAY_NOT_BLOCK) {
+		acl = get_cached_acl_rcu(inode, ACL_TYPE_ACCESS);
+	        if (!acl)
+	                return -EAGAIN;
+		/* no ->get_acl() calls in RCU mode... */
+		if (acl == ACL_NOT_CACHED)
+			return -ECHILD;
+	        return posix_acl_permission(inode, acl, mask & ~MAY_NOT_BLOCK);
+	}
+
+	acl = get_cached_acl(inode, ACL_TYPE_ACCESS);
+
+	/*
+	 * A filesystem can force a ACL callback by just never filling the
+	 * ACL cache. But normally you'd fill the cache either at inode
+	 * instantiation time, or on the first ->get_acl call.
+	 *
+	 * If the filesystem doesn't have a get_acl() function at all, we'll
+	 * just create the negative cache entry.
+	 */
+	if (acl == ACL_NOT_CACHED) {
+	        if (inode->i_op->get_acl) {
+			acl = inode->i_op->get_acl(inode, ACL_TYPE_ACCESS);
+			if (IS_ERR(acl))
+				return PTR_ERR(acl);
+		} else {
+		        set_cached_acl(inode, ACL_TYPE_ACCESS, NULL);
+		        return -EAGAIN;
+		}
+	}
+
+	if (acl) {
+	        int error = posix_acl_permission(inode, acl, mask);
+	        posix_acl_release(acl);
+	        return error;
+	}
+#endif
+
+	return -EAGAIN;
+}
+
 /*
- * This does basic POSIX ACL permission checking
+ * This does the basic permission checking
  */
 static int acl_permission_check(struct inode *inode, int mask)
 {
-	int (*check_acl)(struct inode *inode, int mask);
 	unsigned int mode = inode->i_mode;
 
-	mask &= MAY_READ | MAY_WRITE | MAY_EXEC | MAY_NOT_BLOCK;
-
 	if (current_user_ns() != inode_userns(inode))
 		goto other_perms;
 
-	if (current_fsuid() == inode->i_uid)
+	if (likely(current_fsuid() == inode->i_uid))
 		mode >>= 6;
 	else {
-		check_acl = inode->i_op->check_acl;
-		if (IS_POSIXACL(inode) && (mode & S_IRWXG) && check_acl) {
+		if (IS_POSIXACL(inode) && (mode & S_IRWXG)) {
 			int error = check_acl(inode, mask);
 			if (error != -EAGAIN)
 				return error;
@@ -212,7 +257,7 @@ other_perms:
 /**
  * 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)
+ * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, ...)
  *
  * Used to check for read/write/execute permissions on a file.
  * We use "fsuid" for this, letting us set arbitrary permissions
@@ -228,7 +273,7 @@ int generic_permission(struct inode *inode, int mask)
 	int ret;
 
 	/*
-	 * Do the basic POSIX ACL permission checks.
+	 * Do the basic permission checks.
 	 */
 	ret = acl_permission_check(inode, mask);
 	if (ret != -EACCES)
@@ -263,21 +308,43 @@ int generic_permission(struct inode *inode, int mask)
 	return -EACCES;
 }
 
+/*
+ * We _really_ want to just do "generic_permission()" without
+ * even looking at the inode->i_op values. So we keep a cache
+ * flag in inode->i_opflags, that says "this has not special
+ * permission function, use the fast case".
+ */
+static inline int do_inode_permission(struct inode *inode, int mask)
+{
+	if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) {
+		if (likely(inode->i_op->permission))
+			return inode->i_op->permission(inode, mask);
+
+		/* This gets set once for the inode lifetime */
+		spin_lock(&inode->i_lock);
+		inode->i_opflags |= IOP_FASTPERM;
+		spin_unlock(&inode->i_lock);
+	}
+	return generic_permission(inode, mask);
+}
+
 /**
  * inode_permission  -  check for access rights to a given inode
  * @inode:	inode to check permission on
- * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
+ * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, ...)
  *
  * Used to check for read/write/execute permissions on an inode.
  * We use "fsuid" for this, letting us set arbitrary permissions
  * for filesystem access without changing the "normal" uids which
  * are used for other things.
+ *
+ * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask.
  */
 int inode_permission(struct inode *inode, int mask)
 {
 	int retval;
 
-	if (mask & MAY_WRITE) {
+	if (unlikely(mask & MAY_WRITE)) {
 		umode_t mode = inode->i_mode;
 
 		/*
@@ -294,11 +361,7 @@ int inode_permission(struct inode *inode, int mask)
 			return -EACCES;
 	}
 
-	if (inode->i_op->permission)
-		retval = inode->i_op->permission(inode, mask);
-	else
-		retval = generic_permission(inode, mask);
-
+	retval = do_inode_permission(inode, mask);
 	if (retval)
 		return retval;
 
@@ -660,23 +723,20 @@ static int follow_automount(struct path *path, unsigned flags,
 	if (!path->dentry->d_op || !path->dentry->d_op->d_automount)
 		return -EREMOTE;
 
-	/* We don't want to mount if someone supplied AT_NO_AUTOMOUNT
-	 * and this is the terminal part of the path.
-	 */
-	if ((flags & LOOKUP_NO_AUTOMOUNT) && !(flags & LOOKUP_PARENT))
-		return -EISDIR; /* we actually want to stop here */
-
-	/* We want to mount if someone is trying to open/create a file of any
-	 * type under the mountpoint, wants to traverse through the mountpoint
-	 * or wants to open the mounted directory.
+	/* We don't want to mount if someone's just doing a stat -
+	 * unless they're stat'ing a directory and appended a '/' to
+	 * the name.
 	 *
-	 * We don't want to mount if someone's just doing a stat and they've
-	 * set AT_SYMLINK_NOFOLLOW - unless they're stat'ing a directory and
-	 * appended a '/' to the name.
+	 * We do, however, want to mount if someone wants to open or
+	 * create a file of any type under the mountpoint, wants to
+	 * traverse through the mountpoint or wants to open the
+	 * mounted directory.  Also, autofs may mark negative dentries
+	 * as being automount points.  These will need the attentions
+	 * of the daemon to instantiate them before they can be used.
 	 */
-	if (!(flags & LOOKUP_FOLLOW) &&
-	    !(flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
-		       LOOKUP_OPEN | LOOKUP_CREATE)))
+	if (!(flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
+		     LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
+	    path->dentry->d_inode)
 		return -EISDIR;
 
 	current->total_link_count++;
@@ -792,7 +852,7 @@ static int follow_managed(struct path *path, unsigned flags)
 		mntput(path->mnt);
 	if (ret == -EISDIR)
 		ret = 0;
-	return ret;
+	return ret < 0 ? ret : need_mntput;
 }
 
 int follow_down_one(struct path *path)
@@ -840,6 +900,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 			break;
 		path->mnt = mounted;
 		path->dentry = mounted->mnt_root;
+		nd->flags |= LOOKUP_JUMPED;
 		nd->seq = read_seqcount_begin(&path->dentry->d_seq);
 		/*
 		 * Update the inode too. We don't need to re-check the
@@ -1153,6 +1214,8 @@ retry:
 		path_put_conditional(path, nd);
 		return err;
 	}
+	if (err)
+		nd->flags |= LOOKUP_JUMPED;
 	*inode = path->dentry->d_inode;
 	return 0;
 }
@@ -1194,6 +1257,26 @@ static void terminate_walk(struct nameidata *nd)
 	}
 }
 
+/*
+ * Do we need to follow links? We _really_ want to be able
+ * to do this check without having to look at inode->i_op,
+ * so we keep a cache of "no, this doesn't need follow_link"
+ * for the common case.
+ */
+static inline int should_follow_link(struct inode *inode, int follow)
+{
+	if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) {
+		if (likely(inode->i_op->follow_link))
+			return follow;
+
+		/* This gets set once for the inode lifetime */
+		spin_lock(&inode->i_lock);
+		inode->i_opflags |= IOP_NOFOLLOW;
+		spin_unlock(&inode->i_lock);
+	}
+	return 0;
+}
+
 static inline int walk_component(struct nameidata *nd, struct path *path,
 		struct qstr *name, int type, int follow)
 {
@@ -1216,7 +1299,7 @@ static inline int walk_component(struct nameidata *nd, struct path *path,
 		terminate_walk(nd);
 		return -ENOENT;
 	}
-	if (unlikely(inode->i_op->follow_link) && follow) {
+	if (should_follow_link(inode, follow)) {
 		if (nd->flags & LOOKUP_RCU) {
 			if (unlikely(unlazy_walk(nd, path->dentry))) {
 				terminate_walk(nd);
@@ -1269,6 +1352,26 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd)
 }
 
 /*
+ * We really don't want to look at inode->i_op->lookup
+ * when we don't have to. So we keep a cache bit in
+ * the inode ->i_opflags field that says "yes, we can
+ * do lookup on this inode".
+ */
+static inline int can_lookup(struct inode *inode)
+{
+	if (likely(inode->i_opflags & IOP_LOOKUP))
+		return 1;
+	if (likely(!inode->i_op->lookup))
+		return 0;
+
+	/* We do this once for the lifetime of the inode */
+	spin_lock(&inode->i_lock);
+	inode->i_opflags |= IOP_LOOKUP;
+	spin_unlock(&inode->i_lock);
+	return 1;
+}
+
+/*
  * 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.
@@ -1347,10 +1450,10 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 			if (err)
 				return err;
 		}
+		if (can_lookup(nd->inode))
+			continue;
 		err = -ENOTDIR; 
-		if (!nd->inode->i_op->lookup)
-			break;
-		continue;
+		break;
 		/* here ends the main loop */
 
 last_component:
@@ -1700,11 +1803,11 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 	return __lookup_hash(&this, base, NULL);
 }
 
-int user_path_at(int dfd, const char __user *name, unsigned flags,
-		 struct path *path)
+int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
+		 struct path *path, int *empty)
 {
 	struct nameidata nd;
-	char *tmp = getname_flags(name, flags);
+	char *tmp = getname_flags(name, flags, empty);
 	int err = PTR_ERR(tmp);
 	if (!IS_ERR(tmp)) {
 
@@ -1718,6 +1821,12 @@ int user_path_at(int dfd, const char __user *name, unsigned flags,
 	return err;
 }
 
+int user_path_at(int dfd, const char __user *name, unsigned flags,
+		 struct path *path)
+{
+	return user_path_at_empty(dfd, name, flags, path, 0);
+}
+
 static int user_path_parent(int dfd, const char __user *path,
 			struct nameidata *nd, char **name)
 {
@@ -1937,10 +2046,7 @@ static int may_open(struct path *path, int acc_mode, int flag)
 	if (flag & O_NOATIME && !inode_owner_or_capable(inode))
 		return -EPERM;
 
-	/*
-	 * Ensure there are no outstanding leases on the file.
-	 */
-	return break_lease(inode, flag);
+	return 0;
 }
 
 static int handle_truncate(struct file *filp)
@@ -2043,6 +2149,10 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	}
 
 	/* create side of things */
+	/*
+	 * This will *only* deal with leaving RCU mode - LOOKUP_JUMPED has been
+	 * cleared when we got to the last component we are about to look up
+	 */
 	error = complete_walk(nd);
 	if (error)
 		return ERR_PTR(error);
@@ -2111,6 +2221,9 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	if (error < 0)
 		goto exit_dput;
 
+	if (error)
+		nd->flags |= LOOKUP_JUMPED;
+
 	error = -ENOENT;
 	if (!path->dentry->d_inode)
 		goto exit_dput;
@@ -2120,6 +2233,10 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 
 	path_to_nameidata(path, nd);
 	nd->inode = path->dentry->d_inode;
+	/* Why this, you ask?  _Now_ we might have grown LOOKUP_JUMPED... */
+	error = complete_walk(nd);
+	if (error)
+		goto exit;
 	error = -EISDIR;
 	if (S_ISDIR(nd->inode->i_mode))
 		goto exit;
@@ -2512,6 +2629,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 	if (!dir->i_op->rmdir)
 		return -EPERM;
 
+	dget(dentry);
 	mutex_lock(&dentry->d_inode->i_mutex);
 
 	error = -EBUSY;
@@ -2532,6 +2650,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 
 out:
 	mutex_unlock(&dentry->d_inode->i_mutex);
+	dput(dentry);
 	if (!error)
 		d_delete(dentry);
 	return error;
@@ -2921,6 +3040,7 @@ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
 	if (error)
 		return error;
 
+	dget(new_dentry);
 	if (target)
 		mutex_lock(&target->i_mutex);
 
@@ -2941,6 +3061,7 @@ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
 out:
 	if (target)
 		mutex_unlock(&target->i_mutex);
+	dput(new_dentry);
 	if (!error)
 		if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
 			d_move(old_dentry,new_dentry);