X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fopen.c;h=b70e7666bb2c3f725a761b268b2370e5c151ba63;hb=bc36a686a65dd9b941463ff894a3868c62851186;hp=43fcd6031969509cb6d64d7d705cb1990a920e2e;hpb=3287629eff75c7323e875b942be82f7ac6ca18da;p=safe%2Fjmp%2Flinux-2.6

diff --git a/fs/open.c b/fs/open.c
index 43fcd60..b70e766 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -127,10 +127,10 @@ asmlinkage long sys_statfs(const char __user * path, struct statfs __user * buf)
 	error = user_path_walk(path, &nd);
 	if (!error) {
 		struct statfs tmp;
-		error = vfs_statfs_native(nd.dentry, &tmp);
+		error = vfs_statfs_native(nd.path.dentry, &tmp);
 		if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
 			error = -EFAULT;
-		path_release(&nd);
+		path_put(&nd.path);
 	}
 	return error;
 }
@@ -146,10 +146,10 @@ asmlinkage long sys_statfs64(const char __user *path, size_t sz, struct statfs64
 	error = user_path_walk(path, &nd);
 	if (!error) {
 		struct statfs64 tmp;
-		error = vfs_statfs64(nd.dentry, &tmp);
+		error = vfs_statfs64(nd.path.dentry, &tmp);
 		if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
 			error = -EFAULT;
-		path_release(&nd);
+		path_put(&nd.path);
 	}
 	return error;
 }
@@ -233,7 +233,7 @@ static long do_sys_truncate(const char __user * path, loff_t length)
 	error = user_path_walk(path, &nd);
 	if (error)
 		goto out;
-	inode = nd.dentry->d_inode;
+	inode = nd.path.dentry->d_inode;
 
 	/* For directories it's -EISDIR, for other non-regulars - -EINVAL */
 	error = -EISDIR;
@@ -244,21 +244,21 @@ static long do_sys_truncate(const char __user * path, loff_t length)
 	if (!S_ISREG(inode->i_mode))
 		goto dput_and_out;
 
-	error = vfs_permission(&nd, MAY_WRITE);
+	error = mnt_want_write(nd.path.mnt);
 	if (error)
 		goto dput_and_out;
 
-	error = -EROFS;
-	if (IS_RDONLY(inode))
-		goto dput_and_out;
+	error = vfs_permission(&nd, MAY_WRITE);
+	if (error)
+		goto mnt_drop_write_and_out;
 
 	error = -EPERM;
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
-		goto dput_and_out;
+		goto mnt_drop_write_and_out;
 
 	error = get_write_access(inode);
 	if (error)
-		goto dput_and_out;
+		goto mnt_drop_write_and_out;
 
 	/*
 	 * Make sure that there are no leases.  get_write_access() protects
@@ -271,13 +271,15 @@ static long do_sys_truncate(const char __user * path, loff_t length)
 	error = locks_verify_truncate(inode, NULL, length);
 	if (!error) {
 		DQUOT_INIT(inode);
-		error = do_truncate(nd.dentry, length, 0, NULL);
+		error = do_truncate(nd.path.dentry, length, 0, NULL);
 	}
 
 put_write_and_out:
 	put_write_access(inode);
+mnt_drop_write_and_out:
+	mnt_drop_write(nd.path.mnt);
 dput_and_out:
-	path_release(&nd);
+	path_put(&nd.path);
 out:
 	return error;
 }
@@ -335,7 +337,7 @@ asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length)
 {
 	long ret = do_sys_ftruncate(fd, length, 1);
 	/* avoid REGPARM breakage on x86: */
-	prevent_tail_call(ret);
+	asmlinkage_protect(2, ret, fd, length);
 	return ret;
 }
 
@@ -350,7 +352,7 @@ asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length)
 {
 	long ret = do_sys_ftruncate(fd, length, 0);
 	/* avoid REGPARM breakage on x86: */
-	prevent_tail_call(ret);
+	asmlinkage_protect(2, ret, fd, length);
 	return ret;
 }
 #endif
@@ -455,14 +457,23 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
 	res = vfs_permission(&nd, mode);
 	/* SuS v2 requires we report a read only fs too */
 	if(res || !(mode & S_IWOTH) ||
-	   special_file(nd.dentry->d_inode->i_mode))
+	   special_file(nd.path.dentry->d_inode->i_mode))
 		goto out_path_release;
-
-	if(IS_RDONLY(nd.dentry->d_inode))
+	/*
+	 * This is a rare case where using __mnt_is_readonly()
+	 * is OK without a mnt_want/drop_write() pair.  Since
+	 * no actual write to the fs is performed here, we do
+	 * not need to telegraph to that to anyone.
+	 *
+	 * By doing this, we accept that this access is
+	 * inherently racy and know that the fs may change
+	 * state before we even see this result.
+	 */
+	if (__mnt_is_readonly(nd.path.mnt))
 		res = -EROFS;
 
 out_path_release:
-	path_release(&nd);
+	path_put(&nd.path);
 out:
 	current->fsuid = old_fsuid;
 	current->fsgid = old_fsgid;
@@ -490,10 +501,10 @@ asmlinkage long sys_chdir(const char __user * filename)
 	if (error)
 		goto dput_and_out;
 
-	set_fs_pwd(current->fs, nd.mnt, nd.dentry);
+	set_fs_pwd(current->fs, &nd.path);
 
 dput_and_out:
-	path_release(&nd);
+	path_put(&nd.path);
 out:
 	return error;
 }
@@ -501,9 +512,7 @@ out:
 asmlinkage long sys_fchdir(unsigned int fd)
 {
 	struct file *file;
-	struct dentry *dentry;
 	struct inode *inode;
-	struct vfsmount *mnt;
 	int error;
 
 	error = -EBADF;
@@ -511,9 +520,7 @@ asmlinkage long sys_fchdir(unsigned int fd)
 	if (!file)
 		goto out;
 
-	dentry = file->f_path.dentry;
-	mnt = file->f_path.mnt;
-	inode = dentry->d_inode;
+	inode = file->f_path.dentry->d_inode;
 
 	error = -ENOTDIR;
 	if (!S_ISDIR(inode->i_mode))
@@ -521,7 +528,7 @@ asmlinkage long sys_fchdir(unsigned int fd)
 
 	error = file_permission(file, MAY_EXEC);
 	if (!error)
-		set_fs_pwd(current->fs, mnt, dentry);
+		set_fs_pwd(current->fs, &file->f_path);
 out_putf:
 	fput(file);
 out:
@@ -545,11 +552,11 @@ asmlinkage long sys_chroot(const char __user * filename)
 	if (!capable(CAP_SYS_CHROOT))
 		goto dput_and_out;
 
-	set_fs_root(current->fs, nd.mnt, nd.dentry);
+	set_fs_root(current->fs, &nd.path);
 	set_fs_altroot();
 	error = 0;
 dput_and_out:
-	path_release(&nd);
+	path_put(&nd.path);
 out:
 	return error;
 }
@@ -571,12 +578,12 @@ asmlinkage long sys_fchmod(unsigned int fd, mode_t mode)
 
 	audit_inode(NULL, dentry);
 
-	err = -EROFS;
-	if (IS_RDONLY(inode))
+	err = mnt_want_write(file->f_path.mnt);
+	if (err)
 		goto out_putf;
 	err = -EPERM;
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
-		goto out_putf;
+		goto out_drop_write;
 	mutex_lock(&inode->i_mutex);
 	if (mode == (mode_t) -1)
 		mode = inode->i_mode;
@@ -585,6 +592,8 @@ asmlinkage long sys_fchmod(unsigned int fd, mode_t mode)
 	err = notify_change(dentry, &newattrs);
 	mutex_unlock(&inode->i_mutex);
 
+out_drop_write:
+	mnt_drop_write(file->f_path.mnt);
 out_putf:
 	fput(file);
 out:
@@ -602,26 +611,28 @@ asmlinkage long sys_fchmodat(int dfd, const char __user *filename,
 	error = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW, &nd);
 	if (error)
 		goto out;
-	inode = nd.dentry->d_inode;
+	inode = nd.path.dentry->d_inode;
 
-	error = -EROFS;
-	if (IS_RDONLY(inode))
+	error = mnt_want_write(nd.path.mnt);
+	if (error)
 		goto dput_and_out;
 
 	error = -EPERM;
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
-		goto dput_and_out;
+		goto out_drop_write;
 
 	mutex_lock(&inode->i_mutex);
 	if (mode == (mode_t) -1)
 		mode = inode->i_mode;
 	newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
 	newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-	error = notify_change(nd.dentry, &newattrs);
+	error = notify_change(nd.path.dentry, &newattrs);
 	mutex_unlock(&inode->i_mutex);
 
+out_drop_write:
+	mnt_drop_write(nd.path.mnt);
 dput_and_out:
-	path_release(&nd);
+	path_put(&nd.path);
 out:
 	return error;
 }
@@ -642,9 +653,6 @@ static int chown_common(struct dentry * dentry, uid_t user, gid_t group)
 		printk(KERN_ERR "chown_common: NULL inode\n");
 		goto out;
 	}
-	error = -EROFS;
-	if (IS_RDONLY(inode))
-		goto out;
 	error = -EPERM;
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
 		goto out;
@@ -675,8 +683,13 @@ asmlinkage long sys_chown(const char __user * filename, uid_t user, gid_t group)
 	error = user_path_walk(filename, &nd);
 	if (error)
 		goto out;
-	error = chown_common(nd.dentry, user, group);
-	path_release(&nd);
+	error = mnt_want_write(nd.path.mnt);
+	if (error)
+		goto out_release;
+	error = chown_common(nd.path.dentry, user, group);
+	mnt_drop_write(nd.path.mnt);
+out_release:
+	path_put(&nd.path);
 out:
 	return error;
 }
@@ -695,8 +708,13 @@ asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user,
 	error = __user_walk_fd(dfd, filename, follow, &nd);
 	if (error)
 		goto out;
-	error = chown_common(nd.dentry, user, group);
-	path_release(&nd);
+	error = mnt_want_write(nd.path.mnt);
+	if (error)
+		goto out_release;
+	error = chown_common(nd.path.dentry, user, group);
+	mnt_drop_write(nd.path.mnt);
+out_release:
+	path_put(&nd.path);
 out:
 	return error;
 }
@@ -709,8 +727,13 @@ asmlinkage long sys_lchown(const char __user * filename, uid_t user, gid_t group
 	error = user_path_walk_link(filename, &nd);
 	if (error)
 		goto out;
-	error = chown_common(nd.dentry, user, group);
-	path_release(&nd);
+	error = mnt_want_write(nd.path.mnt);
+	if (error)
+		goto out_release;
+	error = chown_common(nd.path.dentry, user, group);
+	mnt_drop_write(nd.path.mnt);
+out_release:
+	path_put(&nd.path);
 out:
 	return error;
 }
@@ -726,14 +749,48 @@ asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group)
 	if (!file)
 		goto out;
 
+	error = mnt_want_write(file->f_path.mnt);
+	if (error)
+		goto out_fput;
 	dentry = file->f_path.dentry;
 	audit_inode(NULL, dentry);
 	error = chown_common(dentry, user, group);
+	mnt_drop_write(file->f_path.mnt);
+out_fput:
 	fput(file);
 out:
 	return error;
 }
 
+/*
+ * You have to be very careful that these write
+ * counts get cleaned up in error cases and
+ * upon __fput().  This should probably never
+ * be called outside of __dentry_open().
+ */
+static inline int __get_file_write_access(struct inode *inode,
+					  struct vfsmount *mnt)
+{
+	int error;
+	error = get_write_access(inode);
+	if (error)
+		return error;
+	/*
+	 * Do not take mount writer counts on
+	 * special files since no writes to
+	 * the mount itself will occur.
+	 */
+	if (!special_file(inode->i_mode)) {
+		/*
+		 * Balanced in __fput()
+		 */
+		error = mnt_want_write(mnt);
+		if (error)
+			put_write_access(inode);
+	}
+	return error;
+}
+
 static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 					int flags, struct file *f,
 					int (*open)(struct inode *, struct file *))
@@ -746,9 +803,11 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 				FMODE_PREAD | FMODE_PWRITE;
 	inode = dentry->d_inode;
 	if (f->f_mode & FMODE_WRITE) {
-		error = get_write_access(inode);
+		error = __get_file_write_access(inode, mnt);
 		if (error)
 			goto cleanup_file;
+		if (!special_file(inode->i_mode))
+			file_take_write(f);
 	}
 
 	f->f_mapping = inode->i_mapping;
@@ -788,8 +847,19 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 
 cleanup_all:
 	fops_put(f->f_op);
-	if (f->f_mode & FMODE_WRITE)
+	if (f->f_mode & FMODE_WRITE) {
 		put_write_access(inode);
+		if (!special_file(inode->i_mode)) {
+			/*
+			 * We don't consider this a real
+			 * mnt_want/drop_write() pair
+			 * because it all happenend right
+			 * here, so just reset the state.
+			 */
+			file_reset_write(f);
+			mnt_drop_write(mnt);
+		}
+	}
 	file_kill(f);
 	f->f_path.dentry = NULL;
 	f->f_path.mnt = NULL;
@@ -800,43 +870,6 @@ cleanup_file:
 	return ERR_PTR(error);
 }
 
-/*
- * Note that while the flag value (low two bits) for sys_open means:
- *	00 - read-only
- *	01 - write-only
- *	10 - read-write
- *	11 - special
- * it is changed into
- *	00 - no permissions needed
- *	01 - read-permission
- *	10 - write-permission
- *	11 - read-write
- * for the internal routines (ie open_namei()/follow_link() etc). 00 is
- * used by symlinks.
- */
-static struct file *do_filp_open(int dfd, const char *filename, int flags,
-				 int mode)
-{
-	int namei_flags, error;
-	struct nameidata nd;
-
-	namei_flags = flags;
-	if ((namei_flags+1) & O_ACCMODE)
-		namei_flags++;
-
-	error = open_namei(dfd, filename, namei_flags, mode, &nd);
-	if (!error)
-		return nameidata_to_filp(&nd, flags);
-
-	return ERR_PTR(error);
-}
-
-struct file *filp_open(const char *filename, int flags, int mode)
-{
-	return do_filp_open(AT_FDCWD, filename, flags, mode);
-}
-EXPORT_SYMBOL(filp_open);
-
 /**
  * lookup_instantiate_filp - instantiates the open intent filp
  * @nd: pointer to nameidata
@@ -863,7 +896,7 @@ struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry
 		goto out;
 	if (IS_ERR(dentry))
 		goto out_err;
-	nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->mnt),
+	nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->path.mnt),
 					     nd->intent.open.flags - 1,
 					     nd->intent.open.file,
 					     open);
@@ -891,9 +924,10 @@ struct file *nameidata_to_filp(struct nameidata *nd, int flags)
 	filp = nd->intent.open.file;
 	/* Has the filesystem initialised the file for us? */
 	if (filp->f_path.dentry == NULL)
-		filp = __dentry_open(nd->dentry, nd->mnt, flags, filp, NULL);
+		filp = __dentry_open(nd->path.dentry, nd->path.mnt, flags, filp,
+				     NULL);
 	else
-		path_release(nd);
+		path_put(&nd->path);
 	return filp;
 }
 
@@ -906,6 +940,18 @@ struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags)
 	int error;
 	struct file *f;
 
+	/*
+	 * We must always pass in a valid mount pointer.   Historically
+	 * callers got away with not passing it, but we must enforce this at
+	 * the earliest possible point now to avoid strange problems deep in the
+	 * filesystem stack.
+	 */
+	if (!mnt) {
+		printk(KERN_WARNING "%s called with NULL vfsmount\n", __func__);
+		dump_stack();
+		return ERR_PTR(-EINVAL);
+	}
+
 	error = -ENFILE;
 	f = get_empty_filp();
 	if (f == NULL) {
@@ -1058,7 +1104,7 @@ asmlinkage long sys_open(const char __user *filename, int flags, int mode)
 
 	ret = do_sys_open(AT_FDCWD, filename, flags, mode);
 	/* avoid REGPARM breakage on x86: */
-	prevent_tail_call(ret);
+	asmlinkage_protect(3, ret, filename, flags, mode);
 	return ret;
 }
 
@@ -1072,7 +1118,7 @@ asmlinkage long sys_openat(int dfd, const char __user *filename, int flags,
 
 	ret = do_sys_open(dfd, filename, flags, mode);
 	/* avoid REGPARM breakage on x86: */
-	prevent_tail_call(ret);
+	asmlinkage_protect(4, ret, dfd, filename, flags, mode);
 	return ret;
 }