Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932383AbbGPCQY (ORCPT ); Wed, 15 Jul 2015 22:16:24 -0400 Received: from youngberry.canonical.com ([91.189.89.112]:55312 "EHLO youngberry.canonical.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754209AbbGPBKI (ORCPT ); Wed, 15 Jul 2015 21:10:08 -0400 From: Kamal Mostafa To: linux-kernel@vger.kernel.org, stable@vger.kernel.org, kernel-team@lists.ubuntu.com Cc: "Eric W. Biederman" , Kamal Mostafa Subject: [PATCH 3.19.y-ckt 040/251] mnt: Refactor the logic for mounting sysfs and proc in a user namespace Date: Wed, 15 Jul 2015 18:06:01 -0700 Message-Id: <1437008972-9140-41-git-send-email-kamal@canonical.com> X-Mailer: git-send-email 1.9.1 In-Reply-To: <1437008972-9140-1-git-send-email-kamal@canonical.com> References: <1437008972-9140-1-git-send-email-kamal@canonical.com> X-Extended-Stable: 3.19 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4633 Lines: 136 3.19.8-ckt4 -stable review patch. If anyone has any objections, please let me know. ------------------ From: "Eric W. Biederman" commit 1b852bceb0d111e510d1a15826ecc4a19358d512 upstream. Fresh mounts of proc and sysfs are a very special case that works very much like a bind mount. Unfortunately the current structure can not preserve the MNT_LOCK... mount flags. Therefore refactor the logic into a form that can be modified to preserve those lock bits. Add a new filesystem flag FS_USERNS_VISIBLE that requires some mount of the filesystem be fully visible in the current mount namespace, before the filesystem may be mounted. Move the logic for calling fs_fully_visible from proc and sysfs into fs/namespace.c where it has greater access to mount namespace state. Signed-off-by: "Eric W. Biederman" Signed-off-by: Kamal Mostafa --- fs/namespace.c | 8 +++++++- fs/proc/root.c | 5 +---- fs/sysfs/mount.c | 5 +---- include/linux/fs.h | 2 +- 4 files changed, 10 insertions(+), 10 deletions(-) diff --git a/fs/namespace.c b/fs/namespace.c index 8129c51..7fd1659 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2293,6 +2293,8 @@ unlock: return err; } +static bool fs_fully_visible(struct file_system_type *fs_type); + /* * create a new mount for userspace and request it to be added into the * namespace's tree @@ -2324,6 +2326,10 @@ static int do_new_mount(struct path *path, const char *fstype, int flags, flags |= MS_NODEV; mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV; } + if (type->fs_flags & FS_USERNS_VISIBLE) { + if (!fs_fully_visible(type)) + return -EPERM; + } } mnt = vfs_kern_mount(type, flags, name, data); @@ -3125,7 +3131,7 @@ bool current_chrooted(void) return chrooted; } -bool fs_fully_visible(struct file_system_type *type) +static bool fs_fully_visible(struct file_system_type *type) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct mount *mnt; diff --git a/fs/proc/root.c b/fs/proc/root.c index e74ac9f..eeb04f3 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -112,9 +112,6 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, ns = task_active_pid_ns(current); options = data; - if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) - return ERR_PTR(-EPERM); - /* Does the mounter have privilege over the pid namespace? */ if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); @@ -159,7 +156,7 @@ static struct file_system_type proc_fs_type = { .name = "proc", .mount = proc_mount, .kill_sb = proc_kill_sb, - .fs_flags = FS_USERNS_MOUNT, + .fs_flags = FS_USERNS_VISIBLE | FS_USERNS_MOUNT, }; void __init proc_root_init(void) diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 8a49486..1c6ac6f 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -31,9 +31,6 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, bool new_sb; if (!(flags & MS_KERNMOUNT)) { - if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) - return ERR_PTR(-EPERM); - if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET)) return ERR_PTR(-EPERM); } @@ -58,7 +55,7 @@ static struct file_system_type sysfs_fs_type = { .name = "sysfs", .mount = sysfs_mount, .kill_sb = sysfs_kill_sb, - .fs_flags = FS_USERNS_MOUNT, + .fs_flags = FS_USERNS_VISIBLE | FS_USERNS_MOUNT, }; int __init sysfs_init(void) diff --git a/include/linux/fs.h b/include/linux/fs.h index 42efe13..eba0c7d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1817,6 +1817,7 @@ struct file_system_type { #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_USERNS_DEV_MOUNT 16 /* A userns mount does not imply MNT_NODEV */ +#define FS_USERNS_VISIBLE 32 /* FS must already be visible */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); @@ -1904,7 +1905,6 @@ extern int vfs_ustat(dev_t, struct kstatfs *); extern int freeze_super(struct super_block *super); extern int thaw_super(struct super_block *super); extern bool our_mnt(struct vfsmount *mnt); -extern bool fs_fully_visible(struct file_system_type *); extern int current_umask(void); -- 1.9.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/