From 1b18dc2beb31f588db1c75901b0112324c72124f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 21 Aug 2013 16:28:26 -0700 Subject: sysfs: fix up space coding style issues This fixes up all of the space-related coding style issues for the sysfs code. Signed-off-by: Greg Kroah-Hartman --- fs/sysfs/mount.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/sysfs/mount.c') diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index afd83273e6c..fd7ce7a39f9 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -64,7 +64,7 @@ static int sysfs_fill_super(struct super_block *sb, void *data, int silent) /* instantiate and link root dentry */ root = d_make_root(inode); if (!root) { - pr_debug("%s: could not get root dentry!\n",__func__); + pr_debug("%s: could not get root dentry!\n", __func__); return -ENOMEM; } root->d_fsdata = &sysfs_root; -- cgit v1.2.3-70-g09d2 From e51db73532955dc5eaba4235e62b74b460709d5b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 30 Mar 2013 19:57:41 -0700 Subject: userns: Better restrictions on when proc and sysfs can be mounted Rely on the fact that another flavor of the filesystem is already mounted and do not rely on state in the user namespace. Verify that the mounted filesystem is not covered in any significant way. I would love to verify that the previously mounted filesystem has no mounts on top but there are at least the directories /proc/sys/fs/binfmt_misc and /sys/fs/cgroup/ that exist explicitly for other filesystems to mount on top of. Refactor the test into a function named fs_fully_visible and call that function from the mount routines of proc and sysfs. This makes this test local to the filesystems involved and the results current of when the mounts take place, removing a weird threading of the user namespace, the mount namespace and the filesystems themselves. Signed-off-by: "Eric W. Biederman" --- fs/namespace.c | 37 +++++++++++++++++++++++++------------ fs/proc/root.c | 7 +++++-- fs/sysfs/mount.c | 3 ++- include/linux/fs.h | 1 + include/linux/user_namespace.h | 4 ---- kernel/user.c | 2 -- kernel/user_namespace.c | 2 -- 7 files changed, 33 insertions(+), 23 deletions(-) (limited to 'fs/sysfs/mount.c') diff --git a/fs/namespace.c b/fs/namespace.c index 64627f883bf..877e4277f49 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2867,25 +2867,38 @@ bool current_chrooted(void) return chrooted; } -void update_mnt_policy(struct user_namespace *userns) +bool fs_fully_visible(struct file_system_type *type) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct mount *mnt; + bool visible = false; - down_read(&namespace_sem); + if (unlikely(!ns)) + return false; + + namespace_lock(); list_for_each_entry(mnt, &ns->list, mnt_list) { - switch (mnt->mnt.mnt_sb->s_magic) { - case SYSFS_MAGIC: - userns->may_mount_sysfs = true; - break; - case PROC_SUPER_MAGIC: - userns->may_mount_proc = true; - break; + struct mount *child; + if (mnt->mnt.mnt_sb->s_type != type) + continue; + + /* This mount is not fully visible if there are any child mounts + * that cover anything except for empty directories. + */ + list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { + struct inode *inode = child->mnt_mountpoint->d_inode; + if (!S_ISDIR(inode->i_mode)) + goto next; + if (inode->i_nlink != 2) + goto next; } - if (userns->may_mount_sysfs && userns->may_mount_proc) - break; + visible = true; + goto found; + next: ; } - up_read(&namespace_sem); +found: + namespace_unlock(); + return visible; } static void *mntns_get(struct task_struct *task) diff --git a/fs/proc/root.c b/fs/proc/root.c index 38bd5d423fc..45e5fb7da09 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -110,8 +110,11 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, ns = task_active_pid_ns(current); options = data; - if (!current_user_ns()->may_mount_proc || - !ns_capable(ns->user_ns, CAP_SYS_ADMIN)) + 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); } diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index afd83273e6c..4a2da3a4b1b 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -112,7 +112,8 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, struct super_block *sb; int error; - if (!(flags & MS_KERNMOUNT) && !current_user_ns()->may_mount_sysfs) + if (!(flags & MS_KERNMOUNT) && !capable(CAP_SYS_ADMIN) && + !fs_fully_visible(fs_type)) return ERR_PTR(-EPERM); info = kzalloc(sizeof(*info), GFP_KERNEL); diff --git a/include/linux/fs.h b/include/linux/fs.h index 981874773e8..3050c620f06 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1897,6 +1897,7 @@ 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); diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index b6b215f13b4..4ce00932493 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -26,8 +26,6 @@ struct user_namespace { kuid_t owner; kgid_t group; unsigned int proc_inum; - bool may_mount_sysfs; - bool may_mount_proc; }; extern struct user_namespace init_user_ns; @@ -84,6 +82,4 @@ static inline void put_user_ns(struct user_namespace *ns) #endif -void update_mnt_policy(struct user_namespace *userns); - #endif /* _LINUX_USER_H */ diff --git a/kernel/user.c b/kernel/user.c index 69b4c3d48cd..5bbb91988e6 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -51,8 +51,6 @@ struct user_namespace init_user_ns = { .owner = GLOBAL_ROOT_UID, .group = GLOBAL_ROOT_GID, .proc_inum = PROC_USER_INIT_INO, - .may_mount_sysfs = true, - .may_mount_proc = true, }; EXPORT_SYMBOL_GPL(init_user_ns); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index d8c30db06c5..d58ad1e7a79 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -97,8 +97,6 @@ int create_user_ns(struct cred *new) set_cred_user_ns(new, ns); - update_mnt_policy(ns); - return 0; } -- cgit v1.2.3-70-g09d2 From 7dc5dbc879bd0779924b5132a48b731a0bc04a1e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 25 Mar 2013 20:07:01 -0700 Subject: sysfs: Restrict mounting sysfs Don't allow mounting sysfs unless the caller has CAP_SYS_ADMIN rights over the net namespace. The principle here is if you create or have capabilities over it you can mount it, otherwise you get to live with what other people have mounted. Instead of testing this with a straight forward ns_capable call, perform this check the long and torturous way with kobject helpers, this keeps direct knowledge of namespaces out of sysfs, and preserves the existing sysfs abstractions. Acked-by: Greg Kroah-Hartman Signed-off-by: "Eric W. Biederman" --- fs/sysfs/mount.c | 12 +++++++++--- include/linux/kobject_ns.h | 2 ++ lib/kobject.c | 15 +++++++++++++++ net/core/net-sysfs.c | 8 ++++++++ 4 files changed, 34 insertions(+), 3 deletions(-) (limited to 'fs/sysfs/mount.c') diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 4a2da3a4b1b..8c69ef49c7f 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -112,9 +112,15 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, struct super_block *sb; int error; - if (!(flags & MS_KERNMOUNT) && !capable(CAP_SYS_ADMIN) && - !fs_fully_visible(fs_type)) - return ERR_PTR(-EPERM); + if (!(flags & MS_KERNMOUNT)) { + if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) + return ERR_PTR(-EPERM); + + for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) { + if (!kobj_ns_current_may_mount(type)) + return ERR_PTR(-EPERM); + } + } info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h index f66b065a8b5..df32d250829 100644 --- a/include/linux/kobject_ns.h +++ b/include/linux/kobject_ns.h @@ -39,6 +39,7 @@ enum kobj_ns_type { */ struct kobj_ns_type_operations { enum kobj_ns_type type; + bool (*current_may_mount)(void); void *(*grab_current_ns)(void); const void *(*netlink_ns)(struct sock *sk); const void *(*initial_ns)(void); @@ -50,6 +51,7 @@ int kobj_ns_type_registered(enum kobj_ns_type type); const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent); const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj); +bool kobj_ns_current_may_mount(enum kobj_ns_type type); void *kobj_ns_grab_current(enum kobj_ns_type type); const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk); const void *kobj_ns_initial(enum kobj_ns_type type); diff --git a/lib/kobject.c b/lib/kobject.c index 4a1f33d4354..3bbde222c90 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -915,6 +915,21 @@ const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj) return kobj_child_ns_ops(kobj->parent); } +bool kobj_ns_current_may_mount(enum kobj_ns_type type) +{ + bool may_mount = false; + + if (type == KOBJ_NS_TYPE_NONE) + return true; + + spin_lock(&kobj_ns_type_lock); + if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) && + kobj_ns_ops_tbl[type]) + may_mount = kobj_ns_ops_tbl[type]->current_may_mount(); + spin_unlock(&kobj_ns_type_lock); + + return may_mount; +} void *kobj_ns_grab_current(enum kobj_ns_type type) { diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 981fed397d1..9bd9ae16adf 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1157,6 +1157,13 @@ static void remove_queue_kobjects(struct net_device *net) #endif } +static bool net_current_may_mount(void) +{ + struct net *net = current->nsproxy->net_ns; + + return ns_capable(net->user_ns, CAP_SYS_ADMIN); +} + static void *net_grab_current_ns(void) { struct net *ns = current->nsproxy->net_ns; @@ -1179,6 +1186,7 @@ static const void *net_netlink_ns(struct sock *sk) struct kobj_ns_type_operations net_ns_type_operations = { .type = KOBJ_NS_TYPE_NET, + .current_may_mount = net_current_may_mount, .grab_current_ns = net_grab_current_ns, .netlink_ns = net_netlink_ns, .initial_ns = net_initial_ns, -- cgit v1.2.3-70-g09d2