Seth Forshee <seth.forshee@xxxxxxxxxxxxx> writes:
> Initially this will be used to eliminate the implicit MNT_NODEV
> flag for mounts from user namespaces. In the future it will also
> be used for translating ids and checking capabilities for
> filesystems mounted from user namespaces.
>
> s_user_ns is initialized in alloc_super() and is generally set to
> current_user_ns(). To avoid security and corruption issues, two
> additional mount checks are also added:
>
> - do_new_mount() gains a check that the user has CAP_SYS_ADMIN
> in current_user_ns().
>
> - sget() will fail with EBUSY when the filesystem it's looking
> for is already mounted from another user namespace.
>
> proc requires some special handling. The user namespace of
> current isn't appropriate when forking as a result of clone (2)
> with CLONE_NEWPID|CLONE_NEWUSER, as it will set s_user_ns to the
> namespace of the parent and make proc unmountable in the new user
> namespace. Instead, the user namespace which owns the new pid
> namespace is used. sget_userns() is allowed to allow passing in
> a namespace other than that of current, and sget becomes a
> wrapper around sget_userns() which passes current_user_ns().
Minor nits below. I have fixed them up.
> Signed-off-by: Seth Forshee <seth.forshee@xxxxxxxxxxxxx>
> ---
> fs/namespace.c | 3 +++
> fs/proc/root.c | 3 ++-
> fs/super.c | 38 +++++++++++++++++++++++++++++++++-----
> include/linux/fs.h | 9 ++++++++-
> 4 files changed, 46 insertions(+), 7 deletions(-)
>
> diff --git a/fs/namespace.c b/fs/namespace.c
> index 0570729c87fd..d023a353dc63 100644
> --- a/fs/namespace.c
> +++ b/fs/namespace.c
> @@ -2381,6 +2381,9 @@ static int do_new_mount(struct path *path, const char *fstype, int flags,
> struct vfsmount *mnt;
> int err;
>
> + if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN))
> + return -EPERM;
> +
> if (!fstype)
> return -EINVAL;
>
> diff --git a/fs/proc/root.c b/fs/proc/root.c
> index 361ab4ee42fc..4b302cbf13f9 100644
> --- a/fs/proc/root.c
> +++ b/fs/proc/root.c
> @@ -117,7 +117,8 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
> return ERR_PTR(-EPERM);
> }
>
> - sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
> + sb = sget_userns(fs_type, proc_test_super, proc_set_super, flags,
> + ns->user_ns, ns);
> if (IS_ERR(sb))
> return ERR_CAST(sb);
>
> diff --git a/fs/super.c b/fs/super.c
> index 954aeb80e202..42837da7d641 100644
> --- a/fs/super.c
> +++ b/fs/super.c
> @@ -33,6 +33,7 @@
> #include <linux/cleancache.h>
> #include <linux/fsnotify.h>
> #include <linux/lockdep.h>
> +#include <linux/user_namespace.h>
> #include "internal.h"
>
>
> @@ -163,6 +164,7 @@ static void destroy_super(struct super_block *s)
> {
> list_lru_destroy(&s->s_dentry_lru);
> list_lru_destroy(&s->s_inode_lru);
> + put_user_ns(s->s_user_ns);
> security_sb_free(s);
> WARN_ON(!list_empty(&s->s_mounts));
> kfree(s->s_subtype);
> @@ -178,7 +180,8 @@ static void destroy_super(struct super_block *s)
> * Allocates and initializes a new &struct super_block. alloc_super()
> * returns a pointer new superblock or %NULL if allocation had failed.
> */
> -static struct super_block *alloc_super(struct file_system_type *type, int flags)
> +static struct super_block *alloc_super(struct file_system_type *type, int flags,
> + struct user_namespace *user_ns)
> {
> struct super_block *s = kzalloc(sizeof(struct super_block), GFP_USER);
> static const struct super_operations default_op;
> @@ -246,6 +249,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
> s->s_shrink.count_objects = super_cache_count;
> s->s_shrink.batch = 1024;
> s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;
> +
> + s->s_user_ns = get_user_ns(user_ns);
> return s;
>
> fail:
> @@ -442,17 +447,17 @@ void generic_shutdown_super(struct super_block *sb)
> EXPORT_SYMBOL(generic_shutdown_super);
>
> /**
> - * sget - find or create a superblock
> + * sget_userns - find or create a superblock
> * @type: filesystem type superblock should belong to
> * @test: comparison callback
> * @set: setup callback
> * @flags: mount flags
You don't mention the user namespace parameter here. I have fixed that
as.
+ * @user_ns: User namespace you need CAP_SYS_ADMIN over to mount this fs.
> * @data: argument to each of them
> */
> -struct super_block *sget(struct file_system_type *type,
> +struct super_block *sget_userns(struct file_system_type *type,
> int (*test)(struct super_block *,void *),
> int (*set)(struct super_block *,void *),
> - int flags,
> + int flags, struct user_namespace *user_ns,
> void *data)
> {
> struct super_block *s = NULL;
> @@ -465,6 +470,10 @@ retry:
> hlist_for_each_entry(old, &type->fs_supers, s_instances) {
> if (!test(old, data))
> continue;
> + if (user_ns != old->s_user_ns) {
> + spin_unlock(&sb_lock);
> + return ERR_PTR(-EBUSY);
> + }
> if (!grab_super(old))
> goto retry;
> if (s) {
> @@ -477,7 +486,7 @@ retry:
> }
> if (!s) {
> spin_unlock(&sb_lock);
> - s = alloc_super(type, flags);
> + s = alloc_super(type, flags, user_ns);
> if (!s)
> return ERR_PTR(-ENOMEM);
> goto retry;
> @@ -500,6 +509,25 @@ retry:
> return s;
> }
>
> +EXPORT_SYMBOL(sget_userns);
> +
> +/**
> + * sget - find or create a superblock
> + * @type: filesystem type superblock should belong to
> + * @test: comparison callback
> + * @set: setup callback
> + * @flags: mount flags
> + * @data: argument to each of them
> + */
> +struct super_block *sget(struct file_system_type *type,
> + int (*test)(struct super_block *,void *),
> + int (*set)(struct super_block *,void *),
> + int flags,
> + void *data)
> +{
> + return sget_userns(type, test, set, flags, current_user_ns(), data);
> +}
> +
> EXPORT_SYMBOL(sget);
>
> void drop_super(struct super_block *sb)
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 72d8a844c692..79c15ab2159d 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -31,6 +31,7 @@
> #include <linux/blk_types.h>
> #include <linux/workqueue.h>
> #include <linux/percpu-rwsem.h>
> +#include <linux/user_namespace.h>
>
> #include <asm/byteorder.h>
> #include <uapi/linux/fs.h>
> @@ -1367,6 +1368,8 @@ struct super_block {
> struct workqueue_struct *s_dio_done_wq;
> struct hlist_head s_pins;
>
> + struct user_namespace *s_user_ns;
> +
> /*
> * Keep the lru lists last in the structure so they always sit on their
> * own individual cachelines.
> @@ -1509,7 +1512,6 @@ static inline void sb_start_intwrite(struct super_block *sb)
> __sb_start_write(sb, SB_FREEZE_FS, true);
> }
>
> -
You are unncessarily deleting a line here.
> extern bool inode_owner_or_capable(const struct inode *inode);
>
> /*
> @@ -1984,6 +1986,11 @@ void deactivate_locked_super(struct super_block *sb);
> int set_anon_super(struct super_block *s, void *data);
> int get_anon_bdev(dev_t *);
> void free_anon_bdev(dev_t);
> +struct super_block *sget_userns(struct file_system_type *type,
> + int (*test)(struct super_block *,void *),
> + int (*set)(struct super_block *,void *),
> + int flags, struct user_namespace *user_ns,
> + void *data);
> struct super_block *sget(struct file_system_type *type,
> int (*test)(struct super_block *,void *),
> int (*set)(struct super_block *,void *),
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
