diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-02-20 22:53:11 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-02-20 22:53:11 +0300 |
commit | 05e6295f7b5e05f09e369a3eb2882ec5b40fff20 (patch) | |
tree | 60ea7c6806f58371bfafe6317089c7ae1a65fca4 /fs/namespace.c | |
parent | de630176bdf885eed442902afe94eb60d8f5f826 (diff) | |
parent | 7a80e5b8c6fa7d0ae6624bd6aedc4a6a1cfc62fa (diff) | |
download | linux-05e6295f7b5e05f09e369a3eb2882ec5b40fff20.tar.xz |
Merge tag 'fs.idmapped.v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping
Pull vfs idmapping updates from Christian Brauner:
- Last cycle we introduced the dedicated struct mnt_idmap type for
mount idmapping and the required infrastucture in 256c8aed2b42 ("fs:
introduce dedicated idmap type for mounts"). As promised in last
cycle's pull request message this converts everything to rely on
struct mnt_idmap.
Currently we still pass around the plain namespace that was attached
to a mount. This is in general pretty convenient but it makes it easy
to conflate namespaces that are relevant on the filesystem with
namespaces that are relevant on the mount level. Especially for
non-vfs developers without detailed knowledge in this area this was a
potential source for bugs.
This finishes the conversion. Instead of passing the plain namespace
around this updates all places that currently take a pointer to a
mnt_userns with a pointer to struct mnt_idmap.
Now that the conversion is done all helpers down to the really
low-level helpers only accept a struct mnt_idmap argument instead of
two namespace arguments.
Conflating mount and other idmappings will now cause the compiler to
complain loudly thus eliminating the possibility of any bugs. This
makes it impossible for filesystem developers to mix up mount and
filesystem idmappings as they are two distinct types and require
distinct helpers that cannot be used interchangeably.
Everything associated with struct mnt_idmap is moved into a single
separate file. With that change no code can poke around in struct
mnt_idmap. It can only be interacted with through dedicated helpers.
That means all filesystems are and all of the vfs is completely
oblivious to the actual implementation of idmappings.
We are now also able to extend struct mnt_idmap as we see fit. For
example, we can decouple it completely from namespaces for users that
don't require or don't want to use them at all. We can also extend
the concept of idmappings so we can cover filesystem specific
requirements.
In combination with the vfs{g,u}id_t work we finished in v6.2 this
makes this feature substantially more robust and thus difficult to
implement wrong by a given filesystem and also protects the vfs.
- Enable idmapped mounts for tmpfs and fulfill a longstanding request.
A long-standing request from users had been to make it possible to
create idmapped mounts for tmpfs. For example, to share the host's
tmpfs mount between multiple sandboxes. This is a prerequisite for
some advanced Kubernetes cases. Systemd also has a range of use-cases
to increase service isolation. And there are more users of this.
However, with all of the other work going on this was way down on the
priority list but luckily someone other than ourselves picked this
up.
As usual the patch is tiny as all the infrastructure work had been
done multiple kernel releases ago. In addition to all the tests that
we already have I requested that Rodrigo add a dedicated tmpfs
testsuite for idmapped mounts to xfstests. It is to be included into
xfstests during the v6.3 development cycle. This should add a slew of
additional tests.
* tag 'fs.idmapped.v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping: (26 commits)
shmem: support idmapped mounts for tmpfs
fs: move mnt_idmap
fs: port vfs{g,u}id helpers to mnt_idmap
fs: port fs{g,u}id helpers to mnt_idmap
fs: port i_{g,u}id_into_vfs{g,u}id() to mnt_idmap
fs: port i_{g,u}id_{needs_}update() to mnt_idmap
quota: port to mnt_idmap
fs: port privilege checking helpers to mnt_idmap
fs: port inode_owner_or_capable() to mnt_idmap
fs: port inode_init_owner() to mnt_idmap
fs: port acl to mnt_idmap
fs: port xattr to mnt_idmap
fs: port ->permission() to pass mnt_idmap
fs: port ->fileattr_set() to pass mnt_idmap
fs: port ->set_acl() to pass mnt_idmap
fs: port ->get_acl() to pass mnt_idmap
fs: port ->tmpfile() to pass mnt_idmap
fs: port ->rename() to pass mnt_idmap
fs: port ->mknod() to pass mnt_idmap
fs: port ->mkdir() to pass mnt_idmap
...
Diffstat (limited to 'fs/namespace.c')
-rw-r--r-- | fs/namespace.c | 118 |
1 files changed, 2 insertions, 116 deletions
diff --git a/fs/namespace.c b/fs/namespace.c index ab467ee58341..5927d90e24a0 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -75,22 +75,6 @@ static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ -struct mnt_idmap { - struct user_namespace *owner; - refcount_t count; -}; - -/* - * Carries the initial idmapping of 0:0:4294967295 which is an identity - * mapping. This means that {g,u}id 0 is mapped to {g,u}id 0, {g,u}id 1 is - * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...]. - */ -struct mnt_idmap nop_mnt_idmap = { - .owner = &init_user_ns, - .count = REFCOUNT_INIT(1), -}; -EXPORT_SYMBOL_GPL(nop_mnt_idmap); - struct mount_kattr { unsigned int attr_set; unsigned int attr_clr; @@ -210,104 +194,6 @@ int mnt_get_count(struct mount *mnt) #endif } -/** - * mnt_idmap_owner - retrieve owner of the mount's idmapping - * @idmap: mount idmapping - * - * This helper will go away once the conversion to use struct mnt_idmap - * everywhere has finished at which point the helper will be unexported. - * - * Only code that needs to perform permission checks based on the owner of the - * idmapping will get access to it. All other code will solely rely on - * idmappings. This will get us type safety so it's impossible to conflate - * filesystems idmappings with mount idmappings. - * - * Return: The owner of the idmapping. - */ -struct user_namespace *mnt_idmap_owner(const struct mnt_idmap *idmap) -{ - return idmap->owner; -} -EXPORT_SYMBOL_GPL(mnt_idmap_owner); - -/** - * mnt_user_ns - retrieve owner of an idmapped mount - * @mnt: the relevant vfsmount - * - * This helper will go away once the conversion to use struct mnt_idmap - * everywhere has finished at which point the helper will be unexported. - * - * Only code that needs to perform permission checks based on the owner of the - * idmapping will get access to it. All other code will solely rely on - * idmappings. This will get us type safety so it's impossible to conflate - * filesystems idmappings with mount idmappings. - * - * Return: The owner of the idmapped. - */ -struct user_namespace *mnt_user_ns(const struct vfsmount *mnt) -{ - struct mnt_idmap *idmap = mnt_idmap(mnt); - - /* Return the actual owner of the filesystem instead of the nop. */ - if (idmap == &nop_mnt_idmap && - !initial_idmapping(mnt->mnt_sb->s_user_ns)) - return mnt->mnt_sb->s_user_ns; - return mnt_idmap_owner(idmap); -} -EXPORT_SYMBOL_GPL(mnt_user_ns); - -/** - * alloc_mnt_idmap - allocate a new idmapping for the mount - * @mnt_userns: owning userns of the idmapping - * - * Allocate a new struct mnt_idmap which carries the idmapping of the mount. - * - * Return: On success a new idmap, on error an error pointer is returned. - */ -static struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns) -{ - struct mnt_idmap *idmap; - - idmap = kzalloc(sizeof(struct mnt_idmap), GFP_KERNEL_ACCOUNT); - if (!idmap) - return ERR_PTR(-ENOMEM); - - idmap->owner = get_user_ns(mnt_userns); - refcount_set(&idmap->count, 1); - return idmap; -} - -/** - * mnt_idmap_get - get a reference to an idmapping - * @idmap: the idmap to bump the reference on - * - * If @idmap is not the @nop_mnt_idmap bump the reference count. - * - * Return: @idmap with reference count bumped if @not_mnt_idmap isn't passed. - */ -static inline struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap) -{ - if (idmap != &nop_mnt_idmap) - refcount_inc(&idmap->count); - - return idmap; -} - -/** - * mnt_idmap_put - put a reference to an idmapping - * @idmap: the idmap to put the reference on - * - * If this is a non-initial idmapping, put the reference count when a mount is - * released and free it if we're the last user. - */ -static inline void mnt_idmap_put(struct mnt_idmap *idmap) -{ - if (idmap != &nop_mnt_idmap && refcount_dec_and_test(&idmap->count)) { - put_user_ns(idmap->owner); - kfree(idmap); - } -} - static struct mount *alloc_vfsmnt(const char *name) { struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL); @@ -4094,7 +3980,7 @@ static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) * Creating an idmapped mount with the filesystem wide idmapping * doesn't make sense so block that. We don't allow mushy semantics. */ - if (mnt_idmap_owner(kattr->mnt_idmap) == fs_userns) + if (!check_fsmapping(kattr->mnt_idmap, m->mnt_sb)) return -EINVAL; /* @@ -4340,7 +4226,7 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, * result. */ mnt_userns = container_of(ns, struct user_namespace, ns); - if (initial_idmapping(mnt_userns)) { + if (mnt_userns == &init_user_ns) { err = -EPERM; goto out_fput; } |