diff mbox series

[v2,07/25] capability: provide a helper for converting vfs_caps to xattr for userspace

Message ID 20240221-idmap-fscap-refactor-v2-7-3039364623bd@kernel.org
State New
Headers
Series fs: use type-safe uid representation for filesystem capabilities |

Commit Message

Seth Forshee (DigitalOcean) Feb. 21, 2024, 9:24 p.m. UTC 
  cap_inode_getsecurity() implements a handful of policies for capability
xattrs read by userspace:

 - It returns EINVAL if the on-disk capability is in v1 format.

 - It masks off all bits in magic_etc except for the version and
   VFS_CAP_FLAGS_EFFECTIVE.

 - v3 capabilities are converted to v2 format if the rootid returned to
   userspace would be 0 or if the rootid corresponds to root in an
   ancestor user namespace.

 - It returns EOVERFLOW for a v3 capability whose rootid does not map to
   a valid id in current_user_ns() or to root in an ancestor namespace.

These policies must be maintained when converting vfs_caps to an xattr
for userspace. Provide a vfs_caps_to_user_xattr() helper which will
enforce these policies.

Signed-off-by: Seth Forshee (DigitalOcean) <sforshee@kernel.org>
---
 include/linux/capability.h |  4 +++
 security/commoncap.c       | 78 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 82 insertions(+)

Comments

Christian Brauner Feb. 22, 2024, 3:22 p.m. UTC | #1 
On Wed, Feb 21, 2024 at 03:24:38PM -0600, Seth Forshee (DigitalOcean) wrote:
> cap_inode_getsecurity() implements a handful of policies for capability
> xattrs read by userspace:
> 
>  - It returns EINVAL if the on-disk capability is in v1 format.
> 
>  - It masks off all bits in magic_etc except for the version and
>    VFS_CAP_FLAGS_EFFECTIVE.
> 
>  - v3 capabilities are converted to v2 format if the rootid returned to
>    userspace would be 0 or if the rootid corresponds to root in an
>    ancestor user namespace.
> 
>  - It returns EOVERFLOW for a v3 capability whose rootid does not map to
>    a valid id in current_user_ns() or to root in an ancestor namespace.
> 
> These policies must be maintained when converting vfs_caps to an xattr
> for userspace. Provide a vfs_caps_to_user_xattr() helper which will
> enforce these policies.
> 
> Signed-off-by: Seth Forshee (DigitalOcean) <sforshee@kernel.org>
> ---

Looks good,
Reviewed-by: Christian Brauner <brauner@kernel.org>
diff mbox series

Patch

diff --git a/include/linux/capability.h b/include/linux/capability.h
index a0893ac4664b..eb06d7c6224b 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -218,6 +218,10 @@  ssize_t vfs_caps_to_xattr(struct mnt_idmap *idmap,
 			  struct user_namespace *dest_userns,
 			  const struct vfs_caps *vfs_caps,
 			  void *data, size_t size);
+ssize_t vfs_caps_to_user_xattr(struct mnt_idmap *idmap,
+			       struct user_namespace *dest_userns,
+			       const struct vfs_caps *vfs_caps,
+			       void *data, size_t size);
 
 /* audit system wants to get cap info from files as well */
 int get_vfs_caps_from_disk(struct mnt_idmap *idmap,
diff --git a/security/commoncap.c b/security/commoncap.c
index 7531c9634997..289530e58c37 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -791,6 +791,84 @@  ssize_t vfs_caps_to_xattr(struct mnt_idmap *idmap,
 	return ret;
 }
 
+/**
+ * vfs_caps_to_user_xattr - convert vfs_caps to caps xattr for userspace
+ *
+ * @idmap:       idmap of the mount the inode was found from
+ * @dest_userns: user namespace for ids in xattr data
+ * @vfs_caps:    source vfs_caps data
+ * @data:        destination buffer for rax xattr caps data
+ * @size:        size of the @data buffer
+ *
+ * Converts a kernel-internal capability into the raw security.capability
+ * xattr format. Implements the following policies required for fscaps
+ * returned to userspace:
+ *
+ *  - Returns -EINVAL if the on-disk capability is in v1 format.
+ *  - Masks off all bits in magic_etc except for the version and
+ *    VFS_CAP_FLAGS_EFFECTIVE.
+ *  - Converts v3 capabilities to v2 format if the rootid returned to
+ *    userspace would be 0 or if the rootid corresponds to root in an
+ *    ancestor user namespace.
+ *  - Returns EOVERFLOW for a v3 capability whose rootid does not map to a
+ *    valid id in current_user_ns() or to root in an ancestor namespace.
+ *
+ * If the xattr is being read or written through an idmapped mount the
+ * idmap of the vfsmount must be passed through @idmap. This function
+ * will then take care to map the rootid according to @idmap.
+ *
+ * Return: On success, return the size of the xattr data. On error,
+ * return < 0.
+ */
+ssize_t vfs_caps_to_user_xattr(struct mnt_idmap *idmap,
+			       struct user_namespace *dest_userns,
+			       const struct vfs_caps *vfs_caps,
+			       void *data, size_t size)
+{
+	struct vfs_ns_cap_data *ns_caps = data;
+	bool is_v3;
+	u32 magic;
+
+	/* Preserve previous behavior of returning EINVAL for v1 caps */
+	if ((vfs_caps->magic_etc & VFS_CAP_REVISION_MASK) == VFS_CAP_REVISION_1)
+		return -EINVAL;
+
+	size = __vfs_caps_to_xattr(idmap, dest_userns, vfs_caps, data, size);
+	if (size < 0)
+		return size;
+
+	magic = vfs_caps->magic_etc &
+		(VFS_CAP_REVISION_MASK | VFS_CAP_FLAGS_EFFECTIVE);
+	ns_caps->magic_etc = cpu_to_le32(magic);
+
+	/*
+	 * If this is a v3 capability with a valid, non-zero rootid, return
+	 * the v3 capability to userspace. A v3 capability with a rootid of
+	 * 0 will be converted to a v2 capability below for compatibility
+	 * with old userspace.
+	 */
+	is_v3 = (vfs_caps->magic_etc & VFS_CAP_REVISION_MASK) == VFS_CAP_REVISION_3;
+	if (is_v3) {
+		uid_t rootid = le32_to_cpu(ns_caps->rootid);
+		if (rootid != (uid_t)-1 && rootid != (uid_t)0)
+			return size;
+	}
+
+	if (!rootid_owns_currentns(vfs_caps->rootid))
+		return -EOVERFLOW;
+
+	/* This comes from a parent namespace. Return as a v2 capability. */
+	if (is_v3) {
+		magic = VFS_CAP_REVISION_2 |
+			(vfs_caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE);
+		ns_caps->magic_etc = cpu_to_le32(magic);
+		ns_caps->rootid = cpu_to_le32(0);
+		size = XATTR_CAPS_SZ_2;
+	}
+
+	return size;
+}
+
 /**
  * get_vfs_caps_from_disk - retrieve vfs caps from disk
  *