1 files changed, 56 insertions, 61 deletions

diff --git a/security/commoncap.c b/security/commoncap.c
index 1164278b97fd..5bb7d1e96277 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -305,24 +305,24 @@ int cap_inode_need_killpriv(struct dentry *dentry)
 /**
  * cap_inode_killpriv - Erase the security markings on an inode
  *
- * @mnt_userns:	user namespace of the mount the inode was found from
+ * @idmap:	idmap of the mount the inode was found from
  * @dentry:	The inode/dentry to alter
  *
  * Erase the privilege-enhancing security markings on an inode.
  *
- * If the inode has been found through an idmapped mount the user namespace of
- * the vfsmount must be passed through @mnt_userns. This function will then
- * take care to map the inode according to @mnt_userns before checking
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs init_user_ns.
+ * performed on the raw inode simply passs @nop_mnt_idmap.
  *
  * Return: 0 if successful, -ve on error.
  */
-int cap_inode_killpriv(struct user_namespace *mnt_userns, struct dentry *dentry)
+int cap_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry)
 {
 	int error;
 
-	error = __vfs_removexattr(mnt_userns, dentry, XATTR_NAME_CAPS);
+	error = __vfs_removexattr(idmap, dentry, XATTR_NAME_CAPS);
 	if (error == -EOPNOTSUPP)
 		error = 0;
 	return error;
@@ -377,7 +377,7 @@ static bool is_v3header(int size, const struct vfs_cap_data *cap)
  * by the integrity subsystem, which really wants the unconverted values -
  * so that's good.
  */
-int cap_inode_getsecurity(struct user_namespace *mnt_userns,
+int cap_inode_getsecurity(struct mnt_idmap *idmap,
 			  struct inode *inode, const char *name, void **buffer,
 			  bool alloc)
 {
@@ -398,7 +398,7 @@ int cap_inode_getsecurity(struct user_namespace *mnt_userns,
 	dentry = d_find_any_alias(inode);
 	if (!dentry)
 		return -EINVAL;
-	size = vfs_getxattr_alloc(mnt_userns, dentry, XATTR_NAME_CAPS, &tmpbuf,
+	size = vfs_getxattr_alloc(idmap, dentry, XATTR_NAME_CAPS, &tmpbuf,
 				  sizeof(struct vfs_ns_cap_data), GFP_NOFS);
 	dput(dentry);
 	/* gcc11 complains if we don't check for !tmpbuf */
@@ -420,7 +420,7 @@ int cap_inode_getsecurity(struct user_namespace *mnt_userns,
 	kroot = make_kuid(fs_ns, root);
 
 	/* If this is an idmapped mount shift the kuid. */
-	vfsroot = make_vfsuid(mnt_userns, fs_ns, kroot);
+	vfsroot = make_vfsuid(idmap, fs_ns, kroot);
 
 	/* If the root kuid maps to a valid uid in current ns, then return
 	 * this as a nscap. */
@@ -510,7 +510,7 @@ static bool validheader(size_t size, const struct vfs_cap_data *cap)
 /**
  * cap_convert_nscap - check vfs caps
  *
- * @mnt_userns:	user namespace of the mount the inode was found from
+ * @idmap:	idmap of the mount the inode was found from
  * @dentry:	used to retrieve inode to check permissions on
  * @ivalue:	vfs caps value which may be modified by this function
  * @size:	size of @ivalue
@@ -518,15 +518,15 @@ static bool validheader(size_t size, const struct vfs_cap_data *cap)
  * User requested a write of security.capability.  If needed, update the
  * xattr to change from v2 to v3, or to fixup the v3 rootid.
  *
- * If the inode has been found through an idmapped mount the user namespace of
- * the vfsmount must be passed through @mnt_userns. This function will then
- * take care to map the inode according to @mnt_userns before checking
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs init_user_ns.
+ * performed on the raw inode simply passs @nop_mnt_idmap.
  *
  * Return: On success, return the new size; on error, return < 0.
  */
-int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry,
+int cap_convert_nscap(struct mnt_idmap *idmap, struct dentry *dentry,
 		      const void **ivalue, size_t size)
 {
 	struct vfs_ns_cap_data *nscap;
@@ -544,9 +544,9 @@ int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry,
 		return -EINVAL;
 	if (!validheader(size, cap))
 		return -EINVAL;
-	if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP))
+	if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP))
 		return -EPERM;
-	if (size == XATTR_CAPS_SZ_2 && (mnt_userns == fs_ns))
+	if (size == XATTR_CAPS_SZ_2 && (idmap == &nop_mnt_idmap))
 		if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP))
 			/* user is privileged, just write the v2 */
 			return size;
@@ -555,7 +555,7 @@ int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry,
 	if (!vfsuid_valid(vfsrootid))
 		return -EINVAL;
 
-	rootid = from_vfsuid(mnt_userns, fs_ns, vfsrootid);
+	rootid = from_vfsuid(idmap, fs_ns, vfsrootid);
 	if (!uid_valid(rootid))
 		return -EINVAL;
 
@@ -589,7 +589,6 @@ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps,
 					  bool *has_fcap)
 {
 	struct cred *new = bprm->cred;
-	unsigned i;
 	int ret = 0;
 
 	if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE)
@@ -598,22 +597,17 @@ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps,
 	if (caps->magic_etc & VFS_CAP_REVISION_MASK)
 		*has_fcap = true;
 
-	CAP_FOR_EACH_U32(i) {
-		__u32 permitted = caps->permitted.cap[i];
-		__u32 inheritable = caps->inheritable.cap[i];
-
-		/*
-		 * pP' = (X & fP) | (pI & fI)
-		 * The addition of pA' is handled later.
-		 */
-		new->cap_permitted.cap[i] =
-			(new->cap_bset.cap[i] & permitted) |
-			(new->cap_inheritable.cap[i] & inheritable);
+	/*
+	 * pP' = (X & fP) | (pI & fI)
+	 * The addition of pA' is handled later.
+	 */
+	new->cap_permitted.val =
+		(new->cap_bset.val & caps->permitted.val) |
+		(new->cap_inheritable.val & caps->inheritable.val);
 
-		if (permitted & ~new->cap_permitted.cap[i])
-			/* insufficient to execute correctly */
-			ret = -EPERM;
-	}
+	if (caps->permitted.val & ~new->cap_permitted.val)
+		/* insufficient to execute correctly */
+		ret = -EPERM;
 
 	/*
 	 * For legacy apps, with no internal support for recognizing they
@@ -626,25 +620,24 @@ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps,
 /**
  * get_vfs_caps_from_disk - retrieve vfs caps from disk
  *
- * @mnt_userns:	user namespace of the mount the inode was found from
+ * @idmap:	idmap of the mount the inode was found from
  * @dentry:	dentry from which @inode is retrieved
  * @cpu_caps:	vfs capabilities
  *
  * Extract the on-exec-apply capability sets for an executable file.
  *
- * If the inode has been found through an idmapped mount the user namespace of
- * the vfsmount must be passed through @mnt_userns. This function will then
- * take care to map the inode according to @mnt_userns before checking
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs init_user_ns.
+ * performed on the raw inode simply passs @nop_mnt_idmap.
  */
-int get_vfs_caps_from_disk(struct user_namespace *mnt_userns,
+int get_vfs_caps_from_disk(struct mnt_idmap *idmap,
 			   const struct dentry *dentry,
 			   struct cpu_vfs_cap_data *cpu_caps)
 {
 	struct inode *inode = d_backing_inode(dentry);
 	__u32 magic_etc;
-	unsigned tocopy, i;
 	int size;
 	struct vfs_ns_cap_data data, *nscaps = &data;
 	struct vfs_cap_data *caps = (struct vfs_cap_data *) &data;
@@ -677,17 +670,14 @@ int get_vfs_caps_from_disk(struct user_namespace *mnt_userns,
 	case VFS_CAP_REVISION_1:
 		if (size != XATTR_CAPS_SZ_1)
 			return -EINVAL;
-		tocopy = VFS_CAP_U32_1;
 		break;
 	case VFS_CAP_REVISION_2:
 		if (size != XATTR_CAPS_SZ_2)
 			return -EINVAL;
-		tocopy = VFS_CAP_U32_2;
 		break;
 	case VFS_CAP_REVISION_3:
 		if (size != XATTR_CAPS_SZ_3)
 			return -EINVAL;
-		tocopy = VFS_CAP_U32_3;
 		rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid));
 		break;
 
@@ -695,7 +685,7 @@ int get_vfs_caps_from_disk(struct user_namespace *mnt_userns,
 		return -EINVAL;
 	}
 
-	rootvfsuid = make_vfsuid(mnt_userns, fs_ns, rootkuid);
+	rootvfsuid = make_vfsuid(idmap, fs_ns, rootkuid);
 	if (!vfsuid_valid(rootvfsuid))
 		return -ENODATA;
 
@@ -705,15 +695,20 @@ int get_vfs_caps_from_disk(struct user_namespace *mnt_userns,
 	if (!rootid_owns_currentns(rootvfsuid))
 		return -ENODATA;
 
-	CAP_FOR_EACH_U32(i) {
-		if (i >= tocopy)
-			break;
-		cpu_caps->permitted.cap[i] = le32_to_cpu(caps->data[i].permitted);
-		cpu_caps->inheritable.cap[i] = le32_to_cpu(caps->data[i].inheritable);
+	cpu_caps->permitted.val = le32_to_cpu(caps->data[0].permitted);
+	cpu_caps->inheritable.val = le32_to_cpu(caps->data[0].inheritable);
+
+	/*
+	 * Rev1 had just a single 32-bit word, later expanded
+	 * to a second one for the high bits
+	 */
+	if ((magic_etc & VFS_CAP_REVISION_MASK) != VFS_CAP_REVISION_1) {
+		cpu_caps->permitted.val += (u64)le32_to_cpu(caps->data[1].permitted) << 32;
+		cpu_caps->inheritable.val += (u64)le32_to_cpu(caps->data[1].inheritable) << 32;
 	}
 
-	cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
-	cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+	cpu_caps->permitted.val &= CAP_VALID_MASK;
+	cpu_caps->inheritable.val &= CAP_VALID_MASK;
 
 	cpu_caps->rootid = vfsuid_into_kuid(rootvfsuid);
 
@@ -747,7 +742,7 @@ static int get_file_caps(struct linux_binprm *bprm, struct file *file,
 	if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns))
 		return 0;
 
-	rc = get_vfs_caps_from_disk(file_mnt_user_ns(file),
+	rc = get_vfs_caps_from_disk(file_mnt_idmap(file),
 				    file->f_path.dentry, &vcaps);
 	if (rc < 0) {
 		if (rc == -EINVAL)
@@ -1016,23 +1011,23 @@ int cap_inode_setxattr(struct dentry *dentry, const char *name,
 /**
  * cap_inode_removexattr - Determine whether an xattr may be removed
  *
- * @mnt_userns:	User namespace of the mount the inode was found from
+ * @idmap:	idmap of the mount the inode was found from
  * @dentry:	The inode/dentry being altered
  * @name:	The name of the xattr to be changed
  *
  * Determine whether an xattr may be removed from an inode, returning 0 if
  * permission is granted, -ve if denied.
  *
- * If the inode has been found through an idmapped mount the user namespace of
- * the vfsmount must be passed through @mnt_userns. This function will then
- * take care to map the inode according to @mnt_userns before checking
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs init_user_ns.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
  *
  * This is used to make sure security xattrs don't get removed by those who
  * aren't privileged to remove them.
  */
-int cap_inode_removexattr(struct user_namespace *mnt_userns,
+int cap_inode_removexattr(struct mnt_idmap *idmap,
 			  struct dentry *dentry, const char *name)
 {
 	struct user_namespace *user_ns = dentry->d_sb->s_user_ns;
@@ -1047,7 +1042,7 @@ int cap_inode_removexattr(struct user_namespace *mnt_userns,
 		struct inode *inode = d_backing_inode(dentry);
 		if (!inode)
 			return -EINVAL;
-		if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP))
+		if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP))
 			return -EPERM;
 		return 0;
 	}