@@ -24,6 +24,7 @@
#include <linux/user_namespace.h>
#include <linux/namei.h>
#include <linux/mnt_idmapping.h>
+#include <linux/fsnotify.h>
static struct posix_acl **acl_by_type(struct inode *inode, int type)
{
@@ -1253,3 +1254,109 @@ int simple_acl_create(struct inode *dir, struct inode *inode)
posix_acl_release(acl);
return 0;
}
+
+static inline int posix_acl_type(const char *name)
+{
+ if (strcmp(name, XATTR_NAME_POSIX_ACL_ACCESS) == 0)
+ return ACL_TYPE_ACCESS;
+ else if (strcmp(name, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)
+ return ACL_TYPE_DEFAULT;
+
+ return -1;
+}
+
+static int vfs_set_acl_idmapped_mnt(struct user_namespace *mnt_userns,
+ struct user_namespace *fs_userns,
+ struct posix_acl *acl)
+{
+ for (int n = 0; n < acl->a_count; n++) {
+ struct posix_acl_entry *acl_e = &acl->a_entries[n];
+
+ switch (acl_e->e_tag) {
+ case ACL_USER:
+ acl_e->e_uid = from_vfsuid(mnt_userns, fs_userns,
+ VFSUIDT_INIT(acl_e->e_uid));
+ break;
+ case ACL_GROUP:
+ acl_e->e_gid = from_vfsgid(mnt_userns, fs_userns,
+ VFSGIDT_INIT(acl_e->e_gid));
+ break;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * vfs_set_acl - set posix acls
+ * @mnt_userns: user namespace of the mount
+ * @dentry: the dentry based on which to set the posix acls
+ * @acl_name: the name of the posix acl
+ * @kacl: the posix acls in the appropriate VFS format
+ *
+ * This function sets @kacl. The caller must all posix_acl_release() on @kacl
+ * afterwards.
+ *
+ * Return: On success 0, on error negative errno.
+ */
+int vfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
+ const char *acl_name, struct posix_acl *kacl)
+{
+ int acl_type;
+ int error;
+ struct inode *inode = d_inode(dentry);
+ struct inode *delegated_inode = NULL;
+
+ acl_type = posix_acl_type(acl_name);
+ if (acl_type < 0)
+ return -EINVAL;
+
+ if (kacl) {
+ /*
+ * If we're on an idmapped mount translate from mount specific
+ * vfs{g,u}id_t into global filesystem k{g,u}id_t so.
+ * Afterwards we can cache the POSIX ACLs filesystem wide and -
+ * if this is a filesystem with a backing store - translate
+ * them to backing store values.
+ */
+ error = vfs_set_acl_idmapped_mnt(mnt_userns, i_user_ns(inode), kacl);
+ if (error)
+ return error;
+ }
+
+retry_deleg:
+ inode_lock(inode);
+
+ /*
+ * We only care about restrictions the inode struct itself places upon
+ * us otherwise POSIX ACLs aren't subject to any VFS restrictions.
+ */
+ error = xattr_permission(mnt_userns, inode, acl_name, MAY_WRITE);
+ if (error)
+ goto out_inode_unlock;
+
+ error = try_break_deleg(inode, &delegated_inode);
+ if (error)
+ goto out_inode_unlock;
+
+ if (inode->i_opflags & IOP_XATTR)
+ error = set_posix_acl(mnt_userns, dentry, acl_type, kacl);
+ else if (unlikely(is_bad_inode(inode)))
+ error = -EIO;
+ else
+ error = -EOPNOTSUPP;
+ if (!error)
+ fsnotify_xattr(dentry);
+
+out_inode_unlock:
+ inode_unlock(inode);
+
+ if (delegated_inode) {
+ error = break_deleg_wait(&delegated_inode);
+ if (!error)
+ goto retry_deleg;
+ }
+
+ return error;
+}
+EXPORT_SYMBOL(vfs_set_acl);
@@ -84,9 +84,8 @@ xattr_resolve_name(struct inode *inode, const char **name)
* Check permissions for extended attribute access. This is a bit complicated
* because different namespaces have very different rules.
*/
-static int
-xattr_permission(struct user_namespace *mnt_userns, struct inode *inode,
- const char *name, int mask)
+int xattr_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ const char *name, int mask)
{
/*
* We can never set or remove an extended attribute on a read-only
@@ -99,6 +99,9 @@ static inline void cache_no_acl(struct inode *inode)
inode->i_acl = NULL;
inode->i_default_acl = NULL;
}
+
+int vfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
+ const char *acl_name, struct posix_acl *kacl);
#else
static inline int posix_acl_chmod(struct user_namespace *mnt_userns,
struct dentry *dentry, umode_t mode)
@@ -126,6 +129,13 @@ static inline int posix_acl_create(struct inode *inode, umode_t *mode,
static inline void forget_all_cached_acls(struct inode *inode)
{
}
+
+static inline int vfs_set_acl(struct user_namespace *mnt_userns,
+ struct dentry *dentry, const char *name,
+ struct posix_acl *acl)
+{
+ return 0;
+}
#endif /* CONFIG_FS_POSIX_ACL */
struct posix_acl *get_acl(struct inode *inode, int type);
@@ -73,6 +73,8 @@ ssize_t vfs_getxattr_alloc(struct user_namespace *mnt_userns,
char **xattr_value, size_t size, gfp_t flags);
int xattr_supported_namespace(struct inode *inode, const char *prefix);
+int xattr_permission(struct user_namespace *mnt_userns, struct inode *inode,
+ const char *name, int mask);
static inline const char *xattr_prefix(const struct xattr_handler *handler)
{
In previous patches we implemented get and set inode operations for all non-stacking filesystems that support posix acls but didn't yet implement get and/or set acl inode operations. This specifically affected cifs and 9p. Now we can build a posix acl api based solely on get and set inode operations. We add a new vfs_set_acl() api that can be used to set posix acls. This finally removes all type unsafety and type conversion issues explained in detail in [1] that we aim to get rid of. After we finished building the vfs api we can switch stacking filesystems to rely on the new posix api and then finally switch the xattr system calls themselves to rely on the posix acl api. Link: https://lore.kernel.org/all/20220801145520.1532837-1-brauner@kernel.org [1] Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org> --- fs/posix_acl.c | 107 ++++++++++++++++++++++++++++++++++++++ fs/xattr.c | 5 +- include/linux/posix_acl.h | 10 ++++ include/linux/xattr.h | 2 + 4 files changed, 121 insertions(+), 3 deletions(-)