summaryrefslogtreecommitdiff
path: root/fs/attr.c
diff options
context:
space:
mode:
authorChristian Brauner <brauner@kernel.org>2022-10-17 17:06:37 +0200
committerChristian Brauner (Microsoft) <brauner@kernel.org>2022-10-18 10:09:47 +0200
commited5a7047d2011cb6b2bf84ceb6680124cc6a7d95 (patch)
treea2963497f1f02b0b102adf9ed8fbf125888a44f5 /fs/attr.c
parent72ae017c5451860443a16fb2a8c243bff3e396b8 (diff)
attr: use consistent sgid stripping checks
Currently setgid stripping in file_remove_privs()'s should_remove_suid() helper is inconsistent with other parts of the vfs. Specifically, it only raises ATTR_KILL_SGID if the inode is S_ISGID and S_IXGRP but not if the inode isn't in the caller's groups and the caller isn't privileged over the inode although we require this already in setattr_prepare() and setattr_copy() and so all filesystem implement this requirement implicitly because they have to use setattr_{prepare,copy}() anyway. But the inconsistency shows up in setgid stripping bugs for overlayfs in xfstests (e.g., generic/673, generic/683, generic/685, generic/686, generic/687). For example, we test whether suid and setgid stripping works correctly when performing various write-like operations as an unprivileged user (fallocate, reflink, write, etc.): echo "Test 1 - qa_user, non-exec file $verb" setup_testfile chmod a+rws $junk_file commit_and_check "$qa_user" "$verb" 64k 64k The test basically creates a file with 6666 permissions. While the file has the S_ISUID and S_ISGID bits set it does not have the S_IXGRP set. On a regular filesystem like xfs what will happen is: sys_fallocate() -> vfs_fallocate() -> xfs_file_fallocate() -> file_modified() -> __file_remove_privs() -> dentry_needs_remove_privs() -> should_remove_suid() -> __remove_privs() newattrs.ia_valid = ATTR_FORCE | kill; -> notify_change() -> setattr_copy() In should_remove_suid() we can see that ATTR_KILL_SUID is raised unconditionally because the file in the test has S_ISUID set. But we also see that ATTR_KILL_SGID won't be set because while the file is S_ISGID it is not S_IXGRP (see above) which is a condition for ATTR_KILL_SGID being raised. So by the time we call notify_change() we have attr->ia_valid set to ATTR_KILL_SUID | ATTR_FORCE. Now notify_change() sees that ATTR_KILL_SUID is set and does: ia_valid = attr->ia_valid |= ATTR_MODE attr->ia_mode = (inode->i_mode & ~S_ISUID); which means that when we call setattr_copy() later we will definitely update inode->i_mode. Note that attr->ia_mode still contains S_ISGID. Now we call into the filesystem's ->setattr() inode operation which will end up calling setattr_copy(). Since ATTR_MODE is set we will hit: if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode); if (!vfsgid_in_group_p(vfsgid) && !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) mode &= ~S_ISGID; inode->i_mode = mode; } and since the caller in the test is neither capable nor in the group of the inode the S_ISGID bit is stripped. But assume the file isn't suid then ATTR_KILL_SUID won't be raised which has the consequence that neither the setgid nor the suid bits are stripped even though it should be stripped because the inode isn't in the caller's groups and the caller isn't privileged over the inode. If overlayfs is in the mix things become a bit more complicated and the bug shows up more clearly. When e.g., ovl_setattr() is hit from ovl_fallocate()'s call to file_remove_privs() then ATTR_KILL_SUID and ATTR_KILL_SGID might be raised but because the check in notify_change() is questioning the ATTR_KILL_SGID flag again by requiring S_IXGRP for it to be stripped the S_ISGID bit isn't removed even though it should be stripped: sys_fallocate() -> vfs_fallocate() -> ovl_fallocate() -> file_remove_privs() -> dentry_needs_remove_privs() -> should_remove_suid() -> __remove_privs() newattrs.ia_valid = ATTR_FORCE | kill; -> notify_change() -> ovl_setattr() // TAKE ON MOUNTER'S CREDS -> ovl_do_notify_change() -> notify_change() // GIVE UP MOUNTER'S CREDS // TAKE ON MOUNTER'S CREDS -> vfs_fallocate() -> xfs_file_fallocate() -> file_modified() -> __file_remove_privs() -> dentry_needs_remove_privs() -> should_remove_suid() -> __remove_privs() newattrs.ia_valid = attr_force | kill; -> notify_change() The fix for all of this is to make file_remove_privs()'s should_remove_suid() helper to perform the same checks as we already require in setattr_prepare() and setattr_copy() and have notify_change() not pointlessly requiring S_IXGRP again. It doesn't make any sense in the first place because the caller must calculate the flags via should_remove_suid() anyway which would raise ATTR_KILL_SGID. While we're at it we move should_remove_suid() from inode.c to attr.c where it belongs with the rest of the iattr helpers. Especially since it returns ATTR_KILL_S{G,U}ID flags. We also rename it to setattr_should_drop_suidgid() to better reflect that it indicates both setuid and setgid bit removal and also that it returns attr flags. Running xfstests with this doesn't report any regressions. We should really try and use consistent checks. Reviewed-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Diffstat (limited to 'fs/attr.c')
-rw-r--r--fs/attr.c33
1 files changed, 19 insertions, 14 deletions
diff --git a/fs/attr.c b/fs/attr.c
index 085322536127..b45f30e516fa 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -48,34 +48,39 @@ int setattr_should_drop_sgid(struct user_namespace *mnt_userns,
return 0;
}
-/*
- * The logic we want is
+/**
+ * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to
+ * be dropped
+ * @mnt_userns: user namespace of the mount @inode was found from
+ * @inode: inode to check
*
- * if suid or (sgid and xgrp)
- * remove privs
+ * This function determines whether the set{g,u}id bits need to be removed.
+ * If the setuid bit needs to be removed ATTR_KILL_SUID is returned. If the
+ * setgid bit needs to be removed ATTR_KILL_SGID is returned. If both
+ * set{g,u}id bits need to be removed the corresponding mask of both flags is
+ * returned.
+ *
+ * Return: A mask of ATTR_KILL_S{G,U}ID indicating which - if any - setid bits
+ * to remove, 0 otherwise.
*/
-int should_remove_suid(struct dentry *dentry)
+int setattr_should_drop_suidgid(struct user_namespace *mnt_userns,
+ struct inode *inode)
{
- umode_t mode = d_inode(dentry)->i_mode;
+ umode_t mode = inode->i_mode;
int kill = 0;
/* suid always must be killed */
if (unlikely(mode & S_ISUID))
kill = ATTR_KILL_SUID;
- /*
- * sgid without any exec bits is just a mandatory locking mark; leave
- * it alone. If some exec bits are set, it's a real sgid; kill it.
- */
- if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
- kill |= ATTR_KILL_SGID;
+ kill |= setattr_should_drop_sgid(mnt_userns, inode);
if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode)))
return kill;
return 0;
}
-EXPORT_SYMBOL(should_remove_suid);
+EXPORT_SYMBOL(setattr_should_drop_suidgid);
/**
* chown_ok - verify permissions to chown inode
@@ -432,7 +437,7 @@ int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
}
}
if (ia_valid & ATTR_KILL_SGID) {
- if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
+ if (mode & S_ISGID) {
if (!(ia_valid & ATTR_MODE)) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = inode->i_mode;