summaryrefslogtreecommitdiff
path: root/security
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-10-04 05:48:54 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2022-10-04 05:48:54 +0300
commit223b8452530da8816de09ec76a2182d1ad8f4fe2 (patch)
treeb1b9d1024337415a3bf4c99770f713b0ac220da0 /security
parentda380aefdd185f6dfe3e5555d554dc6a006d2682 (diff)
parent38e316398e4e6338b80223fb5f74415c0513718f (diff)
downloadlinux-223b8452530da8816de09ec76a2182d1ad8f4fe2.tar.xz
Merge tag 'fs.acl.rework.prep.v6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping
Pull vfs acl updates from Christian Brauner: "These are general fixes and preparatory changes related to the ongoing posix acl rework. The actual rework where we build a type safe posix acl api wasn't ready for this merge window but we're hopeful for the next merge window. General fixes: - Some filesystems like 9p and cifs have to implement custom posix acl handlers because they require access to the dentry in order to set and get posix acls while the set and get inode operations currently don't. But the ntfs3 filesystem has no such requirement and thus implemented custom posix acl xattr handlers when it really didn't have to. So this pr contains patch that just implements set and get inode operations for ntfs3 and switches it to rely on the generic posix acl xattr handlers. (We would've appreciated reviews from the ntfs3 maintainers but we didn't get any. But hey, if we really broke it we'll fix it. But fstests for ntfs3 said it's fine.) - The posix_acl_fix_xattr_common() helper has been adapted so it can be used by a few more callers and avoiding open-coding the same checks over and over. Other than the two general fixes this series introduces a new helper vfs_set_acl_prepare(). The reason for this helper is so that we can mitigate one of the source that change {g,u}id values directly in the uapi struct. With the vfs_set_acl_prepare() helper we can move the idmapped mount fixup into the generic posix acl set handler. The advantage of this is that it allows us to remove the posix_acl_setxattr_idmapped_mnt() helper which so far we had to call in vfs_setxattr() to account for idmapped mounts. While semantically correct the problem with this approach was that we had to keep the value parameter of the generic vfs_setxattr() call as non-const. This is rectified in this series. Ultimately, we will get rid of all the extreme kludges and type unsafety once we have merged the posix api - hopefully during the next merge window - built solely around get and set inode operations. Which incidentally will also improve handling of posix acls in security and especially in integrity modesl. While this will come with temporarily having two inode operation for posix acls that is nothing compared to the problems we have right now and so well worth it. We'll end up with something that we can actually reason about instead of needing to write novels to explain what's going on" * tag 'fs.acl.rework.prep.v6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping: xattr: always us is_posix_acl_xattr() helper acl: fix the comments of posix_acl_xattr_set xattr: constify value argument in vfs_setxattr() ovl: use vfs_set_acl_prepare() acl: move idmapping handling into posix_acl_xattr_set() acl: add vfs_set_acl_prepare() acl: return EOPNOTSUPP in posix_acl_fix_xattr_common() ntfs3: rework xattr handlers and switch to POSIX ACL VFS helpers
Diffstat (limited to 'security')
-rw-r--r--security/integrity/evm/evm_main.c17
1 files changed, 14 insertions, 3 deletions
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index 2e6fb6e2ffd2..23d484e05e6f 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -457,10 +457,21 @@ static int evm_xattr_acl_change(struct user_namespace *mnt_userns,
int rc;
/*
- * user_ns is not relevant here, ACL_USER/ACL_GROUP don't have impact
- * on the inode mode (see posix_acl_equiv_mode()).
+ * An earlier comment here mentioned that the idmappings for
+ * ACL_{GROUP,USER} don't matter since EVM is only interested in the
+ * mode stored as part of POSIX ACLs. Nonetheless, if it must translate
+ * from the uapi POSIX ACL representation to the VFS internal POSIX ACL
+ * representation it should do so correctly. There's no guarantee that
+ * we won't change POSIX ACLs in a way that ACL_{GROUP,USER} matters
+ * for the mode at some point and it's difficult to keep track of all
+ * the LSM and integrity modules and what they do to POSIX ACLs.
+ *
+ * Frankly, EVM shouldn't try to interpret the uapi struct for POSIX
+ * ACLs it received. It requires knowledge that only the VFS is
+ * guaranteed to have.
*/
- acl = posix_acl_from_xattr(&init_user_ns, xattr_value, xattr_value_len);
+ acl = vfs_set_acl_prepare(mnt_userns, i_user_ns(inode),
+ xattr_value, xattr_value_len);
if (IS_ERR_OR_NULL(acl))
return 1;