summaryrefslogtreecommitdiff
path: root/security/lsm_audit.c
diff options
context:
space:
mode:
authorVivek Goyal <vgoyal@redhat.com>2016-09-09 18:37:49 +0300
committerPaul Moore <paul@paul-moore.com>2016-09-19 20:42:38 +0300
commit43af5de74288a7cdc3684902c5259346ae67adf8 (patch)
tree40ffe7231d18197267a947500c776c520d0b548b /security/lsm_audit.c
parent9b6a9ecc2d88ccdc57efc22d69436b9dd7e2eceb (diff)
downloadlinux-43af5de74288a7cdc3684902c5259346ae67adf8.tar.xz
lsm,audit,selinux: Introduce a new audit data type LSM_AUDIT_DATA_FILE
Right now LSM_AUDIT_DATA_PATH type contains "struct path" in union "u" of common_audit_data. This information is used to print path of file at the same time it is also used to get to dentry and inode. And this inode information is used to get to superblock and device and print device information. This does not work well for layered filesystems like overlay where dentry contained in path is overlay dentry and not the real dentry of underlying file system. That means inode retrieved from dentry is also overlay inode and not the real inode. SELinux helpers like file_path_has_perm() are doing checks on inode retrieved from file_inode(). This returns the real inode and not the overlay inode. That means we are doing check on real inode but for audit purposes we are printing details of overlay inode and that can be confusing while debugging. Hence, introduce a new type LSM_AUDIT_DATA_FILE which carries file information and inode retrieved is real inode using file_inode(). That way right avc denied information is given to user. For example, following is one example avc before the patch. type=AVC msg=audit(1473360868.399:214): avc: denied { read open } for pid=1765 comm="cat" path="/root/.../overlay/container1/merged/readfile" dev="overlay" ino=21443 scontext=unconfined_u:unconfined_r:test_overlay_client_t:s0:c10,c20 tcontext=unconfined_u:object_r:test_overlay_files_ro_t:s0 tclass=file permissive=0 It looks as follows after the patch. type=AVC msg=audit(1473360017.388:282): avc: denied { read open } for pid=2530 comm="cat" path="/root/.../overlay/container1/merged/readfile" dev="dm-0" ino=2377915 scontext=unconfined_u:unconfined_r:test_overlay_client_t:s0:c10,c20 tcontext=unconfined_u:object_r:test_overlay_files_ro_t:s0 tclass=file permissive=0 Notice that now dev information points to "dm-0" device instead of "overlay" device. This makes it clear that check failed on underlying inode and not on the overlay inode. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> [PM: slight tweaks to the description to make checkpatch.pl happy] Signed-off-by: Paul Moore <paul@paul-moore.com>
Diffstat (limited to 'security/lsm_audit.c')
-rw-r--r--security/lsm_audit.c13
1 files changed, 13 insertions, 0 deletions
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 9bf851884800..8bfa3147fd54 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -245,6 +245,19 @@ static void dump_common_audit_data(struct audit_buffer *ab,
}
break;
}
+ case LSM_AUDIT_DATA_FILE: {
+ struct inode *inode;
+
+ audit_log_d_path(ab, " path=", &a->u.file->f_path);
+
+ inode = file_inode(a->u.file);
+ if (inode) {
+ audit_log_format(ab, " dev=");
+ audit_log_untrustedstring(ab, inode->i_sb->s_id);
+ audit_log_format(ab, " ino=%lu", inode->i_ino);
+ }
+ break;
+ }
case LSM_AUDIT_DATA_IOCTL_OP: {
struct inode *inode;