The oomkiller calculations make decisions based on capabilities. Since

these are not security decisions and LSMs should not record if they fall
the request they should use the new has_capability_noaudit() interface so
the denials will not be recorded.

Signed-off-by: Eric Paris <eparis@redhat.com>
Acked-by:  Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: James Morris <jmorris@namei.org>

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 64e5b4bcd964cd912b5a5f6b22dc392621269d84..34a458aa79976f011095c8bbcb2796d9392b9408 100644 (file)
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -129,8 +129,8 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
         * Superuser processes are usually more important, so we make it
         * less likely that we kill those.
         */
-       if (has_capability(p, CAP_SYS_ADMIN) ||
-           has_capability(p, CAP_SYS_RESOURCE))
+       if (has_capability_noaudit(p, CAP_SYS_ADMIN) ||
+           has_capability_noaudit(p, CAP_SYS_RESOURCE))
                points /= 4;
 
        /*
@@ -139,7 +139,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
         * tend to only have this flag set on applications they think
         * of as important.
         */
-       if (has_capability(p, CAP_SYS_RAWIO))
+       if (has_capability_noaudit(p, CAP_SYS_RAWIO))
                points /= 4;
 
        /*