mm: memcg: enable memcg OOM killer only for user faults

System calls and kernel faults (uaccess, gup) can handle an out of memory
situation gracefully and just return -ENOMEM.

Enable the memcg OOM killer only for user faults, where it's really the
only option available.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: azurIt <azurit@pobox.sk>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 30 insertions, 10 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 2b73dbde2274..a8f9deab8719 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3754,22 +3754,14 @@ unlock:
 /*
  * By the time we get here, we already hold the mm semaphore
  */
-int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
-                unsigned long address, unsigned int flags)
+static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+                             unsigned long address, unsigned int flags)
 {
         pgd_t *pgd;
         pud_t *pud;
         pmd_t *pmd;
         pte_t *pte;
 
-        __set_current_state(TASK_RUNNING);
-
-        count_vm_event(PGFAULT);
-        mem_cgroup_count_vm_event(mm, PGFAULT);
-
-        /* do counter updates before entering really critical section. */
-        check_sync_rss_stat(current);
-
         if (unlikely(is_vm_hugetlb_page(vma)))
                 return hugetlb_fault(mm, vma, address, flags);
 
@@ -3850,6 +3842,34 @@ retry:
         return handle_pte_fault(mm, vma, address, pte, pmd, flags);
 }
 
+int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+                    unsigned long address, unsigned int flags)
+{
+        int ret;
+
+        __set_current_state(TASK_RUNNING);
+
+        count_vm_event(PGFAULT);
+        mem_cgroup_count_vm_event(mm, PGFAULT);
+
+        /* do counter updates before entering really critical section. */
+        check_sync_rss_stat(current);
+
+        /*
+         * Enable the memcg OOM handling for faults triggered in user
+         * space.  Kernel faults are handled more gracefully.
+         */
+        if (flags & FAULT_FLAG_USER)
+                mem_cgroup_enable_oom();
+
+        ret = __handle_mm_fault(mm, vma, address, flags);
+
+        if (flags & FAULT_FLAG_USER)
+                mem_cgroup_disable_oom();
+
+        return ret;
+}
+
 #ifndef __PAGETABLE_PUD_FOLDED
 /*
  * Allocate page upper directory.