mm, oom: avoid reaping only for mm's with blockable invalidate callbacks

This uses the new annotation to determine if an mm has mmu notifiers
with blockable invalidate range callbacks to avoid oom reaping.
Otherwise, the callbacks are used around unmap_page_range().

Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: David Rientjes <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Cc: Paolo Bonzini <[email protected]>
Cc: Christian König <[email protected]>
Cc: Dimitri Sivanich <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Oded Gabbay <[email protected]>
Cc: Alex Deucher <[email protected]>
Cc: David Airlie <[email protected]>
Cc: Joerg Roedel <[email protected]>
Cc: Doug Ledford <[email protected]>
Cc: Jani Nikula <[email protected]>
Cc: Mike Marciniszyn <[email protected]>
Cc: Sean Hefty <[email protected]>
Cc: Boris Ostrovsky <[email protected]>
Cc: Jérôme Glisse <[email protected]>
Cc: Radim Krčmář <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

mm/oom_kill.c

@@ -514,15 +514,12 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 	}
 
 	/*
-	 * If the mm has notifiers then we would need to invalidate them around
-	 * unmap_page_range and that is risky because notifiers can sleep and
-	 * what they do is basically undeterministic.  So let's have a short
+	 * If the mm has invalidate_{start,end}() notifiers that could block,
 	 * sleep to give the oom victim some more time.
 	 * TODO: we really want to get rid of this ugly hack and make sure that
-	 * notifiers cannot block for unbounded amount of time and add
-	 * mmu_notifier_invalidate_range_{start,end} around unmap_page_range
+	 * notifiers cannot block for unbounded amount of time
 	 */
-	if (mm_has_notifiers(mm)) {
+	if (mm_has_blockable_invalidate_notifiers(mm)) {
 		up_read(&mm->mmap_sem);
 		schedule_timeout_idle(HZ);
 		goto unlock_oom;
@@ -565,10 +562,14 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 		 * count elevated without a good reason.
 		 */
 		if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
-			tlb_gather_mmu(&tlb, mm, vma->vm_start, vma->vm_end);
-			unmap_page_range(&tlb, vma, vma->vm_start, vma->vm_end,
-					 NULL);
-			tlb_finish_mmu(&tlb, vma->vm_start, vma->vm_end);
+			const unsigned long start = vma->vm_start;
+			const unsigned long end = vma->vm_end;
+
+			tlb_gather_mmu(&tlb, mm, start, end);
+			mmu_notifier_invalidate_range_start(mm, start, end);
+			unmap_page_range(&tlb, vma, start, end, NULL);
+			mmu_notifier_invalidate_range_end(mm, start, end);
+			tlb_finish_mmu(&tlb, start, end);
 		}
 	}
 	pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",