mm, thp: remove cond_resched from __collapse_huge_page_copy
authorDavid Rientjes <rientjes@google.com>
Fri, 23 Jun 2017 22:08:38 +0000 (15:08 -0700)
committerLinus Torvalds <torvalds@linux-foundation.org>
Fri, 23 Jun 2017 23:15:55 +0000 (16:15 -0700)
This is a partial revert of commit 338a16ba1549 ("mm, thp: copying user
pages must schedule on collapse") which added a cond_resched() to
__collapse_huge_page_copy().

On x86 with CONFIG_HIGHPTE, __collapse_huge_page_copy is called in
atomic context and thus scheduling is not possible.  This is only a
possible config on arm and i386.

Although need_resched has been shown to be set for over 100 jiffies
while doing the iteration in __collapse_huge_page_copy, this is better
than doing

if (in_atomic())
cond_resched()

to cover only non-CONFIG_HIGHPTE configs.

Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1706191341550.97821@chino.kir.corp.google.com
Signed-off-by: David Rientjes <rientjes@google.com>
Reported-by: Larry Finger <Larry.Finger@lwfinger.net>
Tested-by: Larry Finger <Larry.Finger@lwfinger.net>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mm/khugepaged.c

index 945fd1ca49b5af0bc3b87dbfe8098f0f602775a2..df4ebdb2b10a373723330dc0124957cd2cb1c021 100644 (file)
@@ -652,7 +652,6 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
                        spin_unlock(ptl);
                        free_page_and_swap_cache(src_page);
                }
-               cond_resched();
        }
 }