[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Sun, 11 Nov 2018 19:49:05 +0000
From: Ben Hutchings <ben@...adent.org.uk>
To: linux-kernel@...r.kernel.org, stable@...r.kernel.org
CC: akpm@...ux-foundation.org,
"Linus Torvalds" <torvalds@...ux-foundation.org>,
"Peter Feiner" <pfeiner@...gle.com>,
"Greg Thelen" <gthelen@...gle.com>,
"Mike Kravetz" <mike.kravetz@...cle.com>,
"Andres Lagar-Cavilla" <andreslc@...gle.com>,
"Cannon Matthews" <cannonmatthews@...gle.com>,
"Michal Hocko" <mhocko@...e.com>
Subject: [PATCH 3.16 226/366] mm: hugetlb: yield when prepping struct pages
3.16.61-rc1 review patch. If anyone has any objections, please let me know.
------------------
From: Cannon Matthews <cannonmatthews@...gle.com>
commit 520495fe96d74e05db585fc748351e0504d8f40d upstream.
When booting with very large numbers of gigantic (i.e. 1G) pages, the
operations in the loop of gather_bootmem_prealloc, and specifically
prep_compound_gigantic_page, takes a very long time, and can cause a
softlockup if enough pages are requested at boot.
For example booting with 3844 1G pages requires prepping
(set_compound_head, init the count) over 1 billion 4K tail pages, which
takes considerable time.
Add a cond_resched() to the outer loop in gather_bootmem_prealloc() to
prevent this lockup.
Tested: Booted with softlockup_panic=1 hugepagesz=1G hugepages=3844 and
no softlockup is reported, and the hugepages are reported as
successfully setup.
Link: http://lkml.kernel.org/r/20180627214447.260804-1-cannonmatthews@google.com
Signed-off-by: Cannon Matthews <cannonmatthews@...gle.com>
Reviewed-by: Andrew Morton <akpm@...ux-foundation.org>
Reviewed-by: Mike Kravetz <mike.kravetz@...cle.com>
Acked-by: Michal Hocko <mhocko@...e.com>
Cc: Andres Lagar-Cavilla <andreslc@...gle.com>
Cc: Peter Feiner <pfeiner@...gle.com>
Cc: Greg Thelen <gthelen@...gle.com>
Signed-off-by: Andrew Morton <akpm@...ux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@...ux-foundation.org>
Signed-off-by: Ben Hutchings <ben@...adent.org.uk>
---
mm/hugetlb.c | 1 +
1 file changed, 1 insertion(+)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1546,6 +1546,7 @@ static void __init gather_bootmem_preall
*/
if (hstate_is_gigantic(h))
adjust_managed_page_count(page, 1 << h->order);
+ cond_resched();
}
}
Powered by blists - more mailing lists