From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1759507AbdEONNe (ORCPT <rfc822;w@1wt.eu>);
        Mon, 15 May 2017 09:13:34 -0400
Received: from mx2.suse.de ([195.135.220.15]:37993 "EHLO mx1.suse.de"
        rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP
        id S1758488AbdEONNd (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
        Mon, 15 May 2017 09:13:33 -0400
From: Vlastimil Babka <vbabka@suse.cz>
To: Ingo Molnar <mingo@redhat.com>, Peter Zijlstra <peterz@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>,
        Rik van Riel <riel@redhat.com>, linux-kernel@vger.kernel.org,
        Vlastimil Babka <vbabka@suse.cz>
Subject: [PATCH] sched/numa: use down_read_trylock for mmap_sem
Date: Mon, 15 May 2017 15:13:16 +0200
Message-Id: <20170515131316.21909-1-vbabka@suse.cz>
X-Mailer: git-send-email 2.12.2
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

A customer has reported a soft-lockup when running a proprietary intensive
memory stress test, where the trace on multiple CPU's looks like this:

 RIP: 0010:[<ffffffff810c53fe>]
  [<ffffffff810c53fe>] native_queued_spin_lock_slowpath+0x10e/0x190
...
 Call Trace:
  [<ffffffff81182d07>] queued_spin_lock_slowpath+0x7/0xa
  [<ffffffff811bc331>] change_protection_range+0x3b1/0x930
  [<ffffffff811d4be8>] change_prot_numa+0x18/0x30
  [<ffffffff810adefe>] task_numa_work+0x1fe/0x310
  [<ffffffff81098322>] task_work_run+0x72/0x90

Further investigation showed that the lock contention here is pmd_lock().

The task_numa_work() function makes sure that only one thread is let to perform
the work in a single scan period (via cmpxchg), but if there's a thread with
mmap_sem locked for writing for several periods, multiple threads in
task_numa_work() can build up a convoy waiting for mmap_sem for read and then
all get unblocked at once.

This patch changes the down_read() to the trylock version, which prevents the
build up. For a workload experiencing mmap_sem contention, it's probably better
to postpone the NUMA balancing work anyway. This seems to have fixed the soft
lockups involving pmd_lock(), which is in line with the convoy theory.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 kernel/sched/fair.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index dea138964b91..d70f9026defc 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2475,7 +2475,8 @@ void task_numa_work(struct callback_head *work)
 		return;
 
 
-	down_read(&mm->mmap_sem);
+	if (!down_read_trylock(&mm->mmap_sem))
+		return;
 	vma = find_vma(mm, start);
 	if (!vma) {
 		reset_ptenuma_scan(p);
-- 
2.12.2