From:   Dave Chinner <david@fromorbit.com>
To:     linux-kernel@vger.kernel.org, linux-xfs@vger.kernel.org
Cc:     linux-mm@vger.kernel.org, linux-fsdevel@vger.kernel.org,
        yebin10@huawei.com
Subject: [PATCH 3/4] fork: remove use of percpu_counter_sum_all
Date:   Wed, 15 Mar 2023 19:49:37 +1100
Message-Id: <20230315084938.2544737-4-david@fromorbit.com>
In-Reply-To: <20230315084938.2544737-1-david@fromorbit.com>
References: <20230315084938.2544737-1-david@fromorbit.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Dave Chinner <dchinner@redhat.com>

This effectively reverts the change made in commit f689054aace2
("percpu_counter: add percpu_counter_sum_all interface") as the
race condition percpu_counter_sum_all() was invented to avoid is
now handled directly in percpu_counter_sum() and nobody needs to
care about summing racing with cpu unplug anymore.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
 kernel/fork.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index d8cda4c6de6c..c0257cbee093 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -755,11 +755,6 @@ static void check_mm(struct mm_struct *mm)
 	for (i = 0; i < NR_MM_COUNTERS; i++) {
 		long x = percpu_counter_sum(&mm->rss_stat[i]);
 
-		if (likely(!x))
-			continue;
-
-		/* Making sure this is not due to race with CPU offlining. */
-		x = percpu_counter_sum_all(&mm->rss_stat[i]);
 		if (unlikely(x))
 			pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n",
 				 mm, resident_page_types[i], x);
-- 
2.39.2