Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Yu Kuai <yukuai1@huaweicloud.com>
To:     guoqing.jiang@linux.dev, logang@deltatee.com,
        pmenzel@molgen.mpg.de, agk@redhat.com, snitzer@kernel.org,
        song@kernel.org
Cc:     linux-kernel@vger.kernel.org, linux-raid@vger.kernel.org,
        yukuai3@huawei.com, yukuai1@huaweicloud.com, yi.zhang@huawei.com,
        yangerkun@huawei.com
Subject: [PATCH -next 2/6] md: refactor action_store() for 'idle' and 'frozen'
Date:   Wed, 22 Mar 2023 14:41:18 +0800
Message-Id: <20230322064122.2384589-3-yukuai1@huaweicloud.com>
In-Reply-To: <20230322064122.2384589-1-yukuai1@huaweicloud.com>
References: <20230322064122.2384589-1-yukuai1@huaweicloud.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Yu Kuai <yukuai3@huawei.com>

Prepare to handle 'idle' and 'frozen' differently to fix a deadlock, there
are no functional changes except that MD_RECOVERY_RUNNING is checked
again after 'reconfig_mutex' is held.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 drivers/md/md.c | 61 ++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 45 insertions(+), 16 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index acf57a5156c7..076936fee65a 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4753,6 +4753,46 @@ action_show(struct mddev *mddev, char *page)
 	return sprintf(page, "%s\n", type);
 }
 
+static void stop_sync_thread(struct mddev *mddev)
+{
+	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+		return;
+
+	if (mddev_lock(mddev))
+		return;
+
+	/*
+	 * Check again in case MD_RECOVERY_RUNNING is cleared before lock is
+	 * held.
+	 */
+	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
+		mddev_unlock(mddev);
+		return;
+	}
+
+	if (work_pending(&mddev->del_work))
+		flush_workqueue(md_misc_wq);
+
+	if (mddev->sync_thread) {
+		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+		md_reap_sync_thread(mddev);
+	}
+
+	mddev_unlock(mddev);
+}
+
+static void idle_sync_thread(struct mddev *mddev)
+{
+	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	stop_sync_thread(mddev);
+}
+
+static void frozen_sync_thread(struct mddev *mddev)
+{
+	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	stop_sync_thread(mddev);
+}
+
 static ssize_t
 action_store(struct mddev *mddev, const char *page, size_t len)
 {
@@ -4760,22 +4800,11 @@ action_store(struct mddev *mddev, const char *page, size_t len)
 		return -EINVAL;
 
 
-	if (cmd_match(page, "idle") || cmd_match(page, "frozen")) {
-		if (cmd_match(page, "frozen"))
-			set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-		else
-			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-		if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
-		    mddev_lock(mddev) == 0) {
-			if (work_pending(&mddev->del_work))
-				flush_workqueue(md_misc_wq);
-			if (mddev->sync_thread) {
-				set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-				md_reap_sync_thread(mddev);
-			}
-			mddev_unlock(mddev);
-		}
-	} else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+	if (cmd_match(page, "idle"))
+		idle_sync_thread(mddev);
+	else if (cmd_match(page, "frozen"))
+		frozen_sync_thread(mddev);
+	else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
 		return -EBUSY;
 	else if (cmd_match(page, "resync"))
 		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-- 
2.31.1