Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.36 as permitted sender) client-ip=23.128.96.36;
From:   Yu Kuai <yukuai1@huaweicloud.com>
To:     xni@redhat.com, agk@redhat.com, snitzer@kernel.org,
        dm-devel@redhat.com, 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 v3 03/25] md: add new helpers to suspend/resume array
Date:   Thu, 28 Sep 2023 14:15:21 +0800
Message-Id: <20230928061543.1845742-4-yukuai1@huaweicloud.com>
In-Reply-To: <20230928061543.1845742-1-yukuai1@huaweicloud.com>
References: <20230928061543.1845742-1-yukuai1@huaweicloud.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Yu Kuai <yukuai3@huawei.com>

Advantages for new apis:
 - reconfig_mutex is not required;
 - the weird logical that suspend array hold 'reconfig_mutex' for
   mddev_check_recovery() to update superblock is not needed;
 - the specail handling, 'pers->prepare_suspend', for raid456 is not
   needed;
 - It's safe to be called at any time once mddev is allocated, and it's
   designed to be used from slow path where array configuration is changed;
 - the new helpers is designed to be called before mddev_lock(), hence
   it support to be interrupted by user as well.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 drivers/md/md.c | 102 +++++++++++++++++++++++++++++++++++++++++++++++-
 drivers/md/md.h |   3 ++
 2 files changed, 103 insertions(+), 2 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index e460b380143d..a075d03d03d3 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -443,12 +443,22 @@ void mddev_suspend(struct mddev *mddev)
 			lockdep_is_held(&mddev->reconfig_mutex));
 
 	WARN_ON_ONCE(thread && current == thread->tsk);
-	if (mddev->suspended++)
+
+	/* can't concurrent with __mddev_suspend() and __mddev_resume() */
+	mutex_lock(&mddev->suspend_mutex);
+	if (mddev->suspended++) {
+		mutex_unlock(&mddev->suspend_mutex);
 		return;
+	}
+
 	wake_up(&mddev->sb_wait);
 	set_bit(MD_ALLOW_SB_UPDATE, &mddev->flags);
 	percpu_ref_kill(&mddev->active_io);
 
+	/*
+	 * TODO: cleanup 'pers->prepare_suspend after all callers are replaced
+	 * by __mddev_suspend().
+	 */
 	if (mddev->pers && mddev->pers->prepare_suspend)
 		mddev->pers->prepare_suspend(mddev);
 
@@ -459,14 +469,21 @@ void mddev_suspend(struct mddev *mddev)
 	del_timer_sync(&mddev->safemode_timer);
 	/* restrict memory reclaim I/O during raid array is suspend */
 	mddev->noio_flag = memalloc_noio_save();
+
+	mutex_unlock(&mddev->suspend_mutex);
 }
 EXPORT_SYMBOL_GPL(mddev_suspend);
 
 void mddev_resume(struct mddev *mddev)
 {
 	lockdep_assert_held(&mddev->reconfig_mutex);
-	if (--mddev->suspended)
+
+	/* can't concurrent with __mddev_suspend() and __mddev_resume() */
+	mutex_lock(&mddev->suspend_mutex);
+	if (--mddev->suspended) {
+		mutex_unlock(&mddev->suspend_mutex);
 		return;
+	}
 
 	/* entred the memalloc scope from mddev_suspend() */
 	memalloc_noio_restore(mddev->noio_flag);
@@ -477,9 +494,89 @@ void mddev_resume(struct mddev *mddev)
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
+
+	mutex_unlock(&mddev->suspend_mutex);
 }
 EXPORT_SYMBOL_GPL(mddev_resume);
 
+int __mddev_suspend(struct mddev *mddev, bool interruptible)
+{
+	int err = 0;
+
+	/*
+	 * hold reconfig_mutex to wait for normal io will deadlock, because
+	 * other context can't update super_block, and normal io can rely on
+	 * updating super_block.
+	 */
+	lockdep_assert_not_held(&mddev->reconfig_mutex);
+
+	if (interruptible)
+		err = mutex_lock_interruptible(&mddev->suspend_mutex);
+	else
+		mutex_lock(&mddev->suspend_mutex);
+	if (err)
+		return err;
+
+	if (mddev->suspended) {
+		WRITE_ONCE(mddev->suspended, mddev->suspended + 1);
+		mutex_unlock(&mddev->suspend_mutex);
+		return 0;
+	}
+
+	percpu_ref_kill(&mddev->active_io);
+	if (interruptible)
+		err = wait_event_interruptible(mddev->sb_wait,
+				percpu_ref_is_zero(&mddev->active_io));
+	else
+		wait_event(mddev->sb_wait,
+				percpu_ref_is_zero(&mddev->active_io));
+	if (err) {
+		percpu_ref_resurrect(&mddev->active_io);
+		mutex_unlock(&mddev->suspend_mutex);
+		return err;
+	}
+
+	/*
+	 * For raid456, io might be waiting for reshape to make progress,
+	 * allow new reshape to start while waiting for io to be done to
+	 * prevent deadlock.
+	 */
+	WRITE_ONCE(mddev->suspended, mddev->suspended + 1);
+
+	del_timer_sync(&mddev->safemode_timer);
+	/* restrict memory reclaim I/O during raid array is suspend */
+	mddev->noio_flag = memalloc_noio_save();
+
+	mutex_unlock(&mddev->suspend_mutex);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__mddev_suspend);
+
+void __mddev_resume(struct mddev *mddev)
+{
+	lockdep_assert_not_held(&mddev->reconfig_mutex);
+
+	mutex_lock(&mddev->suspend_mutex);
+	WRITE_ONCE(mddev->suspended, mddev->suspended - 1);
+	if (mddev->suspended) {
+		mutex_unlock(&mddev->suspend_mutex);
+		return;
+	}
+
+	/* entred the memalloc scope from __mddev_suspend() */
+	memalloc_noio_restore(mddev->noio_flag);
+
+	percpu_ref_resurrect(&mddev->active_io);
+	wake_up(&mddev->sb_wait);
+
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	md_wakeup_thread(mddev->thread);
+	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
+
+	mutex_unlock(&mddev->suspend_mutex);
+}
+EXPORT_SYMBOL_GPL(__mddev_resume);
+
 /*
  * Generic flush handling for md
  */
@@ -672,6 +769,7 @@ int mddev_init(struct mddev *mddev)
 	mutex_init(&mddev->open_mutex);
 	mutex_init(&mddev->reconfig_mutex);
 	mutex_init(&mddev->sync_mutex);
+	mutex_init(&mddev->suspend_mutex);
 	mutex_init(&mddev->bitmap_info.mutex);
 	INIT_LIST_HEAD(&mddev->disks);
 	INIT_LIST_HEAD(&mddev->all_mddevs);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index b628c292506e..b5894dc64615 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -316,6 +316,7 @@ struct mddev {
 	unsigned long			sb_flags;
 
 	int				suspended;
+	struct mutex			suspend_mutex;
 	struct percpu_ref		active_io;
 	int				ro;
 	int				sysfs_active; /* set when sysfs deletes
@@ -811,6 +812,8 @@ extern void md_rdev_clear(struct md_rdev *rdev);
 extern void md_handle_request(struct mddev *mddev, struct bio *bio);
 extern void mddev_suspend(struct mddev *mddev);
 extern void mddev_resume(struct mddev *mddev);
+extern int __mddev_suspend(struct mddev *mddev, bool interruptible);
+extern void __mddev_resume(struct mddev *mddev);
 
 extern void md_reload_sb(struct mddev *mddev, int raid_disk);
 extern void md_update_sb(struct mddev *mddev, int force);
-- 
2.39.2