Received-SPF: pass (google.com: domain of linux-kernel+bounces-43809-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.48.161 as permitted sender) client-ip=147.75.48.161;
From: Yu Kuai <yukuai1@huaweicloud.com>
To: mpatocka@redhat.com,
	heinzm@redhat.com,
	xni@redhat.com,
	agk@redhat.com,
	snitzer@kernel.org,
	dm-devel@lists.linux.dev,
	song@kernel.org,
	yukuai3@huawei.com,
	jbrassow@f14.redhat.com,
	neilb@suse.de,
	shli@fb.com,
	akpm@osdl.org
Cc: linux-kernel@vger.kernel.org,
	linux-raid@vger.kernel.org,
	yukuai1@huaweicloud.com,
	yi.zhang@huawei.com,
	yangerkun@huawei.com
Subject: [PATCH v4 04/14] md: don't register sync_thread for reshape directly
Date: Tue, 30 Jan 2024 10:18:33 +0800
Message-Id: <20240130021843.3608859-5-yukuai1@huaweicloud.com>
In-Reply-To: <20240130021843.3608859-1-yukuai1@huaweicloud.com>
References: <20240130021843.3608859-1-yukuai1@huaweicloud.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

From: Yu Kuai <yukuai3@huawei.com>

Currently, if reshape is interrupted, then reassemble the array will
register sync_thread directly from pers->run(), in this case
'MD_RECOVERY_RUNNING' is set directly, however, there is no guarantee
that md_do_sync() will be executed, hence stop_sync_thread() will hang
because 'MD_RECOVERY_RUNNING' can't be cleared.

Last patch make sure that md_do_sync() will set MD_RECOVERY_DONE,
however, following hang can still be triggered by dm-raid test
shell/lvconvert-raid-reshape.sh occasionally:

[root@fedora ~]# cat /proc/1982/stack
[<0>] stop_sync_thread+0x1ab/0x270 [md_mod]
[<0>] md_frozen_sync_thread+0x5c/0xa0 [md_mod]
[<0>] raid_presuspend+0x1e/0x70 [dm_raid]
[<0>] dm_table_presuspend_targets+0x40/0xb0 [dm_mod]
[<0>] __dm_destroy+0x2a5/0x310 [dm_mod]
[<0>] dm_destroy+0x16/0x30 [dm_mod]
[<0>] dev_remove+0x165/0x290 [dm_mod]
[<0>] ctl_ioctl+0x4bb/0x7b0 [dm_mod]
[<0>] dm_ctl_ioctl+0x11/0x20 [dm_mod]
[<0>] vfs_ioctl+0x21/0x60
[<0>] __x64_sys_ioctl+0xb9/0xe0
[<0>] do_syscall_64+0xc6/0x230
[<0>] entry_SYSCALL_64_after_hwframe+0x6c/0x74

Meanwhile mddev->recovery is:
MD_RECOVERY_RUNNING |
MD_RECOVERY_INTR |
MD_RECOVERY_RESHAPE |
MD_RECOVERY_FROZEN

Fix this problem by remove the code to register sync_thread directly
from raid10 and raid5. And let md_check_recovery() to register
sync_thread.

Fixes: f67055780caa ("[PATCH] md: Checkpoint and allow restart of raid5 reshape")
Fixes: f52f5c71f3d4 ("md: fix stopping sync thread")
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 drivers/md/md.c     |  5 ++++-
 drivers/md/raid10.c | 16 ++--------------
 drivers/md/raid5.c  | 29 ++---------------------------
 3 files changed, 8 insertions(+), 42 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index c65dfd156090..6c5d0a372927 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -9372,6 +9372,7 @@ static void md_start_sync(struct work_struct *ws)
 	struct mddev *mddev = container_of(ws, struct mddev, sync_work);
 	int spares = 0;
 	bool suspend = false;
+	char *name;
 
 	if (md_spares_need_change(mddev))
 		suspend = true;
@@ -9404,8 +9405,10 @@ static void md_start_sync(struct work_struct *ws)
 	if (spares)
 		md_bitmap_write_all(mddev->bitmap);
 
+	name = test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) ?
+			"reshape" : "resync";
 	rcu_assign_pointer(mddev->sync_thread,
-			   md_register_thread(md_do_sync, mddev, "resync"));
+			   md_register_thread(md_do_sync, mddev, name));
 	if (!mddev->sync_thread) {
 		pr_warn("%s: could not start resync thread...\n",
 			mdname(mddev));
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 7412066ea22c..a5f8419e2df1 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4175,11 +4175,7 @@ static int raid10_run(struct mddev *mddev)
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-		set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-		rcu_assign_pointer(mddev->sync_thread,
-			md_register_thread(md_do_sync, mddev, "reshape"));
-		if (!mddev->sync_thread)
-			goto out_free_conf;
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
 
 	return 0;
@@ -4573,16 +4569,8 @@ static int raid10_start_reshape(struct mddev *mddev)
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 	clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-	set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-
-	rcu_assign_pointer(mddev->sync_thread,
-			   md_register_thread(md_do_sync, mddev, "reshape"));
-	if (!mddev->sync_thread) {
-		ret = -EAGAIN;
-		goto abort;
-	}
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	conf->reshape_checkpoint = jiffies;
-	md_wakeup_thread(mddev->sync_thread);
 	md_new_event();
 	return 0;
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 8497880135ee..6a7a32f7fb91 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7936,11 +7936,7 @@ static int raid5_run(struct mddev *mddev)
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-		set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-		rcu_assign_pointer(mddev->sync_thread,
-			md_register_thread(md_do_sync, mddev, "reshape"));
-		if (!mddev->sync_thread)
-			goto abort;
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
 
 	/* Ok, everything is just fine now */
@@ -8506,29 +8502,8 @@ static int raid5_start_reshape(struct mddev *mddev)
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 	clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-	set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-	rcu_assign_pointer(mddev->sync_thread,
-			   md_register_thread(md_do_sync, mddev, "reshape"));
-	if (!mddev->sync_thread) {
-		mddev->recovery = 0;
-		spin_lock_irq(&conf->device_lock);
-		write_seqcount_begin(&conf->gen_lock);
-		mddev->raid_disks = conf->raid_disks = conf->previous_raid_disks;
-		mddev->new_chunk_sectors =
-			conf->chunk_sectors = conf->prev_chunk_sectors;
-		mddev->new_layout = conf->algorithm = conf->prev_algo;
-		rdev_for_each(rdev, mddev)
-			rdev->new_data_offset = rdev->data_offset;
-		smp_wmb();
-		conf->generation --;
-		conf->reshape_progress = MaxSector;
-		mddev->reshape_position = MaxSector;
-		write_seqcount_end(&conf->gen_lock);
-		spin_unlock_irq(&conf->device_lock);
-		return -EAGAIN;
-	}
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	conf->reshape_checkpoint = jiffies;
-	md_wakeup_thread(mddev->sync_thread);
 	md_new_event();
 	return 0;
 }
-- 
2.39.2