linux-raid.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Xiao Ni <xni@redhat.com>
To: song@kernel.org
Cc: yukuai1@huaweicloud.com, bmarzins@redhat.com, heinzm@redhat.com,
	snitzer@kernel.org, ncroxon@redhat.com,
	linux-raid@vger.kernel.org, dm-devel@lists.linux.dev
Subject: [PATCH 1/6] md: Revert "md: Don't register sync_thread for reshape directly"
Date: Thu, 29 Feb 2024 23:49:36 +0800	[thread overview]
Message-ID: <20240229154941.99557-2-xni@redhat.com> (raw)
In-Reply-To: <20240229154941.99557-1-xni@redhat.com>

This reverts commit ad39c08186f8a0f221337985036ba86731d6aafe.

Function stop_sync_thread only wakes up sync task. It also needs to
wake up sync thread. This problem will be fixed in the following
patch.

Signed-off-by: Xiao Ni <xni@redhat.com>
---
 drivers/md/md.c     |  5 +----
 drivers/md/raid10.c | 16 ++++++++++++++--
 drivers/md/raid5.c  | 29 +++++++++++++++++++++++++++--
 3 files changed, 42 insertions(+), 8 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 9e41a9aaba8b..db4743ba7f6c 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -9376,7 +9376,6 @@ 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 reshape is still in progress, spares won't be added or removed
@@ -9414,10 +9413,8 @@ 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, name));
+			   md_register_thread(md_do_sync, mddev, "resync"));
 	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 a5f8419e2df1..7412066ea22c 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4175,7 +4175,11 @@ 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_NEEDED, &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;
 	}
 
 	return 0;
@@ -4569,8 +4573,16 @@ 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_NEEDED, &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;
+	}
 	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 6a7a32f7fb91..8497880135ee 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7936,7 +7936,11 @@ 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_NEEDED, &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;
 	}
 
 	/* Ok, everything is just fine now */
@@ -8502,8 +8506,29 @@ 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_NEEDED, &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;
+	}
 	conf->reshape_checkpoint = jiffies;
+	md_wakeup_thread(mddev->sync_thread);
 	md_new_event();
 	return 0;
 }
-- 
2.32.0 (Apple Git-132)


  reply	other threads:[~2024-02-29 15:49 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-29 15:49 [PATCH 0/6] Fix dmraid regression bugs Xiao Ni
2024-02-29 15:49 ` Xiao Ni [this message]
2024-03-01  2:38   ` [PATCH 1/6] md: Revert "md: Don't register sync_thread for reshape directly" Yu Kuai
2024-03-01  4:41     ` Xiao Ni
2024-02-29 15:49 ` [PATCH 2/6] md: Revert "md: Make sure md_do_sync() will set MD_RECOVERY_DONE" Xiao Ni
2024-02-29 22:53   ` Song Liu
2024-02-29 23:45     ` Song Liu
2024-03-01  0:49       ` Xiao Ni
2024-03-01  1:11         ` Song Liu
2024-02-29 15:49 ` [PATCH 3/6] md: Revert "md: Don't ignore suspended array in md_check_recovery()" Xiao Ni
2024-02-29 15:49 ` [PATCH 4/6] dm-raid/md: Clear MD_RECOVERY_WAIT when stopping dmraid Xiao Ni
2024-03-01  2:44   ` Yu Kuai
2024-03-01  4:19     ` Xiao Ni
2024-02-29 15:49 ` [PATCH 5/6] md: Set MD_RECOVERY_FROZEN before stop sync thread Xiao Ni
2024-02-29 15:49 ` [PATCH 6/6] md/raid5: Don't check crossing reshape when reshape hasn't started Xiao Ni
2024-02-29 19:39 ` [PATCH 0/6] Fix dmraid regression bugs Christoph Hellwig
2024-02-29 19:45   ` Song Liu
2024-03-01  2:12 ` Yu Kuai
2024-03-01  2:22   ` Xiao Ni

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20240229154941.99557-2-xni@redhat.com \
    --to=xni@redhat.com \
    --cc=bmarzins@redhat.com \
    --cc=dm-devel@lists.linux.dev \
    --cc=heinzm@redhat.com \
    --cc=linux-raid@vger.kernel.org \
    --cc=ncroxon@redhat.com \
    --cc=snitzer@kernel.org \
    --cc=song@kernel.org \
    --cc=yukuai1@huaweicloud.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).