md: introduce new personality funciton start()

In do_md_run(), md threads should not wake up until the array is fully
initialized in md_run(). However, in raid5_run(), raid5-cache may wake
up mddev->thread to flush stripes that need to be written back. This
design doesn't break badly right now. But it could lead to bad bug in
the future.

This patch tries to resolve this problem by splitting start up work
into two personality functions, run() and start(). Tasks that do not
require the md threads should go into run(), while task that require
the md threads go into start().

r5l_load_log() is moved to raid5_start(), so it is not called until
the md threads are started in do_md_run().

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Shaohua Li <shli@fb.com>

1 files changed, 20 insertions, 6 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4e4dee0ec2de..a71adb3c34b9 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5560,11 +5560,6 @@ int md_run(struct mddev *mddev)
 	if (start_readonly && mddev->ro == 0)
 		mddev->ro = 2; /* read-only, but switch on first write */
 
-	/*
-	 * NOTE: some pers->run(), for example r5l_recovery_log(), wakes
-	 * up mddev->thread. It is important to initialize critical
-	 * resources for mddev->thread BEFORE calling pers->run().
-	 */
 	err = pers->run(mddev);
 	if (err)
 		pr_warn("md: pers->run() failed ...\n");
@@ -5678,6 +5673,9 @@ static int do_md_run(struct mddev *mddev)
 	if (mddev_is_clustered(mddev))
 		md_allow_write(mddev);
 
+	/* run start up tasks that require md_thread */
+	md_start(mddev);
+
 	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
@@ -5689,6 +5687,21 @@ out:
 	return err;
 }
 
+int md_start(struct mddev *mddev)
+{
+	int ret = 0;
+
+	if (mddev->pers->start) {
+		set_bit(MD_RECOVERY_WAIT, &mddev->recovery);
+		md_wakeup_thread(mddev->thread);
+		ret = mddev->pers->start(mddev);
+		clear_bit(MD_RECOVERY_WAIT, &mddev->recovery);
+		md_wakeup_thread(mddev->sync_thread);
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(md_start);
+
 static int restart_array(struct mddev *mddev)
 {
 	struct gendisk *disk = mddev->gendisk;
@@ -8169,7 +8182,8 @@ void md_do_sync(struct md_thread *thread)
 	int ret;
 
 	/* just incase thread restarts... */
-	if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
+	if (test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
+	    test_bit(MD_RECOVERY_WAIT, &mddev->recovery))
 		return;
 	if (mddev->ro) {/* never try to sync a read-only array */
 		set_bit(MD_RECOVERY_INTR, &mddev->recovery);