Merge tag 'md-next-20230613' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-6.5/block

Pull MD updates from Song:

"The major changes are:

 1. Protect md_thread with rcu, by Yu Kuai;
 2. Various non-urgent raid5 and raid1/10 fixes, by Yu Kuai;
 3. Non-urgent raid10 fixes, by Li Nan."

* tag 'md-next-20230613' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md: (29 commits)
  md/raid1-10: limit the number of plugged bio
  md/raid1-10: don't handle pluged bio by daemon thread
  md/md-bitmap: add a new helper to unplug bitmap asynchrously
  md/raid1-10: submit write io directly if bitmap is not enabled
  md/raid1-10: factor out a helper to submit normal write
  md/raid1-10: factor out a helper to add bio to plug
  md/raid10: prevent soft lockup while flush writes
  md/raid10: fix io loss while replacement replace rdev
  md/raid10: Do not add spare disk when recovery fails
  md/raid10: clean up md_add_new_disk()
  md/raid10: prioritize adding disk to 'removed' mirror
  md/raid10: improve code of mrdev in raid10_sync_request
  md/raid10: fix null-ptr-deref of mreplace in raid10_sync_request
  md/raid5: don't start reshape when recovery or replace is in progress
  md: protect md_thread with rcu
  md/bitmap: factor out a helper to set timeout
  md/bitmap: always wake up md_thread in timeout_store
  dm-raid: remove useless checking in raid_message()
  md: factor out a helper to wake up md_thread directly
  md: fix duplicate filename for rdev
  ...

Author: axboe

drivers/md/dm-raid.c

@@ -3750,11 +3750,11 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
 		 * canceling read-auto mode
 		 */
 		mddev->ro = 0;
-		if (!mddev->suspended && mddev->sync_thread)
+		if (!mddev->suspended)
 			md_wakeup_thread(mddev->sync_thread);
 	}
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	if (!mddev->suspended && mddev->thread)
+	if (!mddev->suspended)
 		md_wakeup_thread(mddev->thread);
 
 	return 0;

drivers/md/md-bitmap.c

@@ -54,14 +54,7 @@ __acquires(bitmap->lock)
 {
 	unsigned char *mappage;
 
-	if (page >= bitmap->pages) {
-		/* This can happen if bitmap_start_sync goes beyond
-		 * End-of-device while looking for a whole page.
-		 * It is harmless.
-		 */
-		return -EINVAL;
-	}
-
+	WARN_ON_ONCE(page >= bitmap->pages);
 	if (bitmap->bp[page].hijacked) /* it's hijacked, don't try to alloc */
 		return 0;
 
@@ -1023,7 +1016,6 @@ static int md_bitmap_file_test_bit(struct bitmap *bitmap, sector_t block)
 	return set;
 }
 
-
 /* this gets called when the md device is ready to unplug its underlying
  * (slave) device queues -- before we let any writes go down, we need to
  * sync the dirty pages of the bitmap file to disk */
@@ -1033,8 +1025,7 @@ void md_bitmap_unplug(struct bitmap *bitmap)
 	int dirty, need_write;
 	int writing = 0;
 
-	if (!bitmap || !bitmap->storage.filemap ||
-	    test_bit(BITMAP_STALE, &bitmap->flags))
+	if (!md_bitmap_enabled(bitmap))
 		return;
 
 	/* look at each page to see if there are any set bits that need to be
@@ -1063,6 +1054,35 @@ void md_bitmap_unplug(struct bitmap *bitmap)
 }
 EXPORT_SYMBOL(md_bitmap_unplug);
 
+struct bitmap_unplug_work {
+	struct work_struct work;
+	struct bitmap *bitmap;
+	struct completion *done;
+};
+
+static void md_bitmap_unplug_fn(struct work_struct *work)
+{
+	struct bitmap_unplug_work *unplug_work =
+		container_of(work, struct bitmap_unplug_work, work);
+
+	md_bitmap_unplug(unplug_work->bitmap);
+	complete(unplug_work->done);
+}
+
+void md_bitmap_unplug_async(struct bitmap *bitmap)
+{
+	DECLARE_COMPLETION_ONSTACK(done);
+	struct bitmap_unplug_work unplug_work;
+
+	INIT_WORK_ONSTACK(&unplug_work.work, md_bitmap_unplug_fn);
+	unplug_work.bitmap = bitmap;
+	unplug_work.done = &done;
+
+	queue_work(md_bitmap_wq, &unplug_work.work);
+	wait_for_completion(&done);
+}
+EXPORT_SYMBOL(md_bitmap_unplug_async);
+
 static void md_bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed);
 /* * bitmap_init_from_disk -- called at bitmap_create time to initialize
  * the in-memory bitmap from the on-disk bitmap -- also, sets up the
@@ -1241,11 +1261,28 @@ static bitmap_counter_t *md_bitmap_get_counter(struct bitmap_counts *bitmap,
 					       sector_t offset, sector_t *blocks,
 					       int create);
 
+static void mddev_set_timeout(struct mddev *mddev, unsigned long timeout,
+			      bool force)
+{
+	struct md_thread *thread;
+
+	rcu_read_lock();
+	thread = rcu_dereference(mddev->thread);
+
+	if (!thread)
+		goto out;
+
+	if (force || thread->timeout < MAX_SCHEDULE_TIMEOUT)
+		thread->timeout = timeout;
+
+out:
+	rcu_read_unlock();
+}
+
 /*
  * bitmap daemon -- periodically wakes up to clean bits and flush pages
  *			out to disk
  */
-
 void md_bitmap_daemon_work(struct mddev *mddev)
 {
 	struct bitmap *bitmap;
@@ -1269,7 +1306,7 @@ void md_bitmap_daemon_work(struct mddev *mddev)
 
 	bitmap->daemon_lastrun = jiffies;
 	if (bitmap->allclean) {
-		mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
+		mddev_set_timeout(mddev, MAX_SCHEDULE_TIMEOUT, true);
 		goto done;
 	}
 	bitmap->allclean = 1;
@@ -1366,8 +1403,7 @@ void md_bitmap_daemon_work(struct mddev *mddev)
 
  done:
 	if (bitmap->allclean == 0)
-		mddev->thread->timeout =
-			mddev->bitmap_info.daemon_sleep;
+		mddev_set_timeout(mddev, mddev->bitmap_info.daemon_sleep, true);
 	mutex_unlock(&mddev->bitmap_info.mutex);
 }
 
@@ -1387,6 +1423,14 @@ __acquires(bitmap->lock)
 	sector_t csize;
 	int err;
 
+	if (page >= bitmap->pages) {
+		/*
+		 * This can happen if bitmap_start_sync goes beyond
+		 * End-of-device while looking for a whole page or
+		 * user set a huge number to sysfs bitmap_set_bits.
+		 */
+		return NULL;
+	}
 	err = md_bitmap_checkpage(bitmap, page, create, 0);
 
 	if (bitmap->bp[page].hijacked ||
@@ -1820,8 +1864,7 @@ void md_bitmap_destroy(struct mddev *mddev)
 	mddev->bitmap = NULL; /* disconnect from the md device */
 	spin_unlock(&mddev->lock);
 	mutex_unlock(&mddev->bitmap_info.mutex);
-	if (mddev->thread)
-		mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
+	mddev_set_timeout(mddev, MAX_SCHEDULE_TIMEOUT, true);
 
 	md_bitmap_free(bitmap);
 }
@@ -1964,7 +2007,7 @@ int md_bitmap_load(struct mddev *mddev)
 	/* Kick recovery in case any bits were set */
 	set_bit(MD_RECOVERY_NEEDED, &bitmap->mddev->recovery);
 
-	mddev->thread->timeout = mddev->bitmap_info.daemon_sleep;
+	mddev_set_timeout(mddev, mddev->bitmap_info.daemon_sleep, true);
 	md_wakeup_thread(mddev->thread);
 
 	md_bitmap_update_sb(bitmap);
@@ -2469,17 +2512,11 @@ timeout_store(struct mddev *mddev, const char *buf, size_t len)
 		timeout = MAX_SCHEDULE_TIMEOUT-1;
 	if (timeout < 1)
 		timeout = 1;
+
 	mddev->bitmap_info.daemon_sleep = timeout;
-	if (mddev->thread) {
-		/* if thread->timeout is MAX_SCHEDULE_TIMEOUT, then
-		 * the bitmap is all clean and we don't need to
-		 * adjust the timeout right now
-		 */
-		if (mddev->thread->timeout < MAX_SCHEDULE_TIMEOUT) {
-			mddev->thread->timeout = timeout;
-			md_wakeup_thread(mddev->thread);
-		}
-	}
+	mddev_set_timeout(mddev, timeout, false);
+	md_wakeup_thread(mddev->thread);
+
 	return len;
 }
 

drivers/md/md-bitmap.h

@@ -264,6 +264,7 @@ void md_bitmap_sync_with_cluster(struct mddev *mddev,
 				 sector_t new_lo, sector_t new_hi);
 
 void md_bitmap_unplug(struct bitmap *bitmap);
+void md_bitmap_unplug_async(struct bitmap *bitmap);
 void md_bitmap_daemon_work(struct mddev *mddev);
 
 int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks,
@@ -273,6 +274,13 @@ int md_bitmap_copy_from_slot(struct mddev *mddev, int slot,
 			     sector_t *lo, sector_t *hi, bool clear_bits);
 void md_bitmap_free(struct bitmap *bitmap);
 void md_bitmap_wait_behind_writes(struct mddev *mddev);
+
+static inline bool md_bitmap_enabled(struct bitmap *bitmap)
+{
+	return bitmap && bitmap->storage.filemap &&
+	       !test_bit(BITMAP_STALE, &bitmap->flags);
+}
+
 #endif
 
 #endif

drivers/md/md-cluster.c

@@ -75,14 +75,14 @@ struct md_cluster_info {
 	sector_t suspend_hi;
 	int suspend_from; /* the slot which broadcast suspend_lo/hi */
 
-	struct md_thread *recovery_thread;
+	struct md_thread __rcu *recovery_thread;
 	unsigned long recovery_map;
 	/* communication loc resources */
 	struct dlm_lock_resource *ack_lockres;
 	struct dlm_lock_resource *message_lockres;
 	struct dlm_lock_resource *token_lockres;
 	struct dlm_lock_resource *no_new_dev_lockres;
-	struct md_thread *recv_thread;
+	struct md_thread __rcu *recv_thread;
 	struct completion newdisk_completion;
 	wait_queue_head_t wait;
 	unsigned long state;
@@ -362,8 +362,8 @@ static void __recover_slot(struct mddev *mddev, int slot)
 
 	set_bit(slot, &cinfo->recovery_map);
 	if (!cinfo->recovery_thread) {
-		cinfo->recovery_thread = md_register_thread(recover_bitmaps,
-				mddev, "recover");
+		rcu_assign_pointer(cinfo->recovery_thread,
+			md_register_thread(recover_bitmaps, mddev, "recover"));
 		if (!cinfo->recovery_thread) {
 			pr_warn("md-cluster: Could not create recovery thread\n");
 			return;
@@ -526,11 +526,15 @@ static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
 static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg)
 {
 	int got_lock = 0;
+	struct md_thread *thread;
 	struct md_cluster_info *cinfo = mddev->cluster_info;
 	mddev->good_device_nr = le32_to_cpu(msg->raid_slot);
 
 	dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR);
-	wait_event(mddev->thread->wqueue,
+
+	/* daemaon thread must exist */
+	thread = rcu_dereference_protected(mddev->thread, true);
+	wait_event(thread->wqueue,
 		   (got_lock = mddev_trylock(mddev)) ||
 		    test_bit(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state));
 	md_reload_sb(mddev, mddev->good_device_nr);
@@ -889,7 +893,8 @@ static int join(struct mddev *mddev, int nodes)
 	}
 	/* Initiate the communication resources */
 	ret = -ENOMEM;
-	cinfo->recv_thread = md_register_thread(recv_daemon, mddev, "cluster_recv");
+	rcu_assign_pointer(cinfo->recv_thread,
+			md_register_thread(recv_daemon, mddev, "cluster_recv"));
 	if (!cinfo->recv_thread) {
 		pr_err("md-cluster: cannot allocate memory for recv_thread!\n");
 		goto err;

drivers/md/md-multipath.c

@@ -400,8 +400,8 @@ static int multipath_run (struct mddev *mddev)
 	if (ret)
 		goto out_free_conf;
 
-	mddev->thread = md_register_thread(multipathd, mddev,
-					   "multipath");
+	rcu_assign_pointer(mddev->thread,
+			   md_register_thread(multipathd, mddev, "multipath"));
 	if (!mddev->thread)
 		goto out_free_conf;