Merge tag 'md-6.10-20240425' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-6.10/block

Pull MD fixes from Song:

"These changes contain various fixes by Yu Kuai, Li Nan, and
 Florian-Ewald Mueller."

* tag 'md-6.10-20240425' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md:
  md: don't account sync_io if iostats of the disk is disabled
  md: Fix overflow in is_mddev_idle
  md: add check for sleepers in md_wakeup_thread()
  md/raid5: fix deadlock that raid5d() wait for itself to clear MD_SB_CHANGE_PENDING

Author: axboe

drivers/md/md.c

@@ -8087,7 +8087,8 @@ void md_wakeup_thread(struct md_thread __rcu *thread)
 	if (t) {
 		pr_debug("md: waking up MD thread %s.\n", t->tsk->comm);
 		set_bit(THREAD_WAKEUP, &t->flags);
-		wake_up(&t->wqueue);
+		if (wq_has_sleeper(&t->wqueue))
+			wake_up(&t->wqueue);
 	}
 	rcu_read_unlock();
 }
@@ -8576,14 +8577,19 @@ static int is_mddev_idle(struct mddev *mddev, int init)
 {
 	struct md_rdev *rdev;
 	int idle;
-	int curr_events;
+	long long curr_events;
 
 	idle = 1;
 	rcu_read_lock();
 	rdev_for_each_rcu(rdev, mddev) {
 		struct gendisk *disk = rdev->bdev->bd_disk;
-		curr_events = (int)part_stat_read_accum(disk->part0, sectors) -
-			      atomic_read(&disk->sync_io);
+
+		if (!init && !blk_queue_io_stat(disk->queue))
+			continue;
+
+		curr_events =
+			(long long)part_stat_read_accum(disk->part0, sectors) -
+			atomic64_read(&disk->sync_io);
 		/* sync IO will cause sync_io to increase before the disk_stats
 		 * as sync_io is counted when a request starts, and
 		 * disk_stats is counted when it completes.

drivers/md/md.h

@@ -51,7 +51,7 @@ struct md_rdev {
 
 	sector_t sectors;		/* Device size (in 512bytes sectors) */
 	struct mddev *mddev;		/* RAID array if running */
-	int last_events;		/* IO event timestamp */
+	long long last_events;		/* IO event timestamp */
 
 	/*
 	 * If meta_bdev is non-NULL, it means that a separate device is
@@ -621,7 +621,8 @@ extern void mddev_unlock(struct mddev *mddev);
 
 static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors)
 {
-	atomic_add(nr_sectors, &bdev->bd_disk->sync_io);
+	if (blk_queue_io_stat(bdev->bd_disk->queue))
+		atomic64_add(nr_sectors, &bdev->bd_disk->sync_io);
 }
 
 static inline void md_sync_acct_bio(struct bio *bio, unsigned long nr_sectors)

drivers/md/raid5.c

@@ -36,7 +36,6 @@
  */
 
 #include <linux/blkdev.h>
-#include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/async_tx.h>
@@ -6734,6 +6733,9 @@ static void raid5d(struct md_thread *thread)
 		int batch_size, released;
 		unsigned int offset;
 
+		if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
+			break;
+
 		released = release_stripe_list(conf, conf->temp_inactive_list);
 		if (released)
 			clear_bit(R5_DID_ALLOC, &conf->cache_state);
@@ -6770,18 +6772,7 @@ static void raid5d(struct md_thread *thread)
 			spin_unlock_irq(&conf->device_lock);
 			md_check_recovery(mddev);
 			spin_lock_irq(&conf->device_lock);
-
-			/*
-			 * Waiting on MD_SB_CHANGE_PENDING below may deadlock
-			 * seeing md_check_recovery() is needed to clear
-			 * the flag when using mdmon.
-			 */
-			continue;
 		}
-
-		wait_event_lock_irq(mddev->sb_wait,
-			!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
-			conf->device_lock);
 	}
 	pr_debug("%d stripes handled\n", handled);
 

include/linux/blkdev.h

@@ -172,7 +172,7 @@ struct gendisk {
 	struct list_head slave_bdevs;
 #endif
 	struct timer_rand_state *random;
-	atomic_t sync_io;		/* RAID */
+	atomic64_t sync_io;		/* RAID */
 	struct disk_events *ev;
 
 #ifdef CONFIG_BLK_DEV_ZONED