Merge tag 'md-6.16-20250513' of https://git.kernel.org/pub/scm/linux/kernel/git/mdraid/linux into for-6.16/block

Pull MD changes from Yu Kuai:

- Fix that normal IO can be starved by sync IO, found by mkfs on newly
  created large raid5, with some clean up patches for bdev inflight
  counters.

* tag 'md-6.16-20250513' of https://git.kernel.org/pub/scm/linux/kernel/git/mdraid/linux:
  md: clean up accounting for issued sync IO
  md: fix is_mddev_idle()
  md: add a new api sync_io_depth
  md: record dm-raid gendisk in mddev
  block: export API to get the number of bdev inflight IO
  block: clean up blk_mq_in_flight_rw()
  block: WARN if bdev inflight counter is negative
  block: reuse part_in_flight_rw for part_in_flight
  blk-mq: remove blk_mq_in_flight()

5 files changed, 48 insertions, 51 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index e8cc270a453f..b862c66018f2 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1018,7 +1018,7 @@ again:
 	stamp = READ_ONCE(part->bd_stamp);
 	if (unlikely(time_after(now, stamp)) &&
 	    likely(try_cmpxchg(&part->bd_stamp, &stamp, now)) &&
-	    (end || part_in_flight(part)))
+	    (end || bdev_count_inflight(part)))
 		__part_stat_add(part, io_ticks, now - stamp);
 
 	if (bdev_is_partition(part)) {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index cbc9a9f97a31..4806b867e37d 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -89,7 +89,7 @@ struct mq_inflight {
 	unsigned int inflight[2];
 };
 
-static bool blk_mq_check_inflight(struct request *rq, void *priv)
+static bool blk_mq_check_in_driver(struct request *rq, void *priv)
 {
 	struct mq_inflight *mi = priv;
 
@@ -101,24 +101,14 @@ static bool blk_mq_check_inflight(struct request *rq, void *priv)
 	return true;
 }
 
-unsigned int blk_mq_in_flight(struct request_queue *q,
-		struct block_device *part)
+void blk_mq_in_driver_rw(struct block_device *part, unsigned int inflight[2])
 {
 	struct mq_inflight mi = { .part = part };
 
-	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
-
-	return mi.inflight[0] + mi.inflight[1];
-}
-
-void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part,
-		unsigned int inflight[2])
-{
-	struct mq_inflight mi = { .part = part };
-
-	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
-	inflight[0] = mi.inflight[0];
-	inflight[1] = mi.inflight[1];
+	blk_mq_queue_tag_busy_iter(bdev_get_queue(part), blk_mq_check_in_driver,
+				   &mi);
+	inflight[READ] = mi.inflight[READ];
+	inflight[WRITE] = mi.inflight[WRITE];
 }
 
 #ifdef CONFIG_LOCKDEP
diff --git a/block/blk-mq.h b/block/blk-mq.h
index d15ff1e130c8..affb2e14b56e 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -246,10 +246,7 @@ static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
 	return hctx->nr_ctx && hctx->tags;
 }
 
-unsigned int blk_mq_in_flight(struct request_queue *q,
-		struct block_device *part);
-void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part,
-		unsigned int inflight[2]);
+void blk_mq_in_driver_rw(struct block_device *part, unsigned int inflight[2]);
 
 static inline void blk_mq_put_dispatch_budget(struct request_queue *q,
 					      int budget_token)
diff --git a/block/blk.h b/block/blk.h
index 665b3d1fb504..21af4f0c4c00 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -419,7 +419,6 @@ void blk_apply_bdi_limits(struct backing_dev_info *bdi,
 int blk_dev_init(void);
 
 void update_io_ticks(struct block_device *part, unsigned long now, bool end);
-unsigned int part_in_flight(struct block_device *part);
 
 static inline void req_set_nomerge(struct request_queue *q, struct request *req)
 {
diff --git a/block/genhd.c b/block/genhd.c
index 9c7c657380db..8171a6bc3210 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -125,37 +125,46 @@ static void part_stat_read_all(struct block_device *part,
 	}
 }
 
-unsigned int part_in_flight(struct block_device *part)
+static void bdev_count_inflight_rw(struct block_device *part,
+		unsigned int inflight[2], bool mq_driver)
 {
-	unsigned int inflight = 0;
 	int cpu;
 
-	for_each_possible_cpu(cpu) {
-		inflight += part_stat_local_read_cpu(part, in_flight[0], cpu) +
-			    part_stat_local_read_cpu(part, in_flight[1], cpu);
+	if (mq_driver) {
+		blk_mq_in_driver_rw(part, inflight);
+	} else {
+		for_each_possible_cpu(cpu) {
+			inflight[READ] += part_stat_local_read_cpu(
+						part, in_flight[READ], cpu);
+			inflight[WRITE] += part_stat_local_read_cpu(
+						part, in_flight[WRITE], cpu);
+		}
 	}
-	if ((int)inflight < 0)
-		inflight = 0;
 
-	return inflight;
+	if (WARN_ON_ONCE((int)inflight[READ] < 0))
+		inflight[READ] = 0;
+	if (WARN_ON_ONCE((int)inflight[WRITE] < 0))
+		inflight[WRITE] = 0;
 }
 
-static void part_in_flight_rw(struct block_device *part,
-		unsigned int inflight[2])
+/**
+ * bdev_count_inflight - get the number of inflight IOs for a block device.
+ *
+ * @part: the block device.
+ *
+ * Inflight here means started IO accounting, from bdev_start_io_acct() for
+ * bio-based block device, and from blk_account_io_start() for rq-based block
+ * device.
+ */
+unsigned int bdev_count_inflight(struct block_device *part)
 {
-	int cpu;
+	unsigned int inflight[2] = {0};
 
-	inflight[0] = 0;
-	inflight[1] = 0;
-	for_each_possible_cpu(cpu) {
-		inflight[0] += part_stat_local_read_cpu(part, in_flight[0], cpu);
-		inflight[1] += part_stat_local_read_cpu(part, in_flight[1], cpu);
-	}
-	if ((int)inflight[0] < 0)
-		inflight[0] = 0;
-	if ((int)inflight[1] < 0)
-		inflight[1] = 0;
+	bdev_count_inflight_rw(part, inflight, false);
+
+	return inflight[READ] + inflight[WRITE];
 }
+EXPORT_SYMBOL_GPL(bdev_count_inflight);
 
 /*
  * Can be deleted altogether. Later.
@@ -1053,7 +1062,7 @@ ssize_t part_stat_show(struct device *dev,
 	struct disk_stats stat;
 	unsigned int inflight;
 
-	inflight = part_in_flight(bdev);
+	inflight = bdev_count_inflight(bdev);
 	if (inflight) {
 		part_stat_lock();
 		update_io_ticks(bdev, jiffies, true);
@@ -1090,19 +1099,21 @@ ssize_t part_stat_show(struct device *dev,
 		(unsigned int)div_u64(stat.nsecs[STAT_FLUSH], NSEC_PER_MSEC));
 }
 
+/*
+ * Show the number of IOs issued to driver.
+ * For bio-based device, started from bdev_start_io_acct();
+ * For rq-based device, started from blk_mq_start_request();
+ */
 ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
 	struct block_device *bdev = dev_to_bdev(dev);
 	struct request_queue *q = bdev_get_queue(bdev);
-	unsigned int inflight[2];
+	unsigned int inflight[2] = {0};
 
-	if (queue_is_mq(q))
-		blk_mq_in_flight_rw(q, bdev, inflight);
-	else
-		part_in_flight_rw(bdev, inflight);
+	bdev_count_inflight_rw(bdev, inflight, queue_is_mq(q));
 
-	return sysfs_emit(buf, "%8u %8u\n", inflight[0], inflight[1]);
+	return sysfs_emit(buf, "%8u %8u\n", inflight[READ], inflight[WRITE]);
 }
 
 static ssize_t disk_capability_show(struct device *dev,
@@ -1355,7 +1366,7 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 		if (bdev_is_partition(hd) && !bdev_nr_sectors(hd))
 			continue;
 
-		inflight = part_in_flight(hd);
+		inflight = bdev_count_inflight(hd);
 		if (inflight) {
 			part_stat_lock();
 			update_io_ticks(hd, jiffies, true);