md: add io accounting for raid0 and raid5

We introduce a new bioset (io_acct_set) for raid0 and raid5 since they
don't own clone infrastructure to accounting io. And the bioset is added
to mddev instead of to raid0 and raid5 layer, because with this way, we
can put common functions to md.h and reuse them in raid0 and raid5.

Also struct md_io_acct is added accordingly which includes io start_time,
the origin bio and cloned bio. Then we can call bio_{start,end}_io_acct
to get related io status.

Signed-off-by: Guoqing Jiang <jiangguoqing@kylinos.cn>
Signed-off-by: Song Liu <song@kernel.org>

Author: GuoqingJiang-Linux

drivers/md/md.c

@@ -2340,7 +2340,8 @@ int md_integrity_register(struct mddev *mddev)
 			       bdev_get_integrity(reference->bdev));
 
 	pr_debug("md: data integrity enabled on %s\n", mdname(mddev));
-	if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE)) {
+	if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE) ||
+	    bioset_integrity_create(&mddev->io_acct_set, BIO_POOL_SIZE)) {
 		pr_err("md: failed to create integrity pool for %s\n",
 		       mdname(mddev));
 		return -EINVAL;
@@ -5569,6 +5570,7 @@ static void md_free(struct kobject *ko)
 
 	bioset_exit(&mddev->bio_set);
 	bioset_exit(&mddev->sync_set);
+	bioset_exit(&mddev->io_acct_set);
 	kfree(mddev);
 }
 
@@ -5862,7 +5864,13 @@ int md_run(struct mddev *mddev)
 	if (!bioset_initialized(&mddev->sync_set)) {
 		err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
 		if (err)
-			return err;
+			goto exit_bio_set;
+	}
+	if (!bioset_initialized(&mddev->io_acct_set)) {
+		err = bioset_init(&mddev->io_acct_set, BIO_POOL_SIZE,
+				  offsetof(struct md_io_acct, bio_clone), 0);
+		if (err)
+			goto exit_sync_set;
 	}
 
 	spin_lock(&pers_lock);
@@ -5990,6 +5998,7 @@ int md_run(struct mddev *mddev)
 			blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue);
 		else
 			blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue);
+		blk_queue_flag_set(QUEUE_FLAG_IO_STAT, mddev->queue);
 	}
 	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
@@ -6039,8 +6048,11 @@ int md_run(struct mddev *mddev)
 	module_put(pers->owner);
 	md_bitmap_destroy(mddev);
 abort:
-	bioset_exit(&mddev->bio_set);
+	bioset_exit(&mddev->io_acct_set);
+exit_sync_set:
 	bioset_exit(&mddev->sync_set);
+exit_bio_set:
+	bioset_exit(&mddev->bio_set);
 	return err;
 }
 EXPORT_SYMBOL_GPL(md_run);
@@ -6264,6 +6276,7 @@ void md_stop(struct mddev *mddev)
 	__md_stop(mddev);
 	bioset_exit(&mddev->bio_set);
 	bioset_exit(&mddev->sync_set);
+	bioset_exit(&mddev->io_acct_set);
 }
 
 EXPORT_SYMBOL_GPL(md_stop);
@@ -8568,6 +8581,38 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 }
 EXPORT_SYMBOL_GPL(md_submit_discard_bio);
 
+static void md_end_io_acct(struct bio *bio)
+{
+	struct md_io_acct *md_io_acct = bio->bi_private;
+	struct bio *orig_bio = md_io_acct->orig_bio;
+
+	orig_bio->bi_status = bio->bi_status;
+
+	bio_end_io_acct(orig_bio, md_io_acct->start_time);
+	bio_put(bio);
+	bio_endio(orig_bio);
+}
+
+/* used by personalities (raid0 and raid5) to account io stats */
+void md_account_bio(struct mddev *mddev, struct bio **bio)
+{
+	struct md_io_acct *md_io_acct;
+	struct bio *clone;
+
+	if (!blk_queue_io_stat((*bio)->bi_bdev->bd_disk->queue))
+		return;
+
+	clone = bio_clone_fast(*bio, GFP_NOIO, &mddev->io_acct_set);
+	md_io_acct = container_of(clone, struct md_io_acct, bio_clone);
+	md_io_acct->orig_bio = *bio;
+	md_io_acct->start_time = bio_start_io_acct(*bio);
+
+	clone->bi_end_io = md_end_io_acct;
+	clone->bi_private = md_io_acct;
+	*bio = clone;
+}
+EXPORT_SYMBOL_GPL(md_account_bio);
+
 /* md_allow_write(mddev)
  * Calling this ensures that the array is marked 'active' so that writes
  * may proceed without blocking.  It is important to call this before

drivers/md/md.h

@@ -487,6 +487,7 @@ struct mddev {
 	struct bio_set			sync_set; /* for sync operations like
 						   * metadata and bitmap writes
 						   */
+	struct bio_set			io_acct_set; /* for raid0 and raid5 io accounting */
 
 	/* Generic flush handling.
 	 * The last to finish preflush schedules a worker to submit
@@ -683,6 +684,12 @@ struct md_thread {
 	void			*private;
 };
 
+struct md_io_acct {
+	struct bio *orig_bio;
+	unsigned long start_time;
+	struct bio bio_clone;
+};
+
 #define THREAD_WAKEUP  0
 
 static inline void safe_put_page(struct page *p)
@@ -714,6 +721,7 @@ extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
 extern void md_finish_reshape(struct mddev *mddev);
 void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 			struct bio *bio, sector_t start, sector_t size);
+void md_account_bio(struct mddev *mddev, struct bio **bio);
 
 extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,

drivers/md/raid0.c

@@ -546,6 +546,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 		bio = split;
 	}
 
+	if (bio->bi_pool != &mddev->bio_set)
+		md_account_bio(mddev, &bio);
+
 	orig_sector = sector;
 	zone = find_zone(mddev->private, &sector);
 	switch (conf->layout) {

drivers/md/raid5.c

@@ -5468,6 +5468,7 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
 	sector_t sector = raid_bio->bi_iter.bi_sector;
 	unsigned chunk_sects = mddev->chunk_sectors;
 	unsigned sectors = chunk_sects - (sector & (chunk_sects-1));
+	struct r5conf *conf = mddev->private;
 
 	if (sectors < bio_sectors(raid_bio)) {
 		struct r5conf *conf = mddev->private;
@@ -5477,6 +5478,9 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
 		raid_bio = split;
 	}
 
+	if (raid_bio->bi_pool != &conf->bio_split)
+		md_account_bio(mddev, &raid_bio);
+
 	if (!raid5_read_one_chunk(mddev, raid_bio))
 		return raid_bio;
 
@@ -5756,6 +5760,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 	DEFINE_WAIT(w);
 	bool do_prepare;
 	bool do_flush = false;
+	bool do_clone = false;
 
 	if (unlikely(bi->bi_opf & REQ_PREFLUSH)) {
 		int ret = log_handle_flush_request(conf, bi);
@@ -5784,6 +5789,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 	if (rw == READ && mddev->degraded == 0 &&
 	    mddev->reshape_position == MaxSector) {
 		bi = chunk_aligned_read(mddev, bi);
+		do_clone = true;
 		if (!bi)
 			return true;
 	}
@@ -5798,6 +5804,9 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 	last_sector = bio_end_sector(bi);
 	bi->bi_next = NULL;
 
+	if (!do_clone)
+		md_account_bio(mddev, &bi);
+
 	prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
 	for (; logical_sector < last_sector; logical_sector += RAID5_STRIPE_SECTORS(conf)) {
 		int previous;