blk-throttle: Fix io statistics for cgroup v1

After commit f382fb0b ("block: remove legacy IO schedulers"),
blkio.throttle.io_serviced and blkio.throttle.io_service_bytes become
the only stable io stats interface of cgroup v1, and these statistics
are done in the blk-throttle code. But the current code only counts the
bios that are actually throttled. When the user does not add the throttle
limit, the io stats for cgroup v1 has nothing. I fix it according to the
statistical method of v2, and made it count all ios accurately.

Fixes: a7b36ee6 ("block: move blk-throtl fast path inline")
Tested-by: Andrea Righi <andrea.righi@canonical.com>
Signed-off-by: Jinke Han <hanjinke.666@bytedance.com>
Acked-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20230507170631.89607-1-hanjinke.666@bytedance.comSigned-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-cgroup.c

@@ -2062,6 +2062,9 @@ void blk_cgroup_bio_start(struct bio *bio)
 	struct blkg_iostat_set *bis;
 	unsigned long flags;
 
+	if (!cgroup_subsys_on_dfl(io_cgrp_subsys))
+		return;
+
 	/* Root-level stats are sourced from system-wide IO stats */
 	if (!cgroup_parent(blkcg->css.cgroup))
 		return;
@@ -2093,8 +2096,7 @@ void blk_cgroup_bio_start(struct bio *bio)
 	}
 
 	u64_stats_update_end_irqrestore(&bis->sync, flags);
-	if (cgroup_subsys_on_dfl(io_cgrp_subsys))
-		cgroup_rstat_updated(blkcg->css.cgroup, cpu);
+	cgroup_rstat_updated(blkcg->css.cgroup, cpu);
 	put_cpu();
 }
 

block/blk-throttle.c

@@ -2178,12 +2178,6 @@ bool __blk_throtl_bio(struct bio *bio)
 
 	rcu_read_lock();
 
-	if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) {
-		blkg_rwstat_add(&tg->stat_bytes, bio->bi_opf,
-				bio->bi_iter.bi_size);
-		blkg_rwstat_add(&tg->stat_ios, bio->bi_opf, 1);
-	}
-
 	spin_lock_irq(&q->queue_lock);
 
 	throtl_update_latency_buckets(td);

block/blk-throttle.h

@@ -185,6 +185,15 @@ static inline bool blk_should_throtl(struct bio *bio)
 	struct throtl_grp *tg = blkg_to_tg(bio->bi_blkg);
 	int rw = bio_data_dir(bio);
 
+	if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) {
+		if (!bio_flagged(bio, BIO_CGROUP_ACCT)) {
+			bio_set_flag(bio, BIO_CGROUP_ACCT);
+			blkg_rwstat_add(&tg->stat_bytes, bio->bi_opf,
+					bio->bi_iter.bi_size);
+		}
+		blkg_rwstat_add(&tg->stat_ios, bio->bi_opf, 1);
+	}
+
 	/* iops limit is always counted */
 	if (tg->has_rules_iops[rw])
 		return true;