blk-throttle: make blk_throtl_bio() ready for hierarchy

Currently, blk_throtl_bio() issues the passed in bio directly if it's
within limits of its associated tg (throtl_grp).  This behavior
becomes incorrect with hierarchy support as the bio should be
accounted to and throttled by the ancestor throtl_grps too.

This patch makes the direct issue path of blk_throtl_bio() to loop
until it reaches the top-level service_queue or gets throttled.  If
the former, the bio can be issued directly; otherwise, it gets queued
at the first layer it was above limits.

As tg->parent_sq is always the top-level service queue currently, this
patch in itself doesn't make any behavior differences.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Vivek Goyal <vgoyal@redhat.com>

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 8c6e133..52321a4 100644 (file)
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1239,12 +1239,16 @@ bool blk_throtl_bio(struct request_queue *q, struct bio *bio)
 
        sq = &tg->service_queue;
 
-       /* throtl is FIFO - if other bios are already queued, should queue */
-       if (sq->nr_queued[rw])
-               goto queue_bio;
+       while (true) {
+               /* throtl is FIFO - if bios are already queued, should queue */
+               if (sq->nr_queued[rw])
+                       break;
 
-       /* Bio is with-in rate limit of group */
-       if (tg_may_dispatch(tg, bio, NULL)) {
+               /* if above limits, break to queue */
+               if (!tg_may_dispatch(tg, bio, NULL))
+                       break;
+
+               /* within limits, let's charge and dispatch directly */
                throtl_charge_bio(tg, bio);
 
                /*
@@ -1259,10 +1263,19 @@ bool blk_throtl_bio(struct request_queue *q, struct bio *bio)
                 * So keep on trimming slice even if bio is not queued.
                 */
                throtl_trim_slice(tg, rw);
-               goto out_unlock;
+
+               /*
+                * @bio passed through this layer without being throttled.
+                * Climb up the ladder.  If we''re already at the top, it
+                * can be executed directly.
+                */
+               sq = sq->parent_sq;
+               tg = sq_to_tg(sq);
+               if (!tg)
+                       goto out_unlock;
        }
 
-queue_bio:
+       /* out-of-limit, queue to @tg */
        throtl_log(sq, "[%c] bio. bdisp=%llu sz=%u bps=%llu iodisp=%u iops=%u queued=%d/%d",
                   rw == READ ? 'R' : 'W',
                   tg->bytes_disp[rw], bio->bi_size, tg->bps[rw],