[PATCH v3 01/11] block-throttle: prepare support multiple limits

[Shaohua Li <shli@fb.com>]

We are going to support high/max limit, each cgroup will have 2 limits
after that. This patch prepares for the multiple limits change.

Signed-off-by: Shaohua Li <shli@fb.com>
---
 block/blk-throttle.c | 109 ++++++++++++++++++++++++++++++++-------------------
 1 file changed, 68 insertions(+), 41 deletions(-)

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index a3ea826..964b713 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -83,6 +83,11 @@ enum tg_state_flags {
 
 #define rb_entry_tg(node)	rb_entry((node), struct throtl_grp, rb_node)
 
+enum {
+	LIMIT_MAX = 0,
+	LIMIT_CNT = 1,
+};
+
 struct throtl_grp {
 	/* must be the first member */
 	struct blkg_policy_data pd;
@@ -120,10 +125,10 @@ struct throtl_grp {
 	bool has_rules[2];
 
 	/* bytes per second rate limits */
-	uint64_t bps[2];
+	uint64_t bps[2][LIMIT_CNT];
 
 	/* IOPS limits */
-	unsigned int iops[2];
+	unsigned int iops[2][LIMIT_CNT];
 
 	/* Number of bytes disptached in current slice */
 	uint64_t bytes_disp[2];
@@ -147,6 +152,8 @@ struct throtl_data
 
 	/* Work for dispatching throttled bios */
 	struct work_struct dispatch_work;
+	unsigned int limit_index;
+	bool limit_valid[LIMIT_CNT];
 };
 
 static void throtl_pending_timer_fn(unsigned long arg);
@@ -198,6 +205,16 @@ static struct throtl_data *sq_to_td(struct throtl_service_queue *sq)
 		return container_of(sq, struct throtl_data, service_queue);
 }
 
+static uint64_t tg_bps_limit(struct throtl_grp *tg, int rw)
+{
+	return tg->bps[rw][tg->td->limit_index];
+}
+
+static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw)
+{
+	return tg->iops[rw][tg->td->limit_index];
+}
+
 /**
  * throtl_log - log debug message via blktrace
  * @sq: the service_queue being reported
@@ -320,7 +337,7 @@ static void throtl_service_queue_init(struct throtl_service_queue *sq)
 static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, int node)
 {
 	struct throtl_grp *tg;
-	int rw;
+	int rw, index;
 
 	tg = kzalloc_node(sizeof(*tg), gfp, node);
 	if (!tg)
@@ -334,10 +351,12 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, int node)
 	}
 
 	RB_CLEAR_NODE(&tg->rb_node);
-	tg->bps[READ] = -1;
-	tg->bps[WRITE] = -1;
-	tg->iops[READ] = -1;
-	tg->iops[WRITE] = -1;
+	for (rw = READ; rw <= WRITE; rw++) {
+		for (index = LIMIT_MAX; index < LIMIT_CNT; index++) {
+			tg->bps[rw][index] = -1;
+			tg->iops[rw][index] = -1;
+		}
+	}
 
 	return &tg->pd;
 }
@@ -376,11 +395,14 @@ static void throtl_pd_init(struct blkg_policy_data *pd)
 static void tg_update_has_rules(struct throtl_grp *tg)
 {
 	struct throtl_grp *parent_tg = sq_to_tg(tg->service_queue.parent_sq);
+	struct throtl_data *td = tg->td;
 	int rw;
 
 	for (rw = READ; rw <= WRITE; rw++)
 		tg->has_rules[rw] = (parent_tg && parent_tg->has_rules[rw]) ||
-				    (tg->bps[rw] != -1 || tg->iops[rw] != -1);
+			(td->limit_valid[td->limit_index] &&
+			 (tg_bps_limit(tg, rw) != -1 ||
+			  tg_iops_limit(tg, rw) != -1));
 }
 
 static void throtl_pd_online(struct blkg_policy_data *pd)
@@ -632,11 +654,11 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
 
 	if (!nr_slices)
 		return;
-	tmp = tg->bps[rw] * throtl_slice * nr_slices;
+	tmp = tg_bps_limit(tg, rw) * throtl_slice * nr_slices;
 	do_div(tmp, HZ);
 	bytes_trim = tmp;
 
-	io_trim = (tg->iops[rw] * throtl_slice * nr_slices)/HZ;
+	io_trim = (tg_iops_limit(tg, rw) * throtl_slice * nr_slices)/HZ;
 
 	if (!bytes_trim && !io_trim)
 		return;
@@ -682,7 +704,7 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 	 * have been trimmed.
 	 */
 
-	tmp = (u64)tg->iops[rw] * jiffy_elapsed_rnd;
+	tmp = (u64)tg_iops_limit(tg, rw) * jiffy_elapsed_rnd;
 	do_div(tmp, HZ);
 
 	if (tmp > UINT_MAX)
@@ -697,7 +719,7 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 	}
 
 	/* Calc approx time to dispatch */
-	jiffy_wait = ((tg->io_disp[rw] + 1) * HZ)/tg->iops[rw] + 1;
+	jiffy_wait = ((tg->io_disp[rw] + 1) * HZ)/tg_iops_limit(tg, rw) + 1;
 
 	if (jiffy_wait > jiffy_elapsed)
 		jiffy_wait = jiffy_wait - jiffy_elapsed;
@@ -724,7 +746,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
 
 	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, throtl_slice);
 
-	tmp = tg->bps[rw] * jiffy_elapsed_rnd;
+	tmp = tg_bps_limit(tg, rw) * jiffy_elapsed_rnd;
 	do_div(tmp, HZ);
 	bytes_allowed = tmp;
 
@@ -736,7 +758,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
 
 	/* Calc approx time to dispatch */
 	extra_bytes = tg->bytes_disp[rw] + bio->bi_iter.bi_size - bytes_allowed;
-	jiffy_wait = div64_u64(extra_bytes * HZ, tg->bps[rw]);
+	jiffy_wait = div64_u64(extra_bytes * HZ, tg_bps_limit(tg, rw));
 
 	if (!jiffy_wait)
 		jiffy_wait = 1;
@@ -771,7 +793,7 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
 	       bio != throtl_peek_queued(&tg->service_queue.queued[rw]));
 
 	/* If tg->bps = -1, then BW is unlimited */
-	if (tg->bps[rw] == -1 && tg->iops[rw] == -1) {
+	if (tg_bps_limit(tg, rw) == -1 && tg_iops_limit(tg, rw) == -1) {
 		if (wait)
 			*wait = 0;
 		return true;
@@ -1148,8 +1170,8 @@ static void tg_conf_updated(struct throtl_grp *tg)
 
 	throtl_log(&tg->service_queue,
 		   "limit change rbps=%llu wbps=%llu riops=%u wiops=%u",
-		   tg->bps[READ], tg->bps[WRITE],
-		   tg->iops[READ], tg->iops[WRITE]);
+		   tg_bps_limit(tg, READ), tg_bps_limit(tg, WRITE),
+		   tg_iops_limit(tg, READ), tg_iops_limit(tg, WRITE));
 
 	/*
 	 * Update has_rules[] flags for the updated tg's subtree.  A tg is
@@ -1226,25 +1248,25 @@ static ssize_t tg_set_conf_uint(struct kernfs_open_file *of,
 static struct cftype throtl_legacy_files[] = {
 	{
 		.name = "throttle.read_bps_device",
-		.private = offsetof(struct throtl_grp, bps[READ]),
+		.private = offsetof(struct throtl_grp, bps[READ][LIMIT_MAX]),
 		.seq_show = tg_print_conf_u64,
 		.write = tg_set_conf_u64,
 	},
 	{
 		.name = "throttle.write_bps_device",
-		.private = offsetof(struct throtl_grp, bps[WRITE]),
+		.private = offsetof(struct throtl_grp, bps[WRITE][LIMIT_MAX]),
 		.seq_show = tg_print_conf_u64,
 		.write = tg_set_conf_u64,
 	},
 	{
 		.name = "throttle.read_iops_device",
-		.private = offsetof(struct throtl_grp, iops[READ]),
+		.private = offsetof(struct throtl_grp, iops[READ][LIMIT_MAX]),
 		.seq_show = tg_print_conf_uint,
 		.write = tg_set_conf_uint,
 	},
 	{
 		.name = "throttle.write_iops_device",
-		.private = offsetof(struct throtl_grp, iops[WRITE]),
+		.private = offsetof(struct throtl_grp, iops[WRITE][LIMIT_MAX]),
 		.seq_show = tg_print_conf_uint,
 		.write = tg_set_conf_uint,
 	},
@@ -1270,18 +1292,22 @@ static u64 tg_prfill_max(struct seq_file *sf, struct blkg_policy_data *pd,
 
 	if (!dname)
 		return 0;
-	if (tg->bps[READ] == -1 && tg->bps[WRITE] == -1 &&
-	    tg->iops[READ] == -1 && tg->iops[WRITE] == -1)
+	if (tg->bps[READ][LIMIT_MAX] == -1 && tg->bps[WRITE][LIMIT_MAX] == -1 &&
+	    tg->iops[READ][LIMIT_MAX] == -1 && tg->iops[WRITE][LIMIT_MAX] == -1)
 		return 0;
 
-	if (tg->bps[READ] != -1)
-		snprintf(bufs[0], sizeof(bufs[0]), "%llu", tg->bps[READ]);
-	if (tg->bps[WRITE] != -1)
-		snprintf(bufs[1], sizeof(bufs[1]), "%llu", tg->bps[WRITE]);
-	if (tg->iops[READ] != -1)
-		snprintf(bufs[2], sizeof(bufs[2]), "%u", tg->iops[READ]);
-	if (tg->iops[WRITE] != -1)
-		snprintf(bufs[3], sizeof(bufs[3]), "%u", tg->iops[WRITE]);
+	if (tg->bps[READ][LIMIT_MAX] != -1)
+		snprintf(bufs[0], sizeof(bufs[0]), "%llu",
+			tg->bps[READ][LIMIT_MAX]);
+	if (tg->bps[WRITE][LIMIT_MAX] != -1)
+		snprintf(bufs[1], sizeof(bufs[1]), "%llu",
+			tg->bps[WRITE][LIMIT_MAX]);
+	if (tg->iops[READ][LIMIT_MAX] != -1)
+		snprintf(bufs[2], sizeof(bufs[2]), "%u",
+			tg->iops[READ][LIMIT_MAX]);
+	if (tg->iops[WRITE][LIMIT_MAX] != -1)
+		snprintf(bufs[3], sizeof(bufs[3]), "%u",
+			tg->iops[WRITE][LIMIT_MAX]);
 
 	seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s\n",
 		   dname, bufs[0], bufs[1], bufs[2], bufs[3]);
@@ -1310,10 +1336,10 @@ static ssize_t tg_set_max(struct kernfs_open_file *of,
 
 	tg = blkg_to_tg(ctx.blkg);
 
-	v[0] = tg->bps[READ];
-	v[1] = tg->bps[WRITE];
-	v[2] = tg->iops[READ];
-	v[3] = tg->iops[WRITE];
+	v[0] = tg->bps[READ][LIMIT_MAX];
+	v[1] = tg->bps[WRITE][LIMIT_MAX];
+	v[2] = tg->iops[READ][LIMIT_MAX];
+	v[3] = tg->iops[WRITE][LIMIT_MAX];
 
 	while (true) {
 		char tok[27];	/* wiops=18446744073709551616 */
@@ -1350,10 +1376,10 @@ static ssize_t tg_set_max(struct kernfs_open_file *of,
 			goto out_finish;
 	}
 
-	tg->bps[READ] = v[0];
-	tg->bps[WRITE] = v[1];
-	tg->iops[READ] = v[2];
-	tg->iops[WRITE] = v[3];
+	tg->bps[READ][LIMIT_MAX] = v[0];
+	tg->bps[WRITE][LIMIT_MAX] = v[1];
+	tg->iops[READ][LIMIT_MAX] = v[2];
+	tg->iops[WRITE][LIMIT_MAX] = v[3];
 
 	tg_conf_updated(tg);
 	ret = 0;
@@ -1451,8 +1477,8 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 	/* 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_iter.bi_size, tg->bps[rw],
-		   tg->io_disp[rw], tg->iops[rw],
+		   tg->bytes_disp[rw], bio->bi_iter.bi_size, tg_bps_limit(tg, rw),
+		   tg->io_disp[rw], tg_iops_limit(tg, rw),
 		   sq->nr_queued[READ], sq->nr_queued[WRITE]);
 
 	bio_associate_current(bio);
@@ -1563,6 +1589,7 @@ int blk_throtl_init(struct request_queue *q)
 	q->td = td;
 	td->queue = q;
 
+	td->limit_valid[LIMIT_MAX] = true;
 	/* activate policy */
 	ret = blkcg_activate_policy(q, &blkcg_policy_throtl);
 	if (ret)
-- 
2.9.3