1 files changed, 40 insertions, 52 deletions

diff --git a/block/blk-throttle.h b/block/blk-throttle.h
index bffbc9cfc8ab..3b27755bfbff 100644
--- a/block/blk-throttle.h
+++ b/block/blk-throttle.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef BLK_THROTTLE_H
 #define BLK_THROTTLE_H
 
@@ -28,7 +29,8 @@
  */
 struct throtl_qnode {
 	struct list_head	node;		/* service_queue->queued[] */
-	struct bio_list		bios;		/* queued bios */
+	struct bio_list		bios_bps;	/* queued bios for bps limit */
+	struct bio_list		bios_iops;	/* queued bios for iops limit */
 	struct throtl_grp	*tg;		/* tg this qnode belongs to */
 };
 
@@ -40,7 +42,8 @@ struct throtl_service_queue {
 	 * children throtl_grp's.
 	 */
 	struct list_head	queued[2];	/* throtl_qnode [READ/WRITE] */
-	unsigned int		nr_queued[2];	/* number of queued bios */
+	unsigned int		nr_queued_bps[2];	/* number of queued bps bios */
+	unsigned int		nr_queued_iops[2];	/* number of queued iops bios */
 
 	/*
 	 * RB tree of active children throtl_grp's, which are sorted by
@@ -53,15 +56,14 @@ struct throtl_service_queue {
 };
 
 enum tg_state_flags {
-	THROTL_TG_PENDING	= 1 << 0,	/* on parent's pending tree */
-	THROTL_TG_WAS_EMPTY	= 1 << 1,	/* bio_lists[] became non-empty */
-	THROTL_TG_CANCELING	= 1 << 2,	/* starts to cancel bio */
-};
-
-enum {
-	LIMIT_LOW,
-	LIMIT_MAX,
-	LIMIT_CNT,
+	THROTL_TG_PENDING		= 1 << 0,	/* on parent's pending tree */
+	THROTL_TG_WAS_EMPTY		= 1 << 1,	/* bio_lists[] became non-empty */
+	/*
+	 * The sq's iops queue is empty, and a bio is about to be enqueued
+	 * to the first qnode's bios_iops list.
+	 */
+	THROTL_TG_IOPS_WAS_EMPTY	= 1 << 2,
+	THROTL_TG_CANCELING		= 1 << 3,	/* starts to cancel bio */
 };
 
 struct throtl_grp {
@@ -101,53 +103,29 @@ struct throtl_grp {
 	bool has_rules_bps[2];
 	bool has_rules_iops[2];
 
-	/* internally used bytes per second rate limits */
-	uint64_t bps[2][LIMIT_CNT];
-	/* user configured bps limits */
-	uint64_t bps_conf[2][LIMIT_CNT];
+	/* bytes per second rate limits */
+	uint64_t bps[2];
 
-	/* internally used IOPS limits */
-	unsigned int iops[2][LIMIT_CNT];
-	/* user configured IOPS limits */
-	unsigned int iops_conf[2][LIMIT_CNT];
-
-	/* Number of bytes dispatched in current slice */
-	uint64_t bytes_disp[2];
-	/* Number of bio's dispatched in current slice */
-	unsigned int io_disp[2];
-
-	unsigned long last_low_overflow_time[2];
-
-	uint64_t last_bytes_disp[2];
-	unsigned int last_io_disp[2];
+	/* IOPS limits */
+	unsigned int iops[2];
 
 	/*
-	 * The following two fields are updated when new configuration is
-	 * submitted while some bios are still throttled, they record how many
-	 * bytes/ios are waited already in previous configuration, and they will
-	 * be used to calculate wait time under new configuration.
+	 * Number of bytes/bio's dispatched in current slice.
+	 * When new configuration is submitted while some bios are still throttled,
+	 * first calculate the carryover: the amount of bytes/IOs already waited
+	 * under the previous configuration. Then, [bytes/io]_disp are represented
+	 * as the negative of the carryover, and they will be used to calculate the
+	 * wait time under the new configuration.
 	 */
-	long long carryover_bytes[2];
-	int carryover_ios[2];
+	int64_t bytes_disp[2];
+	int io_disp[2];
 
 	unsigned long last_check_time;
 
-	unsigned long latency_target; /* us */
-	unsigned long latency_target_conf; /* us */
 	/* When did we start a new slice */
 	unsigned long slice_start[2];
 	unsigned long slice_end[2];
 
-	unsigned long last_finish_time; /* ns / 1024 */
-	unsigned long checked_last_finish_time; /* ns / 1024 */
-	unsigned long avg_idletime; /* ns / 1024 */
-	unsigned long idletime_threshold; /* us */
-	unsigned long idletime_threshold_conf; /* us */
-
-	unsigned int bio_cnt; /* total bios */
-	unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
-	unsigned long bio_cnt_reset_time;
-
 	struct blkg_rwstat stat_bytes;
 	struct blkg_rwstat stat_ios;
 };
@@ -168,23 +146,33 @@ static inline struct throtl_grp *blkg_to_tg(struct blkcg_gq *blkg)
  * Internal throttling interface
  */
 #ifndef CONFIG_BLK_DEV_THROTTLING
-static inline int blk_throtl_init(struct gendisk *disk) { return 0; }
 static inline void blk_throtl_exit(struct gendisk *disk) { }
-static inline void blk_throtl_register(struct gendisk *disk) { }
 static inline bool blk_throtl_bio(struct bio *bio) { return false; }
 static inline void blk_throtl_cancel_bios(struct gendisk *disk) { }
 #else /* CONFIG_BLK_DEV_THROTTLING */
-int blk_throtl_init(struct gendisk *disk);
 void blk_throtl_exit(struct gendisk *disk);
-void blk_throtl_register(struct gendisk *disk);
 bool __blk_throtl_bio(struct bio *bio);
 void blk_throtl_cancel_bios(struct gendisk *disk);
 
+static inline bool blk_throtl_activated(struct request_queue *q)
+{
+	return q->td != NULL;
+}
+
 static inline bool blk_should_throtl(struct bio *bio)
 {
-	struct throtl_grp *tg = blkg_to_tg(bio->bi_blkg);
+	struct throtl_grp *tg;
 	int rw = bio_data_dir(bio);
 
+	/*
+	 * This is called under bio_queue_enter(), and it's synchronized with
+	 * the activation of blk-throtl, which is protected by
+	 * blk_mq_freeze_queue().
+	 */
+	if (!blk_throtl_activated(bio->bi_bdev->bd_queue))
+		return false;
+
+	tg = blkg_to_tg(bio->bi_blkg);
 	if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) {
 		if (!bio_flagged(bio, BIO_CGROUP_ACCT)) {
 			bio_set_flag(bio, BIO_CGROUP_ACCT);