blk-rq-qos: refactor out common elements of blk-wbt

blkcg-qos is going to do essentially what wbt does, only on a cgroup
basis.  Break out the common code that will be shared between blkcg-qos
and wbt into blk-rq-qos.* so they can both utilize the same
infrastructure.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/Makefile

@@ -9,7 +9,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
 			genhd.o partition-generic.o ioprio.o \
-			badblocks.o partitions/
+			badblocks.o partitions/ blk-rq-qos.o
 
 obj-$(CONFIG_BOUNCE)		+= bounce.o
 obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_ioctl.o

block/blk-core.c

@@ -1645,7 +1645,7 @@ void blk_requeue_request(struct request_queue *q, struct request *rq)
 	blk_delete_timer(rq);
 	blk_clear_rq_complete(rq);
 	trace_block_rq_requeue(q, rq);
-	wbt_requeue(q->rq_wb, rq);
+	rq_qos_requeue(q, rq);
 
 	if (rq->rq_flags & RQF_QUEUED)
 		blk_queue_end_tag(q, rq);
@@ -1752,7 +1752,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	/* this is a bio leak */
 	WARN_ON(req->bio != NULL);
 
-	wbt_done(q->rq_wb, req);
+	rq_qos_done(q, req);
 
 	/*
 	 * Request may not have originated from ll_rw_blk. if not,
@@ -2044,7 +2044,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	}
 
 get_rq:
-	wb_acct = wbt_wait(q->rq_wb, bio, q->queue_lock);
+	wb_acct = rq_qos_throttle(q, bio, q->queue_lock);
 
 	/*
 	 * Grab a free request. This is might sleep but can not fail.
@@ -2054,7 +2054,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	req = get_request(q, bio->bi_opf, bio, 0, GFP_NOIO);
 	if (IS_ERR(req)) {
 		blk_queue_exit(q);
-		__wbt_done(q->rq_wb, wb_acct);
+		rq_qos_cleanup(q, wb_acct);
 		if (PTR_ERR(req) == -ENOMEM)
 			bio->bi_status = BLK_STS_RESOURCE;
 		else
@@ -2983,7 +2983,7 @@ void blk_start_request(struct request *req)
 		req->throtl_size = blk_rq_sectors(req);
 #endif
 		req->rq_flags |= RQF_STATS;
-		wbt_issue(req->q->rq_wb, req);
+		rq_qos_issue(req->q, req);
 	}
 
 	BUG_ON(blk_rq_is_complete(req));
@@ -3207,7 +3207,7 @@ void blk_finish_request(struct request *req, blk_status_t error)
 	blk_account_io_done(req, now);
 
 	if (req->end_io) {
-		wbt_done(req->q->rq_wb, req);
+		rq_qos_done(q, req);
 		req->end_io(req, error);
 	} else {
 		if (blk_bidi_rq(req))

block/blk-mq.c

@@ -504,7 +504,7 @@ void blk_mq_free_request(struct request *rq)
 	if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
 		laptop_io_completion(q->backing_dev_info);
 
-	wbt_done(q->rq_wb, rq);
+	rq_qos_done(q, rq);
 
 	if (blk_rq_rl(rq))
 		blk_put_rl(blk_rq_rl(rq));
@@ -527,7 +527,7 @@ inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
 	blk_account_io_done(rq, now);
 
 	if (rq->end_io) {
-		wbt_done(rq->q->rq_wb, rq);
+		rq_qos_done(rq->q, rq);
 		rq->end_io(rq, error);
 	} else {
 		if (unlikely(blk_bidi_rq(rq)))
@@ -641,7 +641,7 @@ void blk_mq_start_request(struct request *rq)
 		rq->throtl_size = blk_rq_sectors(rq);
 #endif
 		rq->rq_flags |= RQF_STATS;
-		wbt_issue(q->rq_wb, rq);
+		rq_qos_issue(q, rq);
 	}
 
 	WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE);
@@ -667,7 +667,7 @@ static void __blk_mq_requeue_request(struct request *rq)
 	blk_mq_put_driver_tag(rq);
 
 	trace_block_rq_requeue(q, rq);
-	wbt_requeue(q->rq_wb, rq);
+	rq_qos_requeue(q, rq);
 
 	if (blk_mq_request_started(rq)) {
 		WRITE_ONCE(rq->state, MQ_RQ_IDLE);
@@ -1806,13 +1806,13 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	if (blk_mq_sched_bio_merge(q, bio))
 		return BLK_QC_T_NONE;
 
-	wb_acct = wbt_wait(q->rq_wb, bio, NULL);
+	wb_acct = rq_qos_throttle(q, bio, NULL);
 
 	trace_block_getrq(q, bio, bio->bi_opf);
 
 	rq = blk_mq_get_request(q, bio, bio->bi_opf, &data);
 	if (unlikely(!rq)) {
-		__wbt_done(q->rq_wb, wb_acct);
+		rq_qos_cleanup(q, wb_acct);
 		if (bio->bi_opf & REQ_NOWAIT)
 			bio_wouldblock_error(bio);
 		return BLK_QC_T_NONE;

block/blk-rq-qos.c

+#include "blk-rq-qos.h"
+
+#include "blk-wbt.h"
+
+/*
+ * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
+ * false if 'v' + 1 would be bigger than 'below'.
+ */
+static bool atomic_inc_below(atomic_t *v, int below)
+{
+	int cur = atomic_read(v);
+
+	for (;;) {
+		int old;
+
+		if (cur >= below)
+			return false;
+		old = atomic_cmpxchg(v, cur, cur + 1);
+		if (old == cur)
+			break;
+		cur = old;
+	}
+
+	return true;
+}
+
+bool rq_wait_inc_below(struct rq_wait *rq_wait, int limit)
+{
+	return atomic_inc_below(&rq_wait->inflight, limit);
+}
+
+void rq_qos_cleanup(struct request_queue *q, enum wbt_flags wb_acct)
+{
+	struct rq_qos *rqos;
+
+	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->cleanup)
+			rqos->ops->cleanup(rqos, wb_acct);
+	}
+}
+
+void rq_qos_done(struct request_queue *q, struct request *rq)
+{
+	struct rq_qos *rqos;
+
+	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->done)
+			rqos->ops->done(rqos, rq);
+	}
+}
+
+void rq_qos_issue(struct request_queue *q, struct request *rq)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->issue)
+			rqos->ops->issue(rqos, rq);
+	}
+}
+
+void rq_qos_requeue(struct request_queue *q, struct request *rq)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->requeue)
+			rqos->ops->requeue(rqos, rq);
+	}
+}
+
+enum wbt_flags rq_qos_throttle(struct request_queue *q, struct bio *bio,
+			       spinlock_t *lock)
+{
+	struct rq_qos *rqos;
+	enum wbt_flags flags = 0;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->throttle)
+			flags |= rqos->ops->throttle(rqos, bio, lock);
+	}
+	return flags;
+}
+
+/*
+ * Return true, if we can't increase the depth further by scaling
+ */
+bool rq_depth_calc_max_depth(struct rq_depth *rqd)
+{
+	unsigned int depth;
+	bool ret = false;
+
+	/*
+	 * For QD=1 devices, this is a special case. It's important for those
+	 * to have one request ready when one completes, so force a depth of
+	 * 2 for those devices. On the backend, it'll be a depth of 1 anyway,
+	 * since the device can't have more than that in flight. If we're
+	 * scaling down, then keep a setting of 1/1/1.
+	 */
+	if (rqd->queue_depth == 1) {
+		if (rqd->scale_step > 0)
+			rqd->max_depth = 1;
+		else {
+			rqd->max_depth = 2;
+			ret = true;
+		}
+	} else {
+		/*
+		 * scale_step == 0 is our default state. If we have suffered
+		 * latency spikes, step will be > 0, and we shrink the
+		 * allowed write depths. If step is < 0, we're only doing
+		 * writes, and we allow a temporarily higher depth to
+		 * increase performance.
+		 */
+		depth = min_t(unsigned int, rqd->default_depth,
+			      rqd->queue_depth);
+		if (rqd->scale_step > 0)
+			depth = 1 + ((depth - 1) >> min(31, rqd->scale_step));
+		else if (rqd->scale_step < 0) {
+			unsigned int maxd = 3 * rqd->queue_depth / 4;
+
+			depth = 1 + ((depth - 1) << -rqd->scale_step);
+			if (depth > maxd) {
+				depth = maxd;
+				ret = true;
+			}
+		}
+
+		rqd->max_depth = depth;
+	}
+
+	return ret;
+}
+
+void rq_depth_scale_up(struct rq_depth *rqd)
+{
+	/*
+	 * Hit max in previous round, stop here
+	 */
+	if (rqd->scaled_max)
+		return;
+
+	rqd->scale_step--;
+
+	rqd->scaled_max = rq_depth_calc_max_depth(rqd);
+}
+
+/*
+ * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we
+ * had a latency violation.
+ */
+void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle)
+{
+	/*
+	 * Stop scaling down when we've hit the limit. This also prevents
+	 * ->scale_step from going to crazy values, if the device can't
+	 * keep up.
+	 */
+	if (rqd->max_depth == 1)
+		return;
+
+	if (rqd->scale_step < 0 && hard_throttle)
+		rqd->scale_step = 0;
+	else
+		rqd->scale_step++;
+
+	rqd->scaled_max = false;
+	rq_depth_calc_max_depth(rqd);
+}
+
+void rq_qos_exit(struct request_queue *q)
+{
+	while (q->rq_qos) {
+		struct rq_qos *rqos = q->rq_qos;
+		q->rq_qos = rqos->next;
+		rqos->ops->exit(rqos);
+	}
+}

block/blk-rq-qos.h

+#ifndef RQ_QOS_H
+#define RQ_QOS_H
+
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/blk_types.h>
+#include <linux/atomic.h>
+#include <linux/wait.h>
+
+enum rq_qos_id {
+	RQ_QOS_WBT,
+	RQ_QOS_CGROUP,
+};
+
+struct rq_wait {
+	wait_queue_head_t wait;
+	atomic_t inflight;
+};
+
+struct rq_qos {
+	struct rq_qos_ops *ops;
+	struct request_queue *q;
+	enum rq_qos_id id;
+	struct rq_qos *next;
+};
+
+struct rq_qos_ops {
+	enum wbt_flags (*throttle)(struct rq_qos *, struct bio *,
+				   spinlock_t *);
+	void (*issue)(struct rq_qos *, struct request *);
+	void (*requeue)(struct rq_qos *, struct request *);
+	void (*done)(struct rq_qos *, struct request *);
+	void (*cleanup)(struct rq_qos *, enum wbt_flags);
+	void (*exit)(struct rq_qos *);
+};
+
+struct rq_depth {
+	unsigned int max_depth;
+
+	int scale_step;
+	bool scaled_max;
+
+	unsigned int queue_depth;
+	unsigned int default_depth;
+};
+
+static inline struct rq_qos *rq_qos_id(struct request_queue *q,
+				       enum rq_qos_id id)
+{
+	struct rq_qos *rqos;
+	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->id == id)
+			break;
+	}
+	return rqos;
+}
+
+static inline struct rq_qos *wbt_rq_qos(struct request_queue *q)
+{
+	return rq_qos_id(q, RQ_QOS_WBT);
+}
+
+static inline struct rq_qos *blkcg_rq_qos(struct request_queue *q)
+{
+	return rq_qos_id(q, RQ_QOS_CGROUP);
+}
+
+static inline void rq_wait_init(struct rq_wait *rq_wait)
+{
+	atomic_set(&rq_wait->inflight, 0);
+	init_waitqueue_head(&rq_wait->wait);
+}
+
+static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
+{
+	rqos->next = q->rq_qos;
+	q->rq_qos = rqos;
+}
+
+static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)
+{
+	struct rq_qos *cur, *prev = NULL;
+	for (cur = q->rq_qos; cur; cur = cur->next) {
+		if (cur == rqos) {
+			if (prev)
+				prev->next = rqos->next;
+			else
+				q->rq_qos = cur;
+			break;
+		}
+		prev = cur;
+	}
+}
+
+bool rq_wait_inc_below(struct rq_wait *rq_wait, int limit);
+void rq_depth_scale_up(struct rq_depth *rqd);
+void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle);
+bool rq_depth_calc_max_depth(struct rq_depth *rqd);
+
+void rq_qos_cleanup(struct request_queue *, enum wbt_flags);
+void rq_qos_done(struct request_queue *, struct request *);
+void rq_qos_issue(struct request_queue *, struct request *);
+void rq_qos_requeue(struct request_queue *, struct request *);
+enum wbt_flags rq_qos_throttle(struct request_queue *, struct bio *, spinlock_t *);
+void rq_qos_exit(struct request_queue *);
+#endif

block/blk-settings.c

@@ -875,7 +875,7 @@ EXPORT_SYMBOL_GPL(blk_queue_flush_queueable);
 void blk_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
 	q->queue_depth = depth;
-	wbt_set_queue_depth(q->rq_wb, depth);
+	wbt_set_queue_depth(q, depth);
 }
 EXPORT_SYMBOL(blk_set_queue_depth);
 
@@ -900,7 +900,7 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
 		queue_flag_clear(QUEUE_FLAG_FUA, q);
 	spin_unlock_irq(q->queue_lock);
 
-	wbt_set_write_cache(q->rq_wb, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
+	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 }
 EXPORT_SYMBOL_GPL(blk_queue_write_cache);
 

block/blk-sysfs.c

@@ -422,16 +422,16 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page,
 
 static ssize_t queue_wb_lat_show(struct request_queue *q, char *page)
 {
-	if (!q->rq_wb)
+	if (!wbt_rq_qos(q))
 		return -EINVAL;
 
-	return sprintf(page, "%llu\n", div_u64(q->rq_wb->min_lat_nsec, 1000));
+	return sprintf(page, "%llu\n", div_u64(wbt_get_min_lat(q), 1000));
 }
 
 static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 				  size_t count)
 {
-	struct rq_wb *rwb;
+	struct rq_qos *rqos;
 	ssize_t ret;
 	s64 val;
 
@@ -441,23 +441,21 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 	if (val < -1)
 		return -EINVAL;
 
-	rwb = q->rq_wb;
-	if (!rwb) {
+	rqos = wbt_rq_qos(q);
+	if (!rqos) {
 		ret = wbt_init(q);
 		if (ret)
 			return ret;
 	}
 
-	rwb = q->rq_wb;
 	if (val == -1)
-		rwb->min_lat_nsec = wbt_default_latency_nsec(q);
+		val = wbt_default_latency_nsec(q);
 	else if (val >= 0)
-		rwb->min_lat_nsec = val * 1000ULL;
+		val *= 1000ULL;
 
-	if (rwb->enable_state == WBT_STATE_ON_DEFAULT)
-		rwb->enable_state = WBT_STATE_ON_MANUAL;
+	wbt_set_min_lat(q, val);
 
-	wbt_update_limits(rwb);
+	wbt_update_limits(q);
 	return count;
 }
 
@@ -964,7 +962,7 @@ void blk_unregister_queue(struct gendisk *disk)
 	kobject_del(&q->kobj);
 	blk_trace_remove_sysfs(disk_to_dev(disk));
 
-	wbt_exit(q);
+	rq_qos_exit(q);
 
 	mutex_lock(&q->sysfs_lock);
 	if (q->request_fn || (q->mq_ops && q->elevator))

block/blk-wbt.h

@@ -9,6 +9,7 @@
 #include <linux/ktime.h>
 
 #include "blk-stat.h"
+#include "blk-rq-qos.h"
 
 enum wbt_flags {
 	WBT_TRACKED		= 1,	/* write, tracked for throttling */
@@ -35,20 +36,12 @@ enum {
 	WBT_STATE_ON_MANUAL	= 2,
 };
 
-struct rq_wait {
-	wait_queue_head_t wait;
-	atomic_t inflight;
-};
-
 struct rq_wb {
 	/*
 	 * Settings that govern how we throttle
 	 */
 	unsigned int wb_background;		/* background writeback */
 	unsigned int wb_normal;			/* normal writeback */
-	unsigned int wb_max;			/* max throughput writeback */
-	int scale_step;
-	bool scaled_max;
 
 	short enable_state;			/* WBT_STATE_* */
 
@@ -67,15 +60,20 @@ struct rq_wb {
 	void *sync_cookie;
 
 	unsigned int wc;
-	unsigned int queue_depth;
 
 	unsigned long last_issue;		/* last non-throttled issue */
 	unsigned long last_comp;		/* last non-throttled comp */
 	unsigned long min_lat_nsec;
-	struct request_queue *queue;
+	struct rq_qos rqos;
 	struct rq_wait rq_wait[WBT_NUM_RWQ];
+	struct rq_depth rq_depth;
 };
 
+static inline struct rq_wb *RQWB(struct rq_qos *rqos)
+{
+	return container_of(rqos, struct rq_wb, rqos);
+}
+
 static inline unsigned int wbt_inflight(struct rq_wb *rwb)
 {
 	unsigned int i, ret = 0;
@@ -86,6 +84,7 @@ static inline unsigned int wbt_inflight(struct rq_wb *rwb)
 	return ret;
 }
 
+
 #ifdef CONFIG_BLK_WBT
 
 static inline void wbt_track(struct request *rq, enum wbt_flags flags)
@@ -93,19 +92,16 @@ static inline void wbt_track(struct request *rq, enum wbt_flags flags)
 	rq->wbt_flags |= flags;
 }
 
-void __wbt_done(struct rq_wb *, enum wbt_flags);
-void wbt_done(struct rq_wb *, struct request *);
-enum wbt_flags wbt_wait(struct rq_wb *, struct bio *, spinlock_t *);
 int wbt_init(struct request_queue *);
-void wbt_exit(struct request_queue *);
-void wbt_update_limits(struct rq_wb *);
-void wbt_requeue(struct rq_wb *, struct request *);
-void wbt_issue(struct rq_wb *, struct request *);
+void wbt_update_limits(struct request_queue *);
 void wbt_disable_default(struct request_queue *);
 void wbt_enable_default(struct request_queue *);
 
-void wbt_set_queue_depth(struct rq_wb *, unsigned int);
-void wbt_set_write_cache(struct rq_wb *, bool);
+u64 wbt_get_min_lat(struct request_queue *q);
+void wbt_set_min_lat(struct request_queue *q, u64 val);
+
+void wbt_set_queue_depth(struct request_queue *, unsigned int);
+void wbt_set_write_cache(struct request_queue *, bool);
 
 u64 wbt_default_latency_nsec(struct request_queue *);
 
@@ -114,43 +110,30 @@ u64 wbt_default_latency_nsec(struct request_queue *);
 static inline void wbt_track(struct request *rq, enum wbt_flags flags)
 {
 }
-static inline void __wbt_done(struct rq_wb *rwb, enum wbt_flags flags)
-{
-}
-static inline void wbt_done(struct rq_wb *rwb, struct request *rq)
-{
-}
-static inline enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio,
-				      spinlock_t *lock)
-{
-	return 0;
-}
 static inline int wbt_init(struct request_queue *q)
 {
 	return -EINVAL;
 }
-static inline void wbt_exit(struct request_queue *q)
-{
-}
-static inline void wbt_update_limits(struct rq_wb *rwb)
+static inline void wbt_update_limits(struct request_queue *q)
 {
 }
-static inline void wbt_requeue(struct rq_wb *rwb, struct request *rq)
+static inline void wbt_disable_default(struct request_queue *q)
 {
 }
-static inline void wbt_issue(struct rq_wb *rwb, struct request *rq)
+static inline void wbt_enable_default(struct request_queue *q)
 {
 }
-static inline void wbt_disable_default(struct request_queue *q)
+static inline void wbt_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
 }
-static inline void wbt_enable_default(struct request_queue *q)
+static inline void wbt_set_write_cache(struct request_queue *q, bool wc)
 {
 }
-static inline void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
+static inline u64 wbt_get_min_lat(struct request_queue *q)
 {
+	return 0;
 }
-static inline void wbt_set_write_cache(struct rq_wb *rwb, bool wc)
+static inline void wbt_set_min_lat(struct request_queue *q, u64 val)
 {
 }
 static inline u64 wbt_default_latency_nsec(struct request_queue *q)

include/linux/blkdev.h

@@ -42,7 +42,7 @@ struct bsg_job;
 struct blkcg_gq;
 struct blk_flush_queue;
 struct pr_ops;
-struct rq_wb;
+struct rq_qos;
 struct blk_queue_stats;
 struct blk_stat_callback;
 
@@ -443,7 +443,7 @@ struct request_queue {
 	int			nr_rqs_elvpriv;	/* # allocated rqs w/ elvpriv */
 
 	struct blk_queue_stats	*stats;
-	struct rq_wb		*rq_wb;
+	struct rq_qos		*rq_qos;
 
 	/*
 	 * If blkcg is not used, @q->root_rl serves all requests.  If blkcg